diff --git a/.ci/azure/android_arm64.yml b/.ci/azure/android_arm64.yml
index bdd6bc9eb..3d6d09ea4 100644
--- a/.ci/azure/android_arm64.yml
+++ b/.ci/azure/android_arm64.yml
@@ -6,7 +6,7 @@ trigger:
   paths:
     exclude:
     - modules/optimum
-    - modules/cuda_plugin
+    - modules/nvidia_plugin
 
 pr:
   branches:
@@ -16,7 +16,7 @@ pr:
   paths:
     exclude:
     - modules/optimum
-    - modules/cuda_plugin
+    - modules/nvidia_plugin
 
 resources:
   repositories:
@@ -120,7 +120,7 @@ jobs:
         -DENABLE_SAMPLES=ON
         -DENABLE_INTEL_MYRIAD=OFF
         -DBUILD_java_api=ON
-        -DBUILD_cuda_plugin=OFF
+        -DBUILD_nvidia_plugin=OFF
         -DTHREADING=SEQ
         -DIE_EXTRA_MODULES=$(REPO_DIR)/modules
         $(OPENVINO_REPO_DIR)
diff --git a/.ci/azure/linux.yml b/.ci/azure/linux.yml
index 244e9952d..4dbd67796 100644
--- a/.ci/azure/linux.yml
+++ b/.ci/azure/linux.yml
@@ -6,7 +6,7 @@ trigger:
   paths:
     exclude:
     - modules/optimum
-    - modules/cuda_plugin
+    - modules/nvidia_plugin
 
 pr:
   branches:
@@ -16,7 +16,7 @@ pr:
   paths:
     exclude:
     - modules/optimum
-    - modules/cuda_plugin
+    - modules/nvidia_plugin
 
 resources:
   repositories:
@@ -122,7 +122,7 @@ jobs:
         -DVERBOSE_BUILD=ON
         -DCMAKE_BUILD_TYPE=$(BUILD_TYPE)
         -DNGRAPH_ONNX_IMPORT_ENABLE=OFF
-        -DBUILD_cuda_plugin=OFF
+        -DBUILD_nvidia_plugin=OFF
         -DIE_EXTRA_MODULES=$(REPO_DIR)/modules
         -DENABLE_PYTHON=ON
         -DPYTHON_EXECUTABLE=/usr/bin/python3.8
diff --git a/.ci/azure/linux_arm64.yml b/.ci/azure/linux_arm64.yml
index 63c677c4b..2207872f1 100644
--- a/.ci/azure/linux_arm64.yml
+++ b/.ci/azure/linux_arm64.yml
@@ -6,7 +6,7 @@ trigger:
   paths:
     exclude:
     - modules/optimum
-    - modules/cuda_plugin
+    - modules/nvidia_plugin
 
 pr:
   branches:
@@ -16,7 +16,7 @@ pr:
   paths:
     exclude:
     - modules/optimum
-    - modules/cuda_plugin
+    - modules/nvidia_plugin
 
 resources:
   repositories:
@@ -153,7 +153,7 @@ jobs:
         -DCMAKE_BUILD_TYPE=$(BUILD_TYPE)
         -DENABLE_SAMPLES=ON
         -DBUILD_java_api=OFF
-        -DBUILD_cuda_plugin=OFF
+        -DBUILD_nvidia_plugin=OFF
         -DENABLE_INTEL_MYRIAD=OFF
         -DTHREADING=SEQ
         -DIE_EXTRA_MODULES=$(OPENVINO_CONTRIB_REPO_DIR)/modules
diff --git a/.ci/azure/linux_coverity_arm64.yml b/.ci/azure/linux_coverity_arm64.yml
index 41e14c1ca..891227a9a 100644
--- a/.ci/azure/linux_coverity_arm64.yml
+++ b/.ci/azure/linux_coverity_arm64.yml
@@ -6,7 +6,7 @@ trigger:
   paths:
     exclude:
     - modules/optimum
-    - modules/cuda_plugin
+    - modules/nvidia_plugin
 
 pr:
   branches:
@@ -16,7 +16,7 @@ pr:
   paths:
     exclude:
     - modules/optimum
-    - modules/cuda_plugin
+    - modules/nvidia_plugin
 
 resources:
   repositories:
diff --git a/.ci/azure/linux_cuda.yml b/.ci/azure/linux_cuda.yml
index ca276258c..65abd602f 100644
--- a/.ci/azure/linux_cuda.yml
+++ b/.ci/azure/linux_cuda.yml
@@ -5,7 +5,7 @@ trigger:
     - releases/*
   paths:
     include:
-    - modules/cuda_plugin
+    - modules/nvidia_plugin
 
 pr:
   branches:
@@ -14,7 +14,7 @@ pr:
     - releases/*
   paths:
     include:
-    - modules/cuda_plugin
+    - modules/nvidia_plugin
 
 resources:
   repositories:
diff --git a/.ci/azure/mac.yml b/.ci/azure/mac.yml
index 2ec1645ff..131c8f831 100644
--- a/.ci/azure/mac.yml
+++ b/.ci/azure/mac.yml
@@ -6,7 +6,7 @@ trigger:
   paths:
     exclude:
     - modules/optimum
-    - modules/cuda_plugin
+    - modules/nvidia_plugin
 
 pr:
   branches:
@@ -16,7 +16,7 @@ pr:
   paths:
     exclude:
     - modules/optimum
-    - modules/cuda_plugin
+    - modules/nvidia_plugin
 
 resources:
   repositories:
@@ -104,7 +104,7 @@ jobs:
       # Disable errors with Ninja
       export CXXFLAGS="-Wno-error=unused-command-line-argument"
       export CFLAGS="-Wno-error=unused-command-line-argument"
-      cmake -GNinja -DVERBOSE_BUILD=ON -DNGRAPH_ONNX_IMPORT_ENABLE=OFF -DCMAKE_BUILD_TYPE=$(BUILD_TYPE) -DBUILD_cuda_plugin=OFF -DIE_EXTRA_MODULES=$(REPO_DIR)/modules $(OPENVINO_REPO_DIR)
+      cmake -GNinja -DVERBOSE_BUILD=ON -DNGRAPH_ONNX_IMPORT_ENABLE=OFF -DCMAKE_BUILD_TYPE=$(BUILD_TYPE) -DBUILD_nvidia_plugin=OFF -DIE_EXTRA_MODULES=$(REPO_DIR)/modules $(OPENVINO_REPO_DIR)
     workingDirectory: $(BUILD_DIR)
     displayName: 'CMake'
 
diff --git a/.ci/azure/windows.yml b/.ci/azure/windows.yml
index 1e292f857..1d99742b4 100644
--- a/.ci/azure/windows.yml
+++ b/.ci/azure/windows.yml
@@ -6,7 +6,7 @@ trigger:
   paths:
     exclude:
     - modules/optimum
-    - modules/cuda_plugin
+    - modules/nvidia_plugin
 
 pr:
   branches:
@@ -16,7 +16,7 @@ pr:
   paths:
     exclude:
     - modules/optimum
-    - modules/cuda_plugin
+    - modules/nvidia_plugin
 
 resources:
   repositories:
@@ -103,7 +103,7 @@ jobs:
 
   - script: |
       set PATH=$(WORK_DIR)\ninja-win;%PATH%
-      call "$(MSVS_VARS_PATH)" && cmake -GNinja -DNGRAPH_ONNX_IMPORT_ENABLE=OFF -DCMAKE_BUILD_TYPE=$(BUILD_TYPE) -DBUILD_cuda_plugin=OFF -DIE_EXTRA_MODULES=$(REPO_DIR)/modules -DCMAKE_C_COMPILER:PATH="$(MSVC_COMPILER_PATH)" -DCMAKE_CXX_COMPILER:PATH="$(MSVC_COMPILER_PATH)" $(OPENVINO_REPO_DIR)
+      call "$(MSVS_VARS_PATH)" && cmake -GNinja -DNGRAPH_ONNX_IMPORT_ENABLE=OFF -DCMAKE_BUILD_TYPE=$(BUILD_TYPE) -DBUILD_nvidia_plugin=OFF -DIE_EXTRA_MODULES=$(REPO_DIR)/modules -DCMAKE_C_COMPILER:PATH="$(MSVC_COMPILER_PATH)" -DCMAKE_CXX_COMPILER:PATH="$(MSVC_COMPILER_PATH)" $(OPENVINO_REPO_DIR)
     workingDirectory: $(BUILD_DIR)
     displayName: 'CMake'
 
diff --git a/.github/workflows/code_style.yml b/.github/workflows/code_style.yml
index ca8ace150..1b5556301 100644
--- a/.github/workflows/code_style.yml
+++ b/.github/workflows/code_style.yml
@@ -3,11 +3,11 @@ on:
   push:
     paths:
       - '**'
-      - '!modules/cuda_plugin/**'
+      - '!modules/nvidia_plugin/**'
   pull_request:
     paths:
       - '**'
-      - '!modules/cuda_plugin/**'
+      - '!modules/nvidia_plugin/**'
 
 jobs:
   Java:
diff --git a/.github/workflows/history_cuda.yml b/.github/workflows/history_cuda.yml
index c65cc18be..8e5a5d07d 100644
--- a/.github/workflows/history_cuda.yml
+++ b/.github/workflows/history_cuda.yml
@@ -2,16 +2,18 @@ name: History CUDA
 on:
   push:
     paths:
-      - 'modules/cuda_plugin/**.*'
+      - 'modules/nvidia_plugin/**.*'
   pull_request:
     paths:
-      - 'modules/cuda_plugin/**.*'
+      - 'modules/nvidia_plugin/**.*'
 jobs:
   history:
     runs-on: lohika-ci
     steps:
     - name: checkout master branch
       run: git -C ~/runner/openvino_contrib checkout master
+    - name: fetch master branch
+      run: git -C ~/runner/openvino_contrib pull origin master
     - name: delete temporary branch
       run: git -C ~/runner/openvino_contrib branch -D temporary-ci-branch | echo 1
     - name: fetch
diff --git a/.github/workflows/sanitizer_cuda.yml b/.github/workflows/sanitizer_cuda.yml
index 9ea7393d5..1c2d0b400 100644
--- a/.github/workflows/sanitizer_cuda.yml
+++ b/.github/workflows/sanitizer_cuda.yml
@@ -4,7 +4,10 @@ on:
     branches:
       - master
     paths:
-      - 'modules/cuda_plugin/**.*'
+      - 'modules/nvidia_plugin/**.*'
+  pull_request:
+    paths:
+      - 'modules/nvidia_plugin/**.*'
   workflow_dispatch:
 
 jobs:
@@ -18,6 +21,8 @@ jobs:
       run: git -C ~/runner/openvino submodule update --init --recursive
     - name: checkout openvino_contrib master branch
       run: git -C ~/runner/openvino_contrib checkout master
+    - name: fetch openvino_contrib master branch
+      run: git -C ~/runner/openvino_contrib pull origin master
     - name: delete openvino_contrib temporary branch
       run: git -C ~/runner/openvino_contrib branch -D temporary-ci-branch | echo 1
     - name: fetch openvino_contrib
@@ -29,4 +34,4 @@ jobs:
     - name: ninja
       run: echo 'all:; +NINJA_STATUS="[%u/%r/%f] " ninja -C ~/runner/build_cuda_sanitizer -v CudaFuncTests CudaUnitTests' | make -j`nproc` -f-
     - name: functional tests
-      run: env -C ~/runner PATH=/usr/local/cuda-11.2/bin:/usr/local/cuda-11.4/bin:/usr/local/cuda-11.7/bin:$PATH ./openvino_contrib/modules/cuda_plugin/utils/cuda-sanitizer.sh ./build_cuda_sanitizer/bin/intel64/CudaFuncTests --gtest_filter=*smoke*:-*dynamic*:*Dynamic*:smoke_GRU*:smoke_LSTM*:smoke_TensorIterator*:*ConvBiasFusion*:*smoke*OVExecGraphImportExportTest.importExportedIENetwork*:*smoke*OVClassBasicTestP.registerNewPluginNoThrows*:*smoke*OVHoldersTest.Orders*:*smoke*IEClassBasicTestP.registerNewPluginNoThrows*:*smoke*IEClassBasicTestP.smoke_registerPluginsXMLUnicodePath*
+      run: env -C ~/runner PATH=/usr/local/cuda-11.2/bin:/usr/local/cuda-11.4/bin:/usr/local/cuda-11.7/bin:$PATH ./openvino_contrib/modules/nvidia_plugin/utils/cuda-sanitizer.sh ./build_cuda_sanitizer/bin/intel64/CudaFuncTests --gtest_filter=*smoke*:-*dynamic*:*Dynamic*:smoke_GRU*:smoke_LSTM*:smoke_TensorIterator*:*ConvBiasFusion*:*smoke*OVExecGraphImportExportTest.importExportedIENetwork*:*smoke*OVClassBasicTestP.registerNewPluginNoThrows*:*smoke*OVHoldersTest.Orders*:*smoke*IEClassBasicTestP.registerNewPluginNoThrows*:*smoke*IEClassBasicTestP.smoke_registerPluginsXMLUnicodePath*
diff --git a/.github/workflows/test_cuda.yml b/.github/workflows/test_cuda.yml
index 30f246487..01eb4a21a 100644
--- a/.github/workflows/test_cuda.yml
+++ b/.github/workflows/test_cuda.yml
@@ -2,10 +2,10 @@ name: Test CUDA
 on:
   push:
     paths:
-      - 'modules/cuda_plugin/**.*'
+      - 'modules/nvidia_plugin/**.*'
   pull_request:
     paths:
-      - 'modules/cuda_plugin/**.*'
+      - 'modules/nvidia_plugin/**.*'
 jobs:
   build:
     runs-on: lohika-ci
@@ -16,6 +16,8 @@ jobs:
       run: git -C ~/runner/openvino submodule update --init --recursive
     - name: checkout openvino_contrib master branch
       run: git -C ~/runner/openvino_contrib checkout master
+    - name: fetch openvino_contrib master branch
+      run: git -C ~/runner/openvino_contrib pull origin master
     - name: delete openvino_contrib temporary branch
       run: git -C ~/runner/openvino_contrib branch -D temporary-ci-branch | echo 1
     - name: fetch openvino_contrib
@@ -23,7 +25,7 @@ jobs:
     - name: checkout openvino_contrib
       run: git -C ~/runner/openvino_contrib checkout temporary-ci-branch
     - name: format openvino_contrib
-      run: cd ~/runner/openvino_contrib && ./modules/cuda_plugin/utils/check.sh
+      run: cd ~/runner/openvino_contrib && ./modules/nvidia_plugin/utils/check.sh
     - name: cmake
       run: env -C ~/runner ./configrelease.sh
     - name: ninja
diff --git a/README.md b/README.md
index ac7b5206f..a48d8f37b 100644
--- a/README.md
+++ b/README.md
@@ -9,7 +9,7 @@ So, all the new modules should be developed separately, and published in the `op
 This list gives an overview of all modules available inside the contrib repository.
 
 * [**arm_plugin**](./modules/arm_plugin): ARM CPU Plugin -- allows to perform deep neural networks inference on ARM CPUs, using OpenVINO API.
-* [**cuda_plugin**](./modules/cuda_plugin): CUDA GPU Plugin -- allows to perform deep neural networks inference on NVIDIA GPUs using CUDA, using OpenVINO API.
+* [**nvidia_plugin**](./modules/nvidia_plugin): NVIDIA GPU Plugin -- allows to perform deep neural networks inference on NVIDIA GPUs using CUDA, using OpenVINO API.
 * [**java_api**](./modules/java_api): Inference Engine Java API -- provides Java wrappers for Inference Engine public API.
 * [**mo_pytorch**](./modules/mo_pytorch): PyTorch extensions for Model Optimizer -- native PyTorch to OpenVINO IR converter
 * [**optimum**](./modules/optimum): Optimum OpenVINO -- Python extension for Hugging Face [Transformers](https://github.com/huggingface/transformers) including runtime and NNCF quantization.
@@ -35,7 +35,7 @@ $ cmake -DIE_EXTRA_MODULES=<openvino_contrib>/modules -DBUILD_java_api=OFF <open
 Additional build instructions are available for the following modules:
 
 * [**arm_plugin**](./modules/arm_plugin/README.md)
-* [**cuda_plugin**](./modules/cuda_plugin/README.md)
+* [**nvidia_plugin**](./modules/nvidia_plugin/README.md)
 * [**ovms_ai_extension**](./modules/ovms_ai_extension/README.md)
 
 ## Update the repository documentation
diff --git a/modules/cuda_plugin/.clang-format b/modules/nvidia_plugin/.clang-format
similarity index 100%
rename from modules/cuda_plugin/.clang-format
rename to modules/nvidia_plugin/.clang-format
diff --git a/modules/cuda_plugin/.gitignore b/modules/nvidia_plugin/.gitignore
similarity index 100%
rename from modules/cuda_plugin/.gitignore
rename to modules/nvidia_plugin/.gitignore
diff --git a/modules/cuda_plugin/CMakeLists.txt b/modules/nvidia_plugin/CMakeLists.txt
similarity index 93%
rename from modules/cuda_plugin/CMakeLists.txt
rename to modules/nvidia_plugin/CMakeLists.txt
index be123d056..218e0155a 100644
--- a/modules/cuda_plugin/CMakeLists.txt
+++ b/modules/nvidia_plugin/CMakeLists.txt
@@ -3,7 +3,7 @@
 #
 
 cmake_minimum_required(VERSION 3.13)
-project(InferenceEngineCUDAPlugin CXX CUDA)
+project(InferenceEngineNVIDIAGpuPlugin CXX CUDA)
 
 set(CMAKE_CXX_STANDARD 17)
 set(CMAKE_CXX_EXTENSIONS OFF)
@@ -20,7 +20,7 @@ if (ENABLE_CUDNN_BACKEND_API)
     add_definitions(-DENABLE_CUDNN_BACKEND_API)
 endif()
 
-set(IE_MAIN_CUDA_PLUGIN_SOURCE_DIR ${InferenceEngineCUDAPlugin_SOURCE_DIR})
+set(IE_MAIN_CUDA_PLUGIN_SOURCE_DIR ${InferenceEngineNVIDIAGpuPlugin_SOURCE_DIR})
 
 find_package(InferenceEngineDeveloperPackage REQUIRED)
 
@@ -78,10 +78,10 @@ find_library(CUTENSOR_PATH
 get_filename_component(CUTENSOR_INCLUDE_DIR "${CUTENSOR_PATH}" DIRECTORY)
 get_filename_component(CUTENSOR_INCLUDE_DIR "${CUTENSOR_INCLUDE_DIR}/../../include" REALPATH)
 
-message("-- [CUDAPlugin] CUTENSOR_PATH ${CUTENSOR_PATH}")
-message("-- [CUDAPlugin] CUTENSOR_INCLUDE_DIR ${CUTENSOR_INCLUDE_DIR}")
-message("-- [CUDAPlugin] CUDNN_PATH ${CUDNN_PATH}")
-message("-- [CUDAPlugin] CUBLAS_PATH ${CUBLAS_PATH}")
+message("-- [nvidia_gpu] CUTENSOR_PATH ${CUTENSOR_PATH}")
+message("-- [nvidia_gpu] CUTENSOR_INCLUDE_DIR ${CUTENSOR_INCLUDE_DIR}")
+message("-- [nvidia_gpu] CUDNN_PATH ${CUDNN_PATH}")
+message("-- [nvidia_gpu] CUBLAS_PATH ${CUBLAS_PATH}")
 
 add_library(CUDA::cudnn SHARED IMPORTED)
 set_target_properties(CUDA::cudnn PROPERTIES IMPORTED_LOCATION "${CUDNN_PATH}")
diff --git a/modules/cuda_plugin/Dockerfile b/modules/nvidia_plugin/Dockerfile
similarity index 100%
rename from modules/cuda_plugin/Dockerfile
rename to modules/nvidia_plugin/Dockerfile
diff --git a/modules/cuda_plugin/README.md b/modules/nvidia_plugin/README.md
similarity index 86%
rename from modules/cuda_plugin/README.md
rename to modules/nvidia_plugin/README.md
index 36c6a6945..4b1b34107 100644
--- a/modules/cuda_plugin/README.md
+++ b/modules/nvidia_plugin/README.md
@@ -1,24 +1,24 @@
 
-# [OpenVINO™ Toolkit](https://01.org/openvinotoolkit) - CUDA plugin
+# [OpenVINO™ Toolkit](https://01.org/openvinotoolkit) - NVIDIA GPU plugin
 
-OpenVINO™ CUDA plugin is developed in order to enable deep neural networks inference on NVIDIA GPUs, using OpenVINO™ API.
+OpenVINO™ NVIDIA GPU plugin is developed in order to enable deep neural networks inference on NVIDIA GPUs, using OpenVINO™ API.
 The plugin uses custom kernels and [cuBLAS, cuDNN, cuTENSOR libraries\*] as a backend.
 
 ## Supported Platforms
-OpenVINO™ CUDA plugin is supported and validated on the following platforms: 
+OpenVINO™ NVIDIA GPU plugin is supported and validated on the following platforms: 
 
 OS                     | GPU
 ---------------------- | ----------------------
 Ubuntu* 18.04 (64-bit) | Geforce 1080 Ti, NVIDIA T4
 
 ## Distribution
-OpenVINO™ CUDA plugin is not included into Intel® Distribution of OpenVINO™. To use the plugin, it should be built from source code.
+OpenVINO™ NVIDIA GPU plugin is not included into Intel® Distribution of OpenVINO™. To use the plugin, it should be built from source code.
 
 ## How to build
 
 ### Prerequisites
 
-In order to build CUDA plugin the next dependencies must be installed.
+In order to build NVIDIA GPU plugin the next dependencies must be installed.
 
 1. Install one of the following compilers with support of **C++17**:
 - Install **gcc-7** compiler
@@ -52,7 +52,7 @@ git clone --recurse-submodules --single-branch --branch=master https://github.co
 ```
 2. Go to plugin directory:
 ```bash
-cd openvino_contrib/modules/cuda_plugin
+cd openvino_contrib/modules/nvidia_plugin
 git checkout develop
 ```
 3. Prepare a build folder:
@@ -89,7 +89,7 @@ mkdir build && cd build
   Run the following command:
   ```bash
   cmake -DInferenceEngineDeveloperPackage_DIR=<path to OpenVINO package build folder> -DCMAKE_BUILD_TYPE=Release ..
-  cmake --build . --target CUDAPlugin -j `nproc`
+  cmake --build . --target nvidia_gpu -j `nproc`
   ```
 
 ### Build with _setup.py_
@@ -102,7 +102,7 @@ git clone --recurse-submodules --single-branch --branch=master https://github.co
 ```
 2. Go to plugin directory:
 ```bash
-cd openvino_contrib/modules/cuda_plugin
+cd openvino_contrib/modules/nvidia_plugin
 git checkout develop
 ```
 3. Setup `CUDACXX` environment variable to point to the CUDA _nvcc_ compiler like the next (use yours path)
@@ -117,12 +117,12 @@ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda-11.2/bin/nvcc
 
 5. Run setup.py build command as follows.
 ```bash
-export CUDA_PLUGIN_SRC_ROOT_DIR=</path/to/openvino_contrib>/modules/cuda_plugin
+export CUDA_PLUGIN_SRC_ROOT_DIR=</path/to/openvino_contrib>/modules/nvidia_plugin
 python3 ${CUDA_PLUGIN_SRC_ROOT_DIR}/wheel/setup.py build
 ```
 This will automatically download, build OpenVINO and build CUDA Plugin finally. The location of the resulting library file will be like the next.
 ```
-${CUDA_PLUGIN_SRC_ROOT_DIR}/build/temp.linux-x86_64-3.6/deps/openvino/bin/intel64/Debug/lib/libCUDAPlugin.so
+${CUDA_PLUGIN_SRC_ROOT_DIR}/build/temp.linux-x86_64-3.6/deps/openvino/bin/intel64/Debug/lib/libopenvino_nvidia_gpu_plugin.so
 ```
 
 ## Install as python package with `setup.py`
@@ -131,9 +131,9 @@ To install CUDA Plugin as python package do all steps except last one from the `
 After that installation could be done by running setup.py install command as follows.
 ```bash
 export OPENVINO_CONTRIB=</path/to/openvino_contrib>
-python3 ${OPENVINO_CONTRIB}/modules/cuda_plugin/wheel/setup.py install
+python3 ${OPENVINO_CONTRIB}/modules/nvidia_plugin/wheel/setup.py install
 ```
-This command will install dependent openvino package if needed and update it for using with CUDA plugin.
+This command will install dependent openvino package if needed and update it for using with NVIDIA GPU plugin.
 
 
 ## Docker support
@@ -151,14 +151,14 @@ su $USER # Relogin for current user
 CUDA_PACKAGES_PATH=<path to CUDA pakcages> ./docker.sh build
 ```
 
-### Build CUDAPlugin in docker container
-In order to build CUDAPlugin in docker, follow the steps:
+### Build openvino_nvidia_gpu_plugin in docker container
+In order to build openvino_nvidia_gpu_plugin in docker, follow the steps:
 
 1. Enter the docker container:
 ```bash
 docker run --gpus all -it openvino/cudaplugin-2022.1 bin/bash
 ```
-2. Build the OpenVINO and CUDAPlugin according the steps described in [## How to build](#how-to-build),
+2. Build the OpenVINO and openvino_nvidia_gpu_plugin according the steps described in [## How to build](#how-to-build),
    except 3), 4), 5) steps (this packages already installed in image)
 3. Commit all your changes in container:
 ```bash
@@ -173,7 +173,7 @@ Parameter name  | Parameter values  | Default  | Description
 `CUDA_THROUGHPUT_STREAMS`   | `CUDA_THROUGHPUT_AUTO`, or non negative integer values  | 1  | Specifies number of CPU "execution" streams for the throughput mode. Upper bound for the number of inference requests that can be executed simultaneously.
 `CUDA_OPERATION_BENCHMARK`   | `CUDA_YES`, `CUDA_NO`  | `CUDA_NO`  | Specifies if operation level benchmark should be run for increasing performance of network
 
-During compilation of the CUDAPlugin, user could specify two options:
+During compilation of the openvino_nvidia_gpu_plugin, user could specify two options:
 1) `-DCUDA_KERNEL_PRINT_LOG=ON` enables print logs from kernels (WARNING, be careful with this options, could print to many logs)
 2) `-DENABLE_CUDNN_BACKEND_API` enables cuDNN backend support that could increase performance of convolutions by 20%
 
@@ -207,7 +207,7 @@ The plugin supports IRv10 and higher. The list of supported layers and its limit
 * NC - Supported
 
 ## License
-OpenVINO™ CUDA plugin is licensed under [Apache License Version 2.0](LICENSE).
+OpenVINO™ NVIDIA GPU plugin is licensed under [Apache License Version 2.0](LICENSE).
 By contributing to the project, you agree to the license and copyright terms therein
 and release your contribution under these terms.
 
diff --git a/modules/cuda_plugin/SECURITY.md b/modules/nvidia_plugin/SECURITY.md
similarity index 100%
rename from modules/cuda_plugin/SECURITY.md
rename to modules/nvidia_plugin/SECURITY.md
diff --git a/modules/cuda_plugin/build.sh b/modules/nvidia_plugin/build.sh
similarity index 91%
rename from modules/cuda_plugin/build.sh
rename to modules/nvidia_plugin/build.sh
index 17c58b0a5..277b1d06e 100755
--- a/modules/cuda_plugin/build.sh
+++ b/modules/nvidia_plugin/build.sh
@@ -9,7 +9,7 @@ fi
 
 BUILD_JOBS=${BUILD_JOBS:-$(nproc)}
 BUILD_TYPE=${BUILD_TYPE:-Release}
-BUILD_TARGETS=${BUILD_TARGETS:-"CudaFuncTests CudaUnitTests openvino_cuda_plugin benchmark_app"}
+BUILD_TARGETS=${BUILD_TARGETS:-"CudaFuncTests CudaUnitTests openvino_nvidia_gpu_plugin benchmark_app"}
 WHEEL_VERSION=${WHEEL_VERSION:-"2022.1.0"}
 ENABLE_TESTS=${ENABLE_TESTS:-"ON"}
 
@@ -18,7 +18,7 @@ ENABLE_TESTS=${ENABLE_TESTS:-"ON"}
 [[ -n "${OPENVINO_BUILD_PATH}" ]] || { echo "OPENVINO_BUILD_PATH environment variable is expected"; exit 1; }
 [[ -d "${OPENVINO_HOME}" ]] || { echo "OPENVINO_HOME=${OPENVINO_HOME} does not exist"; exit 1; }
 [[ -d "${OPENVINO_CONTRIB}" ]] || { echo "OPENVINO_CONTRIB=${OPENVINO_CONTRIB} does not exist"; exit 1; }
-[[ -d "${OPENVINO_CONTRIB}/modules/cuda_plugin" ]] || { echo "Path ${OPENVINO_CONTRIB}/modules/cuda_plugin does not exist"; exit 1; }
+[[ -d "${OPENVINO_CONTRIB}/modules/nvidia_plugin" ]] || { echo "Path ${OPENVINO_CONTRIB}/modules/nvidia_plugin does not exist"; exit 1; }
 [[ "$1" == "--setup" || "$1" == "--build" || "$1" == "--rebuild" ]] || {
   printf "One of the following command should be provided:\n\
   - --setup (allow configure cmake project)\n\
diff --git a/modules/cuda_plugin/cmake/features.cmake b/modules/nvidia_plugin/cmake/features.cmake
similarity index 100%
rename from modules/cuda_plugin/cmake/features.cmake
rename to modules/nvidia_plugin/cmake/features.cmake
diff --git a/modules/cuda_plugin/docker.sh b/modules/nvidia_plugin/docker.sh
similarity index 100%
rename from modules/cuda_plugin/docker.sh
rename to modules/nvidia_plugin/docker.sh
diff --git a/modules/cuda_plugin/docs/cuda_opset.md b/modules/nvidia_plugin/docs/cuda_opset.md
similarity index 99%
rename from modules/cuda_plugin/docs/cuda_opset.md
rename to modules/nvidia_plugin/docs/cuda_opset.md
index a862de787..91ed5b9c0 100644
--- a/modules/cuda_plugin/docs/cuda_opset.md
+++ b/modules/nvidia_plugin/docs/cuda_opset.md
@@ -1,13 +1,13 @@
-# CUDA plugin operation set specification
+# NVIDIA GPU plugin operation set specification
 
 This specification document based on [opset6](https://github.com/openvinotoolkit/openvino/blob/master/docs/ops/opset6.md) operation set supported in OpenVINO.
 Examples of operation instances are expressed as IR V10 xml snippets. Such IR is generated by the Model Optimizer.
 The semantics match corresponding nGraph operation classes declared in `namespace opset6`.
 
-> **NOTE**: CUDA plugin doesn't support operations with dynamic shape.
+> **NOTE**: NVIDIA GPU plugin doesn't support operations with dynamic shape.
 ## Table of Contents <a name="toc"></a>
 
-| Layers                                                                                                                                         | CUDA plugin   |
+| Layers                                                                                                                                         | NVIDIA GPU plugin   |
 |------------------------------------------------------------------------------------------------------------------------------------------------|---------------|
 | [Abs](https://github.com/openvinotoolkit/openvino/blob/master/docs/ops/arithmetic/Abs_1.md)                                                    | Not Supported |
 | [Acos](https://github.com/openvinotoolkit/openvino/blob/master/docs/ops/arithmetic/Acos_1.md)                                                  | Not Supported |
diff --git a/modules/cuda_plugin/docs/design-rationales/WorkbufferProvisioning.md b/modules/nvidia_plugin/docs/design-rationales/WorkbufferProvisioning.md
similarity index 95%
rename from modules/cuda_plugin/docs/design-rationales/WorkbufferProvisioning.md
rename to modules/nvidia_plugin/docs/design-rationales/WorkbufferProvisioning.md
index 1738655ff..8714b8969 100644
--- a/modules/cuda_plugin/docs/design-rationales/WorkbufferProvisioning.md
+++ b/modules/nvidia_plugin/docs/design-rationales/WorkbufferProvisioning.md
@@ -15,7 +15,7 @@
 * From the Memory Manager point of view
     - a mutable workbuffer is an input/output tensor with its time box starting on T and lasting till T (1 slot in total)
     - an immutable workbuffer is an input/output tensor a  time box spanning through the nework scope
-    - It's a special case which should work (but not tested in CUDAPlugin::MemorySolver) when producerIndex is equal to lastConsumerIndex. 
+    - It's a special case which should work (but not tested in ov::nvidia_gpu::MemorySolver) when producerIndex is equal to lastConsumerIndex. 
       Trying to use other values will keep buffer alive wirthout a reason.
 * Use several workbufers (i.e. a vector) the same way as for inputs and outputs could be as well beneficial for the following reasons:
     - The smaller workbuffer is, the easier to allocate it in a gaps between other memory segments, 
diff --git a/modules/cuda_plugin/include/cuda/cuda_config.hpp b/modules/nvidia_plugin/include/cuda/cuda_config.hpp
similarity index 96%
rename from modules/cuda_plugin/include/cuda/cuda_config.hpp
rename to modules/nvidia_plugin/include/cuda/cuda_config.hpp
index 45aace2d3..fe4385cc5 100644
--- a/modules/cuda_plugin/include/cuda/cuda_config.hpp
+++ b/modules/nvidia_plugin/include/cuda/cuda_config.hpp
@@ -51,7 +51,7 @@ DECLARE_CUDA_CONFIG_VALUE(YES);
 DECLARE_CUDA_CONFIG_VALUE(NO);
 
 /**
- * @brief Defines the number of throutput streams used by CUDA plugin.
+ * @brief Defines the number of throutput streams used by NVIDIA GPU plugin.
  */
 DECLARE_CUDA_CONFIG_VALUE(THROUGHPUT_AUTO);
 DECLARE_CUDA_CONFIG_KEY(THROUGHPUT_STREAMS);
diff --git a/modules/cuda_plugin/include/gpu/gpu_context_api_cuda.hpp b/modules/nvidia_plugin/include/gpu/gpu_context_api_cuda.hpp
similarity index 100%
rename from modules/cuda_plugin/include/gpu/gpu_context_api_cuda.hpp
rename to modules/nvidia_plugin/include/gpu/gpu_context_api_cuda.hpp
diff --git a/modules/cuda_plugin/src/CMakeLists.txt b/modules/nvidia_plugin/src/CMakeLists.txt
similarity index 97%
rename from modules/cuda_plugin/src/CMakeLists.txt
rename to modules/nvidia_plugin/src/CMakeLists.txt
index 98f8b067c..2a5a4bde4 100644
--- a/modules/cuda_plugin/src/CMakeLists.txt
+++ b/modules/nvidia_plugin/src/CMakeLists.txt
@@ -2,7 +2,7 @@
 # SPDX-License-Identifier: Apache-2.0
 #
 
-set(TARGET_NAME openvino_cuda_plugin)
+set(TARGET_NAME openvino_nvidia_gpu_plugin)
 set(OBJ_NAME ${TARGET_NAME}_obj)
 
 set(SOURCE_MASKS *.cpp *.cu)
@@ -29,7 +29,7 @@ target_compile_definitions(${OBJ_NAME} PRIVATE IMPLEMENT_INFERENCE_ENGINE_PLUGIN
 
 # Adds a shared library with plugin
 ie_add_plugin(NAME ${TARGET_NAME}
-              DEVICE_NAME "CUDA"
+              DEVICE_NAME "NVIDIA"
               SOURCES ${HEADERS} cuda_create_plugin.cpp
               SKIP_INSTALL # ATTENTION: uncomment to install component
               VERSION_DEFINES_FOR cuda_create_plugin.cpp)
diff --git a/modules/cuda_plugin/src/cancellation_token.hpp b/modules/nvidia_plugin/src/cancellation_token.hpp
similarity index 93%
rename from modules/cuda_plugin/src/cancellation_token.hpp
rename to modules/nvidia_plugin/src/cancellation_token.hpp
index f63bb23b4..2577522f4 100644
--- a/modules/cuda_plugin/src/cancellation_token.hpp
+++ b/modules/nvidia_plugin/src/cancellation_token.hpp
@@ -11,7 +11,8 @@
 #include <functional>
 #include <utility>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class CancellationToken {
 public:
@@ -45,4 +46,5 @@ class CancellationToken {
     std::function<void()> cancel_callback_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda/blas.hpp b/modules/nvidia_plugin/src/cuda/blas.hpp
similarity index 89%
rename from modules/cuda_plugin/src/cuda/blas.hpp
rename to modules/nvidia_plugin/src/cuda/blas.hpp
index c352b86ab..aa3224a54 100644
--- a/modules/cuda_plugin/src/cuda/blas.hpp
+++ b/modules/nvidia_plugin/src/cuda/blas.hpp
@@ -39,13 +39,13 @@ inline std::string cublasGetErrorString(cublasStatus_t status) {
 inline void throwIfError(
     cublasStatus_t err,
     const std::experimental::source_location& location = std::experimental::source_location::current()) {
-    if (err != CUBLAS_STATUS_SUCCESS) CUDAPlugin::throwIEException(cublasGetErrorString(err), location);
+    if (err != CUBLAS_STATUS_SUCCESS) ov::nvidia_gpu::throwIEException(cublasGetErrorString(err), location);
 }
 
 inline void logIfError(
     cublasStatus_t err,
     const std::experimental::source_location& location = std::experimental::source_location::current()) {
-    if (err != CUBLAS_STATUS_SUCCESS) CUDAPlugin::logError(cublasGetErrorString(err), location);
+    if (err != CUBLAS_STATUS_SUCCESS) ov::nvidia_gpu::logError(cublasGetErrorString(err), location);
 }
 
 namespace CUDA {
diff --git a/modules/cuda_plugin/src/cuda/constant_factory.hpp b/modules/nvidia_plugin/src/cuda/constant_factory.hpp
similarity index 99%
rename from modules/cuda_plugin/src/cuda/constant_factory.hpp
rename to modules/nvidia_plugin/src/cuda/constant_factory.hpp
index a195ee0f6..051a953ff 100644
--- a/modules/cuda_plugin/src/cuda/constant_factory.hpp
+++ b/modules/nvidia_plugin/src/cuda/constant_factory.hpp
@@ -154,7 +154,7 @@ inline const constants::AnyNumeric& NumericConst(cudaDataType_t computeType) {
             return C<std::uint32_t>::value;
         }
         default:
-            CUDAPlugin::throwIEException(
+            ov::nvidia_gpu::throwIEException(
                 fmt::format("The ngraph element type {} is not supported by "
                             "the cuda library",
                             computeType));
diff --git a/modules/cuda_plugin/src/cuda/cuda_type_traits.hpp b/modules/nvidia_plugin/src/cuda/cuda_type_traits.hpp
similarity index 100%
rename from modules/cuda_plugin/src/cuda/cuda_type_traits.hpp
rename to modules/nvidia_plugin/src/cuda/cuda_type_traits.hpp
diff --git a/modules/cuda_plugin/src/cuda/descriptor_utils.cpp b/modules/nvidia_plugin/src/cuda/descriptor_utils.cpp
similarity index 92%
rename from modules/cuda_plugin/src/cuda/descriptor_utils.cpp
rename to modules/nvidia_plugin/src/cuda/descriptor_utils.cpp
index 02b8167a7..3162016b8 100644
--- a/modules/cuda_plugin/src/cuda/descriptor_utils.cpp
+++ b/modules/nvidia_plugin/src/cuda/descriptor_utils.cpp
@@ -23,7 +23,7 @@ DnnTensorDescriptor makeDnnTensorDescr(const ngraph::element::Type& type, const
     strides.back() = 1;
     for (int i = dims.size() - 1; i > 0; i--) strides[i - 1] = strides[i] * dims[i];
     return DnnTensorDescriptor{}.set(
-        CUDAPlugin::convertDataType<cudnnDataType_t>(type), dims.size(), dims.data(), strides.data());
+        ov::nvidia_gpu::convertDataType<cudnnDataType_t>(type), dims.size(), dims.data(), strides.data());
 }
 
 CUDA::DnnTensorDescriptor makeInputDnnTensorDescr(const ov::Node& node, int n) {
diff --git a/modules/cuda_plugin/src/cuda/descriptor_utils.hpp b/modules/nvidia_plugin/src/cuda/descriptor_utils.hpp
similarity index 100%
rename from modules/cuda_plugin/src/cuda/descriptor_utils.hpp
rename to modules/nvidia_plugin/src/cuda/descriptor_utils.hpp
diff --git a/modules/cuda_plugin/src/cuda/device_pointers.hpp b/modules/nvidia_plugin/src/cuda/device_pointers.hpp
similarity index 100%
rename from modules/cuda_plugin/src/cuda/device_pointers.hpp
rename to modules/nvidia_plugin/src/cuda/device_pointers.hpp
diff --git a/modules/cuda_plugin/src/cuda/dnn.hpp b/modules/nvidia_plugin/src/cuda/dnn.hpp
similarity index 98%
rename from modules/cuda_plugin/src/cuda/dnn.hpp
rename to modules/nvidia_plugin/src/cuda/dnn.hpp
index f6a9e7840..1bf4be568 100644
--- a/modules/cuda_plugin/src/cuda/dnn.hpp
+++ b/modules/nvidia_plugin/src/cuda/dnn.hpp
@@ -39,13 +39,13 @@ inline std::string cudnnGetErrorString(cudnnConvolutionFwdAlgo_t algo) {
 inline void throwIfError(
     cudnnStatus_t err,
     const std::experimental::source_location& location = std::experimental::source_location::current()) {
-    if (err != CUDNN_STATUS_SUCCESS) CUDAPlugin::throwIEException(cudnnGetErrorString(err), location);
+    if (err != CUDNN_STATUS_SUCCESS) ov::nvidia_gpu::throwIEException(cudnnGetErrorString(err), location);
 }
 
 inline void logIfError(
     cudnnStatus_t err,
     const std::experimental::source_location& location = std::experimental::source_location::current()) {
-    if (err != CUDNN_STATUS_SUCCESS) CUDAPlugin::logError(cudnnGetErrorString(err), location);
+    if (err != CUDNN_STATUS_SUCCESS) ov::nvidia_gpu::logError(cudnnGetErrorString(err), location);
 }
 
 namespace CUDA {
diff --git a/modules/cuda_plugin/src/cuda/dnn_be.hpp b/modules/nvidia_plugin/src/cuda/dnn_be.hpp
similarity index 99%
rename from modules/cuda_plugin/src/cuda/dnn_be.hpp
rename to modules/nvidia_plugin/src/cuda/dnn_be.hpp
index 83fd3ea73..87926c97e 100644
--- a/modules/cuda_plugin/src/cuda/dnn_be.hpp
+++ b/modules/nvidia_plugin/src/cuda/dnn_be.hpp
@@ -517,7 +517,7 @@ class DnnBEEngineConfigDescriptor : public DnnBackendDescriptor {
 
     DnnBEEngine getEngine() const {
         auto engines = getBEDescAttributeValues<CUDNN_ATTR_ENGINECFG_ENGINE, DnnBEEngine>();
-        if (engines.size() != 1) CUDAPlugin::throwIEException("Unexpected number of cuDNN Backend engines");
+        if (engines.size() != 1) ov::nvidia_gpu::throwIEException("Unexpected number of cuDNN Backend engines");
         return std::move(*engines[0]);
     }
 
diff --git a/modules/cuda_plugin/src/cuda/dnn_be_algo.hpp b/modules/nvidia_plugin/src/cuda/dnn_be_algo.hpp
similarity index 98%
rename from modules/cuda_plugin/src/cuda/dnn_be_algo.hpp
rename to modules/nvidia_plugin/src/cuda/dnn_be_algo.hpp
index 05cab7958..dc609e9a9 100644
--- a/modules/cuda_plugin/src/cuda/dnn_be_algo.hpp
+++ b/modules/nvidia_plugin/src/cuda/dnn_be_algo.hpp
@@ -69,7 +69,7 @@ std::shared_ptr<CUDA::DnnBEExecutionPlan> performBenchmarks(
         [](const std::vector<size_t>& workspace_sizes) -> std::optional<std::pair<CUDA::DefaultAllocation, size_t>> {
         for (const auto workspace_size : workspace_sizes) {
             try {
-                const auto aligned_workspace_size = CUDAPlugin::applyAllignment(workspace_size);
+                const auto aligned_workspace_size = ov::nvidia_gpu::applyAllignment(workspace_size);
                 CUDA::DefaultAllocation workspace = CUDA::DefaultStream::stream().malloc(aligned_workspace_size);
                 return std::optional<std::pair<CUDA::DefaultAllocation, size_t>>{
                     {std::move(workspace), workspace_size}};
diff --git a/modules/cuda_plugin/src/cuda/dnn_be_attrs.hpp b/modules/nvidia_plugin/src/cuda/dnn_be_attrs.hpp
similarity index 100%
rename from modules/cuda_plugin/src/cuda/dnn_be_attrs.hpp
rename to modules/nvidia_plugin/src/cuda/dnn_be_attrs.hpp
diff --git a/modules/cuda_plugin/src/cuda/dnn_be_desc.hpp b/modules/nvidia_plugin/src/cuda/dnn_be_desc.hpp
similarity index 100%
rename from modules/cuda_plugin/src/cuda/dnn_be_desc.hpp
rename to modules/nvidia_plugin/src/cuda/dnn_be_desc.hpp
diff --git a/modules/cuda_plugin/src/cuda/event.hpp b/modules/nvidia_plugin/src/cuda/event.hpp
similarity index 100%
rename from modules/cuda_plugin/src/cuda/event.hpp
rename to modules/nvidia_plugin/src/cuda/event.hpp
diff --git a/modules/cuda_plugin/src/cuda/float16.hpp b/modules/nvidia_plugin/src/cuda/float16.hpp
similarity index 100%
rename from modules/cuda_plugin/src/cuda/float16.hpp
rename to modules/nvidia_plugin/src/cuda/float16.hpp
diff --git a/modules/cuda_plugin/src/cuda/math.cuh b/modules/nvidia_plugin/src/cuda/math.cuh
similarity index 100%
rename from modules/cuda_plugin/src/cuda/math.cuh
rename to modules/nvidia_plugin/src/cuda/math.cuh
diff --git a/modules/cuda_plugin/src/cuda/props.cpp b/modules/nvidia_plugin/src/cuda/props.cpp
similarity index 100%
rename from modules/cuda_plugin/src/cuda/props.cpp
rename to modules/nvidia_plugin/src/cuda/props.cpp
diff --git a/modules/cuda_plugin/src/cuda/props.hpp b/modules/nvidia_plugin/src/cuda/props.hpp
similarity index 100%
rename from modules/cuda_plugin/src/cuda/props.hpp
rename to modules/nvidia_plugin/src/cuda/props.hpp
diff --git a/modules/cuda_plugin/src/cuda/runtime.hpp b/modules/nvidia_plugin/src/cuda/runtime.hpp
similarity index 98%
rename from modules/cuda_plugin/src/cuda/runtime.hpp
rename to modules/nvidia_plugin/src/cuda/runtime.hpp
index c92964b07..875c2829d 100644
--- a/modules/cuda_plugin/src/cuda/runtime.hpp
+++ b/modules/nvidia_plugin/src/cuda/runtime.hpp
@@ -16,13 +16,13 @@
 inline void throwIfError(
     cudaError_t err,
     const std::experimental::source_location& location = std::experimental::source_location::current()) {
-    if (err != cudaSuccess) CUDAPlugin::throwIEException(cudaGetErrorString(err), location);
+    if (err != cudaSuccess) ov::nvidia_gpu::throwIEException(cudaGetErrorString(err), location);
 }
 
 inline void logIfError(
     cudaError_t err,
     const std::experimental::source_location& location = std::experimental::source_location::current()) {
-    if (err != cudaSuccess) CUDAPlugin::logError(cudaGetErrorString(err), location);
+    if (err != cudaSuccess) ov::nvidia_gpu::logError(cudaGetErrorString(err), location);
 }
 
 namespace CUDA {
diff --git a/modules/cuda_plugin/src/cuda/stl/algorithms/sort.cuh b/modules/nvidia_plugin/src/cuda/stl/algorithms/sort.cuh
similarity index 100%
rename from modules/cuda_plugin/src/cuda/stl/algorithms/sort.cuh
rename to modules/nvidia_plugin/src/cuda/stl/algorithms/sort.cuh
diff --git a/modules/cuda_plugin/src/cuda/stl/array.cuh b/modules/nvidia_plugin/src/cuda/stl/array.cuh
similarity index 100%
rename from modules/cuda_plugin/src/cuda/stl/array.cuh
rename to modules/nvidia_plugin/src/cuda/stl/array.cuh
diff --git a/modules/cuda_plugin/src/cuda/stl/atomic.cuh b/modules/nvidia_plugin/src/cuda/stl/atomic.cuh
similarity index 100%
rename from modules/cuda_plugin/src/cuda/stl/atomic.cuh
rename to modules/nvidia_plugin/src/cuda/stl/atomic.cuh
diff --git a/modules/cuda_plugin/src/cuda/stl/mdspan.cuh b/modules/nvidia_plugin/src/cuda/stl/mdspan.cuh
similarity index 100%
rename from modules/cuda_plugin/src/cuda/stl/mdspan.cuh
rename to modules/nvidia_plugin/src/cuda/stl/mdspan.cuh
diff --git a/modules/cuda_plugin/src/cuda/stl/mdvector.cuh b/modules/nvidia_plugin/src/cuda/stl/mdvector.cuh
similarity index 100%
rename from modules/cuda_plugin/src/cuda/stl/mdvector.cuh
rename to modules/nvidia_plugin/src/cuda/stl/mdvector.cuh
diff --git a/modules/cuda_plugin/src/cuda/stl/pair.cuh b/modules/nvidia_plugin/src/cuda/stl/pair.cuh
similarity index 100%
rename from modules/cuda_plugin/src/cuda/stl/pair.cuh
rename to modules/nvidia_plugin/src/cuda/stl/pair.cuh
diff --git a/modules/cuda_plugin/src/cuda/stl/span.cuh b/modules/nvidia_plugin/src/cuda/stl/span.cuh
similarity index 100%
rename from modules/cuda_plugin/src/cuda/stl/span.cuh
rename to modules/nvidia_plugin/src/cuda/stl/span.cuh
diff --git a/modules/cuda_plugin/src/cuda/stl/vector.cuh b/modules/nvidia_plugin/src/cuda/stl/vector.cuh
similarity index 100%
rename from modules/cuda_plugin/src/cuda/stl/vector.cuh
rename to modules/nvidia_plugin/src/cuda/stl/vector.cuh
diff --git a/modules/cuda_plugin/src/cuda/tensor.hpp b/modules/nvidia_plugin/src/cuda/tensor.hpp
similarity index 74%
rename from modules/cuda_plugin/src/cuda/tensor.hpp
rename to modules/nvidia_plugin/src/cuda/tensor.hpp
index ff7fb9e77..b577927cb 100644
--- a/modules/cuda_plugin/src/cuda/tensor.hpp
+++ b/modules/nvidia_plugin/src/cuda/tensor.hpp
@@ -11,13 +11,13 @@
 inline void throwIfError(
     cutensorStatus_t err,
     const std::experimental::source_location& location = std::experimental::source_location::current()) {
-    if (err != CUTENSOR_STATUS_SUCCESS) CUDAPlugin::throwIEException(cutensorGetErrorString(err), location);
+    if (err != CUTENSOR_STATUS_SUCCESS) ov::nvidia_gpu::throwIEException(cutensorGetErrorString(err), location);
 }
 
 inline void logIfError(
     cutensorStatus_t err,
     const std::experimental::source_location& location = std::experimental::source_location::current()) {
-    if (err != CUTENSOR_STATUS_SUCCESS) CUDAPlugin::logError(cutensorGetErrorString(err), location);
+    if (err != CUTENSOR_STATUS_SUCCESS) ov::nvidia_gpu::logError(cutensorGetErrorString(err), location);
 }
 
 namespace CUDA {
diff --git a/modules/cuda_plugin/src/cuda_async_infer_request.cpp b/modules/nvidia_plugin/src/cuda_async_infer_request.cpp
similarity index 81%
rename from modules/cuda_plugin/src/cuda_async_infer_request.cpp
rename to modules/nvidia_plugin/src/cuda_async_infer_request.cpp
index 78770beb8..001cb9cec 100644
--- a/modules/cuda_plugin/src/cuda_async_infer_request.cpp
+++ b/modules/nvidia_plugin/src/cuda_async_infer_request.cpp
@@ -10,7 +10,8 @@
 #include "cuda_itt.hpp"
 #include "cuda_thread_pool.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 CudaAsyncInferRequest::CudaAsyncInferRequest(const CudaInferRequest::Ptr& inferRequest,
                                              const InferenceEngine::ITaskExecutor::Ptr& cpuTaskExecutor,
@@ -28,23 +29,23 @@ CudaAsyncInferRequest::CudaAsyncInferRequest(const CudaInferRequest::Ptr& inferR
     if (remoteDevice) {
         _pipeline = {{cpuTaskExecutor,
                       [this] {
-                          OV_ITT_SCOPED_TASK(itt::domains::CUDAPlugin, "CudaAsyncInferRequest::Preprocessing");
+                          OV_ITT_SCOPED_TASK(itt::domains::nvidia_gpu, "CudaAsyncInferRequest::Preprocessing");
                           _inferRequest->inferPreprocess();
                       }},
                      {waitExecutor,
                       [this, cudaThreadPool] {
                           auto& threadContext = cudaThreadPool->GetThreadContext();
                           {
-                              OV_ITT_SCOPED_TASK(itt::domains::CUDAPlugin, "CudaAsyncInferRequest::StartPipeline");
+                              OV_ITT_SCOPED_TASK(itt::domains::nvidia_gpu, "CudaAsyncInferRequest::StartPipeline");
                               _inferRequest->startPipeline(threadContext);
                           }
                           {
-                              OV_ITT_SCOPED_TASK(itt::domains::CUDAPlugin, "CudaAsyncInferRequest::WaitPipeline");
+                              OV_ITT_SCOPED_TASK(itt::domains::nvidia_gpu, "CudaAsyncInferRequest::WaitPipeline");
                               _inferRequest->waitPipeline(threadContext);
                           }
                       }},
                      {cpuTaskExecutor, [this] {
-                          OV_ITT_SCOPED_TASK(itt::domains::CUDAPlugin, "CudaAsyncInferRequest::Postprocessing");
+                          OV_ITT_SCOPED_TASK(itt::domains::nvidia_gpu, "CudaAsyncInferRequest::Postprocessing");
                           _inferRequest->inferPostprocess();
                       }}};
     }
@@ -57,4 +58,5 @@ void CudaAsyncInferRequest::Cancel() {
 
 void CudaAsyncInferRequest::Infer_ThreadUnsafe() { StartAsync_ThreadUnsafe(); }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_async_infer_request.hpp b/modules/nvidia_plugin/src/cuda_async_infer_request.hpp
similarity index 91%
rename from modules/cuda_plugin/src/cuda_async_infer_request.hpp
rename to modules/nvidia_plugin/src/cuda_async_infer_request.hpp
index 60b2f199c..af3e7403f 100644
--- a/modules/cuda_plugin/src/cuda_async_infer_request.hpp
+++ b/modules/nvidia_plugin/src/cuda_async_infer_request.hpp
@@ -8,7 +8,8 @@
 
 #include "cuda_infer_request.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class CudaAsyncInferRequest : public InferenceEngine::AsyncInferRequestThreadSafeDefault {
 public:
@@ -30,4 +31,5 @@ class CudaAsyncInferRequest : public InferenceEngine::AsyncInferRequestThreadSaf
     CudaInferRequest::Ptr _inferRequest;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_config.cpp b/modules/nvidia_plugin/src/cuda_config.cpp
similarity index 99%
rename from modules/cuda_plugin/src/cuda_config.cpp
rename to modules/nvidia_plugin/src/cuda_config.cpp
index 21c932e1e..a1bf46669 100644
--- a/modules/cuda_plugin/src/cuda_config.cpp
+++ b/modules/nvidia_plugin/src/cuda_config.cpp
@@ -9,7 +9,7 @@
 #include <cpp_interfaces/interface/ie_internal_plugin_config.hpp>
 #include <error.hpp>
 
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 
 Configuration::Configuration() {}
 
diff --git a/modules/cuda_plugin/src/cuda_config.hpp b/modules/nvidia_plugin/src/cuda_config.hpp
similarity index 94%
rename from modules/cuda_plugin/src/cuda_config.hpp
rename to modules/nvidia_plugin/src/cuda_config.hpp
index 8c243f727..18267cef4 100644
--- a/modules/cuda_plugin/src/cuda_config.hpp
+++ b/modules/nvidia_plugin/src/cuda_config.hpp
@@ -12,7 +12,8 @@
 #include <string>
 #include <threading/ie_istreams_executor.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 using ConfigMap = std::map<std::string, std::string>;
 
@@ -43,4 +44,5 @@ struct Configuration {
     ov::hint::PerformanceMode performance_mode = ov::hint::PerformanceMode::UNDEFINED;
 };
 
-}  //  namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_create_plugin.cpp b/modules/nvidia_plugin/src/cuda_create_plugin.cpp
similarity index 69%
rename from modules/cuda_plugin/src/cuda_create_plugin.cpp
rename to modules/nvidia_plugin/src/cuda_create_plugin.cpp
index 9b27eda7c..a50a66394 100644
--- a/modules/cuda_plugin/src/cuda_create_plugin.cpp
+++ b/modules/nvidia_plugin/src/cuda_create_plugin.cpp
@@ -4,12 +4,14 @@
 
 #include "cuda_plugin.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace {
 
-const InferenceEngine::Version version{{2, 1}, CI_BUILD_NUMBER, "openvino_cuda_plugin"};
+const InferenceEngine::Version version{{2, 1}, CI_BUILD_NUMBER, "openvino_nvidia_gpu_plugin"};
 
 IE_DEFINE_PLUGIN_CREATE_FUNCTION(Plugin, version)
 
 }  // namespace
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_creation_context.hpp b/modules/nvidia_plugin/src/cuda_creation_context.hpp
similarity index 88%
rename from modules/cuda_plugin/src/cuda_creation_context.hpp
rename to modules/nvidia_plugin/src/cuda_creation_context.hpp
index 40118bb10..0fa2986b3 100644
--- a/modules/cuda_plugin/src/cuda_creation_context.hpp
+++ b/modules/nvidia_plugin/src/cuda_creation_context.hpp
@@ -10,7 +10,8 @@
 #include "cuda/dnn.hpp"
 #include "cuda/tensor.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class CreationContext {
     CUDA::Device device_;
@@ -25,4 +26,5 @@ class CreationContext {
     bool opBenchOption() const noexcept { return op_bench_option_; }
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_executable_network.cpp b/modules/nvidia_plugin/src/cuda_executable_network.cpp
similarity index 99%
rename from modules/cuda_plugin/src/cuda_executable_network.cpp
rename to modules/nvidia_plugin/src/cuda_executable_network.cpp
index bff59726e..5816d3a41 100644
--- a/modules/cuda_plugin/src/cuda_executable_network.cpp
+++ b/modules/nvidia_plugin/src/cuda_executable_network.cpp
@@ -30,7 +30,8 @@
 #include "transformations/utils/utils.hpp"
 #include "transformer/cuda_graph_transformer.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 using Time = std::chrono::steady_clock;
 
@@ -366,7 +367,7 @@ InferenceEngine::Parameter ExecutableNetwork::GetMetric(const std::string& name)
 std::shared_ptr<ngraph::Function> ExecutableNetwork::GetExecGraphInfo() { return function_; }
 
 void ExecutableNetwork::Export(std::ostream& modelStream) {
-    OV_ITT_SCOPED_TASK(itt::domains::CUDAPlugin, "ExecutableNetwork::Export");
+    OV_ITT_SCOPED_TASK(itt::domains::nvidia_gpu, "ExecutableNetwork::Export");
 
     // Note: custom ngraph extensions are not supported
     std::stringstream xmlFile, binFile;
@@ -393,4 +394,5 @@ void ExecutableNetwork::Export(std::ostream& modelStream) {
     // TODO: implement network precision, layout, preprocessing info serialization
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_executable_network.hpp b/modules/nvidia_plugin/src/cuda_executable_network.hpp
similarity index 97%
rename from modules/cuda_plugin/src/cuda_executable_network.hpp
rename to modules/nvidia_plugin/src/cuda_executable_network.hpp
index 85c2b0392..4d06c7b5e 100644
--- a/modules/cuda_plugin/src/cuda_executable_network.hpp
+++ b/modules/nvidia_plugin/src/cuda_executable_network.hpp
@@ -20,7 +20,8 @@
 
 class ExecNetworkTest;
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class Plugin;
 
@@ -92,4 +93,5 @@ class ExecutableNetwork : public InferenceEngine::ExecutableNetworkThreadSafeDef
     std::shared_ptr<MemoryPool> memory_pool_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_graph.cpp b/modules/nvidia_plugin/src/cuda_graph.cpp
similarity index 86%
rename from modules/cuda_plugin/src/cuda_graph.cpp
rename to modules/nvidia_plugin/src/cuda_graph.cpp
index 83afe045a..369e4d655 100644
--- a/modules/cuda_plugin/src/cuda_graph.cpp
+++ b/modules/nvidia_plugin/src/cuda_graph.cpp
@@ -4,7 +4,8 @@
 
 #include "cuda_graph.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 CudaGraph::CudaGraph(const CreationContext& context, const std::shared_ptr<const ngraph::Function>& function)
     : SubGraph(context, function) {}
@@ -15,4 +16,5 @@ void CudaGraph::Run(const InferenceRequestContext& context, const DeviceMemBlock
     SubGraph::Execute(context, {}, {}, workbuffers);
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_graph.hpp b/modules/nvidia_plugin/src/cuda_graph.hpp
similarity index 85%
rename from modules/cuda_plugin/src/cuda_graph.hpp
rename to modules/nvidia_plugin/src/cuda_graph.hpp
index e778d7956..73a8d27bf 100644
--- a/modules/cuda_plugin/src/cuda_graph.hpp
+++ b/modules/nvidia_plugin/src/cuda_graph.hpp
@@ -8,7 +8,8 @@
 
 class ExecNetworkTest;
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class CudaGraph final : public SubGraph {
 public:
@@ -20,4 +21,5 @@ class CudaGraph final : public SubGraph {
     void Run(const InferenceRequestContext& context, const DeviceMemBlock& memoryBlock) const;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_infer_request.cpp b/modules/nvidia_plugin/src/cuda_infer_request.cpp
similarity index 98%
rename from modules/cuda_plugin/src/cuda_infer_request.cpp
rename to modules/nvidia_plugin/src/cuda_infer_request.cpp
index c6355082b..8c5084b66 100644
--- a/modules/cuda_plugin/src/cuda_infer_request.cpp
+++ b/modules/nvidia_plugin/src/cuda_infer_request.cpp
@@ -28,7 +28,8 @@
 
 using namespace InferenceEngine;
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 using namespace utils;
 
 using Time = std::chrono::steady_clock;
@@ -163,7 +164,7 @@ void CudaInferRequest::createInferRequest() {
 }
 
 void CudaInferRequest::inferPreprocess() {
-    OV_ITT_SCOPED_TASK(itt::domains::CUDAPlugin, _profilingTask[Profiler::Preprocess]);
+    OV_ITT_SCOPED_TASK(itt::domains::nvidia_gpu, _profilingTask[Profiler::Preprocess]);
     cancellation_token_.Check();
     profiler_.StartStage();
     IInferRequestInternal::convertBatchedInputBlobs();
@@ -196,7 +197,7 @@ void CudaInferRequest::inferPreprocess() {
             for (size_t i = 0; i < blockDims.size(); i++) {
                 const size_t rev_idx = blockDims.size() - i - 1;
                 OPENVINO_ASSERT(order.at(rev_idx) == rev_idx,
-                                "CUDAPlugin: unsupported tensors with mixed axes order: ",
+                                "ov::nvidia_gpu: unsupported tensors with mixed axes order: ",
                                 ngraph::vector_to_string(order));
                 if (strides.at(rev_idx) != exp_stride || offsetPaddingToData.at(rev_idx) != 0) {
                     return false;
@@ -212,7 +213,7 @@ void CudaInferRequest::inferPreprocess() {
                 std::make_shared<ngraph::HostTensor>(parameterType, parameterShape, mem_blob->rmap().as<void*>());
         } else {
             OPENVINO_ASSERT(parameterType.bitwidth() % 8 == 0,
-                            "CUDAPlugin: Unsupported ROI tensor with element type having ",
+                            "ov::nvidia_gpu: Unsupported ROI tensor with element type having ",
                             std::to_string(parameterType.bitwidth()),
                             " bits size");
             // Perform manual extraction of ROI tensor
@@ -222,7 +223,7 @@ void CudaInferRequest::inferPreprocess() {
             auto desc = mem_blob->getTensorDesc();
             auto* src_data = mem_blob->rmap().as<uint8_t*>();
             auto dst_tensor = std::dynamic_pointer_cast<ngraph::runtime::HostTensor>(input_tensors_.at(index));
-            OPENVINO_ASSERT(dst_tensor, "CUDAPlugin error: Can't cast created tensor to HostTensor");
+            OPENVINO_ASSERT(dst_tensor, "nvidia_gpu error: Can't cast created tensor to HostTensor");
             auto* dst_data = dst_tensor->get_data_ptr<uint8_t>();
             std::vector<size_t> indexes(parameterShape.size());
             for (size_t dst_idx = 0; dst_idx < ov::shape_size(parameterShape); dst_idx++) {
@@ -266,7 +267,7 @@ void CudaInferRequest::inferPreprocess() {
 
 void CudaInferRequest::startPipeline(const ThreadContext& threadContext) {
     try {
-        OV_ITT_SCOPED_TASK(itt::domains::CUDAPlugin, _profilingTask[Profiler::StartPipeline])
+        OV_ITT_SCOPED_TASK(itt::domains::nvidia_gpu, _profilingTask[Profiler::StartPipeline])
         profiler_.StartStage();
         memory_proxy_ = _executableNetwork->memory_pool_->WaitAndGet(cancellation_token_);
         auto& memory = memory_proxy_->Get();
@@ -290,7 +291,7 @@ void CudaInferRequest::startPipeline(const ThreadContext& threadContext) {
 }
 
 void CudaInferRequest::waitPipeline(const ThreadContext& threadContext) {
-    OV_ITT_SCOPED_TASK(itt::domains::CUDAPlugin, _profilingTask[Profiler::WaitPipeline])
+    OV_ITT_SCOPED_TASK(itt::domains::nvidia_gpu, _profilingTask[Profiler::WaitPipeline])
     cancellation_token_.Check();
     profiler_.StartStage();
     // TODO: probably all time will be spent in synchonize, out of reach of ThrowIfCanceled
@@ -300,7 +301,7 @@ void CudaInferRequest::waitPipeline(const ThreadContext& threadContext) {
 }
 
 void CudaInferRequest::inferPostprocess() {
-    OV_ITT_SCOPED_TASK(itt::domains::CUDAPlugin, _profilingTask[Profiler::Postprocess]);
+    OV_ITT_SCOPED_TASK(itt::domains::nvidia_gpu, _profilingTask[Profiler::Postprocess]);
     cancellation_token_.Check();
     profiler_.StartStage();
     for (auto&& output : _outputs) {
@@ -731,4 +732,5 @@ void CudaInferRequest::convertPrecision(const Blob::Ptr& src, const Blob::Ptr& d
     }
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_infer_request.hpp b/modules/nvidia_plugin/src/cuda_infer_request.hpp
similarity index 98%
rename from modules/cuda_plugin/src/cuda_infer_request.hpp
rename to modules/nvidia_plugin/src/cuda_infer_request.hpp
index 63bbe1785..a185528e1 100644
--- a/modules/cuda_plugin/src/cuda_infer_request.hpp
+++ b/modules/nvidia_plugin/src/cuda_infer_request.hpp
@@ -25,7 +25,8 @@
 #include "memory_manager/cuda_memory_pool.hpp"
 #include "utils/perf_timing.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class ExecutableNetwork;
 
@@ -107,4 +108,5 @@ class CudaInferRequest : public InferenceEngine::IInferRequestInternal {
 };
 // ! [infer_request:header]
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_inference_request_context.hpp b/modules/nvidia_plugin/src/cuda_inference_request_context.hpp
similarity index 95%
rename from modules/cuda_plugin/src/cuda_inference_request_context.hpp
rename to modules/nvidia_plugin/src/cuda_inference_request_context.hpp
index 42484f289..2f535f9ae 100644
--- a/modules/cuda_plugin/src/cuda_inference_request_context.hpp
+++ b/modules/nvidia_plugin/src/cuda_inference_request_context.hpp
@@ -11,7 +11,8 @@
 #include "cancellation_token.hpp"
 #include "cuda_thread_context.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 using Blob = InferenceEngine::Blob;
 
@@ -81,7 +82,7 @@ class InferenceRequestContext {
         return outputs_mapping.find(output_name) != outputs_mapping.end();
     }
     const ThreadContext& getThreadContext() const noexcept { return threadContext; }
-    [[nodiscard]] CUDAPlugin::CancellationToken& getCancellationToken() const noexcept { return token; }
+    [[nodiscard]] ov::nvidia_gpu::CancellationToken& getCancellationToken() const noexcept { return token; }
     [[nodiscard]] Profiler& getProfiler() const noexcept { return profiler; }
     [[nodiscard]] bool isBenchmarkMode() const noexcept { return is_benchmark_mode_; }
 
@@ -96,4 +97,5 @@ class InferenceRequestContext {
     bool is_benchmark_mode_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_itt.hpp b/modules/nvidia_plugin/src/cuda_itt.hpp
similarity index 70%
rename from modules/cuda_plugin/src/cuda_itt.hpp
rename to modules/nvidia_plugin/src/cuda_itt.hpp
index c410dd2f7..ff6057e9c 100644
--- a/modules/cuda_plugin/src/cuda_itt.hpp
+++ b/modules/nvidia_plugin/src/cuda_itt.hpp
@@ -11,10 +11,12 @@
 
 #include <openvino/itt.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace itt {
 namespace domains {
-OV_ITT_DOMAIN(CUDAPlugin);
+OV_ITT_DOMAIN(nvidia_gpu);
 }
 }  // namespace itt
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_jthread.hpp b/modules/nvidia_plugin/src/cuda_jthread.hpp
similarity index 89%
rename from modules/cuda_plugin/src/cuda_jthread.hpp
rename to modules/nvidia_plugin/src/cuda_jthread.hpp
index c4aea167b..6c96aa2dc 100644
--- a/modules/cuda_plugin/src/cuda_jthread.hpp
+++ b/modules/nvidia_plugin/src/cuda_jthread.hpp
@@ -6,7 +6,8 @@
 
 #include <thread>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class CudaJThread final {
 public:
@@ -29,4 +30,5 @@ class CudaJThread final {
     std::thread thread_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_latch.hpp b/modules/nvidia_plugin/src/cuda_latch.hpp
similarity index 85%
rename from modules/cuda_plugin/src/cuda_latch.hpp
rename to modules/nvidia_plugin/src/cuda_latch.hpp
index 8309e007c..7636c78b7 100644
--- a/modules/cuda_plugin/src/cuda_latch.hpp
+++ b/modules/nvidia_plugin/src/cuda_latch.hpp
@@ -7,7 +7,8 @@
 #include <atomic>
 #include <future>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /// Temporary replacement for `std::latch` (until C++20)
 class CudaLatch final {
@@ -25,4 +26,5 @@ class CudaLatch final {
     std::promise<void> p_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_op_buffers_extractor.cpp b/modules/nvidia_plugin/src/cuda_op_buffers_extractor.cpp
similarity index 99%
rename from modules/cuda_plugin/src/cuda_op_buffers_extractor.cpp
rename to modules/nvidia_plugin/src/cuda_op_buffers_extractor.cpp
index 6b17b6b8c..5b912321f 100644
--- a/modules/cuda_plugin/src/cuda_op_buffers_extractor.cpp
+++ b/modules/nvidia_plugin/src/cuda_op_buffers_extractor.cpp
@@ -19,7 +19,8 @@
 #include <transformer/nodes/concat_optimized.hpp>
 #include <utility>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 OperationBuffersExtractor::OperationBuffersExtractor(gsl::span<const NodePtr> ordered_nodes,
                                                      bool is_stable_params,
@@ -344,4 +345,5 @@ void OperationBuffersExtractor::ThrowGraphIsBadFormedError(const ov::Input<ov::N
                     input.get_node()->get_name()));
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_op_buffers_extractor.hpp b/modules/nvidia_plugin/src/cuda_op_buffers_extractor.hpp
similarity index 99%
rename from modules/cuda_plugin/src/cuda_op_buffers_extractor.hpp
rename to modules/nvidia_plugin/src/cuda_op_buffers_extractor.hpp
index de54e7ad9..2e18cf7d5 100644
--- a/modules/cuda_plugin/src/cuda_op_buffers_extractor.hpp
+++ b/modules/nvidia_plugin/src/cuda_op_buffers_extractor.hpp
@@ -17,7 +17,8 @@
 
 #include "memory_manager/cuda_workbuffers.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * Extracts intermediate buffer ids from intermediate representation.
@@ -274,4 +275,5 @@ class OperationBuffersExtractor {
     const unsigned long num_ordered_nodes_ = 0;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_operation_base.cpp b/modules/nvidia_plugin/src/cuda_operation_base.cpp
similarity index 86%
rename from modules/cuda_plugin/src/cuda_operation_base.cpp
rename to modules/nvidia_plugin/src/cuda_operation_base.cpp
index 0a9af2c18..7025a8903 100644
--- a/modules/cuda_plugin/src/cuda_operation_base.cpp
+++ b/modules/nvidia_plugin/src/cuda_operation_base.cpp
@@ -7,7 +7,8 @@
 #include <ngraph/node.hpp>
 #include <utility>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 OperationBase::OperationBase(const CreationContext& /*context*/,
                              const ov::Node& node,
@@ -18,4 +19,5 @@ OperationBase::OperationBase(const CreationContext& /*context*/,
       input_ids_{move(inputIds)},
       output_ids_{move(outputIds)} {}
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_operation_base.hpp b/modules/nvidia_plugin/src/cuda_operation_base.hpp
similarity index 98%
rename from modules/cuda_plugin/src/cuda_operation_base.hpp
rename to modules/nvidia_plugin/src/cuda_operation_base.hpp
index 52f088a29..90e9e0a53 100644
--- a/modules/cuda_plugin/src/cuda_operation_base.hpp
+++ b/modules/nvidia_plugin/src/cuda_operation_base.hpp
@@ -24,7 +24,8 @@ class Node;
 
 }
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 template <typename T>
 using DevicePointer = CUDA::DevicePointer<T>;
@@ -128,4 +129,5 @@ template <class ConcreteOperator>
 ConcreteOperator& downcast(const std::shared_ptr<ov::Node>& node) {
     return dynamic_cast<ConcreteOperator&>(*node.get());
 }
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_operation_registry.cpp b/modules/nvidia_plugin/src/cuda_operation_registry.cpp
similarity index 96%
rename from modules/cuda_plugin/src/cuda_operation_registry.cpp
rename to modules/nvidia_plugin/src/cuda_operation_registry.cpp
index 528c0bc29..dcb5c2a49 100644
--- a/modules/cuda_plugin/src/cuda_operation_registry.cpp
+++ b/modules/nvidia_plugin/src/cuda_operation_registry.cpp
@@ -6,7 +6,8 @@
 
 #include <ngraph/node.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 OperationRegistry& OperationRegistry::getInstance() {
     static OperationRegistry registry;
@@ -49,4 +50,5 @@ OperationBase::Ptr OperationRegistry::createOperation(const CreationContext& con
     return createOperation(context, node, toVector(inIds), toVector(outIds));
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_operation_registry.hpp b/modules/nvidia_plugin/src/cuda_operation_registry.hpp
similarity index 94%
rename from modules/cuda_plugin/src/cuda_operation_registry.hpp
rename to modules/nvidia_plugin/src/cuda_operation_registry.hpp
index a16b75532..83d5b7495 100644
--- a/modules/cuda_plugin/src/cuda_operation_registry.hpp
+++ b/modules/nvidia_plugin/src/cuda_operation_registry.hpp
@@ -11,7 +11,8 @@
 
 #include "cuda_operation_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 namespace details {
 
@@ -114,7 +115,8 @@ class OperationRegistry::Register<OperationBase> {
     }
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
 
 /**
  * @macro OPERATION_REGISTER
@@ -129,11 +131,11 @@ class OperationRegistry::Register<OperationBase> {
  */
 #define OPERATION_REGISTER(type, name)                                                                              \
     extern "C" {                                                                                                    \
-    [[maybe_unused]] const ::CUDAPlugin::OperationRegistry::Register<type> openvino_cuda_op_register_##name{#name}; \
+    [[maybe_unused]] const ::ov::nvidia_gpu::OperationRegistry::Register<type> openvino_cuda_op_register_##name{#name}; \
     }
 
 #define OPERATION_REGISTER_FACTORY(factory, name)                                                                     \
     extern "C" {                                                                                                      \
-    [[maybe_unused]] const ::CUDAPlugin::OperationRegistry::Register<OperationBase> openvino_cuda_op_register_##name{ \
+    [[maybe_unused]] const ::ov::nvidia_gpu::OperationRegistry::Register<OperationBase> openvino_cuda_op_register_##name{ \
         #name, factory};                                                                                              \
     }
diff --git a/modules/cuda_plugin/src/cuda_plugin.cpp b/modules/nvidia_plugin/src/cuda_plugin.cpp
similarity index 97%
rename from modules/cuda_plugin/src/cuda_plugin.cpp
rename to modules/nvidia_plugin/src/cuda_plugin.cpp
index c221390f2..1de6f4421 100644
--- a/modules/cuda_plugin/src/cuda_plugin.cpp
+++ b/modules/nvidia_plugin/src/cuda_plugin.cpp
@@ -24,9 +24,9 @@
 #include "cuda_operation_registry.hpp"
 #include "cuda_plugin.hpp"
 #include "openvino/runtime/properties.hpp"
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 
-Plugin::Plugin() { _pluginName = "CUDA"; }
+Plugin::Plugin() { _pluginName = "NVIDIA"; }
 
 Plugin::~Plugin() {
     // Plugin should remove executors from executor cache to avoid threads number growth in the whole application
@@ -37,7 +37,7 @@ Plugin::~Plugin() {
 
 InferenceEngine::IExecutableNetworkInternal::Ptr Plugin::LoadExeNetworkImpl(const InferenceEngine::CNNNetwork& network,
                                                                             const ConfigMap& config) {
-    OV_ITT_SCOPED_TASK(itt::domains::CUDAPlugin, "Plugin::LoadExeNetworkImpl");
+    OV_ITT_SCOPED_TASK(itt::domains::nvidia_gpu, "Plugin::LoadExeNetworkImpl");
 
     auto cfg = Configuration{config, _cfg};
     InferenceEngine::InputsDataMap networkInputs = network.getInputsInfo();
@@ -96,7 +96,7 @@ InferenceEngine::ITaskExecutor::Ptr Plugin::GetStreamExecutor(const Configuratio
 
 InferenceEngine::IExecutableNetworkInternal::Ptr Plugin::ImportNetwork(
     std::istream& model, const std::map<std::string, std::string>& config) {
-    OV_ITT_SCOPED_TASK(itt::domains::CUDAPlugin, "CUDAPlugin::ImportNetworkImpl");
+    OV_ITT_SCOPED_TASK(itt::domains::nvidia_gpu, "ov::nvidia_gpu::ImportNetworkImpl");
 
     Configuration cfg{config, _cfg};
     auto waitExecutor = GetStreamExecutor(cfg);
@@ -108,7 +108,7 @@ InferenceEngine::IExecutableNetworkInternal::Ptr Plugin::ImportNetwork(
 
 InferenceEngine::QueryNetworkResult Plugin::QueryNetwork(const InferenceEngine::CNNNetwork& network,
                                                          const ConfigMap& config) const {
-    OV_ITT_SCOPED_TASK(itt::domains::CUDAPlugin, "CUDAPlugin::QueryNetwork");
+    OV_ITT_SCOPED_TASK(itt::domains::nvidia_gpu, "ov::nvidia_gpu::QueryNetwork");
 
     InferenceEngine::QueryNetworkResult res;
     Configuration cfg{config, _cfg, false};
diff --git a/modules/cuda_plugin/src/cuda_plugin.hpp b/modules/nvidia_plugin/src/cuda_plugin.hpp
similarity index 96%
rename from modules/cuda_plugin/src/cuda_plugin.hpp
rename to modules/nvidia_plugin/src/cuda_plugin.hpp
index 1a5279af9..d4ff80fc4 100644
--- a/modules/cuda_plugin/src/cuda_plugin.hpp
+++ b/modules/nvidia_plugin/src/cuda_plugin.hpp
@@ -11,7 +11,8 @@
 #include "cuda_thread_pool.hpp"
 #include "transformer/cuda_graph_transformer.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class Plugin : public InferenceEngine::IInferencePlugin {
 public:
@@ -63,4 +64,5 @@ class Plugin : public InferenceEngine::IInferencePlugin {
 template <>
 std::string Plugin::getCudaAttribute<Plugin::cuda_attribute::name, std::string>() const;
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_plugin_host.cpp b/modules/nvidia_plugin/src/cuda_plugin_host.cpp
similarity index 78%
rename from modules/cuda_plugin/src/cuda_plugin_host.cpp
rename to modules/nvidia_plugin/src/cuda_plugin_host.cpp
index e4b63f50d..81d65ab93 100644
--- a/modules/cuda_plugin/src/cuda_plugin_host.cpp
+++ b/modules/nvidia_plugin/src/cuda_plugin_host.cpp
@@ -6,9 +6,11 @@
 
 #include "cuda_plugin.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 template <>
 std::string Plugin::getCudaAttribute<Plugin::cuda_attribute::name, std::string>() const {
     return CUDA::Device{cudaDeviceID()}.props().name;
 }
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_profiler.cpp b/modules/nvidia_plugin/src/cuda_profiler.cpp
similarity index 98%
rename from modules/cuda_plugin/src/cuda_profiler.cpp
rename to modules/nvidia_plugin/src/cuda_profiler.cpp
index a33fa90fb..f5e28f866 100644
--- a/modules/cuda_plugin/src/cuda_profiler.cpp
+++ b/modules/nvidia_plugin/src/cuda_profiler.cpp
@@ -7,7 +7,8 @@
 #include <ops/parameter.hpp>
 #include <ops/result.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 namespace {
 
@@ -142,4 +143,5 @@ void Profiler::CollectNodeVisitor(const OperationBase::Ptr& execStep,
     }
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_profiler.hpp b/modules/nvidia_plugin/src/cuda_profiler.hpp
similarity index 98%
rename from modules/cuda_plugin/src/cuda_profiler.hpp
rename to modules/nvidia_plugin/src/cuda_profiler.hpp
index 5b8f5f3ad..83cc162ce 100644
--- a/modules/cuda_plugin/src/cuda_profiler.hpp
+++ b/modules/nvidia_plugin/src/cuda_profiler.hpp
@@ -13,7 +13,8 @@
 #include "cuda_graph.hpp"
 #include "cuda_operation_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * Creates profiler sequence and stores profiler results.
@@ -205,4 +206,5 @@ class Profiler::ProfilerSequence {
     const size_t index_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_thread_context.hpp b/modules/nvidia_plugin/src/cuda_thread_context.hpp
similarity index 91%
rename from modules/cuda_plugin/src/cuda_thread_context.hpp
rename to modules/nvidia_plugin/src/cuda_thread_context.hpp
index d86f19b01..da5d9c55b 100644
--- a/modules/cuda_plugin/src/cuda_thread_context.hpp
+++ b/modules/nvidia_plugin/src/cuda_thread_context.hpp
@@ -8,7 +8,8 @@
 #include "cuda/dnn.hpp"
 #include "cuda/tensor.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class ThreadContext {
     CUDA::Device device_;
@@ -29,4 +30,5 @@ class ThreadContext {
     const CUDA::CuTensorHandle& cuTensorHandle() const noexcept { return cuTensorHandle_; }
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_thread_pool.cpp b/modules/nvidia_plugin/src/cuda_thread_pool.cpp
similarity index 96%
rename from modules/cuda_plugin/src/cuda_thread_pool.cpp
rename to modules/nvidia_plugin/src/cuda_thread_pool.cpp
index c8d7a9f0f..e63bed32c 100644
--- a/modules/cuda_plugin/src/cuda_thread_pool.cpp
+++ b/modules/nvidia_plugin/src/cuda_thread_pool.cpp
@@ -10,7 +10,8 @@
 
 #include "cuda_latch.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 static thread_local ThreadContext* contextPtr = nullptr;
 
@@ -76,4 +77,5 @@ void CudaThreadPool::run(Task task) {
     queue_cond_var_.notify_one();
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/cuda_thread_pool.hpp b/modules/nvidia_plugin/src/cuda_thread_pool.hpp
similarity index 90%
rename from modules/cuda_plugin/src/cuda_thread_pool.hpp
rename to modules/nvidia_plugin/src/cuda_thread_pool.hpp
index 3f9d279ec..b1c90a5af 100644
--- a/modules/cuda_plugin/src/cuda_thread_pool.hpp
+++ b/modules/nvidia_plugin/src/cuda_thread_pool.hpp
@@ -15,7 +15,8 @@
 
 #include "cuda_jthread.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class CudaThreadPool : public InferenceEngine::ITaskExecutor {
 public:
@@ -36,4 +37,5 @@ class CudaThreadPool : public InferenceEngine::ITaskExecutor {
     std::vector<CudaJThread> threads_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/error.cpp b/modules/nvidia_plugin/src/error.cpp
similarity index 93%
rename from modules/cuda_plugin/src/error.cpp
rename to modules/nvidia_plugin/src/error.cpp
index d1774120f..9755a50c7 100644
--- a/modules/cuda_plugin/src/error.cpp
+++ b/modules/nvidia_plugin/src/error.cpp
@@ -8,7 +8,8 @@
 
 #include <details/ie_exception.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace {
 template <typename T>
 [[gnu::cold, noreturn]] void throwException(const std::string& msg,
@@ -34,4 +35,5 @@ template <typename T>
 [[gnu::cold]] void logError(const std::string& /*msg*/, const std::experimental::source_location& /*location*/) {
 }  // TODO: log somewhere
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/error.hpp b/modules/nvidia_plugin/src/error.hpp
similarity index 91%
rename from modules/cuda_plugin/src/error.hpp
rename to modules/nvidia_plugin/src/error.hpp
index f0df715a6..11c799ac2 100644
--- a/modules/cuda_plugin/src/error.hpp
+++ b/modules/nvidia_plugin/src/error.hpp
@@ -7,7 +7,8 @@
 
 #include "kernels/error.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 [[gnu::cold, noreturn]] void throwIEException(
     const std::string& msg,
     const std::experimental::source_location& location = std::experimental::source_location::current());
@@ -20,4 +21,5 @@ namespace CUDAPlugin {
 [[gnu::cold]] void logError(
     const std::string& msg,
     const std::experimental::source_location& location = std::experimental::source_location::current());
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/add.cu b/modules/nvidia_plugin/src/kernels/add.cu
similarity index 90%
rename from modules/cuda_plugin/src/kernels/add.cu
rename to modules/nvidia_plugin/src/kernels/add.cu
index a02772e5d..90f424747 100644
--- a/modules/cuda_plugin/src/kernels/add.cu
+++ b/modules/nvidia_plugin/src/kernels/add.cu
@@ -4,7 +4,8 @@
 
 #include "add.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -25,4 +26,5 @@ void Add::operator()(cudaStream_t stream,
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/add.hpp b/modules/nvidia_plugin/src/kernels/add.hpp
similarity index 90%
rename from modules/cuda_plugin/src/kernels/add.hpp
rename to modules/nvidia_plugin/src/kernels/add.hpp
index c4e58f5bc..9feb94d5b 100644
--- a/modules/cuda_plugin/src/kernels/add.hpp
+++ b/modules/nvidia_plugin/src/kernels/add.hpp
@@ -6,7 +6,8 @@
 
 #include "elementwise_binary.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -32,4 +33,5 @@ class Add {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/broadcast.cu b/modules/nvidia_plugin/src/kernels/broadcast.cu
similarity index 89%
rename from modules/cuda_plugin/src/kernels/broadcast.cu
rename to modules/nvidia_plugin/src/kernels/broadcast.cu
index b25fa5b2c..de053fa5c 100644
--- a/modules/cuda_plugin/src/kernels/broadcast.cu
+++ b/modules/nvidia_plugin/src/kernels/broadcast.cu
@@ -7,7 +7,8 @@
 #include "broadcast.hpp"
 #include "tensor_helpers.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -20,7 +21,7 @@ static __global__ void broadcast(const T* src, NumpyBroadcastMapper src_mapper,
     dst[dst_idx] = src[src_idx];
 }
 
-Broadcast::Broadcast(CUDAPlugin::kernel::Type_t element_type, size_t dst_num_elements, size_t max_threads_per_block)
+Broadcast::Broadcast(ov::nvidia_gpu::kernel::Type_t element_type, size_t dst_num_elements, size_t max_threads_per_block)
     : element_type_{element_type}, dst_num_elements_{dst_num_elements} {
     std::tie(num_blocks_, threads_per_block_) = calculateElementwiseGrid(dst_num_elements_, max_threads_per_block);
 }
@@ -47,4 +48,5 @@ void Broadcast::default_(T t, cudaStream_t, const void*, const NumpyBroadcastMap
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/broadcast.hpp b/modules/nvidia_plugin/src/kernels/broadcast.hpp
similarity index 82%
rename from modules/cuda_plugin/src/kernels/broadcast.hpp
rename to modules/nvidia_plugin/src/kernels/broadcast.hpp
index 08177e34d..d09634aa6 100644
--- a/modules/cuda_plugin/src/kernels/broadcast.hpp
+++ b/modules/nvidia_plugin/src/kernels/broadcast.hpp
@@ -11,12 +11,13 @@
 #include "error.hpp"
 #include "numpy_broadcast_mapper.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class Broadcast {
 public:
-    Broadcast(CUDAPlugin::kernel::Type_t element_type, size_t dst_num_elements, size_t max_threads_per_block);
+    Broadcast(ov::nvidia_gpu::kernel::Type_t element_type, size_t dst_num_elements, size_t max_threads_per_block);
 
     void operator()(const cudaStream_t stream,
                     const void* src,
@@ -40,4 +41,5 @@ class Broadcast {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/clamp.cu b/modules/nvidia_plugin/src/kernels/clamp.cu
similarity index 94%
rename from modules/cuda_plugin/src/kernels/clamp.cu
rename to modules/nvidia_plugin/src/kernels/clamp.cu
index db1d9c543..3a8701a40 100644
--- a/modules/cuda_plugin/src/kernels/clamp.cu
+++ b/modules/nvidia_plugin/src/kernels/clamp.cu
@@ -8,7 +8,8 @@
 #include "error.hpp"
 #include "tensor_helpers.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 namespace cumath = CUDA::math;
@@ -48,4 +49,5 @@ void Clamp::operator()(cudaStream_t stream, const void* in, void* out) const {
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/clamp.hpp b/modules/nvidia_plugin/src/kernels/clamp.hpp
similarity index 89%
rename from modules/cuda_plugin/src/kernels/clamp.hpp
rename to modules/nvidia_plugin/src/kernels/clamp.hpp
index 2b90e7959..b1d8b9aed 100644
--- a/modules/cuda_plugin/src/kernels/clamp.hpp
+++ b/modules/nvidia_plugin/src/kernels/clamp.hpp
@@ -7,7 +7,8 @@
 #include "cuda_type_traits.hpp"
 #include "elementwise_unary.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -31,4 +32,5 @@ class Clamp {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/comparison.cu b/modules/nvidia_plugin/src/kernels/comparison.cu
similarity index 98%
rename from modules/cuda_plugin/src/kernels/comparison.cu
rename to modules/nvidia_plugin/src/kernels/comparison.cu
index 1ada3129e..bbfd9a67f 100644
--- a/modules/cuda_plugin/src/kernels/comparison.cu
+++ b/modules/nvidia_plugin/src/kernels/comparison.cu
@@ -8,7 +8,8 @@
 
 #include "comparison.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T, typename OP>
@@ -159,4 +160,5 @@ void Comparison::Call(const cudaStream_t stream,
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/comparison.hpp b/modules/nvidia_plugin/src/kernels/comparison.hpp
similarity index 95%
rename from modules/cuda_plugin/src/kernels/comparison.hpp
rename to modules/nvidia_plugin/src/kernels/comparison.hpp
index 2c0e4c8eb..f7bc9a90d 100644
--- a/modules/cuda_plugin/src/kernels/comparison.hpp
+++ b/modules/nvidia_plugin/src/kernels/comparison.hpp
@@ -7,7 +7,8 @@
 #include "cuda_type_traits.hpp"
 #include "error.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class Comparison {
@@ -53,4 +54,5 @@ class Comparison {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/concat.cu b/modules/nvidia_plugin/src/kernels/concat.cu
similarity index 97%
rename from modules/cuda_plugin/src/kernels/concat.cu
rename to modules/nvidia_plugin/src/kernels/concat.cu
index 93cd117d0..4e7081ef3 100644
--- a/modules/cuda_plugin/src/kernels/concat.cu
+++ b/modules/nvidia_plugin/src/kernels/concat.cu
@@ -9,7 +9,8 @@
 
 #include "concat.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -91,4 +92,5 @@ void Concat::Call(const cudaStream_t stream, const void* chunks, const void* con
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/concat.hpp b/modules/nvidia_plugin/src/kernels/concat.hpp
similarity index 94%
rename from modules/cuda_plugin/src/kernels/concat.hpp
rename to modules/nvidia_plugin/src/kernels/concat.hpp
index 17c2d0dc9..5b69d9aca 100644
--- a/modules/cuda_plugin/src/kernels/concat.hpp
+++ b/modules/nvidia_plugin/src/kernels/concat.hpp
@@ -9,7 +9,8 @@
 #include "cuda_type_traits.hpp"
 #include "error.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class Concat {
@@ -49,4 +50,5 @@ class Concat {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/convert.cu b/modules/nvidia_plugin/src/kernels/convert.cu
similarity index 92%
rename from modules/cuda_plugin/src/kernels/convert.cu
rename to modules/nvidia_plugin/src/kernels/convert.cu
index 7891a774f..424cb04b5 100644
--- a/modules/cuda_plugin/src/kernels/convert.cu
+++ b/modules/nvidia_plugin/src/kernels/convert.cu
@@ -7,7 +7,8 @@
 #include "error.hpp"
 #include "typed_functor.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename TOutput, typename TInput>
@@ -42,7 +43,7 @@ struct ConvertFunctor<TOutput, TInput, typename std::enable_if<!std::is_same<TOu
                          const void* input,
                          unsigned numBlocks,
                          unsigned threadsPerBlock) {
-        CUDAPlugin::kernel::convert_impl<TOutput, TInput><<<numBlocks, threadsPerBlock, 0, stream>>>(
+        ov::nvidia_gpu::kernel::convert_impl<TOutput, TInput><<<numBlocks, threadsPerBlock, 0, stream>>>(
             size, static_cast<TOutput*>(output), static_cast<const TInput*>(input));
     }
 };
@@ -59,4 +60,5 @@ void Convert::operator()(cudaStream_t stream, void* output, const void* src) con
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/convert.cuh b/modules/nvidia_plugin/src/kernels/convert.cuh
similarity index 94%
rename from modules/cuda_plugin/src/kernels/convert.cuh
rename to modules/nvidia_plugin/src/kernels/convert.cuh
index 3cf9d5860..2139a4eba 100644
--- a/modules/cuda_plugin/src/kernels/convert.cuh
+++ b/modules/nvidia_plugin/src/kernels/convert.cuh
@@ -8,7 +8,8 @@
 
 #include "cuda_type_traits.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 #ifdef CUDA_HAS_BF16_TYPE
@@ -42,4 +43,5 @@ __device__ typename std::enable_if<!(std::is_same<TInput, __half>::value || std:
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/convert.hpp b/modules/nvidia_plugin/src/kernels/convert.hpp
similarity index 89%
rename from modules/cuda_plugin/src/kernels/convert.hpp
rename to modules/nvidia_plugin/src/kernels/convert.hpp
index e973fe407..1684fe1f1 100644
--- a/modules/cuda_plugin/src/kernels/convert.hpp
+++ b/modules/nvidia_plugin/src/kernels/convert.hpp
@@ -6,7 +6,8 @@
 
 #include "cuda_type_traits.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class Convert {
@@ -27,4 +28,5 @@ class Convert {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/convert_color.hpp b/modules/nvidia_plugin/src/kernels/convert_color.hpp
similarity index 92%
rename from modules/cuda_plugin/src/kernels/convert_color.hpp
rename to modules/nvidia_plugin/src/kernels/convert_color.hpp
index 1c3dfedee..9c4d44725 100644
--- a/modules/cuda_plugin/src/kernels/convert_color.hpp
+++ b/modules/nvidia_plugin/src/kernels/convert_color.hpp
@@ -10,7 +10,8 @@
 #endif
 #include <cuda/float16.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 enum class ColorConversion { RGB, BGR };
@@ -37,4 +38,5 @@ __device__ void yuv_pixel_to_rgb(const float y_val, const float u_val, const flo
 #endif
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/convert_color_i420.cu b/modules/nvidia_plugin/src/kernels/convert_color_i420.cu
similarity index 98%
rename from modules/cuda_plugin/src/kernels/convert_color_i420.cu
rename to modules/nvidia_plugin/src/kernels/convert_color_i420.cu
index b34960555..744674e28 100644
--- a/modules/cuda_plugin/src/kernels/convert_color_i420.cu
+++ b/modules/nvidia_plugin/src/kernels/convert_color_i420.cu
@@ -12,7 +12,8 @@
 #include "error.hpp"
 #include "tensor_helpers.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <ColorConversion ColorFormat, typename T>
@@ -134,4 +135,5 @@ template class I420ColorConvert<ColorConversion::RGB>;
 template class I420ColorConvert<ColorConversion::BGR>;
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/convert_color_i420.hpp b/modules/nvidia_plugin/src/kernels/convert_color_i420.hpp
similarity index 95%
rename from modules/cuda_plugin/src/kernels/convert_color_i420.hpp
rename to modules/nvidia_plugin/src/kernels/convert_color_i420.hpp
index 13736d549..c67c83f5e 100644
--- a/modules/cuda_plugin/src/kernels/convert_color_i420.hpp
+++ b/modules/nvidia_plugin/src/kernels/convert_color_i420.hpp
@@ -10,7 +10,8 @@
 #include "cuda_type_traits.hpp"
 #include "elementtypeswitch.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <ColorConversion Conversion>
@@ -57,4 +58,5 @@ class I420ColorConvert {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/convert_color_nv12.cu b/modules/nvidia_plugin/src/kernels/convert_color_nv12.cu
similarity index 98%
rename from modules/cuda_plugin/src/kernels/convert_color_nv12.cu
rename to modules/nvidia_plugin/src/kernels/convert_color_nv12.cu
index 9e308813a..193a2e63b 100644
--- a/modules/cuda_plugin/src/kernels/convert_color_nv12.cu
+++ b/modules/nvidia_plugin/src/kernels/convert_color_nv12.cu
@@ -12,7 +12,8 @@
 #include "error.hpp"
 #include "tensor_helpers.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <ColorConversion ColorFormat, typename T>
@@ -131,4 +132,5 @@ template class NV12ColorConvert<ColorConversion::RGB>;
 template class NV12ColorConvert<ColorConversion::BGR>;
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/convert_color_nv12.hpp b/modules/nvidia_plugin/src/kernels/convert_color_nv12.hpp
similarity index 95%
rename from modules/cuda_plugin/src/kernels/convert_color_nv12.hpp
rename to modules/nvidia_plugin/src/kernels/convert_color_nv12.hpp
index 3ec424962..2359c0d1f 100644
--- a/modules/cuda_plugin/src/kernels/convert_color_nv12.hpp
+++ b/modules/nvidia_plugin/src/kernels/convert_color_nv12.hpp
@@ -10,7 +10,8 @@
 #include "cuda_type_traits.hpp"
 #include "elementtypeswitch.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <ColorConversion Conversion>
@@ -57,4 +58,5 @@ class NV12ColorConvert {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/cuda_type_traits.hpp b/modules/nvidia_plugin/src/kernels/cuda_type_traits.hpp
similarity index 96%
rename from modules/cuda_plugin/src/kernels/cuda_type_traits.hpp
rename to modules/nvidia_plugin/src/kernels/cuda_type_traits.hpp
index 18c93b39b..c9877b122 100644
--- a/modules/cuda_plugin/src/kernels/cuda_type_traits.hpp
+++ b/modules/nvidia_plugin/src/kernels/cuda_type_traits.hpp
@@ -7,7 +7,8 @@
 #include <cstdint>
 #include <cuda/float16.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 enum class Type_t : int {
@@ -127,4 +128,5 @@ struct cuda_type_traits<Type_t::u64> {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/detection_output.cu b/modules/nvidia_plugin/src/kernels/detection_output.cu
similarity index 99%
rename from modules/cuda_plugin/src/kernels/detection_output.cu
rename to modules/nvidia_plugin/src/kernels/detection_output.cu
index 8f47e3fb0..6aa2ac51a 100644
--- a/modules/cuda_plugin/src/kernels/detection_output.cu
+++ b/modules/nvidia_plugin/src/kernels/detection_output.cu
@@ -17,7 +17,8 @@
 #include "detection_output.hpp"
 #include "error.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 namespace cumath = CUDA::math;
@@ -1222,4 +1223,5 @@ void DetectionOutput::call(const CUDA::Stream& stream,
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/detection_output.hpp b/modules/nvidia_plugin/src/kernels/detection_output.hpp
similarity index 97%
rename from modules/cuda_plugin/src/kernels/detection_output.hpp
rename to modules/nvidia_plugin/src/kernels/detection_output.hpp
index 3b07e950f..d0a4f1424 100644
--- a/modules/cuda_plugin/src/kernels/detection_output.hpp
+++ b/modules/nvidia_plugin/src/kernels/detection_output.hpp
@@ -13,7 +13,8 @@
 #include "cuda_type_traits.hpp"
 #include "tensor_helpers.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename TDataType>
@@ -130,4 +131,5 @@ class DetectionOutput {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/divide.cu b/modules/nvidia_plugin/src/kernels/divide.cu
similarity index 97%
rename from modules/cuda_plugin/src/kernels/divide.cu
rename to modules/nvidia_plugin/src/kernels/divide.cu
index 801b0f044..d31e8f9bb 100644
--- a/modules/cuda_plugin/src/kernels/divide.cu
+++ b/modules/nvidia_plugin/src/kernels/divide.cu
@@ -8,7 +8,8 @@
 
 #include "divide.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 namespace {
@@ -87,4 +88,5 @@ void PythonDivide::operator()(cudaStream_t stream,
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/divide.hpp b/modules/nvidia_plugin/src/kernels/divide.hpp
similarity index 94%
rename from modules/cuda_plugin/src/kernels/divide.hpp
rename to modules/nvidia_plugin/src/kernels/divide.hpp
index 63e7d80e4..8b07bfee8 100644
--- a/modules/cuda_plugin/src/kernels/divide.hpp
+++ b/modules/nvidia_plugin/src/kernels/divide.hpp
@@ -7,7 +7,8 @@
 #include "cuda_type_traits.hpp"
 #include "elementwise_binary.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -55,4 +56,5 @@ class PythonDivide {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/elementtypeswitch.hpp b/modules/nvidia_plugin/src/kernels/elementtypeswitch.hpp
similarity index 96%
rename from modules/cuda_plugin/src/kernels/elementtypeswitch.hpp
rename to modules/nvidia_plugin/src/kernels/elementtypeswitch.hpp
index c046dcc70..2553a4e9a 100644
--- a/modules/cuda_plugin/src/kernels/elementtypeswitch.hpp
+++ b/modules/nvidia_plugin/src/kernels/elementtypeswitch.hpp
@@ -9,7 +9,8 @@
 #include "cuda_type_traits.hpp"
 #include "switch.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <Type_t... Types>
@@ -51,4 +52,5 @@ using AllElementTypesSwitch = ElementTypesSwitch<Type_t::boolean,
                                                  Type_t::u64>;
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/elementwise_binary.cuh b/modules/nvidia_plugin/src/kernels/elementwise_binary.cuh
similarity index 98%
rename from modules/cuda_plugin/src/kernels/elementwise_binary.cuh
rename to modules/nvidia_plugin/src/kernels/elementwise_binary.cuh
index b9078c66f..4095232a8 100644
--- a/modules/cuda_plugin/src/kernels/elementwise_binary.cuh
+++ b/modules/nvidia_plugin/src/kernels/elementwise_binary.cuh
@@ -16,7 +16,8 @@
 #include "numpy_broadcast_mapper.cuh"
 #include "tensor_helpers.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 #ifdef __CUDACC__
@@ -140,4 +141,5 @@ private:
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/elementwise_unary.cuh b/modules/nvidia_plugin/src/kernels/elementwise_unary.cuh
similarity index 96%
rename from modules/cuda_plugin/src/kernels/elementwise_unary.cuh
rename to modules/nvidia_plugin/src/kernels/elementwise_unary.cuh
index 565408d4b..3a2c37142 100644
--- a/modules/cuda_plugin/src/kernels/elementwise_unary.cuh
+++ b/modules/nvidia_plugin/src/kernels/elementwise_unary.cuh
@@ -18,7 +18,8 @@
 #include "cuda/math.cuh"
 #endif  // __CUDACC__
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 #ifdef __CUDACC__
@@ -75,4 +76,5 @@ private:
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/eltwise.cuh b/modules/nvidia_plugin/src/kernels/eltwise.cuh
similarity index 97%
rename from modules/cuda_plugin/src/kernels/eltwise.cuh
rename to modules/nvidia_plugin/src/kernels/eltwise.cuh
index fecc8820b..bd3eb8267 100644
--- a/modules/cuda_plugin/src/kernels/eltwise.cuh
+++ b/modules/nvidia_plugin/src/kernels/eltwise.cuh
@@ -9,7 +9,8 @@
 #include <ngraph/shape.hpp>
 #endif
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 namespace eltwise {
 
@@ -129,4 +130,5 @@ __device__ int index_in_dim<5>(int dim, const std::size_t shape[5], unsigned ele
 #endif
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/error.cpp b/modules/nvidia_plugin/src/kernels/error.cpp
similarity index 92%
rename from modules/cuda_plugin/src/kernels/error.cpp
rename to modules/nvidia_plugin/src/kernels/error.cpp
index 6e3d24df2..ee45c40f9 100644
--- a/modules/cuda_plugin/src/kernels/error.cpp
+++ b/modules/nvidia_plugin/src/kernels/error.cpp
@@ -8,7 +8,8 @@
 #include <exception>
 #include <kernels/error.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class Error : public std::exception {
@@ -34,4 +35,5 @@ class Error : public std::exception {
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/error.hpp b/modules/nvidia_plugin/src/kernels/error.hpp
similarity index 92%
rename from modules/cuda_plugin/src/kernels/error.hpp
rename to modules/nvidia_plugin/src/kernels/error.hpp
index 31fe1a6ba..5e46c3707 100644
--- a/modules/cuda_plugin/src/kernels/error.hpp
+++ b/modules/nvidia_plugin/src/kernels/error.hpp
@@ -22,7 +22,8 @@ struct source_location {
 #endif
 #include <cuda_runtime.h>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 [[gnu::cold]] void throwIfError(
     cudaError_t err,
@@ -33,4 +34,5 @@ namespace kernel {
     const std::experimental::source_location& location = std::experimental::source_location::current());
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/fake_quantize.cu b/modules/nvidia_plugin/src/kernels/fake_quantize.cu
similarity index 98%
rename from modules/cuda_plugin/src/kernels/fake_quantize.cu
rename to modules/nvidia_plugin/src/kernels/fake_quantize.cu
index b55316fc8..884d0ceb0 100644
--- a/modules/cuda_plugin/src/kernels/fake_quantize.cu
+++ b/modules/nvidia_plugin/src/kernels/fake_quantize.cu
@@ -11,7 +11,8 @@
 #include "fake_quantize.hpp"
 #include "tensor_helpers.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -156,4 +157,5 @@ void FakeQuantize::Call(const cudaStream_t stream,
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/fake_quantize.hpp b/modules/nvidia_plugin/src/kernels/fake_quantize.hpp
similarity index 95%
rename from modules/cuda_plugin/src/kernels/fake_quantize.hpp
rename to modules/nvidia_plugin/src/kernels/fake_quantize.hpp
index de3eebe8f..5c82f7bd4 100644
--- a/modules/cuda_plugin/src/kernels/fake_quantize.hpp
+++ b/modules/nvidia_plugin/src/kernels/fake_quantize.hpp
@@ -9,7 +9,8 @@
 #include "cuda_type_traits.hpp"
 #include "numpy_broadcast_mapper.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class FakeQuantize {
@@ -53,4 +54,5 @@ class FakeQuantize {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/floor.cu b/modules/nvidia_plugin/src/kernels/floor.cu
similarity index 86%
rename from modules/cuda_plugin/src/kernels/floor.cu
rename to modules/nvidia_plugin/src/kernels/floor.cu
index 063060b42..d93a3a7ec 100644
--- a/modules/cuda_plugin/src/kernels/floor.cu
+++ b/modules/nvidia_plugin/src/kernels/floor.cu
@@ -6,7 +6,8 @@
 
 #include "floor.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -20,4 +21,5 @@ Floor::Floor(Type_t element_type, size_t max_threads_per_block, size_t num_eleme
 void Floor::operator()(cudaStream_t stream, const void* in, void* out) const { ewu_(stream, in, out); }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/floor.hpp b/modules/nvidia_plugin/src/kernels/floor.hpp
similarity index 92%
rename from modules/cuda_plugin/src/kernels/floor.hpp
rename to modules/nvidia_plugin/src/kernels/floor.hpp
index 1a5794901..79d53f7fd 100644
--- a/modules/cuda_plugin/src/kernels/floor.hpp
+++ b/modules/nvidia_plugin/src/kernels/floor.hpp
@@ -7,7 +7,8 @@
 #include "cuda_type_traits.hpp"
 #include "elementwise_unary.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -35,4 +36,5 @@ class Floor {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/floor_mod.cu b/modules/nvidia_plugin/src/kernels/floor_mod.cu
similarity index 95%
rename from modules/cuda_plugin/src/kernels/floor_mod.cu
rename to modules/nvidia_plugin/src/kernels/floor_mod.cu
index 7c0b9cd7e..e1b990c3b 100644
--- a/modules/cuda_plugin/src/kernels/floor_mod.cu
+++ b/modules/nvidia_plugin/src/kernels/floor_mod.cu
@@ -8,7 +8,8 @@
 
 #include "floor_mod.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 namespace {
@@ -59,4 +60,5 @@ void FloorMod::operator()(cudaStream_t stream,
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/floor_mod.hpp b/modules/nvidia_plugin/src/kernels/floor_mod.hpp
similarity index 90%
rename from modules/cuda_plugin/src/kernels/floor_mod.hpp
rename to modules/nvidia_plugin/src/kernels/floor_mod.hpp
index 49c560ad1..3d9f179f2 100644
--- a/modules/cuda_plugin/src/kernels/floor_mod.hpp
+++ b/modules/nvidia_plugin/src/kernels/floor_mod.hpp
@@ -7,7 +7,8 @@
 #include "cuda_type_traits.hpp"
 #include "elementwise_binary.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -33,4 +34,5 @@ class FloorMod {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/gather.cu b/modules/nvidia_plugin/src/kernels/gather.cu
similarity index 99%
rename from modules/cuda_plugin/src/kernels/gather.cu
rename to modules/nvidia_plugin/src/kernels/gather.cu
index a0b487368..001f7c0dc 100644
--- a/modules/cuda_plugin/src/kernels/gather.cu
+++ b/modules/nvidia_plugin/src/kernels/gather.cu
@@ -9,7 +9,8 @@
 
 #include "gather.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 namespace kernel {
 
@@ -261,4 +262,5 @@ void Gather::Call(const cudaStream_t stream,
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/gather.hpp b/modules/nvidia_plugin/src/kernels/gather.hpp
similarity index 96%
rename from modules/cuda_plugin/src/kernels/gather.hpp
rename to modules/nvidia_plugin/src/kernels/gather.hpp
index 0e92668bf..c023f2c83 100644
--- a/modules/cuda_plugin/src/kernels/gather.hpp
+++ b/modules/nvidia_plugin/src/kernels/gather.hpp
@@ -9,7 +9,8 @@
 #include "cuda_type_traits.hpp"
 #include "error.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class Gather {
@@ -71,4 +72,5 @@ class Gather {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/insert.cu b/modules/nvidia_plugin/src/kernels/insert.cu
similarity index 97%
rename from modules/cuda_plugin/src/kernels/insert.cu
rename to modules/nvidia_plugin/src/kernels/insert.cu
index 359a76c0f..83a8594a2 100644
--- a/modules/cuda_plugin/src/kernels/insert.cu
+++ b/modules/nvidia_plugin/src/kernels/insert.cu
@@ -10,7 +10,8 @@
 #include "insert.hpp"
 #include "tensor_helpers.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -80,4 +81,5 @@ void Insert::call(const cudaStream_t stream, const void* src, void* dst, const s
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/insert.hpp b/modules/nvidia_plugin/src/kernels/insert.hpp
similarity index 94%
rename from modules/cuda_plugin/src/kernels/insert.hpp
rename to modules/nvidia_plugin/src/kernels/insert.hpp
index 3b74e34ff..fc96bb115 100644
--- a/modules/cuda_plugin/src/kernels/insert.hpp
+++ b/modules/nvidia_plugin/src/kernels/insert.hpp
@@ -10,7 +10,8 @@
 #include "error.hpp"
 #include "tensor_helpers.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class Insert {
@@ -51,4 +52,5 @@ inline void Insert::setImmutableWorkbuffer(void* immutableBuffer) {
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/interpolate_base.hpp b/modules/nvidia_plugin/src/kernels/interpolate_base.hpp
similarity index 88%
rename from modules/cuda_plugin/src/kernels/interpolate_base.hpp
rename to modules/nvidia_plugin/src/kernels/interpolate_base.hpp
index b4054ac32..23b338e0e 100644
--- a/modules/cuda_plugin/src/kernels/interpolate_base.hpp
+++ b/modules/nvidia_plugin/src/kernels/interpolate_base.hpp
@@ -6,7 +6,8 @@
 
 #include "tensor_helpers.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class InterpolateBase {
@@ -31,4 +32,5 @@ class InterpolateBase {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/interpolate_cubic.cu b/modules/nvidia_plugin/src/kernels/interpolate_cubic.cu
similarity index 98%
rename from modules/cuda_plugin/src/kernels/interpolate_cubic.cu
rename to modules/nvidia_plugin/src/kernels/interpolate_cubic.cu
index 3057f1e94..b4662a490 100644
--- a/modules/cuda_plugin/src/kernels/interpolate_cubic.cu
+++ b/modules/nvidia_plugin/src/kernels/interpolate_cubic.cu
@@ -12,7 +12,8 @@
 #include "interpolate_cubic.hpp"
 #include "interpolate_details.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename CT>
@@ -170,4 +171,5 @@ void InterpolateCubic::initImmutableWorkbuffers(const std::vector<void*>& buffer
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/interpolate_cubic.hpp b/modules/nvidia_plugin/src/kernels/interpolate_cubic.hpp
similarity index 94%
rename from modules/cuda_plugin/src/kernels/interpolate_cubic.hpp
rename to modules/nvidia_plugin/src/kernels/interpolate_cubic.hpp
index e6c255516..899dddba8 100644
--- a/modules/cuda_plugin/src/kernels/interpolate_cubic.hpp
+++ b/modules/nvidia_plugin/src/kernels/interpolate_cubic.hpp
@@ -11,7 +11,8 @@
 #include "interpolate_base.hpp"
 #include "tensor_helpers.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class InterpolateCubic : public InterpolateBase {
@@ -58,4 +59,5 @@ class InterpolateCubic : public InterpolateBase {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/interpolate_details.cuh b/modules/nvidia_plugin/src/kernels/interpolate_details.cuh
similarity index 97%
rename from modules/cuda_plugin/src/kernels/interpolate_details.cuh
rename to modules/nvidia_plugin/src/kernels/interpolate_details.cuh
index 2cd026827..34729d1f8 100644
--- a/modules/cuda_plugin/src/kernels/interpolate_details.cuh
+++ b/modules/nvidia_plugin/src/kernels/interpolate_details.cuh
@@ -11,7 +11,8 @@
 #include "convert.cuh"
 #include "interpolate_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class InterpolateBase::details {
@@ -84,4 +85,5 @@ public:
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/interpolate_linear.cu b/modules/nvidia_plugin/src/kernels/interpolate_linear.cu
similarity index 98%
rename from modules/cuda_plugin/src/kernels/interpolate_linear.cu
rename to modules/nvidia_plugin/src/kernels/interpolate_linear.cu
index 3a83d1cac..6f402de46 100644
--- a/modules/cuda_plugin/src/kernels/interpolate_linear.cu
+++ b/modules/nvidia_plugin/src/kernels/interpolate_linear.cu
@@ -13,7 +13,8 @@
 #include "interpolate_details.cuh"
 #include "interpolate_linear.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename CT>
@@ -210,4 +211,5 @@ void InterpolateLinear::initImmutableWorkbuffers(const std::vector<void*>& buffe
 
 }  // namespace kernel
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/interpolate_linear.hpp b/modules/nvidia_plugin/src/kernels/interpolate_linear.hpp
similarity index 95%
rename from modules/cuda_plugin/src/kernels/interpolate_linear.hpp
rename to modules/nvidia_plugin/src/kernels/interpolate_linear.hpp
index 4737a369b..a5e1b96e9 100644
--- a/modules/cuda_plugin/src/kernels/interpolate_linear.hpp
+++ b/modules/nvidia_plugin/src/kernels/interpolate_linear.hpp
@@ -11,7 +11,8 @@
 #include "interpolate_base.hpp"
 #include "tensor_helpers.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class InterpolateLinear : public InterpolateBase {
@@ -60,4 +61,5 @@ class InterpolateLinear : public InterpolateBase {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/interpolate_nearest.cu b/modules/nvidia_plugin/src/kernels/interpolate_nearest.cu
similarity index 98%
rename from modules/cuda_plugin/src/kernels/interpolate_nearest.cu
rename to modules/nvidia_plugin/src/kernels/interpolate_nearest.cu
index 42076ea49..620c9c353 100644
--- a/modules/cuda_plugin/src/kernels/interpolate_nearest.cu
+++ b/modules/nvidia_plugin/src/kernels/interpolate_nearest.cu
@@ -10,7 +10,8 @@
 #include "interpolate_details.cuh"
 #include "interpolate_nearest.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 static inline __device__ float calc_output_index(const InterpolateNearest::CoordinateTransformMode mode,
@@ -184,7 +185,7 @@ static __global__ void upscale_interpolate(const InterpolateNearest::NearestMode
 
 InterpolateNearest::InterpolateNearest(size_t num_blocks,
                                        size_t threads_per_block,
-                                       CUDAPlugin::kernel::Type_t element_type,
+                                       ov::nvidia_gpu::kernel::Type_t element_type,
                                        bool use_optimized_kernel,
                                        NearestMode nearest_mode,
                                        CoordinateTransformMode transform_mode)
@@ -260,4 +261,5 @@ void InterpolateNearest::callKernel(const cudaStream_t stream,
 
 }  // namespace kernel
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/interpolate_nearest.hpp b/modules/nvidia_plugin/src/kernels/interpolate_nearest.hpp
similarity index 91%
rename from modules/cuda_plugin/src/kernels/interpolate_nearest.hpp
rename to modules/nvidia_plugin/src/kernels/interpolate_nearest.hpp
index ac02ade4f..22c36e9c3 100644
--- a/modules/cuda_plugin/src/kernels/interpolate_nearest.hpp
+++ b/modules/nvidia_plugin/src/kernels/interpolate_nearest.hpp
@@ -10,7 +10,8 @@
 #include "error.hpp"
 #include "interpolate_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class InterpolateNearest : public InterpolateBase {
@@ -20,7 +21,7 @@ class InterpolateNearest : public InterpolateBase {
 
     InterpolateNearest(size_t num_blocks,
                        size_t threads_per_block,
-                       CUDAPlugin::kernel::Type_t element_type,
+                       ov::nvidia_gpu::kernel::Type_t element_type,
                        bool upscale,
                        NearestMode nearest_mode,
                        CoordinateTransformMode transform_mode);
@@ -55,4 +56,5 @@ class InterpolateNearest : public InterpolateBase {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/logical_not.cu b/modules/nvidia_plugin/src/kernels/logical_not.cu
similarity index 95%
rename from modules/cuda_plugin/src/kernels/logical_not.cu
rename to modules/nvidia_plugin/src/kernels/logical_not.cu
index 4008a4c10..f2d79b5be 100644
--- a/modules/cuda_plugin/src/kernels/logical_not.cu
+++ b/modules/nvidia_plugin/src/kernels/logical_not.cu
@@ -8,7 +8,8 @@
 
 #include "logical_not.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <int Rank>
@@ -51,4 +52,5 @@ void LogicalNot::operator()(cudaStream_t stream, const bool* src, bool* dst) con
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/logical_not.cuh b/modules/nvidia_plugin/src/kernels/logical_not.cuh
similarity index 88%
rename from modules/cuda_plugin/src/kernels/logical_not.cuh
rename to modules/nvidia_plugin/src/kernels/logical_not.cuh
index 8d951a4d6..9c62e9c83 100644
--- a/modules/cuda_plugin/src/kernels/logical_not.cuh
+++ b/modules/nvidia_plugin/src/kernels/logical_not.cuh
@@ -9,7 +9,8 @@
 #include "eltwise.cuh"
 #include "error.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class LogicalNot {
@@ -28,4 +29,5 @@ private:
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/maximum.cu b/modules/nvidia_plugin/src/kernels/maximum.cu
similarity index 90%
rename from modules/cuda_plugin/src/kernels/maximum.cu
rename to modules/nvidia_plugin/src/kernels/maximum.cu
index 06e76bc5f..83aec3062 100644
--- a/modules/cuda_plugin/src/kernels/maximum.cu
+++ b/modules/nvidia_plugin/src/kernels/maximum.cu
@@ -6,7 +6,8 @@
 
 #include "maximum.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -27,4 +28,5 @@ void Maximum::operator()(cudaStream_t stream,
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/maximum.hpp b/modules/nvidia_plugin/src/kernels/maximum.hpp
similarity index 90%
rename from modules/cuda_plugin/src/kernels/maximum.hpp
rename to modules/nvidia_plugin/src/kernels/maximum.hpp
index 66d98cca0..71d1eb2d4 100644
--- a/modules/cuda_plugin/src/kernels/maximum.hpp
+++ b/modules/nvidia_plugin/src/kernels/maximum.hpp
@@ -6,7 +6,8 @@
 
 #include "elementwise_binary.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -32,4 +33,5 @@ class Maximum {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/minimum.cu b/modules/nvidia_plugin/src/kernels/minimum.cu
similarity index 90%
rename from modules/cuda_plugin/src/kernels/minimum.cu
rename to modules/nvidia_plugin/src/kernels/minimum.cu
index eb7ea6828..a2715e0a4 100644
--- a/modules/cuda_plugin/src/kernels/minimum.cu
+++ b/modules/nvidia_plugin/src/kernels/minimum.cu
@@ -6,7 +6,8 @@
 
 #include "minimum.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -27,4 +28,5 @@ void Minimum::operator()(cudaStream_t stream,
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/minimum.hpp b/modules/nvidia_plugin/src/kernels/minimum.hpp
similarity index 90%
rename from modules/cuda_plugin/src/kernels/minimum.hpp
rename to modules/nvidia_plugin/src/kernels/minimum.hpp
index fe82a6ed1..46e8ab4d2 100644
--- a/modules/cuda_plugin/src/kernels/minimum.hpp
+++ b/modules/nvidia_plugin/src/kernels/minimum.hpp
@@ -6,7 +6,8 @@
 
 #include "elementwise_binary.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -32,4 +33,5 @@ class Minimum {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/mod.cu b/modules/nvidia_plugin/src/kernels/mod.cu
similarity index 94%
rename from modules/cuda_plugin/src/kernels/mod.cu
rename to modules/nvidia_plugin/src/kernels/mod.cu
index d95d18771..6e268556d 100644
--- a/modules/cuda_plugin/src/kernels/mod.cu
+++ b/modules/nvidia_plugin/src/kernels/mod.cu
@@ -8,7 +8,8 @@
 
 #include "mod.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 namespace {
@@ -47,4 +48,5 @@ void Mod::operator()(cudaStream_t stream,
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/mod.hpp b/modules/nvidia_plugin/src/kernels/mod.hpp
similarity index 90%
rename from modules/cuda_plugin/src/kernels/mod.hpp
rename to modules/nvidia_plugin/src/kernels/mod.hpp
index daa588507..9e5a589b0 100644
--- a/modules/cuda_plugin/src/kernels/mod.hpp
+++ b/modules/nvidia_plugin/src/kernels/mod.hpp
@@ -7,7 +7,8 @@
 #include "cuda_type_traits.hpp"
 #include "elementwise_binary.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -33,4 +34,5 @@ class Mod {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/multiply.cu b/modules/nvidia_plugin/src/kernels/multiply.cu
similarity index 90%
rename from modules/cuda_plugin/src/kernels/multiply.cu
rename to modules/nvidia_plugin/src/kernels/multiply.cu
index 69f4bbcca..991072d8b 100644
--- a/modules/cuda_plugin/src/kernels/multiply.cu
+++ b/modules/nvidia_plugin/src/kernels/multiply.cu
@@ -6,7 +6,8 @@
 
 #include "multiply.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -27,4 +28,5 @@ void Multiply::operator()(cudaStream_t stream,
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/multiply.hpp b/modules/nvidia_plugin/src/kernels/multiply.hpp
similarity index 90%
rename from modules/cuda_plugin/src/kernels/multiply.hpp
rename to modules/nvidia_plugin/src/kernels/multiply.hpp
index 16c65c27f..39d7ddf20 100644
--- a/modules/cuda_plugin/src/kernels/multiply.hpp
+++ b/modules/nvidia_plugin/src/kernels/multiply.hpp
@@ -6,7 +6,8 @@
 
 #include "elementwise_binary.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -32,4 +33,5 @@ class Multiply {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/numpy_broadcast_mapper.cuh b/modules/nvidia_plugin/src/kernels/numpy_broadcast_mapper.cuh
similarity index 96%
rename from modules/cuda_plugin/src/kernels/numpy_broadcast_mapper.cuh
rename to modules/nvidia_plugin/src/kernels/numpy_broadcast_mapper.cuh
index c4a7b99d4..4a77783e0 100644
--- a/modules/cuda_plugin/src/kernels/numpy_broadcast_mapper.cuh
+++ b/modules/nvidia_plugin/src/kernels/numpy_broadcast_mapper.cuh
@@ -9,7 +9,8 @@
 
 #include <gsl/gsl_assert>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class NumpyBroadcastMapper {
@@ -64,4 +65,5 @@ private:
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/pad.cu b/modules/nvidia_plugin/src/kernels/pad.cu
similarity index 99%
rename from modules/cuda_plugin/src/kernels/pad.cu
rename to modules/nvidia_plugin/src/kernels/pad.cu
index b83bdd272..7a802c342 100644
--- a/modules/cuda_plugin/src/kernels/pad.cu
+++ b/modules/nvidia_plugin/src/kernels/pad.cu
@@ -9,7 +9,8 @@
 #include "error.hpp"
 #include "pad.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 // TODO: Would be optimized adding template specializations. Left without this optimization in sake of readability.
@@ -217,4 +218,5 @@ void ConstModePad::callNCHWFormatConvKernel(cudaStream_t stream,
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/pad.cuh b/modules/nvidia_plugin/src/kernels/pad.cuh
similarity index 96%
rename from modules/cuda_plugin/src/kernels/pad.cuh
rename to modules/nvidia_plugin/src/kernels/pad.cuh
index 7221bbe05..382b3e42f 100644
--- a/modules/cuda_plugin/src/kernels/pad.cuh
+++ b/modules/nvidia_plugin/src/kernels/pad.cuh
@@ -8,7 +8,8 @@
 #include "eltwise.cuh"
 #include "ngraph/type/element_type.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class ConstModePad {
@@ -70,4 +71,5 @@ private:
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/power.cu b/modules/nvidia_plugin/src/kernels/power.cu
similarity index 92%
rename from modules/cuda_plugin/src/kernels/power.cu
rename to modules/nvidia_plugin/src/kernels/power.cu
index e0ed9b6da..74ba4f9b3 100644
--- a/modules/cuda_plugin/src/kernels/power.cu
+++ b/modules/nvidia_plugin/src/kernels/power.cu
@@ -5,7 +5,8 @@
 #include "convert.cuh"
 #include "power.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -33,4 +34,5 @@ void Power::operator()(cudaStream_t stream,
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/power.hpp b/modules/nvidia_plugin/src/kernels/power.hpp
similarity index 92%
rename from modules/cuda_plugin/src/kernels/power.hpp
rename to modules/nvidia_plugin/src/kernels/power.hpp
index c1ef5fa31..2aa9deb31 100644
--- a/modules/cuda_plugin/src/kernels/power.hpp
+++ b/modules/nvidia_plugin/src/kernels/power.hpp
@@ -6,7 +6,8 @@
 
 #include "elementwise_binary.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -47,4 +48,5 @@ class Power {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/prelu.cu b/modules/nvidia_plugin/src/kernels/prelu.cu
similarity index 89%
rename from modules/cuda_plugin/src/kernels/prelu.cu
rename to modules/nvidia_plugin/src/kernels/prelu.cu
index 3be8ba1b1..f28afe6ef 100644
--- a/modules/cuda_plugin/src/kernels/prelu.cu
+++ b/modules/nvidia_plugin/src/kernels/prelu.cu
@@ -1,6 +1,7 @@
 #include "prelu.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -21,4 +22,5 @@ void PRelu::operator()(cudaStream_t stream,
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/prelu.hpp b/modules/nvidia_plugin/src/kernels/prelu.hpp
similarity index 91%
rename from modules/cuda_plugin/src/kernels/prelu.hpp
rename to modules/nvidia_plugin/src/kernels/prelu.hpp
index 2450bffbc..d77743321 100644
--- a/modules/cuda_plugin/src/kernels/prelu.hpp
+++ b/modules/nvidia_plugin/src/kernels/prelu.hpp
@@ -7,7 +7,8 @@
 #include "cuda_type_traits.hpp"
 #include "elementwise_binary.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -40,4 +41,5 @@ class PRelu {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/range.cu b/modules/nvidia_plugin/src/kernels/range.cu
similarity index 97%
rename from modules/cuda_plugin/src/kernels/range.cu
rename to modules/nvidia_plugin/src/kernels/range.cu
index 86ff5a4ff..8282c3c84 100644
--- a/modules/cuda_plugin/src/kernels/range.cu
+++ b/modules/nvidia_plugin/src/kernels/range.cu
@@ -8,7 +8,8 @@
 #include "kernels/range.hpp"
 #include "typed_functor.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 namespace kernel {
 
@@ -76,4 +77,5 @@ void RangeKernelOp::operator()(
 
 }  // namespace kernel
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/range.hpp b/modules/nvidia_plugin/src/kernels/range.hpp
similarity index 91%
rename from modules/cuda_plugin/src/kernels/range.hpp
rename to modules/nvidia_plugin/src/kernels/range.hpp
index 051a2202d..9ed6edc8e 100644
--- a/modules/cuda_plugin/src/kernels/range.hpp
+++ b/modules/nvidia_plugin/src/kernels/range.hpp
@@ -9,7 +9,8 @@
 #include "cuda_type_traits.hpp"
 #include "ngraph/type/element_type.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class RangeKernelOp {
@@ -33,4 +34,5 @@ class RangeKernelOp {
 
 }  // namespace kernel
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/round.cu b/modules/nvidia_plugin/src/kernels/round.cu
similarity index 86%
rename from modules/cuda_plugin/src/kernels/round.cu
rename to modules/nvidia_plugin/src/kernels/round.cu
index a5c3c0c8c..f141926c0 100644
--- a/modules/cuda_plugin/src/kernels/round.cu
+++ b/modules/nvidia_plugin/src/kernels/round.cu
@@ -6,7 +6,8 @@
 
 #include "round.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -20,4 +21,5 @@ Round::Round(Type_t element_type, size_t max_threads_per_block, size_t num_eleme
 void Round::operator()(cudaStream_t stream, const void* in, void* out) const { ewu_(stream, in, out); }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/round.hpp b/modules/nvidia_plugin/src/kernels/round.hpp
similarity index 92%
rename from modules/cuda_plugin/src/kernels/round.hpp
rename to modules/nvidia_plugin/src/kernels/round.hpp
index afd3e5c91..bf2e70f2e 100644
--- a/modules/cuda_plugin/src/kernels/round.hpp
+++ b/modules/nvidia_plugin/src/kernels/round.hpp
@@ -7,7 +7,8 @@
 #include "cuda_type_traits.hpp"
 #include "elementwise_unary.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -35,4 +36,5 @@ class Round {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/scatter_nd_update.cu b/modules/nvidia_plugin/src/kernels/scatter_nd_update.cu
similarity index 99%
rename from modules/cuda_plugin/src/kernels/scatter_nd_update.cu
rename to modules/nvidia_plugin/src/kernels/scatter_nd_update.cu
index d68947c40..57cf73f51 100644
--- a/modules/cuda_plugin/src/kernels/scatter_nd_update.cu
+++ b/modules/nvidia_plugin/src/kernels/scatter_nd_update.cu
@@ -11,7 +11,8 @@
 
 #include "scatter_nd_update.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename DataType, typename IndexType>
@@ -190,4 +191,5 @@ void ScatterNDUpdate::Call(const cudaStream_t stream,
 }
 }  // namespace kernel
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/scatter_nd_update.hpp b/modules/nvidia_plugin/src/kernels/scatter_nd_update.hpp
similarity index 95%
rename from modules/cuda_plugin/src/kernels/scatter_nd_update.hpp
rename to modules/nvidia_plugin/src/kernels/scatter_nd_update.hpp
index c0584ddd6..5afd82a0b 100644
--- a/modules/cuda_plugin/src/kernels/scatter_nd_update.hpp
+++ b/modules/nvidia_plugin/src/kernels/scatter_nd_update.hpp
@@ -9,7 +9,8 @@
 #include "cuda_type_traits.hpp"
 #include "error.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class ScatterNDUpdate {
@@ -60,4 +61,5 @@ class ScatterNDUpdate {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/select.cu b/modules/nvidia_plugin/src/kernels/select.cu
similarity index 98%
rename from modules/cuda_plugin/src/kernels/select.cu
rename to modules/nvidia_plugin/src/kernels/select.cu
index cf64506b7..0483e495c 100644
--- a/modules/cuda_plugin/src/kernels/select.cu
+++ b/modules/nvidia_plugin/src/kernels/select.cu
@@ -7,7 +7,8 @@
 
 #include "select.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 namespace kernel {
 template <typename T>
@@ -130,4 +131,5 @@ void SelectKernelOp::callKernel(const cudaStream_t stream,
 
 }  // namespace kernel
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/select.hpp b/modules/nvidia_plugin/src/kernels/select.hpp
similarity index 95%
rename from modules/cuda_plugin/src/kernels/select.hpp
rename to modules/nvidia_plugin/src/kernels/select.hpp
index 438e1cf0b..3f9390d76 100644
--- a/modules/cuda_plugin/src/kernels/select.hpp
+++ b/modules/nvidia_plugin/src/kernels/select.hpp
@@ -9,7 +9,8 @@
 #include "error.hpp"
 #include "ngraph/type/element_type.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class SelectKernelOp {
@@ -53,4 +54,5 @@ class SelectKernelOp {
 
 }  // namespace kernel
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/slice.cu b/modules/nvidia_plugin/src/kernels/slice.cu
similarity index 97%
rename from modules/cuda_plugin/src/kernels/slice.cu
rename to modules/nvidia_plugin/src/kernels/slice.cu
index 19802df7a..70a0ee379 100644
--- a/modules/cuda_plugin/src/kernels/slice.cu
+++ b/modules/nvidia_plugin/src/kernels/slice.cu
@@ -10,7 +10,8 @@
 #include "slice.hpp"
 #include "tensor_helpers.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -81,4 +82,5 @@ void Slice::call(cudaStream_t stream, const void *src, void *dst, size_t start)
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/slice.hpp b/modules/nvidia_plugin/src/kernels/slice.hpp
similarity index 94%
rename from modules/cuda_plugin/src/kernels/slice.hpp
rename to modules/nvidia_plugin/src/kernels/slice.hpp
index 3b27144af..a32d3dcf2 100644
--- a/modules/cuda_plugin/src/kernels/slice.hpp
+++ b/modules/nvidia_plugin/src/kernels/slice.hpp
@@ -8,7 +8,8 @@
 #include "error.hpp"
 #include "tensor_helpers.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class Slice {
@@ -49,4 +50,5 @@ inline void Slice::setImmutableWorkbuffer(void* immutableBuffer) {
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/split.cu b/modules/nvidia_plugin/src/kernels/split.cu
similarity index 97%
rename from modules/cuda_plugin/src/kernels/split.cu
rename to modules/nvidia_plugin/src/kernels/split.cu
index c6e564d46..8a9c98429 100644
--- a/modules/cuda_plugin/src/kernels/split.cu
+++ b/modules/nvidia_plugin/src/kernels/split.cu
@@ -9,7 +9,8 @@
 
 #include "split.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -85,4 +86,5 @@ void Split::Call(cudaStream_t stream, const void *src, void **dst) const {
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/split.hpp b/modules/nvidia_plugin/src/kernels/split.hpp
similarity index 91%
rename from modules/cuda_plugin/src/kernels/split.hpp
rename to modules/nvidia_plugin/src/kernels/split.hpp
index 64f3ec372..0e72966ca 100644
--- a/modules/cuda_plugin/src/kernels/split.hpp
+++ b/modules/nvidia_plugin/src/kernels/split.hpp
@@ -7,7 +7,8 @@
 #include "cuda_type_traits.hpp"
 #include "error.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class Split {
@@ -38,4 +39,5 @@ class Split {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/squared_difference.cu b/modules/nvidia_plugin/src/kernels/squared_difference.cu
similarity index 92%
rename from modules/cuda_plugin/src/kernels/squared_difference.cu
rename to modules/nvidia_plugin/src/kernels/squared_difference.cu
index 1273c90f6..dbda10592 100644
--- a/modules/cuda_plugin/src/kernels/squared_difference.cu
+++ b/modules/nvidia_plugin/src/kernels/squared_difference.cu
@@ -7,7 +7,8 @@
 
 #include "squared_difference.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -31,4 +32,5 @@ void SquaredDifference::operator()(cudaStream_t stream,
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/squared_difference.hpp b/modules/nvidia_plugin/src/kernels/squared_difference.hpp
similarity index 91%
rename from modules/cuda_plugin/src/kernels/squared_difference.hpp
rename to modules/nvidia_plugin/src/kernels/squared_difference.hpp
index 366c9df54..33d979068 100644
--- a/modules/cuda_plugin/src/kernels/squared_difference.hpp
+++ b/modules/nvidia_plugin/src/kernels/squared_difference.hpp
@@ -7,7 +7,8 @@
 #include "cuda_type_traits.hpp"
 #include "elementwise_binary.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -33,4 +34,5 @@ class SquaredDifference {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/strided_slice.cu b/modules/nvidia_plugin/src/kernels/strided_slice.cu
similarity index 99%
rename from modules/cuda_plugin/src/kernels/strided_slice.cu
rename to modules/nvidia_plugin/src/kernels/strided_slice.cu
index e6406b899..659eb23dc 100644
--- a/modules/cuda_plugin/src/kernels/strided_slice.cu
+++ b/modules/nvidia_plugin/src/kernels/strided_slice.cu
@@ -6,7 +6,8 @@
 
 #include "strided_slice.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 #ifdef CUDA_KERNEL_PRINT_LOG
@@ -221,4 +222,5 @@ void StridedSliceKernelOp::callReverseAxesKernel(const cudaStream_t stream, void
 
 }  // namespace kernel
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/strided_slice.hpp b/modules/nvidia_plugin/src/kernels/strided_slice.hpp
similarity index 96%
rename from modules/cuda_plugin/src/kernels/strided_slice.hpp
rename to modules/nvidia_plugin/src/kernels/strided_slice.hpp
index 845988424..f7b4ea35f 100644
--- a/modules/cuda_plugin/src/kernels/strided_slice.hpp
+++ b/modules/nvidia_plugin/src/kernels/strided_slice.hpp
@@ -12,7 +12,8 @@
 
 #include "error.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 class StridedSliceKernelOp {
 public:
@@ -66,4 +67,5 @@ class StridedSliceKernelOp {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/subtract.cu b/modules/nvidia_plugin/src/kernels/subtract.cu
similarity index 91%
rename from modules/cuda_plugin/src/kernels/subtract.cu
rename to modules/nvidia_plugin/src/kernels/subtract.cu
index f79765fc7..017b8295b 100644
--- a/modules/cuda_plugin/src/kernels/subtract.cu
+++ b/modules/nvidia_plugin/src/kernels/subtract.cu
@@ -7,7 +7,8 @@
 
 #include "subtract.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -28,4 +29,5 @@ void Subtract::operator()(cudaStream_t stream,
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/subtract.hpp b/modules/nvidia_plugin/src/kernels/subtract.hpp
similarity index 90%
rename from modules/cuda_plugin/src/kernels/subtract.hpp
rename to modules/nvidia_plugin/src/kernels/subtract.hpp
index b50ec107f..9e1ff296a 100644
--- a/modules/cuda_plugin/src/kernels/subtract.hpp
+++ b/modules/nvidia_plugin/src/kernels/subtract.hpp
@@ -7,7 +7,8 @@
 #include "cuda_type_traits.hpp"
 #include "elementwise_binary.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -33,4 +34,5 @@ class Subtract {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/swish.cu b/modules/nvidia_plugin/src/kernels/swish.cu
similarity index 95%
rename from modules/cuda_plugin/src/kernels/swish.cu
rename to modules/nvidia_plugin/src/kernels/swish.cu
index 4adc16ae6..0c0d320ce 100644
--- a/modules/cuda_plugin/src/kernels/swish.cu
+++ b/modules/nvidia_plugin/src/kernels/swish.cu
@@ -7,7 +7,8 @@
 #include "swish.hpp"
 #include "tensor_helpers.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -55,4 +56,5 @@ Swish::Swish(Type_t element_type, size_t max_threads_per_block, size_t num_eleme
 void Swish::operator()(cudaStream_t stream, const void* in, void* out) const { ewu_(stream, in, out, beta_); }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/swish.hpp b/modules/nvidia_plugin/src/kernels/swish.hpp
similarity index 92%
rename from modules/cuda_plugin/src/kernels/swish.hpp
rename to modules/nvidia_plugin/src/kernels/swish.hpp
index e1d747665..17af1d11a 100644
--- a/modules/cuda_plugin/src/kernels/swish.hpp
+++ b/modules/nvidia_plugin/src/kernels/swish.hpp
@@ -7,7 +7,8 @@
 #include "cuda_type_traits.hpp"
 #include "elementwise_unary.cuh"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -36,4 +37,5 @@ class Swish {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/switch.hpp b/modules/nvidia_plugin/src/kernels/switch.hpp
similarity index 95%
rename from modules/cuda_plugin/src/kernels/switch.hpp
rename to modules/nvidia_plugin/src/kernels/switch.hpp
index c7b236017..f9f2373bc 100644
--- a/modules/cuda_plugin/src/kernels/switch.hpp
+++ b/modules/nvidia_plugin/src/kernels/switch.hpp
@@ -6,7 +6,8 @@
 
 #include <utility>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename Int, Int First, Int... Indices, typename TypeT, typename Switch, typename... Args>
@@ -41,4 +42,5 @@ constexpr decltype(auto) templateSwitch(std::integer_sequence<Int>, TypeT v, Swi
 // auto n = templateSwitch(std::integer_sequence<int, 1, 2, 4, 6>{}, 4, SimpleSwitch{}, 2);
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/tensor_helpers.hpp b/modules/nvidia_plugin/src/kernels/tensor_helpers.hpp
similarity index 98%
rename from modules/cuda_plugin/src/kernels/tensor_helpers.hpp
rename to modules/nvidia_plugin/src/kernels/tensor_helpers.hpp
index 95e3cc1ad..4cda0b80a 100644
--- a/modules/cuda_plugin/src/kernels/tensor_helpers.hpp
+++ b/modules/nvidia_plugin/src/kernels/tensor_helpers.hpp
@@ -10,7 +10,8 @@
 #include <limits>
 #include <type_traits>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T, unsigned N>
@@ -148,4 +149,5 @@ std::enable_if_t<!std::is_integral<T>::value, T> double_round_cast(double x, dou
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/topk.cu b/modules/nvidia_plugin/src/kernels/topk.cu
similarity index 99%
rename from modules/cuda_plugin/src/kernels/topk.cu
rename to modules/nvidia_plugin/src/kernels/topk.cu
index 1b4b971cb..21d488174 100644
--- a/modules/cuda_plugin/src/kernels/topk.cu
+++ b/modules/nvidia_plugin/src/kernels/topk.cu
@@ -12,7 +12,8 @@
 #include "tensor_helpers.hpp"
 #include "topk.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 using TopKShape = Shape<size_t, TopK::kNumKernelParamDim>;
@@ -308,4 +309,5 @@ void TopK::operator()(cudaStream_t stream,
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/topk.hpp b/modules/nvidia_plugin/src/kernels/topk.hpp
similarity index 97%
rename from modules/cuda_plugin/src/kernels/topk.hpp
rename to modules/nvidia_plugin/src/kernels/topk.hpp
index 72c2da9ac..6ef8f51e9 100644
--- a/modules/cuda_plugin/src/kernels/topk.hpp
+++ b/modules/nvidia_plugin/src/kernels/topk.hpp
@@ -7,7 +7,8 @@
 #include "cuda_type_traits.hpp"
 #include "elementtypeswitch.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class TopK {
@@ -101,4 +102,5 @@ class TopK {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/typed_functor.hpp b/modules/nvidia_plugin/src/kernels/typed_functor.hpp
similarity index 96%
rename from modules/cuda_plugin/src/kernels/typed_functor.hpp
rename to modules/nvidia_plugin/src/kernels/typed_functor.hpp
index 1005b1aef..97b335681 100644
--- a/modules/cuda_plugin/src/kernels/typed_functor.hpp
+++ b/modules/nvidia_plugin/src/kernels/typed_functor.hpp
@@ -9,7 +9,8 @@
 #include "error.hpp"
 #include "fmt/format.h"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 namespace kernel {
 
@@ -38,7 +39,7 @@ enum Dimension : size_t { DIM_1D = 1, DIM_2D, DIM_3D };
 ///    static constexpr TypedFunctor<FunctorImpl, TFuncPtr, DIM_3D> instance{};
 /// And the function pointer can be accessed like the next.
 ///    auto func_ptr = instance[type_1][type_2][type_3];
-/// Where subscription index (type_1, type_2, type_3) is of type CUDAPlugin::kernel::Type_t enum.
+/// Where subscription index (type_1, type_2, type_3) is of type ov::nvidia_gpu::kernel::Type_t enum.
 ///
 /// This template can be used for any dimension number, if the Dimension enumeration extended properly.
 /// For trivial case with one dimension the functor will be like the next.
@@ -52,7 +53,7 @@ enum Dimension : size_t { DIM_1D = 1, DIM_2D, DIM_3D };
 /// The template structure can be instantiated like the next.
 ///    static constexpr TypedFunctor<FunctorImpl, TFuncPtr, DIM_1D> instance{};
 /// And the function pointer can be accessed like the next.
-///    auto func_ptr = instance[CUDAPlugin::kernel::Type_t::f32];
+///    auto func_ptr = instance[ov::nvidia_gpu::kernel::Type_t::f32];
 // clang-format on
 template <template <typename... Types> class TFunctor, typename TFunPtr, Dimension D>
 struct TypedFunctor : private std::array<TypedFunctor<TFunctor, TFunPtr, Dimension(D - 1)>, type_count> {
@@ -107,4 +108,5 @@ struct TypedFunctor<TFunctor, TFunPtr, DIM_1D> : private std::array<TFunPtr, typ
 
 }  // namespace kernel
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/variadic_split.cu b/modules/nvidia_plugin/src/kernels/variadic_split.cu
similarity index 98%
rename from modules/cuda_plugin/src/kernels/variadic_split.cu
rename to modules/nvidia_plugin/src/kernels/variadic_split.cu
index d844fb32e..c3502f3ff 100644
--- a/modules/cuda_plugin/src/kernels/variadic_split.cu
+++ b/modules/nvidia_plugin/src/kernels/variadic_split.cu
@@ -14,7 +14,8 @@
 
 #include "variadic_split.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 template <typename T>
@@ -116,4 +117,5 @@ void VariadicSplit::call(cudaStream_t stream,
 }
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/variadic_split.hpp b/modules/nvidia_plugin/src/kernels/variadic_split.hpp
similarity index 93%
rename from modules/cuda_plugin/src/kernels/variadic_split.hpp
rename to modules/nvidia_plugin/src/kernels/variadic_split.hpp
index a794c260a..903f0203f 100644
--- a/modules/cuda_plugin/src/kernels/variadic_split.hpp
+++ b/modules/nvidia_plugin/src/kernels/variadic_split.hpp
@@ -7,7 +7,8 @@
 #include "cuda_type_traits.hpp"
 #include "error.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class VariadicSplit {
@@ -46,4 +47,5 @@ class VariadicSplit {
 };
 
 }  // namespace kernel
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/variance_normalization_factor.cu b/modules/nvidia_plugin/src/kernels/variance_normalization_factor.cu
similarity index 92%
rename from modules/cuda_plugin/src/kernels/variance_normalization_factor.cu
rename to modules/nvidia_plugin/src/kernels/variance_normalization_factor.cu
index 9e1af7e84..b34d29597 100644
--- a/modules/cuda_plugin/src/kernels/variance_normalization_factor.cu
+++ b/modules/nvidia_plugin/src/kernels/variance_normalization_factor.cu
@@ -8,7 +8,8 @@
 #include "kernels/variance_normalization_factor.hpp"
 #include "typed_functor.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 namespace kernel {
 
@@ -58,7 +59,7 @@ VarianceNormalizationFactor::VarianceNormalizationFactor(unsigned blocks_number,
         CASE(f32)
         CASE(f64)
         default:
-            throwIEException(fmt::format("CUDAPlugin::MvnOp: unsupported data type, must be any float point type."));
+            throwIEException(fmt::format("ov::nvidia_gpu::MvnOp: unsupported data type, must be any float point type."));
     }
 #undef CASE
 }
@@ -69,4 +70,5 @@ void VarianceNormalizationFactor::operator()(cudaStream_t stream, void *data) co
 
 }  // namespace kernel
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/kernels/variance_normalization_factor.hpp b/modules/nvidia_plugin/src/kernels/variance_normalization_factor.hpp
similarity index 91%
rename from modules/cuda_plugin/src/kernels/variance_normalization_factor.hpp
rename to modules/nvidia_plugin/src/kernels/variance_normalization_factor.hpp
index bdb32e1f6..63894ee03 100644
--- a/modules/cuda_plugin/src/kernels/variance_normalization_factor.hpp
+++ b/modules/nvidia_plugin/src/kernels/variance_normalization_factor.hpp
@@ -9,7 +9,8 @@
 #include "cuda_type_traits.hpp"
 #include "ngraph/type/element_type.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace kernel {
 
 class VarianceNormalizationFactor {
@@ -34,4 +35,5 @@ class VarianceNormalizationFactor {
 
 }  // namespace kernel
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/cuda_device_mem_block.cpp b/modules/nvidia_plugin/src/memory_manager/cuda_device_mem_block.cpp
similarity index 90%
rename from modules/cuda_plugin/src/memory_manager/cuda_device_mem_block.cpp
rename to modules/nvidia_plugin/src/memory_manager/cuda_device_mem_block.cpp
index a0453ab80..72a304be0 100644
--- a/modules/cuda_plugin/src/memory_manager/cuda_device_mem_block.cpp
+++ b/modules/nvidia_plugin/src/memory_manager/cuda_device_mem_block.cpp
@@ -10,7 +10,8 @@
 #include <details/ie_exception.hpp>
 #include <iostream>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 DeviceMemBlock::DeviceMemBlock(MemoryModel::Ptr model) : model_{move(model)} {}
 
@@ -27,4 +28,5 @@ void* DeviceMemBlock::deviceTensorPtr(const TensorID& id) const {
     return nullptr;
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/cuda_device_mem_block.hpp b/modules/nvidia_plugin/src/memory_manager/cuda_device_mem_block.hpp
similarity index 95%
rename from modules/cuda_plugin/src/memory_manager/cuda_device_mem_block.hpp
rename to modules/nvidia_plugin/src/memory_manager/cuda_device_mem_block.hpp
index 1cb5e706b..a67d138b7 100644
--- a/modules/cuda_plugin/src/memory_manager/cuda_device_mem_block.hpp
+++ b/modules/nvidia_plugin/src/memory_manager/cuda_device_mem_block.hpp
@@ -9,7 +9,8 @@
 
 #include "memory_manager/model/cuda_memory_model.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * @brief Allocates and owns continuous memory blob on CUDA device.
@@ -57,4 +58,5 @@ class DeviceMemBlock {
     CUDA::DefaultAllocation device_mem_ptr_ = CUDA::DefaultStream::stream().malloc(model_->deviceMemoryBlockSize());
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/cuda_immutable_memory_block_builder.cpp b/modules/nvidia_plugin/src/memory_manager/cuda_immutable_memory_block_builder.cpp
similarity index 92%
rename from modules/cuda_plugin/src/memory_manager/cuda_immutable_memory_block_builder.cpp
rename to modules/nvidia_plugin/src/memory_manager/cuda_immutable_memory_block_builder.cpp
index 1565e12fe..cf698fac4 100644
--- a/modules/cuda_plugin/src/memory_manager/cuda_immutable_memory_block_builder.cpp
+++ b/modules/nvidia_plugin/src/memory_manager/cuda_immutable_memory_block_builder.cpp
@@ -6,7 +6,8 @@
 
 #include <details/ie_exception.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 void ImmutableMemoryBlockBuilder::addAllocation(BufferID id, const void* data, size_t bsize) {
     IE_ASSERT(data != nullptr);
@@ -27,4 +28,5 @@ std::pair<DeviceMemBlock::Ptr, MemoryModel::Ptr> ImmutableMemoryBlockBuilder::bu
     return {memory_block, memory_model};
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/cuda_immutable_memory_block_builder.hpp b/modules/nvidia_plugin/src/memory_manager/cuda_immutable_memory_block_builder.hpp
similarity index 95%
rename from modules/cuda_plugin/src/memory_manager/cuda_immutable_memory_block_builder.hpp
rename to modules/nvidia_plugin/src/memory_manager/cuda_immutable_memory_block_builder.hpp
index 568a2000c..dcc3e6d15 100644
--- a/modules/cuda_plugin/src/memory_manager/cuda_immutable_memory_block_builder.hpp
+++ b/modules/nvidia_plugin/src/memory_manager/cuda_immutable_memory_block_builder.hpp
@@ -10,7 +10,8 @@
 #include "memory_manager/model/cuda_immutable_memory_model_builder.hpp"
 #include "memory_manager/model/cuda_memory_model.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class DeviceMemBlock;
 
@@ -56,4 +57,5 @@ class ImmutableMemoryBlockBuilder {
     std::vector<AllocRecord> allocations_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/cuda_memory_manager.cpp b/modules/nvidia_plugin/src/memory_manager/cuda_memory_manager.cpp
similarity index 96%
rename from modules/cuda_plugin/src/memory_manager/cuda_memory_manager.cpp
rename to modules/nvidia_plugin/src/memory_manager/cuda_memory_manager.cpp
index eb9bb06a1..416db52c3 100644
--- a/modules/cuda_plugin/src/memory_manager/cuda_memory_manager.cpp
+++ b/modules/nvidia_plugin/src/memory_manager/cuda_memory_manager.cpp
@@ -8,7 +8,8 @@
 
 #include "cuda_operation_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 MemoryManager::MemoryManager(DeviceMemBlock::Ptr immutableTensors,
                              MemoryModel::Ptr mutableMemoryModel,
@@ -59,4 +60,5 @@ Workbuffers MemoryManager::workBuffers(const IOperationExec& operation,
     return result;
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/cuda_memory_manager.hpp b/modules/nvidia_plugin/src/memory_manager/cuda_memory_manager.hpp
similarity index 97%
rename from modules/cuda_plugin/src/memory_manager/cuda_memory_manager.hpp
rename to modules/nvidia_plugin/src/memory_manager/cuda_memory_manager.hpp
index ff29c084d..8bbce0385 100644
--- a/modules/cuda_plugin/src/memory_manager/cuda_memory_manager.hpp
+++ b/modules/nvidia_plugin/src/memory_manager/cuda_memory_manager.hpp
@@ -13,7 +13,8 @@
 #include "cuda_workbuffers.hpp"
 #include "memory_manager/model/cuda_memory_model.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class MemoryModel;
 class IOperationMeta;
@@ -97,4 +98,5 @@ class MemoryManager {
     DeviceMemBlock::Ptr immutable_workbuffers_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/cuda_memory_pool.cpp b/modules/nvidia_plugin/src/memory_manager/cuda_memory_pool.cpp
similarity index 95%
rename from modules/cuda_plugin/src/memory_manager/cuda_memory_pool.cpp
rename to modules/nvidia_plugin/src/memory_manager/cuda_memory_pool.cpp
index 5ac08bff2..7071516b5 100644
--- a/modules/cuda_plugin/src/memory_manager/cuda_memory_pool.cpp
+++ b/modules/nvidia_plugin/src/memory_manager/cuda_memory_pool.cpp
@@ -8,7 +8,8 @@
 
 #include "model/cuda_memory_model.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 MemoryPool::MemoryPool(const size_t num, std::shared_ptr<MemoryModel> memoryModel) {
     memory_blocks_.reserve(num);
@@ -60,4 +61,5 @@ void MemoryPool::PushBack(std::unique_ptr<DeviceMemBlock> memManager) {
     cond_var_.notify_one();
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/cuda_memory_pool.hpp b/modules/nvidia_plugin/src/memory_manager/cuda_memory_pool.hpp
similarity index 97%
rename from modules/cuda_plugin/src/memory_manager/cuda_memory_pool.hpp
rename to modules/nvidia_plugin/src/memory_manager/cuda_memory_pool.hpp
index c9ef219c5..ec704a62b 100644
--- a/modules/cuda_plugin/src/memory_manager/cuda_memory_pool.hpp
+++ b/modules/nvidia_plugin/src/memory_manager/cuda_memory_pool.hpp
@@ -13,7 +13,8 @@
 
 class MemoryPoolTest;
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * @brief MemoryPool provides currently available DeviceMemBlock.
@@ -98,4 +99,5 @@ class MemoryPool : public std::enable_shared_from_this<MemoryPool> {
     std::vector<std::unique_ptr<DeviceMemBlock>> memory_blocks_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/cuda_workbuffers.hpp b/modules/nvidia_plugin/src/memory_manager/cuda_workbuffers.hpp
similarity index 94%
rename from modules/cuda_plugin/src/memory_manager/cuda_workbuffers.hpp
rename to modules/nvidia_plugin/src/memory_manager/cuda_workbuffers.hpp
index 5c87275e6..03e61b2df 100644
--- a/modules/cuda_plugin/src/memory_manager/cuda_workbuffers.hpp
+++ b/modules/nvidia_plugin/src/memory_manager/cuda_workbuffers.hpp
@@ -9,7 +9,8 @@
 
 #include "tensor_types.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * @brief WorkbufferRequest - a POD structure describing operator's memory demands
@@ -52,4 +53,5 @@ struct WorkbufferIds {
     vector_of_ids mutableIds;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/model/cuda_immutable_memory_model_builder.cpp b/modules/nvidia_plugin/src/memory_manager/model/cuda_immutable_memory_model_builder.cpp
similarity index 90%
rename from modules/cuda_plugin/src/memory_manager/model/cuda_immutable_memory_model_builder.cpp
rename to modules/nvidia_plugin/src/memory_manager/model/cuda_immutable_memory_model_builder.cpp
index 42739e9a1..1244ccb58 100644
--- a/modules/cuda_plugin/src/memory_manager/model/cuda_immutable_memory_model_builder.cpp
+++ b/modules/nvidia_plugin/src/memory_manager/model/cuda_immutable_memory_model_builder.cpp
@@ -8,7 +8,8 @@
 
 #include "memory_manager/model/details/cuda_memory_utils.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 ImmutableMemoryModelBuilder::ImmutableMemoryModelBuilder() : end_offset_{0} {}
 
@@ -25,4 +26,5 @@ MemoryModel::Ptr ImmutableMemoryModelBuilder::build() const {
     return std::make_shared<MemoryModel>(end_offset_, offsets_);
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/model/cuda_immutable_memory_model_builder.hpp b/modules/nvidia_plugin/src/memory_manager/model/cuda_immutable_memory_model_builder.hpp
similarity index 92%
rename from modules/cuda_plugin/src/memory_manager/model/cuda_immutable_memory_model_builder.hpp
rename to modules/nvidia_plugin/src/memory_manager/model/cuda_immutable_memory_model_builder.hpp
index 512edcdd9..197920d67 100644
--- a/modules/cuda_plugin/src/memory_manager/model/cuda_immutable_memory_model_builder.hpp
+++ b/modules/nvidia_plugin/src/memory_manager/model/cuda_immutable_memory_model_builder.hpp
@@ -6,7 +6,8 @@
 
 #include "memory_manager/model/cuda_memory_model.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * Builds MemoryModel for immutable memory blob wich contains constant
@@ -42,4 +43,5 @@ class ImmutableMemoryModelBuilder {
     std::unordered_map<BufferID, ptrdiff_t> offsets_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/model/cuda_memory_model.cpp b/modules/nvidia_plugin/src/memory_manager/model/cuda_memory_model.cpp
similarity index 93%
rename from modules/cuda_plugin/src/memory_manager/model/cuda_memory_model.cpp
rename to modules/nvidia_plugin/src/memory_manager/model/cuda_memory_model.cpp
index cc9bcf2e0..5a0fca911 100644
--- a/modules/cuda_plugin/src/memory_manager/model/cuda_memory_model.cpp
+++ b/modules/nvidia_plugin/src/memory_manager/model/cuda_memory_model.cpp
@@ -6,7 +6,8 @@
 
 #include <gsl/pointers>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 MemoryModel::MemoryModel(size_t bsize, const std::unordered_map<BufferID, ptrdiff_t>& offsets)
     : bsize_{bsize}, offsets_{offsets} {
@@ -36,4 +37,5 @@ bool MemoryModel::offsetForBuffer(BufferID id, ptrdiff_t& offset) const {
     return true;
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/model/cuda_memory_model.hpp b/modules/nvidia_plugin/src/memory_manager/model/cuda_memory_model.hpp
similarity index 94%
rename from modules/cuda_plugin/src/memory_manager/model/cuda_memory_model.hpp
rename to modules/nvidia_plugin/src/memory_manager/model/cuda_memory_model.hpp
index 12202bf72..a8dbd8dfb 100644
--- a/modules/cuda_plugin/src/memory_manager/model/cuda_memory_model.hpp
+++ b/modules/nvidia_plugin/src/memory_manager/model/cuda_memory_model.hpp
@@ -10,7 +10,8 @@
 #include <memory_manager/tensor_types.hpp>
 #include <unordered_map>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * @brief MemoryModel describes a size of continous memory block on CUDA device
@@ -51,4 +52,5 @@ class MemoryModel {
     std::unordered_map<BufferID, ptrdiff_t> offsets_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/model/cuda_memory_model_builder.cpp b/modules/nvidia_plugin/src/memory_manager/model/cuda_memory_model_builder.cpp
similarity index 91%
rename from modules/cuda_plugin/src/memory_manager/model/cuda_memory_model_builder.cpp
rename to modules/nvidia_plugin/src/memory_manager/model/cuda_memory_model_builder.cpp
index 983fdfd97..abf83892b 100644
--- a/modules/cuda_plugin/src/memory_manager/model/cuda_memory_model_builder.cpp
+++ b/modules/nvidia_plugin/src/memory_manager/model/cuda_memory_model_builder.cpp
@@ -8,7 +8,8 @@
 
 #include "memory_manager/model/details/cuda_memory_utils.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 void MemoryModelBuilder::addAllocation(BufferID id, int producerIndex, int lastConsumerIndex, size_t bsize) {
     IE_ASSERT(bsize > 0);  // Verify that allocation size isn't zero.
@@ -26,4 +27,5 @@ MemoryModel::Ptr MemoryModelBuilder::build() {
     return std::make_shared<MemoryModel>(blob_size, offsets_);
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/model/cuda_memory_model_builder.hpp b/modules/nvidia_plugin/src/memory_manager/model/cuda_memory_model_builder.hpp
similarity index 93%
rename from modules/cuda_plugin/src/memory_manager/model/cuda_memory_model_builder.hpp
rename to modules/nvidia_plugin/src/memory_manager/model/cuda_memory_model_builder.hpp
index 455b9c954..f63f179bd 100644
--- a/modules/cuda_plugin/src/memory_manager/model/cuda_memory_model_builder.hpp
+++ b/modules/nvidia_plugin/src/memory_manager/model/cuda_memory_model_builder.hpp
@@ -7,7 +7,8 @@
 #include "memory_manager/model/cuda_memory_model.hpp"
 #include "memory_manager/model/details/cuda_memory_solver.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * Builds MemoryModel for mutable memory blob wich contains input,
@@ -40,4 +41,5 @@ class MemoryModelBuilder {
     std::unordered_map<BufferID, ptrdiff_t> offsets_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/model/details/cuda_memory_solver.cpp b/modules/nvidia_plugin/src/memory_manager/model/details/cuda_memory_solver.cpp
similarity index 98%
rename from modules/cuda_plugin/src/memory_manager/model/details/cuda_memory_solver.cpp
rename to modules/nvidia_plugin/src/memory_manager/model/details/cuda_memory_solver.cpp
index 368faab79..312b70e3c 100644
--- a/modules/cuda_plugin/src/memory_manager/model/details/cuda_memory_solver.cpp
+++ b/modules/nvidia_plugin/src/memory_manager/model/details/cuda_memory_solver.cpp
@@ -10,7 +10,8 @@
 #include <map>
 #include <vector>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 MemorySolver::MemorySolver(const std::vector<Box> &boxes) : _boxes(boxes) {
     int max_ts = 0;
@@ -142,4 +143,5 @@ void MemorySolver::calcDepth() {
     }
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/model/details/cuda_memory_solver.hpp b/modules/nvidia_plugin/src/memory_manager/model/details/cuda_memory_solver.hpp
similarity index 96%
rename from modules/cuda_plugin/src/memory_manager/model/details/cuda_memory_solver.hpp
rename to modules/nvidia_plugin/src/memory_manager/model/details/cuda_memory_solver.hpp
index 96fa855bd..fd6bd91fe 100644
--- a/modules/cuda_plugin/src/memory_manager/model/details/cuda_memory_solver.hpp
+++ b/modules/nvidia_plugin/src/memory_manager/model/details/cuda_memory_solver.hpp
@@ -15,7 +15,8 @@
 
 #include "ie_api.h"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * @brief Helps to solve issue of optimal memory allocation only for particular
@@ -91,4 +92,5 @@ class MemorySolver {
     void calcDepth();
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/model/details/cuda_memory_utils.cpp b/modules/nvidia_plugin/src/memory_manager/model/details/cuda_memory_utils.cpp
similarity index 81%
rename from modules/cuda_plugin/src/memory_manager/model/details/cuda_memory_utils.cpp
rename to modules/nvidia_plugin/src/memory_manager/model/details/cuda_memory_utils.cpp
index 11a409a6b..da7ccd57e 100644
--- a/modules/cuda_plugin/src/memory_manager/model/details/cuda_memory_utils.cpp
+++ b/modules/nvidia_plugin/src/memory_manager/model/details/cuda_memory_utils.cpp
@@ -6,11 +6,13 @@
 
 #include "memory_manager/model/cuda_memory_model.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 size_t applyAllignment(size_t value) {
     constexpr size_t allignment = CUDA::memoryAlignment;
     return (value % allignment) == 0 ? value : value - (value % allignment) + allignment;
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/model/details/cuda_memory_utils.hpp b/modules/nvidia_plugin/src/memory_manager/model/details/cuda_memory_utils.hpp
similarity index 82%
rename from modules/cuda_plugin/src/memory_manager/model/details/cuda_memory_utils.hpp
rename to modules/nvidia_plugin/src/memory_manager/model/details/cuda_memory_utils.hpp
index 676f1db5d..38e2c8842 100644
--- a/modules/cuda_plugin/src/memory_manager/model/details/cuda_memory_utils.hpp
+++ b/modules/nvidia_plugin/src/memory_manager/model/details/cuda_memory_utils.hpp
@@ -6,7 +6,8 @@
 
 #include <cstddef>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * Applies CUDA device specific allignment.
@@ -17,4 +18,5 @@ namespace CUDAPlugin {
  */
 size_t applyAllignment(size_t value);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/memory_manager/tensor_types.hpp b/modules/nvidia_plugin/src/memory_manager/tensor_types.hpp
similarity index 95%
rename from modules/cuda_plugin/src/memory_manager/tensor_types.hpp
rename to modules/nvidia_plugin/src/memory_manager/tensor_types.hpp
index a34f848e8..d8ffe0edc 100644
--- a/modules/cuda_plugin/src/memory_manager/tensor_types.hpp
+++ b/modules/nvidia_plugin/src/memory_manager/tensor_types.hpp
@@ -14,7 +14,8 @@
 #include <unordered_map>
 #include <utility>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 using BufferID = unsigned;
 
@@ -77,4 +78,5 @@ inline std::ostream& operator<<(std::ostream& s, const TensorID& t) {
     return s;
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/activation_forward_cudnn_base.cpp b/modules/nvidia_plugin/src/ops/activation_forward_cudnn_base.cpp
similarity index 88%
rename from modules/cuda_plugin/src/ops/activation_forward_cudnn_base.cpp
rename to modules/nvidia_plugin/src/ops/activation_forward_cudnn_base.cpp
index d3daeadac..8df4d1e04 100644
--- a/modules/cuda_plugin/src/ops/activation_forward_cudnn_base.cpp
+++ b/modules/nvidia_plugin/src/ops/activation_forward_cudnn_base.cpp
@@ -12,7 +12,8 @@
 
 #include "converters.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 ActivationForwardCuDnnOpBase::ActivationForwardCuDnnOpBase(std::unique_ptr<CUDA::DnnActivationDescriptor> opDesc,
                                                            const CreationContext& context,
@@ -29,7 +30,7 @@ ActivationForwardCuDnnOpBase::ActivationForwardCuDnnOpBase(std::unique_ptr<CUDA:
 
     if (std::find(supported_types.begin(), supported_types.end(), data_type_) == supported_types.end()) {
         throwIEException(
-            fmt::format("CUDAPlugin::ActivationForwardCuDnnOpBase: unsupported data type: {}", toString(data_type_)));
+            fmt::format("ov::nvidia_gpu::ActivationForwardCuDnnOpBase: unsupported data type: {}", toString(data_type_)));
     }
 
     const auto& shape = node.get_input_shape(0);
@@ -38,7 +39,7 @@ ActivationForwardCuDnnOpBase::ActivationForwardCuDnnOpBase(std::unique_ptr<CUDA:
     const auto in_shape_size = node.get_input_shape(0).size();
     if (in_shape_size > max_shape_size) {
         throwIEException(
-            fmt::format("CUDAPlugin::ActivationForwardCuDnnOpBase: in_shape_size > max_shape_size: in_shape_size = {}, "
+            fmt::format("ov::nvidia_gpu::ActivationForwardCuDnnOpBase: in_shape_size > max_shape_size: in_shape_size = {}, "
                         "max_shape_size = {}",
                         in_shape_size,
                         max_shape_size));
@@ -58,4 +59,5 @@ void ActivationForwardCuDnnOpBase::Execute(const InferenceRequestContext& contex
                                                              outputTensors[0].get());
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/activation_forward_cudnn_base.hpp b/modules/nvidia_plugin/src/ops/activation_forward_cudnn_base.hpp
similarity index 93%
rename from modules/cuda_plugin/src/ops/activation_forward_cudnn_base.hpp
rename to modules/nvidia_plugin/src/ops/activation_forward_cudnn_base.hpp
index 59a03f842..203fb9022 100644
--- a/modules/cuda_plugin/src/ops/activation_forward_cudnn_base.hpp
+++ b/modules/nvidia_plugin/src/ops/activation_forward_cudnn_base.hpp
@@ -11,7 +11,8 @@
 #include <initializer_list>
 #include <ngraph/node.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class ActivationForwardCuDnnOpBase : public OperationCuDnn {
 public:
@@ -37,4 +38,5 @@ class ActivationForwardCuDnnOpBase : public OperationCuDnn {
     cudnnDataType_t data_type_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/add.cpp b/modules/nvidia_plugin/src/ops/add.cpp
similarity index 94%
rename from modules/cuda_plugin/src/ops/add.cpp
rename to modules/nvidia_plugin/src/ops/add.cpp
index 55b36c385..0947a13b5 100644
--- a/modules/cuda_plugin/src/ops/add.cpp
+++ b/modules/nvidia_plugin/src/ops/add.cpp
@@ -11,7 +11,8 @@
 #include "add_cudnn.hpp"
 #include "cuda_operation_registry.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 static OperationBase::Ptr addFactory(const CreationContext& context,
                                      const std::shared_ptr<ov::Node>& in_node,
@@ -41,4 +42,5 @@ static OperationBase::Ptr addFactory(const CreationContext& context,
 
 OPERATION_REGISTER_FACTORY(addFactory, Add)
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/add_cuda.hpp b/modules/nvidia_plugin/src/ops/add_cuda.hpp
similarity index 79%
rename from modules/cuda_plugin/src/ops/add_cuda.hpp
rename to modules/nvidia_plugin/src/ops/add_cuda.hpp
index f2971adc1..ce5a8c210 100644
--- a/modules/cuda_plugin/src/ops/add_cuda.hpp
+++ b/modules/nvidia_plugin/src/ops/add_cuda.hpp
@@ -9,11 +9,13 @@
 #include "elementwise_binary.hpp"
 #include "kernels/add.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class AddCudaOp : public ElementwiseBinaryOp<ov::op::v1::Add, kernel::Add> {
 public:
     using ElementwiseBinaryOp::ElementwiseBinaryOp;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/add_cudnn.cpp b/modules/nvidia_plugin/src/ops/add_cudnn.cpp
similarity index 85%
rename from modules/cuda_plugin/src/ops/add_cudnn.cpp
rename to modules/nvidia_plugin/src/ops/add_cudnn.cpp
index a069f6268..86a23e24d 100644
--- a/modules/cuda_plugin/src/ops/add_cudnn.cpp
+++ b/modules/nvidia_plugin/src/ops/add_cudnn.cpp
@@ -5,7 +5,8 @@
 
 #include <cuda_operation_registry.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 AddCuDnnOp::AddCuDnnOp(const CreationContext& context,
                        const std::shared_ptr<ov::Node>& node,
@@ -13,4 +14,5 @@ AddCuDnnOp::AddCuDnnOp(const CreationContext& context,
                        IndexCollection&& outputIds)
     : CuDnnTensorOpBase{context, node, move(inputIds), move(outputIds), cudnnOpTensorOp_t::CUDNN_OP_TENSOR_ADD} {}
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/add_cudnn.hpp b/modules/nvidia_plugin/src/ops/add_cudnn.hpp
similarity index 81%
rename from modules/cuda_plugin/src/ops/add_cudnn.hpp
rename to modules/nvidia_plugin/src/ops/add_cudnn.hpp
index 7c037ec26..956842a84 100644
--- a/modules/cuda_plugin/src/ops/add_cudnn.hpp
+++ b/modules/nvidia_plugin/src/ops/add_cudnn.hpp
@@ -6,7 +6,8 @@
 
 #include "cudnn_tensor_op_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class AddCuDnnOp : public CuDnnTensorOpBase {
 public:
@@ -16,4 +17,5 @@ class AddCuDnnOp : public CuDnnTensorOpBase {
                IndexCollection&& outputIds);
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/avgpool.cpp b/modules/nvidia_plugin/src/ops/avgpool.cpp
similarity index 92%
rename from modules/cuda_plugin/src/ops/avgpool.cpp
rename to modules/nvidia_plugin/src/ops/avgpool.cpp
index f5955b9df..8b0cb6438 100644
--- a/modules/cuda_plugin/src/ops/avgpool.cpp
+++ b/modules/nvidia_plugin/src/ops/avgpool.cpp
@@ -8,7 +8,8 @@
 #include <gsl/gsl_assert>
 #include <openvino/op/avg_pool.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 AvgPoolOp::AvgPoolOp(const CreationContext& context,
                      const std::shared_ptr<ov::Node>& node,
@@ -31,4 +32,5 @@ void AvgPoolOp::Execute(const InferenceRequestContext& context,
 
 OPERATION_REGISTER(AvgPoolOp, AvgPool);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/avgpool.hpp b/modules/nvidia_plugin/src/ops/avgpool.hpp
similarity index 88%
rename from modules/cuda_plugin/src/ops/avgpool.hpp
rename to modules/nvidia_plugin/src/ops/avgpool.hpp
index f9fea5309..5f307457a 100644
--- a/modules/cuda_plugin/src/ops/avgpool.hpp
+++ b/modules/nvidia_plugin/src/ops/avgpool.hpp
@@ -8,7 +8,8 @@
 
 #include "pooling_impl.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class AvgPoolOp : public OperationCuDnn {
 public:
@@ -25,4 +26,5 @@ class AvgPoolOp : public OperationCuDnn {
     PoolingImpl impl_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/broadcast.cpp b/modules/nvidia_plugin/src/ops/broadcast.cpp
similarity index 93%
rename from modules/cuda_plugin/src/ops/broadcast.cpp
rename to modules/nvidia_plugin/src/ops/broadcast.cpp
index e38a131b1..49bdee7a0 100644
--- a/modules/cuda_plugin/src/ops/broadcast.cpp
+++ b/modules/nvidia_plugin/src/ops/broadcast.cpp
@@ -11,7 +11,8 @@
 #include "cuda_operation_registry.hpp"
 #include "ngraph/shape.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 namespace {
 ov::Shape shape_from_constant_value(const ov::Node* constant_node) {
@@ -50,7 +51,7 @@ BroadcastOp::BroadcastOp(const CreationContext& context,
     broadcast_params_ = NumpyBroadcastParams::create(in_shape, out_shape);
     broadcast_params_->addWorkbufferRequests(immutable_buffer_sizes_);
 
-    const auto element_type = convertDataType<CUDAPlugin::kernel::Type_t>(node.get_input_element_type(0));
+    const auto element_type = convertDataType<ov::nvidia_gpu::kernel::Type_t>(node.get_input_element_type(0));
     const size_t dst_num_elements = ngraph::shape_size(out_shape);
     const size_t max_threads_per_block = context.device().props().maxThreadsPerBlock;
     kernel_.emplace(element_type, dst_num_elements, max_threads_per_block);
@@ -72,4 +73,5 @@ void BroadcastOp::InitSharedImmutableWorkbuffers(const Buffers& buffers) {
 
 OPERATION_REGISTER(BroadcastOp, Broadcast);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/broadcast.hpp b/modules/nvidia_plugin/src/ops/broadcast.hpp
similarity index 92%
rename from modules/cuda_plugin/src/ops/broadcast.hpp
rename to modules/nvidia_plugin/src/ops/broadcast.hpp
index 82438506a..53d15b772 100644
--- a/modules/cuda_plugin/src/ops/broadcast.hpp
+++ b/modules/nvidia_plugin/src/ops/broadcast.hpp
@@ -9,7 +9,8 @@
 #include "kernels/broadcast.hpp"
 #include "ngraph/op/broadcast.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class BroadcastOp : public OperationBase {
 public:
@@ -33,4 +34,5 @@ class BroadcastOp : public OperationBase {
     std::optional<kernel::Broadcast> kernel_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/clamp.cpp b/modules/nvidia_plugin/src/ops/clamp.cpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/clamp.cpp
rename to modules/nvidia_plugin/src/ops/clamp.cpp
index a92a93d65..6750cfb6d 100644
--- a/modules/cuda_plugin/src/ops/clamp.cpp
+++ b/modules/nvidia_plugin/src/ops/clamp.cpp
@@ -13,7 +13,8 @@
 #include "clamp_cudnn.hpp"
 #include "clipped_relu_cudnn.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 using IndexCollection = OperationBase::IndexCollection;
 
@@ -53,4 +54,5 @@ static OperationBase::Ptr clampFactory(const CreationContext& context,
 
 OPERATION_REGISTER_FACTORY(clampFactory, Clamp)
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/clamp_cuda.cpp b/modules/nvidia_plugin/src/ops/clamp_cuda.cpp
similarity index 90%
rename from modules/cuda_plugin/src/ops/clamp_cuda.cpp
rename to modules/nvidia_plugin/src/ops/clamp_cuda.cpp
index b7633dc56..d032ae243 100644
--- a/modules/cuda_plugin/src/ops/clamp_cuda.cpp
+++ b/modules/nvidia_plugin/src/ops/clamp_cuda.cpp
@@ -13,7 +13,8 @@
 #include "converters.hpp"
 #include "error.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 ClampCudaOp::ClampCudaOp(const CreationContext& context,
                          const NodeOp& node,
@@ -38,7 +39,7 @@ ClampCudaOp::ClampCudaOp(const CreationContext& context,
     const double min = node.get_min();
     const double max = node.get_max();
     kernel_ = kernel::Clamp{
-        convertDataType<CUDAPlugin::kernel::Type_t>(element_type), max_threads_per_block, num_elements, min, max};
+        convertDataType<ov::nvidia_gpu::kernel::Type_t>(element_type), max_threads_per_block, num_elements, min, max};
 }
 
 void ClampCudaOp::Execute(const InferenceRequestContext& context,
@@ -52,4 +53,5 @@ void ClampCudaOp::Execute(const InferenceRequestContext& context,
     (*kernel_)(context.getThreadContext().stream().get(), inputTensors[0].get(), outputTensors[0].get());
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/clamp_cuda.hpp b/modules/nvidia_plugin/src/ops/clamp_cuda.hpp
similarity index 89%
rename from modules/cuda_plugin/src/ops/clamp_cuda.hpp
rename to modules/nvidia_plugin/src/ops/clamp_cuda.hpp
index c642b2467..b8b5f4c55 100644
--- a/modules/cuda_plugin/src/ops/clamp_cuda.hpp
+++ b/modules/nvidia_plugin/src/ops/clamp_cuda.hpp
@@ -9,7 +9,8 @@
 
 #include "kernels/clamp.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class ClampCudaOp : public OperationBase {
 public:
@@ -29,4 +30,5 @@ class ClampCudaOp : public OperationBase {
     std::optional<kernel::Clamp> kernel_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/clamp_cudnn.cpp b/modules/nvidia_plugin/src/ops/clamp_cudnn.cpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/clamp_cudnn.cpp
rename to modules/nvidia_plugin/src/ops/clamp_cudnn.cpp
index 46fcc9996..fd1c8f404 100644
--- a/modules/cuda_plugin/src/ops/clamp_cudnn.cpp
+++ b/modules/nvidia_plugin/src/ops/clamp_cudnn.cpp
@@ -17,7 +17,8 @@
 
 #include "converters.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 ClampCuDnnOp::ClampCuDnnOp(const CreationContext& context,
                            const NodeOp& node,
@@ -49,7 +50,7 @@ ClampCuDnnOp::ClampCuDnnOp(const CreationContext& context,
     Expects(node.get_output_element_type(0) == node.get_input_element_type(0));
 
     if (min_ > max_) {
-        throwIEException(fmt::format("CUDAPlugin::ClampCuDnnOp: Clamp min_ > max_: min_ = {}, max_ = {}", min_, max_));
+        throwIEException(fmt::format("ov::nvidia_gpu::ClampCuDnnOp: Clamp min_ > max_: min_ = {}, max_ = {}", min_, max_));
     }
 }
 
@@ -143,4 +144,5 @@ void ClampCuDnnOp::initBuffers(const Buffers& buffers) const {
     stream.upload(buffers[min_index], &min, el_size);
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/clamp_cudnn.hpp b/modules/nvidia_plugin/src/ops/clamp_cudnn.hpp
similarity index 94%
rename from modules/cuda_plugin/src/ops/clamp_cudnn.hpp
rename to modules/nvidia_plugin/src/ops/clamp_cudnn.hpp
index 2156b598c..cd8877e26 100644
--- a/modules/cuda_plugin/src/ops/clamp_cudnn.hpp
+++ b/modules/nvidia_plugin/src/ops/clamp_cudnn.hpp
@@ -14,7 +14,8 @@
 #include <cuda_operation_base.hpp>
 #include <openvino/op/clamp.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class ClampCuDnnOp : public OperationCuDnn {
 public:
@@ -51,4 +52,5 @@ class ClampCuDnnOp : public OperationCuDnn {
     const double max_;
     const double min_;
 };
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/clipped_relu_cudnn.cpp b/modules/nvidia_plugin/src/ops/clipped_relu_cudnn.cpp
similarity index 74%
rename from modules/cuda_plugin/src/ops/clipped_relu_cudnn.cpp
rename to modules/nvidia_plugin/src/ops/clipped_relu_cudnn.cpp
index 8bc9d2f25..e4136b4cf 100644
--- a/modules/cuda_plugin/src/ops/clipped_relu_cudnn.cpp
+++ b/modules/nvidia_plugin/src/ops/clipped_relu_cudnn.cpp
@@ -9,7 +9,8 @@
 #include <cuda/dnn.hpp>
 #include <cuda_operation_registry.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 ClippedReluCuDnnOp::ClippedReluCuDnnOp(const CreationContext& context,
                                        const NodeOp& node,
@@ -23,11 +24,12 @@ ClippedReluCuDnnOp::ClippedReluCuDnnOp(const CreationContext& context,
     const auto min = node.get_min();
     const auto max = node.get_max();
     if (min != 0.0) {
-        throwIEException(fmt::format("CUDAPlugin::ClippedReluCuDnnOp: Clamp min != 0.0, min = {}", min));
+        throwIEException(fmt::format("ov::nvidia_gpu::ClippedReluCuDnnOp: Clamp min != 0.0, min = {}", min));
     }
     if (max < 0.0) {
-        throwIEException(fmt::format("CUDAPlugin::ClippedReluCuDnnOp: Clamp max < 0.0, max = {}", max));
+        throwIEException(fmt::format("ov::nvidia_gpu::ClippedReluCuDnnOp: Clamp max < 0.0, max = {}", max));
     }
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/clipped_relu_cudnn.hpp b/modules/nvidia_plugin/src/ops/clipped_relu_cudnn.hpp
similarity index 85%
rename from modules/cuda_plugin/src/ops/clipped_relu_cudnn.hpp
rename to modules/nvidia_plugin/src/ops/clipped_relu_cudnn.hpp
index 45329436f..bea576e22 100644
--- a/modules/cuda_plugin/src/ops/clipped_relu_cudnn.hpp
+++ b/modules/nvidia_plugin/src/ops/clipped_relu_cudnn.hpp
@@ -8,7 +8,8 @@
 
 #include "activation_forward_cudnn_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class ClippedReluCuDnnOp : public ActivationForwardCuDnnOpBase {
 public:
@@ -20,4 +21,5 @@ class ClippedReluCuDnnOp : public ActivationForwardCuDnnOpBase {
                        IndexCollection&& outputIds);
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/comparison.cpp b/modules/nvidia_plugin/src/ops/comparison.cpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/comparison.cpp
rename to modules/nvidia_plugin/src/ops/comparison.cpp
index 0995f7220..de5d686f4 100644
--- a/modules/cuda_plugin/src/ops/comparison.cpp
+++ b/modules/nvidia_plugin/src/ops/comparison.cpp
@@ -9,7 +9,8 @@
 
 #include "converters.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 static constexpr auto kNumOfDim = 5u;
 static constexpr auto kOffsetBufferSize = kNumOfDim * sizeof(size_t);
@@ -77,7 +78,7 @@ Comparison::Comparison(const CreationContext& context,
     const auto threads_per_block = (num_blocks == 1) ? output_size : max_block_size;
 
     kernel_ = kernel::Comparison{operation_type,
-                                 convertDataType<CUDAPlugin::kernel::Type_t>(element_type),
+                                 convertDataType<ov::nvidia_gpu::kernel::Type_t>(element_type),
                                  output_size,
                                  num_blocks,
                                  threads_per_block};
@@ -129,4 +130,5 @@ void Comparison::calculateOffsets() {
     }
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/comparison.hpp b/modules/nvidia_plugin/src/ops/comparison.hpp
similarity index 93%
rename from modules/cuda_plugin/src/ops/comparison.hpp
rename to modules/nvidia_plugin/src/ops/comparison.hpp
index fcebf894f..cd704bde4 100644
--- a/modules/cuda_plugin/src/ops/comparison.hpp
+++ b/modules/nvidia_plugin/src/ops/comparison.hpp
@@ -9,7 +9,8 @@
 #include "cuda_operation_base.hpp"
 #include "kernels/comparison.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class Comparison : public OperationBase {
 public:
@@ -41,4 +42,5 @@ class Comparison : public OperationBase {
     std::optional<kernel::Comparison> kernel_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/components/numpy_broadcast_params.cpp b/modules/nvidia_plugin/src/ops/components/numpy_broadcast_params.cpp
similarity index 97%
rename from modules/cuda_plugin/src/ops/components/numpy_broadcast_params.cpp
rename to modules/nvidia_plugin/src/ops/components/numpy_broadcast_params.cpp
index bc664af88..00f8d12d0 100644
--- a/modules/cuda_plugin/src/ops/components/numpy_broadcast_params.cpp
+++ b/modules/nvidia_plugin/src/ops/components/numpy_broadcast_params.cpp
@@ -6,7 +6,8 @@
 
 #include <cuda/runtime.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 template <typename T>
 static auto size_in_bytes(const std::vector<T>& v) noexcept {
@@ -68,4 +69,5 @@ kernel::NumpyBroadcastMapper NumpyBroadcastParamsImpl::mapper(
                                         shape_rank_};
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/components/numpy_broadcast_params.h b/modules/nvidia_plugin/src/ops/components/numpy_broadcast_params.h
similarity index 96%
rename from modules/cuda_plugin/src/ops/components/numpy_broadcast_params.h
rename to modules/nvidia_plugin/src/ops/components/numpy_broadcast_params.h
index 228aaa78d..b1723604c 100644
--- a/modules/cuda_plugin/src/ops/components/numpy_broadcast_params.h
+++ b/modules/nvidia_plugin/src/ops/components/numpy_broadcast_params.h
@@ -10,7 +10,8 @@
 #include "kernels/numpy_broadcast_mapper.cuh"
 #include "workbuffer_desc.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class NumpyBroadcastParams {
 public:
@@ -55,4 +56,5 @@ class NumpyBroadcastParamsImpl : public NumpyBroadcastParams {
     WorkbufferDesc ib_broadcasted_dims_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/components/workbuffer_desc.hpp b/modules/nvidia_plugin/src/ops/components/workbuffer_desc.hpp
similarity index 93%
rename from modules/cuda_plugin/src/ops/components/workbuffer_desc.hpp
rename to modules/nvidia_plugin/src/ops/components/workbuffer_desc.hpp
index 7ab31560c..405ebd97e 100644
--- a/modules/cuda_plugin/src/ops/components/workbuffer_desc.hpp
+++ b/modules/nvidia_plugin/src/ops/components/workbuffer_desc.hpp
@@ -8,7 +8,8 @@
 
 #include "memory_manager/cuda_workbuffers.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * Helps operation to handle multiple workbuffers. Allows to easily skip
@@ -44,4 +45,5 @@ class WorkbufferDesc {
     int index_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/concat.cpp b/modules/nvidia_plugin/src/ops/concat.cpp
similarity index 95%
rename from modules/cuda_plugin/src/ops/concat.cpp
rename to modules/nvidia_plugin/src/ops/concat.cpp
index 7cfdebfb6..639351bc7 100644
--- a/modules/cuda_plugin/src/ops/concat.cpp
+++ b/modules/nvidia_plugin/src/ops/concat.cpp
@@ -13,7 +13,8 @@
 
 #include "converters.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 ConcatOp::ConcatOp(const CreationContext& context,
                    const NodeOp& concatOp,
@@ -55,7 +56,7 @@ ConcatOp::ConcatOp(const CreationContext& context,
     const std::size_t numBlocks = (allChunkSize + maxBlockSize - 1) / maxBlockSize;
     const std::size_t threadsPerBlock = (numBlocks == 1) ? allChunkSize : maxBlockSize;
 
-    concat_kernel_ = kernel::Concat{convertDataType<CUDAPlugin::kernel::Type_t>(element_type),
+    concat_kernel_ = kernel::Concat{convertDataType<ov::nvidia_gpu::kernel::Type_t>(element_type),
                                     num_inputs_,
                                     std::move(chunks),
                                     chunk_size,
@@ -92,4 +93,5 @@ void ConcatOp::Execute(const InferenceRequestContext& context,
 }
 
 OPERATION_REGISTER(ConcatOp, Concat);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/concat.hpp b/modules/nvidia_plugin/src/ops/concat.hpp
similarity index 93%
rename from modules/cuda_plugin/src/ops/concat.hpp
rename to modules/nvidia_plugin/src/ops/concat.hpp
index 4efcec6dd..5a4a4efdc 100644
--- a/modules/cuda_plugin/src/ops/concat.hpp
+++ b/modules/nvidia_plugin/src/ops/concat.hpp
@@ -14,7 +14,8 @@
 #include <ngraph/type/element_type.hpp>
 #include <openvino/op/concat.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class ConcatOp : public OperationBase {
 public:
@@ -38,4 +39,5 @@ class ConcatOp : public OperationBase {
     std::optional<kernel::Concat> concat_kernel_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/convert.cpp b/modules/nvidia_plugin/src/ops/convert.cpp
similarity index 88%
rename from modules/cuda_plugin/src/ops/convert.cpp
rename to modules/nvidia_plugin/src/ops/convert.cpp
index ee0b3962f..c3544ea96 100644
--- a/modules/cuda_plugin/src/ops/convert.cpp
+++ b/modules/nvidia_plugin/src/ops/convert.cpp
@@ -14,7 +14,8 @@
 
 #include "converters.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 ConvertOp::ConvertOp(const CreationContext& context,
                      const std::shared_ptr<ov::Node>& node,
@@ -35,8 +36,8 @@ ConvertOp::ConvertOp(const CreationContext& context,
     const auto max_block_size = static_cast<unsigned>(context.device().props().maxThreadsPerBlock);
     const auto num_blocks = (size % max_block_size == 0) ? (size / max_block_size) : (size / max_block_size + 1);
     const auto threads_per_block = (num_blocks == 1) ? size : max_block_size;
-    convert_kernel_ = kernel::Convert(convertDataType<CUDAPlugin::kernel::Type_t>(output_element_type),
-                                      convertDataType<CUDAPlugin::kernel::Type_t>(input_element_type),
+    convert_kernel_ = kernel::Convert(convertDataType<ov::nvidia_gpu::kernel::Type_t>(output_element_type),
+                                      convertDataType<ov::nvidia_gpu::kernel::Type_t>(input_element_type),
                                       size,
                                       num_blocks,
                                       threads_per_block);
@@ -55,4 +56,5 @@ void ConvertOp::Execute(const InferenceRequestContext& context,
 
 OPERATION_REGISTER(ConvertOp, Convert);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/convert.hpp b/modules/nvidia_plugin/src/ops/convert.hpp
similarity index 91%
rename from modules/cuda_plugin/src/ops/convert.hpp
rename to modules/nvidia_plugin/src/ops/convert.hpp
index 76fbedced..5fd36a330 100644
--- a/modules/cuda_plugin/src/ops/convert.hpp
+++ b/modules/nvidia_plugin/src/ops/convert.hpp
@@ -10,7 +10,8 @@
 
 #include "kernels/convert.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class ConvertOp : public OperationBase {
 public:
@@ -30,4 +31,5 @@ class ConvertOp : public OperationBase {
     std::optional<kernel::Convert> convert_kernel_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/convert_color_i420.cpp b/modules/nvidia_plugin/src/ops/convert_color_i420.cpp
similarity index 74%
rename from modules/cuda_plugin/src/ops/convert_color_i420.cpp
rename to modules/nvidia_plugin/src/ops/convert_color_i420.cpp
index f636eb544..c71371d73 100644
--- a/modules/cuda_plugin/src/ops/convert_color_i420.cpp
+++ b/modules/nvidia_plugin/src/ops/convert_color_i420.cpp
@@ -6,9 +6,11 @@
 
 #include <cuda_operation_registry.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 OPERATION_REGISTER(I420toRGBOp, I420toRGB);
 OPERATION_REGISTER(I420toBGROp, I420toBGR);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/convert_color_i420.hpp b/modules/nvidia_plugin/src/ops/convert_color_i420.hpp
similarity index 93%
rename from modules/cuda_plugin/src/ops/convert_color_i420.hpp
rename to modules/nvidia_plugin/src/ops/convert_color_i420.hpp
index 2c757cc2f..92b8e060d 100644
--- a/modules/cuda_plugin/src/ops/convert_color_i420.hpp
+++ b/modules/nvidia_plugin/src/ops/convert_color_i420.hpp
@@ -12,7 +12,8 @@
 #include "openvino/op/i420_to_bgr.hpp"
 #include "openvino/op/i420_to_rgb.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 template <typename TNGraphNode, typename TKernel>
 class I420ConvertColorBase : public OperationBase {
@@ -50,7 +51,7 @@ class I420ConvertColorBase : public OperationBase {
 
         const size_t max_threads_per_block = context.device().props().maxThreadsPerBlock;
         if (single_plane) {
-            kernel_ = TKernel{convertDataType<CUDAPlugin::kernel::Type_t>(element_type),
+            kernel_ = TKernel{convertDataType<ov::nvidia_gpu::kernel::Type_t>(element_type),
                               max_threads_per_block,
                               batch_size,
                               image_h,
@@ -58,7 +59,7 @@ class I420ConvertColorBase : public OperationBase {
                               image_w * image_h * 3 / 2,
                               image_w * image_h * 3 / 2};
         } else {
-            kernel_ = TKernel{convertDataType<CUDAPlugin::kernel::Type_t>(element_type),
+            kernel_ = TKernel{convertDataType<ov::nvidia_gpu::kernel::Type_t>(element_type),
                               max_threads_per_block,
                               batch_size,
                               image_h,
@@ -106,4 +107,5 @@ class I420toBGROp
     using I420ConvertColorBase::I420ConvertColorBase;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/convert_color_nv12.cpp b/modules/nvidia_plugin/src/ops/convert_color_nv12.cpp
similarity index 74%
rename from modules/cuda_plugin/src/ops/convert_color_nv12.cpp
rename to modules/nvidia_plugin/src/ops/convert_color_nv12.cpp
index 216b347b9..fc5779de8 100644
--- a/modules/cuda_plugin/src/ops/convert_color_nv12.cpp
+++ b/modules/nvidia_plugin/src/ops/convert_color_nv12.cpp
@@ -6,9 +6,11 @@
 
 #include <cuda_operation_registry.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 OPERATION_REGISTER(NV12toRGBOp, NV12toRGB);
 OPERATION_REGISTER(NV12toBGROp, NV12toBGR);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/convert_color_nv12.hpp b/modules/nvidia_plugin/src/ops/convert_color_nv12.hpp
similarity index 93%
rename from modules/cuda_plugin/src/ops/convert_color_nv12.hpp
rename to modules/nvidia_plugin/src/ops/convert_color_nv12.hpp
index 5735a9f51..96fa37ef0 100644
--- a/modules/cuda_plugin/src/ops/convert_color_nv12.hpp
+++ b/modules/nvidia_plugin/src/ops/convert_color_nv12.hpp
@@ -12,7 +12,8 @@
 #include "openvino/op/nv12_to_bgr.hpp"
 #include "openvino/op/nv12_to_rgb.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 template <typename TNGraphNode, typename TKernel>
 class NV12ConvertColorBase : public OperationBase {
@@ -50,7 +51,7 @@ class NV12ConvertColorBase : public OperationBase {
 
         const size_t max_threads_per_block = context.device().props().maxThreadsPerBlock;
         if (single_plane) {
-            kernel_ = TKernel{convertDataType<CUDAPlugin::kernel::Type_t>(element_type),
+            kernel_ = TKernel{convertDataType<ov::nvidia_gpu::kernel::Type_t>(element_type),
                               max_threads_per_block,
                               batch_size,
                               image_h,
@@ -58,7 +59,7 @@ class NV12ConvertColorBase : public OperationBase {
                               image_w * image_h * 3 / 2,
                               image_w * image_h * 3 / 2};
         } else {
-            kernel_ = TKernel{convertDataType<CUDAPlugin::kernel::Type_t>(element_type),
+            kernel_ = TKernel{convertDataType<ov::nvidia_gpu::kernel::Type_t>(element_type),
                               max_threads_per_block,
                               batch_size,
                               image_h,
@@ -105,4 +106,5 @@ class NV12toBGROp
     using NV12ConvertColorBase::NV12ConvertColorBase;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/converters.hpp b/modules/nvidia_plugin/src/ops/converters.hpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/converters.hpp
rename to modules/nvidia_plugin/src/ops/converters.hpp
index 88c0945e9..044ac24e6 100644
--- a/modules/cuda_plugin/src/ops/converters.hpp
+++ b/modules/nvidia_plugin/src/ops/converters.hpp
@@ -18,7 +18,8 @@
 
 #include "transformer/nodes/cuda_plugin_custom_node_types.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * Converts OpenVINO data type to T
@@ -188,7 +189,7 @@ inline constexpr std::string_view toString<cudaDataType_t>(const cudaDataType_t&
             return "CUDA_R_32U";
         default:
             throwIEException(
-                fmt::format("CUDAPlugin::toString<cudaDataType_t>(): Unsupported data type: type = {}", type));
+                fmt::format("ov::nvidia_gpu::toString<cudaDataType_t>(): Unsupported data type: type = {}", type));
     }
 }
 
@@ -222,7 +223,7 @@ inline constexpr std::string_view toString<cudnnDataType_t>(const cudnnDataType_
             return "CUDNN_DATA_INT64";
         default:
             throwIEException(
-                fmt::format("CUDAPlugin::toString<cudaDataType_t>(): Unsupported data type: type = {}", type));
+                fmt::format("ov::nvidia_gpu::toString<cudaDataType_t>(): Unsupported data type: type = {}", type));
     }
 }
 
@@ -345,7 +346,7 @@ inline constexpr cudnnDataType_t getCuDnnOpTensorCompType(cudnnDataType_t in0,
                                                           cudnnDataType_t out) {
     auto throwException = [=] {
         throwIEException(
-            fmt::format("CUDAPlugin::getCuDnnOpTensorType(): Unsupported data types: in0 = {}, in1 = {} out = {}",
+            fmt::format("ov::nvidia_gpu::getCuDnnOpTensorType(): Unsupported data types: in0 = {}, in1 = {} out = {}",
                         toString(in0),
                         toString(in1),
                         toString(out)));
@@ -373,4 +374,5 @@ inline constexpr cudnnDataType_t getCuDnnOpTensorCompType(cudnnDataType_t in0,
     return CUDNN_DATA_FLOAT;  // never reached
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/convolution.cpp b/modules/nvidia_plugin/src/ops/convolution.cpp
similarity index 95%
rename from modules/cuda_plugin/src/ops/convolution.cpp
rename to modules/nvidia_plugin/src/ops/convolution.cpp
index 3cd95a479..ed4185ac2 100644
--- a/modules/cuda_plugin/src/ops/convolution.cpp
+++ b/modules/nvidia_plugin/src/ops/convolution.cpp
@@ -14,7 +14,8 @@
 #include "convolution_cudnn_be.hpp"
 #endif  // ENABLE_CUDNN_BACKEND_API
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 static OperationBase::Ptr convolutionFactory(const CreationContext& context,
                                              const std::shared_ptr<ov::Node>& node,
@@ -42,4 +43,5 @@ static OperationBase::Ptr convolutionFactory(const CreationContext& context,
 
 OPERATION_REGISTER_FACTORY(convolutionFactory, Convolution);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/convolution_backprop_data.cpp b/modules/nvidia_plugin/src/ops/convolution_backprop_data.cpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/convolution_backprop_data.cpp
rename to modules/nvidia_plugin/src/ops/convolution_backprop_data.cpp
index afdbb78dc..16da7639c 100644
--- a/modules/cuda_plugin/src/ops/convolution_backprop_data.cpp
+++ b/modules/nvidia_plugin/src/ops/convolution_backprop_data.cpp
@@ -9,7 +9,8 @@
 #include "convolution_components/convolution_components.hpp"
 #include "cuda/constant_factory.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 template <typename T>
 ConvBackpropDataOp<T>::ConvBackpropDataOp(const CreationContext& context,
@@ -44,4 +45,5 @@ void ConvBackpropDataOp<T>::Execute(const InferenceRequestContext& context,
 OPERATION_REGISTER(ConvolutionBackpropDataOp, ConvolutionBackpropData);
 OPERATION_REGISTER(GroupConvolutionBackpropDataOp, GroupConvolutionBackpropData);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/convolution_backprop_data.hpp b/modules/nvidia_plugin/src/ops/convolution_backprop_data.hpp
similarity index 95%
rename from modules/cuda_plugin/src/ops/convolution_backprop_data.hpp
rename to modules/nvidia_plugin/src/ops/convolution_backprop_data.hpp
index 8a57adf34..5f5f5b232 100644
--- a/modules/cuda_plugin/src/ops/convolution_backprop_data.hpp
+++ b/modules/nvidia_plugin/src/ops/convolution_backprop_data.hpp
@@ -9,7 +9,8 @@
 #include "convolution_components/convolution_components.hpp"
 #include "convolution_components/convolution_cudnn_components.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * @brief Implements both `ov::op::v1::ConvolutionBackpropData`
@@ -61,4 +62,5 @@ class GroupConvolutionBackpropDataOp : public ConvBackpropDataOp<ov::op::v1::Gro
     using ConvBackpropDataOp::ConvBackpropDataOp;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/convolution_components/convolution_components.cpp b/modules/nvidia_plugin/src/ops/convolution_components/convolution_components.cpp
similarity index 98%
rename from modules/cuda_plugin/src/ops/convolution_components/convolution_components.cpp
rename to modules/nvidia_plugin/src/ops/convolution_components/convolution_components.cpp
index 8d7271ee6..9db59753c 100644
--- a/modules/cuda_plugin/src/ops/convolution_components/convolution_components.cpp
+++ b/modules/nvidia_plugin/src/ops/convolution_components/convolution_components.cpp
@@ -9,7 +9,7 @@
 #include <ngraph/validation_util.hpp>
 #include <openvino/op/group_conv.hpp>
 
-namespace CUDAPlugin::Convolution::Details {
+namespace ov::nvidia_gpu::Convolution::Details {
 
 constexpr int CONV_1D_DIMS_NUMBER = NON_SPATIAL_DIMS_NUMBER + 1;
 
@@ -186,7 +186,7 @@ template FusedConvolutionParams::FusedConvolutionParams(const nodes::FusedConvol
 template FusedConvolutionParams::FusedConvolutionParams(const nodes::FusedGroupConvolution& node);
 
 FusedConvolutionBackwardDataParams::FusedConvolutionBackwardDataParams(
-    const CUDAPlugin::nodes::FusedConvBackpropData& node)
+    const ov::nvidia_gpu::nodes::FusedConvBackpropData& node)
     : conv_{node} {
     Expects(conv_.NumberOfSpatialDims() == 2 || conv_.NumberOfSpatialDims() == 3);
     if (node.inputs().size() == 4) {
@@ -198,4 +198,4 @@ FusedConvolutionBackwardDataParams::FusedConvolutionBackwardDataParams(
     }
 }
 
-}  // namespace CUDAPlugin::Convolution::Details
+}  // namespace ov::nvidia_gpu::Convolution::Details
diff --git a/modules/cuda_plugin/src/ops/convolution_components/convolution_components.hpp b/modules/nvidia_plugin/src/ops/convolution_components/convolution_components.hpp
similarity index 89%
rename from modules/cuda_plugin/src/ops/convolution_components/convolution_components.hpp
rename to modules/nvidia_plugin/src/ops/convolution_components/convolution_components.hpp
index 720ea3b79..c673f870c 100644
--- a/modules/cuda_plugin/src/ops/convolution_components/convolution_components.hpp
+++ b/modules/nvidia_plugin/src/ops/convolution_components/convolution_components.hpp
@@ -10,7 +10,7 @@
 #include "transformer/nodes/fused_convolution.hpp"
 #include "transformer/nodes/fused_convolution_backprop_data.hpp"
 
-namespace CUDAPlugin::Convolution::Details {
+namespace ov::nvidia_gpu::Convolution::Details {
 
 constexpr int NON_SPATIAL_DIMS_NUMBER = 2;
 
@@ -87,7 +87,7 @@ struct ConvolutionBackwardDataParams {
 
 /**
  * @brief Defines tensor indices for the following nodes:
- *  - `CUDAPlugin::nodes::FusedConvolution`
+ *  - `ov::nvidia_gpu::nodes::FusedConvolution`
  */
 struct FusedConvolutionIndices {
     static constexpr size_t input = 0;
@@ -99,7 +99,7 @@ struct FusedConvolutionIndices {
 
 /**
  * @brief Unified parameters as they are consumed by the following nodes:
- *  - `CUDAPlugin::nodes::FusedConvolution`
+ *  - `ov::nvidia_gpu::nodes::FusedConvolution`
  */
 struct FusedConvolutionParams {
     template <typename TConvNode>
@@ -108,12 +108,12 @@ struct FusedConvolutionParams {
     ConvolutionParams conv_;
     ov::Shape bias_shape_;
     std::optional<ov::Shape> add_shape_;
-    CUDAPlugin::nodes::ActivationMode activation_;
+    ov::nvidia_gpu::nodes::ActivationMode activation_;
 };
 
 /**
  * @brief Defines tensor indices for the following nodes:
- *  - `CUDAPlugin::nodes::FusedConvBackpropData`
+ *  - `ov::nvidia_gpu::nodes::FusedConvBackpropData`
  */
 template <std::size_t InputSize>
 struct FusedConvolutionBackwardDataIndices;
@@ -137,13 +137,13 @@ struct FusedConvolutionBackwardDataIndices<4> {
 
 /**
  * @brief Unified parameters as they are consumed by the following nodes:
- *  - `CUDAPlugin::nodes::FusedConvBackpropData`
+ *  - `ov::nvidia_gpu::nodes::FusedConvBackpropData`
  */
 struct FusedConvolutionBackwardDataParams {
-    FusedConvolutionBackwardDataParams(const CUDAPlugin::nodes::FusedConvBackpropData& node);
+    FusedConvolutionBackwardDataParams(const ov::nvidia_gpu::nodes::FusedConvBackpropData& node);
 
     ConvolutionBackwardDataParams conv_;
     ov::Shape add_shape_;
 };
 
-}  // namespace CUDAPlugin::Convolution::Details
+}  // namespace ov::nvidia_gpu::Convolution::Details
diff --git a/modules/cuda_plugin/src/ops/convolution_components/convolution_cudnn_components.cpp b/modules/nvidia_plugin/src/ops/convolution_components/convolution_cudnn_components.cpp
similarity index 99%
rename from modules/cuda_plugin/src/ops/convolution_components/convolution_cudnn_components.cpp
rename to modules/nvidia_plugin/src/ops/convolution_components/convolution_cudnn_components.cpp
index fd8f4ec33..369e6c7ee 100644
--- a/modules/cuda_plugin/src/ops/convolution_components/convolution_cudnn_components.cpp
+++ b/modules/nvidia_plugin/src/ops/convolution_components/convolution_cudnn_components.cpp
@@ -13,7 +13,7 @@
 #include <ngraph/util.hpp>
 #include <ops/converters.hpp>
 
-namespace CUDAPlugin::Convolution::Details {
+namespace ov::nvidia_gpu::Convolution::Details {
 
 ConvolutionParamsCuDnn::ConvolutionParamsCuDnn(const Convolution::Details::ConvolutionParams& params)
     : number_of_dims_{static_cast<int>(params.NumberOfDims())},
@@ -502,4 +502,4 @@ std::shared_ptr<CUDA::DnnActivationDescriptor> MakeFusedActivationDescriptor(nod
     return desc;
 }
 
-}  // namespace CUDAPlugin::Convolution::Details
+}  // namespace ov::nvidia_gpu::Convolution::Details
diff --git a/modules/cuda_plugin/src/ops/convolution_components/convolution_cudnn_components.hpp b/modules/nvidia_plugin/src/ops/convolution_components/convolution_cudnn_components.hpp
similarity index 98%
rename from modules/cuda_plugin/src/ops/convolution_components/convolution_cudnn_components.hpp
rename to modules/nvidia_plugin/src/ops/convolution_components/convolution_cudnn_components.hpp
index d92fa8c42..8ca068d46 100644
--- a/modules/cuda_plugin/src/ops/convolution_components/convolution_cudnn_components.hpp
+++ b/modules/nvidia_plugin/src/ops/convolution_components/convolution_cudnn_components.hpp
@@ -9,7 +9,7 @@
 #include "convolution_components.hpp"
 #include "cuda/dnn.hpp"
 
-namespace CUDAPlugin::Convolution::Details {
+namespace ov::nvidia_gpu::Convolution::Details {
 
 /**
  * @brief Presents convolution parameters in a form suitable for cuDNN API.
@@ -157,4 +157,4 @@ std::shared_ptr<CUDA::DnnTensorDescriptor> MakeFusedAddDescriptor(const ov::Shap
                                                                   ov::element::Type_t element_type);
 std::shared_ptr<CUDA::DnnActivationDescriptor> MakeFusedActivationDescriptor(nodes::ActivationMode mode);
 
-}  // namespace CUDAPlugin::Convolution::Details
+}  // namespace ov::nvidia_gpu::Convolution::Details
diff --git a/modules/cuda_plugin/src/ops/convolution_cudnn.cpp b/modules/nvidia_plugin/src/ops/convolution_cudnn.cpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/convolution_cudnn.cpp
rename to modules/nvidia_plugin/src/ops/convolution_cudnn.cpp
index fc182fc1d..e6e2bd292 100644
--- a/modules/cuda_plugin/src/ops/convolution_cudnn.cpp
+++ b/modules/nvidia_plugin/src/ops/convolution_cudnn.cpp
@@ -11,7 +11,8 @@
 
 #include "cuda/constant_factory.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 ConvolutionCuDnn::ConvolutionCuDnn(const CreationContext& context,
                                    const ov::Node& node,
@@ -49,4 +50,5 @@ WorkbufferRequest ConvolutionCuDnn::GetWorkBufferRequest() const {
     else
         return {{}, {}};
 }
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/convolution_cudnn.hpp b/modules/nvidia_plugin/src/ops/convolution_cudnn.hpp
similarity index 92%
rename from modules/cuda_plugin/src/ops/convolution_cudnn.hpp
rename to modules/nvidia_plugin/src/ops/convolution_cudnn.hpp
index d2640e5c4..068562c70 100644
--- a/modules/cuda_plugin/src/ops/convolution_cudnn.hpp
+++ b/modules/nvidia_plugin/src/ops/convolution_cudnn.hpp
@@ -9,7 +9,8 @@
 #include "convolution_components/convolution_cudnn_components.hpp"
 #include "cuda_operation_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * @brief Implements `ov::op::v1::Convolution` using cuDNN API
@@ -33,4 +34,5 @@ class ConvolutionCuDnn : public OperationCuDnn {
     Convolution::Details::ConvolutionDescriptorsCuDnn descs_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/convolution_cudnn_be.cpp b/modules/nvidia_plugin/src/ops/convolution_cudnn_be.cpp
similarity index 97%
rename from modules/cuda_plugin/src/ops/convolution_cudnn_be.cpp
rename to modules/nvidia_plugin/src/ops/convolution_cudnn_be.cpp
index be91d24c5..f757cb8c5 100644
--- a/modules/cuda_plugin/src/ops/convolution_cudnn_be.cpp
+++ b/modules/nvidia_plugin/src/ops/convolution_cudnn_be.cpp
@@ -14,7 +14,8 @@
 #include "cuda/constant_factory.hpp"
 #include "cuda/dnn_be_algo.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 constexpr int NON_SPATIAL_DIMS_NUMBER = 2;
 
@@ -111,7 +112,7 @@ std::shared_ptr<CUDA::DnnBEExecutionPlan> ConvolutionCuDnnBE::performBenchmarks(
 WorkbufferRequest ConvolutionCuDnnBE::GetWorkBufferRequest() const {
     Expects(engine_config_);
     if (workspace_size_ < 0) {
-        CUDAPlugin::throwIEException(fmt::format("Workspace Size Invalid = {}", workspace_size_));
+        ov::nvidia_gpu::throwIEException(fmt::format("Workspace Size Invalid = {}", workspace_size_));
     }
     const size_t size = std::max(static_cast<int64_t>(0), workspace_size_);
     if (size > 0) {
@@ -163,4 +164,5 @@ std::shared_ptr<CUDA::DnnBETensorDescriptor> ConvolutionCuDnnBE::MakeTensorDescr
         .setIsVirtual(false)
         .build();
 }
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/convolution_cudnn_be.hpp b/modules/nvidia_plugin/src/ops/convolution_cudnn_be.hpp
similarity index 95%
rename from modules/cuda_plugin/src/ops/convolution_cudnn_be.hpp
rename to modules/nvidia_plugin/src/ops/convolution_cudnn_be.hpp
index f7a4d18aa..7991df92c 100644
--- a/modules/cuda_plugin/src/ops/convolution_cudnn_be.hpp
+++ b/modules/nvidia_plugin/src/ops/convolution_cudnn_be.hpp
@@ -12,7 +12,8 @@
 #include "cuda/dnn_be.hpp"
 #include "cuda_operation_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * @brief Implements `ov::op::v1::Convolution` using cuDNN Backend API.
@@ -48,4 +49,5 @@ class ConvolutionCuDnnBE : public OperationCuDnn {
     int64_t workspace_size_ = 0;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/cudnn_tensor_op_base.cpp b/modules/nvidia_plugin/src/ops/cudnn_tensor_op_base.cpp
similarity index 98%
rename from modules/cuda_plugin/src/ops/cudnn_tensor_op_base.cpp
rename to modules/nvidia_plugin/src/ops/cudnn_tensor_op_base.cpp
index 73541a9ed..70a5521d6 100644
--- a/modules/cuda_plugin/src/ops/cudnn_tensor_op_base.cpp
+++ b/modules/nvidia_plugin/src/ops/cudnn_tensor_op_base.cpp
@@ -11,7 +11,8 @@
 #include "converters.hpp"
 #include "cuda/constant_factory.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 namespace {
 
 bool argTypesSupported(cudnnDataType_t in0, cudnnDataType_t in1, cudnnDataType_t out) {
@@ -172,4 +173,5 @@ CuDnnTensorOpBase::IoParams::IoParams(const ov::Node& node, const Type& io_type,
       array_(toArray<int, max_supported_shape_size>(shape_)),
       desc_(desc(type_, array_)) {}
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/cudnn_tensor_op_base.hpp b/modules/nvidia_plugin/src/ops/cudnn_tensor_op_base.hpp
similarity index 95%
rename from modules/cuda_plugin/src/ops/cudnn_tensor_op_base.hpp
rename to modules/nvidia_plugin/src/ops/cudnn_tensor_op_base.hpp
index 2a51ca3e3..982498563 100644
--- a/modules/cuda_plugin/src/ops/cudnn_tensor_op_base.hpp
+++ b/modules/nvidia_plugin/src/ops/cudnn_tensor_op_base.hpp
@@ -7,7 +7,8 @@
 #include <cuda_operation_base.hpp>
 #include <ngraph/node.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class CuDnnTensorOpBase : public OperationCuDnn {
 public:
@@ -49,4 +50,5 @@ class CuDnnTensorOpBase : public OperationCuDnn {
     int bias_index_ = 0;
     int dest_index_ = 1;
 };
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/details/cuda_ie_api_import_fix.hpp b/modules/nvidia_plugin/src/ops/details/cuda_ie_api_import_fix.hpp
similarity index 100%
rename from modules/cuda_plugin/src/ops/details/cuda_ie_api_import_fix.hpp
rename to modules/nvidia_plugin/src/ops/details/cuda_ie_api_import_fix.hpp
diff --git a/modules/cuda_plugin/src/ops/details/cuda_ngraph_import_fix.hpp b/modules/nvidia_plugin/src/ops/details/cuda_ngraph_import_fix.hpp
similarity index 100%
rename from modules/cuda_plugin/src/ops/details/cuda_ngraph_import_fix.hpp
rename to modules/nvidia_plugin/src/ops/details/cuda_ngraph_import_fix.hpp
diff --git a/modules/cuda_plugin/src/ops/detection_output.cpp b/modules/nvidia_plugin/src/ops/detection_output.cpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/detection_output.cpp
rename to modules/nvidia_plugin/src/ops/detection_output.cpp
index 021b402a1..f903a1483 100644
--- a/modules/cuda_plugin/src/ops/detection_output.cpp
+++ b/modules/nvidia_plugin/src/ops/detection_output.cpp
@@ -8,7 +8,8 @@
 
 #include "converters.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 DetectionOutputOp::DetectionOutputOp(const CreationContext& context,
                                      const NodeOp& node,
@@ -52,7 +53,7 @@ DetectionOutputOp::DetectionOutputOp(const CreationContext& context,
     const size_t max_threads_per_block = context.device().props().maxThreadsPerBlock;
     if (node.inputs().size() == 5) {
         kernel_ =
-            std::make_optional<kernel::DetectionOutput>(convertDataType<CUDAPlugin::kernel::Type_t>(element_type_),
+            std::make_optional<kernel::DetectionOutput>(convertDataType<ov::nvidia_gpu::kernel::Type_t>(element_type_),
                                                         max_threads_per_block,
                                                         ov::shape_size(node.get_input_shape(0)),
                                                         ov::shape_size(node.get_input_shape(1)),
@@ -63,7 +64,7 @@ DetectionOutputOp::DetectionOutputOp(const CreationContext& context,
                                                         kernel_attrs);
     } else {
         kernel_ =
-            std::make_optional<kernel::DetectionOutput>(convertDataType<CUDAPlugin::kernel::Type_t>(element_type_),
+            std::make_optional<kernel::DetectionOutput>(convertDataType<ov::nvidia_gpu::kernel::Type_t>(element_type_),
                                                         max_threads_per_block,
                                                         ov::shape_size(node.get_input_shape(0)),
                                                         ov::shape_size(node.get_input_shape(1)),
@@ -110,4 +111,5 @@ WorkbufferRequest DetectionOutputOp::GetWorkBufferRequest() const {
 }
 
 OPERATION_REGISTER(DetectionOutputOp, DetectionOutput);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/detection_output.hpp b/modules/nvidia_plugin/src/ops/detection_output.hpp
similarity index 92%
rename from modules/cuda_plugin/src/ops/detection_output.hpp
rename to modules/nvidia_plugin/src/ops/detection_output.hpp
index 8f8fa3f81..c45a377a9 100644
--- a/modules/cuda_plugin/src/ops/detection_output.hpp
+++ b/modules/nvidia_plugin/src/ops/detection_output.hpp
@@ -10,7 +10,8 @@
 #include "cuda_operation_base.hpp"
 #include "kernels/detection_output.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class DetectionOutputOp : public OperationBase {
 public:
@@ -32,4 +33,5 @@ class DetectionOutputOp : public OperationBase {
     std::optional<kernel::DetectionOutput> kernel_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/divide.cpp b/modules/nvidia_plugin/src/ops/divide.cpp
similarity index 93%
rename from modules/cuda_plugin/src/ops/divide.cpp
rename to modules/nvidia_plugin/src/ops/divide.cpp
index 204ab1303..dd983d1fc 100644
--- a/modules/cuda_plugin/src/ops/divide.cpp
+++ b/modules/nvidia_plugin/src/ops/divide.cpp
@@ -7,7 +7,8 @@
 #include "cuda_operation_registry.hpp"
 #include "divide_cuda.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 static OperationBase::Ptr divideFactory(const CreationContext& context,
                                         const std::shared_ptr<ov::Node>& in_node,
@@ -29,4 +30,5 @@ static OperationBase::Ptr divideFactory(const CreationContext& context,
 
 OPERATION_REGISTER_FACTORY(divideFactory, Divide)
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/divide_cuda.hpp b/modules/nvidia_plugin/src/ops/divide_cuda.hpp
similarity index 85%
rename from modules/cuda_plugin/src/ops/divide_cuda.hpp
rename to modules/nvidia_plugin/src/ops/divide_cuda.hpp
index b6abdf9de..f0991260f 100644
--- a/modules/cuda_plugin/src/ops/divide_cuda.hpp
+++ b/modules/nvidia_plugin/src/ops/divide_cuda.hpp
@@ -9,7 +9,8 @@
 #include "elementwise_binary.hpp"
 #include "kernels/divide.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class DivideOp : public ElementwiseBinaryOp<ov::op::v1::Divide, kernel::Divide> {
 public:
@@ -20,4 +21,5 @@ class PythonDivideOp : public ElementwiseBinaryOp<ov::op::v1::Divide, kernel::Py
     using ElementwiseBinaryOp::ElementwiseBinaryOp;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/elementwise_binary.hpp b/modules/nvidia_plugin/src/ops/elementwise_binary.hpp
similarity index 93%
rename from modules/cuda_plugin/src/ops/elementwise_binary.hpp
rename to modules/nvidia_plugin/src/ops/elementwise_binary.hpp
index 45b590cac..e6bcefc43 100644
--- a/modules/cuda_plugin/src/ops/elementwise_binary.hpp
+++ b/modules/nvidia_plugin/src/ops/elementwise_binary.hpp
@@ -9,7 +9,8 @@
 #include "components/numpy_broadcast_params.h"
 #include "converters.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 template <typename nGraphNode, typename Kernel>
 class ElementwiseBinaryOp : public OperationBase {
@@ -38,7 +39,7 @@ class ElementwiseBinaryOp : public OperationBase {
         const size_t max_threads_per_block = context.device().props().maxThreadsPerBlock;
         const size_t out_num_elements = ngraph::shape_size(node.get_output_shape(0));
         kernel_ =
-            Kernel{convertDataType<CUDAPlugin::kernel::Type_t>(element_type), out_num_elements, max_threads_per_block};
+            Kernel{convertDataType<ov::nvidia_gpu::kernel::Type_t>(element_type), out_num_elements, max_threads_per_block};
     }
 
     void Execute(const InferenceRequestContext& context,
@@ -73,4 +74,5 @@ class ElementwiseBinaryOp : public OperationBase {
     std::optional<Kernel> kernel_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/eltwise.cpp b/modules/nvidia_plugin/src/ops/eltwise.cpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/eltwise.cpp
rename to modules/nvidia_plugin/src/ops/eltwise.cpp
index 6261d330d..0e472e2b5 100644
--- a/modules/cuda_plugin/src/ops/eltwise.cpp
+++ b/modules/nvidia_plugin/src/ops/eltwise.cpp
@@ -10,7 +10,8 @@
 
 using namespace std::string_literals;
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 namespace eltwise {
 
@@ -50,4 +51,5 @@ KernelExecAttrs::KernelExecAttrs(const ov::Shape& shape, unsigned threadsPerBloc
       elementsPerThread{elementsPerThread} {}
 
 }  // namespace eltwise
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/examples/sigmoid.cu b/modules/nvidia_plugin/src/ops/examples/sigmoid.cu
similarity index 96%
rename from modules/cuda_plugin/src/ops/examples/sigmoid.cu
rename to modules/nvidia_plugin/src/ops/examples/sigmoid.cu
index d6a2a73b7..ff2299f71 100644
--- a/modules/cuda_plugin/src/ops/examples/sigmoid.cu
+++ b/modules/nvidia_plugin/src/ops/examples/sigmoid.cu
@@ -9,7 +9,8 @@
 
 #include "sigmoid.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 static __global__ void sigmoid(const size_t inputSize, const float* x, float* y) {
     const unsigned i = blockIdx.x * blockDim.x + threadIdx.x;
@@ -51,4 +52,5 @@ void SigmoidOp::Execute(const InferenceRequestContext& context,
 }
 
 OPERATION_REGISTER(SigmoidOp, Sigmoid);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/examples/sigmoid.hpp b/modules/nvidia_plugin/src/ops/examples/sigmoid.hpp
similarity index 89%
rename from modules/cuda_plugin/src/ops/examples/sigmoid.hpp
rename to modules/nvidia_plugin/src/ops/examples/sigmoid.hpp
index 48ca7726f..ee2e27bd4 100644
--- a/modules/cuda_plugin/src/ops/examples/sigmoid.hpp
+++ b/modules/nvidia_plugin/src/ops/examples/sigmoid.hpp
@@ -7,7 +7,8 @@
 #include <cuda/device_pointers.hpp>
 #include <cuda_operation_base.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class SigmoidOp : public OperationBase {
 public:
@@ -27,4 +28,5 @@ class SigmoidOp : public OperationBase {
     unsigned threads_per_block_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/fake_quantize.cpp b/modules/nvidia_plugin/src/ops/fake_quantize.cpp
similarity index 94%
rename from modules/cuda_plugin/src/ops/fake_quantize.cpp
rename to modules/nvidia_plugin/src/ops/fake_quantize.cpp
index c5cde3e0a..6e51e8653 100644
--- a/modules/cuda_plugin/src/ops/fake_quantize.cpp
+++ b/modules/nvidia_plugin/src/ops/fake_quantize.cpp
@@ -11,7 +11,8 @@
 
 #include "converters.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 enum InputIdx { ARG, INPUT_LOW, INPUT_HIGH, OUTPUT_LOW, OUTPUT_HIGH };
 
@@ -42,7 +43,7 @@ FakeQuantizeOp::FakeQuantizeOp(const CreationContext &context,
     const auto max_threads_per_block = static_cast<unsigned>(context.device().props().maxThreadsPerBlock);
 
     kernel_ = kernel::FakeQuantize{
-        convertDataType<CUDAPlugin::kernel::Type_t>(element_type), output_size, max_threads_per_block, levels};
+        convertDataType<ov::nvidia_gpu::kernel::Type_t>(element_type), output_size, max_threads_per_block, levels};
 }
 
 void FakeQuantizeOp::Execute(const InferenceRequestContext &context,
@@ -75,4 +76,5 @@ void FakeQuantizeOp::InitSharedImmutableWorkbuffers(const Buffers &buffers) {
 WorkbufferRequest FakeQuantizeOp::GetWorkBufferRequest() const { return {immutable_buffer_sizes_, {}}; }
 
 OPERATION_REGISTER(FakeQuantizeOp, FakeQuantize);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/fake_quantize.hpp b/modules/nvidia_plugin/src/ops/fake_quantize.hpp
similarity index 94%
rename from modules/cuda_plugin/src/ops/fake_quantize.hpp
rename to modules/nvidia_plugin/src/ops/fake_quantize.hpp
index 23b296b9f..4aa43c04e 100644
--- a/modules/cuda_plugin/src/ops/fake_quantize.hpp
+++ b/modules/nvidia_plugin/src/ops/fake_quantize.hpp
@@ -10,7 +10,8 @@
 #include "cuda_operation_base.hpp"
 #include "kernels/fake_quantize.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class FakeQuantizeOp : public OperationBase {
 public:
@@ -39,4 +40,5 @@ class FakeQuantizeOp : public OperationBase {
     std::optional<kernel::FakeQuantize> kernel_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/floor.cpp b/modules/nvidia_plugin/src/ops/floor.cpp
similarity index 88%
rename from modules/cuda_plugin/src/ops/floor.cpp
rename to modules/nvidia_plugin/src/ops/floor.cpp
index 9d70d48eb..8b25c4c14 100644
--- a/modules/cuda_plugin/src/ops/floor.cpp
+++ b/modules/nvidia_plugin/src/ops/floor.cpp
@@ -9,7 +9,8 @@
 
 #include "converters.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 FloorOp::FloorOp(const CreationContext& context,
                  const ov::Node& node,
@@ -27,7 +28,7 @@ FloorOp::FloorOp(const CreationContext& context,
     size_t num_elements = ov::shape_size(input_shape);
     const size_t max_threads_per_block = context.device().props().maxThreadsPerBlock;
     kernel_ = kernel::Floor{
-        convertDataType<CUDAPlugin::kernel::Type_t>(input_element_type), max_threads_per_block, num_elements};
+        convertDataType<ov::nvidia_gpu::kernel::Type_t>(input_element_type), max_threads_per_block, num_elements};
 }
 
 void FloorOp::Execute(const InferenceRequestContext& context,
@@ -43,4 +44,5 @@ void FloorOp::Execute(const InferenceRequestContext& context,
 
 OPERATION_REGISTER(FloorOp, Floor);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/floor.hpp b/modules/nvidia_plugin/src/ops/floor.hpp
similarity index 88%
rename from modules/cuda_plugin/src/ops/floor.hpp
rename to modules/nvidia_plugin/src/ops/floor.hpp
index 2124eb571..11885ff6e 100644
--- a/modules/cuda_plugin/src/ops/floor.hpp
+++ b/modules/nvidia_plugin/src/ops/floor.hpp
@@ -8,7 +8,8 @@
 
 #include "kernels/floor.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class FloorOp : public OperationBase {
 public:
@@ -26,4 +27,5 @@ class FloorOp : public OperationBase {
     std::optional<kernel::Floor> kernel_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/floor_mod.cpp b/modules/nvidia_plugin/src/ops/floor_mod.cpp
similarity index 69%
rename from modules/cuda_plugin/src/ops/floor_mod.cpp
rename to modules/nvidia_plugin/src/ops/floor_mod.cpp
index a28d34d79..4b60e332c 100644
--- a/modules/cuda_plugin/src/ops/floor_mod.cpp
+++ b/modules/nvidia_plugin/src/ops/floor_mod.cpp
@@ -6,8 +6,10 @@
 
 #include <cuda_operation_registry.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 OPERATION_REGISTER(FloorModOp, FloorMod)
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/floor_mod.hpp b/modules/nvidia_plugin/src/ops/floor_mod.hpp
similarity index 80%
rename from modules/cuda_plugin/src/ops/floor_mod.hpp
rename to modules/nvidia_plugin/src/ops/floor_mod.hpp
index 4ee4bd598..777efa01f 100644
--- a/modules/cuda_plugin/src/ops/floor_mod.hpp
+++ b/modules/nvidia_plugin/src/ops/floor_mod.hpp
@@ -9,11 +9,13 @@
 #include "elementwise_binary.hpp"
 #include "kernels/floor_mod.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class FloorModOp : public ElementwiseBinaryOp<ov::op::v1::FloorMod, kernel::FloorMod> {
 public:
     using ElementwiseBinaryOp::ElementwiseBinaryOp;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/fully_connected.cpp b/modules/nvidia_plugin/src/ops/fully_connected.cpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/fully_connected.cpp
rename to modules/nvidia_plugin/src/ops/fully_connected.cpp
index 0029bf127..3d4eebd5d 100644
--- a/modules/cuda_plugin/src/ops/fully_connected.cpp
+++ b/modules/nvidia_plugin/src/ops/fully_connected.cpp
@@ -15,7 +15,8 @@
 #include "cuda/constant_factory.hpp"
 #include "matmul.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 FullyConnectedOp::FullyConnectedOp(const CreationContext& context,
                                    const NodeOp& node,
@@ -55,4 +56,5 @@ void FullyConnectedOp::Execute(const InferenceRequestContext& context,
 }
 
 OPERATION_REGISTER(FullyConnectedOp, FullyConnected);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/fully_connected.hpp b/modules/nvidia_plugin/src/ops/fully_connected.hpp
similarity index 91%
rename from modules/cuda_plugin/src/ops/fully_connected.hpp
rename to modules/nvidia_plugin/src/ops/fully_connected.hpp
index 328df3355..856f0f9b9 100644
--- a/modules/cuda_plugin/src/ops/fully_connected.hpp
+++ b/modules/nvidia_plugin/src/ops/fully_connected.hpp
@@ -11,7 +11,8 @@
 #include "cuda/constant_factory.hpp"
 #include "matmul.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class FullyConnectedOp : public OperationCuBlas {
 public:
@@ -31,4 +32,5 @@ class FullyConnectedOp : public OperationCuBlas {
     size_t batch_bias_count_ = 0;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/fused_convolution.cpp b/modules/nvidia_plugin/src/ops/fused_convolution.cpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/fused_convolution.cpp
rename to modules/nvidia_plugin/src/ops/fused_convolution.cpp
index 57dd2292a..e903f656b 100644
--- a/modules/cuda_plugin/src/ops/fused_convolution.cpp
+++ b/modules/nvidia_plugin/src/ops/fused_convolution.cpp
@@ -18,7 +18,8 @@
 #include "fused_convolution_cudnn_be.hpp"
 #endif  // ENABLE_CUDNN_BACKEND_API
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 OperationBase::Ptr fusedConvolutionFactory(const CreationContext& context,
                                            const std::shared_ptr<ov::Node>& node,
@@ -70,7 +71,7 @@ OperationBase::Ptr fusedConvolutionFactory(const CreationContext& context,
     // separate cuDNN functions.
     // For more information see:
     // https://docs.nvidia.com/deeplearning/cudnn/api/index.html#cudnnConvolutionBiasActivationForward
-    const bool should_decompose = params.activation_ == CUDAPlugin::nodes::ActivationMode::NO_ACTIVATION &&
+    const bool should_decompose = params.activation_ == ov::nvidia_gpu::nodes::ActivationMode::NO_ACTIVATION &&
                                   conv_descs->Algo().algo != CUDNN_CONVOLUTION_FWD_ALGO_IMPLICIT_PRECOMP_GEMM;
 
     if (should_decompose) {
@@ -115,4 +116,5 @@ OperationBase::Ptr fusedConvolutionFactory(const CreationContext& context,
 OPERATION_REGISTER_FACTORY(fusedConvolutionFactory, FusedConvolution);
 OPERATION_REGISTER_FACTORY(fusedConvolutionFactory, FusedGroupConvolution);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/fused_convolution_backprop_data.cpp b/modules/nvidia_plugin/src/ops/fused_convolution_backprop_data.cpp
similarity index 98%
rename from modules/cuda_plugin/src/ops/fused_convolution_backprop_data.cpp
rename to modules/nvidia_plugin/src/ops/fused_convolution_backprop_data.cpp
index c060294ef..9ab7eedbb 100644
--- a/modules/cuda_plugin/src/ops/fused_convolution_backprop_data.cpp
+++ b/modules/nvidia_plugin/src/ops/fused_convolution_backprop_data.cpp
@@ -13,7 +13,8 @@
 
 #include "cuda/constant_factory.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 FusedConvolutionBackpropDataOp::FusedConvolutionBackpropDataOp(const CreationContext& context,
                                                                const NodeOp& node,
@@ -98,4 +99,5 @@ std::size_t FusedConvolutionBackpropDataOp::GetBufferSize(const ov::Output<ov::N
 
 OPERATION_REGISTER(FusedConvolutionBackpropDataOp, FusedConvBackpropData);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/fused_convolution_backprop_data.hpp b/modules/nvidia_plugin/src/ops/fused_convolution_backprop_data.hpp
similarity index 90%
rename from modules/cuda_plugin/src/ops/fused_convolution_backprop_data.hpp
rename to modules/nvidia_plugin/src/ops/fused_convolution_backprop_data.hpp
index 9e1e8fb6b..268409261 100644
--- a/modules/cuda_plugin/src/ops/fused_convolution_backprop_data.hpp
+++ b/modules/nvidia_plugin/src/ops/fused_convolution_backprop_data.hpp
@@ -11,11 +11,12 @@
 #include "cuda/dnn.hpp"
 #include "cuda_operation_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class FusedConvolutionBackpropDataOp : public OperationCuDnn {
 public:
-    using NodeOp = CUDAPlugin::nodes::FusedConvBackpropData;
+    using NodeOp = ov::nvidia_gpu::nodes::FusedConvBackpropData;
     FusedConvolutionBackpropDataOp(const CreationContext& context,
                                    const NodeOp& node,
                                    IndexCollection&& inputIds,
@@ -40,4 +41,5 @@ class FusedConvolutionBackpropDataOp : public OperationCuDnn {
     size_t add_in_bytes_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/fused_convolution_cudnn.cpp b/modules/nvidia_plugin/src/ops/fused_convolution_cudnn.cpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/fused_convolution_cudnn.cpp
rename to modules/nvidia_plugin/src/ops/fused_convolution_cudnn.cpp
index 463f25e45..73dd1a7b1 100644
--- a/modules/cuda_plugin/src/ops/fused_convolution_cudnn.cpp
+++ b/modules/nvidia_plugin/src/ops/fused_convolution_cudnn.cpp
@@ -13,7 +13,8 @@
 #include "cuda/constant_factory.hpp"
 #include "transformer/nodes/cuda_plugin_custom_node_types.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 FusedConvolutionCuDnn::FusedConvolutionCuDnn(const CreationContext& context,
                                              const ov::Node& node,
@@ -114,9 +115,10 @@ void FusedConvolutionCuDnn::ThrowIfShouldDecompose() const {
     if (mode == CUDNN_ACTIVATION_IDENTITY &&
         conv_descs_->Algo().algo != CUDNN_CONVOLUTION_FWD_ALGO_IMPLICIT_PRECOMP_GEMM) {
         throwIEException(
-            "CUDAPlugin::FusedConvolutionCuDnn: CUDNN_ACTIVATION_IDENTITY can't be used with "
+            "ov::nvidia_gpu::FusedConvolutionCuDnn: CUDNN_ACTIVATION_IDENTITY can't be used with "
             "CUDNN_CONVOLUTION_FWD_ALGO_IMPLICIT_PRECOMP_GEMM");
     }
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/fused_convolution_cudnn.hpp b/modules/nvidia_plugin/src/ops/fused_convolution_cudnn.hpp
similarity index 95%
rename from modules/cuda_plugin/src/ops/fused_convolution_cudnn.hpp
rename to modules/nvidia_plugin/src/ops/fused_convolution_cudnn.hpp
index 4806d7330..15c9b1e36 100644
--- a/modules/cuda_plugin/src/ops/fused_convolution_cudnn.hpp
+++ b/modules/nvidia_plugin/src/ops/fused_convolution_cudnn.hpp
@@ -11,7 +11,8 @@
 #include "cuda/dnn.hpp"
 #include "cuda_operation_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class FusedConvolutionCuDnn : public OperationCuDnn {
 public:
@@ -46,4 +47,5 @@ class FusedConvolutionCuDnn : public OperationCuDnn {
     std::shared_ptr<CUDA::DnnActivationDescriptor> activation_desc_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/fused_convolution_cudnn_be.cpp b/modules/nvidia_plugin/src/ops/fused_convolution_cudnn_be.cpp
similarity index 98%
rename from modules/cuda_plugin/src/ops/fused_convolution_cudnn_be.cpp
rename to modules/nvidia_plugin/src/ops/fused_convolution_cudnn_be.cpp
index 514813e0e..34acaef3d 100644
--- a/modules/cuda_plugin/src/ops/fused_convolution_cudnn_be.cpp
+++ b/modules/nvidia_plugin/src/ops/fused_convolution_cudnn_be.cpp
@@ -16,7 +16,8 @@
 #include "cuda/event.hpp"
 #include "memory_manager/model/details/cuda_memory_utils.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 constexpr int NON_SPATIAL_DIMS_NUMBER = 2;
 
@@ -144,7 +145,7 @@ FusedConvolutionCuDnnBE::FusedConvolutionCuDnnBE(const CreationContext& context,
                             .build();
 
         std::shared_ptr<CUDA::DnnBEPointwiseDescriptor> activation_desc;
-        if (params.activation_ != CUDAPlugin::nodes::ActivationMode::NO_ACTIVATION) {
+        if (params.activation_ != ov::nvidia_gpu::nodes::ActivationMode::NO_ACTIVATION) {
             auto activation_desc_builder =
                 CUDA::DnnBEPointwiseDescriptorBuilder()
                     .setMode(convertActivationModeToBE(params.activation_))
@@ -273,7 +274,7 @@ std::shared_ptr<CUDA::DnnBEExecutionPlan> FusedConvolutionCuDnnBE::performBenchm
 WorkbufferRequest FusedConvolutionCuDnnBE::GetWorkBufferRequest() const {
     Expects(engine_config_);
     if (workspace_size_ < 0) {
-        CUDAPlugin::throwIEException(fmt::format("Workspace Size Invalid = {}", workspace_size_));
+        ov::nvidia_gpu::throwIEException(fmt::format("Workspace Size Invalid = {}", workspace_size_));
     }
     const size_t size = std::max(static_cast<int64_t>(0), workspace_size_);
     if (size > 0) {
@@ -334,7 +335,7 @@ std::shared_ptr<CUDA::DnnBETensorDescriptor> FusedConvolutionCuDnnBE::MakeTensor
     bool isVirtual) {
     const int nbDims = shape.size();
     if (nbDims < 4 || nbDims > 5) {
-        CUDAPlugin::throwIEException(
+        ov::nvidia_gpu::throwIEException(
             fmt::format("Unexpected number of dimensions for Convolution input/output: {}", nbDims));
     }
 
@@ -347,4 +348,5 @@ std::shared_ptr<CUDA::DnnBETensorDescriptor> FusedConvolutionCuDnnBE::MakeTensor
     return desc_builder.setIsVirtual(isVirtual).setUniqueId(id).setAlignment(16).build();
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/fused_convolution_cudnn_be.hpp b/modules/nvidia_plugin/src/ops/fused_convolution_cudnn_be.hpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/fused_convolution_cudnn_be.hpp
rename to modules/nvidia_plugin/src/ops/fused_convolution_cudnn_be.hpp
index 84a4faf04..8b603034a 100644
--- a/modules/cuda_plugin/src/ops/fused_convolution_cudnn_be.hpp
+++ b/modules/nvidia_plugin/src/ops/fused_convolution_cudnn_be.hpp
@@ -13,7 +13,8 @@
 #include "cuda_operation_base.hpp"
 #include "ops/convolution_components/convolution_cudnn_components.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * @brief Implements `ov::op::v1::Convolution` using cuDNN Backend API.
@@ -49,4 +50,5 @@ class FusedConvolutionCuDnnBE : public OperationCuDnn {
     const Convolution::Details::FusedConvolutionParams params_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/fused_convolution_cudnn_decomposed.cpp b/modules/nvidia_plugin/src/ops/fused_convolution_cudnn_decomposed.cpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/fused_convolution_cudnn_decomposed.cpp
rename to modules/nvidia_plugin/src/ops/fused_convolution_cudnn_decomposed.cpp
index 64ba2c249..e363f17e0 100644
--- a/modules/cuda_plugin/src/ops/fused_convolution_cudnn_decomposed.cpp
+++ b/modules/nvidia_plugin/src/ops/fused_convolution_cudnn_decomposed.cpp
@@ -12,7 +12,8 @@
 
 #include "cuda/constant_factory.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 FusedConvolutionCuDnnDecomposed::FusedConvolutionCuDnnDecomposed(
     const CreationContext& context,
@@ -103,9 +104,10 @@ void FusedConvolutionCuDnnDecomposed::ThrowIfShouldNotDecompose() const {
     if (mode != CUDNN_ACTIVATION_IDENTITY ||
         conv_descs_->Algo().algo == CUDNN_CONVOLUTION_FWD_ALGO_IMPLICIT_PRECOMP_GEMM) {
         throwIEException(
-            "CUDAPlugin::FusedConvolutionCuDnnDecomposed: FusedConvolutionCuDnnDecomposed should only be used for "
+            "ov::nvidia_gpu::FusedConvolutionCuDnnDecomposed: FusedConvolutionCuDnnDecomposed should only be used for "
             "CUDNN_ACTIVATION_IDENTITY and an algo other than CUDNN_CONVOLUTION_FWD_ALGO_IMPLICIT_PRECOMP_GEMM");
     }
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/fused_convolution_cudnn_decomposed.hpp b/modules/nvidia_plugin/src/ops/fused_convolution_cudnn_decomposed.hpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/fused_convolution_cudnn_decomposed.hpp
rename to modules/nvidia_plugin/src/ops/fused_convolution_cudnn_decomposed.hpp
index aa199bc55..b2b0b388f 100644
--- a/modules/cuda_plugin/src/ops/fused_convolution_cudnn_decomposed.hpp
+++ b/modules/nvidia_plugin/src/ops/fused_convolution_cudnn_decomposed.hpp
@@ -11,7 +11,8 @@
 #include "cuda/dnn.hpp"
 #include "cuda_operation_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * @brief This class was created as a workaround for the following cuDNN behavior:
@@ -49,4 +50,5 @@ class FusedConvolutionCuDnnDecomposed : public OperationCuDnn {
     std::shared_ptr<CUDA::DnnActivationDescriptor> activation_desc_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/gather.cpp b/modules/nvidia_plugin/src/ops/gather.cpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/gather.cpp
rename to modules/nvidia_plugin/src/ops/gather.cpp
index e9485ddc7..f48847d8d 100644
--- a/modules/cuda_plugin/src/ops/gather.cpp
+++ b/modules/nvidia_plugin/src/ops/gather.cpp
@@ -15,7 +15,8 @@
 
 #include "converters.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 namespace {
 
@@ -144,8 +145,8 @@ GatherOp::GatherOp(const CreationContext& context,
     Expects(grid_dim_y <= max_grid_size[1]);
     Expects(blocks_per_grid <= max_grid_size[2]);
 
-    gather_kernel_ = kernel::Gather{convertDataType<CUDAPlugin::kernel::Type_t>(element_type),
-                                    convertDataType<CUDAPlugin::kernel::Type_t>(indices_type),
+    gather_kernel_ = kernel::Gather{convertDataType<ov::nvidia_gpu::kernel::Type_t>(element_type),
+                                    convertDataType<ov::nvidia_gpu::kernel::Type_t>(indices_type),
                                     num_dicts,
                                     index_range,
                                     data_length,
@@ -177,4 +178,5 @@ void GatherOp::Execute(const InferenceRequestContext& context,
 }
 
 OPERATION_REGISTER(GatherOp, Gather);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/gather.hpp b/modules/nvidia_plugin/src/ops/gather.hpp
similarity index 88%
rename from modules/cuda_plugin/src/ops/gather.hpp
rename to modules/nvidia_plugin/src/ops/gather.hpp
index 393ed3d28..2d38382ed 100644
--- a/modules/cuda_plugin/src/ops/gather.hpp
+++ b/modules/nvidia_plugin/src/ops/gather.hpp
@@ -7,7 +7,8 @@
 #include <cuda_operation_base.hpp>
 #include <kernels/gather.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class GatherOp : public OperationBase {
 public:
@@ -24,4 +25,5 @@ class GatherOp : public OperationBase {
     std::optional<kernel::Gather> gather_kernel_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/greater.cpp b/modules/nvidia_plugin/src/ops/greater.cpp
similarity index 85%
rename from modules/cuda_plugin/src/ops/greater.cpp
rename to modules/nvidia_plugin/src/ops/greater.cpp
index d92026b8f..f168368aa 100644
--- a/modules/cuda_plugin/src/ops/greater.cpp
+++ b/modules/nvidia_plugin/src/ops/greater.cpp
@@ -6,7 +6,8 @@
 
 #include <cuda_operation_registry.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 GreaterOp::GreaterOp(const CreationContext& context,
                      const ov::Node& node,
@@ -16,4 +17,5 @@ GreaterOp::GreaterOp(const CreationContext& context,
 
 OPERATION_REGISTER(GreaterOp, Greater);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/greater.hpp b/modules/nvidia_plugin/src/ops/greater.hpp
similarity index 80%
rename from modules/cuda_plugin/src/ops/greater.hpp
rename to modules/nvidia_plugin/src/ops/greater.hpp
index 8b607fc8f..81dd7cd9f 100644
--- a/modules/cuda_plugin/src/ops/greater.hpp
+++ b/modules/nvidia_plugin/src/ops/greater.hpp
@@ -6,7 +6,8 @@
 
 #include "comparison.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class GreaterOp : public Comparison {
 public:
@@ -16,4 +17,5 @@ class GreaterOp : public Comparison {
               IndexCollection&& outputIds);
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/group_convolution.cpp b/modules/nvidia_plugin/src/ops/group_convolution.cpp
similarity index 93%
rename from modules/cuda_plugin/src/ops/group_convolution.cpp
rename to modules/nvidia_plugin/src/ops/group_convolution.cpp
index 9ac9b663f..ac6ea6562 100644
--- a/modules/cuda_plugin/src/ops/group_convolution.cpp
+++ b/modules/nvidia_plugin/src/ops/group_convolution.cpp
@@ -9,7 +9,8 @@
 
 #include "convolution_components/convolution_components.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 GroupConvolutionOp::GroupConvolutionOp(const CreationContext &context,
                                        const NodeOp &node,
@@ -29,4 +30,5 @@ WorkbufferRequest GroupConvolutionOp::GetWorkBufferRequest() const { return conv
 
 OPERATION_REGISTER(GroupConvolutionOp, GroupConvolution);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/group_convolution.hpp b/modules/nvidia_plugin/src/ops/group_convolution.hpp
similarity index 90%
rename from modules/cuda_plugin/src/ops/group_convolution.hpp
rename to modules/nvidia_plugin/src/ops/group_convolution.hpp
index 008e754dc..27891638c 100644
--- a/modules/cuda_plugin/src/ops/group_convolution.hpp
+++ b/modules/nvidia_plugin/src/ops/group_convolution.hpp
@@ -11,7 +11,8 @@
 #include "convolution_cudnn.hpp"
 #include "cuda_operation_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class GroupConvolutionOp : public OperationCuDnn {
 public:
@@ -31,4 +32,5 @@ class GroupConvolutionOp : public OperationCuDnn {
     ConvolutionCuDnn convolution_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/gru_cell.cpp b/modules/nvidia_plugin/src/ops/gru_cell.cpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/gru_cell.cpp
rename to modules/nvidia_plugin/src/ops/gru_cell.cpp
index 5bab5444f..c58084ac4 100644
--- a/modules/cuda_plugin/src/ops/gru_cell.cpp
+++ b/modules/nvidia_plugin/src/ops/gru_cell.cpp
@@ -10,7 +10,8 @@
 #include <utility>
 #include <vector>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 GRUCellOp::GRUCellOp(const CreationContext& context,
                      const ov::Node& node,
@@ -24,7 +25,7 @@ void GRUCellOp::Execute(const InferenceRequestContext& context,
                         Inputs inputs,
                         Outputs outputs,
                         const Workbuffers& workbuffers) const {
-    using CUDAPlugin::RNN::Details::GRUCellArgIndices;
+    using ov::nvidia_gpu::RNN::Details::GRUCellArgIndices;
 
     Expects(inputs.size() == 5);
     Expects(outputs.size() == 1);
@@ -91,4 +92,5 @@ WorkbufferRequest GRUCellOp::GetWorkBufferRequest() const {
 
 OPERATION_REGISTER(GRUCellOp, GRUCell);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/gru_cell.hpp b/modules/nvidia_plugin/src/ops/gru_cell.hpp
similarity index 92%
rename from modules/cuda_plugin/src/ops/gru_cell.hpp
rename to modules/nvidia_plugin/src/ops/gru_cell.hpp
index 0b816b160..e6a015b63 100644
--- a/modules/cuda_plugin/src/ops/gru_cell.hpp
+++ b/modules/nvidia_plugin/src/ops/gru_cell.hpp
@@ -10,7 +10,8 @@
 #include "rnn_components/rnn_components.hpp"
 #include "rnn_components/rnn_cudnn_components.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * @brief Implements `ov::op::v4::GRUCell` using cuDNN API
@@ -34,4 +35,5 @@ class GRUCellOp : public OperationCuDnn {
     RNN::Details::GRUCellDescriptorsCuDnn descs_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/gru_sequence.cpp b/modules/nvidia_plugin/src/ops/gru_sequence.cpp
similarity index 94%
rename from modules/cuda_plugin/src/ops/gru_sequence.cpp
rename to modules/nvidia_plugin/src/ops/gru_sequence.cpp
index 1160621fe..f069fdacd 100644
--- a/modules/cuda_plugin/src/ops/gru_sequence.cpp
+++ b/modules/nvidia_plugin/src/ops/gru_sequence.cpp
@@ -9,7 +9,8 @@
 #include <utility>
 #include <vector>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 GRUSequenceOp::GRUSequenceOp(const CreationContext& context,
                              const NodeOp& node,
@@ -34,7 +35,7 @@ void GRUSequenceOp::Execute(const InferenceRequestContext& context,
                             Inputs inputs,
                             Outputs outputs,
                             const Workbuffers& workbuffers) const {
-    using ArgIndices = CUDAPlugin::RNN::Details::GRUSequenceArgIndices;
+    using ArgIndices = ov::nvidia_gpu::RNN::Details::GRUSequenceArgIndices;
     Expects(inputs.size() == 6);
     Expects(outputs.size() == 2);
 
@@ -78,4 +79,5 @@ WorkbufferRequest GRUSequenceOp::GetWorkBufferRequest() const { return {immut_si
 
 OPERATION_REGISTER(GRUSequenceOp, GRUSequence);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/gru_sequence.hpp b/modules/nvidia_plugin/src/ops/gru_sequence.hpp
similarity index 94%
rename from modules/cuda_plugin/src/ops/gru_sequence.hpp
rename to modules/nvidia_plugin/src/ops/gru_sequence.hpp
index 65b14761c..e49e1b4b2 100644
--- a/modules/cuda_plugin/src/ops/gru_sequence.hpp
+++ b/modules/nvidia_plugin/src/ops/gru_sequence.hpp
@@ -13,7 +13,8 @@
 #include "rnn_components/gru_sequence_cudnn_components.hpp"
 #include "rnn_components/rnn_sequence_components.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * @brief Implements `ov::op::v5::GRUSequence` using cuDNN API
@@ -49,4 +50,5 @@ class GRUSequenceOp : public OperationCuDnn {
     WorkbufferDesc mb_work_space_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/interpolate.cpp b/modules/nvidia_plugin/src/ops/interpolate.cpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/interpolate.cpp
rename to modules/nvidia_plugin/src/ops/interpolate.cpp
index f03d86f66..0bd3bd862 100644
--- a/modules/cuda_plugin/src/ops/interpolate.cpp
+++ b/modules/nvidia_plugin/src/ops/interpolate.cpp
@@ -15,7 +15,8 @@
 #include "ngraph/shape.hpp"
 #include "ngraph/validation_util.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 static OperationBase::Ptr interpolateFactory(const CreationContext& context,
                                              const std::shared_ptr<ngraph::Node>& in_node,
@@ -63,4 +64,5 @@ static OperationBase::Ptr interpolateFactory(const CreationContext& context,
 
 OPERATION_REGISTER_FACTORY(interpolateFactory, Interpolate);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/interpolate_components/interpolate_components.cpp b/modules/nvidia_plugin/src/ops/interpolate_components/interpolate_components.cpp
similarity index 93%
rename from modules/cuda_plugin/src/ops/interpolate_components/interpolate_components.cpp
rename to modules/nvidia_plugin/src/ops/interpolate_components/interpolate_components.cpp
index 217be67ad..169e5aa7a 100644
--- a/modules/cuda_plugin/src/ops/interpolate_components/interpolate_components.cpp
+++ b/modules/nvidia_plugin/src/ops/interpolate_components/interpolate_components.cpp
@@ -10,7 +10,7 @@
 #include "error.hpp"
 #include "ngraph/validation_util.hpp"
 
-namespace CUDAPlugin::Interpolate::Details {
+namespace ov::nvidia_gpu::Interpolate::Details {
 
 void getAxesAndScales(const ov::op::v4::Interpolate& node, std::vector<size_t>& axes, std::vector<float>& scales) {
     axes = ngraph::get_constant_from_source(node.input_value(3))->cast_vector<size_t>();
@@ -34,4 +34,4 @@ void getAxesAndScales(const ov::op::v4::Interpolate& node, std::vector<size_t>&
     }
 }
 
-}  // namespace CUDAPlugin::Interpolate::Details
+}  // namespace ov::nvidia_gpu::Interpolate::Details
diff --git a/modules/cuda_plugin/src/ops/interpolate_components/interpolate_components.hpp b/modules/nvidia_plugin/src/ops/interpolate_components/interpolate_components.hpp
similarity index 71%
rename from modules/cuda_plugin/src/ops/interpolate_components/interpolate_components.hpp
rename to modules/nvidia_plugin/src/ops/interpolate_components/interpolate_components.hpp
index 92b51e53b..74c92f2f6 100644
--- a/modules/cuda_plugin/src/ops/interpolate_components/interpolate_components.hpp
+++ b/modules/nvidia_plugin/src/ops/interpolate_components/interpolate_components.hpp
@@ -6,8 +6,8 @@
 
 #include "openvino/op/interpolate.hpp"
 
-namespace CUDAPlugin::Interpolate::Details {
+namespace ov::nvidia_gpu::Interpolate::Details {
 
 void getAxesAndScales(const ov::op::v4::Interpolate& node, std::vector<size_t>& axes, std::vector<float>& scales);
 
-}  // namespace CUDAPlugin::Interpolate::Details
+}  // namespace ov::nvidia_gpu::Interpolate::Details
diff --git a/modules/cuda_plugin/src/ops/interpolate_cubic.cpp b/modules/nvidia_plugin/src/ops/interpolate_cubic.cpp
similarity index 94%
rename from modules/cuda_plugin/src/ops/interpolate_cubic.cpp
rename to modules/nvidia_plugin/src/ops/interpolate_cubic.cpp
index 446ffce37..f14f24563 100644
--- a/modules/cuda_plugin/src/ops/interpolate_cubic.cpp
+++ b/modules/nvidia_plugin/src/ops/interpolate_cubic.cpp
@@ -8,7 +8,8 @@
 #include "interpolate_components/interpolate_components.hpp"
 #include "ops/converters.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 namespace {
 
@@ -47,7 +48,7 @@ InterpolateCubicOp::InterpolateCubicOp(const CreationContext& context,
 
     const auto transform_mode =
         static_cast<kernel::InterpolateCubic::CoordinateTransformMode>(node.get_attrs().coordinate_transformation_mode);
-    const auto element_type = convertDataType<CUDAPlugin::kernel::Type_t>(node.get_input_element_type(0));
+    const auto element_type = convertDataType<ov::nvidia_gpu::kernel::Type_t>(node.get_input_element_type(0));
     const auto max_threads_per_block = context.device().props().maxThreadsPerBlock;
 
     interpolate_ = kernel::InterpolateCubic(node.get_input_shape(0),
@@ -77,4 +78,5 @@ void InterpolateCubicOp::InitSharedImmutableWorkbuffers(const Buffers& in_buffer
     interpolate_->initImmutableWorkbuffers(buffers);
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/interpolate_cubic.hpp b/modules/nvidia_plugin/src/ops/interpolate_cubic.hpp
similarity index 91%
rename from modules/cuda_plugin/src/ops/interpolate_cubic.hpp
rename to modules/nvidia_plugin/src/ops/interpolate_cubic.hpp
index 6af9f5828..ea70baafa 100644
--- a/modules/cuda_plugin/src/ops/interpolate_cubic.hpp
+++ b/modules/nvidia_plugin/src/ops/interpolate_cubic.hpp
@@ -8,7 +8,8 @@
 #include "kernels/interpolate_cubic.hpp"
 #include "openvino/op/interpolate.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class InterpolateCubicOp : public OperationBase {
 public:
@@ -29,4 +30,5 @@ class InterpolateCubicOp : public OperationBase {
     std::optional<kernel::InterpolateCubic> interpolate_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/interpolate_linear.cpp b/modules/nvidia_plugin/src/ops/interpolate_linear.cpp
similarity index 94%
rename from modules/cuda_plugin/src/ops/interpolate_linear.cpp
rename to modules/nvidia_plugin/src/ops/interpolate_linear.cpp
index 8b949bd02..25f865ddd 100644
--- a/modules/cuda_plugin/src/ops/interpolate_linear.cpp
+++ b/modules/nvidia_plugin/src/ops/interpolate_linear.cpp
@@ -8,7 +8,8 @@
 #include "interpolate_components/interpolate_components.hpp"
 #include "ops/converters.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 namespace {
 
@@ -47,7 +48,7 @@ InterpolateLinearOp::InterpolateLinearOp(const CreationContext& context,
 
     const auto transform_mode = static_cast<kernel::InterpolateLinear::CoordinateTransformMode>(
         node.get_attrs().coordinate_transformation_mode);
-    const auto element_type = convertDataType<CUDAPlugin::kernel::Type_t>(node.get_input_element_type(0));
+    const auto element_type = convertDataType<ov::nvidia_gpu::kernel::Type_t>(node.get_input_element_type(0));
     const auto max_threads_per_block = context.device().props().maxThreadsPerBlock;
 
     interpolate_ = kernel::InterpolateLinear(node.get_input_shape(0),
@@ -77,4 +78,5 @@ void InterpolateLinearOp::InitSharedImmutableWorkbuffers(const Buffers& in_buffe
     interpolate_->initImmutableWorkbuffers(buffers);
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/interpolate_linear.hpp b/modules/nvidia_plugin/src/ops/interpolate_linear.hpp
similarity index 91%
rename from modules/cuda_plugin/src/ops/interpolate_linear.hpp
rename to modules/nvidia_plugin/src/ops/interpolate_linear.hpp
index 395662667..6cb23f2f8 100644
--- a/modules/cuda_plugin/src/ops/interpolate_linear.hpp
+++ b/modules/nvidia_plugin/src/ops/interpolate_linear.hpp
@@ -8,7 +8,8 @@
 #include "kernels/interpolate_linear.hpp"
 #include "openvino/op/interpolate.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class InterpolateLinearOp : public OperationBase {
 public:
@@ -29,4 +30,5 @@ class InterpolateLinearOp : public OperationBase {
     std::optional<kernel::InterpolateLinear> interpolate_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/interpolate_nearest.cpp b/modules/nvidia_plugin/src/ops/interpolate_nearest.cpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/interpolate_nearest.cpp
rename to modules/nvidia_plugin/src/ops/interpolate_nearest.cpp
index 7c358930a..ba01c513a 100644
--- a/modules/cuda_plugin/src/ops/interpolate_nearest.cpp
+++ b/modules/nvidia_plugin/src/ops/interpolate_nearest.cpp
@@ -11,11 +11,12 @@
 #include "ngraph/validation_util.hpp"
 #include "ops/converters.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 namespace {
 
-std::vector<float> getScalesVector(const CUDAPlugin::InterpolateNearestOp::NodeOp& node) {
+std::vector<float> getScalesVector(const ov::nvidia_gpu::InterpolateNearestOp::NodeOp& node) {
     // for calculation scale for nearest mode see
     // https://docs.openvino.ai/2021.1/openvino_docs_ops_image_Interpolate_4.html
     const auto scales = ngraph::get_constant_from_source(node.input_value(2))->cast_vector<float>();
@@ -119,7 +120,7 @@ InterpolateNearestOp::InterpolateNearestOp(const CreationContext& context,
     const auto strides = can_use_upscale_optimizing_ ? in_shape_[0] * in_strides_[0] : out_shape_[0] * out_strides_[0];
     const auto blocks_number = 1 + strides / max_threads_per_block;
     const auto threads_per_block = (blocks_number == 1) ? strides : max_threads_per_block;
-    const auto element_type = convertDataType<CUDAPlugin::kernel::Type_t>(node.get_input_element_type(0));
+    const auto element_type = convertDataType<ov::nvidia_gpu::kernel::Type_t>(node.get_input_element_type(0));
 
     interpolate_ =
         kernel::InterpolateNearest(blocks_number,
@@ -176,4 +177,5 @@ void InterpolateNearestOp::InitSharedImmutableWorkbuffers(const Buffers& buffers
     uploadDataToWorkbuffer(buffers[4], out_shape_);
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/interpolate_nearest.hpp b/modules/nvidia_plugin/src/ops/interpolate_nearest.hpp
similarity index 93%
rename from modules/cuda_plugin/src/ops/interpolate_nearest.hpp
rename to modules/nvidia_plugin/src/ops/interpolate_nearest.hpp
index bc636b9c0..6ed5f19bb 100644
--- a/modules/cuda_plugin/src/ops/interpolate_nearest.hpp
+++ b/modules/nvidia_plugin/src/ops/interpolate_nearest.hpp
@@ -9,7 +9,8 @@
 #include "cuda_operation_base.hpp"
 #include "kernels/interpolate_nearest.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class InterpolateNearestOp : public OperationBase {
 public:
@@ -37,4 +38,5 @@ class InterpolateNearestOp : public OperationBase {
     std::optional<kernel::InterpolateNearest> interpolate_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/less.cpp b/modules/nvidia_plugin/src/ops/less.cpp
similarity index 84%
rename from modules/cuda_plugin/src/ops/less.cpp
rename to modules/nvidia_plugin/src/ops/less.cpp
index e4bf0a2c5..c9631cb9e 100644
--- a/modules/cuda_plugin/src/ops/less.cpp
+++ b/modules/nvidia_plugin/src/ops/less.cpp
@@ -6,7 +6,8 @@
 
 #include <cuda_operation_registry.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 LessOp::LessOp(const CreationContext& context,
                const ov::Node& node,
@@ -16,4 +17,5 @@ LessOp::LessOp(const CreationContext& context,
 
 OPERATION_REGISTER(LessOp, Less);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/less.hpp b/modules/nvidia_plugin/src/ops/less.hpp
similarity index 79%
rename from modules/cuda_plugin/src/ops/less.hpp
rename to modules/nvidia_plugin/src/ops/less.hpp
index 868588235..d1b2ede56 100644
--- a/modules/cuda_plugin/src/ops/less.hpp
+++ b/modules/nvidia_plugin/src/ops/less.hpp
@@ -6,7 +6,8 @@
 
 #include "comparison.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class LessOp : public Comparison {
 public:
@@ -16,4 +17,5 @@ class LessOp : public Comparison {
            IndexCollection&& outputIds);
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/logical_not.cpp b/modules/nvidia_plugin/src/ops/logical_not.cpp
similarity index 94%
rename from modules/cuda_plugin/src/ops/logical_not.cpp
rename to modules/nvidia_plugin/src/ops/logical_not.cpp
index 44444d697..266491a02 100644
--- a/modules/cuda_plugin/src/ops/logical_not.cpp
+++ b/modules/nvidia_plugin/src/ops/logical_not.cpp
@@ -6,7 +6,8 @@
 #include <cuda_operation_registry.hpp>
 #include <ngraph/node.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 LogicalNotOp::LogicalNotOp(const CreationContext& context,
                            const std::shared_ptr<ov::Node>& node,
@@ -31,4 +32,5 @@ void LogicalNotOp::Execute(const InferenceRequestContext& context,
 
 OPERATION_REGISTER(LogicalNotOp, LogicalNot);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/logical_not.hpp b/modules/nvidia_plugin/src/ops/logical_not.hpp
similarity index 89%
rename from modules/cuda_plugin/src/ops/logical_not.hpp
rename to modules/nvidia_plugin/src/ops/logical_not.hpp
index 522748a3c..68fd595e2 100644
--- a/modules/cuda_plugin/src/ops/logical_not.hpp
+++ b/modules/nvidia_plugin/src/ops/logical_not.hpp
@@ -6,7 +6,8 @@
 #include <cuda_operation_base.hpp>
 #include <kernels/logical_not.cuh>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class LogicalNotOp : public OperationBase {
 public:
@@ -23,4 +24,5 @@ class LogicalNotOp : public OperationBase {
     kernel::LogicalNot kernel_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/lstm_cell.cpp b/modules/nvidia_plugin/src/ops/lstm_cell.cpp
similarity index 97%
rename from modules/cuda_plugin/src/ops/lstm_cell.cpp
rename to modules/nvidia_plugin/src/ops/lstm_cell.cpp
index 29b04e763..2eebf5487 100644
--- a/modules/cuda_plugin/src/ops/lstm_cell.cpp
+++ b/modules/nvidia_plugin/src/ops/lstm_cell.cpp
@@ -9,7 +9,8 @@
 #include <utility>
 #include <vector>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 LSTMCellOp::LSTMCellOp(const CreationContext& context,
                        const ov::Node& node,
@@ -87,4 +88,5 @@ WorkbufferRequest LSTMCellOp::GetWorkBufferRequest() const {
 
 OPERATION_REGISTER(LSTMCellOp, LSTMCell);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/lstm_cell.hpp b/modules/nvidia_plugin/src/ops/lstm_cell.hpp
similarity index 92%
rename from modules/cuda_plugin/src/ops/lstm_cell.hpp
rename to modules/nvidia_plugin/src/ops/lstm_cell.hpp
index 2a892c7f1..5812716db 100644
--- a/modules/cuda_plugin/src/ops/lstm_cell.hpp
+++ b/modules/nvidia_plugin/src/ops/lstm_cell.hpp
@@ -10,7 +10,8 @@
 #include "rnn_components/rnn_components.hpp"
 #include "rnn_components/rnn_cudnn_components.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * @brief Implements `ov::op::v4::LSTMCell` using cuDNN API
@@ -34,4 +35,5 @@ class LSTMCellOp : public OperationCuDnn {
     RNN::Details::LSTMCellDescriptorsCuDnn descs_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/lstm_sequence.cpp b/modules/nvidia_plugin/src/ops/lstm_sequence.cpp
similarity index 97%
rename from modules/cuda_plugin/src/ops/lstm_sequence.cpp
rename to modules/nvidia_plugin/src/ops/lstm_sequence.cpp
index 0747bebfa..53eff7580 100644
--- a/modules/cuda_plugin/src/ops/lstm_sequence.cpp
+++ b/modules/nvidia_plugin/src/ops/lstm_sequence.cpp
@@ -11,14 +11,15 @@
 
 #include "rnn_components/lstm_sequence_components.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 LSTMSequenceOp::LSTMSequenceOp(const CreationContext& context,
                                const NodeOp& node,
                                IndexCollection&& inputIds,
                                IndexCollection&& outputIds)
     : LSTMSequenceOpBase(context, LSTMSequenceParams{node}, config(), node, std::move(inputIds), std::move(outputIds)) {
-    using LSTMSequenceArgIndices = CUDAPlugin::RNN::Details::LSTMSequenceArgIndices;
+    using LSTMSequenceArgIndices = ov::nvidia_gpu::RNN::Details::LSTMSequenceArgIndices;
     const int64_t batch_size = params_.batch_size_;
     const int64_t num_directions = params_.numDirections();
     const int64_t hidden_size = params_.hidden_size_;
@@ -131,4 +132,5 @@ void LSTMSequenceOp::setupLayoutAdapters() {
 
 OPERATION_REGISTER(LSTMSequenceOp, LSTMSequence);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/lstm_sequence.hpp b/modules/nvidia_plugin/src/ops/lstm_sequence.hpp
similarity index 87%
rename from modules/cuda_plugin/src/ops/lstm_sequence.hpp
rename to modules/nvidia_plugin/src/ops/lstm_sequence.hpp
index fee9a3a8a..6b208d05a 100644
--- a/modules/cuda_plugin/src/ops/lstm_sequence.hpp
+++ b/modules/nvidia_plugin/src/ops/lstm_sequence.hpp
@@ -6,7 +6,8 @@
 
 #include "lstm_sequence_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * @brief Implements `ov::op::v5::LSTMSequence` using cuDNN API
@@ -24,4 +25,5 @@ class LSTMSequenceOp : public LSTMSequenceOpBase {
     void setupLayoutAdapters();
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/lstm_sequence_base.cpp b/modules/nvidia_plugin/src/ops/lstm_sequence_base.cpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/lstm_sequence_base.cpp
rename to modules/nvidia_plugin/src/ops/lstm_sequence_base.cpp
index 2eda808e9..7e41b741e 100644
--- a/modules/cuda_plugin/src/ops/lstm_sequence_base.cpp
+++ b/modules/nvidia_plugin/src/ops/lstm_sequence_base.cpp
@@ -8,7 +8,8 @@
 #include <utility>
 #include <vector>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 LSTMSequenceOpBase::LSTMSequenceOpBase(const CreationContext& context,
                                        const LSTMSequenceParams& params,
@@ -29,7 +30,7 @@ void LSTMSequenceOpBase::Execute(const InferenceRequestContext& context,
                                  Inputs inputs,
                                  Outputs outputs,
                                  const Workbuffers& workbuffers) const {
-    using ArgIndices = CUDAPlugin::RNN::Details::LSTMSequenceArgIndices;
+    using ArgIndices = ov::nvidia_gpu::RNN::Details::LSTMSequenceArgIndices;
     Expects(inputs.size() == 7);
     Expects(outputs.size() == 3);
 
@@ -90,4 +91,5 @@ void LSTMSequenceOpBase::calcAdapterWorkbuffers() {
     if (cy_adapter) cy_adapter->requestWorkbuffer(mut_sizes_);
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/lstm_sequence_base.hpp b/modules/nvidia_plugin/src/ops/lstm_sequence_base.hpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/lstm_sequence_base.hpp
rename to modules/nvidia_plugin/src/ops/lstm_sequence_base.hpp
index 32341357c..e9022e454 100644
--- a/modules/cuda_plugin/src/ops/lstm_sequence_base.hpp
+++ b/modules/nvidia_plugin/src/ops/lstm_sequence_base.hpp
@@ -12,7 +12,8 @@
 #include "rnn_components/lstm_sequence_cudnn_components.hpp"
 #include "rnn_components/rnn_sequence_components.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class LSTMSequenceOpBase : public OperationCuDnn {
 public:
@@ -59,4 +60,5 @@ class LSTMSequenceOpBase : public OperationCuDnn {
     OutputTensorAdapterPtr cy_adapter;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/lstm_sequence_optimized.cpp b/modules/nvidia_plugin/src/ops/lstm_sequence_optimized.cpp
similarity index 95%
rename from modules/cuda_plugin/src/ops/lstm_sequence_optimized.cpp
rename to modules/nvidia_plugin/src/ops/lstm_sequence_optimized.cpp
index 5b968fad0..9679ddd53 100644
--- a/modules/cuda_plugin/src/ops/lstm_sequence_optimized.cpp
+++ b/modules/nvidia_plugin/src/ops/lstm_sequence_optimized.cpp
@@ -9,7 +9,8 @@
 #include <utility>
 #include <vector>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 LSTMSequenceOptimizedOp::LSTMSequenceOptimizedOp(const CreationContext& context,
                                                  const NodeOp& node,
@@ -40,7 +41,7 @@ LSTMSequenceOptimizedOp::LSTMSequenceOptimizedOp(const CreationContext& context,
             validateSequenceMajorArgShapes(node);
             setupSequenceMajorLayoutAdapters();
             throwIEException(
-                "'CUDAPlugin::nodes::LSTMSequenceOptimized::SequenceMajor': This mode has never been used with real "
+                "'ov::nvidia_gpu::nodes::LSTMSequenceOptimized::SequenceMajor': This mode has never been used with real "
                 "model.");
             break;
         default:
@@ -66,7 +67,7 @@ LSTMSequenceOpBase::Config LSTMSequenceOptimizedOp::config(const NodeOp& node) {
 }
 
 void LSTMSequenceOptimizedOp::validateBatchMajorArgShapes(const NodeOp& node) {
-    using LSTMSequenceArgIndices = CUDAPlugin::RNN::Details::LSTMSequenceArgIndices;
+    using LSTMSequenceArgIndices = ov::nvidia_gpu::RNN::Details::LSTMSequenceArgIndices;
     const int64_t batch_size = params_.batch_size_;
     const int64_t num_directions = params_.numDirections();
     const int64_t hidden_size = params_.hidden_size_;
@@ -137,7 +138,7 @@ void LSTMSequenceOptimizedOp::setupBatchMajorLayoutAdapters() {
 }
 
 void LSTMSequenceOptimizedOp::validateSequenceMajorArgShapes(const NodeOp& node) {
-    using LSTMSequenceArgIndices = CUDAPlugin::RNN::Details::LSTMSequenceArgIndices;
+    using LSTMSequenceArgIndices = ov::nvidia_gpu::RNN::Details::LSTMSequenceArgIndices;
     const int64_t batch_size = params_.batch_size_;
     const int64_t num_directions = params_.numDirections();
     const int64_t hidden_size = params_.hidden_size_;
@@ -209,4 +210,5 @@ void LSTMSequenceOptimizedOp::setupSequenceMajorLayoutAdapters() {
 
 OPERATION_REGISTER(LSTMSequenceOptimizedOp, LSTMSequenceOptimized);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/lstm_sequence_optimized.hpp b/modules/nvidia_plugin/src/ops/lstm_sequence_optimized.hpp
similarity index 87%
rename from modules/cuda_plugin/src/ops/lstm_sequence_optimized.hpp
rename to modules/nvidia_plugin/src/ops/lstm_sequence_optimized.hpp
index b2e40f127..53e68d995 100644
--- a/modules/cuda_plugin/src/ops/lstm_sequence_optimized.hpp
+++ b/modules/nvidia_plugin/src/ops/lstm_sequence_optimized.hpp
@@ -6,10 +6,11 @@
 
 #include "lstm_sequence_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
- * @brief Implements `CUDAPlugin::nodes::LSTMSequenceOptimized` using cuDNN API.
+ * @brief Implements `ov::nvidia_gpu::nodes::LSTMSequenceOptimized` using cuDNN API.
  *
  * OpenVINO and cuDNN are using different layouts for input/output tensor
  * shapes. In general, it takes 5 additional transpose operations to
@@ -30,7 +31,7 @@ namespace CUDAPlugin {
  */
 class LSTMSequenceOptimizedOp : public LSTMSequenceOpBase {
 public:
-    using NodeOp = CUDAPlugin::nodes::LSTMSequenceOptimized;
+    using NodeOp = ov::nvidia_gpu::nodes::LSTMSequenceOptimized;
     LSTMSequenceOptimizedOp(const CreationContext& context,
                             const NodeOp& node,
                             IndexCollection&& inputIds,
@@ -44,4 +45,5 @@ class LSTMSequenceOptimizedOp : public LSTMSequenceOpBase {
     void setupSequenceMajorLayoutAdapters();
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/matmul.cpp b/modules/nvidia_plugin/src/ops/matmul.cpp
similarity index 99%
rename from modules/cuda_plugin/src/ops/matmul.cpp
rename to modules/nvidia_plugin/src/ops/matmul.cpp
index 5069b0e21..866b91cf1 100644
--- a/modules/cuda_plugin/src/ops/matmul.cpp
+++ b/modules/nvidia_plugin/src/ops/matmul.cpp
@@ -17,7 +17,8 @@
 #include "converters.hpp"
 #include "cuda/constant_factory.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 template <typename TOperation>
 MatMulOp::MatMulOp(const CreationContext& context,
@@ -226,4 +227,5 @@ void MatMulOp::Execute(const InferenceRequestContext& context,
 }
 
 OPERATION_REGISTER(MatMulOp, MatMul);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/matmul.hpp b/modules/nvidia_plugin/src/ops/matmul.hpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/matmul.hpp
rename to modules/nvidia_plugin/src/ops/matmul.hpp
index c8829da3c..774b55a97 100644
--- a/modules/cuda_plugin/src/ops/matmul.hpp
+++ b/modules/nvidia_plugin/src/ops/matmul.hpp
@@ -11,7 +11,8 @@
 
 #include "cuda/constant_factory.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class MatMulOp : public OperationCuBlas {
 public:
@@ -81,4 +82,5 @@ class MatMulOp : public OperationCuBlas {
     cublasOperation_t cublas_transpose_b_ = CUBLAS_OP_N;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/maximum.cpp b/modules/nvidia_plugin/src/ops/maximum.cpp
similarity index 69%
rename from modules/cuda_plugin/src/ops/maximum.cpp
rename to modules/nvidia_plugin/src/ops/maximum.cpp
index 8004f8089..de2a6ca3e 100644
--- a/modules/cuda_plugin/src/ops/maximum.cpp
+++ b/modules/nvidia_plugin/src/ops/maximum.cpp
@@ -6,8 +6,10 @@
 
 #include <cuda_operation_registry.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 OPERATION_REGISTER(MaximumOp, Maximum)
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/maximum.hpp b/modules/nvidia_plugin/src/ops/maximum.hpp
similarity index 80%
rename from modules/cuda_plugin/src/ops/maximum.hpp
rename to modules/nvidia_plugin/src/ops/maximum.hpp
index b1a2077b2..2ba20fea6 100644
--- a/modules/cuda_plugin/src/ops/maximum.hpp
+++ b/modules/nvidia_plugin/src/ops/maximum.hpp
@@ -9,11 +9,13 @@
 #include "elementwise_binary.hpp"
 #include "kernels/maximum.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class MaximumOp : public ElementwiseBinaryOp<ov::op::v1::Maximum, kernel::Maximum> {
 public:
     using ElementwiseBinaryOp::ElementwiseBinaryOp;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/maxpool.cpp b/modules/nvidia_plugin/src/ops/maxpool.cpp
similarity index 92%
rename from modules/cuda_plugin/src/ops/maxpool.cpp
rename to modules/nvidia_plugin/src/ops/maxpool.cpp
index b72b8400a..44c8bb600 100644
--- a/modules/cuda_plugin/src/ops/maxpool.cpp
+++ b/modules/nvidia_plugin/src/ops/maxpool.cpp
@@ -8,7 +8,8 @@
 #include <gsl/gsl_assert>
 #include <openvino/op/max_pool.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 MaxPoolOp::MaxPoolOp(const CreationContext& context,
                      const std::shared_ptr<ov::Node>& node,
@@ -31,4 +32,5 @@ void MaxPoolOp::Execute(const InferenceRequestContext& context,
 
 OPERATION_REGISTER(MaxPoolOp, MaxPool);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/maxpool.hpp b/modules/nvidia_plugin/src/ops/maxpool.hpp
similarity index 88%
rename from modules/cuda_plugin/src/ops/maxpool.hpp
rename to modules/nvidia_plugin/src/ops/maxpool.hpp
index 495c8e074..35b6bff32 100644
--- a/modules/cuda_plugin/src/ops/maxpool.hpp
+++ b/modules/nvidia_plugin/src/ops/maxpool.hpp
@@ -8,7 +8,8 @@
 
 #include "pooling_impl.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class MaxPoolOp : public OperationCuDnn {
 public:
@@ -25,4 +26,5 @@ class MaxPoolOp : public OperationCuDnn {
     PoolingImpl impl_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/minimum.cpp b/modules/nvidia_plugin/src/ops/minimum.cpp
similarity index 69%
rename from modules/cuda_plugin/src/ops/minimum.cpp
rename to modules/nvidia_plugin/src/ops/minimum.cpp
index 146484530..3b9107123 100644
--- a/modules/cuda_plugin/src/ops/minimum.cpp
+++ b/modules/nvidia_plugin/src/ops/minimum.cpp
@@ -6,8 +6,10 @@
 
 #include <cuda_operation_registry.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 OPERATION_REGISTER(MinimumOp, Minimum)
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/minimum.hpp b/modules/nvidia_plugin/src/ops/minimum.hpp
similarity index 80%
rename from modules/cuda_plugin/src/ops/minimum.hpp
rename to modules/nvidia_plugin/src/ops/minimum.hpp
index 3eb5eb234..e58684bf5 100644
--- a/modules/cuda_plugin/src/ops/minimum.hpp
+++ b/modules/nvidia_plugin/src/ops/minimum.hpp
@@ -9,11 +9,13 @@
 #include "elementwise_binary.hpp"
 #include "kernels/minimum.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class MinimumOp : public ElementwiseBinaryOp<ov::op::v1::Minimum, kernel::Minimum> {
 public:
     using ElementwiseBinaryOp::ElementwiseBinaryOp;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/mod.cpp b/modules/nvidia_plugin/src/ops/mod.cpp
similarity index 67%
rename from modules/cuda_plugin/src/ops/mod.cpp
rename to modules/nvidia_plugin/src/ops/mod.cpp
index f33d1969e..faa3695bf 100644
--- a/modules/cuda_plugin/src/ops/mod.cpp
+++ b/modules/nvidia_plugin/src/ops/mod.cpp
@@ -6,8 +6,10 @@
 
 #include <cuda_operation_registry.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 OPERATION_REGISTER(ModOp, Mod)
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/mod.hpp b/modules/nvidia_plugin/src/ops/mod.hpp
similarity index 79%
rename from modules/cuda_plugin/src/ops/mod.hpp
rename to modules/nvidia_plugin/src/ops/mod.hpp
index f13e5ba09..63b3ec95c 100644
--- a/modules/cuda_plugin/src/ops/mod.hpp
+++ b/modules/nvidia_plugin/src/ops/mod.hpp
@@ -9,11 +9,13 @@
 #include "elementwise_binary.hpp"
 #include "kernels/mod.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class ModOp : public ElementwiseBinaryOp<ov::op::v1::Mod, kernel::Mod> {
 public:
     using ElementwiseBinaryOp::ElementwiseBinaryOp;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/multiply.cpp b/modules/nvidia_plugin/src/ops/multiply.cpp
similarity index 94%
rename from modules/cuda_plugin/src/ops/multiply.cpp
rename to modules/nvidia_plugin/src/ops/multiply.cpp
index a1369e273..c362efc18 100644
--- a/modules/cuda_plugin/src/ops/multiply.cpp
+++ b/modules/nvidia_plugin/src/ops/multiply.cpp
@@ -11,7 +11,8 @@
 #include "multiply_cuda.hpp"
 #include "multiply_cudnn.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 static OperationBase::Ptr multiplyFactory(const CreationContext& context,
                                           const std::shared_ptr<ov::Node>& in_node,
@@ -41,4 +42,5 @@ static OperationBase::Ptr multiplyFactory(const CreationContext& context,
 
 OPERATION_REGISTER_FACTORY(multiplyFactory, Multiply)
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/multiply_cuda.cpp b/modules/nvidia_plugin/src/ops/multiply_cuda.cpp
similarity index 90%
rename from modules/cuda_plugin/src/ops/multiply_cuda.cpp
rename to modules/nvidia_plugin/src/ops/multiply_cuda.cpp
index 83b592285..5598d4675 100644
--- a/modules/cuda_plugin/src/ops/multiply_cuda.cpp
+++ b/modules/nvidia_plugin/src/ops/multiply_cuda.cpp
@@ -6,7 +6,8 @@
 
 #include <fmt/ostream.h>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 MultiplyCudaOp::MultiplyCudaOp(const CreationContext& context,
                                const NodeOp& node,
@@ -23,4 +24,5 @@ MultiplyCudaOp::MultiplyCudaOp(const CreationContext& context,
     }
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/multiply_cuda.hpp b/modules/nvidia_plugin/src/ops/multiply_cuda.hpp
similarity index 87%
rename from modules/cuda_plugin/src/ops/multiply_cuda.hpp
rename to modules/nvidia_plugin/src/ops/multiply_cuda.hpp
index 416e9571d..80b758731 100644
--- a/modules/cuda_plugin/src/ops/multiply_cuda.hpp
+++ b/modules/nvidia_plugin/src/ops/multiply_cuda.hpp
@@ -9,7 +9,8 @@
 #include "elementwise_binary.hpp"
 #include "kernels/multiply.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 using MultiplyCudaOpBase = ElementwiseBinaryOp<ov::op::v1::Multiply, kernel::Multiply>;
 class MultiplyCudaOp : public MultiplyCudaOpBase {
@@ -21,4 +22,5 @@ class MultiplyCudaOp : public MultiplyCudaOpBase {
                    IndexCollection&& outputIds);
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/multiply_cudnn.cpp b/modules/nvidia_plugin/src/ops/multiply_cudnn.cpp
similarity index 85%
rename from modules/cuda_plugin/src/ops/multiply_cudnn.cpp
rename to modules/nvidia_plugin/src/ops/multiply_cudnn.cpp
index ebd4a59e3..99402fe5c 100644
--- a/modules/cuda_plugin/src/ops/multiply_cudnn.cpp
+++ b/modules/nvidia_plugin/src/ops/multiply_cudnn.cpp
@@ -3,7 +3,8 @@
 //
 #include "multiply_cudnn.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 MultiplyCuDnnOp::MultiplyCuDnnOp(const CreationContext& context,
                                  const std::shared_ptr<ov::Node>& node,
@@ -11,4 +12,5 @@ MultiplyCuDnnOp::MultiplyCuDnnOp(const CreationContext& context,
                                  IndexCollection&& outputIds)
     : CuDnnTensorOpBase{context, node, move(inputIds), move(outputIds), cudnnOpTensorOp_t::CUDNN_OP_TENSOR_MUL} {}
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/multiply_cudnn.hpp b/modules/nvidia_plugin/src/ops/multiply_cudnn.hpp
similarity index 82%
rename from modules/cuda_plugin/src/ops/multiply_cudnn.hpp
rename to modules/nvidia_plugin/src/ops/multiply_cudnn.hpp
index 109a962e0..b2f5e7dbf 100644
--- a/modules/cuda_plugin/src/ops/multiply_cudnn.hpp
+++ b/modules/nvidia_plugin/src/ops/multiply_cudnn.hpp
@@ -6,7 +6,8 @@
 
 #include "cudnn_tensor_op_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class MultiplyCuDnnOp : public CuDnnTensorOpBase {
 public:
@@ -16,4 +17,5 @@ class MultiplyCuDnnOp : public CuDnnTensorOpBase {
                     IndexCollection&& outputIds);
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/mvn.cpp b/modules/nvidia_plugin/src/ops/mvn.cpp
similarity index 94%
rename from modules/cuda_plugin/src/ops/mvn.cpp
rename to modules/nvidia_plugin/src/ops/mvn.cpp
index bd7b32d88..633602688 100644
--- a/modules/cuda_plugin/src/ops/mvn.cpp
+++ b/modules/nvidia_plugin/src/ops/mvn.cpp
@@ -12,7 +12,8 @@
 #include "ngraph/op/mvn.hpp"
 #include "ngraph/shape_util.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 MvnOp::MvnOp(const CreationContext& context,
              const ov::Node& node,
@@ -26,7 +27,7 @@ MvnOp::MvnOp(const CreationContext& context,
                                             : mvn_op_v6_->get_normalize_variance()},
       epsilon_{version_ == MvnV1 ? mvn_op_v1_->get_eps() : mvn_op_v6_->get_eps()},
       eps_mode_{version_ == MvnV1 ? ov::op::MVNEpsMode::INSIDE_SQRT : mvn_op_v6_->get_eps_mode()},
-      comp_type_{CUDAPlugin::convertDataType<cudnnDataType_t>(node.get_input_element_type(0))},
+      comp_type_{ov::nvidia_gpu::convertDataType<cudnnDataType_t>(node.get_input_element_type(0))},
       op_desc_type_{comp_type_ != CUDNN_DATA_DOUBLE ? CUDNN_DATA_FLOAT : CUDNN_DATA_DOUBLE},
       reduce_mean_desc_{op_desc_type_},
       sub_desc_(CUDA::DnnOpTensorDescriptor{}.set(
@@ -48,7 +49,7 @@ MvnOp::MvnOp(const CreationContext& context,
             threads_per_block,
             epsilon_,
             size,
-            convertDataType<CUDAPlugin::kernel::Type_t>(node.get_input_element_type(0)),
+            convertDataType<ov::nvidia_gpu::kernel::Type_t>(node.get_input_element_type(0)),
             eps_mode_ == ov::op::MVNEpsMode::INSIDE_SQRT);
     }
 }
@@ -145,7 +146,7 @@ MvnOp::MvnVersion MvnOp::validateAndGetVersion(const ov::Node& node) {
                             mvnOp_v6->get_eps()));
         }
         if (ngraph::get_constant_from_source(node.get_input_node_shared_ptr(1)) == nullptr) {
-            throwIEException("The CUDAPlugin MVN-6 operation implemented only for constant axes input.");
+            throwIEException("The nvidia_gpu MVN-6 operation implemented only for constant axes input.");
         }
     }
     if (!node.get_input_partial_shape(0).rank().is_static()) {
@@ -165,7 +166,7 @@ MvnOp::MvnVersion MvnOp::validateAndGetVersion(const ov::Node& node) {
                                       // https://docs.nvidia.com/deeplearning/cudnn/api/index.html#cudnnOpTensor
     if (outputShape.size() > max_shape_size) {
         throwIEException(
-            fmt::format("CUDAPlugin::MvnOp: the tensor shape size ({}) is exceeded maximum supported value of {}.",
+            fmt::format("ov::nvidia_gpu::MvnOp: the tensor shape size ({}) is exceeded maximum supported value of {}.",
                         outputShape.size(),
                         max_shape_size));
     }
@@ -200,7 +201,7 @@ ngraph::Shape MvnOp::makeReducedShape(const ov::Node& node) {
             auto size = static_cast<int64_t>(reducedShape.size());
             if (v >= size || v < -size) {
                 throwIEException(
-                    fmt::format("CUDAPlugin::MVN-6: the axes entry ({}) out of range [{}; {}].", v, -size, size - 1));
+                    fmt::format("ov::nvidia_gpu::MVN-6: the axes entry ({}) out of range [{}; {}].", v, -size, size - 1));
             }
             axes.emplace(static_cast<size_t>((v + size) % size));
         }
@@ -217,4 +218,5 @@ CUDA::DnnTensorDescriptor MvnOp::makeReducedTensorDescriptor(const ov::Node& nod
 }
 
 OPERATION_REGISTER(MvnOp, MVN);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/mvn.hpp b/modules/nvidia_plugin/src/ops/mvn.hpp
similarity index 97%
rename from modules/cuda_plugin/src/ops/mvn.hpp
rename to modules/nvidia_plugin/src/ops/mvn.hpp
index 5202b33de..a972f1e1c 100644
--- a/modules/cuda_plugin/src/ops/mvn.hpp
+++ b/modules/nvidia_plugin/src/ops/mvn.hpp
@@ -11,7 +11,8 @@
 #include "ngraph/op/mvn.hpp"
 #include "ngraph/shape.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class MvnOp : public OperationCuDnn {
 public:
@@ -103,4 +104,5 @@ inline WorkbufferRequest MvnOp::GetWorkBufferRequest() const {
     return {};
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/nop_op.cpp b/modules/nvidia_plugin/src/ops/nop_op.cpp
similarity index 80%
rename from modules/cuda_plugin/src/ops/nop_op.cpp
rename to modules/nvidia_plugin/src/ops/nop_op.cpp
index 60822c699..ffdfabf2b 100644
--- a/modules/cuda_plugin/src/ops/nop_op.cpp
+++ b/modules/nvidia_plugin/src/ops/nop_op.cpp
@@ -6,7 +6,8 @@
 
 #include <cuda_operation_registry.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 OPERATION_REGISTER(NopOp, Constant);
 OPERATION_REGISTER(NopOp, Reshape);
@@ -14,4 +15,5 @@ OPERATION_REGISTER(NopOp, Squeeze);
 OPERATION_REGISTER(NopOp, Unsqueeze);
 OPERATION_REGISTER(NopOp, ConcatOptimized);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/nop_op.hpp b/modules/nvidia_plugin/src/ops/nop_op.hpp
similarity index 94%
rename from modules/cuda_plugin/src/ops/nop_op.hpp
rename to modules/nvidia_plugin/src/ops/nop_op.hpp
index 3d4db7deb..a42588f39 100644
--- a/modules/cuda_plugin/src/ops/nop_op.hpp
+++ b/modules/nvidia_plugin/src/ops/nop_op.hpp
@@ -6,7 +6,8 @@
 
 #include <cuda_operation_base.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 /**
  * @brief NOP - no operation. Common implementation for all operations which
@@ -39,4 +40,5 @@ class NopOp : public OperationBase {
                  const Workbuffers& workbuffers) const override {}
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/pad.cpp b/modules/nvidia_plugin/src/ops/pad.cpp
similarity index 97%
rename from modules/cuda_plugin/src/ops/pad.cpp
rename to modules/nvidia_plugin/src/ops/pad.cpp
index 86e438968..2837fa289 100644
--- a/modules/cuda_plugin/src/ops/pad.cpp
+++ b/modules/nvidia_plugin/src/ops/pad.cpp
@@ -12,7 +12,8 @@
 
 #include "converters.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 static bool isNCHWConvolutionPadding(const PadOp::NodeOp& node) {
     auto padsBegin = ov::get_constant_from_source(node.input_value(1));
@@ -69,4 +70,5 @@ void PadOp::InitSharedImmutableWorkbuffers(const Buffers& devicePointers) {
 
 OPERATION_REGISTER(PadOp, Pad);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/pad.hpp b/modules/nvidia_plugin/src/ops/pad.hpp
similarity index 92%
rename from modules/cuda_plugin/src/ops/pad.hpp
rename to modules/nvidia_plugin/src/ops/pad.hpp
index 74b4a99b2..01a70435d 100644
--- a/modules/cuda_plugin/src/ops/pad.hpp
+++ b/modules/nvidia_plugin/src/ops/pad.hpp
@@ -7,7 +7,8 @@
 #include <kernels/pad.cuh>
 #include <openvino/op/pad.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class PadOp : public OperationBase {
 public:
@@ -45,4 +46,5 @@ class PadOp : public OperationBase {
     ov::Shape dst_shape_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/parameter.cpp b/modules/nvidia_plugin/src/ops/parameter.cpp
similarity index 93%
rename from modules/cuda_plugin/src/ops/parameter.cpp
rename to modules/nvidia_plugin/src/ops/parameter.cpp
index ae0be1dc7..ef006bb29 100644
--- a/modules/cuda_plugin/src/ops/parameter.cpp
+++ b/modules/nvidia_plugin/src/ops/parameter.cpp
@@ -10,7 +10,8 @@
 #include <gsl/gsl_assert>
 #include <ngraph/node.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 ParameterOp::ParameterOp(const CreationContext& context,
                          const ov::Node& node,
@@ -35,4 +36,5 @@ void ParameterOp::Execute(const InferenceRequestContext& context,
 std::string ParameterOp::GetInputTensorName(const ov::Node& node) { return node.get_friendly_name(); }
 
 OPERATION_REGISTER(ParameterOp, Parameter);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/parameter.hpp b/modules/nvidia_plugin/src/ops/parameter.hpp
similarity index 89%
rename from modules/cuda_plugin/src/ops/parameter.hpp
rename to modules/nvidia_plugin/src/ops/parameter.hpp
index 4ebbb6389..2435e23b9 100644
--- a/modules/cuda_plugin/src/ops/parameter.hpp
+++ b/modules/nvidia_plugin/src/ops/parameter.hpp
@@ -7,7 +7,8 @@
 #include <cuda/device_pointers.hpp>
 #include <cuda_operation_base.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class ParameterOp : public OperationBase {
 public:
@@ -25,4 +26,5 @@ class ParameterOp : public OperationBase {
     std::string input_tensor_name_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/pooling_impl.cpp b/modules/nvidia_plugin/src/ops/pooling_impl.cpp
similarity index 98%
rename from modules/cuda_plugin/src/ops/pooling_impl.cpp
rename to modules/nvidia_plugin/src/ops/pooling_impl.cpp
index c3d258d7f..b3f45c8f5 100644
--- a/modules/cuda_plugin/src/ops/pooling_impl.cpp
+++ b/modules/nvidia_plugin/src/ops/pooling_impl.cpp
@@ -13,7 +13,8 @@
 #include "converters.hpp"
 #include "cuda/constant_factory.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 static constexpr size_t non_spatial_dims_{2};
 static constexpr size_t min_spatial_dims_{2};
@@ -153,4 +154,5 @@ std::vector<int> PoolingImpl::paddings_from_ngraph(const ov::Shape& pads_begin,
 
 int PoolingImpl::spatial_dims() const { return dims_ - non_spatial_dims_; }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/pooling_impl.hpp b/modules/nvidia_plugin/src/ops/pooling_impl.hpp
similarity index 94%
rename from modules/cuda_plugin/src/ops/pooling_impl.hpp
rename to modules/nvidia_plugin/src/ops/pooling_impl.hpp
index 74c581abf..8b56e1a21 100644
--- a/modules/cuda_plugin/src/ops/pooling_impl.hpp
+++ b/modules/nvidia_plugin/src/ops/pooling_impl.hpp
@@ -9,7 +9,8 @@
 #include <openvino/op/avg_pool.hpp>
 #include <openvino/op/max_pool.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class PoolingImpl {
 public:
@@ -43,4 +44,5 @@ class PoolingImpl {
     CUDA::DnnTensorDescriptor output_tensor_descriptor_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/power.cpp b/modules/nvidia_plugin/src/ops/power.cpp
similarity index 68%
rename from modules/cuda_plugin/src/ops/power.cpp
rename to modules/nvidia_plugin/src/ops/power.cpp
index 24f247e12..b81b5f886 100644
--- a/modules/cuda_plugin/src/ops/power.cpp
+++ b/modules/nvidia_plugin/src/ops/power.cpp
@@ -6,8 +6,10 @@
 
 #include <cuda_operation_registry.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 OPERATION_REGISTER(PowerOp, Power)
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/power.hpp b/modules/nvidia_plugin/src/ops/power.hpp
similarity index 80%
rename from modules/cuda_plugin/src/ops/power.hpp
rename to modules/nvidia_plugin/src/ops/power.hpp
index 010767e94..14b5a3301 100644
--- a/modules/cuda_plugin/src/ops/power.hpp
+++ b/modules/nvidia_plugin/src/ops/power.hpp
@@ -9,11 +9,13 @@
 #include "elementwise_binary.hpp"
 #include "kernels/power.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class PowerOp : public ElementwiseBinaryOp<ov::op::v1::Power, kernel::Power> {
 public:
     using ElementwiseBinaryOp::ElementwiseBinaryOp;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/prelu.cpp b/modules/nvidia_plugin/src/ops/prelu.cpp
similarity index 73%
rename from modules/cuda_plugin/src/ops/prelu.cpp
rename to modules/nvidia_plugin/src/ops/prelu.cpp
index 3d9a31a36..f93db4356 100644
--- a/modules/cuda_plugin/src/ops/prelu.cpp
+++ b/modules/nvidia_plugin/src/ops/prelu.cpp
@@ -10,8 +10,10 @@
 
 #include "cuda_operation_registry.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 OPERATION_REGISTER(PReluOp, PRelu)
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/prelu.hpp b/modules/nvidia_plugin/src/ops/prelu.hpp
similarity index 81%
rename from modules/cuda_plugin/src/ops/prelu.hpp
rename to modules/nvidia_plugin/src/ops/prelu.hpp
index 3ec36a780..47930f3ff 100644
--- a/modules/cuda_plugin/src/ops/prelu.hpp
+++ b/modules/nvidia_plugin/src/ops/prelu.hpp
@@ -10,11 +10,13 @@
 #include "elementwise_binary.hpp"
 #include "kernels/prelu.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class PReluOp : public ElementwiseBinaryOp<ov::op::v0::PRelu, kernel::PRelu> {
 public:
     using ElementwiseBinaryOp::ElementwiseBinaryOp;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/range.cpp b/modules/nvidia_plugin/src/ops/range.cpp
similarity index 83%
rename from modules/cuda_plugin/src/ops/range.cpp
rename to modules/nvidia_plugin/src/ops/range.cpp
index cbd6fb4df..e554004bc 100644
--- a/modules/cuda_plugin/src/ops/range.cpp
+++ b/modules/nvidia_plugin/src/ops/range.cpp
@@ -14,7 +14,8 @@
 #include "kernels/cuda_type_traits.hpp"
 #include "kernels/range.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 static constexpr auto OUTPUT_INDX = 0u;
 
@@ -43,10 +44,10 @@ RangeOp::RangeOp(const CreationContext& context,
     kernel_op_ = kernel::RangeKernelOp(max_size,
                                        blocks_number,
                                        threads_per_block,
-                                       convertDataType<CUDAPlugin::kernel::Type_t>(inputStart_type),
-                                       convertDataType<CUDAPlugin::kernel::Type_t>(inputStop_type),
-                                       convertDataType<CUDAPlugin::kernel::Type_t>(inputStep_type),
-                                       convertDataType<CUDAPlugin::kernel::Type_t>(output_type));
+                                       convertDataType<ov::nvidia_gpu::kernel::Type_t>(inputStart_type),
+                                       convertDataType<ov::nvidia_gpu::kernel::Type_t>(inputStop_type),
+                                       convertDataType<ov::nvidia_gpu::kernel::Type_t>(inputStep_type),
+                                       convertDataType<ov::nvidia_gpu::kernel::Type_t>(output_type));
 }
 
 void RangeOp::Execute(const InferenceRequestContext& context,
@@ -64,4 +65,5 @@ void RangeOp::Execute(const InferenceRequestContext& context,
 }
 
 OPERATION_REGISTER(RangeOp, Range);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/range.hpp b/modules/nvidia_plugin/src/ops/range.hpp
similarity index 89%
rename from modules/cuda_plugin/src/ops/range.hpp
rename to modules/nvidia_plugin/src/ops/range.hpp
index c5dd4567f..714935786 100644
--- a/modules/cuda_plugin/src/ops/range.hpp
+++ b/modules/nvidia_plugin/src/ops/range.hpp
@@ -9,7 +9,8 @@
 
 #include "kernels/range.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class RangeOp : public OperationBase {
     enum InputIdx { START_INDX, STOP_INDX, STEP_INDX };
@@ -30,4 +31,5 @@ class RangeOp : public OperationBase {
     std::optional<kernel::RangeKernelOp> kernel_op_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/reduce_sum.cpp b/modules/nvidia_plugin/src/ops/reduce_sum.cpp
similarity index 95%
rename from modules/cuda_plugin/src/ops/reduce_sum.cpp
rename to modules/nvidia_plugin/src/ops/reduce_sum.cpp
index 8180efb2c..f2d5dd759 100644
--- a/modules/cuda_plugin/src/ops/reduce_sum.cpp
+++ b/modules/nvidia_plugin/src/ops/reduce_sum.cpp
@@ -7,7 +7,8 @@
 #include <cuda/descriptor_utils.hpp>
 #include <cuda_operation_registry.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 cudnnDataType_t reduceCompType(const ov::Node& node) {
     if (node.get_input_element_type(0) == ov::element::Type_t::f64) return CUDNN_DATA_DOUBLE;
@@ -40,4 +41,5 @@ void ReduceSumOp::Execute(const InferenceRequestContext& context,
 }
 
 OPERATION_REGISTER(ReduceSumOp, ReduceSum);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/reduce_sum.hpp b/modules/nvidia_plugin/src/ops/reduce_sum.hpp
similarity index 92%
rename from modules/cuda_plugin/src/ops/reduce_sum.hpp
rename to modules/nvidia_plugin/src/ops/reduce_sum.hpp
index 93e453795..6b28a7f53 100644
--- a/modules/cuda_plugin/src/ops/reduce_sum.hpp
+++ b/modules/nvidia_plugin/src/ops/reduce_sum.hpp
@@ -6,7 +6,8 @@
 
 #include <cuda_operation_base.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class ReduceSumOp : public OperationCuDnn {
 public:
@@ -34,4 +35,5 @@ inline WorkbufferRequest ReduceSumOp::GetWorkBufferRequest() const {
     return {{}, {workspace_size_}};  // TODO: find a way to allocate buffers from constructor
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/relu.cpp b/modules/nvidia_plugin/src/ops/relu.cpp
similarity index 85%
rename from modules/cuda_plugin/src/ops/relu.cpp
rename to modules/nvidia_plugin/src/ops/relu.cpp
index 6439438eb..567a5820d 100644
--- a/modules/cuda_plugin/src/ops/relu.cpp
+++ b/modules/nvidia_plugin/src/ops/relu.cpp
@@ -6,7 +6,8 @@
 
 #include <cuda_operation_registry.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 ReluOp::ReluOp(const CreationContext& context,
                const std::shared_ptr<ov::Node>& node,
@@ -16,4 +17,5 @@ ReluOp::ReluOp(const CreationContext& context,
           std::make_unique<CUDA::ReluDescriptor>(), context, *node, move(inputIds), move(outputIds)} {}
 
 OPERATION_REGISTER(ReluOp, Relu);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/relu.hpp b/modules/nvidia_plugin/src/ops/relu.hpp
similarity index 83%
rename from modules/cuda_plugin/src/ops/relu.hpp
rename to modules/nvidia_plugin/src/ops/relu.hpp
index 50bea75ef..bebb1e4c7 100644
--- a/modules/cuda_plugin/src/ops/relu.hpp
+++ b/modules/nvidia_plugin/src/ops/relu.hpp
@@ -8,7 +8,8 @@
 
 #include "activation_forward_cudnn_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class ReluOp : public ActivationForwardCuDnnOpBase {
 public:
@@ -18,4 +19,5 @@ class ReluOp : public ActivationForwardCuDnnOpBase {
            IndexCollection&& outputIds);
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/result.cpp b/modules/nvidia_plugin/src/ops/result.cpp
similarity index 98%
rename from modules/cuda_plugin/src/ops/result.cpp
rename to modules/nvidia_plugin/src/ops/result.cpp
index cb748138c..18a7a204e 100644
--- a/modules/cuda_plugin/src/ops/result.cpp
+++ b/modules/nvidia_plugin/src/ops/result.cpp
@@ -17,7 +17,8 @@
 #include "nop_op.hpp"
 #include "transformations/utils/utils.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 ResultOp::ResultOp(const CreationContext& context,
                    const NodeOp& node,
@@ -112,4 +113,5 @@ std::vector<std::string> ResultOp::GetOutputTensorName(const ov::op::v0::Result&
 }
 
 OPERATION_REGISTER(ResultOp, Result);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/result.hpp b/modules/nvidia_plugin/src/ops/result.hpp
similarity index 92%
rename from modules/cuda_plugin/src/ops/result.hpp
rename to modules/nvidia_plugin/src/ops/result.hpp
index 329fb7f13..a8858c2bf 100644
--- a/modules/cuda_plugin/src/ops/result.hpp
+++ b/modules/nvidia_plugin/src/ops/result.hpp
@@ -8,7 +8,8 @@
 #include <cuda_operation_base.hpp>
 #include <openvino/op/result.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class ResultOp : public OperationBase {
 public:
@@ -31,4 +32,5 @@ class ResultOp : public OperationBase {
     std::vector<std::string> output_tensor_names_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/rnn_components/gru_sequence_components.cpp b/modules/nvidia_plugin/src/ops/rnn_components/gru_sequence_components.cpp
similarity index 97%
rename from modules/cuda_plugin/src/ops/rnn_components/gru_sequence_components.cpp
rename to modules/nvidia_plugin/src/ops/rnn_components/gru_sequence_components.cpp
index 3f6a52cca..12b8f486d 100644
--- a/modules/cuda_plugin/src/ops/rnn_components/gru_sequence_components.cpp
+++ b/modules/nvidia_plugin/src/ops/rnn_components/gru_sequence_components.cpp
@@ -13,7 +13,7 @@
 #include <openvino/op/unsqueeze.hpp>
 #include <typeinfo>
 
-namespace CUDAPlugin::RNN::Details {
+namespace ov::nvidia_gpu::RNN::Details {
 
 namespace {
 
@@ -95,4 +95,4 @@ GRUSequenceParams::GRUSequenceParams(const ov::op::v5::GRUSequence& node)
     Expects(b_host_buffers_.size_bytes() == ov::shape_size(b_shape) * element_type_size);
 }
 
-}  // namespace CUDAPlugin::RNN::Details
+}  // namespace ov::nvidia_gpu::RNN::Details
diff --git a/modules/cuda_plugin/src/ops/rnn_components/gru_sequence_components.hpp b/modules/nvidia_plugin/src/ops/rnn_components/gru_sequence_components.hpp
similarity index 93%
rename from modules/cuda_plugin/src/ops/rnn_components/gru_sequence_components.hpp
rename to modules/nvidia_plugin/src/ops/rnn_components/gru_sequence_components.hpp
index 32a156ea4..f887d8dbb 100644
--- a/modules/cuda_plugin/src/ops/rnn_components/gru_sequence_components.hpp
+++ b/modules/nvidia_plugin/src/ops/rnn_components/gru_sequence_components.hpp
@@ -10,7 +10,7 @@
 
 #include "gru_sequence_components.hpp"
 
-namespace CUDAPlugin::RNN::Details {
+namespace ov::nvidia_gpu::RNN::Details {
 
 /**
  * @brief Defines tensor indices for `ov::op::v5::GRUSequence` node.
@@ -50,4 +50,4 @@ struct GRUSequenceParams {
     size_t hidden_size_;
 };
 
-}  // namespace CUDAPlugin::RNN::Details
+}  // namespace ov::nvidia_gpu::RNN::Details
diff --git a/modules/cuda_plugin/src/ops/rnn_components/gru_sequence_cudnn_components.cpp b/modules/nvidia_plugin/src/ops/rnn_components/gru_sequence_cudnn_components.cpp
similarity index 98%
rename from modules/cuda_plugin/src/ops/rnn_components/gru_sequence_cudnn_components.cpp
rename to modules/nvidia_plugin/src/ops/rnn_components/gru_sequence_cudnn_components.cpp
index 42d56edb4..cc2fc2123 100644
--- a/modules/cuda_plugin/src/ops/rnn_components/gru_sequence_cudnn_components.cpp
+++ b/modules/nvidia_plugin/src/ops/rnn_components/gru_sequence_cudnn_components.cpp
@@ -8,12 +8,12 @@
 #include <gsl/gsl_assert>
 #include <ops/converters.hpp>
 
-namespace CUDAPlugin::RNN::Details {
+namespace ov::nvidia_gpu::RNN::Details {
 
 GRUSequenceParamsCuDnn::GRUSequenceParamsCuDnn(const GRUSequenceParams& params)
     : element_type_{convertDataType<cudnnDataType_t>(params.element_type_)},
       element_type_cuda_{convertDataType<cudaDataType_t>(params.element_type_)},
-      element_size_{CUDAPlugin::elementSize(element_type_)},
+      element_size_{ov::nvidia_gpu::elementSize(element_type_)},
       direction_{CUDNN_UNIDIRECTIONAL},
       linear_before_reset_{params.linear_before_reset_},
       batch_size_{static_cast<int32_t>(params.batch_size_)},
@@ -260,7 +260,7 @@ void GRUSequenceDescriptorsCuDnn::calculateWeightBuffers(DevPtr buffer) {
     const auto data_type = params_.element_type_;
     const auto input_size = params_.input_size_;
     const auto hidden_size = params_.hidden_size_;
-    const auto element_size = CUDAPlugin::elementSize(params_.element_type_);
+    const auto element_size = ov::nvidia_gpu::elementSize(params_.element_type_);
 
     w_dev_buffers_.clear();
     r_dev_buffers_.clear();
@@ -363,4 +363,4 @@ void GRUSequenceDescriptorsCuDnn::calculateWeightBuffers(DevPtr buffer) {
             r_total_bytes >= params_.r_host_buffers_.size_bytes());
 }
 
-}  // namespace CUDAPlugin::RNN::Details
+}  // namespace ov::nvidia_gpu::RNN::Details
diff --git a/modules/cuda_plugin/src/ops/rnn_components/gru_sequence_cudnn_components.hpp b/modules/nvidia_plugin/src/ops/rnn_components/gru_sequence_cudnn_components.hpp
similarity index 97%
rename from modules/cuda_plugin/src/ops/rnn_components/gru_sequence_cudnn_components.hpp
rename to modules/nvidia_plugin/src/ops/rnn_components/gru_sequence_cudnn_components.hpp
index 215816de3..1847ecf38 100644
--- a/modules/cuda_plugin/src/ops/rnn_components/gru_sequence_cudnn_components.hpp
+++ b/modules/nvidia_plugin/src/ops/rnn_components/gru_sequence_cudnn_components.hpp
@@ -9,7 +9,7 @@
 
 #include "gru_sequence_components.hpp"
 
-namespace CUDAPlugin::RNN::Details {
+namespace ov::nvidia_gpu::RNN::Details {
 
 /**
  * @brief Presents GRU Sequence parameters in a form suitable for cuDNN API.
@@ -99,4 +99,4 @@ class GRUSequenceDescriptorsCuDnn {
     DevBuffers b2_dev_buffers_;
 };
 
-}  // namespace CUDAPlugin::RNN::Details
+}  // namespace ov::nvidia_gpu::RNN::Details
diff --git a/modules/cuda_plugin/src/ops/rnn_components/lstm_sequence_components.cpp b/modules/nvidia_plugin/src/ops/rnn_components/lstm_sequence_components.cpp
similarity index 95%
rename from modules/cuda_plugin/src/ops/rnn_components/lstm_sequence_components.cpp
rename to modules/nvidia_plugin/src/ops/rnn_components/lstm_sequence_components.cpp
index 44215a227..6ddbcfa52 100644
--- a/modules/cuda_plugin/src/ops/rnn_components/lstm_sequence_components.cpp
+++ b/modules/nvidia_plugin/src/ops/rnn_components/lstm_sequence_components.cpp
@@ -14,7 +14,7 @@
 #include <openvino/op/unsqueeze.hpp>
 #include <typeinfo>
 
-namespace CUDAPlugin::RNN::Details {
+namespace ov::nvidia_gpu::RNN::Details {
 
 namespace {
 
@@ -58,7 +58,7 @@ LSTMSequenceParams::LSTMSequenceParams(const ov::op::v5::LSTMSequence& node)
     validate(node);
 }
 
-LSTMSequenceParams::LSTMSequenceParams(const CUDAPlugin::nodes::LSTMSequenceOptimized& node)
+LSTMSequenceParams::LSTMSequenceParams(const ov::nvidia_gpu::nodes::LSTMSequenceOptimized& node)
     : element_type_{node.get_input_element_type(LSTMSequenceArgIndices::x)},
       direction_{node.get_direction()},
       activations_{node.get_activations()},
@@ -71,7 +71,7 @@ LSTMSequenceParams::LSTMSequenceParams(const CUDAPlugin::nodes::LSTMSequenceOpti
 
     const auto& x_shape = node.get_input_shape(LSTMSequenceArgIndices::x);
     Expects(x_shape.size() == 3);
-    using LSTMSequenceOptimized = CUDAPlugin::nodes::LSTMSequenceOptimized;
+    using LSTMSequenceOptimized = ov::nvidia_gpu::nodes::LSTMSequenceOptimized;
     switch (node.get_major_format()) {
         case LSTMSequenceOptimized::BatchMajor:
             batch_size_ = x_shape[0];
@@ -134,4 +134,4 @@ void LSTMSequenceParams::validate(const ov::op::v5::LSTMSequence& node) {
     Expects(b_host_buffers_.size_bytes() == ov::shape_size(b_shape) * element_type_size);
 }
 
-}  // namespace CUDAPlugin::RNN::Details
+}  // namespace ov::nvidia_gpu::RNN::Details
diff --git a/modules/cuda_plugin/src/ops/rnn_components/lstm_sequence_components.hpp b/modules/nvidia_plugin/src/ops/rnn_components/lstm_sequence_components.hpp
similarity index 90%
rename from modules/cuda_plugin/src/ops/rnn_components/lstm_sequence_components.hpp
rename to modules/nvidia_plugin/src/ops/rnn_components/lstm_sequence_components.hpp
index 1f22195fc..b50521db5 100644
--- a/modules/cuda_plugin/src/ops/rnn_components/lstm_sequence_components.hpp
+++ b/modules/nvidia_plugin/src/ops/rnn_components/lstm_sequence_components.hpp
@@ -9,7 +9,7 @@
 #include <openvino/op/lstm_sequence.hpp>
 #include <transformer/nodes/lstm_sequence_optimized.hpp>
 
-namespace CUDAPlugin::RNN::Details {
+namespace ov::nvidia_gpu::RNN::Details {
 
 /**
  * @brief Defines tensor indices for `ov::op::v5::LSTMSequence` node.
@@ -32,7 +32,7 @@ struct LSTMSequenceArgIndices {
  */
 struct LSTMSequenceParams {
     LSTMSequenceParams(const ov::op::v5::LSTMSequence& node);
-    LSTMSequenceParams(const CUDAPlugin::nodes::LSTMSequenceOptimized& node);
+    LSTMSequenceParams(const ov::nvidia_gpu::nodes::LSTMSequenceOptimized& node);
 
     static constexpr int lin_layer_count = 4;
 
@@ -57,4 +57,4 @@ struct LSTMSequenceParams {
     void validate(const ov::op::v5::LSTMSequence& node);
 };
 
-}  // namespace CUDAPlugin::RNN::Details
+}  // namespace ov::nvidia_gpu::RNN::Details
diff --git a/modules/cuda_plugin/src/ops/rnn_components/lstm_sequence_cudnn_components.cpp b/modules/nvidia_plugin/src/ops/rnn_components/lstm_sequence_cudnn_components.cpp
similarity index 98%
rename from modules/cuda_plugin/src/ops/rnn_components/lstm_sequence_cudnn_components.cpp
rename to modules/nvidia_plugin/src/ops/rnn_components/lstm_sequence_cudnn_components.cpp
index 15e2a53d9..01323696f 100644
--- a/modules/cuda_plugin/src/ops/rnn_components/lstm_sequence_cudnn_components.cpp
+++ b/modules/nvidia_plugin/src/ops/rnn_components/lstm_sequence_cudnn_components.cpp
@@ -8,12 +8,12 @@
 #include <gsl/gsl_assert>
 #include <ops/converters.hpp>
 
-namespace CUDAPlugin::RNN::Details {
+namespace ov::nvidia_gpu::RNN::Details {
 
 LSTMSequenceParamsCuDnn::LSTMSequenceParamsCuDnn(const LSTMSequenceParams& params)
     : element_type_{convertDataType<cudnnDataType_t>(params.element_type_)},
       element_type_cuda_{convertDataType<cudaDataType_t>(params.element_type_)},
-      element_size_{CUDAPlugin::elementSize(element_type_)},
+      element_size_{ov::nvidia_gpu::elementSize(element_type_)},
       direction_{params.direction_ == LSTMSequenceParams::direction::BIDIRECTIONAL ? CUDNN_BIDIRECTIONAL
                                                                                    : CUDNN_UNIDIRECTIONAL},
       batch_size_{static_cast<int32_t>(params.batch_size_)},
@@ -269,7 +269,7 @@ void LSTMSequenceDescriptorsCuDnn::calculateWeightBuffers(DevPtr buffer) {
     const auto data_type = params_.element_type_;
     const auto input_size = params_.input_size_;
     const auto hidden_size = params_.hidden_size_;
-    const auto element_size = CUDAPlugin::elementSize(params_.element_type_);
+    const auto element_size = ov::nvidia_gpu::elementSize(params_.element_type_);
 
     w_dev_buffers_.clear();
     r_dev_buffers_.clear();
@@ -373,4 +373,4 @@ void LSTMSequenceDescriptorsCuDnn::calculateWeightBuffers(DevPtr buffer) {
             b1_total_bytes >= params_.b_host_buffers_.size_bytes());
 }
 
-}  // namespace CUDAPlugin::RNN::Details
+}  // namespace ov::nvidia_gpu::RNN::Details
diff --git a/modules/cuda_plugin/src/ops/rnn_components/lstm_sequence_cudnn_components.hpp b/modules/nvidia_plugin/src/ops/rnn_components/lstm_sequence_cudnn_components.hpp
similarity index 97%
rename from modules/cuda_plugin/src/ops/rnn_components/lstm_sequence_cudnn_components.hpp
rename to modules/nvidia_plugin/src/ops/rnn_components/lstm_sequence_cudnn_components.hpp
index 4b1c9635e..024d38c97 100644
--- a/modules/cuda_plugin/src/ops/rnn_components/lstm_sequence_cudnn_components.hpp
+++ b/modules/nvidia_plugin/src/ops/rnn_components/lstm_sequence_cudnn_components.hpp
@@ -9,7 +9,7 @@
 
 #include "lstm_sequence_components.hpp"
 
-namespace CUDAPlugin::RNN::Details {
+namespace ov::nvidia_gpu::RNN::Details {
 
 /**
  * @brief Presents LSTM Sequence parameters in a form suitable for cuDNN API.
@@ -101,4 +101,4 @@ class LSTMSequenceDescriptorsCuDnn {
     DevBuffers b2_dev_buffers_;
 };
 
-}  // namespace CUDAPlugin::RNN::Details
+}  // namespace ov::nvidia_gpu::RNN::Details
diff --git a/modules/cuda_plugin/src/ops/rnn_components/rnn_components.cpp b/modules/nvidia_plugin/src/ops/rnn_components/rnn_components.cpp
similarity index 98%
rename from modules/cuda_plugin/src/ops/rnn_components/rnn_components.cpp
rename to modules/nvidia_plugin/src/ops/rnn_components/rnn_components.cpp
index 40527f25e..060832f77 100644
--- a/modules/cuda_plugin/src/ops/rnn_components/rnn_components.cpp
+++ b/modules/nvidia_plugin/src/ops/rnn_components/rnn_components.cpp
@@ -9,7 +9,7 @@
 #include <openvino/op/constant.hpp>
 #include <typeinfo>
 
-namespace CUDAPlugin::RNN::Details {
+namespace ov::nvidia_gpu::RNN::Details {
 
 namespace {
 
@@ -187,4 +187,4 @@ GRUCellParams::GRUCellParams(const ov::op::v3::GRUCell& cell)
     r_host_buffers_ = {r_data_host, r_size_bytes};
     b_host_buffers_ = {b_data_host, b_size_bytes};
 }
-}  // namespace CUDAPlugin::RNN::Details
+}  // namespace ov::nvidia_gpu::RNN::Details
diff --git a/modules/cuda_plugin/src/ops/rnn_components/rnn_components.hpp b/modules/nvidia_plugin/src/ops/rnn_components/rnn_components.hpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/rnn_components/rnn_components.hpp
rename to modules/nvidia_plugin/src/ops/rnn_components/rnn_components.hpp
index 2b584435a..c5f269c1c 100644
--- a/modules/cuda_plugin/src/ops/rnn_components/rnn_components.hpp
+++ b/modules/nvidia_plugin/src/ops/rnn_components/rnn_components.hpp
@@ -8,7 +8,7 @@
 #include <openvino/op/gru_cell.hpp>
 #include <openvino/op/lstm_cell.hpp>
 
-namespace CUDAPlugin::RNN::Details {
+namespace ov::nvidia_gpu::RNN::Details {
 
 /**
  * @brief Defines tensor indices for `ov::op::v4::LSTMCell` node.
@@ -89,4 +89,4 @@ struct GRUCellParams {
     gsl::span<const uint8_t> b_host_buffers_;
 };
 
-}  // namespace CUDAPlugin::RNN::Details
+}  // namespace ov::nvidia_gpu::RNN::Details
diff --git a/modules/cuda_plugin/src/ops/rnn_components/rnn_cudnn_components.cpp b/modules/nvidia_plugin/src/ops/rnn_components/rnn_cudnn_components.cpp
similarity index 99%
rename from modules/cuda_plugin/src/ops/rnn_components/rnn_cudnn_components.cpp
rename to modules/nvidia_plugin/src/ops/rnn_components/rnn_cudnn_components.cpp
index 632ed4c1f..d58f3a340 100644
--- a/modules/cuda_plugin/src/ops/rnn_components/rnn_cudnn_components.cpp
+++ b/modules/nvidia_plugin/src/ops/rnn_components/rnn_cudnn_components.cpp
@@ -10,12 +10,12 @@
 
 #define CUDNN_VERSION_MIN(major, minor, patch) (CUDNN_VERSION >= ((major)*1000 + (minor)*100 + (patch)))
 
-namespace CUDAPlugin::RNN::Details {
+namespace ov::nvidia_gpu::RNN::Details {
 
 LSTMCellParamsCuDnn::LSTMCellParamsCuDnn(const CreationContext& context, const LSTMCellParams& params)
     : lstm_cell_params_(params),
       data_type_{convertDataType<cudnnDataType_t>(lstm_cell_params_.element_type_)},
-      element_size_{CUDAPlugin::elementSize(data_type_)},
+      element_size_{ov::nvidia_gpu::elementSize(data_type_)},
       is_half_supported_(CUDA::isHalfSupported(context.device())) {
     if (inputSize() == 1 && hiddenSize() == 1) {
         throwIEException(
@@ -363,7 +363,7 @@ void LSTMCellDescriptorsCuDnn::calculateWeightBuffers(DevPtr buffer) {
 GRUCellParamsCuDnn::GRUCellParamsCuDnn(const CreationContext& context, const GRUCellParams& params)
     : gru_cell_params_(params),
       data_type_{convertDataType<cudnnDataType_t>(gru_cell_params_.element_type_)},
-      element_size_{CUDAPlugin::elementSize(data_type_)},
+      element_size_{ov::nvidia_gpu::elementSize(data_type_)},
       is_half_supported_(CUDA::isHalfSupported(context.device())) {
     const auto supported_activations = std::vector<std::string>{"sigmoid", "tanh"};
     if (gru_cell_params_.activations_ != supported_activations) {
@@ -704,4 +704,4 @@ void GRUCellDescriptorsCuDnn::calculateWeightBuffers(DevPtr buffer) {
     Ensures(weight_space_size_ >= w_total_bytes + r_total_bytes + b1_total_bytes + b2_total_bytes);
 }
 
-}  // namespace CUDAPlugin::RNN::Details
+}  // namespace ov::nvidia_gpu::RNN::Details
diff --git a/modules/cuda_plugin/src/ops/rnn_components/rnn_cudnn_components.hpp b/modules/nvidia_plugin/src/ops/rnn_components/rnn_cudnn_components.hpp
similarity index 98%
rename from modules/cuda_plugin/src/ops/rnn_components/rnn_cudnn_components.hpp
rename to modules/nvidia_plugin/src/ops/rnn_components/rnn_cudnn_components.hpp
index e35ea7537..b4b289cd4 100644
--- a/modules/cuda_plugin/src/ops/rnn_components/rnn_cudnn_components.hpp
+++ b/modules/nvidia_plugin/src/ops/rnn_components/rnn_cudnn_components.hpp
@@ -9,7 +9,7 @@
 
 #include "rnn_components.hpp"
 
-namespace CUDAPlugin::RNN::Details {
+namespace ov::nvidia_gpu::RNN::Details {
 
 /**
  * @brief Presents LSTM Cell parameters in a form suitable for cuDNN API.
@@ -220,4 +220,4 @@ class GRUCellDescriptorsCuDnn {
     DevBuffers b2_dev_buffers_;
 };
 
-}  // namespace CUDAPlugin::RNN::Details
+}  // namespace ov::nvidia_gpu::RNN::Details
diff --git a/modules/cuda_plugin/src/ops/rnn_components/rnn_sequence_components.cpp b/modules/nvidia_plugin/src/ops/rnn_components/rnn_sequence_components.cpp
similarity index 97%
rename from modules/cuda_plugin/src/ops/rnn_components/rnn_sequence_components.cpp
rename to modules/nvidia_plugin/src/ops/rnn_components/rnn_sequence_components.cpp
index 8d9897fcb..ff2dc5846 100644
--- a/modules/cuda_plugin/src/ops/rnn_components/rnn_sequence_components.cpp
+++ b/modules/nvidia_plugin/src/ops/rnn_components/rnn_sequence_components.cpp
@@ -8,7 +8,7 @@
 
 #include "ngraph/shape.hpp"
 
-namespace CUDAPlugin::RNN::Details {
+namespace ov::nvidia_gpu::RNN::Details {
 
 TransposeTensorAdapterBase::TransposeTensorAdapterBase(cudaDataType_t element_type,
                                                        size_t element_size,
@@ -76,4 +76,4 @@ void TransposeOutputTensorAdapter::execute(const InferenceRequestContext& contex
     TransposeTensorAdapterBase::execute(context, workbuffer_.requiredPtr(src), output.get());
 }
 
-}  // namespace CUDAPlugin::RNN::Details
+}  // namespace ov::nvidia_gpu::RNN::Details
diff --git a/modules/cuda_plugin/src/ops/rnn_components/rnn_sequence_components.hpp b/modules/nvidia_plugin/src/ops/rnn_components/rnn_sequence_components.hpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/rnn_components/rnn_sequence_components.hpp
rename to modules/nvidia_plugin/src/ops/rnn_components/rnn_sequence_components.hpp
index e252bf4f7..7c79b8246 100644
--- a/modules/cuda_plugin/src/ops/rnn_components/rnn_sequence_components.hpp
+++ b/modules/nvidia_plugin/src/ops/rnn_components/rnn_sequence_components.hpp
@@ -8,7 +8,7 @@
 #include <gsl/span>
 #include <ops/components/workbuffer_desc.hpp>
 
-namespace CUDAPlugin::RNN::Details {
+namespace ov::nvidia_gpu::RNN::Details {
 
 /**
  * Base class for `TransposeInputTensorAdapter` and `TransposeOutputTensorAdapter`
@@ -62,4 +62,4 @@ class TransposeOutputTensorAdapter : public TransposeTensorAdapterBase {
                  CUDA::DevicePointer<void*> output) const;
 };
 
-}  // namespace CUDAPlugin::RNN::Details
+}  // namespace ov::nvidia_gpu::RNN::Details
diff --git a/modules/cuda_plugin/src/ops/round.cpp b/modules/nvidia_plugin/src/ops/round.cpp
similarity index 89%
rename from modules/cuda_plugin/src/ops/round.cpp
rename to modules/nvidia_plugin/src/ops/round.cpp
index 7b5b90c90..b0765e124 100644
--- a/modules/cuda_plugin/src/ops/round.cpp
+++ b/modules/nvidia_plugin/src/ops/round.cpp
@@ -10,7 +10,8 @@
 #include "openvino/op/round.hpp"
 #include "round.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 RoundOp::RoundOp(const CreationContext& context,
                  const NodeOp& node,
@@ -33,7 +34,7 @@ RoundOp::RoundOp(const CreationContext& context,
 
     const size_t max_threads_per_block = context.device().props().maxThreadsPerBlock;
     kernel_ =
-        kernel::Round{convertDataType<CUDAPlugin::kernel::Type_t>(element_type), max_threads_per_block, num_elements};
+        kernel::Round{convertDataType<ov::nvidia_gpu::kernel::Type_t>(element_type), max_threads_per_block, num_elements};
 }
 
 void RoundOp::Execute(const InferenceRequestContext& context,
@@ -49,4 +50,5 @@ void RoundOp::Execute(const InferenceRequestContext& context,
 
 OPERATION_REGISTER(RoundOp, Round);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/round.hpp b/modules/nvidia_plugin/src/ops/round.hpp
similarity index 88%
rename from modules/cuda_plugin/src/ops/round.hpp
rename to modules/nvidia_plugin/src/ops/round.hpp
index c4bf0726d..30afe76a6 100644
--- a/modules/cuda_plugin/src/ops/round.hpp
+++ b/modules/nvidia_plugin/src/ops/round.hpp
@@ -8,7 +8,8 @@
 
 #include "openvino/op/round.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class RoundOp : public OperationBase {
 public:
@@ -28,4 +29,5 @@ class RoundOp : public OperationBase {
     std::optional<kernel::Round> kernel_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/scatter_nd_update.cpp b/modules/nvidia_plugin/src/ops/scatter_nd_update.cpp
similarity index 94%
rename from modules/cuda_plugin/src/ops/scatter_nd_update.cpp
rename to modules/nvidia_plugin/src/ops/scatter_nd_update.cpp
index f9e09c05e..a4400f849 100644
--- a/modules/cuda_plugin/src/ops/scatter_nd_update.cpp
+++ b/modules/nvidia_plugin/src/ops/scatter_nd_update.cpp
@@ -12,7 +12,8 @@
 
 #include "converters.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 ScatterNDUpdateOp::ScatterNDUpdateOp(const CreationContext& context,
                                      const ov::Node& node,
@@ -69,8 +70,8 @@ ScatterNDUpdateOp::ScatterNDUpdateOp(const CreationContext& context,
 
     const size_t num_of_threads{num_of_blocks == 1 ? num_of_items : max_block_size};
 
-    kernel_ = kernel::ScatterNDUpdate{convertDataType<CUDAPlugin::kernel::Type_t>(input_type),
-                                      convertDataType<CUDAPlugin::kernel::Type_t>(indices_type),
+    kernel_ = kernel::ScatterNDUpdate{convertDataType<ov::nvidia_gpu::kernel::Type_t>(input_type),
+                                      convertDataType<ov::nvidia_gpu::kernel::Type_t>(indices_type),
                                       indices_last_dim,
                                       num_of_update_elements,
                                       num_of_input_elements,
@@ -117,4 +118,5 @@ void ScatterNDUpdateOp::InitSharedImmutableWorkbuffers(const Buffers& buffers) {
 
 OPERATION_REGISTER(ScatterNDUpdateOp, ScatterNDUpdate);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/scatter_nd_update.hpp b/modules/nvidia_plugin/src/ops/scatter_nd_update.hpp
similarity index 91%
rename from modules/cuda_plugin/src/ops/scatter_nd_update.hpp
rename to modules/nvidia_plugin/src/ops/scatter_nd_update.hpp
index f94b634ed..148289175 100644
--- a/modules/cuda_plugin/src/ops/scatter_nd_update.hpp
+++ b/modules/nvidia_plugin/src/ops/scatter_nd_update.hpp
@@ -7,7 +7,8 @@
 #include "cuda_operation_base.hpp"
 #include "kernels/scatter_nd_update.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class ScatterNDUpdateOp : public OperationBase {
 public:
@@ -28,4 +29,5 @@ class ScatterNDUpdateOp : public OperationBase {
     std::vector<size_t> input_data_dim_pading_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/select.cpp b/modules/nvidia_plugin/src/ops/select.cpp
similarity index 98%
rename from modules/cuda_plugin/src/ops/select.cpp
rename to modules/nvidia_plugin/src/ops/select.cpp
index b1b96e824..4fe3cfc2a 100644
--- a/modules/cuda_plugin/src/ops/select.cpp
+++ b/modules/nvidia_plugin/src/ops/select.cpp
@@ -10,7 +10,8 @@
 #include <openvino/op/constant.hpp>
 #include <openvino/op/select.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 static constexpr auto OUTPUT = 0u;
 static constexpr auto kNumOfDim = 5u;
@@ -116,4 +117,5 @@ void SelectOp::calculateOffsets() {
 }
 
 OPERATION_REGISTER(SelectOp, Select);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/select.hpp b/modules/nvidia_plugin/src/ops/select.hpp
similarity index 94%
rename from modules/cuda_plugin/src/ops/select.hpp
rename to modules/nvidia_plugin/src/ops/select.hpp
index e46f63c45..a446b5eec 100644
--- a/modules/cuda_plugin/src/ops/select.hpp
+++ b/modules/nvidia_plugin/src/ops/select.hpp
@@ -9,7 +9,8 @@
 
 #include "kernels/select.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class SelectOp : public OperationBase {
     enum InputIdx { CONDITION, THEN, ELSE, SIZES };
@@ -50,4 +51,5 @@ class SelectOp : public OperationBase {
     std::optional<kernel::SelectKernelOp> kernel_op_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/sigmoid.cpp b/modules/nvidia_plugin/src/ops/sigmoid.cpp
similarity index 86%
rename from modules/cuda_plugin/src/ops/sigmoid.cpp
rename to modules/nvidia_plugin/src/ops/sigmoid.cpp
index c55d5d075..4149e489a 100644
--- a/modules/cuda_plugin/src/ops/sigmoid.cpp
+++ b/modules/nvidia_plugin/src/ops/sigmoid.cpp
@@ -6,7 +6,8 @@
 
 #include <cuda_operation_registry.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 SigmoidOp::SigmoidOp(const CreationContext& context,
                      const std::shared_ptr<ov::Node>& node,
@@ -16,4 +17,5 @@ SigmoidOp::SigmoidOp(const CreationContext& context,
           std::make_unique<CUDA::SigmoidDescriptor>(), context, *node, move(inputIds), move(outputIds)} {}
 
 OPERATION_REGISTER(SigmoidOp, Sigmoid);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/sigmoid.hpp b/modules/nvidia_plugin/src/ops/sigmoid.hpp
similarity index 83%
rename from modules/cuda_plugin/src/ops/sigmoid.hpp
rename to modules/nvidia_plugin/src/ops/sigmoid.hpp
index 6c3ebf571..cc054b00e 100644
--- a/modules/cuda_plugin/src/ops/sigmoid.hpp
+++ b/modules/nvidia_plugin/src/ops/sigmoid.hpp
@@ -8,7 +8,8 @@
 
 #include "activation_forward_cudnn_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class SigmoidOp : public ActivationForwardCuDnnOpBase {
 public:
@@ -18,4 +19,5 @@ class SigmoidOp : public ActivationForwardCuDnnOpBase {
               IndexCollection&& outputIds);
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/softmax.cpp b/modules/nvidia_plugin/src/ops/softmax.cpp
similarity index 98%
rename from modules/cuda_plugin/src/ops/softmax.cpp
rename to modules/nvidia_plugin/src/ops/softmax.cpp
index 7b6e41abf..0cf7a2fc5 100644
--- a/modules/cuda_plugin/src/ops/softmax.cpp
+++ b/modules/nvidia_plugin/src/ops/softmax.cpp
@@ -14,7 +14,8 @@
 #include "converters.hpp"
 #include "cuda/constant_factory.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 static int take(const ov::Shape& shape, size_t i) noexcept { return i < shape.size() ? shape[i] : 1; }
 
@@ -175,4 +176,5 @@ void SoftmaxOp::Execute(const InferenceRequestContext& context,
 }
 
 OPERATION_REGISTER(SoftmaxOp, Softmax);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/softmax.hpp b/modules/nvidia_plugin/src/ops/softmax.hpp
similarity index 92%
rename from modules/cuda_plugin/src/ops/softmax.hpp
rename to modules/nvidia_plugin/src/ops/softmax.hpp
index 1d87ba497..29b175407 100644
--- a/modules/cuda_plugin/src/ops/softmax.hpp
+++ b/modules/nvidia_plugin/src/ops/softmax.hpp
@@ -13,7 +13,8 @@
 #include <ngraph/type/element_type.hpp>
 #include <openvino/op/softmax.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class SoftmaxOp : public OperationCuDnn {
 public:
@@ -34,4 +35,5 @@ class SoftmaxOp : public OperationCuDnn {
     CUDA::DnnTensorDescriptor tensor_descriptor_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/split.cpp b/modules/nvidia_plugin/src/ops/split.cpp
similarity index 95%
rename from modules/cuda_plugin/src/ops/split.cpp
rename to modules/nvidia_plugin/src/ops/split.cpp
index 1d9023964..43e3f6cd5 100644
--- a/modules/cuda_plugin/src/ops/split.cpp
+++ b/modules/nvidia_plugin/src/ops/split.cpp
@@ -16,7 +16,8 @@
 #include "converters.hpp"
 #include "cuda/runtime.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 SplitOp::SplitOp(const CreationContext& context,
                  const ov::Node& node,
@@ -62,7 +63,7 @@ SplitOp::SplitOp(const CreationContext& context,
                                                                            : (num_split_elements / max_block_size + 1);
     const unsigned threads_per_block = (num_blocks == 1) ? num_split_elements : max_block_size;
 
-    split_kernel_ = kernel::Split{convertDataType<CUDAPlugin::kernel::Type_t>(element_type),
+    split_kernel_ = kernel::Split{convertDataType<ov::nvidia_gpu::kernel::Type_t>(element_type),
                                   num_splits_,
                                   num_split_chunks,
                                   split_step_size,
@@ -89,4 +90,5 @@ void SplitOp::Execute(const InferenceRequestContext& context,
 }
 
 OPERATION_REGISTER(SplitOp, Split);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/split.hpp b/modules/nvidia_plugin/src/ops/split.hpp
similarity index 93%
rename from modules/cuda_plugin/src/ops/split.hpp
rename to modules/nvidia_plugin/src/ops/split.hpp
index b16467151..5949f2679 100644
--- a/modules/cuda_plugin/src/ops/split.hpp
+++ b/modules/nvidia_plugin/src/ops/split.hpp
@@ -14,7 +14,8 @@
 #include <ngraph/type/element_type.hpp>
 #include <openvino/op/softmax.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class SplitOp : public OperationBase {
 public:
@@ -40,4 +41,5 @@ class SplitOp : public OperationBase {
     std::optional<kernel::Split> split_kernel_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/squared_difference.cpp b/modules/nvidia_plugin/src/ops/squared_difference.cpp
similarity index 72%
rename from modules/cuda_plugin/src/ops/squared_difference.cpp
rename to modules/nvidia_plugin/src/ops/squared_difference.cpp
index 2bfe6fc1c..c3dab8a34 100644
--- a/modules/cuda_plugin/src/ops/squared_difference.cpp
+++ b/modules/nvidia_plugin/src/ops/squared_difference.cpp
@@ -6,8 +6,10 @@
 
 #include <cuda_operation_registry.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 OPERATION_REGISTER(SquaredDifferenceOp, SquaredDifference)
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/squared_difference.hpp b/modules/nvidia_plugin/src/ops/squared_difference.hpp
similarity index 82%
rename from modules/cuda_plugin/src/ops/squared_difference.hpp
rename to modules/nvidia_plugin/src/ops/squared_difference.hpp
index 1dca783dc..83bc0d5da 100644
--- a/modules/cuda_plugin/src/ops/squared_difference.hpp
+++ b/modules/nvidia_plugin/src/ops/squared_difference.hpp
@@ -9,11 +9,13 @@
 #include "elementwise_binary.hpp"
 #include "kernels/squared_difference.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class SquaredDifferenceOp : public ElementwiseBinaryOp<ov::op::v0::SquaredDifference, kernel::SquaredDifference> {
 public:
     using ElementwiseBinaryOp::ElementwiseBinaryOp;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/strided_slice.cpp b/modules/nvidia_plugin/src/ops/strided_slice.cpp
similarity index 98%
rename from modules/cuda_plugin/src/ops/strided_slice.cpp
rename to modules/nvidia_plugin/src/ops/strided_slice.cpp
index 5ca87c6be..1b1ad13a4 100644
--- a/modules/cuda_plugin/src/ops/strided_slice.cpp
+++ b/modules/nvidia_plugin/src/ops/strided_slice.cpp
@@ -12,7 +12,8 @@
 #include "ngraph/axis_set.hpp"
 #include "strided_slice.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 namespace {
 ov::AxisSet convert_mask_to_axis_set(const std::vector<int64_t>& mask) {
@@ -126,4 +127,5 @@ std::vector<int64_t> StridedSliceOp::getNodeConstantValues(const ov::Node* node)
 
 OPERATION_REGISTER(StridedSliceOp, StridedSlice);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/strided_slice.hpp b/modules/nvidia_plugin/src/ops/strided_slice.hpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/strided_slice.hpp
rename to modules/nvidia_plugin/src/ops/strided_slice.hpp
index ae1505440..8826a0f80 100644
--- a/modules/cuda_plugin/src/ops/strided_slice.hpp
+++ b/modules/nvidia_plugin/src/ops/strided_slice.hpp
@@ -10,7 +10,8 @@
 #include "kernels/strided_slice.hpp"
 #include "ngraph/slice_plan.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class StridedSliceOp : public OperationBase {
 public:
@@ -63,4 +64,5 @@ class StridedSliceOp : public OperationBase {
     std::optional<kernel::StridedSliceKernelOp> kernel_op_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/subgraph.cpp b/modules/nvidia_plugin/src/ops/subgraph.cpp
similarity index 98%
rename from modules/cuda_plugin/src/ops/subgraph.cpp
rename to modules/nvidia_plugin/src/ops/subgraph.cpp
index 628a4967f..dc122880e 100644
--- a/modules/cuda_plugin/src/ops/subgraph.cpp
+++ b/modules/nvidia_plugin/src/ops/subgraph.cpp
@@ -18,7 +18,8 @@
 #include "parameter.hpp"
 #include "result.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 SubGraph::SubGraph(const CreationContext& context,
                    const SubGraphOp& op,
@@ -144,4 +145,5 @@ void SubGraph::Execute(const InferenceRequestContext& context, Inputs, Outputs,
     }
 }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/subgraph.hpp b/modules/nvidia_plugin/src/ops/subgraph.hpp
similarity index 97%
rename from modules/cuda_plugin/src/ops/subgraph.hpp
rename to modules/nvidia_plugin/src/ops/subgraph.hpp
index 667e2313d..f3c040cf0 100644
--- a/modules/cuda_plugin/src/ops/subgraph.hpp
+++ b/modules/nvidia_plugin/src/ops/subgraph.hpp
@@ -12,7 +12,8 @@
 
 class ExecNetworkTest;
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class SubGraph : public OperationBase {
 public:
@@ -74,4 +75,5 @@ inline SubGraph::~SubGraph() {}
 
 inline const std::vector<OperationBase::Ptr>& SubGraph::getExecSequence() const { return exec_sequence_; }
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/subtract.cpp b/modules/nvidia_plugin/src/ops/subtract.cpp
similarity index 69%
rename from modules/cuda_plugin/src/ops/subtract.cpp
rename to modules/nvidia_plugin/src/ops/subtract.cpp
index 490b99e93..200cd8750 100644
--- a/modules/cuda_plugin/src/ops/subtract.cpp
+++ b/modules/nvidia_plugin/src/ops/subtract.cpp
@@ -6,8 +6,10 @@
 
 #include <cuda_operation_registry.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 OPERATION_REGISTER(SubtractOp, Subtract)
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/subtract.hpp b/modules/nvidia_plugin/src/ops/subtract.hpp
similarity index 80%
rename from modules/cuda_plugin/src/ops/subtract.hpp
rename to modules/nvidia_plugin/src/ops/subtract.hpp
index ff64dc48b..86facf2df 100644
--- a/modules/cuda_plugin/src/ops/subtract.hpp
+++ b/modules/nvidia_plugin/src/ops/subtract.hpp
@@ -9,11 +9,13 @@
 #include "elementwise_binary.hpp"
 #include "kernels/subtract.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class SubtractOp : public ElementwiseBinaryOp<ov::op::v1::Subtract, kernel::Subtract> {
 public:
     using ElementwiseBinaryOp::ElementwiseBinaryOp;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/swish.cpp b/modules/nvidia_plugin/src/ops/swish.cpp
similarity index 92%
rename from modules/cuda_plugin/src/ops/swish.cpp
rename to modules/nvidia_plugin/src/ops/swish.cpp
index 3de1013e5..22e983551 100644
--- a/modules/cuda_plugin/src/ops/swish.cpp
+++ b/modules/nvidia_plugin/src/ops/swish.cpp
@@ -12,7 +12,8 @@
 
 #include "converters.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 namespace {
 double beta_from_constant(const ov::Node& swish_node) {
@@ -54,7 +55,7 @@ SwishOp::SwishOp(const CreationContext& context,
     const size_t max_threads_per_block = context.device().props().maxThreadsPerBlock;
     const double beta = beta_from_constant(node);
     kernel_ = kernel::Swish{
-        convertDataType<CUDAPlugin::kernel::Type_t>(input_element_type), max_threads_per_block, num_elements, beta};
+        convertDataType<ov::nvidia_gpu::kernel::Type_t>(input_element_type), max_threads_per_block, num_elements, beta};
 }
 
 void SwishOp::Execute(const InferenceRequestContext& context,
@@ -69,4 +70,5 @@ void SwishOp::Execute(const InferenceRequestContext& context,
 }
 
 OPERATION_REGISTER(SwishOp, Swish);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/swish.hpp b/modules/nvidia_plugin/src/ops/swish.hpp
similarity index 88%
rename from modules/cuda_plugin/src/ops/swish.hpp
rename to modules/nvidia_plugin/src/ops/swish.hpp
index 7bc276a11..9fcbd7389 100644
--- a/modules/cuda_plugin/src/ops/swish.hpp
+++ b/modules/nvidia_plugin/src/ops/swish.hpp
@@ -9,7 +9,8 @@
 
 #include "kernels/swish.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class SwishOp : public OperationBase {
 public:
@@ -27,4 +28,5 @@ class SwishOp : public OperationBase {
     std::optional<kernel::Swish> kernel_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/tanh.cpp b/modules/nvidia_plugin/src/ops/tanh.cpp
similarity index 87%
rename from modules/cuda_plugin/src/ops/tanh.cpp
rename to modules/nvidia_plugin/src/ops/tanh.cpp
index 714cd8b31..122302e25 100644
--- a/modules/cuda_plugin/src/ops/tanh.cpp
+++ b/modules/nvidia_plugin/src/ops/tanh.cpp
@@ -9,7 +9,8 @@
 #include "converters.hpp"
 #include "cuda/constant_factory.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 TanhOp::TanhOp(const CreationContext& context,
                const std::shared_ptr<ov::Node>& node,
@@ -19,4 +20,5 @@ TanhOp::TanhOp(const CreationContext& context,
           std::make_unique<CUDA::TanhDescriptor>(), context, *node, move(inputIds), move(outputIds)} {}
 
 OPERATION_REGISTER(TanhOp, Tanh);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/tanh.hpp b/modules/nvidia_plugin/src/ops/tanh.hpp
similarity index 81%
rename from modules/cuda_plugin/src/ops/tanh.hpp
rename to modules/nvidia_plugin/src/ops/tanh.hpp
index ce8885497..ae0767c51 100644
--- a/modules/cuda_plugin/src/ops/tanh.hpp
+++ b/modules/nvidia_plugin/src/ops/tanh.hpp
@@ -6,7 +6,8 @@
 
 #include "activation_forward_cudnn_base.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class TanhOp : public ActivationForwardCuDnnOpBase {
 public:
@@ -16,4 +17,5 @@ class TanhOp : public ActivationForwardCuDnnOpBase {
            IndexCollection&& outputIds);
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/tensor_iterator.cpp b/modules/nvidia_plugin/src/ops/tensor_iterator.cpp
similarity index 98%
rename from modules/cuda_plugin/src/ops/tensor_iterator.cpp
rename to modules/nvidia_plugin/src/ops/tensor_iterator.cpp
index ceeb7740c..b27776ba5 100644
--- a/modules/cuda_plugin/src/ops/tensor_iterator.cpp
+++ b/modules/nvidia_plugin/src/ops/tensor_iterator.cpp
@@ -19,7 +19,8 @@
 #include "parameter.hpp"
 #include "result.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 TensorIteratorOp::TensorIteratorOp(const CreationContext& context,
                                    const NodeOp& op,
@@ -111,7 +112,7 @@ TensorIteratorOp::TensorIteratorOp(const CreationContext& context,
         const auto inputShape = inputs_info_[inputIdx].shape_;
         const auto inputType = inputs_info_[inputIdx].type_;
 
-        kernel::Type_t element_type = convertDataType<CUDAPlugin::kernel::Type_t>(inputType);
+        kernel::Type_t element_type = convertDataType<ov::nvidia_gpu::kernel::Type_t>(inputType);
         kernel::Slice::Props props;
         std::copy(inputShape.begin(), inputShape.end(), props.old_shape);
         std::copy(inputShape.begin(), inputShape.end(), props.new_shape);
@@ -310,4 +311,5 @@ void TensorIteratorOp::copyResult(const CUDA::Stream& stream,
 
 OPERATION_REGISTER(TensorIteratorOp, TensorIterator);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/tensor_iterator.hpp b/modules/nvidia_plugin/src/ops/tensor_iterator.hpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/tensor_iterator.hpp
rename to modules/nvidia_plugin/src/ops/tensor_iterator.hpp
index a8bf65e64..66f4f665e 100644
--- a/modules/cuda_plugin/src/ops/tensor_iterator.hpp
+++ b/modules/nvidia_plugin/src/ops/tensor_iterator.hpp
@@ -12,7 +12,8 @@
 
 #include "subgraph.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class TensorIteratorOp : public SubGraph {
 public:
@@ -70,4 +71,5 @@ class TensorIteratorOp : public SubGraph {
     std::unordered_map<uint64_t, uint64_t> results_parameters_map_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/topk.cpp b/modules/nvidia_plugin/src/ops/topk.cpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/topk.cpp
rename to modules/nvidia_plugin/src/ops/topk.cpp
index 51546ae93..f8a414e74 100644
--- a/modules/cuda_plugin/src/ops/topk.cpp
+++ b/modules/nvidia_plugin/src/ops/topk.cpp
@@ -8,7 +8,8 @@
 
 #include "converters.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 namespace {
 
@@ -132,8 +133,8 @@ TopKOp::TopKOp(const CreationContext& context,
 
     const auto& prop = context.device().props();
     const std::size_t max_threads_per_block = prop.maxThreadsPerBlock;
-    kernel_ = kernel::TopK{convertDataType<CUDAPlugin::kernel::Type_t>(element_type),
-                           convertDataType<CUDAPlugin::kernel::Type_t>(index_element_type),
+    kernel_ = kernel::TopK{convertDataType<ov::nvidia_gpu::kernel::Type_t>(element_type),
+                           convertDataType<ov::nvidia_gpu::kernel::Type_t>(index_element_type),
                            convertComputeType(topKOp.get_mode()),
                            convertSortType(topKOp.get_sort_type()),
                            num_input_element,
@@ -186,4 +187,5 @@ void TopKOp::InitSharedImmutableWorkbuffers(const Buffers& buffers) {
 WorkbufferRequest TopKOp::GetWorkBufferRequest() const { return {{sizeof(kernel_param_)}, {workspace_size_}}; }
 
 OPERATION_REGISTER(TopKOp, TopK);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/topk.hpp b/modules/nvidia_plugin/src/ops/topk.hpp
similarity index 92%
rename from modules/cuda_plugin/src/ops/topk.hpp
rename to modules/nvidia_plugin/src/ops/topk.hpp
index 5bbbe2d2d..8b03c5a2a 100644
--- a/modules/cuda_plugin/src/ops/topk.hpp
+++ b/modules/nvidia_plugin/src/ops/topk.hpp
@@ -13,7 +13,8 @@
 #include <ngraph/shape.hpp>
 #include <ngraph/type/element_type.hpp>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class TopKOp : public OperationBase {
 public:
@@ -35,4 +36,5 @@ class TopKOp : public OperationBase {
     std::optional<kernel::TopK> kernel_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/transpose.cpp b/modules/nvidia_plugin/src/ops/transpose.cpp
similarity index 99%
rename from modules/cuda_plugin/src/ops/transpose.cpp
rename to modules/nvidia_plugin/src/ops/transpose.cpp
index 2aed2fef8..a97c3234a 100644
--- a/modules/cuda_plugin/src/ops/transpose.cpp
+++ b/modules/nvidia_plugin/src/ops/transpose.cpp
@@ -17,7 +17,8 @@
 
 using namespace std::string_literals;
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 TransposeOp::TransposeOp(const CreationContext& context,
                          const std::shared_ptr<ov::Node>& node,
@@ -199,4 +200,5 @@ inline std::vector<int> TransposeOp::downloadPermutationVector(const InferenceRe
 
 OPERATION_REGISTER(TransposeOp, Transpose);
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/transpose.hpp b/modules/nvidia_plugin/src/ops/transpose.hpp
similarity index 96%
rename from modules/cuda_plugin/src/ops/transpose.hpp
rename to modules/nvidia_plugin/src/ops/transpose.hpp
index b084a3635..2b29c77d0 100644
--- a/modules/cuda_plugin/src/ops/transpose.hpp
+++ b/modules/nvidia_plugin/src/ops/transpose.hpp
@@ -10,7 +10,8 @@
 #include <unordered_map>
 #include <vector>
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class TransposeOp : public OperationCuTensor {
 public:
@@ -64,4 +65,5 @@ class TransposeOp : public OperationCuTensor {
     ov::element::Type_t permutationElementsType_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/variadic_split.cpp b/modules/nvidia_plugin/src/ops/variadic_split.cpp
similarity index 98%
rename from modules/cuda_plugin/src/ops/variadic_split.cpp
rename to modules/nvidia_plugin/src/ops/variadic_split.cpp
index e20b9101b..86d61e7ec 100644
--- a/modules/cuda_plugin/src/ops/variadic_split.cpp
+++ b/modules/nvidia_plugin/src/ops/variadic_split.cpp
@@ -18,7 +18,8 @@
 #include "cuda/runtime.hpp"
 #include "cuda_op_buffers_extractor.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 namespace {
 
@@ -112,7 +113,7 @@ VariadicSplitOp::VariadicSplitOp(const CreationContext& context,
                                                                            : (num_split_elements / max_block_size + 1);
     const unsigned threads_per_block = (num_blocks == 1) ? num_split_elements : max_block_size;
 
-    variadic_split_kernel_ = kernel::VariadicSplit{convertDataType<CUDAPlugin::kernel::Type_t>(element_type),
+    variadic_split_kernel_ = kernel::VariadicSplit{convertDataType<ov::nvidia_gpu::kernel::Type_t>(element_type),
                                                    num_all_chunks,
                                                    axis_split_step_size,
                                                    orig_axis_size,
@@ -196,4 +197,5 @@ void VariadicSplitOp::Execute(const InferenceRequestContext& context,
 }
 
 OPERATION_REGISTER(VariadicSplitOp, VariadicSplit);
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/ops/variadic_split.hpp b/modules/nvidia_plugin/src/ops/variadic_split.hpp
similarity index 95%
rename from modules/cuda_plugin/src/ops/variadic_split.hpp
rename to modules/nvidia_plugin/src/ops/variadic_split.hpp
index 18710875a..3cb1fce47 100644
--- a/modules/cuda_plugin/src/ops/variadic_split.hpp
+++ b/modules/nvidia_plugin/src/ops/variadic_split.hpp
@@ -16,7 +16,8 @@
 
 #include "kernels/variadic_split.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class VariadicSplitOp : public OperationBase {
 public:
@@ -51,4 +52,5 @@ class VariadicSplitOp : public OperationBase {
     std::optional<kernel::VariadicSplit> variadic_split_kernel_;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/transformer/bidirectional_lstm_sequence_composition.cpp b/modules/nvidia_plugin/src/transformer/bidirectional_lstm_sequence_composition.cpp
similarity index 97%
rename from modules/cuda_plugin/src/transformer/bidirectional_lstm_sequence_composition.cpp
rename to modules/nvidia_plugin/src/transformer/bidirectional_lstm_sequence_composition.cpp
index 58295ab04..5815c09ba 100644
--- a/modules/cuda_plugin/src/transformer/bidirectional_lstm_sequence_composition.cpp
+++ b/modules/nvidia_plugin/src/transformer/bidirectional_lstm_sequence_composition.cpp
@@ -43,7 +43,7 @@ Node* findConcat(const Output<Node>& node, ov::op::v1::Transpose*& transpose) {
         }
         if (dynamic_cast<ov::op::v0::Concat*>(in.get_node())) {
             return in.get_node();
-        } else if (dynamic_cast<CUDAPlugin::nodes::ConcatOptimized*>(in.get_node())) {
+        } else if (dynamic_cast<ov::nvidia_gpu::nodes::ConcatOptimized*>(in.get_node())) {
             return in.get_node();
         }
         for (const auto& out : in.get_node()->outputs()) {
@@ -81,7 +81,7 @@ auto transposePerm(const Node* tran) {
         auto perm_const = dynamic_cast<ov::op::v0::Constant*>(tran->get_input_source_output(1).get_node());
         const int64_t* ptr = reinterpret_cast<const int64_t*>(perm_const->get_data_ptr());
         auto span = gsl::make_span(
-            ptr, CUDAPlugin::OperationBuffersExtractor::GetTensorByteSize(perm_const->output(0)) / sizeof(int64_t));
+            ptr, ov::nvidia_gpu::OperationBuffersExtractor::GetTensorByteSize(perm_const->output(0)) / sizeof(int64_t));
         return std::vector<int64_t>{span.begin(), span.end()};
     }
     return std::vector<int64_t>{};
@@ -233,7 +233,7 @@ bool bidirectional_lstm_sequence_composition(ngraph::pattern::Matcher& m) {
         lstmSequenceOutputReplacer(co_replacement, co);
 
         auto& rt_info = lstm_sequence_bidirectional->get_rt_info();
-        rt_info[CUDAPlugin::RtInfo::CUDA_FUSED_NAMES_MAPPING] = original_names_mapping;
+        rt_info[ov::nvidia_gpu::RtInfo::CUDA_FUSED_NAMES_MAPPING] = original_names_mapping;
     }
 
     return true;
@@ -258,7 +258,7 @@ bool bidirectional_lstm_sequence_cudnn_optimized(ngraph::pattern::Matcher& m) {
     //   cell/hidden in  - [batch_size, num_directions, hidden_size]
     //   cell/hidden out - [num_directions, batch_size, hidden_size]
 
-    using MajorFormat = CUDAPlugin::nodes::LSTMSequenceOptimized::MajorFormat;
+    using MajorFormat = ov::nvidia_gpu::nodes::LSTMSequenceOptimized::MajorFormat;
 
     auto lstm_sequence_bidirectional = std::dynamic_pointer_cast<ov::op::v5::LSTMSequence>(m.get_match_root());
     if (!lstm_sequence_bidirectional ||
@@ -301,7 +301,7 @@ bool bidirectional_lstm_sequence_cudnn_optimized(ngraph::pattern::Matcher& m) {
         return false;
     }
 
-    auto new_lstm_sequence_bidirectional = std::make_shared<CUDAPlugin::nodes::LSTMSequenceOptimized>(
+    auto new_lstm_sequence_bidirectional = std::make_shared<ov::nvidia_gpu::nodes::LSTMSequenceOptimized>(
         x_transpose ? x_transpose : lstm_sequence_bidirectional->get_input_source_output(0),
         lstm_sequence_bidirectional->get_input_source_output(1),
         lstm_sequence_bidirectional->get_input_source_output(2),
@@ -366,7 +366,7 @@ bool bidirectional_lstm_sequence_cudnn_optimized(ngraph::pattern::Matcher& m) {
     lstmSequenceOutputReplacer(co_replacement, co);
 
     auto& rt_info = new_lstm_sequence_bidirectional->get_rt_info();
-    rt_info[CUDAPlugin::RtInfo::CUDA_FUSED_NAMES_MAPPING] = original_names_mapping;
+    rt_info[ov::nvidia_gpu::RtInfo::CUDA_FUSED_NAMES_MAPPING] = original_names_mapping;
 
     return true;
 }
diff --git a/modules/cuda_plugin/src/transformer/bidirectional_lstm_sequence_composition.hpp b/modules/nvidia_plugin/src/transformer/bidirectional_lstm_sequence_composition.hpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/bidirectional_lstm_sequence_composition.hpp
rename to modules/nvidia_plugin/src/transformer/bidirectional_lstm_sequence_composition.hpp
diff --git a/modules/cuda_plugin/src/transformer/concat_transformation.cpp b/modules/nvidia_plugin/src/transformer/concat_transformation.cpp
similarity index 98%
rename from modules/cuda_plugin/src/transformer/concat_transformation.cpp
rename to modules/nvidia_plugin/src/transformer/concat_transformation.cpp
index a458a0fd2..1d5d88e76 100644
--- a/modules/cuda_plugin/src/transformer/concat_transformation.cpp
+++ b/modules/nvidia_plugin/src/transformer/concat_transformation.cpp
@@ -17,7 +17,7 @@ namespace ngraph::pass {
 NGRAPH_RTTI_DEFINITION(ngraph::pass::ConcatTransformation, "ConcatTransformation", 0);
 
 bool change_concat_to_concat_optimized(pattern::Matcher& m) {
-    using CUDAPlugin::nodes::ConcatOptimized;
+    using ov::nvidia_gpu::nodes::ConcatOptimized;
 
     auto concat = std::dynamic_pointer_cast<ov::op::v0::Concat>(m.get_match_root());
     for (auto& in : concat->inputs()) {
diff --git a/modules/cuda_plugin/src/transformer/concat_transformation.hpp b/modules/nvidia_plugin/src/transformer/concat_transformation.hpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/concat_transformation.hpp
rename to modules/nvidia_plugin/src/transformer/concat_transformation.hpp
diff --git a/modules/cuda_plugin/src/transformer/convolution_asym_padding_transformation.cpp b/modules/nvidia_plugin/src/transformer/convolution_asym_padding_transformation.cpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/convolution_asym_padding_transformation.cpp
rename to modules/nvidia_plugin/src/transformer/convolution_asym_padding_transformation.cpp
diff --git a/modules/cuda_plugin/src/transformer/convolution_asym_padding_transformation.hpp b/modules/nvidia_plugin/src/transformer/convolution_asym_padding_transformation.hpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/convolution_asym_padding_transformation.hpp
rename to modules/nvidia_plugin/src/transformer/convolution_asym_padding_transformation.hpp
diff --git a/modules/cuda_plugin/src/transformer/cuda_fullyconnected_transformation.cpp b/modules/nvidia_plugin/src/transformer/cuda_fullyconnected_transformation.cpp
similarity index 85%
rename from modules/cuda_plugin/src/transformer/cuda_fullyconnected_transformation.cpp
rename to modules/nvidia_plugin/src/transformer/cuda_fullyconnected_transformation.cpp
index b4a476862..a4edd1965 100644
--- a/modules/cuda_plugin/src/transformer/cuda_fullyconnected_transformation.cpp
+++ b/modules/nvidia_plugin/src/transformer/cuda_fullyconnected_transformation.cpp
@@ -42,14 +42,14 @@ bool fuse_matmul_and_add(ngraph::pattern::Matcher &m) {
     auto matrixAShape = matMulNode->get_input_shape(0);
     auto matrixBShape = matMulNode->get_input_shape(1);
     const auto matrixShape = matMulNode->get_output_shape(0);
-    CUDAPlugin::MatMulOp::BroadcastToMatrix(matrixAShape);
-    CUDAPlugin::MatMulOp::BroadcastToMatrix(matrixBShape);
-    const auto matMulBatch = std::max(CUDAPlugin::MatMulOp::GetMatrixNumBatches(matrixAShape),
-                                      CUDAPlugin::MatMulOp::GetMatrixNumBatches(matrixBShape));
+    ov::nvidia_gpu::MatMulOp::BroadcastToMatrix(matrixAShape);
+    ov::nvidia_gpu::MatMulOp::BroadcastToMatrix(matrixBShape);
+    const auto matMulBatch = std::max(ov::nvidia_gpu::MatMulOp::GetMatrixNumBatches(matrixAShape),
+                                      ov::nvidia_gpu::MatMulOp::GetMatrixNumBatches(matrixBShape));
 
     auto constShape = constantNode->get_output_shape(0);
-    CUDAPlugin::MatMulOp::BroadcastToMatrix(constShape);
-    const auto constBatch = CUDAPlugin::MatMulOp::GetMatrixNumBatches(constShape);
+    ov::nvidia_gpu::MatMulOp::BroadcastToMatrix(constShape);
+    const auto constBatch = ov::nvidia_gpu::MatMulOp::GetMatrixNumBatches(constShape);
     const auto constShapeSize = ov::shape_size(constShape);
     const auto matrixShapeSize = ov::shape_size(matrixShape);
     const auto numAutoConstBatch = matrixShapeSize / constShapeSize;
@@ -59,7 +59,7 @@ bool fuse_matmul_and_add(ngraph::pattern::Matcher &m) {
     }
 
     const auto fullyConnectedNode =
-        std::make_shared<CUDAPlugin::nodes::FullyConnected>(matMulNode->get_input_node_shared_ptr(0),
+        std::make_shared<ov::nvidia_gpu::nodes::FullyConnected>(matMulNode->get_input_node_shared_ptr(0),
                                                             matMulNode->get_input_node_shared_ptr(1),
                                                             constantNode,
                                                             matMulNode->get_transpose_a(),
diff --git a/modules/cuda_plugin/src/transformer/cuda_fullyconnected_transformation.hpp b/modules/nvidia_plugin/src/transformer/cuda_fullyconnected_transformation.hpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/cuda_fullyconnected_transformation.hpp
rename to modules/nvidia_plugin/src/transformer/cuda_fullyconnected_transformation.hpp
diff --git a/modules/cuda_plugin/src/transformer/cuda_function_transformation.cpp b/modules/nvidia_plugin/src/transformer/cuda_function_transformation.cpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/cuda_function_transformation.cpp
rename to modules/nvidia_plugin/src/transformer/cuda_function_transformation.cpp
diff --git a/modules/cuda_plugin/src/transformer/cuda_function_transformation.hpp b/modules/nvidia_plugin/src/transformer/cuda_function_transformation.hpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/cuda_function_transformation.hpp
rename to modules/nvidia_plugin/src/transformer/cuda_function_transformation.hpp
diff --git a/modules/cuda_plugin/src/transformer/cuda_graph_transformer.cpp b/modules/nvidia_plugin/src/transformer/cuda_graph_transformer.cpp
similarity index 96%
rename from modules/cuda_plugin/src/transformer/cuda_graph_transformer.cpp
rename to modules/nvidia_plugin/src/transformer/cuda_graph_transformer.cpp
index 1dfb8b839..4da0a5abc 100644
--- a/modules/cuda_plugin/src/transformer/cuda_graph_transformer.cpp
+++ b/modules/nvidia_plugin/src/transformer/cuda_graph_transformer.cpp
@@ -33,7 +33,7 @@
 #include "transformations/op_conversions/convert_subtract.hpp"
 #include "transformations/op_conversions/mvn6_decomposition.hpp"
 
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 
 std::shared_ptr<ngraph::Function> GraphTransformer::export_transform(
     const CUDA::Device& device,
@@ -55,7 +55,7 @@ std::shared_ptr<ngraph::Function> GraphTransformer::export_transform(
     // However this is not valid for the case with broadcasting of very large shapes (e.g. {{1024, 1024, 384, 2}, {1}})
     // on CUDA, for them decomposed cuDNN versions are faster.
     // TODO: Consider as possible optimisations: enabling these decompositions for large shapes, creating cuDNN versions
-    // for these operations, implementing in-place logic in CUDA plugin for these operations.
+    // for these operations, implementing in-place logic in NVIDIA GPU plugin for these operations.
     passConfig->disable<ngraph::pass::ConvertSubtract>();
     passConfig->disable<ngraph::pass::ConvertDivide>();
     passConfig->disable<ngraph::pass::ConvertMod>();
@@ -67,7 +67,7 @@ std::shared_ptr<ngraph::Function> GraphTransformer::export_transform(
     manager.register_pass<ngraph::pass::AddPreprocessing>(inputInfoMap);
     manager.register_pass<ngraph::pass::CommonOptimizations>();
     // NOTE: G-API supports only FP32 networks for pre-processing
-    //       CUDAPlugin supports FP16 networks, but this transformation is needed for export
+    //       nvidia_gpu supports FP16 networks, but this transformation is needed for export
     bool needF16toF32 = false;
     for (const auto& param : function->get_parameters()) {
         if (param->get_element_type() == ngraph::element::f16 &&
@@ -109,7 +109,7 @@ std::shared_ptr<ngraph::Function> GraphTransformer::transform(const CUDA::Device
     // However this is not valid for the case with broadcasting of very large shapes (e.g. {{1024, 1024, 384, 2}, {1}})
     // on CUDA, for them decomposed cuDNN versions are faster.
     // TODO: Consider as possible optimisations: enabling these decompositions for large shapes, creating cuDNN versions
-    // for these operations, implementing in-place logic in CUDA plugin for these operations.
+    // for these operations, implementing in-place logic in NVIDIA GPU plugin for these operations.
     passConfig->disable<ngraph::pass::ConvertSubtract>();
     passConfig->disable<ngraph::pass::ConvertDivide>();
     passConfig->disable<ngraph::pass::ConvertMod>();
diff --git a/modules/cuda_plugin/src/transformer/cuda_graph_transformer.hpp b/modules/nvidia_plugin/src/transformer/cuda_graph_transformer.hpp
similarity index 95%
rename from modules/cuda_plugin/src/transformer/cuda_graph_transformer.hpp
rename to modules/nvidia_plugin/src/transformer/cuda_graph_transformer.hpp
index 98cf334e1..3907a492f 100644
--- a/modules/cuda_plugin/src/transformer/cuda_graph_transformer.hpp
+++ b/modules/nvidia_plugin/src/transformer/cuda_graph_transformer.hpp
@@ -10,7 +10,8 @@
 #include "cpp/ie_cnn_network.h"
 #include "cuda_config.hpp"
 
-namespace CUDAPlugin {
+namespace ov {
+namespace nvidia_gpu {
 
 class GraphTransformer {
 public:
@@ -39,4 +40,5 @@ class GraphTransformer {
                                                 const Configuration& config) const;
 };
 
-}  // namespace CUDAPlugin
+}  // namespace nvidia_gpu
+}  // namespace ov
diff --git a/modules/cuda_plugin/src/transformer/cuda_rt_info.hpp b/modules/nvidia_plugin/src/transformer/cuda_rt_info.hpp
similarity index 84%
rename from modules/cuda_plugin/src/transformer/cuda_rt_info.hpp
rename to modules/nvidia_plugin/src/transformer/cuda_rt_info.hpp
index 9db4857f1..b2939d8a1 100644
--- a/modules/cuda_plugin/src/transformer/cuda_rt_info.hpp
+++ b/modules/nvidia_plugin/src/transformer/cuda_rt_info.hpp
@@ -4,7 +4,7 @@
 
 #pragma once
 
-namespace CUDAPlugin::RtInfo {
+namespace ov::nvidia_gpu::RtInfo {
 
 static constexpr char CUDA_FUSED_NAMES_MAPPING[] = "CUDA_FUSED_NAMES_MAPPING";
 
diff --git a/modules/cuda_plugin/src/transformer/fuse_conv_biasadd_activation.cpp b/modules/nvidia_plugin/src/transformer/fuse_conv_biasadd_activation.cpp
similarity index 98%
rename from modules/cuda_plugin/src/transformer/fuse_conv_biasadd_activation.cpp
rename to modules/nvidia_plugin/src/transformer/fuse_conv_biasadd_activation.cpp
index 57034e901..99ec43546 100644
--- a/modules/cuda_plugin/src/transformer/fuse_conv_biasadd_activation.cpp
+++ b/modules/nvidia_plugin/src/transformer/fuse_conv_biasadd_activation.cpp
@@ -25,11 +25,11 @@
 #include "nodes/fused_convolution.hpp"
 #include "nodes/fused_convolution_backprop_data.hpp"
 
-using CUDAPlugin::nodes::FusedConvolution;
-using CUDAPlugin::nodes::FusedGroupConvolution;
+using ov::nvidia_gpu::nodes::FusedConvolution;
+using ov::nvidia_gpu::nodes::FusedGroupConvolution;
 
-using ActivationMode = CUDAPlugin::nodes::ActivationMode;
-using FusedConvBackpropData = CUDAPlugin::nodes::FusedConvBackpropData;
+using ActivationMode = ov::nvidia_gpu::nodes::ActivationMode;
+using FusedConvBackpropData = ov::nvidia_gpu::nodes::FusedConvBackpropData;
 
 template <class A, class B>
 std::pair<std::shared_ptr<A>, std::shared_ptr<B>> parse_eltwise_inputs(std::shared_ptr<ov::Node> node) {
diff --git a/modules/cuda_plugin/src/transformer/fuse_conv_biasadd_activation.hpp b/modules/nvidia_plugin/src/transformer/fuse_conv_biasadd_activation.hpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/fuse_conv_biasadd_activation.hpp
rename to modules/nvidia_plugin/src/transformer/fuse_conv_biasadd_activation.hpp
diff --git a/modules/cuda_plugin/src/transformer/matmul_transformations.cpp b/modules/nvidia_plugin/src/transformer/matmul_transformations.cpp
similarity index 95%
rename from modules/cuda_plugin/src/transformer/matmul_transformations.cpp
rename to modules/nvidia_plugin/src/transformer/matmul_transformations.cpp
index f438a4133..fec75387c 100644
--- a/modules/cuda_plugin/src/transformer/matmul_transformations.cpp
+++ b/modules/nvidia_plugin/src/transformer/matmul_transformations.cpp
@@ -23,9 +23,9 @@ bool verify_permutation(std::shared_ptr<ov::op::v0::Constant> permConstant) {
     const auto perm3D = std::vector<T>{0, 2, 1};
     const auto perm4D = std::vector<T>{0, 1, 3, 2};
     const auto perm5D = std::vector<T>{0, 1, 2, 4, 3};
-    auto span =
-        gsl::make_span(static_cast<const T *>(permConstant->get_data_ptr()),
-                       CUDAPlugin::OperationBuffersExtractor::GetTensorByteSize(permConstant->output(0)) / sizeof(T));
+    auto span = gsl::make_span(
+        static_cast<const T *>(permConstant->get_data_ptr()),
+        ov::nvidia_gpu::OperationBuffersExtractor::GetTensorByteSize(permConstant->output(0)) / sizeof(T));
     switch (span.size()) {
         case 2:
             return span == gsl::make_span(perm2D);
diff --git a/modules/cuda_plugin/src/transformer/matmul_transformations.hpp b/modules/nvidia_plugin/src/transformer/matmul_transformations.hpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/matmul_transformations.hpp
rename to modules/nvidia_plugin/src/transformer/matmul_transformations.hpp
diff --git a/modules/cuda_plugin/src/transformer/nodes/concat_optimized.hpp b/modules/nvidia_plugin/src/transformer/nodes/concat_optimized.hpp
similarity index 88%
rename from modules/cuda_plugin/src/transformer/nodes/concat_optimized.hpp
rename to modules/nvidia_plugin/src/transformer/nodes/concat_optimized.hpp
index 10370c808..3238da179 100644
--- a/modules/cuda_plugin/src/transformer/nodes/concat_optimized.hpp
+++ b/modules/nvidia_plugin/src/transformer/nodes/concat_optimized.hpp
@@ -6,7 +6,7 @@
 
 #include <openvino/op/concat.hpp>
 
-namespace CUDAPlugin::nodes {
+namespace ov::nvidia_gpu::nodes {
 
 class ConcatOptimized : public ov::op::v0::Concat {
 public:
@@ -19,4 +19,4 @@ class ConcatOptimized : public ov::op::v0::Concat {
         return std::make_shared<ConcatOptimized>(new_args, m_axis);
     }
 };
-}  // namespace CUDAPlugin::nodes
+}  // namespace ov::nvidia_gpu::nodes
diff --git a/modules/cuda_plugin/src/transformer/nodes/cuda_plugin_custom_node_types.hpp b/modules/nvidia_plugin/src/transformer/nodes/cuda_plugin_custom_node_types.hpp
similarity index 80%
rename from modules/cuda_plugin/src/transformer/nodes/cuda_plugin_custom_node_types.hpp
rename to modules/nvidia_plugin/src/transformer/nodes/cuda_plugin_custom_node_types.hpp
index a7f17804f..c3b361424 100644
--- a/modules/cuda_plugin/src/transformer/nodes/cuda_plugin_custom_node_types.hpp
+++ b/modules/nvidia_plugin/src/transformer/nodes/cuda_plugin_custom_node_types.hpp
@@ -4,7 +4,7 @@
 
 #pragma once
 
-namespace CUDAPlugin::nodes {
+namespace ov::nvidia_gpu::nodes {
 
 /**
  * @brief Activation modes for fused convolutions.
@@ -13,4 +13,4 @@ namespace CUDAPlugin::nodes {
  */
 enum class ActivationMode { SIGMOID, RELU, TANH, CLIPPED_RELU, ELU, SWISH, NO_ACTIVATION };
 
-}  // namespace CUDAPlugin::nodes
+}  // namespace ov::nvidia_gpu::nodes
diff --git a/modules/cuda_plugin/src/transformer/nodes/fully_connected.cpp b/modules/nvidia_plugin/src/transformer/nodes/fully_connected.cpp
similarity index 99%
rename from modules/cuda_plugin/src/transformer/nodes/fully_connected.cpp
rename to modules/nvidia_plugin/src/transformer/nodes/fully_connected.cpp
index 8b86c27a2..70c7aaa04 100644
--- a/modules/cuda_plugin/src/transformer/nodes/fully_connected.cpp
+++ b/modules/nvidia_plugin/src/transformer/nodes/fully_connected.cpp
@@ -4,7 +4,7 @@
 
 #include "fully_connected.hpp"
 
-namespace CUDAPlugin::nodes {
+namespace ov::nvidia_gpu::nodes {
 
 namespace matmul {
 
@@ -207,4 +207,4 @@ ov::PartialShape validate_matmul_output_shape(const ov::PartialShape& arg0_shape
 
 }  // namespace matmul
 
-}  // namespace CUDAPlugin::nodes
+}  // namespace ov::nvidia_gpu::nodes
diff --git a/modules/cuda_plugin/src/transformer/nodes/fully_connected.hpp b/modules/nvidia_plugin/src/transformer/nodes/fully_connected.hpp
similarity index 93%
rename from modules/cuda_plugin/src/transformer/nodes/fully_connected.hpp
rename to modules/nvidia_plugin/src/transformer/nodes/fully_connected.hpp
index 2eaf50925..33b4f55e3 100644
--- a/modules/cuda_plugin/src/transformer/nodes/fully_connected.hpp
+++ b/modules/nvidia_plugin/src/transformer/nodes/fully_connected.hpp
@@ -8,7 +8,7 @@
 #include <ngraph/ops.hpp>
 #include <ngraph/type/element_type.hpp>
 
-namespace CUDAPlugin::nodes {
+namespace ov::nvidia_gpu::nodes {
 
 class FullyConnected : public ov::op::Op {
 public:
@@ -35,4 +35,4 @@ class FullyConnected : public ov::op::Op {
     bool m_transpose_b;
 };
 
-}  // namespace CUDAPlugin::nodes
+}  // namespace ov::nvidia_gpu::nodes
diff --git a/modules/cuda_plugin/src/transformer/nodes/fused_convolution.hpp b/modules/nvidia_plugin/src/transformer/nodes/fused_convolution.hpp
similarity index 99%
rename from modules/cuda_plugin/src/transformer/nodes/fused_convolution.hpp
rename to modules/nvidia_plugin/src/transformer/nodes/fused_convolution.hpp
index 5fb91aa7f..44ac8a1c4 100644
--- a/modules/cuda_plugin/src/transformer/nodes/fused_convolution.hpp
+++ b/modules/nvidia_plugin/src/transformer/nodes/fused_convolution.hpp
@@ -14,7 +14,7 @@
 
 #include "cuda_plugin_custom_node_types.hpp"
 
-namespace CUDAPlugin::nodes {
+namespace ov::nvidia_gpu::nodes {
 
 namespace {
 
@@ -147,4 +147,4 @@ class FusedGroupConvolution : public BasicFusedConvolution<ov::op::v1::GroupConv
     using BasicFusedConvolution::BasicFusedConvolution;
 };
 
-}  // namespace CUDAPlugin::nodes
+}  // namespace ov::nvidia_gpu::nodes
diff --git a/modules/cuda_plugin/src/transformer/nodes/fused_convolution_backprop_data.cpp b/modules/nvidia_plugin/src/transformer/nodes/fused_convolution_backprop_data.cpp
similarity index 99%
rename from modules/cuda_plugin/src/transformer/nodes/fused_convolution_backprop_data.cpp
rename to modules/nvidia_plugin/src/transformer/nodes/fused_convolution_backprop_data.cpp
index 890568096..e3b642339 100644
--- a/modules/cuda_plugin/src/transformer/nodes/fused_convolution_backprop_data.cpp
+++ b/modules/nvidia_plugin/src/transformer/nodes/fused_convolution_backprop_data.cpp
@@ -7,7 +7,7 @@
 #include <gsl/gsl_assert>
 #include <ngraph/validation_util.hpp>
 
-namespace CUDAPlugin::nodes {
+namespace ov::nvidia_gpu::nodes {
 
 FusedConvBackpropData::FusedConvBackpropData(const ov::Output<Node>& data_batch,
                                              const ov::Output<Node>& filters,
@@ -264,4 +264,4 @@ void FusedConvBackpropData::validate_and_infer_types() {
     Expects(element_type == add_type_);
 }
 
-}  // namespace CUDAPlugin::nodes
+}  // namespace ov::nvidia_gpu::nodes
diff --git a/modules/cuda_plugin/src/transformer/nodes/fused_convolution_backprop_data.hpp b/modules/nvidia_plugin/src/transformer/nodes/fused_convolution_backprop_data.hpp
similarity index 98%
rename from modules/cuda_plugin/src/transformer/nodes/fused_convolution_backprop_data.hpp
rename to modules/nvidia_plugin/src/transformer/nodes/fused_convolution_backprop_data.hpp
index 7c9e23df4..2f634f8a8 100644
--- a/modules/cuda_plugin/src/transformer/nodes/fused_convolution_backprop_data.hpp
+++ b/modules/nvidia_plugin/src/transformer/nodes/fused_convolution_backprop_data.hpp
@@ -13,7 +13,7 @@
 #include "ngraph/ngraph_visibility.hpp"
 #include "ngraph/type.hpp"
 
-namespace CUDAPlugin::nodes {
+namespace ov::nvidia_gpu::nodes {
 
 // TODO: Try to use BasicFusedConvolution or derive from ov::op::v1::ConvolutionBackpropData
 class FusedConvBackpropData : public ov::op::Op {
@@ -76,4 +76,4 @@ class FusedConvBackpropData : public ov::op::Op {
     ov::element::Type add_type_;
 };
 
-}  // namespace CUDAPlugin::nodes
+}  // namespace ov::nvidia_gpu::nodes
diff --git a/modules/cuda_plugin/src/transformer/nodes/lstm_sequence_optimized.cpp b/modules/nvidia_plugin/src/transformer/nodes/lstm_sequence_optimized.cpp
similarity index 99%
rename from modules/cuda_plugin/src/transformer/nodes/lstm_sequence_optimized.cpp
rename to modules/nvidia_plugin/src/transformer/nodes/lstm_sequence_optimized.cpp
index d413900fe..378a41a7f 100644
--- a/modules/cuda_plugin/src/transformer/nodes/lstm_sequence_optimized.cpp
+++ b/modules/nvidia_plugin/src/transformer/nodes/lstm_sequence_optimized.cpp
@@ -7,7 +7,7 @@
 #include <gsl/gsl_assert>
 #include <ngraph/op/util/recurrent_sequence.hpp>
 
-namespace CUDAPlugin::nodes {
+namespace ov::nvidia_gpu::nodes {
 
 LSTMSequenceOptimized::LSTMSequenceOptimized(const ov::Output<Node>& X,
                                              const ov::Output<Node>& initial_hidden_state,
@@ -186,4 +186,4 @@ void LSTMSequenceOptimized::validate_and_infer_types() {
     set_output_type(2, result_et, {merged_num_directions, merged_batch_size, merged_hidden_size});
 }
 
-}  // namespace CUDAPlugin::nodes
+}  // namespace ov::nvidia_gpu::nodes
diff --git a/modules/cuda_plugin/src/transformer/nodes/lstm_sequence_optimized.hpp b/modules/nvidia_plugin/src/transformer/nodes/lstm_sequence_optimized.hpp
similarity index 96%
rename from modules/cuda_plugin/src/transformer/nodes/lstm_sequence_optimized.hpp
rename to modules/nvidia_plugin/src/transformer/nodes/lstm_sequence_optimized.hpp
index 2c91eac28..6b235446d 100644
--- a/modules/cuda_plugin/src/transformer/nodes/lstm_sequence_optimized.hpp
+++ b/modules/nvidia_plugin/src/transformer/nodes/lstm_sequence_optimized.hpp
@@ -6,7 +6,7 @@
 
 #include <openvino/op/lstm_sequence.hpp>
 
-namespace CUDAPlugin::nodes {
+namespace ov::nvidia_gpu::nodes {
 
 class LSTMSequenceOptimized : public ov::op::v5::LSTMSequence {
 public:
@@ -40,4 +40,4 @@ class LSTMSequenceOptimized : public ov::op::v5::LSTMSequence {
     MajorFormat m_major_format;
 };
 
-}  // namespace CUDAPlugin::nodes
+}  // namespace ov::nvidia_gpu::nodes
diff --git a/modules/cuda_plugin/src/transformer/noop_broadcast_transformation.cpp b/modules/nvidia_plugin/src/transformer/noop_broadcast_transformation.cpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/noop_broadcast_transformation.cpp
rename to modules/nvidia_plugin/src/transformer/noop_broadcast_transformation.cpp
diff --git a/modules/cuda_plugin/src/transformer/noop_broadcast_transformation.hpp b/modules/nvidia_plugin/src/transformer/noop_broadcast_transformation.hpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/noop_broadcast_transformation.hpp
rename to modules/nvidia_plugin/src/transformer/noop_broadcast_transformation.hpp
diff --git a/modules/cuda_plugin/src/transformer/preprocessing/mean_image_or_value.cpp b/modules/nvidia_plugin/src/transformer/preprocessing/mean_image_or_value.cpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/preprocessing/mean_image_or_value.cpp
rename to modules/nvidia_plugin/src/transformer/preprocessing/mean_image_or_value.cpp
diff --git a/modules/cuda_plugin/src/transformer/preprocessing/mean_image_or_value.hpp b/modules/nvidia_plugin/src/transformer/preprocessing/mean_image_or_value.hpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/preprocessing/mean_image_or_value.hpp
rename to modules/nvidia_plugin/src/transformer/preprocessing/mean_image_or_value.hpp
diff --git a/modules/cuda_plugin/src/transformer/preprocessing/preprocessing.cpp b/modules/nvidia_plugin/src/transformer/preprocessing/preprocessing.cpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/preprocessing/preprocessing.cpp
rename to modules/nvidia_plugin/src/transformer/preprocessing/preprocessing.cpp
diff --git a/modules/cuda_plugin/src/transformer/preprocessing/preprocessing.hpp b/modules/nvidia_plugin/src/transformer/preprocessing/preprocessing.hpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/preprocessing/preprocessing.hpp
rename to modules/nvidia_plugin/src/transformer/preprocessing/preprocessing.hpp
diff --git a/modules/cuda_plugin/src/transformer/preprocessing/std_scale.cpp b/modules/nvidia_plugin/src/transformer/preprocessing/std_scale.cpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/preprocessing/std_scale.cpp
rename to modules/nvidia_plugin/src/transformer/preprocessing/std_scale.cpp
diff --git a/modules/cuda_plugin/src/transformer/preprocessing/std_scale.hpp b/modules/nvidia_plugin/src/transformer/preprocessing/std_scale.hpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/preprocessing/std_scale.hpp
rename to modules/nvidia_plugin/src/transformer/preprocessing/std_scale.hpp
diff --git a/modules/cuda_plugin/src/transformer/remove_duplicated_results_transformation.cpp b/modules/nvidia_plugin/src/transformer/remove_duplicated_results_transformation.cpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/remove_duplicated_results_transformation.cpp
rename to modules/nvidia_plugin/src/transformer/remove_duplicated_results_transformation.cpp
diff --git a/modules/cuda_plugin/src/transformer/remove_duplicated_results_transformation.hpp b/modules/nvidia_plugin/src/transformer/remove_duplicated_results_transformation.hpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/remove_duplicated_results_transformation.hpp
rename to modules/nvidia_plugin/src/transformer/remove_duplicated_results_transformation.hpp
diff --git a/modules/cuda_plugin/src/transformer/remove_redundant_convert_transformation.cpp b/modules/nvidia_plugin/src/transformer/remove_redundant_convert_transformation.cpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/remove_redundant_convert_transformation.cpp
rename to modules/nvidia_plugin/src/transformer/remove_redundant_convert_transformation.cpp
diff --git a/modules/cuda_plugin/src/transformer/remove_redundant_convert_transformation.hpp b/modules/nvidia_plugin/src/transformer/remove_redundant_convert_transformation.hpp
similarity index 100%
rename from modules/cuda_plugin/src/transformer/remove_redundant_convert_transformation.hpp
rename to modules/nvidia_plugin/src/transformer/remove_redundant_convert_transformation.hpp
diff --git a/modules/cuda_plugin/src/utils/perf_timing.hpp b/modules/nvidia_plugin/src/utils/perf_timing.hpp
similarity index 94%
rename from modules/cuda_plugin/src/utils/perf_timing.hpp
rename to modules/nvidia_plugin/src/utils/perf_timing.hpp
index 5c3f71ec7..cc9c5ba23 100644
--- a/modules/cuda_plugin/src/utils/perf_timing.hpp
+++ b/modules/nvidia_plugin/src/utils/perf_timing.hpp
@@ -8,7 +8,7 @@
 
 #include "cuda/event.hpp"
 
-namespace CUDAPlugin::utils {
+namespace ov::nvidia_gpu::utils {
 /**
  * @brief class PerformaceTiming measures time between two events
  * and accumulates results from sequential start/stop calls
@@ -40,4 +40,4 @@ class PerformaceTiming {
     std::optional<CUDA::Event> stop_{};
     float duration_{};
 };
-}  // namespace CUDAPlugin::utils
+}  // namespace ov::nvidia_gpu::utils
diff --git a/modules/cuda_plugin/tests/functional/CMakeLists.txt b/modules/nvidia_plugin/tests/functional/CMakeLists.txt
similarity index 90%
rename from modules/cuda_plugin/tests/functional/CMakeLists.txt
rename to modules/nvidia_plugin/tests/functional/CMakeLists.txt
index 75dcd928b..85b427300 100644
--- a/modules/cuda_plugin/tests/functional/CMakeLists.txt
+++ b/modules/nvidia_plugin/tests/functional/CMakeLists.txt
@@ -16,10 +16,10 @@ addIeTargetTest(
         NAME ${TARGET_NAME}
         ROOT ${CMAKE_CURRENT_SOURCE_DIR}
         DEPENDENCIES
-        openvino_cuda_plugin
+        openvino_nvidia_gpu_plugin
         ${OPENVINO_ADDITIONAL_DEPENDENCIES}
         LINK_LIBRARIES_WHOLE_ARCHIVE
-        openvino_cuda_plugin_obj
+        openvino_nvidia_gpu_plugin_obj
         LINK_LIBRARIES
         IE::funcSharedTests
         gmock
diff --git a/modules/cuda_plugin/tests/functional/core_config.cpp b/modules/nvidia_plugin/tests/functional/core_config.cpp
similarity index 100%
rename from modules/cuda_plugin/tests/functional/core_config.cpp
rename to modules/nvidia_plugin/tests/functional/core_config.cpp
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/executable_network/cpp_holders.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/executable_network/cpp_holders.cpp
similarity index 92%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/executable_network/cpp_holders.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/executable_network/cpp_holders.cpp
index c34d5c482..5d5f61aaf 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/executable_network/cpp_holders.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/executable_network/cpp_holders.cpp
@@ -23,19 +23,19 @@ const std::vector<std::vector<int>> orders = {
 
 INSTANTIATE_TEST_CASE_P(smoke_BehaviorTests,
                         HoldersTest,
-                        ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                        ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::ValuesIn(orders)),
                         HoldersTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_BehaviorTests,
                         HoldersTestImportNetwork,
-                        ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA, "HETERO:CUDA"),
+                        ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA, "HETERO:NVIDIA"),
                                            ::testing::ValuesIn(orders)),
                         HoldersTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_BehaviorTests,
                         HoldersTestOnImportedNetwork,
-                        ::testing::Values(CommonTestUtils::DEVICE_CUDA, "HETERO:CUDA"),
+                        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA, "HETERO:NVIDIA"),
                         HoldersTestOnImportedNetwork::getTestCaseName);
 
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/executable_network/exec_network_base.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/executable_network/exec_network_base.cpp
similarity index 95%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/executable_network/exec_network_base.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/executable_network/exec_network_base.cpp
index 2c4b172f3..8b35e1633 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/executable_network/exec_network_base.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/executable_network/exec_network_base.cpp
@@ -14,7 +14,7 @@ const std::vector<std::map<std::string, std::string>> configs = {{}};
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          ExecutableNetworkBaseTest,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(configs)),
                          ExecutableNetworkBaseTest::getTestCaseName);
 
@@ -24,7 +24,7 @@ const std::vector<InferenceEngine::Precision> netPrecisions = {InferenceEngine::
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          ExecNetSetPrecision,
                          ::testing::Combine(::testing::ValuesIn(netPrecisions),
-                                            ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(configs)),
                          ExecNetSetPrecision::getTestCaseName);
 }  // namespace
\ No newline at end of file
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/executable_network/get_metric.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/executable_network/get_metric.cpp
similarity index 90%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/executable_network/get_metric.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/executable_network/get_metric.cpp
index 260199812..f6db9296a 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/executable_network/get_metric.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/executable_network/get_metric.cpp
@@ -18,34 +18,34 @@ namespace {
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassExecutableNetworkGetMetricTest,
                          IEClassExecutableNetworkGetMetricTest_SUPPORTED_CONFIG_KEYS,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA, "MULTI:CUDA", "HETERO:CUDA"));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA, "MULTI:NVIDIA", "HETERO:NVIDIA"));
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassExecutableNetworkGetMetricTest,
                          IEClassExecutableNetworkGetMetricTest_SUPPORTED_METRICS,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA, "MULTI:CUDA", "HETERO:CUDA"));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA, "MULTI:NVIDIA", "HETERO:NVIDIA"));
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassExecutableNetworkGetMetricTest,
                          IEClassExecutableNetworkGetMetricTest_NETWORK_NAME,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA, "MULTI:CUDA", "HETERO:CUDA"));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA, "MULTI:NVIDIA", "HETERO:NVIDIA"));
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassExecutableNetworkGetMetricTest,
                          IEClassExecutableNetworkGetMetricTest_OPTIMAL_NUMBER_OF_INFER_REQUESTS,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA, "MULTI:CUDA", "HETERO:CUDA"));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA, "MULTI:NVIDIA", "HETERO:NVIDIA"));
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassExecutableNetworkGetMetricTest_ThrowsUnsupported,
                          IEClassExecutableNetworkGetMetricTest,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA, "MULTI:CUDA", "HETERO:CUDA"));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA, "MULTI:NVIDIA", "HETERO:NVIDIA"));
 //
 // Executable Network GetConfig / SetConfig
 //
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassExecutableNetworkGetConfigTest,
                          IEClassExecutableNetworkGetConfigTest,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassExecutableNetworkSetConfigTest,
                          IEClassExecutableNetworkSetConfigTest,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 //
 // Hetero Executable Network GetMetric
@@ -55,19 +55,19 @@ INSTANTIATE_TEST_SUITE_P(smoke_IEClassExecutableNetworkSetConfigTest,
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassHeteroExecutableNetworlGetMetricTest,
                          IEClassHeteroExecutableNetworkGetMetricTest_SUPPORTED_CONFIG_KEYS,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassHeteroExecutableNetworlGetMetricTest,
                          IEClassHeteroExecutableNetworkGetMetricTest_SUPPORTED_METRICS,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassHeteroExecutableNetworlGetMetricTest,
                          IEClassHeteroExecutableNetworkGetMetricTest_NETWORK_NAME,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassHeteroExecutableNetworlGetMetricTest,
                          IEClassHeteroExecutableNetworkGetMetricTest_TARGET_FALLBACK,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 #endif  // ENABLE_INTEL_CPU
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/infer_request/callback.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/infer_request/callback.cpp
similarity index 97%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/infer_request/callback.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/infer_request/callback.cpp
index 88fbad23a..19cfa8b4a 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/infer_request/callback.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/infer_request/callback.cpp
@@ -24,7 +24,7 @@ const std::vector<std::map<std::string, std::string>> configs = {{}};
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          InferRequestCallbackTests,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(configs)),
                          InferRequestCallbackTests::getTestCaseName);
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/infer_request/config.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/infer_request/config.cpp
similarity index 96%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/infer_request/config.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/infer_request/config.cpp
index 98d7020f7..a531f3ee1 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/infer_request/config.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/infer_request/config.cpp
@@ -20,7 +20,7 @@ const std::vector<std::map<std::string, std::string>> configs = {};
 INSTANTIATE_TEST_CASE_P(smoke_BehaviorTests_IncorrectConfig,
                         InferRequestConfigTest,
                         ::testing::Combine(::testing::Values(0ul),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::ValuesIn(configs)),
                         InferRequestConfigTest::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/infer_request/infer_request.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/infer_request/infer_request.cpp
similarity index 97%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/infer_request/infer_request.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/infer_request/infer_request.cpp
index db550a79d..886c5dd1d 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/infer_request/infer_request.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/infer_request/infer_request.cpp
@@ -76,7 +76,7 @@ inline std::pair<size_t, size_t> getTensorHeightWidth(const InferenceEngine::Ten
         // Regardless of layout, dimensions are stored in fixed order
         return std::make_pair(dims.back(), dims.at(size - 2));
     } else {
-        CUDAPlugin::throwIEException("Tensor does not have height and width dimensions");
+        ov::nvidia_gpu::throwIEException("Tensor does not have height and width dimensions");
     }
 }
 
@@ -214,7 +214,7 @@ void fillBlobs(InferenceEngine::InferRequest inferRequest,
             } else if (item.second->getPrecision() == InferenceEngine::Precision::I32) {
                 fillBlobImInfo<int32_t>(inputBlob, batchSize, image_size);
             } else {
-                CUDAPlugin::throwIEException("Input precision is not supported for image info!");
+                ov::nvidia_gpu::throwIEException("Input precision is not supported for image info!");
             }
             continue;
         }
@@ -234,7 +234,7 @@ void fillBlobs(InferenceEngine::InferRequest inferRequest,
         } else if (item.second->getPrecision() == InferenceEngine::Precision::I16) {
             fillBlobRandom<int16_t>(inputBlob, Randomize<int16_t>{});
         } else {
-            CUDAPlugin::throwIEException(fmt::format("Input precision is not supported for {}", item.first));
+            ov::nvidia_gpu::throwIEException(fmt::format("Input precision is not supported for {}", item.first));
         }
     }
 }
@@ -346,7 +346,7 @@ TEST_F(smoke_InferenceRequestTest, ParameterResult) {
     InferenceEngine::Core ie{};
     InferenceEngine::Blob::Ptr a{};
     auto testNet = ie.ReadNetwork(model10, a);
-    auto execNet = ie.LoadNetwork(testNet, "CUDA");
+    auto execNet = ie.LoadNetwork(testNet, "NVIDIA");
     InferenceEngine::InferRequest request{execNet.CreateInferRequest()};
 
     const InferenceEngine::ConstInputsDataMap inputsInfo{execNet.GetInputsInfo()};
@@ -364,7 +364,7 @@ TEST_F(smoke_InferenceRequestTest, AsyncParameterResult) {
     InferenceEngine::Core ie{};
     InferenceEngine::Blob::Ptr a{};
     auto testNet = ie.ReadNetwork(model10, a);
-    auto execNet = ie.LoadNetwork(testNet, CommonTestUtils::DEVICE_CUDA);
+    auto execNet = ie.LoadNetwork(testNet, CommonTestUtils::DEVICE_NVIDIA);
     InferenceEngine::InferRequest inferRequest{execNet.CreateInferRequest()};
     const InferenceEngine::ConstInputsDataMap inputsInfo{execNet.GetInputsInfo()};
     fillBlobs(inferRequest, inputsInfo, 1);
@@ -379,7 +379,7 @@ TEST_F(InferenceRequestBasicTest, AsyncParameterResultCancel) {
     InferenceEngine::Core ie{};
     InferenceEngine::Blob::Ptr a{};
     auto testNet = ie.ReadNetwork(heavyModel10, a);
-    auto execNet = ie.LoadNetwork(testNet, CommonTestUtils::DEVICE_CUDA);
+    auto execNet = ie.LoadNetwork(testNet, CommonTestUtils::DEVICE_NVIDIA);
     InferenceEngine::InferRequest inferRequest{execNet.CreateInferRequest()};
     const InferenceEngine::ConstInputsDataMap inputsInfo{execNet.GetInputsInfo()};
     fillBlobs(inferRequest, inputsInfo, 1);
@@ -395,7 +395,7 @@ TEST_F(smoke_InferenceRequestTest, PerformanceCounters) {
         {InferenceEngine::PluginConfigParams::KEY_PERF_COUNT, InferenceEngine::PluginConfigParams::YES}};
 
     auto testNet = ie.ReadNetwork(model10, a);
-    auto execNet = ie.LoadNetwork(testNet, CommonTestUtils::DEVICE_CUDA, config);
+    auto execNet = ie.LoadNetwork(testNet, CommonTestUtils::DEVICE_NVIDIA, config);
     InferenceEngine::InferRequest request{execNet.CreateInferRequest()};
 
     const InferenceEngine::ConstInputsDataMap inputsInfo{execNet.GetInputsInfo()};
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/infer_request/io_blob.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/infer_request/io_blob.cpp
similarity index 96%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/infer_request/io_blob.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/infer_request/io_blob.cpp
index bf7a4fb16..c86c991a7 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/infer_request/io_blob.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/infer_request/io_blob.cpp
@@ -19,7 +19,7 @@ const std::vector<std::map<std::string, std::string>> configs = {{}};
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          InferRequestIOBBlobTest,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(configs)),
                          InferRequestIOBBlobTest::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/infer_request/perf_counters.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/infer_request/perf_counters.cpp
similarity index 96%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/infer_request/perf_counters.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/infer_request/perf_counters.cpp
index a183af9b8..fd6511f65 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/infer_request/perf_counters.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/infer_request/perf_counters.cpp
@@ -14,11 +14,11 @@ namespace {
 const std::vector<std::map<std::string, std::string>> configs = {{}};
 
 const std::vector<std::map<std::string, std::string>> Multiconfigs = {
-    {{MULTI_CONFIG_KEY(DEVICE_PRIORITIES), CommonTestUtils::DEVICE_CUDA}}};
+    {{MULTI_CONFIG_KEY(DEVICE_PRIORITIES), CommonTestUtils::DEVICE_NVIDIA}}};
 
 INSTANTIATE_TEST_CASE_P(smoke_BehaviorTests,
                         InferRequestPerfCountersTest,
-                        ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                        ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::ValuesIn(configs)),
                         InferRequestPerfCountersTest::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_executable_network/ov_exec_net_import_export.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_executable_network/ov_exec_net_import_export.cpp
similarity index 94%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_executable_network/ov_exec_net_import_export.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_executable_network/ov_exec_net_import_export.cpp
index 873978453..dfc39f178 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_executable_network/ov_exec_net_import_export.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_executable_network/ov_exec_net_import_export.cpp
@@ -16,14 +16,14 @@ const std::vector<ov::element::Type_t> netPrecisions = {
 const std::vector<ov::AnyMap> configs = {
     {},
 };
-const std::vector<ov::AnyMap> multiConfigs = {{ov::device::priorities(CommonTestUtils::DEVICE_CUDA)}};
+const std::vector<ov::AnyMap> multiConfigs = {{ov::device::priorities(CommonTestUtils::DEVICE_NVIDIA)}};
 
-const std::vector<ov::AnyMap> heteroConfigs = {{ov::device::priorities(CommonTestUtils::DEVICE_CUDA)}};
+const std::vector<ov::AnyMap> heteroConfigs = {{ov::device::priorities(CommonTestUtils::DEVICE_NVIDIA)}};
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          OVExecGraphImportExportTest,
                          ::testing::Combine(::testing::ValuesIn(netPrecisions),
-                                            ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(configs)),
                          OVExecGraphImportExportTest::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_executable_network/properties.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_executable_network/properties.cpp
similarity index 90%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_executable_network/properties.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_executable_network/properties.cpp
index 7f3cba406..83ea71b8a 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_executable_network/properties.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_executable_network/properties.cpp
@@ -30,13 +30,13 @@ const std::vector<ov::AnyMap> auto_inproperties = {
 
 const std::vector<ov::AnyMap> auto_batch_inproperties = {
     {ov::device::id("UNSUPPORTED_DEVICE_ID_STRING")},
-    {{CONFIG_KEY(AUTO_BATCH_DEVICE_CONFIG), std::string(CommonTestUtils::DEVICE_CUDA) + "(4)"},
+    {{CONFIG_KEY(AUTO_BATCH_DEVICE_CONFIG), std::string(CommonTestUtils::DEVICE_NVIDIA) + "(4)"},
      {ov::auto_batch_timeout(-1)}},
 };
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          OVCompiledModelPropertiesIncorrectTests,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(inproperties)),
                          OVCompiledModelPropertiesIncorrectTests::getTestCaseName);
 
@@ -71,7 +71,7 @@ const std::vector<ov::AnyMap> default_properties = {
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          OVCompiledModelPropertiesDefaultTests,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(default_properties)),
                          OVCompiledModelPropertiesDefaultTests::getTestCaseName);
 
@@ -81,26 +81,26 @@ const std::vector<ov::AnyMap> properties = {
 };
 
 const std::vector<ov::AnyMap> hetero_properties = {
-    {ov::device::priorities(CommonTestUtils::DEVICE_CUDA), ov::enable_profiling(true)},
-    {ov::device::priorities(CommonTestUtils::DEVICE_CUDA), ov::device::id("0")},
+    {ov::device::priorities(CommonTestUtils::DEVICE_NVIDIA), ov::enable_profiling(true)},
+    {ov::device::priorities(CommonTestUtils::DEVICE_NVIDIA), ov::device::id("0")},
 };
 
 const std::vector<ov::AnyMap> multi_properties = {
-    {ov::device::priorities(CommonTestUtils::DEVICE_CUDA), ov::enable_profiling(true)},
-    {ov::device::priorities(CommonTestUtils::DEVICE_CUDA), ov::device::id("0")},
+    {ov::device::priorities(CommonTestUtils::DEVICE_NVIDIA), ov::enable_profiling(true)},
+    {ov::device::priorities(CommonTestUtils::DEVICE_NVIDIA), ov::device::id("0")},
 };
 
 const std::vector<ov::AnyMap> auto_batch_properties = {
-    {{CONFIG_KEY(AUTO_BATCH_DEVICE_CONFIG), std::string(CommonTestUtils::DEVICE_CUDA) + "(4)"}},
-    {{CONFIG_KEY(AUTO_BATCH_DEVICE_CONFIG), std::string(CommonTestUtils::DEVICE_CUDA) + "(4)"},
+    {{CONFIG_KEY(AUTO_BATCH_DEVICE_CONFIG), std::string(CommonTestUtils::DEVICE_NVIDIA) + "(4)"}},
+    {{CONFIG_KEY(AUTO_BATCH_DEVICE_CONFIG), std::string(CommonTestUtils::DEVICE_NVIDIA) + "(4)"},
      {CONFIG_KEY(AUTO_BATCH_TIMEOUT), "1"}},
-    {{CONFIG_KEY(AUTO_BATCH_DEVICE_CONFIG), std::string(CommonTestUtils::DEVICE_CUDA) + "(4)"},
+    {{CONFIG_KEY(AUTO_BATCH_DEVICE_CONFIG), std::string(CommonTestUtils::DEVICE_NVIDIA) + "(4)"},
      {ov::auto_batch_timeout(10)}},
 };
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          OVCompiledModelPropertiesTests,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(properties)),
                          OVCompiledModelPropertiesTests::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/batched_tensors.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/batched_tensors.cpp
similarity index 99%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/batched_tensors.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/batched_tensors.cpp
index eab896a80..f09d6ecc2 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/batched_tensors.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/batched_tensors.cpp
@@ -81,7 +81,7 @@ using namespace ov;
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          OVInferRequestBatchedTests,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                          OVInferRequestBatchedTests::getTestCaseName);
 
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/callback.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/callback.cpp
similarity index 95%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/callback.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/callback.cpp
index 568ba4956..898f0721a 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/callback.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/callback.cpp
@@ -14,7 +14,7 @@ const std::vector<ov::AnyMap> configs = {{}};
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          OVInferRequestCallbackTests,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(configs)),
                          OVInferRequestCallbackTests::getTestCaseName);
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/cancellation.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/cancellation.cpp
similarity index 95%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/cancellation.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/cancellation.cpp
index 3b0af7dd3..edef573e8 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/cancellation.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/cancellation.cpp
@@ -15,7 +15,7 @@ const std::vector<ov::AnyMap> configs = {
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          OVInferRequestCancellationTests,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(configs)),
                          OVInferRequestCancellationTests::getTestCaseName);
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/infer_request_dynamic.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/infer_request_dynamic.cpp
similarity index 96%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/infer_request_dynamic.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/infer_request_dynamic.cpp
index 430a914b3..f0f789aa7 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/infer_request_dynamic.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/infer_request_dynamic.cpp
@@ -13,7 +13,7 @@ namespace {
 
 const std::vector<ov::AnyMap> configs = {{}};
 
-const std::vector<ov::AnyMap> HeteroConfigs = {{ov::device::priorities(CommonTestUtils::DEVICE_CUDA)}};
+const std::vector<ov::AnyMap> HeteroConfigs = {{ov::device::priorities(CommonTestUtils::DEVICE_NVIDIA)}};
 
 INSTANTIATE_TEST_SUITE_P(
     smoke_BehaviorTests,
@@ -21,7 +21,7 @@ INSTANTIATE_TEST_SUITE_P(
     ::testing::Combine(::testing::Values(ngraph::builder::subgraph::makeSplitConvConcat()),
                        ::testing::Values(std::vector<std::pair<std::vector<size_t>, std::vector<size_t>>>{
                            {{1, 4, 20, 20}, {1, 10, 18, 18}}, {{2, 4, 20, 20}, {2, 10, 18, 18}}}),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                        ::testing::ValuesIn(configs)),
     OVInferRequestDynamicTests::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/inference.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/inference.cpp
similarity index 95%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/inference.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/inference.cpp
index 629bbde28..544a289f3 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/inference.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/inference.cpp
@@ -15,7 +15,7 @@ using namespace ov;
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          OVInferRequestInferenceTests,
                          ::testing::Combine(::testing::Values(tensor_roi::roi_nchw(), tensor_roi::roi_1d()),
-                                            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                          OVInferRequestInferenceTests::getTestCaseName);
 
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/inference_chaining.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/inference_chaining.cpp
similarity index 93%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/inference_chaining.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/inference_chaining.cpp
index 0a0771c95..661c9aff1 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/inference_chaining.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/inference_chaining.cpp
@@ -14,11 +14,11 @@ namespace {
 
 const std::vector<ov::AnyMap> configs = {{}};
 
-const std::vector<ov::AnyMap> HeteroConfigs = {{ov::device::priorities(CommonTestUtils::DEVICE_CUDA)}};
+const std::vector<ov::AnyMap> HeteroConfigs = {{ov::device::priorities(CommonTestUtils::DEVICE_NVIDIA)}};
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          OVInferenceChaining,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(configs)),
                          OVInferenceChaining::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/io_tensor.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/io_tensor.cpp
similarity index 94%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/io_tensor.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/io_tensor.cpp
index 08386a18d..457866a2f 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/io_tensor.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/io_tensor.cpp
@@ -14,7 +14,7 @@ const std::vector<ov::AnyMap> configs = {{}};
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          OVInferRequestIOTensorTest,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(configs)),
                          OVInferRequestIOTensorTest::getTestCaseName);
 
@@ -25,14 +25,14 @@ std::vector<ov::element::Type> prcs = {
 
 const std::vector<ov::AnyMap> emptyConfigs = {{}};
 
-const std::vector<ov::AnyMap> HeteroConfigs = {{ov::device::priorities(CommonTestUtils::DEVICE_CUDA)}};
+const std::vector<ov::AnyMap> HeteroConfigs = {{ov::device::priorities(CommonTestUtils::DEVICE_NVIDIA)}};
 
-const std::vector<ov::AnyMap> Multiconfigs = {{ov::device::priorities(CommonTestUtils::DEVICE_CUDA)}};
+const std::vector<ov::AnyMap> Multiconfigs = {{ov::device::priorities(CommonTestUtils::DEVICE_NVIDIA)}};
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          OVInferRequestCheckTensorPrecision,
                          ::testing::Combine(::testing::ValuesIn(prcs),
-                                            ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(emptyConfigs)),
                          OVInferRequestCheckTensorPrecision::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/multithreading.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/multithreading.cpp
similarity index 95%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/multithreading.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/multithreading.cpp
index fe3d7891c..b2c7872ba 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/multithreading.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/multithreading.cpp
@@ -15,7 +15,7 @@ const std::vector<ov::AnyMap> configs = {{}};
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          OVInferRequestMultithreadingTests,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(configs)),
                          OVInferRequestMultithreadingTests::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/wait.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/wait.cpp
similarity index 95%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/wait.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/wait.cpp
index 1af01e81a..377945a65 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/wait.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_infer_request/wait.cpp
@@ -14,7 +14,7 @@ const std::vector<ov::AnyMap> configs = {{}};
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          OVInferRequestWaitTests,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(configs)),
                          OVInferRequestWaitTests::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/caching_tests.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/caching_tests.cpp
similarity index 97%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/caching_tests.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/caching_tests.cpp
index b1b6c3f1d..8b1e1e0b7 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/caching_tests.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/caching_tests.cpp
@@ -20,7 +20,7 @@ INSTANTIATE_TEST_SUITE_P(smoke_Behavior_CachingSupportCase_Template,
                          ::testing::Combine(::testing::ValuesIn(CompileModelCacheTestBase::getStandardFunctions()),
                                             ::testing::ValuesIn(precisionsTemplate),
                                             ::testing::ValuesIn(batchSizesTemplate),
-                                            ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::Values(ov::AnyMap())),
                          CompileModelCacheTestBase::getTestCaseName);
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/core_integration.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/core_integration.cpp
similarity index 92%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/core_integration.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/core_integration.cpp
index 7dbf0ad39..b4885dc5d 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/core_integration.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/core_integration.cpp
@@ -19,11 +19,12 @@ namespace {
 
 INSTANTIATE_TEST_SUITE_P(smoke_OVClassBasicTestP,
                          OVClassBasicTestP,
-                         ::testing::Values(std::make_pair("openvino_cuda_plugin", CommonTestUtils::DEVICE_CUDA)));
+                         ::testing::Values(std::make_pair("openvino_nvidia_gpu_plugin",
+                                                          CommonTestUtils::DEVICE_NVIDIA)));
 
 INSTANTIATE_TEST_SUITE_P(smoke_OVClassNetworkTestP,
                          OVClassNetworkTestP,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 //
 // OV Class GetMetric
@@ -31,39 +32,39 @@ INSTANTIATE_TEST_SUITE_P(smoke_OVClassNetworkTestP,
 
 INSTANTIATE_TEST_SUITE_P(smoke_OVClassGetMetricTest,
                          OVClassGetMetricTest_SUPPORTED_CONFIG_KEYS,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_OVClassGetMetricTest,
                          OVClassGetMetricTest_SUPPORTED_METRICS,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_OVClassGetMetricTest,
                          OVClassGetMetricTest_AVAILABLE_DEVICES,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_OVClassGetMetricTest,
                          OVClassGetMetricTest_FULL_DEVICE_NAME,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_OVClassGetMetricTest,
                          OVClassGetMetricTest_OPTIMIZATION_CAPABILITIES,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_OVClassGetMetricTest,
                          OVClassGetMetricTest_RANGE_FOR_ASYNC_INFER_REQUESTS,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_OVClassGetMetricTest,
                          OVClassGetMetricTest_ThrowUnsupported,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_OVClassGetConfigTest,
                          OVClassGetConfigTest_ThrowUnsupported,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_OVClassGetAvailableDevices,
                          OVClassGetAvailableDevices,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 //
 // OV Class GetConfig
@@ -71,12 +72,12 @@ INSTANTIATE_TEST_SUITE_P(smoke_OVClassGetAvailableDevices,
 
 INSTANTIATE_TEST_SUITE_P(smoke_OVClassGetConfigTest,
                          OVClassGetConfigTest,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 TEST(OVClassBasicTest, smoke_CUDAGetSetConfigNoThrow) {
     ov::Core core = createCoreWithTemplate();
 
-    auto device_name = CommonTestUtils::DEVICE_CUDA;
+    auto device_name = CommonTestUtils::DEVICE_NVIDIA;
 
     for (auto&& property : core.get_property(device_name, ov::supported_properties)) {
         if (ov::device::id == property) {
@@ -100,11 +101,11 @@ TEST(OVClassBasicTest, smoke_CUDAGetSetConfigNoThrow) {
 
 INSTANTIATE_TEST_SUITE_P(smoke_OVClassQueryNetworkTest,
                          OVClassQueryNetworkTest,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 // OV Class Load network
 
 INSTANTIATE_TEST_SUITE_P(smoke_OVClassLoadNetworkTest,
                          OVClassLoadNetworkTest,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/life_time.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/life_time.cpp
similarity index 94%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/life_time.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/life_time.cpp
index 06569029c..029527ea0 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/life_time.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/life_time.cpp
@@ -12,12 +12,12 @@ namespace {
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          OVHoldersTest,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                          OVHoldersTest::getTestCaseName);
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          OVHoldersTestOnImportedNetwork,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA, "HETERO:CUDA"),
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA, "HETERO:NVIDIA"),
                          OVHoldersTestOnImportedNetwork::getTestCaseName);
 
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/properties_tests.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/properties_tests.cpp
similarity index 90%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/properties_tests.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/properties_tests.cpp
index 166cb27a4..829128dbd 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/properties_tests.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/ov_plugin/properties_tests.cpp
@@ -34,7 +34,7 @@ const std::vector<ov::AnyMap> auto_batch_inproperties = {
 
 INSTANTIATE_TEST_SUITE_P(DISABLED_smoke_BehaviorTests,
                          OVPropertiesIncorrectTests,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(inproperties)),
                          OVPropertiesIncorrectTests::getTestCaseName);
 
@@ -69,7 +69,7 @@ const std::vector<ov::AnyMap> default_properties = {
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          OVPropertiesDefaultTests,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(default_properties)),
                          OVPropertiesDefaultTests::getTestCaseName);
 
@@ -79,23 +79,23 @@ const std::vector<ov::AnyMap> properties = {
 };
 
 const std::vector<ov::AnyMap> hetero_properties = {
-    {ov::device::priorities(CommonTestUtils::DEVICE_CUDA), ov::enable_profiling(true)},
-    {ov::device::priorities(CommonTestUtils::DEVICE_CUDA), ov::device::id(0)},
+    {ov::device::priorities(CommonTestUtils::DEVICE_NVIDIA), ov::enable_profiling(true)},
+    {ov::device::priorities(CommonTestUtils::DEVICE_NVIDIA), ov::device::id(0)},
 };
 
 const std::vector<ov::AnyMap> multi_properties = {
-    {ov::device::priorities(CommonTestUtils::DEVICE_CUDA), ov::enable_profiling(true)},
-    {ov::device::priorities(CommonTestUtils::DEVICE_CUDA), ov::device::id(0)},
+    {ov::device::priorities(CommonTestUtils::DEVICE_NVIDIA), ov::enable_profiling(true)},
+    {ov::device::priorities(CommonTestUtils::DEVICE_NVIDIA), ov::device::id(0)},
 };
 
 const std::vector<ov::AnyMap> auto_batch_properties = {
-    {{CONFIG_KEY(AUTO_BATCH_DEVICE_CONFIG), CommonTestUtils::DEVICE_CUDA}},
-    {{CONFIG_KEY(AUTO_BATCH_DEVICE_CONFIG), CommonTestUtils::DEVICE_CUDA}, {CONFIG_KEY(AUTO_BATCH_TIMEOUT), "1"}},
+    {{CONFIG_KEY(AUTO_BATCH_DEVICE_CONFIG), CommonTestUtils::DEVICE_NVIDIA}},
+    {{CONFIG_KEY(AUTO_BATCH_DEVICE_CONFIG), CommonTestUtils::DEVICE_NVIDIA}, {CONFIG_KEY(AUTO_BATCH_TIMEOUT), "1"}},
 };
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          OVPropertiesTests,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(properties)),
                          OVPropertiesTests::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/caching_tests.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/caching_tests.cpp
similarity index 96%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/caching_tests.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/caching_tests.cpp
index b1dc688f9..ebe047f87 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/caching_tests.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/caching_tests.cpp
@@ -20,6 +20,6 @@ INSTANTIATE_TEST_SUITE_P(smoke_Behavior_CachingSupportCase_Template,
                          ::testing::Combine(::testing::ValuesIn(LoadNetworkCacheTestBase::getStandardFunctions()),
                                             ::testing::ValuesIn(precisionsTemplate),
                                             ::testing::ValuesIn(batchSizesTemplate),
-                                            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                          LoadNetworkCacheTestBase::getTestCaseName);
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/config.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/config.cpp
similarity index 96%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/config.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/config.cpp
index f089d8bb1..c88540b49 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/config.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/config.cpp
@@ -29,13 +29,13 @@ const std::vector<std::map<std::string, std::string>> inconfigs = {
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          IncorrectConfigTests,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(inconfigs)),
                          IncorrectConfigTests::getTestCaseName);
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          IncorrectConfigAPITests,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(inconfigs)),
                          IncorrectConfigAPITests::getTestCaseName);
 }  // namespace
\ No newline at end of file
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/core_integration.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/core_integration.cpp
similarity index 94%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/core_integration.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/core_integration.cpp
index 93ccc5a56..d894ac2ed 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/core_integration.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/core_integration.cpp
@@ -19,11 +19,12 @@ namespace {
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassBasicTestP,
                          IEClassBasicTestP,
-                         ::testing::Values(std::make_pair("openvino_cuda_plugin", CommonTestUtils::DEVICE_CUDA)));
+                         ::testing::Values(std::make_pair("openvino_nvidia_gpu_plugin",
+                                                          CommonTestUtils::DEVICE_NVIDIA)));
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassNetworkTestP,
                          IEClassNetworkTestP,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 //
 // IE Class GetMetric
@@ -31,39 +32,39 @@ INSTANTIATE_TEST_SUITE_P(smoke_IEClassNetworkTestP,
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassGetMetricTest,
                          IEClassGetMetricTest_SUPPORTED_CONFIG_KEYS,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassGetMetricTest,
                          IEClassGetMetricTest_SUPPORTED_METRICS,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassGetMetricTest,
                          IEClassGetMetricTest_AVAILABLE_DEVICES,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassGetMetricTest,
                          IEClassGetMetricTest_FULL_DEVICE_NAME,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassGetMetricTest,
                          IEClassGetMetricTest_OPTIMIZATION_CAPABILITIES,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassGetMetricTest,
                          IEClassGetMetricTest_RANGE_FOR_ASYNC_INFER_REQUESTS,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassGetMetricTest,
                          IEClassGetMetricTest_ThrowUnsupported,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassGetConfigTest,
                          IEClassGetConfigTest_ThrowUnsupported,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassGetAvailableDevices,
                          IEClassGetAvailableDevices,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 //
 // IE Class SetConfig
@@ -119,7 +120,7 @@ TEST_F(IEClassSetConfigTestHETERO, smoke_SetConfigNoThrow) {
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassGetConfigTest,
                          IEClassGetConfigTest,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 class IEClassGetConfigTestCUDA : public BehaviorTestsUtils::IEClassNetworkTest,
                                  public BehaviorTestsUtils::IEPluginTestBase {
@@ -132,7 +133,7 @@ class IEClassGetConfigTestCUDA : public BehaviorTestsUtils::IEClassNetworkTest,
 TEST_F(IEClassGetConfigTestCUDA, smoke_GetConfigNoThrow) {
     InferenceEngine::Core ie = BehaviorTestsUtils::createIECoreWithTemplate();
     InferenceEngine::Parameter p;
-    std::string deviceName = CommonTestUtils::DEVICE_CUDA;
+    std::string deviceName = CommonTestUtils::DEVICE_NVIDIA;
 
     ASSERT_NO_THROW(p = ie.GetMetric(deviceName, METRIC_KEY(SUPPORTED_CONFIG_KEYS)));
     std::vector<std::string> configValues = p;
@@ -155,11 +156,11 @@ TEST_F(IEClassGetConfigTestCUDA, smoke_GetConfigNoThrow) {
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassQueryNetworkTest,
                          IEClassQueryNetworkTest,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 // IE Class Load network
 
 INSTANTIATE_TEST_SUITE_P(smoke_IEClassLoadNetworkTest,
                          IEClassLoadNetworkTest,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/life_time.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/life_time.cpp
similarity index 92%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/life_time.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/life_time.cpp
index 315b4cc7f..3879d6bb4 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/life_time.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/life_time.cpp
@@ -23,19 +23,19 @@ const std::vector<std::vector<int>> orders = {
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          HoldersTest,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(orders)),
                          HoldersTest::getTestCaseName);
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          HoldersTestImportNetwork,
-                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_CUDA, "HETERO:CUDA"),
+                         ::testing::Combine(::testing::Values(CommonTestUtils::DEVICE_NVIDIA, "HETERO:NVIDIA"),
                                             ::testing::ValuesIn(orders)),
                          HoldersTest::getTestCaseName);
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          HoldersTestOnImportedNetwork,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA, "HETERO:CUDA"),
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA, "HETERO:NVIDIA"),
                          HoldersTestOnImportedNetwork::getTestCaseName);
 
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/preprocessing.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/preprocessing.cpp
similarity index 96%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/preprocessing.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/preprocessing.cpp
index 6d959af57..6e4262117 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/preprocessing.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/preprocessing.cpp
@@ -22,7 +22,7 @@ INSTANTIATE_TEST_SUITE_P(smoke_Behavior_PreprocessingPrecisionConvertTestsViaSet
                          ::testing::Combine(::testing::ValuesIn(inputPrecisions),
                                             ::testing::Values(4),     // Number of input tensor channels
                                             ::testing::Values(true),  // Use SetInput
-                                            ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(configs)),
                          PreprocessingPrecisionConvertTest::getTestCaseName);
 
@@ -32,7 +32,7 @@ INSTANTIATE_TEST_SUITE_P(smoke_Behavior_PreprocessingPrecisionConvertTestsViaGet
                                             ::testing::Values(4),  // Number of input tensor channels (blob_copy only
                                                                    // supports 4d and 5d tensors)
                                             ::testing::Values(false),  // use GetBlob
-                                            ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(configs)),
                          PreprocessingPrecisionConvertTest::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/set_preprocess.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/set_preprocess.cpp
similarity index 95%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/set_preprocess.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/set_preprocess.cpp
index ff5996bb3..356bdb1d6 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/set_preprocess.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/set_preprocess.cpp
@@ -18,15 +18,15 @@ const std::vector<InferenceEngine::Precision> netPrecisions = {InferenceEngine::
 const std::vector<std::map<std::string, std::string>> configs = {{}};
 
 const std::vector<std::map<std::string, std::string>> multiConfigs = {
-    {{InferenceEngine::MultiDeviceConfigParams::KEY_MULTI_DEVICE_PRIORITIES, CommonTestUtils::DEVICE_CUDA}}};
+    {{InferenceEngine::MultiDeviceConfigParams::KEY_MULTI_DEVICE_PRIORITIES, CommonTestUtils::DEVICE_NVIDIA}}};
 
 const std::vector<std::map<std::string, std::string>> heteroConfigs = {
-    {{"TARGET_FALLBACK", CommonTestUtils::DEVICE_CUDA}}};
+    {{"TARGET_FALLBACK", CommonTestUtils::DEVICE_NVIDIA}}};
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          InferRequestPreprocessTest,
                          ::testing::Combine(::testing::ValuesIn(netPrecisions),
-                                            ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(configs)),
                          InferRequestPreprocessTest::getTestCaseName);
 
@@ -60,7 +60,7 @@ INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                                             ::testing::ValuesIn(ioLayouts),
                                             ::testing::Bool(),
                                             ::testing::Bool(),
-                                            ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(configs)),
                          InferRequestPreprocessConversionTest::getTestCaseName);
 
@@ -74,7 +74,7 @@ INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                                             ::testing::Bool(),
                                             ::testing::Values(true),  // only SetBlob
                                             ::testing::Values(true),  // only SetBlob
-                                            ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                             ::testing::ValuesIn(configs)),
                          InferRequestPreprocessDynamicallyInSetBlobTest::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/synthetic.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/synthetic.cpp
similarity index 79%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/synthetic.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/synthetic.cpp
index 73b3d3bad..17971aa67 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/synthetic.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/synthetic.cpp
@@ -18,8 +18,8 @@ using namespace HeteroTests;
 INSTANTIATE_TEST_SUITE_P(
     smoke_manyTargetInputs,
     HeteroSyntheticTest,
-    ::testing::Combine(::testing::Values(std::vector<PluginParameter>{{"CUDA", "openvino_cuda_plugin"},
-                                                                      {"CUDA", "openvino_cuda_plugin"}}),
+    ::testing::Combine(::testing::Values(std::vector<PluginParameter>{{"NVIDIA", "openvino_nvidia_gpu_plugin"},
+                                                                      {"NVIDIA", "openvino_nvidia_gpu_plugin"}}),
                        ::testing::ValuesIn(HeteroTests::HeteroSyntheticTest::withMajorNodesFunctions(
                            [] { return ngraph::builder::subgraph::makeConvPool2Relu2(); }, {"Conv_1"}, true))),
     HeteroSyntheticTest::getTestCaseName);
@@ -27,16 +27,16 @@ INSTANTIATE_TEST_SUITE_P(
 INSTANTIATE_TEST_SUITE_P(
     smoke_SingleMajorNode,
     HeteroSyntheticTest,
-    ::testing::Combine(::testing::Values(std::vector<PluginParameter>{{"CUDA", "openvino_cuda_plugin"},
-                                                                      {"CUDA", "openvino_cuda_plugin"}}),
+    ::testing::Combine(::testing::Values(std::vector<PluginParameter>{{"NVIDIA", "openvino_nvidia_gpu_plugin"},
+                                                                      {"NVIDIA", "openvino_nvidia_gpu_plugin"}}),
                        ::testing::ValuesIn(HeteroTests::HeteroSyntheticTest::_singleMajorNodeFunctions)),
     HeteroSyntheticTest::getTestCaseName);
 
 INSTANTIATE_TEST_SUITE_P(
     nightly_RandomMajorNodes,
     HeteroSyntheticTest,
-    ::testing::Combine(::testing::Values(std::vector<PluginParameter>{{"CUDA", "openvino_cuda_plugin"},
-                                                                      {"CUDA", "openvino_cuda_plugin"}}),
+    ::testing::Combine(::testing::Values(std::vector<PluginParameter>{{"NVIDIA", "openvino_nvidia_gpu_plugin"},
+                                                                      {"NVIDIA", "openvino_nvidia_gpu_plugin"}}),
                        ::testing::ValuesIn(HeteroTests::HeteroSyntheticTest::_randomMajorNodeFunctions)),
     HeteroSyntheticTest::getTestCaseName);
 
@@ -47,8 +47,8 @@ static std::vector<std::function<std::shared_ptr<ngraph::Function>()>> dynamicBu
 INSTANTIATE_TEST_SUITE_P(
     smoke_NonZeroMajorNode_dynamic,
     HeteroSyntheticTest,
-    ::testing::Combine(::testing::Values(std::vector<PluginParameter>{{"CUDA", "openvino_cuda_plugin"},
-                                                                      {"CUDA", "openvino_cuda_plugin"}}),
+    ::testing::Combine(::testing::Values(std::vector<PluginParameter>{{"NVIDIA", "openvino_nvidia_gpu_plugin"},
+                                                                      {"NVIDIA", "openvino_nvidia_gpu_plugin"}}),
                        ::testing::ValuesIn(HeteroTests::HeteroSyntheticTest::withMajorNodesFunctions(
                            dynamicBuilders.front(), {"nonZero_1"}))),
     HeteroSyntheticTest::getTestCaseName);
@@ -56,8 +56,8 @@ INSTANTIATE_TEST_SUITE_P(
 INSTANTIATE_TEST_SUITE_P(
     smoke_NonZeroMajorNode_dynamic_batch,
     HeteroSyntheticTest,
-    ::testing::Combine(::testing::Values(std::vector<PluginParameter>{{"CUDA", "openvino_cuda_plugin"},
-                                                                      {"CUDA", "openvino_cuda_plugin"}}),
+    ::testing::Combine(::testing::Values(std::vector<PluginParameter>{{"NVIDIA", "openvino_nvidia_gpu_plugin"},
+                                                                      {"NVIDIA", "openvino_nvidia_gpu_plugin"}}),
                        ::testing::ValuesIn(HeteroTests::HeteroSyntheticTest::withMajorNodesFunctions(
                            dynamicBuilders.front(), {"nonZero_1"}, true))),
     HeteroSyntheticTest::getTestCaseName);
@@ -66,8 +66,8 @@ INSTANTIATE_TEST_SUITE_P(
     smoke_SingleMajorNode_dynamic,
     HeteroSyntheticTest,
     ::testing::Combine(
-        ::testing::Values(std::vector<PluginParameter>{{"CUDA", "openvino_cuda_plugin"},
-                                                       {"CUDA", "openvino_cuda_plugin"}}),
+        ::testing::Values(std::vector<PluginParameter>{{"NVIDIA", "openvino_nvidia_gpu_plugin"},
+                                                       {"NVIDIA", "openvino_nvidia_gpu_plugin"}}),
         ::testing::ValuesIn(HeteroTests::HeteroSyntheticTest::singleMajorNodeFunctions(dynamicBuilders))),
     HeteroSyntheticTest::getTestCaseName);
 
@@ -75,16 +75,16 @@ INSTANTIATE_TEST_SUITE_P(
     nightly_RandomMajorNodes_dynamic,
     HeteroSyntheticTest,
     ::testing::Combine(
-        ::testing::Values(std::vector<PluginParameter>{{"CUDA", "openvino_cuda_plugin"},
-                                                       {"CUDA", "openvino_cuda_plugin"}}),
+        ::testing::Values(std::vector<PluginParameter>{{"NVIDIA", "openvino_nvidia_gpu_plugin"},
+                                                       {"NVIDIA", "openvino_nvidia_gpu_plugin"}}),
         ::testing::ValuesIn(HeteroTests::HeteroSyntheticTest::randomMajorNodeFunctions(dynamicBuilders))),
     HeteroSyntheticTest::getTestCaseName);
 
 INSTANTIATE_TEST_SUITE_P(
     smoke_SingleMajorNode_dynamic_batch,
     HeteroSyntheticTest,
-    ::testing::Combine(::testing::Values(std::vector<PluginParameter>{{"CUDA", "openvino_cuda_plugin"},
-                                                                      {"CUDA", "openvino_cuda_plugin"}}),
+    ::testing::Combine(::testing::Values(std::vector<PluginParameter>{{"NVIDIA", "openvino_nvidia_gpu_plugin"},
+                                                                      {"NVIDIA", "openvino_nvidia_gpu_plugin"}}),
                        ::testing::ValuesIn(HeteroTests::HeteroSyntheticTest::singleMajorNodeFunctions(dynamicBuilders,
                                                                                                       true))),
     HeteroSyntheticTest::getTestCaseName);
@@ -92,8 +92,8 @@ INSTANTIATE_TEST_SUITE_P(
 INSTANTIATE_TEST_SUITE_P(
     nightly_RandomMajorNodes_dynamic_batch,
     HeteroSyntheticTest,
-    ::testing::Combine(::testing::Values(std::vector<PluginParameter>{{"CUDA", "openvino_cuda_plugin"},
-                                                                      {"CUDA", "openvino_cuda_plugin"}}),
+    ::testing::Combine(::testing::Values(std::vector<PluginParameter>{{"NVIDIA", "openvino_nvidia_gpu_plugin"},
+                                                                      {"NVIDIA", "openvino_nvidia_gpu_plugin"}}),
                        ::testing::ValuesIn(HeteroTests::HeteroSyntheticTest::randomMajorNodeFunctions(dynamicBuilders,
                                                                                                       true))),
     HeteroSyntheticTest::getTestCaseName);
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/version.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/version.cpp
similarity index 97%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/version.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/version.cpp
index 922e5157c..8921e89f8 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/behavior/plugin/version.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/behavior/plugin/version.cpp
@@ -14,7 +14,7 @@ const std::vector<std::map<std::string, std::string>> configs = {{}};
 
 INSTANTIATE_TEST_SUITE_P(smoke_BehaviorTests,
                          VersionTest,
-                         ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                          VersionTest::getTestCaseName);
 
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/activation.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/activation.cpp
similarity index 99%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/activation.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/activation.cpp
index ac82b4d14..0209fb29c 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/activation.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/activation.cpp
@@ -98,7 +98,7 @@ const auto basicCases = ::testing::Combine(::testing::ValuesIn(CommonTestUtils::
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(CommonTestUtils::combineParams(basic)),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 const auto basicPreluCases =
     ::testing::Combine(::testing::ValuesIn(CommonTestUtils::combineParams(preluActivationParamTypes)),
@@ -108,7 +108,7 @@ const auto basicPreluCases =
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::ValuesIn(CommonTestUtils::combineParams(preluBasic)),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 const auto basicPReluConstParamCases =
     ::testing::Combine(::testing::ValuesIn(CommonTestUtils::combineParams(preluActivationParamTypes)),
@@ -118,7 +118,7 @@ const auto basicPReluConstParamCases =
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::ValuesIn(CommonTestUtils::combineParams(preluBasic)),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 // TODO int parameter activation tests don't work for CUDA now
 // const auto basicIntegerOperations =
@@ -129,7 +129,7 @@ const auto basicPReluConstParamCases =
 //                       ::testing::Values(InferenceEngine::Layout::ANY),
 //                       ::testing::Values(InferenceEngine::Layout::ANY),
 //                       ::testing::ValuesIn(CommonTestUtils::combineParams(basic)),
-//                       ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+//                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 TEST_P(ActivationLayerTest, CompareWithRefs) { Run(); }
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/activation_slt.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/activation_slt.cpp
similarity index 94%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/activation_slt.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/activation_slt.cpp
index 3b3488bb8..287b038e2 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/activation_slt.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/activation_slt.cpp
@@ -56,7 +56,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 1000, 14, 14}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 // Attrs:  {}
@@ -75,7 +75,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 1024, 14, 14}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -94,7 +94,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 128, 100, 171}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -113,7 +113,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 128, 112, 112}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -132,7 +132,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 128, 16, 16}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -151,7 +151,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 128, 17, 17}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -170,7 +170,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 128, 18, 18, 18}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -189,7 +189,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 128, 28, 28}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -208,7 +208,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 128, 50, 86}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -227,7 +227,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 128, 56, 56}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -246,7 +246,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 16, 128, 128}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -265,7 +265,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 16, 144, 144, 144}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -284,7 +284,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 16, 56, 56}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -303,7 +303,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 160, 50, 86}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -322,7 +322,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 192, 14, 14}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -341,7 +341,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 192, 17, 17}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -360,7 +360,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 192, 200, 342}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -379,7 +379,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 192, 35, 35}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -398,7 +398,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 192, 50, 86}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -417,7 +417,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 192, 8, 8}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -436,7 +436,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 2048, 7, 7}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -455,7 +455,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 224, 17, 17}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -474,7 +474,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 224, 35, 35}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -493,7 +493,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 224, 50, 86}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -512,7 +512,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 256}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -531,7 +531,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 256, 14, 14}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -550,7 +550,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 256, 17, 17}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -569,7 +569,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 256, 28, 28}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -588,7 +588,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 256, 56, 56}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -607,7 +607,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 256, 8, 8}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -626,7 +626,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 256, 9, 9, 9}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -645,7 +645,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 32, 100, 171}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -664,7 +664,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 32, 147, 147}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -683,7 +683,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 32, 149, 149}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -702,7 +702,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 32, 224, 224}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -721,7 +721,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 32, 28, 28}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -740,7 +740,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 32, 64, 64}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -759,7 +759,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 32, 72, 72, 72}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -778,7 +778,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 320, 17, 17}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -797,7 +797,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 320, 8, 8}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -816,7 +816,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 384, 17, 17}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -835,7 +835,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 384, 8, 8}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -854,7 +854,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 4096}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -873,7 +873,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 448, 8, 8}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -892,7 +892,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 48, 14, 14}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -911,7 +911,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 512, 1000}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -930,7 +930,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 512, 14, 14}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -949,7 +949,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 512, 28, 28}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -968,7 +968,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 512, 7, 7}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -987,7 +987,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 512, 8, 8}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1006,7 +1006,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 64, 100, 171}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1025,7 +1025,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 64, 112, 112}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1044,7 +1044,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 64, 113, 113}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1063,7 +1063,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 64, 14, 14}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1082,7 +1082,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 64, 147, 147}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1101,7 +1101,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 64, 200, 342}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1120,7 +1120,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 64, 224, 224}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1139,7 +1139,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 64, 32, 32}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1158,7 +1158,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 64, 35, 35}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1177,7 +1177,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 64, 36, 36, 36}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1196,7 +1196,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 64, 400, 683}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1215,7 +1215,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 64, 50, 86}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1234,7 +1234,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 64, 56, 56}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1253,7 +1253,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 64, 73, 73}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1272,7 +1272,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 96, 100, 171}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1291,7 +1291,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 96, 35, 35}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1310,7 +1310,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 96, 50, 86}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1329,7 +1329,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 96, 71, 71}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1348,7 +1348,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 96, 73, 73}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1367,7 +1367,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{100, 128, 4, 4}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1386,7 +1386,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{100, 128, 7, 7}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1405,7 +1405,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{100, 160, 4, 4}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1424,7 +1424,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{100, 192, 4, 4}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1443,7 +1443,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{100, 192, 7, 7}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1462,7 +1462,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{100, 224, 4, 4}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1481,7 +1481,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{100, 256, 15, 15}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1500,7 +1500,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{100, 256, 4, 4}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1519,7 +1519,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{100, 256, 7, 7}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1538,7 +1538,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{100, 320, 4, 4}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1557,7 +1557,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{100, 352, 4, 4}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1576,7 +1576,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{64, 1024}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1595,7 +1595,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{64, 6272}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1614,7 +1614,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{64, 64, 14, 14}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 // {AUTOGENERATED_TESTS_END_TAG_RELU}
@@ -1640,7 +1640,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 1, 128, 128}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1659,7 +1659,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 1, 144, 144, 144}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1678,7 +1678,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 1, 1917, 91}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1697,7 +1697,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 1152, 1, 1}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1716,7 +1716,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 144, 1, 1}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1735,7 +1735,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 16, 1, 1}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1754,7 +1754,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 1920, 1, 1}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1773,7 +1773,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 240, 1, 1}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1792,7 +1792,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 3, 20, 20, 85}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1811,7 +1811,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 3, 40, 40, 85}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1830,7 +1830,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 3, 80, 80, 85}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1849,7 +1849,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 32, 1, 1}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1868,7 +1868,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 480, 1, 1}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1887,7 +1887,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 672, 1, 1}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1906,7 +1906,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 76725, 90}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1925,7 +1925,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 96, 1, 1}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1944,7 +1944,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{100, 90, 15, 15}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -1963,7 +1963,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{64, 1, 28, 28}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 // {AUTOGENERATED_TESTS_END_TAG_SIGMOID}
@@ -1997,7 +1997,7 @@ const auto basicTanhCases =
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::ValuesIn(listToVectors(tanhShapes)),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_CASE_P(smoke_Activation_Basic_Tanh,
                         ActivationLayerTest,
@@ -2040,7 +2040,7 @@ const auto clampCasesSmoke = ::testing::Combine(::testing::ValuesIn(clampParamsS
                                                 ::testing::Values(InferenceEngine::Layout::ANY),
                                                 ::testing::Values(InferenceEngine::Layout::ANY),
                                                 ::testing::ValuesIn(clampInShapesSmoke),
-                                                ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                                ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_CASE_P(smoke_Activation_Basic_Clamp,
                         ActivationLayerTest,
@@ -2069,7 +2069,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid357_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2090,7 +2090,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid329_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2111,7 +2111,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid306_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2132,7 +2132,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid301_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2153,7 +2153,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid265_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2174,7 +2174,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid57_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2195,7 +2195,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid37_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2216,7 +2216,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid101_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2237,7 +2237,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid66_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2258,7 +2258,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid278_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2279,7 +2279,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid334_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2300,7 +2300,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid311_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2321,7 +2321,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid283_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2342,7 +2342,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid14_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2363,7 +2363,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid110_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2384,7 +2384,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid288_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2405,7 +2405,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_mask_rcnn_inception_v2_coco_opid277_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2426,7 +2426,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid212_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2447,7 +2447,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid169_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2468,7 +2468,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid352_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2489,7 +2489,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid347_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2510,7 +2510,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid23_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2531,7 +2531,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid28_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2552,7 +2552,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(autogen_Clamp_ssd_mobilenet_v2_coco_opid221_params.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 const std::vector<std::reference_wrapper<const AutogenClampParams>> autogen_Clamp_all_params{
@@ -2602,7 +2602,7 @@ const auto clampCasesBig = ::testing::Combine(::testing::Values(clampParamsBig),
                                               ::testing::Values(InferenceEngine::Layout::ANY),
                                               ::testing::Values(InferenceEngine::Layout::ANY),
                                               ::testing::Values(clampInShapeBig),
-                                              ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                              ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 struct ClampBenchmark : testing::Test {
     template <typename T>
@@ -2617,17 +2617,17 @@ struct ClampBenchmark : testing::Test {
 
         const auto& minMax = params.second;
 
-        CUDAPlugin::ThreadContext threadContext{{}};
-        CUDAPlugin::OperationBase::Ptr operation = [&] {
+        ov::nvidia_gpu::ThreadContext threadContext{{}};
+        ov::nvidia_gpu::OperationBase::Ptr operation = [&] {
             const bool optimizeOption = false;
             auto param = std::make_shared<ov::op::v0::Parameter>(ov::element::from<T>(), ov::PartialShape{shape.first});
             auto node = std::make_shared<ov::op::v0::Clamp>(param->output(0), minMax[0], minMax[1]);
 
-            auto& registry = CUDAPlugin::OperationRegistry::getInstance();
-            auto op = registry.createOperation(CUDAPlugin::CreationContext{threadContext.device(), optimizeOption},
+            auto& registry = ov::nvidia_gpu::OperationRegistry::getInstance();
+            auto op = registry.createOperation(ov::nvidia_gpu::CreationContext{threadContext.device(), optimizeOption},
                                                node,
-                                               std::array{CUDAPlugin::TensorID{0}},
-                                               std::array{CUDAPlugin::TensorID{0}});
+                                               std::array{ov::nvidia_gpu::TensorID{0}},
+                                               std::array{ov::nvidia_gpu::TensorID{0}});
             return op;
         }();
         const int tesnorSize = ov::shape_size(shape.first);
@@ -2640,10 +2640,10 @@ struct ClampBenchmark : testing::Test {
 
         std::vector<std::shared_ptr<ngraph::runtime::Tensor>> emptyTensor;
         std::map<std::string, std::size_t> emptyMapping;
-        CUDAPlugin::CancellationToken token{};
-        CUDAPlugin::CudaGraph graph{CUDAPlugin::CreationContext{CUDA::Device{}, false}, {}};
-        CUDAPlugin::Profiler profiler{false, graph};
-        CUDAPlugin::InferenceRequestContext context{
+        ov::nvidia_gpu::CancellationToken token{};
+        ov::nvidia_gpu::CudaGraph graph{ov::nvidia_gpu::CreationContext{CUDA::Device{}, false}, {}};
+        ov::nvidia_gpu::Profiler profiler{false, graph};
+        ov::nvidia_gpu::InferenceRequestContext context{
             emptyTensor, emptyMapping, emptyTensor, emptyMapping, threadContext, token, profiler};
 
         std::vector<T> inHost(tesnorSize);
@@ -2660,13 +2660,13 @@ struct ClampBenchmark : testing::Test {
         CUDA::Allocation maxAlloc = stream.malloc(minMaxSizeBytes);
         CUDA::Allocation minAlloc = stream.malloc(minMaxSizeBytes);
 
-        CUDAPlugin::Workbuffers workbuffers{};
-        CUDAPlugin::WorkbufferRequest wbRequest{operation->GetWorkBufferRequest()};
+        ov::nvidia_gpu::Workbuffers workbuffers{};
+        ov::nvidia_gpu::WorkbufferRequest wbRequest{operation->GetWorkBufferRequest()};
         if (!wbRequest.immutable_sizes.empty()) {
             Ensures(wbRequest.immutable_sizes.size() == 2);
             Ensures(wbRequest.immutable_sizes[0] == minMaxSizeBytes && wbRequest.immutable_sizes[1] == minMaxSizeBytes);
 
-            CUDAPlugin::IOperationExec::Buffers initBuffers{static_cast<DevPtr>(maxAlloc),
+            ov::nvidia_gpu::IOperationExec::Buffers initBuffers{static_cast<DevPtr>(maxAlloc),
                                                             static_cast<DevPtr>(minAlloc)};
             operation->InitSharedImmutableWorkbuffers(initBuffers);
 
@@ -2736,7 +2736,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Swish,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(listToVectors(smoke_SwishShapes)),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ActivationLayerTest::getTestCaseName);
 
 // clang-format off
@@ -2757,7 +2757,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 10, 1, 1}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2776,7 +2776,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 1152, 20, 20}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2795,7 +2795,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 128, 40, 40}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2814,7 +2814,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 128, 80, 80}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2833,7 +2833,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 144, 160, 160}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2852,7 +2852,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 144, 80, 80}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2871,7 +2871,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 16, 320, 320}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2890,7 +2890,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 1920, 20, 20}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2909,7 +2909,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 20, 1, 1}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2928,7 +2928,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 240, 40, 40}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2947,7 +2947,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 240, 80, 80}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2966,7 +2966,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 256, 20, 20}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -2985,7 +2985,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 256, 40, 40}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3004,7 +3004,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 28, 1, 1}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3023,7 +3023,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 32, 160, 160}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3042,7 +3042,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 32, 320, 320}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3061,7 +3061,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 4, 1, 1}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3080,7 +3080,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 48, 1, 1}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3099,7 +3099,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 480, 40, 40}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3118,7 +3118,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 512, 20, 20}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3137,7 +3137,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 6, 1, 1}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3156,7 +3156,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 64, 160, 160}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3175,7 +3175,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 64, 80, 80}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3194,7 +3194,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 672, 20, 20}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3213,7 +3213,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 672, 40, 40}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3232,7 +3232,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 8, 1, 1}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3251,7 +3251,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 80, 1, 1}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3270,7 +3270,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 88, 10, 10}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3289,7 +3289,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 88, 20, 20}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3308,7 +3308,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 88, 40, 40}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3327,7 +3327,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 88, 5, 5}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3346,7 +3346,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 88, 80, 80}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3365,7 +3365,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 96, 160, 160}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 
@@ -3384,7 +3384,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::pair<std::vector<size_t>, std::vector<size_t>>{{1, 96, 320, 320}, {}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 // {AUTOGENERATED_TESTS_END_TAG_SWISH}
@@ -3405,7 +3405,7 @@ INSTANTIATE_TEST_CASE_P(
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::ValuesIn(listToVectors(Floor_shapes)),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ActivationLayerTest::getTestCaseName);
 
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/benchmark.hpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/benchmark.hpp
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/benchmark.hpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/benchmark.hpp
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/broadcast.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/broadcast.cpp
similarity index 96%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/broadcast.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/broadcast.cpp
index 8729091e0..ecce5efda 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/broadcast.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/broadcast.cpp
@@ -23,7 +23,7 @@ INSTANTIATE_TEST_CASE_P(smoke_TestNumpyBroadcast1,
                                            ::testing::Values(ov::op::BroadcastType::NUMPY),
                                            ::testing::Values(ov::Shape{3, 1}),  // input shape
                                            ::testing::ValuesIn(inputPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         BroadcastLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_TestNumpyBroadcast2,
@@ -33,7 +33,7 @@ INSTANTIATE_TEST_CASE_P(smoke_TestNumpyBroadcast2,
                                            ::testing::Values(ov::op::BroadcastType::NUMPY),
                                            ::testing::Values(ov::Shape{1, 4, 1}),  // input shape
                                            ::testing::ValuesIn(inputPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         BroadcastLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_TestNumpyBroadcast3,
@@ -43,7 +43,7 @@ INSTANTIATE_TEST_CASE_P(smoke_TestNumpyBroadcast3,
                                            ::testing::Values(ov::op::BroadcastType::NUMPY),
                                            ::testing::Values(ov::Shape{3, 1, 1}),  // input shape
                                            ::testing::ValuesIn(inputPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         BroadcastLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_TestNumpyBroadcast4,
@@ -53,7 +53,7 @@ INSTANTIATE_TEST_CASE_P(smoke_TestNumpyBroadcast4,
                                            ::testing::Values(ov::op::BroadcastType::NUMPY),
                                            ::testing::Values(ov::Shape{1, 3, 1, 3, 1, 3, 1}),  // input shape
                                            ::testing::ValuesIn(inputPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         BroadcastLayerTest::getTestCaseName);
 
 // BIDIRECTIONAL MODE
@@ -65,7 +65,7 @@ INSTANTIATE_TEST_CASE_P(smoke_TestBidirectionalBroadcast1,
                                            ::testing::Values(ov::op::BroadcastType::BIDIRECTIONAL),
                                            ::testing::Values(ov::Shape{4, 1}),  // input shape
                                            ::testing::ValuesIn(inputPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         BroadcastLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_TestBidirectionalBroadcast2,
@@ -75,7 +75,7 @@ INSTANTIATE_TEST_CASE_P(smoke_TestBidirectionalBroadcast2,
                                            ::testing::Values(ov::op::BroadcastType::BIDIRECTIONAL),
                                            ::testing::Values(ov::Shape{1, 4, 1}),  // input shape
                                            ::testing::ValuesIn(inputPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         BroadcastLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_TestBidirectionalBroadcas3,
@@ -85,7 +85,7 @@ INSTANTIATE_TEST_CASE_P(smoke_TestBidirectionalBroadcas3,
                                            ::testing::Values(ov::op::BroadcastType::BIDIRECTIONAL),
                                            ::testing::Values(ov::Shape{4, 1, 1}),  // input shape
                                            ::testing::ValuesIn(inputPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         BroadcastLayerTest::getTestCaseName);
 
 // EXPLICIT MODE
@@ -97,7 +97,7 @@ INSTANTIATE_TEST_CASE_P(smoke_TestExplicitBroadcast1,
                                            ::testing::Values(ov::op::BroadcastType::EXPLICIT),
                                            ::testing::Values(ov::Shape{3, 1}),  // input shape
                                            ::testing::ValuesIn(inputPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         BroadcastLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_TestExplicitBroadcast2,
@@ -107,7 +107,7 @@ INSTANTIATE_TEST_CASE_P(smoke_TestExplicitBroadcast2,
                                            ::testing::Values(ov::op::BroadcastType::EXPLICIT),
                                            ::testing::Values(ov::Shape{5, 7}),  // input shape
                                            ::testing::ValuesIn(inputPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         BroadcastLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_TestExplicitBroadcast3,
@@ -117,7 +117,7 @@ INSTANTIATE_TEST_CASE_P(smoke_TestExplicitBroadcast3,
                                            ::testing::Values(ov::op::BroadcastType::EXPLICIT),
                                            ::testing::Values(ov::Shape{4, 7, 6}),  // input shape
                                            ::testing::ValuesIn(inputPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         BroadcastLayerTest::getTestCaseName);
 
 // YOLOv5 operators
@@ -134,7 +134,7 @@ INSTANTIATE_TEST_CASE_P(yolov5_BroadcastTest1,
                                            ::testing::Values(ov::op::BroadcastType::BIDIRECTIONAL),
                                            ::testing::Values(ov::Shape{1, 3, 80, 80, 2}),
                                            ::testing::ValuesIn(precisionsYOLOv5),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         BroadcastLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(yolov5_BroadcastTest2,
@@ -144,7 +144,7 @@ INSTANTIATE_TEST_CASE_P(yolov5_BroadcastTest2,
                                            ::testing::Values(ov::op::BroadcastType::BIDIRECTIONAL),
                                            ::testing::Values(ov::Shape{1, 3, 40, 40, 2}),
                                            ::testing::ValuesIn(precisionsYOLOv5),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         BroadcastLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(yolov5_BroadcastTest3,
@@ -154,7 +154,7 @@ INSTANTIATE_TEST_CASE_P(yolov5_BroadcastTest3,
                                            ::testing::Values(ov::op::BroadcastType::BIDIRECTIONAL),
                                            ::testing::Values(ov::Shape{1, 3, 20, 20, 2}),
                                            ::testing::ValuesIn(precisionsYOLOv5),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         BroadcastLayerTest::getTestCaseName);
 
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/comparison.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/comparison.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/comparison.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/comparison.cpp
index 5928230e7..de75b0791 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/comparison.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/comparison.cpp
@@ -58,7 +58,7 @@ const auto smokeComparisonTestParams =
                        ::testing::ValuesIn(secondInputTypes),
                        ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                        ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                        ::testing::Values(additional_config));
 
 const auto comparisonTestParams = ::testing::Combine(::testing::ValuesIn(CommonTestUtils::combineParams(shapes)),
@@ -67,7 +67,7 @@ const auto comparisonTestParams = ::testing::Combine(::testing::ValuesIn(CommonT
                                                      ::testing::ValuesIn(secondInputTypes),
                                                      ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                                      ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
-                                                     ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                                     ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                                      ::testing::Values(additional_config));
 
 INSTANTIATE_TEST_CASE_P(smoke_ComparisonCompareWithRefs,
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/concat.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/concat.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/concat.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/concat.cpp
index 1580589e0..185efda5a 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/concat.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/concat.cpp
@@ -33,7 +33,7 @@ INSTANTIATE_TEST_CASE_P(smoke_NoReshape,
                                            ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConcatLayerTest::getTestCaseName);
 
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convert.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convert.cpp
similarity index 97%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convert.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convert.cpp
index 9074fbdb1..2c8f82629 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convert.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convert.cpp
@@ -58,7 +58,7 @@ INSTANTIATE_TEST_SUITE_P(smoke_ConversionLayerTest_From_F32,
                                             ::testing::ValuesIn(out_precisions),
                                             ::testing::Values(InferenceEngine::Layout::ANY),
                                             ::testing::Values(InferenceEngine::Layout::ANY),
-                                            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                          ConversionLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_SUITE_P(smoke_ConversionLayerTest_To_F32,
@@ -69,7 +69,7 @@ INSTANTIATE_TEST_SUITE_P(smoke_ConversionLayerTest_To_F32,
                                             ::testing::Values(Precision::FP32),
                                             ::testing::Values(InferenceEngine::Layout::ANY),
                                             ::testing::Values(InferenceEngine::Layout::ANY),
-                                            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                          ConversionLayerTest::getTestCaseName);
 
 /* TODO Uncomment when BF16 support is implemented
@@ -80,7 +80,7 @@ INSTANTIATE_TEST_CASE_P(smoke_ConvertLayerTest_From_BF16, ConversionCUDALayerTes
                                 ::testing::ValuesIn(precisions),
                                 ::testing::Values(Layout::ANY),
                                 ::testing::Values(Layout::ANY),
-                                ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvertLayerTest::getTestCaseName);
 INSTANTIATE_TEST_CASE_P(smoke_ConvertLayerTest_To_BF16, ConversionCUDALayerTest,
                         ::testing::Combine(
@@ -89,7 +89,7 @@ INSTANTIATE_TEST_CASE_P(smoke_ConvertLayerTest_To_BF16, ConversionCUDALayerTest,
                                 ::testing::Values(Precision::BF16),
                                 ::testing::Values(Layout::ANY),
                                 ::testing::Values(Layout::ANY),
-                                ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvertLayerTest::getTestCaseName);
 */
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convert_color_i420.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convert_color_i420.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convert_color_i420.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convert_color_i420.cpp
index 963aa26a1..ab4c5343d 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convert_color_i420.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convert_color_i420.cpp
@@ -122,7 +122,7 @@ const auto testCase_values = ::testing::Combine(::testing::ValuesIn(inShapes_nhw
                                                 ::testing::ValuesIn(inTypes),
                                                 ::testing::Bool(),
                                                 ::testing::Bool(),
-                                                ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                                ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_TestsConvertColorI420,
                          ConvertColorI420CUDALayerTest,
@@ -133,7 +133,7 @@ const auto testCase_accuracy_values = ::testing::Combine(::testing::Values(ov::S
                                                          ::testing::Values(ov::element::u8),
                                                          ::testing::Values(false),
                                                          ::testing::Values(true),
-                                                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_TestsConvertColorI420_acc,
                          ConvertColorI420CUDAAccuracyTest,
@@ -144,7 +144,7 @@ const auto testCase_accuracy_values_nightly = ::testing::Combine(::testing::Valu
                                                                  ::testing::Values(ov::element::u8),
                                                                  ::testing::Values(false),
                                                                  ::testing::Values(true),
-                                                                 ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                                                 ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(nightly_TestsConvertColorI420_acc,
                          ConvertColorI420CUDAAccuracyTest,
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convert_color_nv12.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convert_color_nv12.cpp
similarity index 96%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convert_color_nv12.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convert_color_nv12.cpp
index 8821f56ad..d90697d96 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convert_color_nv12.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convert_color_nv12.cpp
@@ -43,7 +43,7 @@ const auto testCase_values = ::testing::Combine(::testing::ValuesIn(inShapes_nhw
                                                 ::testing::ValuesIn(inTypes),
                                                 ::testing::Bool(),
                                                 ::testing::Bool(),
-                                                ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                                ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_TestsConvertColorNV12,
                          ConvertColorNV12CUDALayerTest,
@@ -63,7 +63,7 @@ const auto testCase_accuracy_values = ::testing::Combine(::testing::Values(ov::S
                                                          ::testing::Values(ov::element::u8),
                                                          ::testing::Values(false),
                                                          ::testing::Values(true),
-                                                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(smoke_TestsConvertColorNV12_acc,
                          ConvertColorNV12CUDAAccuracyTest,
@@ -74,7 +74,7 @@ const auto testCase_accuracy_values_nightly = ::testing::Combine(::testing::Valu
                                                                  ::testing::Values(ov::element::u8),
                                                                  ::testing::Values(false),
                                                                  ::testing::Values(true),
-                                                                 ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                                                 ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_SUITE_P(nightly_TestsConvertColorNV12_acc,
                          ConvertColorNV12CUDAAccuracyTest,
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution.cpp
similarity index 96%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution.cpp
index 51a65dafe..91840f7ef 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution.cpp
@@ -102,7 +102,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution1D_ExplicitPaddingSymmetric1,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 30})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionLayerThresholdTest::getTestCaseName);
 INSTANTIATE_TEST_CASE_P(smoke_Convolution1D_ExplicitPaddingSymmetric2,
                         ConvolutionLayerThresholdTest,
@@ -113,7 +113,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution1D_ExplicitPaddingSymmetric2,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 30})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionLayerThresholdTest::getTestCaseName);
 INSTANTIATE_TEST_CASE_P(smoke_Convolution1D_ExplicitPaddingAsymmetric1,
                         ConvolutionLayerThresholdTest,
@@ -124,7 +124,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution1D_ExplicitPaddingAsymmetric1,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 30})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionLayerThresholdTest::getTestCaseName);
 INSTANTIATE_TEST_CASE_P(smoke_Convolution1D_ExplicitPaddingAsymmetric2,
                         ConvolutionLayerThresholdTest,
@@ -135,7 +135,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution1D_ExplicitPaddingAsymmetric2,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 30})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionLayerThresholdTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_Convolution1D_AutoPadValid,
@@ -147,7 +147,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution1D_AutoPadValid,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 30})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionLayerThresholdTest::getTestCaseName);
 
 /* ============= 2D Convolution ============= */
@@ -206,7 +206,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_ExplicitPaddingSymmetric1,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 30, 30})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionLayerThresholdTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_ExplicitPaddingSymmetric2_FP32,
@@ -218,7 +218,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_ExplicitPaddingSymmetric2_FP32,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 30, 30})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionLayerThresholdTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_ExplicitPaddingSymmetric2,
@@ -230,7 +230,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_ExplicitPaddingSymmetric2,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 30, 30})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionLayerThresholdTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_ExplicitPaddingAsymmetric1,
@@ -242,7 +242,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_ExplicitPaddingAsymmetric1,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 30, 30})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionLayerThresholdTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_ExplicitPaddingAsymmetric2,
@@ -254,7 +254,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_ExplicitPaddingAsymmetric2,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 30, 30})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionLayerThresholdTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_AutoPadValid,
@@ -266,7 +266,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_AutoPadValid,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 30, 30})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionLayerThresholdTest::getTestCaseName);
 
 /* ============= 3D Convolution ============= */
@@ -324,7 +324,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution3D_ExplicitPaddingSymmetric1,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 10, 10, 10})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionLayerThresholdTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_Convolution3D_ExplicitPaddingSymmetric2,
@@ -336,7 +336,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution3D_ExplicitPaddingSymmetric2,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 10, 10, 10})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionLayerThresholdTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_Convolution3D_ExplicitPaddingAsymmetric1,
@@ -348,7 +348,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution3D_ExplicitPaddingAsymmetric1,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 10, 10, 10})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionLayerThresholdTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_Convolution3D_ExplicitPaddingAsymmetric2,
@@ -360,7 +360,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution3D_ExplicitPaddingAsymmetric2,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 10, 10, 10})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionLayerThresholdTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_Convolution3D_AutoPadValid,
@@ -372,7 +372,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution3D_AutoPadValid,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 10, 10, 10})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionLayerThresholdTest::getTestCaseName);
 
 // =============================================================================
@@ -401,7 +401,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 2, 1000})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -427,7 +427,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 1000})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -453,7 +453,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 1000})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -479,7 +479,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 80, 1000})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -505,7 +505,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1024, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -531,7 +531,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1024, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -557,7 +557,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1024, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -583,7 +583,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 114, 114})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -609,7 +609,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 28, 28})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -635,7 +635,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 28, 28})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -661,7 +661,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -687,7 +687,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -713,7 +713,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 58, 58})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -739,7 +739,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 80, 80})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -765,7 +765,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 80, 80})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -791,7 +791,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 80, 80})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -817,7 +817,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 16, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -843,7 +843,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 2048, 7, 7})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -869,7 +869,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -895,7 +895,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -921,7 +921,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -947,7 +947,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 28, 28})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -973,7 +973,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -999,7 +999,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1025,7 +1025,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1051,7 +1051,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1077,7 +1077,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1103,7 +1103,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 80, 80})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1129,7 +1129,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 3, 232, 232})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1155,7 +1155,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 160, 160})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1181,7 +1181,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 232, 232})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1207,7 +1207,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 28, 28})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1233,7 +1233,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 384, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1259,7 +1259,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 384, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1285,7 +1285,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 48, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1311,7 +1311,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1337,7 +1337,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1363,7 +1363,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1389,7 +1389,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1415,7 +1415,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1441,7 +1441,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 28, 28})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1467,7 +1467,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 28, 28})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1493,7 +1493,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1519,7 +1519,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 7, 7})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1545,7 +1545,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1571,7 +1571,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 160, 160})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1597,7 +1597,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 160, 160})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1623,7 +1623,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 226, 226})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1649,7 +1649,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1675,7 +1675,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1701,7 +1701,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1727,7 +1727,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 80, 80})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1753,7 +1753,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({100, 5, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1779,7 +1779,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1024, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1805,7 +1805,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1831,7 +1831,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 3, 227, 227})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1857,7 +1857,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 226, 226})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1883,7 +1883,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 28, 28})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1909,7 +1909,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 114, 114})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1935,7 +1935,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 104, 104})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1961,7 +1961,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 152, 152})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -1987,7 +1987,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 76, 76})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2013,7 +2013,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 38, 38})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2039,7 +2039,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 52, 52})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2065,7 +2065,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 76, 76})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2091,7 +2091,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 416, 416})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2117,7 +2117,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 608, 608})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2143,7 +2143,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 26, 26})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2169,7 +2169,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 38, 38})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2195,7 +2195,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 208, 208})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2221,7 +2221,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 304, 304})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2247,7 +2247,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 12, 320, 320})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2273,7 +2273,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 112, 112})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2299,7 +2299,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 28, 28})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2325,7 +2325,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2351,7 +2351,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2377,7 +2377,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 16, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2403,7 +2403,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2429,7 +2429,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2455,7 +2455,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 28, 28})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2481,7 +2481,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2507,7 +2507,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 3, 224, 224})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2533,7 +2533,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 160, 160})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2559,7 +2559,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 28, 28})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2585,7 +2585,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 48, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2611,7 +2611,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2637,7 +2637,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 28, 28})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2663,7 +2663,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 7, 7})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2689,7 +2689,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 112, 112})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2715,7 +2715,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2741,7 +2741,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 224, 224})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2767,7 +2767,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2793,7 +2793,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 80, 80})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2819,7 +2819,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2845,7 +2845,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 80, 80})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2871,7 +2871,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 80, 80})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2897,7 +2897,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 28, 28})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2923,7 +2923,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2949,7 +2949,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -2975,7 +2975,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 320, 320})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3001,7 +3001,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3027,7 +3027,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 160, 160})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3053,7 +3053,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 3, 224, 224})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3079,7 +3079,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({64, 106, 64})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3105,7 +3105,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({64, 128, 64})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3131,7 +3131,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1, 128, 128})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3157,7 +3157,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1, 224, 224})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3183,7 +3183,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 10, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3209,7 +3209,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1024, 13, 13})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3235,7 +3235,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1024, 13, 13})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3261,7 +3261,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1024, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3287,7 +3287,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1024, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3313,7 +3313,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1024, 17, 17})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3339,7 +3339,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1024, 17, 17})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3365,7 +3365,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1024, 17, 17})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3391,7 +3391,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1024, 17, 17})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3417,7 +3417,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1024, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3443,7 +3443,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1024, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3469,7 +3469,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1024, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3495,7 +3495,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 112, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3521,7 +3521,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 112, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3547,7 +3547,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1152, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3573,7 +3573,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1152, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3599,7 +3599,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1152, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3625,7 +3625,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3651,7 +3651,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3677,7 +3677,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 104, 104})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3703,7 +3703,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 152, 152})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3729,7 +3729,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 152, 152})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3755,7 +3755,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 16, 16})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3781,7 +3781,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 2, 2})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3807,7 +3807,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 28, 28})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3833,7 +3833,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 28, 28})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3859,7 +3859,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 3, 3})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3885,7 +3885,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 304, 304})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3911,7 +3911,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 32, 32})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3937,7 +3937,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 50, 86})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3963,7 +3963,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 50, 86})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -3989,7 +3989,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 50, 86})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4015,7 +4015,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 52, 52})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4041,7 +4041,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 76, 76})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4067,7 +4067,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 76, 76})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4093,7 +4093,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 76, 76})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4119,7 +4119,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 8, 8})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4145,7 +4145,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1280, 10, 10})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4171,7 +4171,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1280, 10, 10})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4197,7 +4197,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1280, 10, 10})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4223,7 +4223,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 144, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4249,7 +4249,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 144, 160, 160})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4275,7 +4275,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 144, 38, 38})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4301,7 +4301,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 144, 75, 75})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4327,7 +4327,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 144, 80, 80})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4353,7 +4353,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1536, 8, 8})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4379,7 +4379,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1536, 8, 8})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4405,7 +4405,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 16, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4431,7 +4431,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 16, 128, 128})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4457,7 +4457,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 16, 150, 150})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4483,7 +4483,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 16, 320, 320})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4509,7 +4509,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 16, 320, 320})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4535,7 +4535,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 16, 64, 64})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4561,7 +4561,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 160, 10, 10})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4587,7 +4587,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 160, 50, 86})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4613,7 +4613,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 160, 50, 86})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4639,7 +4639,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 160, 73, 73})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4665,7 +4665,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 192, 100, 171})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4691,7 +4691,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 192, 100, 171})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4717,7 +4717,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 192, 17, 17})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4743,7 +4743,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 192, 17, 17})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4769,7 +4769,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 192, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4795,7 +4795,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 192, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4821,7 +4821,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 192, 35, 35})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4847,7 +4847,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 192, 38, 38})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4873,7 +4873,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 192, 50, 86})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4899,7 +4899,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1920, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4925,7 +4925,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1920, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4951,7 +4951,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 20, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -4977,7 +4977,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 2048, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5003,7 +5003,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 2048, 7, 7})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5029,7 +5029,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 224, 17, 17})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5055,7 +5055,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 224, 17, 17})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5081,7 +5081,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 224, 17, 17})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5107,7 +5107,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 24, 160, 160})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5133,7 +5133,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 24, 75, 75})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5159,7 +5159,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 240, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5185,7 +5185,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 240, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5211,7 +5211,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 240, 80, 80})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5237,7 +5237,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 100, 171})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5263,7 +5263,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5289,7 +5289,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5315,7 +5315,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 16, 16})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5341,7 +5341,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 17, 17})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5367,7 +5367,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 17, 17})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5393,7 +5393,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 2, 2})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5419,7 +5419,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 2, 2})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5445,7 +5445,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 2, 2})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5471,7 +5471,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 26, 26})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5497,7 +5497,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 26, 26})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5523,7 +5523,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 3, 3})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5549,7 +5549,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 3, 3})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5575,7 +5575,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 3, 3})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5601,7 +5601,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 38, 38})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5627,7 +5627,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 38, 38})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5653,7 +5653,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 38, 38})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5679,7 +5679,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 38, 38})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5705,7 +5705,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 5, 5})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5731,7 +5731,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 52, 52})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5757,7 +5757,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 52, 52})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5783,7 +5783,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5809,7 +5809,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5835,7 +5835,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 76, 76})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5861,7 +5861,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 76, 76})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5887,7 +5887,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 76, 76})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5913,7 +5913,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 8, 8})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5939,7 +5939,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 28, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5965,7 +5965,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 3, 416, 416})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -5991,7 +5991,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 3, 608, 608})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6017,7 +6017,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6043,7 +6043,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 128, 128})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6069,7 +6069,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 147, 147})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6095,7 +6095,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 150, 150})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6121,7 +6121,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 208, 208})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6147,7 +6147,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 224, 224})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6173,7 +6173,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 224, 224})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6199,7 +6199,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 304, 304})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6225,7 +6225,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 32, 32})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6251,7 +6251,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 320, 320})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6277,7 +6277,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 38, 38})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6303,7 +6303,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 64, 64})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6329,7 +6329,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 320, 10, 10})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6355,7 +6355,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 320, 100, 171})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6381,7 +6381,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 320, 100, 171})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6407,7 +6407,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 320, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6433,7 +6433,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 320, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6459,7 +6459,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 384, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6485,7 +6485,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 384, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6511,7 +6511,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 384, 35, 35})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6537,7 +6537,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 384, 35, 35})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6563,7 +6563,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 384, 35, 35})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6589,7 +6589,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 384, 52, 52})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6615,7 +6615,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 384, 8, 8})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6641,7 +6641,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 384, 8, 8})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6667,7 +6667,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 384, 8, 8})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6693,7 +6693,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 4, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6719,7 +6719,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 4, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6745,7 +6745,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 40, 80, 80})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6771,7 +6771,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 40, 80, 80})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6797,7 +6797,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 448, 8, 8})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6823,7 +6823,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 48, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6849,7 +6849,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 480, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6875,7 +6875,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 480, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6901,7 +6901,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 480, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6927,7 +6927,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 5, 224, 224})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6953,7 +6953,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 5, 224, 224})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -6979,7 +6979,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 13, 13})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7005,7 +7005,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 13, 13})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7031,7 +7031,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7057,7 +7057,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7083,7 +7083,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7109,7 +7109,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7135,7 +7135,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 26, 26})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7161,7 +7161,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 26, 26})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7187,7 +7187,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 28, 28})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7213,7 +7213,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 28, 28})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7239,7 +7239,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 38, 38})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7265,7 +7265,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 38, 38})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7291,7 +7291,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 38, 38})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7317,7 +7317,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 5, 5})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7343,7 +7343,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 5, 5})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7369,7 +7369,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 5, 5})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7395,7 +7395,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 50, 86})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7421,7 +7421,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 50, 86})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7447,7 +7447,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 7, 7})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7473,7 +7473,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 7, 7})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7499,7 +7499,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 8, 8})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7525,7 +7525,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 8, 8})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7551,7 +7551,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 576, 10, 10})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7577,7 +7577,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 576, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7603,7 +7603,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 576, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7629,7 +7629,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 576, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7655,7 +7655,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 576, 50, 86})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7681,7 +7681,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 576, 50, 86})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7707,7 +7707,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 576, 50, 86})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7733,7 +7733,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 576, 50, 86})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7759,7 +7759,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 576, 50, 86})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7785,7 +7785,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 576, 50, 86})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7811,7 +7811,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 576, 50, 86})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7837,7 +7837,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 6, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7863,7 +7863,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7889,7 +7889,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 100, 171})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7915,7 +7915,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 100, 171})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7941,7 +7941,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 104, 104})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7967,7 +7967,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 152, 152})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -7993,7 +7993,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 152, 152})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8019,7 +8019,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 16, 16})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8045,7 +8045,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8071,7 +8071,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 200, 342})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8097,7 +8097,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 200, 342})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8123,7 +8123,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 208, 208})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8149,7 +8149,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 304, 304})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8175,7 +8175,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 304, 304})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8201,7 +8201,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 32, 32})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8227,7 +8227,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 35, 35})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8253,7 +8253,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 50, 86})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8279,7 +8279,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8305,7 +8305,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8331,7 +8331,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8357,7 +8357,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 64, 64})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8383,7 +8383,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 73, 73})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8409,7 +8409,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 73, 73})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8435,7 +8435,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 672, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8461,7 +8461,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 672, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8487,7 +8487,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 672, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8513,7 +8513,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 768, 26, 26})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8539,7 +8539,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 8, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8565,7 +8565,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 80, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8591,7 +8591,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 80, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8617,7 +8617,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 96, 1, 1})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8643,7 +8643,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 96, 100, 171})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8669,7 +8669,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 96, 160, 160})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8695,7 +8695,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 96, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8721,7 +8721,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 96, 35, 35})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8747,7 +8747,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 96, 50, 86})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8773,7 +8773,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 96, 75, 75})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8799,7 +8799,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 960, 10, 10})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8825,7 +8825,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 960, 10, 10})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8851,7 +8851,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({100, 1024, 15, 15})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8877,7 +8877,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({100, 1024, 4, 4})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8903,7 +8903,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({100, 1024, 4, 4})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8929,7 +8929,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({100, 1024, 4, 4})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8955,7 +8955,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({100, 1024, 4, 4})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -8981,7 +8981,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({100, 160, 4, 4})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9007,7 +9007,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({100, 192, 4, 4})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9033,7 +9033,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({100, 192, 4, 4})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9059,7 +9059,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({100, 192, 7, 7})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9085,7 +9085,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({100, 224, 4, 4})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9111,7 +9111,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({100, 256, 15, 15})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9137,7 +9137,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({100, 576, 7, 7})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9163,7 +9163,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({100, 576, 7, 7})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9189,7 +9189,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 100, 171})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9215,7 +9215,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 3, 300, 300})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9241,7 +9241,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 3, 640, 640})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9267,7 +9267,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 96, 100, 171})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9293,7 +9293,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({100, 128, 7, 7})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9319,7 +9319,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({100, 256, 7, 7})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9345,7 +9345,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1, 144, 144, 144})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9371,7 +9371,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 18, 18, 18})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9397,7 +9397,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 36, 36, 36})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9423,7 +9423,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 9, 9, 9})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9449,7 +9449,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 16, 144, 144, 144})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9475,7 +9475,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 16, 72, 72, 72})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9501,7 +9501,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 18, 18, 18})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9527,7 +9527,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 9, 9, 9})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9553,7 +9553,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 144, 144, 144})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9579,7 +9579,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 36, 36, 36})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9605,7 +9605,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 72, 72, 72})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9631,7 +9631,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 18, 18, 18})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9657,7 +9657,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 36, 36, 36})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9683,7 +9683,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 72, 72, 72})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9709,7 +9709,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 16, 128, 128})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9735,7 +9735,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 24, 400, 683})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9761,7 +9761,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 149, 149})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9787,7 +9787,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 73, 73})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9813,7 +9813,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 10, 10})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9839,7 +9839,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 10, 10})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9865,7 +9865,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 10, 10})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9891,7 +9891,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9917,7 +9917,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9943,7 +9943,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9969,7 +9969,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -9995,7 +9995,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -10021,7 +10021,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -10047,7 +10047,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 5, 5})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -10073,7 +10073,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 5, 5})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -10099,7 +10099,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 5, 5})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -10125,7 +10125,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 80, 80})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -10151,7 +10151,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 80, 80})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -10177,7 +10177,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 80, 80})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -10203,7 +10203,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1024, 14, 14})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -10229,7 +10229,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 192, 17, 17})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -10255,7 +10255,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 192, 71, 71})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -10281,7 +10281,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 224, 35, 35})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -10307,7 +10307,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 56, 56})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -10333,7 +10333,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 3, 299, 299})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -10359,7 +10359,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 320, 17, 17})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -10385,7 +10385,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 384, 35, 35})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -10411,7 +10411,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 512, 28, 28})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -10437,7 +10437,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 147, 147})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -10463,7 +10463,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 16, 144, 144, 144})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionLayerThresholdTest::getTestCaseName);
 
 // {AUTOGENERATED_TESTS_END_TAG}
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_asym_pad.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_asym_pad.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_asym_pad.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_asym_pad.cpp
index 07883d8c4..801a48734 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_asym_pad.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_asym_pad.cpp
@@ -42,7 +42,7 @@ INSTANTIATE_TEST_CASE_P(smoke_ConvolutionAsymPadCUDA2D_Run,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(inputShapes),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionAsymPadCUDALayerTest::getTestCaseName);
 }  // namespace
 }  // namespace CUDALayerTestsDefinitions
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_backprop_data.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_backprop_data.cpp
similarity index 97%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_backprop_data.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_backprop_data.cpp
index 82eea85c2..557f84aa0 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_backprop_data.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_backprop_data.cpp
@@ -226,7 +226,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_group_0,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input2D_group_0),
                                            ::testing::Values(output2D_group_0),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataLayerTest::getTestCaseName);
 
 // Attributes: {'dilations': '1,1', 'strides': '2,2'}
@@ -242,7 +242,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_group_0,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input2D_group_0),
                                            ::testing::Values(output2D_group_0),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1', 'strides': '2,2'}
@@ -275,7 +275,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_group_1,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input2D_group_1),
                                            ::testing::Values(output2D_group_1),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1', 'strides': '2,2'}
@@ -291,7 +291,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_group_1,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input2D_group_1),
                                            ::testing::Values(output2D_group_1),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1', 'strides': '2,2'}
@@ -324,7 +324,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_group_2,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input2D_group_2),
                                            ::testing::Values(output2D_group_2),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1', 'strides': '2,2'}
@@ -340,7 +340,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_group_2,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input2D_group_2),
                                            ::testing::Values(output2D_group_2),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1', 'strides': '2,2'}
@@ -372,7 +372,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_group_3,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input2D_group_3),
                                            ::testing::Values(output2D_group_3),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1', 'strides': '2,2'}
@@ -388,7 +388,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_group_3,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input2D_group_3),
                                            ::testing::Values(output2D_group_3),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1', 'strides': '2,2'}
@@ -420,7 +420,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_group_4,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input2D_group_4),
                                            ::testing::Values(output2D_group_4),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1', 'strides': '2,2'}
@@ -436,7 +436,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_group_4,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input2D_group_4),
                                            ::testing::Values(output2D_group_4),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 /* ============= ConvolutionBackpropData params (3D) ============= */
@@ -469,7 +469,7 @@ INSTANTIATE_TEST_CASE_P(Convolution3D_group_0,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input3D_group_0),
                                            ::testing::Values(output3D_group_0),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataLayerTest::getTestCaseName);
 
 // Attributes: {'dilations': '1,1,1', 'strides': '2,2,2'}
@@ -485,7 +485,7 @@ INSTANTIATE_TEST_CASE_P(Convolution3D_group_0,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input3D_group_0),
                                            ::testing::Values(output3D_group_0),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1,1', 'strides': '2,2,2'}
@@ -517,7 +517,7 @@ INSTANTIATE_TEST_CASE_P(Convolution3D_group_1,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input3D_group_1),
                                            ::testing::Values(output3D_group_1),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1,1', 'strides': '2,2,2'}
@@ -533,7 +533,7 @@ INSTANTIATE_TEST_CASE_P(Convolution3D_group_1,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input3D_group_1),
                                            ::testing::Values(output3D_group_1),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1,1', 'strides': '2,2,2'}
@@ -565,7 +565,7 @@ INSTANTIATE_TEST_CASE_P(Convolution3D_group_2,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input3D_group_2),
                                            ::testing::Values(output3D_group_2),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1,1', 'strides': '2,2,2'}
@@ -581,7 +581,7 @@ INSTANTIATE_TEST_CASE_P(Convolution3D_group_2,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input3D_group_2),
                                            ::testing::Values(output3D_group_2),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1,1', 'strides': '2,2,2'}
@@ -613,7 +613,7 @@ INSTANTIATE_TEST_CASE_P(Convolution3D_group_3,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input3D_group_3),
                                            ::testing::Values(output3D_group_3),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1,1', 'strides': '2,2,2'}
@@ -629,7 +629,7 @@ INSTANTIATE_TEST_CASE_P(Convolution3D_group_3,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input3D_group_3),
                                            ::testing::Values(output3D_group_3),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1,1', 'strides': '2,2,2'}
@@ -661,7 +661,7 @@ INSTANTIATE_TEST_CASE_P(Convolution3D_group_4,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input3D_group_4),
                                            ::testing::Values(output3D_group_4),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1,1', 'strides': '2,2,2'}
@@ -677,7 +677,7 @@ INSTANTIATE_TEST_CASE_P(Convolution3D_group_4,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input3D_group_4),
                                            ::testing::Values(output3D_group_4),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 // Attributes: {'padbegin': '2,2,2', 'padend': '2,2,2', 'dilations': '1,1,1', 'strides': '2,2,2'}
@@ -709,7 +709,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution3D_group_5,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input3D_group_5),
                                            ::testing::Values(output3D_group_5),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataLayerTest::getTestCaseName);
 
 // Attributes: {'padbegin': '2,2,2', 'padend': '2,2,2', 'dilations': '1,1,1', 'strides': '2,2,2'}
@@ -725,7 +725,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution3D_group_5,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input3D_group_5),
                                            ::testing::Values(output3D_group_5),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1,1', 'strides': '2,2,2'}
@@ -757,7 +757,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution3D_group_6,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input3D_group_6),
                                            ::testing::Values(output3D_group_6),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1,1', 'strides': '2,2,2'}
@@ -773,7 +773,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution3D_group_6,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input3D_group_6),
                                            ::testing::Values(output3D_group_6),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 // =============================================================================
@@ -804,7 +804,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(InferenceEngine::SizeVector {1, 128, 16, 16}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {32, 32}), // Output shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)), // Device name
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)), // Device name
     ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 
@@ -832,7 +832,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(InferenceEngine::SizeVector {1, 256, 8, 8}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {16, 16}), // Output shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)), // Device name
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)), // Device name
     ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 
@@ -860,7 +860,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(InferenceEngine::SizeVector {1, 32, 64, 64}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {128, 128}), // Output shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)), // Device name
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)), // Device name
     ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 
@@ -888,7 +888,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(InferenceEngine::SizeVector {1, 64, 32, 32}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {64, 64}), // Output shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)), // Device name
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)), // Device name
     ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 
@@ -916,7 +916,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(InferenceEngine::SizeVector {64, 128, 7, 7}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {14, 14}), // Output shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)), // Device name
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)), // Device name
     ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 
@@ -944,7 +944,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(InferenceEngine::SizeVector {64, 64, 14, 14}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {28, 28}), // Output shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)), // Device name
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)), // Device name
     ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 
@@ -972,7 +972,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(InferenceEngine::SizeVector {1, 128, 18, 18, 18}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {36, 36, 36}), // Output shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)), // Device name
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)), // Device name
     ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 
@@ -1000,7 +1000,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(InferenceEngine::SizeVector {1, 256, 9, 9, 9}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {18, 18, 18}), // Output shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)), // Device name
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)), // Device name
     ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 
@@ -1028,7 +1028,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(InferenceEngine::SizeVector {1, 32, 72, 72, 72}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {144, 144, 144}), // Output shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)), // Device name
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)), // Device name
     ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 
@@ -1056,7 +1056,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(InferenceEngine::SizeVector {1, 64, 36, 36, 36}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {72, 72, 72}), // Output shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)), // Device name
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)), // Device name
     ConvolutionBackpropDataExtendedLayerTest::getTestCaseName);
 
 // {AUTOGENERATED_TESTS_END_TAG}
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_backprop_data_add.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_backprop_data_add.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_backprop_data_add.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_backprop_data_add.cpp
index fca7ac61d..64fc4c54a 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_backprop_data_add.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_backprop_data_add.cpp
@@ -215,7 +215,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_group_0,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input2D_group_0),
                                            ::testing::Values(output2D_group_0),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataAddExtendedLayerTest::getTestCaseName);
 
 // Attributes: {'auto_pad': 'same_lower', 'dilations': '1,1', 'strides': '2,2'}
@@ -247,7 +247,7 @@ INSTANTIATE_TEST_CASE_P(smoke_Convolution2D_group_1,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(input2D_group_1),
                                            ::testing::Values(output2D_group_1),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         ConvolutionBackpropDataAddExtendedLayerTest::getTestCaseName);
 
 // =============================================================================
@@ -278,7 +278,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::SizeVector {1, 128, 16, 16}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {32, 32}), // Output spatial shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionBackpropDataAddExtendedLayerTest::getTestCaseName);
 
 
@@ -306,7 +306,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::SizeVector {1, 256, 8, 8}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {16, 16}), // Output spatial shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionBackpropDataAddExtendedLayerTest::getTestCaseName);
 
 
@@ -334,7 +334,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::SizeVector {1, 32, 64, 64}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {128, 128}), // Output spatial shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionBackpropDataAddExtendedLayerTest::getTestCaseName);
 
 
@@ -362,7 +362,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::SizeVector {1, 64, 32, 32}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {64, 64}), // Output spatial shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionBackpropDataAddExtendedLayerTest::getTestCaseName);
 
 
@@ -390,7 +390,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::SizeVector {1, 128, 18, 18, 18}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {36, 36, 36}), // Output spatial shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionBackpropDataAddExtendedLayerTest::getTestCaseName);
 
 
@@ -418,7 +418,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::SizeVector {1, 256, 9, 9, 9}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {18, 18, 18}), // Output spatial shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionBackpropDataAddExtendedLayerTest::getTestCaseName);
 
 
@@ -446,7 +446,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::SizeVector {1, 32, 72, 72, 72}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {144, 144, 144}), // Output spatial shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionBackpropDataAddExtendedLayerTest::getTestCaseName);
 
 
@@ -474,7 +474,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::SizeVector {1, 64, 36, 36, 36}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {72, 72, 72}), // Output spatial shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ConvolutionBackpropDataAddExtendedLayerTest::getTestCaseName);
 
 // {AUTOGENERATED_TESTS_END_TAG}
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_biasadd_activation.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_biasadd_activation.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_biasadd_activation.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_biasadd_activation.cpp
index 200ea2a98..78fd12883 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_biasadd_activation.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_biasadd_activation.cpp
@@ -151,7 +151,7 @@ INSTANTIATE_TEST_CASE_P(
                                           ::testing::Values(InferenceEngine::Layout::ANY),
                                           ::testing::Values(InferenceEngine::Layout::ANY),
                                           ::testing::Values(std::vector<size_t>({1, 3, 30, 30})),
-                                          ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                          ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                        ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -165,7 +165,7 @@ INSTANTIATE_TEST_CASE_P(
                                           ::testing::Values(InferenceEngine::Layout::ANY),
                                           ::testing::Values(InferenceEngine::Layout::ANY),
                                           ::testing::Values(std::vector<size_t>({1, 3, 30, 30})),
-                                          ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                          ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                        ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -179,7 +179,7 @@ INSTANTIATE_TEST_CASE_P(
                                           ::testing::Values(InferenceEngine::Layout::ANY),
                                           ::testing::Values(InferenceEngine::Layout::ANY),
                                           ::testing::Values(std::vector<size_t>({1, 3, 30, 30})),
-                                          ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                          ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                        ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -193,7 +193,7 @@ INSTANTIATE_TEST_CASE_P(
                                           ::testing::Values(InferenceEngine::Layout::ANY),
                                           ::testing::Values(InferenceEngine::Layout::ANY),
                                           ::testing::Values(std::vector<size_t>({1, 3, 30, 30})),
-                                          ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                          ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                        ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -207,7 +207,7 @@ INSTANTIATE_TEST_CASE_P(
                                           ::testing::Values(InferenceEngine::Layout::ANY),
                                           ::testing::Values(InferenceEngine::Layout::ANY),
                                           ::testing::Values(std::vector<size_t>({1, 3, 30, 30})),
-                                          ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                          ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                        ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -221,7 +221,7 @@ INSTANTIATE_TEST_CASE_P(
                                           ::testing::Values(InferenceEngine::Layout::ANY),
                                           ::testing::Values(InferenceEngine::Layout::ANY),
                                           ::testing::Values(std::vector<size_t>({1, 3, 30, 30})),
-                                          ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                          ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                        ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -242,7 +242,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 88, 10, 10})),               // Input shape
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::Values(ngraph::helpers::ActivationTypes::None)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -267,7 +267,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 256, 28, 28})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -290,7 +290,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 128, 56, 56})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -313,7 +313,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 512, 14, 14})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -336,7 +336,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 3, 224, 224})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -359,7 +359,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 256, 56, 56})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -382,7 +382,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 1024, 14, 14})),             // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -405,7 +405,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 512, 28, 28})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -428,7 +428,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 256, 14, 14})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -451,7 +451,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 64, 56, 56})),               // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -474,7 +474,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 128, 28, 28})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -497,7 +497,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 256, 14, 14})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -520,7 +520,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 64, 56, 56})),               // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -543,7 +543,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 64, 56, 56})),               // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -566,7 +566,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 256, 56, 56})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -589,7 +589,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 512, 28, 28})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -612,7 +612,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 2048, 7, 7})),               // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -635,7 +635,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 1024, 14, 14})),             // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -658,7 +658,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 512, 7, 7})),                // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -681,7 +681,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 256, 56, 56})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -704,7 +704,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 512, 28, 28})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -727,7 +727,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 512, 7, 7})),                // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -750,7 +750,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 128, 28, 28})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -773,7 +773,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 1024, 14, 14})),             // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -796,7 +796,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 64, 224, 224})),             // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -819,7 +819,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 3, 224, 224})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -842,7 +842,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 128, 56, 56})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -865,7 +865,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 512, 28, 28})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -888,7 +888,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 512, 14, 14})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -911,7 +911,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 256, 28, 28})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -934,7 +934,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 256, 56, 56})),              // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -957,7 +957,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 64, 112, 112})),             // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -980,7 +980,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 128, 112, 112})),            // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1003,7 +1003,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Input layout
                            ::testing::Values(InferenceEngine::Layout::ANY),                       // Output layout
                            ::testing::Values(std::vector<size_t>({1, 128, 112, 112})),            // Input shapes
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(netActivations)),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1012,7 +1012,7 @@ INSTANTIATE_TEST_CASE_P(
 // These tests cover only 2d_unet and 3d_unet
 //
 // WARNING: Currently the fusing of 3D Convolution is disabled in
-// openvino_cuda_plugin/modules/cuda_plugin/src/transformer/fuse_conv_biasadd_activation.cpp
+// openvino_nvidia_gpu_plugin/modules/nvidia_plugin/src/transformer/fuse_conv_biasadd_activation.cpp
 // so the the following tests for 3d_unet run on graphs without FusedConvolution nodes
 //
 // =============================================================================
@@ -1042,7 +1042,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 1, 128, 128})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1070,7 +1070,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 128, 16, 16})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1098,7 +1098,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 128, 32, 32})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1126,7 +1126,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 128, 8, 8})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1154,7 +1154,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 16, 128, 128})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1182,7 +1182,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 16, 64, 64})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1210,7 +1210,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 256, 16, 16})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1238,7 +1238,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 256, 8, 8})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1266,7 +1266,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 32, 128, 128})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1294,7 +1294,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 32, 32, 32})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1322,7 +1322,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 32, 64, 64})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1350,7 +1350,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 64, 16, 16})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1378,7 +1378,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 64, 32, 32})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1406,7 +1406,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 64, 64, 64})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1434,7 +1434,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 1, 144, 144, 144})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1462,7 +1462,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 128, 18, 18, 18})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1490,7 +1490,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 128, 36, 36, 36})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1518,7 +1518,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 128, 9, 9, 9})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1546,7 +1546,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 16, 144, 144, 144})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1574,7 +1574,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 16, 72, 72, 72})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1602,7 +1602,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 256, 18, 18, 18})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1630,7 +1630,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 256, 9, 9, 9})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1658,7 +1658,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 32, 144, 144, 144})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1686,7 +1686,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 32, 36, 36, 36})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1714,7 +1714,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 32, 72, 72, 72})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1742,7 +1742,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 64, 18, 18, 18})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1770,7 +1770,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 64, 36, 36, 36})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1798,7 +1798,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 64, 72, 72, 72})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1826,7 +1826,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 16, 128, 128})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
@@ -1854,7 +1854,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 16, 144, 144, 144})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None,ngraph::helpers::ActivationTypes::Relu})),
     ConvolutionBiasAddActivationLayerFiniteComparerTest::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_biasadd_activation.hpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_biasadd_activation.hpp
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_biasadd_activation.hpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/convolution_biasadd_activation.hpp
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/cuda_eltwise.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/cuda_eltwise.cpp
similarity index 99%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/cuda_eltwise.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/cuda_eltwise.cpp
index 255155166..902cf0e86 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/cuda_eltwise.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/cuda_eltwise.cpp
@@ -103,7 +103,7 @@ void replace(InferenceEngine::Blob::Ptr& blob,
             replace<InferenceEngine::Precision::U64>(blob, old_value, new_value, is_integer);
             break;
         default:
-            CUDAPlugin::throwIEException(fmt::format("replace(): Unsupported type: {}", precision.name()));
+            ov::nvidia_gpu::throwIEException(fmt::format("replace(): Unsupported type: {}", precision.name()));
     }
 }
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/cuda_eltwise.hpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/cuda_eltwise.hpp
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/cuda_eltwise.hpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/cuda_eltwise.hpp
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/detection_output.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/detection_output.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/detection_output.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/detection_output.cpp
index c4966db21..e14244594 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/detection_output.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/detection_output.cpp
@@ -14,7 +14,7 @@ namespace {
 
 template <typename TDataType>
 struct TestDetectionOutputResult {
-    CUDAPlugin::kernel::DetectionOutputResult<TDataType> data;
+    ov::nvidia_gpu::kernel::DetectionOutputResult<TDataType> data;
 
     static float threshold;
 
@@ -203,7 +203,7 @@ const auto params3Inputs = ::testing::Combine(commonAttributes,
                                               ::testing::ValuesIn(specificParams3In),
                                               ::testing::ValuesIn(numberBatch),
                                               ::testing::Values(0.0f),
-                                              ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                              ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_CASE_P(smoke_DetectionOutput3In,
                         CudaDetectionOutputLayerTest,
@@ -227,7 +227,7 @@ const auto params5Inputs = ::testing::Combine(commonAttributes,
                                               ::testing::ValuesIn(specificParams5In),
                                               ::testing::ValuesIn(numberBatch),
                                               ::testing::Values(objectnessScore),
-                                              ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                              ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_CASE_P(smoke_DetectionOutput5In,
                         CudaDetectionOutputLayerTest,
@@ -267,7 +267,7 @@ const auto paramsSSDMobileNetInputs = ::testing::Combine(commonAttributesSSDMobi
                                                          ::testing::ValuesIn(specificParamsSSDMobileNetIn),
                                                          ::testing::ValuesIn(numberBatchSSDMobileNet),
                                                          ::testing::Values(objectnessScoreSSDMobileNet),
-                                                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_CASE_P(DetectionOutputSSDMobileNetIn,
                         CudaDetectionOutputLayerTest,
@@ -307,7 +307,7 @@ const auto paramsEfficientDetInputs = ::testing::Combine(commonAttributesEfficie
                                                          ::testing::ValuesIn(specificParamsEfficientDetIn),
                                                          ::testing::ValuesIn(numberBatchEfficientDet),
                                                          ::testing::Values(objectnessScoreEfficientDet),
-                                                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 // NOTE: Too many elements with similar confidence that leads test to fail
 INSTANTIATE_TEST_CASE_P(DISABLED_DetectionOutputEfficientDetIn,
@@ -332,7 +332,7 @@ const auto paramsEfficientDetInputs = ::testing::Combine(commonAttributesEfficie
                                                          ::testing::ValuesIn(specificParamsEfficientDetIn),
                                                          ::testing::ValuesIn(numberBatchEfficientDet),
                                                          ::testing::Values(objectnessScoreEfficientDet),
-                                                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_CASE_P(DetectionOutputEfficientDetIn,
                         CudaDetectionOutputLayerBenchmarkTest,
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/eltwise_test.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/eltwise_test.cpp
similarity index 99%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/eltwise_test.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/eltwise_test.cpp
index affe54285..ad6217cb9 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/eltwise_test.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/eltwise_test.cpp
@@ -56,7 +56,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::ValuesIn(add_precisions),
                            ::testing::Values(ov::test::ElementType::undefined),
                            ::testing::Values(ov::test::ElementType::undefined),
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                            ::testing::Values(additional_config)),
         ::testing::Values(OperationMode::NORMAL)),
     CudaEltwiseLayerTest::getTestCaseName);
@@ -75,7 +75,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::ValuesIn(mul_precisions),
                            ::testing::Values(ov::test::ElementType::undefined),
                            ::testing::Values(ov::test::ElementType::undefined),
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                            ::testing::Values(additional_config)),
         ::testing::Values(OperationMode::NORMAL)),
     CudaEltwiseLayerTest::getTestCaseName);
@@ -94,7 +94,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::ValuesIn(sub_precisions),
                            ::testing::Values(ov::test::ElementType::undefined),
                            ::testing::Values(ov::test::ElementType::undefined),
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                            ::testing::Values(additional_config)),
         ::testing::Values(OperationMode::NORMAL)),
     CudaEltwiseLayerTest::getTestCaseName);
@@ -113,7 +113,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::ValuesIn(div_precisions),
                            ::testing::Values(ov::test::ElementType::undefined),
                            ::testing::Values(ov::test::ElementType::undefined),
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                            ::testing::Values(additional_config)),
         ::testing::ValuesIn({OperationMode::NORMAL, OperationMode::PYTHON_DIVIDE})),
     CudaEltwiseLayerTest::getTestCaseName);
@@ -135,7 +135,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::ValuesIn(sq_diff_precisions),
                            ::testing::Values(ov::test::ElementType::undefined),
                            ::testing::Values(ov::test::ElementType::undefined),
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                            ::testing::Values(additional_config)),
         ::testing::Values(OperationMode::NORMAL)),
     CudaEltwiseLayerTest::getTestCaseName);
@@ -154,7 +154,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::ValuesIn(floor_mod_precisions),
                            ::testing::Values(ov::test::ElementType::undefined),
                            ::testing::Values(ov::test::ElementType::undefined),
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                            ::testing::Values(additional_config)),
         ::testing::Values(OperationMode::NORMAL)),
     CudaEltwiseLayerTest::getTestCaseName);
@@ -178,7 +178,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::ValuesIn(mod_precisions),
                            ::testing::Values(ov::test::ElementType::undefined),
                            ::testing::Values(ov::test::ElementType::undefined),
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                            ::testing::Values(additional_config)),
         ::testing::Values(OperationMode::NORMAL)),
     CudaEltwiseLayerTest::getTestCaseName);
@@ -225,7 +225,7 @@ INSTANTIATE_TEST_CASE_P(
                                           ::testing::ValuesIn(renset50_vgg16_input_precisions),
                                           ::testing::Values(ov::test::ElementType::undefined),
                                           ::testing::Values(ov::test::ElementType::undefined),
-                                          ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                          ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                           ::testing::Values(additional_config)),
                        ::testing::Values(OperationMode::NORMAL)),
     CudaEltwiseLayerTest::getTestCaseName);
@@ -256,7 +256,7 @@ INSTANTIATE_TEST_CASE_P(
                                           ::testing::ValuesIn(tacotron2_Multiply_input_precisions),
                                           ::testing::Values(ov::test::ElementType::undefined),
                                           ::testing::Values(ov::test::ElementType::undefined),
-                                          ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                          ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                           ::testing::Values(additional_config)),
                        ::testing::Values(OperationMode::NORMAL)),
     CudaEltwiseLayerTest::getTestCaseName);
@@ -299,7 +299,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::ValuesIn(bench_add_precisions),
                            ::testing::Values(ov::test::ElementType::undefined),
                            ::testing::Values(ov::test::ElementType::undefined),
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                            ::testing::Values(additional_config)),
         ::testing::Values(OperationMode::NORMAL)),
     CudaEltwiseLayerTest::getTestCaseName);
@@ -328,7 +328,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::ValuesIn(bench_mul_precisions),
                            ::testing::Values(ov::test::ElementType::undefined),
                            ::testing::Values(ov::test::ElementType::undefined),
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                            ::testing::Values(additional_config)),
         ::testing::Values(OperationMode::NORMAL)),
     CudaEltwiseLayerTest::getTestCaseName);
@@ -357,7 +357,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::ValuesIn(bench_sub_precisions),
                            ::testing::Values(ov::test::ElementType::undefined),
                            ::testing::Values(ov::test::ElementType::undefined),
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                            ::testing::Values(additional_config)),
         ::testing::Values(OperationMode::NORMAL)),
     CudaEltwiseLayerTest::getTestCaseName);
@@ -386,7 +386,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::ValuesIn(bench_div_precisions),
                            ::testing::Values(ov::test::ElementType::undefined),
                            ::testing::Values(ov::test::ElementType::undefined),
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                            ::testing::Values(additional_config)),
         ::testing::ValuesIn({OperationMode::NORMAL, OperationMode::PYTHON_DIVIDE})),
     CudaEltwiseLayerTest::getTestCaseName);
@@ -420,7 +420,7 @@ INSTANTIATE_TEST_CASE_P(
                            ::testing::ValuesIn(bench_mod_precisions),
                            ::testing::Values(ov::test::ElementType::undefined),
                            ::testing::Values(ov::test::ElementType::undefined),
-                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                            ::testing::Values(additional_config)),
         ::testing::Values(OperationMode::NORMAL)),
     CudaEltwiseLayerTest::getTestCaseName);
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/fake_quantize.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/fake_quantize.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/fake_quantize.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/fake_quantize.cpp
index 493e37e39..27311a927 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/fake_quantize.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/fake_quantize.cpp
@@ -50,7 +50,7 @@ INSTANTIATE_TEST_CASE_P(smoke_CUDAFakeQuantize,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(inputShapes),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(config)),
                         FakeQuantizeLayerTest::getTestCaseName);
 
@@ -71,7 +71,7 @@ INSTANTIATE_TEST_CASE_P(smoke_CUDAFakeQuantizeBr,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(inputShapesBr),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(config)),
                         FakeQuantizeLayerTest::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/finite_comparer.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/finite_comparer.cpp
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/finite_comparer.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/finite_comparer.cpp
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/finite_comparer.hpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/finite_comparer.hpp
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/finite_comparer.hpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/finite_comparer.hpp
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/fully_connected.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/fully_connected.cpp
similarity index 99%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/fully_connected.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/fully_connected.cpp
index e98124eba..04ea3f557 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/fully_connected.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/fully_connected.cpp
@@ -295,7 +295,7 @@ INSTANTIATE_TEST_CASE_P(smoke_MatMulFP16,
                                            ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(secondaryInputTypes),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(additional_config)),
                         FullyConnectedLayerTest::getTestCaseName);
 
@@ -307,7 +307,7 @@ INSTANTIATE_TEST_CASE_P(MatMul_Resnet50FP16,
                                            ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(secondaryInputTypes),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(additional_config)),
                         FullyConnectedLayerTest::getTestCaseName);
 
@@ -319,7 +319,7 @@ INSTANTIATE_TEST_CASE_P(MatMul_VGG16FP16,
                                            ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(secondaryInputTypes),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(additional_config)),
                         FullyConnectedLayerTest::getTestCaseName);
 
@@ -331,7 +331,7 @@ INSTANTIATE_TEST_CASE_P(MatMul_Tacatron2,
                                            ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(secondaryInputTypes),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(additional_config)),
                         FullyConnectedLayer2MatMulTest::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/gather.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/gather.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/gather.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/gather.cpp
index cc3eaf264..9e241cf37 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/gather.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/gather.cpp
@@ -73,7 +73,7 @@ struct GatherTestParams {
     InferenceEngine::Precision output_precision_ = InferenceEngine::Precision::UNSPECIFIED;
     InferenceEngine::Layout input_layout_ = InferenceEngine::Layout::ANY;
     InferenceEngine::Layout output_layout_ = InferenceEngine::Layout::ANY;
-    LayerTestsUtils::TargetDevice device_ = CommonTestUtils::DEVICE_CUDA;
+    LayerTestsUtils::TargetDevice device_ = CommonTestUtils::DEVICE_NVIDIA;
 };
 
 template <typename T>
@@ -85,7 +85,7 @@ std::vector<T> generate_indices(const GatherTestParams& test_params) {
     const auto axis = test_params.axis_;
     const unsigned normalized_axis = axis >= 0 ? axis : axis + params_shape_size;
     if (normalized_axis >= params_shape_size) {
-        CUDAPlugin::throwIEException(
+        ov::nvidia_gpu::throwIEException(
             fmt::format("normalized_axis >= params_shape_size: {} >= {}", normalized_axis, params_shape_size));
     }
     std::uniform_int_distribution<T> distr(0, test_params.params_shape_[normalized_axis] - 1);
@@ -638,9 +638,9 @@ void test_one_shape(const GatherTestParams& params, bool is_v7) {
     constexpr int NUM_ATTEMPTS = 20;
     constexpr milliseconds WARMUP_TIME{2000.0};
 
-    CUDAPlugin::ThreadContext threadContext{{}};
+    ov::nvidia_gpu::ThreadContext threadContext{{}};
     int out_size = 0;
-    CUDAPlugin::OperationBase::Ptr operation = [&] {
+    ov::nvidia_gpu::OperationBase::Ptr operation = [&] {
         const bool optimizeOption = false;
         auto dict_param = std::make_shared<ov::op::v0::Parameter>(ov::element::from<ElementType>(),
                                                                   ov::PartialShape{params.params_shape_});
@@ -654,11 +654,11 @@ void test_one_shape(const GatherTestParams& params, bool is_v7) {
                                 dict_param->output(0), indices_param->output(0), axis_constant));
 
         out_size = ov::shape_size(node->get_output_shape(0));
-        auto& registry = CUDAPlugin::OperationRegistry::getInstance();
-        auto op = registry.createOperation(CUDAPlugin::CreationContext{threadContext.device(), optimizeOption},
+        auto& registry = ov::nvidia_gpu::OperationRegistry::getInstance();
+        auto op = registry.createOperation(ov::nvidia_gpu::CreationContext{threadContext.device(), optimizeOption},
                                            node,
-                                           std::array{CUDAPlugin::TensorID{0}},
-                                           std::array{CUDAPlugin::TensorID{0}});
+                                           std::array{ov::nvidia_gpu::TensorID{0}},
+                                           std::array{ov::nvidia_gpu::TensorID{0}});
         return op;
     }();
     const int dict_size = ov::shape_size(params.params_shape_);
@@ -673,12 +673,12 @@ void test_one_shape(const GatherTestParams& params, bool is_v7) {
     std::vector<cdevptr_t> inputs{dict_alloc, indices_alloc, axis_alloc};
     std::vector<devptr_t> outputs{out_alloc};
 
-    CUDAPlugin::CancellationToken token{};
-    CUDAPlugin::CudaGraph graph{CUDAPlugin::CreationContext{CUDA::Device{}, false}, {}};
-    CUDAPlugin::Profiler profiler{false, graph};
+    ov::nvidia_gpu::CancellationToken token{};
+    ov::nvidia_gpu::CudaGraph graph{ov::nvidia_gpu::CreationContext{CUDA::Device{}, false}, {}};
+    ov::nvidia_gpu::Profiler profiler{false, graph};
     std::vector<std::shared_ptr<ngraph::runtime::Tensor>> emptyTensor;
     std::map<std::string, std::size_t> emptyMapping;
-    CUDAPlugin::InferenceRequestContext context{
+    ov::nvidia_gpu::InferenceRequestContext context{
         emptyTensor, emptyMapping, emptyTensor, emptyMapping, threadContext, token, profiler};
     std::vector<IndicesType> indices = generate_indices<IndicesType>(params);
     std::vector<ElementType> dict(dict_size);
@@ -694,7 +694,7 @@ void test_one_shape(const GatherTestParams& params, bool is_v7) {
     auto& stream = context.getThreadContext().stream();
     stream.upload(dict_alloc, dict.data(), dict_size_bytes);
     stream.upload(indices_alloc, indices.data(), indices_size_bytes);
-    CUDAPlugin::Workbuffers workbuffers{};
+    ov::nvidia_gpu::Workbuffers workbuffers{};
 
     // Warmup
     auto warm_cur = std::chrono::steady_clock::now();
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/README b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/README
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/README
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/README
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/cfg_disabled_tests.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/cfg_disabled_tests.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/cfg_disabled_tests.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/cfg_disabled_tests.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/cfg_overridden_precisions.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/cfg_overridden_precisions.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/cfg_overridden_precisions.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/cfg_overridden_precisions.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/cfg_overridden_test_classes.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/cfg_overridden_test_classes.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/cfg_overridden_test_classes.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/cfg_overridden_test_classes.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ir_model.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ir_model.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ir_model.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ir_model.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ir_op_preprocessing.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ir_op_preprocessing.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ir_op_preprocessing.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ir_op_preprocessing.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/main.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/main.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/main.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/main.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/avgpool.cpp.jinja2 b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/avgpool.cpp.jinja2
similarity index 95%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/avgpool.cpp.jinja2
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/avgpool.cpp.jinja2
index c188a9d3f..ec3d99e24 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/avgpool.cpp.jinja2
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/avgpool.cpp.jinja2
@@ -20,7 +20,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{{op.cpp_list_input}}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     {{op.cpp_test_class_name}}::getTestCaseName);
 
 {% endfor -%}
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/avgpool.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/avgpool.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/avgpool.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/avgpool.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/clamp.cpp.jinja2 b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/clamp.cpp.jinja2
similarity index 94%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/clamp.cpp.jinja2
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/clamp.cpp.jinja2
index 052c0f89a..86da945bf 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/clamp.cpp.jinja2
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/clamp.cpp.jinja2
@@ -16,7 +16,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values({{op.cpp_params_name}}.second),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     {{op.cpp_test_class_name}}::getTestCaseName);
 
 {% endfor -%}
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/clamp.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/clamp.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/clamp.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/clamp.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution.cpp.jinja2 b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution.cpp.jinja2
similarity index 95%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution.cpp.jinja2
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution.cpp.jinja2
index f567db654..b7497c9cc 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution.cpp.jinja2
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution.cpp.jinja2
@@ -18,7 +18,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({{op.cpp_list_input}})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     {{op.cpp_test_class_name}}::getTestCaseName);
 
 {% endfor -%}
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data.cpp.jinja2 b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data.cpp.jinja2
similarity index 95%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data.cpp.jinja2
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data.cpp.jinja2
index 7442646df..3577944e8 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data.cpp.jinja2
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data.cpp.jinja2
@@ -21,7 +21,7 @@ INSTANTIATE_TEST_CASE_P(
 {%- if op.has_outputshape_input %}
         ::testing::Values(InferenceEngine::SizeVector {{op.cpp_list_output_shape}}), // Output shape
 {%- endif %}
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)), // Device name
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)), // Device name
     {{op.cpp_test_class_name}}::getTestCaseName);
 
 {% endfor -%}
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data_add.cpp.jinja2 b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data_add.cpp.jinja2
similarity index 96%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data_add.cpp.jinja2
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data_add.cpp.jinja2
index ebd864230..394641514 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data_add.cpp.jinja2
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data_add.cpp.jinja2
@@ -19,7 +19,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::SizeVector {{op.cpp_list_input_shape}}), // Input shape
         ::testing::Values(InferenceEngine::SizeVector {{op.cpp_list_output_shape}}), // Output spatial shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     {{op.cpp_test_class_name}}::getTestCaseName);
 
 {% endfor -%}
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data_add.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data_add.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data_add.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_backprop_data_add.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_biasadd_activation.cpp.jinja2 b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_biasadd_activation.cpp.jinja2
similarity index 96%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_biasadd_activation.cpp.jinja2
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_biasadd_activation.cpp.jinja2
index 2fc2d4f39..8dd67108a 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_biasadd_activation.cpp.jinja2
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_biasadd_activation.cpp.jinja2
@@ -19,7 +19,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({{op.cpp_list_input}})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{{op.cpp_activations}})),
     {{op.cpp_test_class_name}}::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_biasadd_activation.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_biasadd_activation.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_biasadd_activation.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/convolution_biasadd_activation.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution.cpp.jinja2 b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution.cpp.jinja2
similarity index 96%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution.cpp.jinja2
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution.cpp.jinja2
index ee10d697c..39812b4fe 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution.cpp.jinja2
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution.cpp.jinja2
@@ -19,7 +19,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({{op.cpp_list_input}})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     {{op.cpp_test_class_name}}::getTestCaseName);
 
 {% endfor -%}
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution_biasadd_activation.cpp.jinja2 b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution_biasadd_activation.cpp.jinja2
similarity index 96%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution_biasadd_activation.cpp.jinja2
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution_biasadd_activation.cpp.jinja2
index 703efebb2..53927c69b 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution_biasadd_activation.cpp.jinja2
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution_biasadd_activation.cpp.jinja2
@@ -20,7 +20,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({{op.cpp_list_input}})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{{op.cpp_activations}})),
     {{op.cpp_test_class_name}}::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution_biasadd_activation.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution_biasadd_activation.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution_biasadd_activation.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/group_convolution_biasadd_activation.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/mat_mul.cpp.jinja2 b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/mat_mul.cpp.jinja2
similarity index 92%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/mat_mul.cpp.jinja2
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/mat_mul.cpp.jinja2
index 2039f791e..e91ef45b2 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/mat_mul.cpp.jinja2
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/mat_mul.cpp.jinja2
@@ -10,7 +10,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn({{op.cpp_secondary_input_types}}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values({{op.cpp_additional_config}})), // additional config
     {{op.cpp_test_class_name}}::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/mat_mul.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/mat_mul.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/mat_mul.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/mat_mul.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/maxpool.cpp.jinja2 b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/maxpool.cpp.jinja2
similarity index 95%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/maxpool.cpp.jinja2
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/maxpool.cpp.jinja2
index 4532e0b43..a9d0b6250 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/maxpool.cpp.jinja2
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/maxpool.cpp.jinja2
@@ -20,7 +20,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{{op.cpp_list_input}}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     {{op.cpp_test_class_name}}::getTestCaseName);
 
 {% endfor -%}
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/maxpool.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/maxpool.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/maxpool.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/maxpool.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/relu.cpp.jinja2 b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/relu.cpp.jinja2
similarity index 92%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/relu.cpp.jinja2
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/relu.cpp.jinja2
index e3e20f00d..9c0a53bfc 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/relu.cpp.jinja2
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/relu.cpp.jinja2
@@ -11,7 +11,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values({{op.cpp_shape}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     {{op.cpp_test_class_name}}::getTestCaseName);
 
 {% endfor -%}
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/relu.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/relu.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/relu.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/relu.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/sigmoid.cpp.jinja2 b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/sigmoid.cpp.jinja2
similarity index 92%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/sigmoid.cpp.jinja2
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/sigmoid.cpp.jinja2
index 67c58ab97..ec01a489a 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/sigmoid.cpp.jinja2
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/sigmoid.cpp.jinja2
@@ -11,7 +11,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values({{op.cpp_shape}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     {{op.cpp_test_class_name}}::getTestCaseName);
 
 {% endfor -%}
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/sigmoid.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/sigmoid.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/sigmoid.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/sigmoid.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/swish.cpp.jinja2 b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/swish.cpp.jinja2
similarity index 93%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/swish.cpp.jinja2
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/swish.cpp.jinja2
index 1ab2c349a..91fef8c50 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/swish.cpp.jinja2
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/swish.cpp.jinja2
@@ -14,7 +14,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values({{op.cpp_shape}}),
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     {{op.cpp_test_class_name}}::getTestCaseName);
 
 {% endfor -%}
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/swish.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/swish.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/swish.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/ops/swish.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/requirements.txt b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/requirements.txt
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/requirements.txt
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/requirements.txt
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/test_definition_base.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/test_definition_base.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/test_definition_base.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/test_definition_base.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/utils.py b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/utils.py
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/utils.py
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/generator/utils.py
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution.cpp
index 045a8ec5b..0ca14e57b 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution.cpp
@@ -46,7 +46,7 @@ INSTANTIATE_TEST_CASE_P(smoke_GroupConvolutionCUDA2D_Run,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(inputShapes),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         GroupConvolutionCUDALayerTest::getTestCaseName);
 }  // namespace
 }  // namespace CUDALayerTestsDefinitions
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_autogenerated.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_autogenerated.cpp
similarity index 96%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_autogenerated.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_autogenerated.cpp
index 0b9e2daa7..28ec87091 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_autogenerated.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_autogenerated.cpp
@@ -68,7 +68,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 144, 75, 75})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -95,7 +95,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 192, 38, 38})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -122,7 +122,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 150, 150})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -149,7 +149,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 384, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -176,7 +176,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 576, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -203,7 +203,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 960, 10, 10})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -230,7 +230,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 3, 3})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -257,7 +257,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 128, 5, 5})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -284,7 +284,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 144, 75, 75})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -311,7 +311,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 192, 38, 38})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -338,7 +338,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 256, 10, 10})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -365,7 +365,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 576, 19, 19})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -392,7 +392,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 64, 2, 2})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -419,7 +419,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 96, 150, 150})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -446,7 +446,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1152, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -473,7 +473,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1152, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -500,7 +500,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 144, 160, 160})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -527,7 +527,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 16, 320, 320})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -554,7 +554,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 1920, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -581,7 +581,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 240, 80, 80})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -608,7 +608,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 32, 320, 320})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -635,7 +635,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 480, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -662,7 +662,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 480, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -689,7 +689,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 672, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -716,7 +716,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 10, 10})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -743,7 +743,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 20, 20})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -770,7 +770,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -797,7 +797,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 5, 5})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -824,7 +824,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 88, 80, 80})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -851,7 +851,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 144, 160, 160})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -878,7 +878,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 240, 80, 80})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -905,7 +905,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 672, 40, 40})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 
@@ -932,7 +932,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
         ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
         ::testing::Values(std::vector<size_t>({1, 96, 320, 320})), // Input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GroupConvolutionLayerThresholdTest::getTestCaseName);
 
 // {AUTOGENERATED_TESTS_END_TAG}
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_backprop_data.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_backprop_data.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_backprop_data.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_backprop_data.cpp
index 29471ff25..34eb98f19 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_backprop_data.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_backprop_data.cpp
@@ -60,7 +60,7 @@ INSTANTIATE_TEST_CASE_P(smoke_GroupConvolutionBackprop2D_ExplicitPadding,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(inputShapes2D),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         GroupConvBackpropDataLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_GroupConvolutionBackprop2D_AutoPadding,
@@ -72,7 +72,7 @@ INSTANTIATE_TEST_CASE_P(smoke_GroupConvolutionBackprop2D_AutoPadding,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(inputShapes2D),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         GroupConvBackpropDataLayerTest::getTestCaseName);
 
 /* ============= 3D GroupConvolution ============= */
@@ -111,7 +111,7 @@ INSTANTIATE_TEST_CASE_P(smoke_GroupConvolutionBackprop3D_ExpicitPadding,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(inputShapes3D),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         GroupConvBackpropDataLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_GroupConvolutionBackprop3D_AutoPadding,
@@ -123,7 +123,7 @@ INSTANTIATE_TEST_CASE_P(smoke_GroupConvolutionBackprop3D_AutoPadding,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(inputShapes3D),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         GroupConvBackpropDataLayerTest::getTestCaseName);
 
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_biasadd_activation.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_biasadd_activation.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_biasadd_activation.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_biasadd_activation.cpp
index 7b0cda692..6d3f71b5d 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_biasadd_activation.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_biasadd_activation.cpp
@@ -65,7 +65,7 @@ const auto smoke_1D_AutoPadValid_Params =
                                           ::testing::Values(InferenceEngine::Layout::ANY),
                                           ::testing::Values(InferenceEngine::Layout::ANY),
                                           ::testing::Values(std::vector<size_t>({5, 8, 30})),
-                                          ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                          ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                        ::testing::ValuesIn(netActivations));
 
 const auto smoke_1D_ExplicitPaddingAsymmetric_Params = ::testing::Combine(
@@ -83,7 +83,7 @@ const auto smoke_1D_ExplicitPaddingAsymmetric_Params = ::testing::Combine(
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::Values(std::vector<size_t>({2, 16, 15})),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ::testing::ValuesIn(netActivations));
 
 INSTANTIATE_TEST_CASE_P(smoke_GroupConvolutionBiasAdd_1D_AutoPadValid_Params,
@@ -128,7 +128,7 @@ const auto smoke_2D_ExplicitPaddingSymmetric_Params = ::testing::Combine(
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::Values(std::vector<size_t>({2, 16, 12, 6})),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ::testing::ValuesIn(netActivations));
 
 const auto smoke_2D_ExplicitPaddingAsymmetric_Params = ::testing::Combine(
@@ -146,7 +146,7 @@ const auto smoke_2D_ExplicitPaddingAsymmetric_Params = ::testing::Combine(
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::Values(std::vector<size_t>({3, 8, 21, 11})),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ::testing::ValuesIn(netActivations));
 
 INSTANTIATE_TEST_CASE_P(smoke_GroupConvolutionBiasAdd_2D_ExplicitPaddingSymmetric,
@@ -170,7 +170,7 @@ INSTANTIATE_TEST_CASE_P(smoke_GroupConvolutionBiasAddAdd_smoke_2D_ExplicitPaddin
                         GroupConvolutionBiasAddAddActivationLayerTest::getTestCaseName);
 
 // WARNING: Currently the fusing of 3D Convolution is disabled in
-// openvino_cuda_plugin/modules/cuda_plugin/src/transformer/fuse_conv_biasadd_activation.cpp
+// openvino_nvidia_gpu_plugin/modules/nvidia_plugin/src/transformer/fuse_conv_biasadd_activation.cpp
 // so the the following smoke tests on graphs without FusedConvolution nodes
 //
 /* ============= 3D Convolution ============= */
@@ -195,7 +195,7 @@ const auto smoke_3D_ExplicitPaddingSymmetric_Params = ::testing::Combine(
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::Values(std::vector<size_t>({1, 6, 9, 12, 10})),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ::testing::ValuesIn(netActivations));
 
 const auto smoke_3D_ExplicitPaddingAsymmetric_Params = ::testing::Combine(
@@ -213,7 +213,7 @@ const auto smoke_3D_ExplicitPaddingAsymmetric_Params = ::testing::Combine(
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::Values(std::vector<size_t>({2, 6, 12, 15, 20})),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     ::testing::ValuesIn(netActivations));
 
 INSTANTIATE_TEST_CASE_P(smoke_GroupConvolutionBiasAdd_3D_ExplicitPaddingSymmetric,
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_biasadd_activation_autogenerated.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_biasadd_activation_autogenerated.cpp
similarity index 96%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_biasadd_activation_autogenerated.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_biasadd_activation_autogenerated.cpp
index 254838eb5..a90c47f51 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_biasadd_activation_autogenerated.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/group_convolution_biasadd_activation_autogenerated.cpp
@@ -44,7 +44,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 144, 163, 163})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -73,7 +73,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 192, 39, 39})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -102,7 +102,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 240, 81, 81})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -131,7 +131,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 256, 11, 11})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -160,7 +160,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 64, 3, 3})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -189,7 +189,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 672, 43, 43})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -218,7 +218,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 96, 151, 151})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -247,7 +247,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 96, 321, 321})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -276,7 +276,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 1152, 20, 20})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -305,7 +305,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 144, 160, 160})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -334,7 +334,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 144, 75, 75})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -363,7 +363,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 16, 320, 320})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -392,7 +392,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 192, 38, 38})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -421,7 +421,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 1920, 20, 20})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -450,7 +450,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 32, 150, 150})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -479,7 +479,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 32, 320, 320})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -508,7 +508,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 384, 19, 19})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -537,7 +537,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 480, 40, 40})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -566,7 +566,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 576, 19, 19})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -595,7 +595,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 960, 10, 10})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -624,7 +624,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 128, 3, 3})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -653,7 +653,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 128, 5, 5})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -682,7 +682,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 144, 75, 75})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -711,7 +711,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 576, 19, 19})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -740,7 +740,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 1152, 20, 20})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -769,7 +769,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 240, 80, 80})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -798,7 +798,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 480, 40, 40})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
@@ -827,7 +827,7 @@ INSTANTIATE_TEST_CASE_P(
             ::testing::Values(InferenceEngine::Layout::ANY), // Input layout
             ::testing::Values(InferenceEngine::Layout::ANY), // Output layout
             ::testing::Values(std::vector<size_t>({1, 672, 40, 40})), // Input shape
-            ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+            ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
         ::testing::ValuesIn(std::vector<ngraph::helpers::ActivationTypes>{ngraph::helpers::ActivationTypes::None})),
     GroupConvolutionBiasAddActivationLayerTest::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/gru_cell.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/gru_cell.cpp
similarity index 97%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/gru_cell.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/gru_cell.cpp
index ccab4e110..4cbcd7dd1 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/gru_cell.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/gru_cell.cpp
@@ -82,7 +82,7 @@ INSTANTIATE_TEST_CASE_P(smoke_GRUCellCommon_01,
                                            ::testing::ValuesIn(clips),
                                            ::testing::ValuesIn(linear_before_reset),
                                            ::testing::ValuesIn(net_precisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         GRUCellTest::getTestCaseName);
 
 const size_t smoke_batch_02 = 9;
@@ -99,7 +99,7 @@ INSTANTIATE_TEST_CASE_P(smoke_GRUCellCommon_02_FP32,
                                            ::testing::ValuesIn(clips),
                                            ::testing::ValuesIn(linear_before_reset),
                                            ::testing::Values(InferenceEngine::Precision::FP32),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         GRUCellTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_GRUCellCommon_02_FP16,
@@ -112,7 +112,7 @@ INSTANTIATE_TEST_CASE_P(smoke_GRUCellCommon_02_FP16,
                                            ::testing::ValuesIn(clips),
                                            ::testing::ValuesIn(linear_before_reset),
                                            ::testing::Values(InferenceEngine::Precision::FP16),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         GRUCellTest::getTestCaseName);
 
 // ------------- LPCNet shapes -------------
@@ -130,7 +130,7 @@ INSTANTIATE_TEST_CASE_P(GRUCell_LPCNet,
                                            ::testing::ValuesIn(clips),
                                            ::testing::ValuesIn(linear_before_reset),
                                            ::testing::ValuesIn(net_precisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         GRUCellTest::getTestCaseName);
 
 }  // namespace
@@ -144,7 +144,7 @@ const auto benchmark_params = ::testing::Combine(::testing::Values(should_decomp
                                                  ::testing::Values(clips[0]),
                                                  ::testing::Values(linear_before_reset[0]),
                                                  ::testing::Values(net_precisions[0]),
-                                                 ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                                 ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 namespace benchmark {
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/gru_sequence.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/gru_sequence.cpp
similarity index 99%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/gru_sequence.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/gru_sequence.cpp
index c078699f3..665abeb64 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/gru_sequence.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/gru_sequence.cpp
@@ -169,7 +169,7 @@ INSTANTIATE_TEST_CASE_P(
                        ::testing::ValuesIn(linear_before_reset),
                        ::testing::ValuesIn(direction),
                        ::testing::ValuesIn(netPrecisions),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GRUSequenceTest::getTestCaseName);
 
 // ------------- Smoke test -------------
@@ -189,7 +189,7 @@ INSTANTIATE_TEST_CASE_P(
                        ::testing::ValuesIn(linear_before_reset),
                        ::testing::ValuesIn(direction),
                        ::testing::ValuesIn(netPrecisions),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     GRUSequenceTest::getTestCaseName);
 
 // -------------  LPCNet shapes  -------------
@@ -208,7 +208,7 @@ INSTANTIATE_TEST_CASE_P(LPCNetCUDNNGRUSequenceShapeTest,
                                            ::testing::ValuesIn(linear_before_reset),
                                            ::testing::ValuesIn(direction),
                                            ::testing::ValuesIn(netPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         GRUSequenceTest::getTestCaseName);
 
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/interpolate.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/interpolate.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/interpolate.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/interpolate.cpp
index c4d9ca66c..1946b8e9a 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/interpolate.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/interpolate.cpp
@@ -147,7 +147,7 @@ const auto simpleCombine4DScaleParamTests =
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::ValuesIn(inShapes),
                        ::testing::ValuesIn(targetShapes),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                        ::testing::Values(additional_config));
 
 INSTANTIATE_TEST_CASE_P(smoke_Simple_Interpolate_Nearest_4D_Scale_Param_Test,
@@ -164,7 +164,7 @@ const auto simpleCombine2DScaleParamTests =
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::ValuesIn(inShapes),
                        ::testing::ValuesIn(targetShapes),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                        ::testing::Values(additional_config));
 
 INSTANTIATE_TEST_CASE_P(smoke_Simple_Interpolate_Nearest_2D_Scale_Param_Test,
@@ -180,7 +180,7 @@ const auto downscaleCombineTests = ::testing::Combine(interpolate4DScaleParams,
                                                       ::testing::Values(InferenceEngine::Layout::ANY),
                                                       ::testing::ValuesIn(downscaleInShapes),
                                                       ::testing::ValuesIn(downscaleTargetShapes),
-                                                      ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                                      ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                                       ::testing::Values(additional_config));
 INSTANTIATE_TEST_CASE_P(smoke_Downscale_Interpolate_Nearest_Test,
                         CUDAInterpolateLayerTest,
@@ -199,7 +199,7 @@ const auto highResolutionCombineTest =
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::ValuesIn(std::vector<std::vector<size_t>>{{1, 88, 20, 20}}),
                        ::testing::ValuesIn(std::vector<std::vector<size_t>>{{1, 88, 40, 40}}),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                        ::testing::Values(additional_config));
 
 INSTANTIATE_TEST_CASE_P(smoke_High_Resolution_Interpolate_Nearest_4D_Scale_Param_Test,
@@ -215,7 +215,7 @@ const auto efficientdetCombinations = ::testing::Combine(interpolate4DScaleParam
                                                          ::testing::Values(InferenceEngine::Layout::ANY),
                                                          ::testing::ValuesIn(efficientdetShapes),
                                                          ::testing::ValuesIn(efficientdetShapes),
-                                                         ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                                          ::testing::Values(additional_config));
 INSTANTIATE_TEST_CASE_P(efficientdetInterpolateCombinationTests,
                         CUDAInterpolateLayerTest,
@@ -231,7 +231,7 @@ const auto yolov5InterpolateFrom20To40Shape =
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::ValuesIn(yolov5From20To40Shape),
                        ::testing::ValuesIn(yolov5From20To40Shape),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                        ::testing::Values(additional_config));
 INSTANTIATE_TEST_CASE_P(yolov5InterpolateFrom20To40ShapeTests,
                         CUDAInterpolateLayerTest,
@@ -247,7 +247,7 @@ const auto yolov5InterpolateFrom40To80Shape =
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::ValuesIn(yolov5From40To80Shape),
                        ::testing::ValuesIn(yolov5From40To80Shape),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                        ::testing::Values(additional_config));
 INSTANTIATE_TEST_CASE_P(yolov5InterpolateFrom40To80ShapeTests,
                         CUDAInterpolateLayerTest,
@@ -293,7 +293,7 @@ INSTANTIATE_TEST_CASE_P(smoke_InterpolateLinear_2D_Scale_Test,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(linearInput2DScaleShapes),
                                            ::testing::ValuesIn(linearTest2DSizes),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(additional_config)),
                         InterpolateLayerTest::getTestCaseName);
 
@@ -321,7 +321,7 @@ INSTANTIATE_TEST_CASE_P(smoke_InterpolateLinear_3D_Scale_Test,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(linearInput3DScaleShapes),
                                            ::testing::ValuesIn(linearTest3DSizes),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(additional_config)),
                         InterpolateLayerTest::getTestCaseName);
 
@@ -367,7 +367,7 @@ INSTANTIATE_TEST_CASE_P(smoke_InterpolateCubic_2D_Scale_Test,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(cubicInput2DScaleShapes),
                                            ::testing::ValuesIn(cubicTest2DSizes),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(additional_config)),
                         InterpolateLayerTest::getTestCaseName);
 
@@ -395,7 +395,7 @@ INSTANTIATE_TEST_CASE_P(smoke_InterpolateCubic_3D_Scale_Test,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(cubicInput3DScaleShapes),
                                            ::testing::ValuesIn(cubicTest3DSizes),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(additional_config)),
                         InterpolateLayerTest::getTestCaseName);
 
@@ -417,7 +417,7 @@ const auto nearestBenchmarkParams =
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::ValuesIn(std::vector<std::vector<size_t>>{{1, 88, 40, 40}}),
                        ::testing::ValuesIn(std::vector<std::vector<size_t>>{{1, 88, 80, 80}}),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                        ::testing::Values(additional_config));
 
 INSTANTIATE_TEST_CASE_P(CUDAInterpolate_Nearest_Benchmark,
@@ -449,7 +449,7 @@ const auto benchmarkParams =
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::Values(std::vector<size_t>{1, 3, 50, 50, 50}),  // input data shape
                        ::testing::Values(std::vector<size_t>{0, 0, 0}),           // sizes, not used
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                        ::testing::Values(additional_config));
 
 INSTANTIATE_TEST_CASE_P(CUDAInterpolate_Benchmark,
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/logical_test.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/logical_test.cpp
similarity index 99%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/logical_test.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/logical_test.cpp
index 80f932a52..afc48715f 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/logical_test.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/logical_test.cpp
@@ -37,7 +37,7 @@ const auto LogicalTestParamsNot =
                        ::testing::Values(InferenceEngine::Precision::BOOL),
                        ::testing::Values(InferenceEngine::Layout::ANY),
                        ::testing::Values(InferenceEngine::Layout::ANY),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                        ::testing::Values(additional_config));
 
 INSTANTIATE_TEST_CASE_P(smoke_LogicalNot, LogicalLayerTest, LogicalTestParamsNot, LogicalLayerTest::getTestCaseName);
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/lstm_cell.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/lstm_cell.cpp
similarity index 93%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/lstm_cell.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/lstm_cell.cpp
index d896d4c30..df6f0240c 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/lstm_cell.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/lstm_cell.cpp
@@ -70,7 +70,7 @@ INSTANTIATE_TEST_CASE_P(smoke_LSTMCell_01,
                                            ::testing::Values(activations),
                                            ::testing::ValuesIn(smoke_clip),
                                            ::testing::ValuesIn(netPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         CUDNNLSTMCellTest::getTestCaseName);
 
 const std::vector<size_t> smoke_input_sizes_02{2, 3, 30};
@@ -85,7 +85,7 @@ INSTANTIATE_TEST_CASE_P(smoke_LSTMCell_02,
                                            ::testing::Values(activations),
                                            ::testing::ValuesIn(smoke_clip),
                                            ::testing::ValuesIn(netPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         CUDNNLSTMCellTest::getTestCaseName);
 
 // ------------- Other shapes -------------
@@ -108,7 +108,7 @@ INSTANTIATE_TEST_CASE_P(LSTMCell_Tacotron2_dec_01,
                                            ::testing::Values(activations),
                                            ::testing::Values(tacotron2_dec_01.clip),
                                            ::testing::ValuesIn(netPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         CUDNNLSTMCellTest::getTestCaseName);
 
 LSTMCellTestParams tacotron2_dec_02{1, 1536, 1024, 0.0f};
@@ -122,7 +122,7 @@ INSTANTIATE_TEST_CASE_P(LSTMCell_Tacotron2_dec_02,
                                            ::testing::Values(activations),
                                            ::testing::Values(tacotron2_dec_02.clip),
                                            ::testing::ValuesIn(netPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         CUDNNLSTMCellTest::getTestCaseName);
 
 LSTMCellTestParams tacotron2_enc_01{1, 512, 256, 0.0f};
@@ -136,7 +136,7 @@ INSTANTIATE_TEST_CASE_P(LSTMCell_Tacotron2_enc_01,
                                            ::testing::Values(activations),
                                            ::testing::Values(tacotron2_enc_01.clip),
                                            ::testing::ValuesIn(netPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         CUDNNLSTMCellTest::getTestCaseName);
 
 // ------------- Big shapes -------------
@@ -151,7 +151,7 @@ INSTANTIATE_TEST_CASE_P(LSTMCell_OV_Doc_01,
                                            ::testing::Values(activations),
                                            ::testing::Values(ov_doc_01.clip),
                                            ::testing::ValuesIn(netPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         CUDNNLSTMCellTest::getTestCaseName);
 
 LSTMCellTestParams big_01{10, 2048, 2048, 0.0f};
@@ -165,7 +165,7 @@ INSTANTIATE_TEST_CASE_P(LSTMCell_Big_01,
                                            ::testing::Values(activations),
                                            ::testing::Values(big_01.clip),
                                            ::testing::ValuesIn(netPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         CUDNNLSTMCellTest::getTestCaseName);
 
 LSTMCellTestParams big_02{1, 8192, 4096, 0.0f};
@@ -179,7 +179,7 @@ INSTANTIATE_TEST_CASE_P(LSTMCell_Big_02,
                                            ::testing::Values(activations),
                                            ::testing::Values(big_02.clip),
                                            ::testing::ValuesIn(netPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         CUDNNLSTMCellTest::getTestCaseName);
 
 LSTMCellTestParams big_03{3, 1781, 5003, 0.0f};
@@ -193,7 +193,7 @@ INSTANTIATE_TEST_CASE_P(LSTMCell_Big_03,
                                            ::testing::Values(activations),
                                            ::testing::Values(big_03.clip),
                                            ::testing::ValuesIn(netPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         CUDNNLSTMCellTest::getTestCaseName);
 
 // ------------- Benchmark -------------
@@ -220,7 +220,7 @@ void testOneShape(const LSTMCellTestParams& params) {
     const auto ho_size = params.batch * params.hidden_size;
     const auto co_size = params.batch * params.hidden_size;
 
-    CUDAPlugin::ThreadContext threadContext{{}};
+    ov::nvidia_gpu::ThreadContext threadContext{{}};
 
     CUDA::Allocation x_alloc{threadContext.stream().malloc(x_size * sizeof(ElementType))};
     CUDA::Allocation hi_alloc{threadContext.stream().malloc(hi_size * sizeof(ElementType))};
@@ -235,10 +235,10 @@ void testOneShape(const LSTMCellTestParams& params) {
 
     std::vector<std::shared_ptr<ngraph::runtime::Tensor>> emptyTensor;
     std::map<std::string, std::size_t> emptyMapping;
-    CUDAPlugin::CudaGraph graph{CUDAPlugin::CreationContext{CUDA::Device{}, false}, {}};
-    CUDAPlugin::CancellationToken token{};
-    CUDAPlugin::Profiler profiler{false, graph};
-    CUDAPlugin::InferenceRequestContext context{
+    ov::nvidia_gpu::CudaGraph graph{ov::nvidia_gpu::CreationContext{CUDA::Device{}, false}, {}};
+    ov::nvidia_gpu::CancellationToken token{};
+    ov::nvidia_gpu::Profiler profiler{false, graph};
+    ov::nvidia_gpu::InferenceRequestContext context{
         emptyTensor, emptyMapping, emptyTensor, emptyMapping, threadContext, token, profiler};
     std::vector<ElementType> x_host(x_size);
     std::vector<ElementType> hi_host(hi_size);
@@ -280,7 +280,7 @@ void testOneShape(const LSTMCellTestParams& params) {
         std::make_shared<ov::op::v0::Constant>(type, ov::Shape({4 * params.hidden_size, params.hidden_size}), r_host);
     auto b_constant = std::make_shared<ov::op::v0::Constant>(type, ov::Shape({4 * params.hidden_size}), b_host);
 
-    CUDAPlugin::OperationBase::Ptr operation = [&] {
+    ov::nvidia_gpu::OperationBase::Ptr operation = [&] {
         const bool optimizeOption = false;
 
         auto x_param = std::make_shared<ov::op::v0::Parameter>(type, ov::Shape{params.batch, params.input_size});
@@ -297,15 +297,15 @@ void testOneShape(const LSTMCellTestParams& params) {
         Ensures(ho_size == ov::shape_size(node->get_output_shape(0)));
         Ensures(co_size == ov::shape_size(node->get_output_shape(1)));
 
-        auto& registry = CUDAPlugin::OperationRegistry::getInstance();
-        auto op = registry.createOperation(CUDAPlugin::CreationContext{threadContext.device(), optimizeOption},
+        auto& registry = ov::nvidia_gpu::OperationRegistry::getInstance();
+        auto op = registry.createOperation(ov::nvidia_gpu::CreationContext{threadContext.device(), optimizeOption},
                                            node,
-                                           std::array{CUDAPlugin::TensorID{0}},
-                                           std::array{CUDAPlugin::TensorID{0}});
+                                           std::array{ov::nvidia_gpu::TensorID{0}},
+                                           std::array{ov::nvidia_gpu::TensorID{0}});
         return op;
     }();
 
-    CUDAPlugin::WorkbufferRequest wb_request{operation->GetWorkBufferRequest()};
+    ov::nvidia_gpu::WorkbufferRequest wb_request{operation->GetWorkBufferRequest()};
     Ensures(wb_request.immutable_sizes.size() != 0);
     Ensures(wb_request.mutable_sizes.size() != 0);
 
@@ -319,14 +319,14 @@ void testOneShape(const LSTMCellTestParams& params) {
     auto y_alloc = CUDA::DefaultStream::stream().malloc(y_size_bytes);
     auto work_space_alloc = CUDA::DefaultStream::stream().malloc(work_space_size);
 
-    CUDAPlugin::IOperationExec::Buffers init_buffers;
+    ov::nvidia_gpu::IOperationExec::Buffers init_buffers;
     init_buffers.emplace_back(DevPtr{sla_alloc.get()});
     if (weight_space_size != 0) {
         init_buffers.emplace_back(DevPtr{weight_space_alloc.get()});
     }
     operation->InitSharedImmutableWorkbuffers(init_buffers);
 
-    CUDAPlugin::Workbuffers workbuffers{};
+    ov::nvidia_gpu::Workbuffers workbuffers{};
     workbuffers.immutable_buffers.emplace_back(CDevPtr{sla_alloc.get()});
     if (weight_space_size != 0) {
         workbuffers.immutable_buffers.emplace_back(CDevPtr{weight_space_alloc.get()});
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/lstm_sequence.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/lstm_sequence.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/lstm_sequence.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/lstm_sequence.cpp
index 0dc94198e..77794b838 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/lstm_sequence.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/lstm_sequence.cpp
@@ -76,7 +76,7 @@ INSTANTIATE_TEST_CASE_P(smoke_LSTMSequence_01,
                                            ::testing::Values(no_clip),
                                            ::testing::ValuesIn(sequenceDirections),
                                            ::testing::ValuesIn(netPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         CUDALSTMSequenceTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_LSTMSequence_02,
@@ -90,7 +90,7 @@ INSTANTIATE_TEST_CASE_P(smoke_LSTMSequence_02,
                                            ::testing::Values(no_clip),
                                            ::testing::ValuesIn(sequenceDirections),
                                            ::testing::ValuesIn(netPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         CUDALSTMSequenceTest::getTestCaseName);
 
 // ------------- Tacotron2 Tests -------------
@@ -106,7 +106,7 @@ INSTANTIATE_TEST_CASE_P(LSTMSequence_Tacotron2_decoder_01,
                                            ::testing::Values(no_clip),  // clip
                                            ::testing::Values(ov::op::RecurrentSequenceDirection::FORWARD),
                                            ::testing::ValuesIn(netPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         CUDALSTMSequenceTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(LSTMSequence_Tacotron2_decoder_02,
@@ -120,7 +120,7 @@ INSTANTIATE_TEST_CASE_P(LSTMSequence_Tacotron2_decoder_02,
                                            ::testing::Values(no_clip),  // clip
                                            ::testing::Values(ov::op::RecurrentSequenceDirection::FORWARD),
                                            ::testing::ValuesIn(netPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         CUDALSTMSequenceTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(LSTMSequence_Tacotron2_encoder_01,
@@ -134,7 +134,7 @@ INSTANTIATE_TEST_CASE_P(LSTMSequence_Tacotron2_encoder_01,
                                            ::testing::Values(no_clip),  // clip
                                            ::testing::Values(ov::op::RecurrentSequenceDirection::BIDIRECTIONAL),
                                            ::testing::ValuesIn(netPrecisions),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         CUDALSTMSequenceTest::getTestCaseName);
 
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/mat_mul.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/mat_mul.cpp
similarity index 95%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/mat_mul.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/mat_mul.cpp
index ec0f8c4b0..0ab697735 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/mat_mul.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/mat_mul.cpp
@@ -123,7 +123,7 @@ INSTANTIATE_TEST_CASE_P(smoke_MatMul,
                                            ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(secondaryInputTypes),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(additional_config)),
                         MatMulLayerTest::getTestCaseName);
 
@@ -135,7 +135,7 @@ INSTANTIATE_TEST_CASE_P(MatMul_Resnet50,
                                            ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(secondaryInputTypes),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(additional_config)),
                         MatMulLayerTest::getTestCaseName);
 
@@ -147,7 +147,7 @@ INSTANTIATE_TEST_CASE_P(MatMul_VGG16,
                                            ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(secondaryInputTypes),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(additional_config)),
                         MatMulLayerTest::getTestCaseName);
 
@@ -169,7 +169,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -188,7 +188,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -207,7 +207,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -226,7 +226,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -245,7 +245,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -264,7 +264,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -283,7 +283,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -302,7 +302,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -321,7 +321,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -340,7 +340,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -359,7 +359,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -378,7 +378,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -397,7 +397,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -416,7 +416,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -435,7 +435,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -454,7 +454,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -473,7 +473,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -492,7 +492,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -511,7 +511,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -530,7 +530,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
@@ -549,7 +549,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::ValuesIn(std::vector<ngraph::helpers::InputLayerType> {ngraph::helpers::InputLayerType::CONSTANT, ngraph::helpers::InputLayerType::PARAMETER}), // secondary input types
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
         ::testing::Values(std::map<std::string, std::string> {})), // additional config
     MatMulLayerTest::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/minimum_maximum.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/minimum_maximum.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/minimum_maximum.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/minimum_maximum.cpp
index 362842517..3bb0d0058 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/minimum_maximum.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/minimum_maximum.cpp
@@ -46,7 +46,7 @@ INSTANTIATE_TEST_CASE_P(smoke_MaxMin,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(inputType),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         MaxMinLayerTest::getTestCaseName);
 
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/mvn.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/mvn.cpp
similarity index 97%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/mvn.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/mvn.cpp
index 5f52550bd..728f8101d 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/mvn.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/mvn.cpp
@@ -54,7 +54,7 @@ const auto MvnCases = ::testing::Combine(::testing::ValuesIn(inputShapes),
                                          ::testing::ValuesIn(acrossChannels),
                                          ::testing::ValuesIn(normalizeVariance),
                                          ::testing::ValuesIn(epsilon),
-                                         ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                         ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_CASE_P(smoke_CUDA_TestsMVN, Mvn1LayerTest, MvnCases, Mvn1LayerTest::getTestCaseName);
 
@@ -79,7 +79,7 @@ INSTANTIATE_TEST_CASE_P(smoke_CUDA_MVN_5D,
                                            ::testing::ValuesIn(normalizeVariance),
                                            ::testing::ValuesIn(epsilonF),
                                            ::testing::ValuesIn(epsMode),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         Mvn6_4DPreprocessLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(
@@ -92,7 +92,7 @@ INSTANTIATE_TEST_CASE_P(
                        ::testing::ValuesIn(normalizeVariance),
                        ::testing::ValuesIn(epsilonF),
                        ::testing::ValuesIn(epsMode),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     Mvn6_4DPreprocessLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(
@@ -105,7 +105,7 @@ INSTANTIATE_TEST_CASE_P(
                        ::testing::ValuesIn(normalizeVariance),
                        ::testing::ValuesIn(epsilonF),
                        ::testing::ValuesIn(epsMode),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     Mvn6_4DPreprocessLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_CUDA_MVN_2D,
@@ -117,7 +117,7 @@ INSTANTIATE_TEST_CASE_P(smoke_CUDA_MVN_2D,
                                            ::testing::ValuesIn(normalizeVariance),
                                            ::testing::ValuesIn(epsilonF),
                                            ::testing::ValuesIn(epsMode),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         Mvn6_4DPreprocessLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_CUDA_MVN_1D,
@@ -129,7 +129,7 @@ INSTANTIATE_TEST_CASE_P(smoke_CUDA_MVN_1D,
                                            ::testing::ValuesIn(normalizeVariance),
                                            ::testing::ValuesIn(epsilonF),
                                            ::testing::ValuesIn(epsMode),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         Mvn6_4DPreprocessLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_CUDA_Decomposition_3D,
@@ -142,7 +142,7 @@ INSTANTIATE_TEST_CASE_P(smoke_CUDA_Decomposition_3D,
                                            ::testing::ValuesIn(normalizeVariance),
                                            ::testing::ValuesIn(epsilonF),
                                            ::testing::ValuesIn(epsMode),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         Mvn6_4DPreprocessLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(smoke_CUDA_Decomposition_4D,
@@ -156,7 +156,7 @@ INSTANTIATE_TEST_CASE_P(smoke_CUDA_Decomposition_4D,
                                            ::testing::ValuesIn(normalizeVariance),
                                            ::testing::ValuesIn(epsilonF),
                                            ::testing::ValuesIn(epsMode),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         Mvn6_4DPreprocessLayerTest::getTestCaseName);
 
 // TODO: uncomment this when implementation for higher rang tensor will be supported, current CUDNN implementation
@@ -172,6 +172,6 @@ INSTANTIATE_TEST_CASE_P(smoke_CUDA_Decomposition_4D,
 //                                           ::testing::ValuesIn(normalizeVariance),
 //                                           ::testing::ValuesIn(epsilonF),
 //                                           ::testing::ValuesIn(epsMode),
-//                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+//                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
 //                        Mvn6_4DPreprocessLayerTest::getTestCaseName);
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/pad_test.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/pad_test.cpp
similarity index 97%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/pad_test.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/pad_test.cpp
index e063b75d0..895be572d 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/pad_test.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/pad_test.cpp
@@ -51,7 +51,7 @@ const auto pad1DConstparams = testing::Combine(testing::ValuesIn(padsBegin1D),
                                                testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                                testing::Values(InferenceEngine::Layout::ANY),
                                                testing::ValuesIn(inputs1d),
-                                               testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                               testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_CASE_P(smoke_Pad1DConst, PadLayerTest, pad1DConstparams, PadLayerTest::getTestCaseName);
 
@@ -67,7 +67,7 @@ const auto pad2DConstparams = testing::Combine(testing::ValuesIn(padsBegin2D),
                                                testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                                testing::Values(InferenceEngine::Layout::ANY),
                                                testing::Values(std::vector<size_t>{3, 512}),
-                                               testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                               testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_CASE_P(smoke_Pad2DConst, PadLayerTest, pad2DConstparams, PadLayerTest::getTestCaseName);
 
@@ -83,7 +83,7 @@ const auto pad3DConstparams = testing::Combine(testing::ValuesIn(padsBegin3D),
                                                testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                                testing::Values(InferenceEngine::Layout::ANY),
                                                testing::Values(std::vector<size_t>{3, 5, 11}),
-                                               testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                               testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_CASE_P(smoke_Pad3DConst, PadLayerTest, pad3DConstparams, PadLayerTest::getTestCaseName);
 
@@ -99,7 +99,7 @@ const auto pad4DConstparams = testing::Combine(testing::ValuesIn(padsBegin4D),
                                                testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                                testing::Values(InferenceEngine::Layout::ANY),
                                                testing::Values(std::vector<size_t>{3, 5, 10, 512}),
-                                               testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                               testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_CASE_P(smoke_Pad4DConst, PadLayerTest, pad4DConstparams, PadLayerTest::getTestCaseName);
 
@@ -115,7 +115,7 @@ const auto pad5DConstparams = testing::Combine(testing::ValuesIn(padsBegin5D),
                                                testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                                testing::Values(InferenceEngine::Layout::ANY),
                                                testing::Values(std::vector<size_t>{7, 3, 5, 10, 512}),
-                                               testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                               testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_CASE_P(smoke_Pad5DConst, PadLayerTest, pad5DConstparams, PadLayerTest::getTestCaseName);
 
@@ -128,7 +128,7 @@ const auto padPrecesionParams = testing::Combine(testing::ValuesIn(padsBegin2D),
                                                  testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                                  testing::Values(InferenceEngine::Layout::ANY),
                                                  testing::Values(std::vector<size_t>{3, 128}),
-                                                 testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                                 testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_CASE_P(smoke_PadPrecesionParams, PadLayerTest, padPrecesionParams, PadLayerTest::getTestCaseName);
 
@@ -151,7 +151,7 @@ const auto pad4DBenchmarkParams =
                      testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                      testing::Values(InferenceEngine::Layout::ANY),
                      testing::ValuesIn(benchmarkShapes),
-                     testing::Values(CommonTestUtils::DEVICE_CUDA));
+                     testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_CASE_P(Benchmark4DPadOperation,
                         NCHWFormatPadBenchmarkTest,
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/pooling.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/pooling.cpp
similarity index 96%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/pooling.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/pooling.cpp
index 0a8919ae0..4e74e3737 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/pooling.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/pooling.cpp
@@ -47,7 +47,7 @@ INSTANTIATE_TEST_CASE_P(smoke_MaxPool_ExplicitPad_FloorRounding,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 50, 50})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         PoolingLayerTest::getTestCaseName);
 
 /* ========== Explicit Pad Ceil Rounding ========== */
@@ -74,7 +74,7 @@ INSTANTIATE_TEST_CASE_P(smoke_MaxPool_ExplicitPad_CeilRounding,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 50, 50})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         PoolingLayerTest::getTestCaseName);
 
 ////* ========== Avg Pooling ========== */
@@ -100,7 +100,7 @@ INSTANTIATE_TEST_CASE_P(smoke_AvgPool_ExplicitPad_CeilRounding,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 30, 30})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         PoolingLayerTest::getTestCaseName);
 
 /* +========== Explicit Pad Floor Rounding ========== */
@@ -122,7 +122,7 @@ INSTANTIATE_TEST_CASE_P(smoke_AvgPool_ExplicitPad_FloorRounding,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 30, 30})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         PoolingLayerTest::getTestCaseName);
 
 ////* ========== Avg and Max Pooling Cases ========== */
@@ -150,7 +150,7 @@ INSTANTIATE_TEST_CASE_P(smoke_MAX_and_AVGPool_ValidPad,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({1, 3, 50, 50})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         PoolingLayerTest::getTestCaseName);
 
 // =============================================================================
@@ -181,7 +181,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 256, 20, 20}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -209,7 +209,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 128, 112, 112}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -237,7 +237,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 256, 56, 56}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -265,7 +265,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 512, 14, 14}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -293,7 +293,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 512, 28, 28}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -321,7 +321,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 64, 224, 224}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -349,7 +349,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 128, 56, 56}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -377,7 +377,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 256, 28, 28}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -405,7 +405,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 64, 113, 113}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -433,7 +433,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 64, 112, 112}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -461,7 +461,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 256, 20, 20}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -489,7 +489,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 256, 20, 20}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -517,7 +517,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 512, 19, 19}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -545,7 +545,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{100, 1024, 4, 4}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -573,7 +573,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 192, 200, 342}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -601,7 +601,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 320, 100, 171}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -629,7 +629,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 64, 112, 112}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -657,7 +657,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 64, 400, 683}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -685,7 +685,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 88, 10, 10}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -713,7 +713,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 88, 20, 20}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -741,7 +741,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 88, 40, 40}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -769,7 +769,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 88, 80, 80}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -797,7 +797,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{100, 576, 7, 7}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -825,7 +825,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 512, 19, 19}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -853,7 +853,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 512, 19, 19}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -881,7 +881,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 128, 16, 16}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -909,7 +909,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 16, 128, 128}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -937,7 +937,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 32, 64, 64}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -965,7 +965,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 64, 32, 32}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -993,7 +993,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{100, 576, 14, 14}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -1021,7 +1021,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 128, 18, 18, 18}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -1049,7 +1049,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 16, 144, 144, 144}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -1077,7 +1077,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 32, 72, 72, 72}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -1105,7 +1105,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 64, 36, 36, 36}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -1133,7 +1133,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 1024, 17, 17}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -1161,7 +1161,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 192, 71, 71}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -1189,7 +1189,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 384, 35, 35}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -1217,7 +1217,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 64, 147, 147}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 // {AUTOGENERATED_TESTS_END_TAG_MAXPOOL}
@@ -1252,7 +1252,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 2048, 7, 7}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -1280,7 +1280,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 1024, 17, 17}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -1308,7 +1308,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 1536, 8, 8}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -1336,7 +1336,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 192, 100, 171}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -1364,7 +1364,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 256, 100, 171}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -1392,7 +1392,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 384, 35, 35}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -1420,7 +1420,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 576, 50, 86}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -1448,7 +1448,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{100, 1024, 4, 4}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 
@@ -1476,7 +1476,7 @@ INSTANTIATE_TEST_CASE_P(
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(InferenceEngine::Layout::ANY),
         ::testing::Values(std::vector<size_t>{1, 1536, 8, 8}), // input shape
-        ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+        ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     PoolingLayerTest::getTestCaseName);
 
 // {AUTOGENERATED_TESTS_END_TAG_AVGPOOL}
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/power.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/power.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/power.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/power.cpp
index a34a5f000..378e71957 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/power.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/power.cpp
@@ -50,7 +50,7 @@ INSTANTIATE_TEST_CASE_P(smoke_powerCuda,
                                            ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::ValuesIn(Power)),
                         PowerLayerTest::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/range.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/range.cpp
similarity index 93%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/range.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/range.cpp
index 6a9c63767..11fd9d2e9 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/range.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/range.cpp
@@ -35,7 +35,7 @@ typedef std::tuple<dataType,  // start
     CudaRangeParams;
 
 struct CudaRangeLayerTest : public testing::WithParamInterface<CudaRangeParams>, virtual public ::testing::Test {
-    using TensorID = CUDAPlugin::TensorID;
+    using TensorID = ov::nvidia_gpu::TensorID;
     CudaRangeParams param = GetParam();
     dataType start = std::get<0>(param);
     dataType stop = std::get<1>(param);
@@ -44,7 +44,7 @@ struct CudaRangeLayerTest : public testing::WithParamInterface<CudaRangeParams>,
     Type_t step_type = std::get<4>(param);
     Type_t out_type = std::get<5>(param);
     size_t outputSize = computeRangeOutputSize(start, stop, step, start_type, step_type, out_type);
-    CUDAPlugin::ThreadContext threadContext{{}};
+    ov::nvidia_gpu::ThreadContext threadContext{{}};
     CUDA::Allocation startParamAlloc = threadContext.stream().malloc(Type(start_type).size());
     CUDA::Allocation stopParamAlloc = threadContext.stream().malloc(sizeof(dataType));
     CUDA::Allocation stepParamAlloc = threadContext.stream().malloc(Type(step_type).size());
@@ -52,7 +52,7 @@ struct CudaRangeLayerTest : public testing::WithParamInterface<CudaRangeParams>,
     std::vector<cdevptr_t> inputs = {startParamAlloc, stopParamAlloc, stepParamAlloc};
     std::vector<devptr_t> outputs{outAlloc};
     InferenceEngine::BlobMap empty;
-    CUDAPlugin::OperationBase::Ptr operation = createOperation();
+    ov::nvidia_gpu::OperationBase::Ptr operation = createOperation();
 
     static std::string getTestCaseName(testing::TestParamInfo<CudaRangeParams> obj) {
         dataType start, stop, step;
@@ -113,9 +113,9 @@ struct CudaRangeLayerTest : public testing::WithParamInterface<CudaRangeParams>,
         return ref;
     }
 
-    template <CUDAPlugin::kernel::Type_t T>
+    template <ov::nvidia_gpu::kernel::Type_t T>
     static void upload(const CUDA::Stream& stream, CUDA::Allocation& dst, const dataType* src, size_t size) {
-        using TOutput = CUDAPlugin::kernel::cuda_type_traits_t<T>;
+        using TOutput = ov::nvidia_gpu::kernel::cuda_type_traits_t<T>;
         std::vector<TOutput> data;
         data.reserve(size);
         for (size_t c = 0; c < size; ++c) {
@@ -126,7 +126,7 @@ struct CudaRangeLayerTest : public testing::WithParamInterface<CudaRangeParams>,
 
     static void upload(
         const CUDA::Stream& stream, CUDA::Allocation& dst, const dataType* src, Type_t type, size_t size) {
-        using Type_k = CUDAPlugin::kernel::Type_t;
+        using Type_k = ov::nvidia_gpu::kernel::Type_t;
         switch (type) {
 #if defined __CUDACC__
 #ifdef CUDA_HAS_BF16_TYPE
@@ -163,9 +163,9 @@ struct CudaRangeLayerTest : public testing::WithParamInterface<CudaRangeParams>,
         }
     }
 
-    template <CUDAPlugin::kernel::Type_t T>
+    template <ov::nvidia_gpu::kernel::Type_t T>
     static void download(const CUDA::Stream& stream, dataType* dst, devptr_t src, size_t size) {
-        using TOutput = CUDAPlugin::kernel::cuda_type_traits_t<T>;
+        using TOutput = ov::nvidia_gpu::kernel::cuda_type_traits_t<T>;
         std::vector<TOutput> data;
         data.resize(size);
         stream.download(&data[0], src, size * sizeof(TOutput));
@@ -176,7 +176,7 @@ struct CudaRangeLayerTest : public testing::WithParamInterface<CudaRangeParams>,
     }
 
     static void download(const CUDA::Stream& stream, dataType* dst, devptr_t src, Type_t type, size_t size) {
-        using Type_k = CUDAPlugin::kernel::Type_t;
+        using Type_k = ov::nvidia_gpu::kernel::Type_t;
         switch (type) {
 #if defined __CUDACC__
 #ifdef CUDA_HAS_BF16_TYPE
@@ -214,7 +214,7 @@ struct CudaRangeLayerTest : public testing::WithParamInterface<CudaRangeParams>,
     }
 
 protected:
-    CUDAPlugin::OperationBase::Ptr createOperation() {
+    ov::nvidia_gpu::OperationBase::Ptr createOperation() {
         using namespace ngraph;
         CUDA::Device device{};
         const bool optimizeOption = false;
@@ -226,9 +226,9 @@ struct CudaRangeLayerTest : public testing::WithParamInterface<CudaRangeParams>,
         params[1]->set_friendly_name("stop");
         params[2]->set_friendly_name("step");
         auto node = std::make_shared<opset4::Range>(params[0], params[1], params[2], Type(out_type));
-        auto& registry = CUDAPlugin::OperationRegistry::getInstance();
+        auto& registry = ov::nvidia_gpu::OperationRegistry::getInstance();
         assert(registry.hasOperation(node));
-        auto op = registry.createOperation(CUDAPlugin::CreationContext{device, optimizeOption},
+        auto op = registry.createOperation(ov::nvidia_gpu::CreationContext{device, optimizeOption},
                                            node,
                                            std::vector<TensorID>{TensorID{0}, TensorID{1}, TensorID{2}},
                                            std::vector<TensorID>{TensorID{0u}});
@@ -249,12 +249,12 @@ MATCHER_P(FloatNearPointwise, tol, "Out of range") {
 
 TEST_P(CudaRangeLayerTest, CompareWithRefs) {
     ASSERT_TRUE(outputSize > 0);
-    CUDAPlugin::CancellationToken token{};
-    CUDAPlugin::CudaGraph graph{CUDAPlugin::CreationContext{CUDA::Device{}, false}, {}};
-    CUDAPlugin::Profiler profiler{false, graph};
+    ov::nvidia_gpu::CancellationToken token{};
+    ov::nvidia_gpu::CudaGraph graph{ov::nvidia_gpu::CreationContext{CUDA::Device{}, false}, {}};
+    ov::nvidia_gpu::Profiler profiler{false, graph};
     std::vector<std::shared_ptr<ngraph::runtime::Tensor>> emptyTensor;
     std::map<std::string, std::size_t> emptyMapping;
-    CUDAPlugin::InferenceRequestContext context{
+    ov::nvidia_gpu::InferenceRequestContext context{
         emptyTensor, emptyMapping, emptyTensor, emptyMapping, threadContext, token, profiler};
     auto& stream = context.getThreadContext().stream();
     CudaRangeLayerTest::upload(stream, startParamAlloc, &start, start_type, 1);
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/reshape.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/reshape.cpp
similarity index 97%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/reshape.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/reshape.cpp
index 7c24f9467..eae9b03c7 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/reshape.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/reshape.cpp
@@ -26,7 +26,7 @@ INSTANTIATE_TEST_CASE_P(ReshapeCheckDynBatch,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({30, 30, 30, 30})),
                                            ::testing::Values(std::vector<int64_t>({30, 30, 30, 30})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(std::map<std::string, std::string>({}))),
                         ReshapeLayerTest::getTestCaseName);
 
@@ -40,7 +40,7 @@ INSTANTIATE_TEST_CASE_P(ReshapeCheck,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({10, 10, 10, 10})),
                                            ::testing::Values(std::vector<int64_t>({10, 0, 100})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(std::map<std::string, std::string>({}))),
                         ReshapeLayerTest::getTestCaseName);
 }  // namespace
\ No newline at end of file
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/scatter_nd_update.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/scatter_nd_update.cpp
similarity index 99%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/scatter_nd_update.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/scatter_nd_update.cpp
index d14bd551f..07a62594e 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/scatter_nd_update.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/scatter_nd_update.cpp
@@ -143,7 +143,7 @@ INSTANTIATE_TEST_CASE_P(
     ::testing::Combine(::testing::ValuesIn(CudaScatterNDUpdateLayerTest::combineShapes(smoke_shapes)),
                        ::testing::ValuesIn(inputPrecisions),
                        ::testing::ValuesIn(idxPrecisions),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     CudaScatterNDUpdateLayerTest::getTestCaseName);
 
 // map<inputShape map<indicesShape, emptyIndicesValue>>
@@ -167,7 +167,7 @@ INSTANTIATE_TEST_CASE_P(
     ::testing::Combine(::testing::ValuesIn(CudaScatterNDUpdateLayerTest::combineShapes(smoke_shapes_index_generation)),
                        ::testing::ValuesIn(inputPrecisions),
                        ::testing::ValuesIn(idxPrecisions),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     CudaScatterNDUpdateLayerTest::getTestCaseName);
 
 // yolov5b6 shapes
@@ -182,7 +182,7 @@ INSTANTIATE_TEST_CASE_P(
     ::testing::Combine(::testing::ValuesIn(CudaScatterNDUpdateLayerTest::combineShapes(yolov5b6_shapes)),
                        ::testing::ValuesIn(inputPrecisions),
                        ::testing::ValuesIn(idxPrecisions),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     CudaScatterNDUpdateLayerTest::getTestCaseName);
 
 namespace benchmark {
@@ -206,7 +206,7 @@ INSTANTIATE_TEST_CASE_P(
     ::testing::Combine(::testing::ValuesIn(CudaScatterNDUpdateLayerTest::combineShapes(benchmark_shapes)),
                        ::testing::Values(InferenceEngine::Precision::FP32),
                        ::testing::Values(InferenceEngine::Precision::I64),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     CudaScatterNDUpdateLayerTest::getTestCaseName);
 }  // namespace benchmark
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/select.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/select.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/select.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/select.cpp
index 712a8b0bf..ba10e7139 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/select.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/select.cpp
@@ -28,7 +28,7 @@ const std::vector<std::vector<std::vector<size_t>>> noneShapes = {{{1}, {1}, {1}
 const auto noneCases = ::testing::Combine(::testing::ValuesIn(noneShapes),
                                           ::testing::ValuesIn(inputPrecision),
                                           ::testing::Values(ov::op::AutoBroadcastSpec::NONE),
-                                          ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                          ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 const std::vector<std::vector<std::vector<size_t>>> numpyShapes = {{{1}, {1}, {1}},
                                                                    {{1}, {16}, {1}},
@@ -71,7 +71,7 @@ const std::vector<std::vector<std::vector<size_t>>> numpyShapes = {{{1}, {1}, {1
 const auto numpyCases = ::testing::Combine(::testing::ValuesIn(numpyShapes),
                                            ::testing::ValuesIn(inputPrecision),
                                            ::testing::Values(ov::op::AutoBroadcastSpec::NUMPY),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 const std::vector<std::vector<std::vector<size_t>>> tacotronShapes = {
     {{}, {1, 200}, {1, 200}},
@@ -82,7 +82,7 @@ const std::vector<std::vector<std::vector<size_t>>> tacotronShapes = {
 const auto tacotronCases = ::testing::Combine(::testing::ValuesIn(noneShapes),
                                               ::testing::ValuesIn(inputPrecision),
                                               ::testing::Values(ov::op::AutoBroadcastSpec::NUMPY),
-                                              ::testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                              ::testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_CASE_P(smoke_CUDA_TestsSelect_none, SelectLayerTest, noneCases, SelectLayerTest::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/softmax.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/softmax.cpp
similarity index 96%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/softmax.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/softmax.cpp
index a2fa77b3d..bd932c8aa 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/softmax.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/softmax.cpp
@@ -36,7 +36,7 @@ const auto params2D = testing::Combine(testing::ValuesIn(netPrecisions),
                                        testing::Values(ov::element::undefined),
                                        testing::ValuesIn(ov::test::static_shapes_to_test_representation(inputShapes2D)),
                                        testing::ValuesIn(axis2D),
-                                       testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                       testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                        testing::Values(ov::AnyMap()));
 
 INSTANTIATE_TEST_CASE_P(SoftMax2D, SoftMaxLayerTest, params2D, SoftMaxLayerTest::getTestCaseName);
@@ -55,7 +55,7 @@ const auto params3D = testing::Combine(testing::ValuesIn(netPrecisions),
                                        testing::Values(ov::element::undefined),
                                        testing::ValuesIn(ov::test::static_shapes_to_test_representation(inputShapes3D)),
                                        testing::ValuesIn(axis3D),
-                                       testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                       testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                        testing::Values(ov::AnyMap()));
 
 INSTANTIATE_TEST_CASE_P(SoftMax3D, SoftMaxLayerTest, params3D, SoftMaxLayerTest::getTestCaseName);
@@ -77,7 +77,7 @@ const auto params4D = testing::Combine(testing::ValuesIn(netPrecisions),
                                        testing::Values(ov::element::undefined),
                                        testing::ValuesIn(ov::test::static_shapes_to_test_representation(inputShapes4D)),
                                        testing::ValuesIn(axis4D),
-                                       testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                       testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                        testing::Values(ov::AnyMap()));
 
 INSTANTIATE_TEST_CASE_P(SoftMax4D, SoftMaxLayerTest, params4D, SoftMaxLayerTest::getTestCaseName);
@@ -96,7 +96,7 @@ const auto params5D = testing::Combine(testing::ValuesIn(netPrecisions),
                                        testing::Values(ov::element::undefined),
                                        testing::ValuesIn(ov::test::static_shapes_to_test_representation(inputShapes5D)),
                                        testing::ValuesIn(axis5D),
-                                       testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                       testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                        testing::Values(ov::AnyMap()));
 
 INSTANTIATE_TEST_CASE_P(SoftMax5D, SoftMaxLayerTest, params5D, SoftMaxLayerTest::getTestCaseName);
@@ -115,7 +115,7 @@ const auto resnet5Params =
                      testing::Values(ov::element::undefined),
                      testing::ValuesIn(ov::test::static_shapes_to_test_representation(resnet5Shapes)),
                      testing::ValuesIn(axis2D),
-                     testing::Values(CommonTestUtils::DEVICE_CUDA),
+                     testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                      testing::Values(ov::AnyMap()));
 
 INSTANTIATE_TEST_CASE_P(SoftMax2Dresnet5, SoftMaxLayerTest, resnet5Params, SoftMaxLayerTest::getTestCaseName);
@@ -129,7 +129,7 @@ const auto vggParams = testing::Combine(testing::ValuesIn(netPrecisions),
                                         testing::Values(ov::element::undefined),
                                         testing::ValuesIn(ov::test::static_shapes_to_test_representation(vggShapes)),
                                         testing::ValuesIn(axis2D),
-                                        testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                        testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                         testing::Values(ov::AnyMap()));
 
 INSTANTIATE_TEST_CASE_P(SoftMax2Dvgg, SoftMaxLayerTest, vggParams, SoftMaxLayerTest::getTestCaseName);
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/split.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/split.cpp
similarity index 97%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/split.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/split.cpp
index fd659b76a..1639c56c6 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/split.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/split.cpp
@@ -23,7 +23,7 @@ INSTANTIATE_TEST_CASE_P(NumSplitsCheck,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({30, 30, 30, 30})),
                                            ::testing::Values(std::vector<size_t>({})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         SplitLayerTest::getTestCaseName);
 
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/squeeze_unsqueeze.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/squeeze_unsqueeze.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/squeeze_unsqueeze.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/squeeze_unsqueeze.cpp
index 14ffc0d99..4d6798e68 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/squeeze_unsqueeze.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/squeeze_unsqueeze.cpp
@@ -37,6 +37,6 @@ INSTANTIATE_TEST_CASE_P(smoke_Basic,
                                            ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         SqueezeUnsqueezeLayerTest::getTestCaseName);
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/strided_slice.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/strided_slice.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/strided_slice.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/strided_slice.cpp
index 0234284fb..023d36814 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/strided_slice.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/strided_slice.cpp
@@ -142,7 +142,7 @@ INSTANTIATE_TEST_CASE_P(StridedSliceTest_FP32,
                                            ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(std::map<std::string, std::string>())),
                         StridedSliceLayerTest::getTestCaseName);
 
@@ -154,7 +154,7 @@ INSTANTIATE_TEST_CASE_P(StridedSliceTest_FP16,
                                            ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(std::map<std::string, std::string>())),
                         StridedSliceLayerTest::getTestCaseName);
 
@@ -166,7 +166,7 @@ INSTANTIATE_TEST_CASE_P(StridedSliceTest_I32,
                                            ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(std::map<std::string, std::string>())),
                         StridedSliceLayerTest::getTestCaseName);
 
@@ -178,7 +178,7 @@ INSTANTIATE_TEST_CASE_P(smoke_StridedSliceTest_FP32,
                                            ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA),
                                            ::testing::Values(std::map<std::string, std::string>())),
                         StridedSliceLayerTest::getTestCaseName);
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/tensor_iterator.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/tensor_iterator.cpp
similarity index 99%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/tensor_iterator.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/tensor_iterator.cpp
index 1aac0d9a6..afb0944b8 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/tensor_iterator.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/tensor_iterator.cpp
@@ -65,7 +65,7 @@ INSTANTIATE_TEST_CASE_P(
                        ::testing::ValuesIn(body_type),
                        ::testing::ValuesIn(direction),
                        ::testing::ValuesIn(netPrecisions),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     TensorIteratorDisabledTransformationsTest::getTestCaseName);
 
 std::vector<size_t> seq_lengths_clip_non_zero{1000};
@@ -82,7 +82,7 @@ INSTANTIATE_TEST_CASE_P(
                        ::testing::ValuesIn(body_type),
                        ::testing::ValuesIn(direction),
                        ::testing::ValuesIn(netPrecisions),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     TensorIteratorDisabledTransformationsTest::getTestCaseName);
 
 // ------------- Benchmark -------------
@@ -123,7 +123,7 @@ INSTANTIATE_TEST_CASE_P(
                        ::testing::ValuesIn(body_type),
                        ::testing::ValuesIn(direction),
                        ::testing::ValuesIn(netPrecisions),
-                       ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                       ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
     TensorIteratorBenchmarkTest::getTestCaseName);
 
 }  // namespace benchmark
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/topk.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/topk.cpp
similarity index 97%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/topk.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/topk.cpp
index 4e6b3d755..c8d4e2449 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/topk.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/topk.cpp
@@ -56,7 +56,7 @@ INSTANTIATE_TEST_CASE_P(smoke_TopK3D,
                                            ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(shapes3D),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         TopKLayerTest::getTestCaseName);
 
 const std::vector<int64_t> axes4D = {
@@ -83,7 +83,7 @@ INSTANTIATE_TEST_CASE_P(TopK4D,
                                            ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(shapes4D),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         TopKLayerTest::getTestCaseName);
 
 const std::vector<int64_t> axes5D = {
@@ -111,7 +111,7 @@ INSTANTIATE_TEST_CASE_P(TopK5D,
                                            ::testing::Values(InferenceEngine::Precision::UNSPECIFIED),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::ValuesIn(shapes5D),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         TopKLayerTest::getTestCaseName);
 
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/transpose_test.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/transpose_test.cpp
similarity index 94%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/transpose_test.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/transpose_test.cpp
index 7d6d618e3..8265b2e5d 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/transpose_test.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/transpose_test.cpp
@@ -25,7 +25,7 @@ const std::vector<std::vector<size_t>> inputShapes = {
 
 const std::vector<std::vector<size_t>> inputOrder = {
     std::vector<size_t>{0, 3, 2, 1},
-    // Empty inputs are currently unsupported in CUDAPlugin.
+    // Empty inputs are currently unsupported in nvidia_gpu.
     //        std::vector<size_t>{},
 };
 
@@ -36,7 +36,7 @@ const auto params = testing::Combine(testing::ValuesIn(inputOrder),
                                      testing::Values(InferenceEngine::Layout::ANY),
                                      testing::Values(InferenceEngine::Layout::ANY),
                                      testing::ValuesIn(inputShapes),
-                                     testing::Values(CommonTestUtils::DEVICE_CUDA));
+                                     testing::Values(CommonTestUtils::DEVICE_NVIDIA));
 
 INSTANTIATE_TEST_CASE_P(smoke_Transpose, TransposeLayerTest, params, TransposeLayerTest::getTestCaseName);
 
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/unsymmetrical_comparer.hpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/unsymmetrical_comparer.hpp
similarity index 100%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/unsymmetrical_comparer.hpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/unsymmetrical_comparer.hpp
diff --git a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/variadic_split.cpp b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/variadic_split.cpp
similarity index 97%
rename from modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/variadic_split.cpp
rename to modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/variadic_split.cpp
index fa1b18fd5..df8262e4d 100644
--- a/modules/cuda_plugin/tests/functional/shared_tests_instances/single_layer_tests/variadic_split.cpp
+++ b/modules/nvidia_plugin/tests/functional/shared_tests_instances/single_layer_tests/variadic_split.cpp
@@ -37,7 +37,7 @@ INSTANTIATE_TEST_CASE_P(smoke_NumSplitsCheck,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>({30, 30, 30, 30})),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         VariadicSplitLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape0_axis1,
@@ -50,7 +50,7 @@ INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape0_axis1,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>{1, 3, 40, 40, 85}),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         VariadicSplitLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape0_axis2,
@@ -63,7 +63,7 @@ INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape0_axis2,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>{1, 3, 40, 40, 85}),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         VariadicSplitLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape0_axis3,
@@ -76,7 +76,7 @@ INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape0_axis3,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>{1, 3, 40, 40, 85}),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         VariadicSplitLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape0_axis4,
@@ -89,7 +89,7 @@ INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape0_axis4,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>{1, 3, 40, 40, 85}),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         VariadicSplitLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape1_axis1,
@@ -102,7 +102,7 @@ INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape1_axis1,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>{1, 3, 20, 20, 85}),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         VariadicSplitLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape1_axis2,
@@ -115,7 +115,7 @@ INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape1_axis2,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>{1, 3, 20, 20, 85}),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         VariadicSplitLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape1_axis3,
@@ -128,7 +128,7 @@ INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape1_axis3,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>{1, 3, 20, 20, 85}),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         VariadicSplitLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape1_axis4,
@@ -141,7 +141,7 @@ INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape1_axis4,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>{1, 3, 20, 20, 85}),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         VariadicSplitLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape2_axis1,
@@ -154,7 +154,7 @@ INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape2_axis1,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>{1, 3, 80, 80, 85}),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         VariadicSplitLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape2_axis2,
@@ -167,7 +167,7 @@ INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape2_axis2,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>{1, 3, 80, 80, 85}),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         VariadicSplitLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape2_axis3,
@@ -180,7 +180,7 @@ INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape2_axis3,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>{1, 3, 80, 80, 85}),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         VariadicSplitLayerTest::getTestCaseName);
 
 INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape2_axis4,
@@ -193,7 +193,7 @@ INSTANTIATE_TEST_CASE_P(yolov5_NumSplitsCheck_shape2_axis4,
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(InferenceEngine::Layout::ANY),
                                            ::testing::Values(std::vector<size_t>{1, 3, 80, 80, 85}),
-                                           ::testing::Values(CommonTestUtils::DEVICE_CUDA)),
+                                           ::testing::Values(CommonTestUtils::DEVICE_NVIDIA)),
                         VariadicSplitLayerTest::getTestCaseName);
 
 }  // namespace
diff --git a/modules/cuda_plugin/tests/functional/skip_tests_config.cpp b/modules/nvidia_plugin/tests/functional/skip_tests_config.cpp
similarity index 100%
rename from modules/cuda_plugin/tests/functional/skip_tests_config.cpp
rename to modules/nvidia_plugin/tests/functional/skip_tests_config.cpp
diff --git a/modules/cuda_plugin/tests/functional/transformations/cuda_transformations_test.cpp b/modules/nvidia_plugin/tests/functional/transformations/cuda_transformations_test.cpp
similarity index 100%
rename from modules/cuda_plugin/tests/functional/transformations/cuda_transformations_test.cpp
rename to modules/nvidia_plugin/tests/functional/transformations/cuda_transformations_test.cpp
diff --git a/modules/cuda_plugin/tests/include/cuda_test_constants.hpp b/modules/nvidia_plugin/tests/include/cuda_test_constants.hpp
similarity index 80%
rename from modules/cuda_plugin/tests/include/cuda_test_constants.hpp
rename to modules/nvidia_plugin/tests/include/cuda_test_constants.hpp
index 96ea006b5..9b2250be2 100644
--- a/modules/cuda_plugin/tests/include/cuda_test_constants.hpp
+++ b/modules/nvidia_plugin/tests/include/cuda_test_constants.hpp
@@ -5,6 +5,6 @@
 
 namespace CommonTestUtils {
 
-const char DEVICE_CUDA[] = "CUDA";
+const char DEVICE_NVIDIA[] = "NVIDIA";
 
 }  // namespace CommonTestUtils
diff --git a/modules/cuda_plugin/tests/include/fix_win32_gtest_assert_ne_macro.hpp b/modules/nvidia_plugin/tests/include/fix_win32_gtest_assert_ne_macro.hpp
similarity index 100%
rename from modules/cuda_plugin/tests/include/fix_win32_gtest_assert_ne_macro.hpp
rename to modules/nvidia_plugin/tests/include/fix_win32_gtest_assert_ne_macro.hpp
diff --git a/modules/cuda_plugin/tests/unit/CMakeLists.txt b/modules/nvidia_plugin/tests/unit/CMakeLists.txt
similarity index 97%
rename from modules/cuda_plugin/tests/unit/CMakeLists.txt
rename to modules/nvidia_plugin/tests/unit/CMakeLists.txt
index f38c92786..bad757a2e 100644
--- a/modules/cuda_plugin/tests/unit/CMakeLists.txt
+++ b/modules/nvidia_plugin/tests/unit/CMakeLists.txt
@@ -26,7 +26,7 @@ addIeTargetTest(
 		OBJECT_FILES
 		${CUDA_SOURCES}
         LINK_LIBRARIES_WHOLE_ARCHIVE
-        openvino_cuda_plugin_obj
+        openvino_nvidia_gpu_plugin_obj
         ${EXCLUDED_SOURCE_PATHS}
         LINK_LIBRARIES
         IE::funcSharedTests
diff --git a/modules/cuda_plugin/tests/unit/cancellation_token.cpp b/modules/nvidia_plugin/tests/unit/cancellation_token.cpp
similarity index 95%
rename from modules/cuda_plugin/tests/unit/cancellation_token.cpp
rename to modules/nvidia_plugin/tests/unit/cancellation_token.cpp
index 7a32e5547..0f828d01a 100644
--- a/modules/cuda_plugin/tests/unit/cancellation_token.cpp
+++ b/modules/nvidia_plugin/tests/unit/cancellation_token.cpp
@@ -6,7 +6,7 @@
 
 #include <cancellation_token.hpp>
 
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 
 class CancellationTokenTest : public testing::Test {
     void SetUp() override {}
diff --git a/modules/cuda_plugin/tests/unit/concat.cpp b/modules/nvidia_plugin/tests/unit/concat.cpp
similarity index 99%
rename from modules/cuda_plugin/tests/unit/concat.cpp
rename to modules/nvidia_plugin/tests/unit/concat.cpp
index bd2c89530..4b99bc09e 100644
--- a/modules/cuda_plugin/tests/unit/concat.cpp
+++ b/modules/nvidia_plugin/tests/unit/concat.cpp
@@ -15,7 +15,7 @@
 
 using namespace InferenceEngine::gpu;
 using namespace InferenceEngine;
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 using devptr_t = DevicePointer<void*>;
 using cdevptr_t = DevicePointer<const void*>;
 
diff --git a/modules/cuda_plugin/tests/unit/convert_benchmark.cpp b/modules/nvidia_plugin/tests/unit/convert_benchmark.cpp
similarity index 85%
rename from modules/cuda_plugin/tests/unit/convert_benchmark.cpp
rename to modules/nvidia_plugin/tests/unit/convert_benchmark.cpp
index 49d229c19..9f39e7c36 100644
--- a/modules/cuda_plugin/tests/unit/convert_benchmark.cpp
+++ b/modules/nvidia_plugin/tests/unit/convert_benchmark.cpp
@@ -18,7 +18,7 @@
 namespace {
 
 struct ConvertTest : testing::Test {
-    CUDAPlugin::ThreadContext threadContext{CUDA::Device{}};
+    ov::nvidia_gpu::ThreadContext threadContext{CUDA::Device{}};
     const ov::Shape inputTensorShape{1, 1, 3, 1024, 1024};
     std::vector<std::shared_ptr<ngraph::runtime::Tensor>> emptyTensor;
     std::map<std::string, std::size_t> emptyMapping;
@@ -29,11 +29,11 @@ struct ConvertTest : testing::Test {
         const auto node = std::make_shared<ov::op::v0::Convert>(param->output(0), ov::element::Type(output));
 
         static constexpr bool optimizeOption = false;
-        auto& registry = CUDAPlugin::OperationRegistry::getInstance();
-        return registry.createOperation(CUDAPlugin::CreationContext{threadContext.device(), optimizeOption},
+        auto& registry = ov::nvidia_gpu::OperationRegistry::getInstance();
+        return registry.createOperation(ov::nvidia_gpu::CreationContext{threadContext.device(), optimizeOption},
                                         node,
-                                        std::vector<CUDAPlugin::TensorID>{CUDAPlugin::TensorID{0u}},
-                                        std::vector<CUDAPlugin::TensorID>{CUDAPlugin::TensorID{0u}});
+                                        std::vector<ov::nvidia_gpu::TensorID>{ov::nvidia_gpu::TensorID{0u}},
+                                        std::vector<ov::nvidia_gpu::TensorID>{ov::nvidia_gpu::TensorID{0u}});
     }
 };
 
@@ -42,10 +42,10 @@ TEST_F(ConvertTest, DISABLED_benchmark) {
     constexpr int kNumAttempts = 200;
 
     auto& stream = threadContext.stream();
-    CUDAPlugin::CudaGraph graph{CUDAPlugin::CreationContext{CUDA::Device{}, false}, {}};
-    CUDAPlugin::CancellationToken token{};
-    CUDAPlugin::Profiler profiler{false, graph};
-    CUDAPlugin::InferenceRequestContext context{
+    ov::nvidia_gpu::CudaGraph graph{ov::nvidia_gpu::CreationContext{CUDA::Device{}, false}, {}};
+    ov::nvidia_gpu::CancellationToken token{};
+    ov::nvidia_gpu::Profiler profiler{false, graph};
+    ov::nvidia_gpu::InferenceRequestContext context{
         emptyTensor, emptyMapping, emptyTensor, emptyMapping, threadContext, token, profiler};
 
     using Type_t = ov::element::Type_t;
@@ -89,7 +89,7 @@ TEST_F(ConvertTest, DISABLED_benchmark) {
 
             auto start = std::chrono::steady_clock::now();
             for (int i = 0; i < kNumAttempts; i++) {
-                CUDAPlugin::Workbuffers workbuffers{};
+                ov::nvidia_gpu::Workbuffers workbuffers{};
                 op->Execute(context, inputs, outputs, workbuffers);
                 stream.synchronize();
             }
diff --git a/modules/cuda_plugin/tests/unit/cuda/stl/algorithms/sort.cu b/modules/nvidia_plugin/tests/unit/cuda/stl/algorithms/sort.cu
similarity index 99%
rename from modules/cuda_plugin/tests/unit/cuda/stl/algorithms/sort.cu
rename to modules/nvidia_plugin/tests/unit/cuda/stl/algorithms/sort.cu
index 616f5fc14..748c56185 100644
--- a/modules/cuda_plugin/tests/unit/cuda/stl/algorithms/sort.cu
+++ b/modules/nvidia_plugin/tests/unit/cuda/stl/algorithms/sort.cu
@@ -9,7 +9,7 @@
 #include <cuda/stl/algorithms/sort.cuh>
 #include <random>
 
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 
 namespace {
 
diff --git a/modules/cuda_plugin/tests/unit/cuda/stl/atomic.cu b/modules/nvidia_plugin/tests/unit/cuda/stl/atomic.cu
similarity index 99%
rename from modules/cuda_plugin/tests/unit/cuda/stl/atomic.cu
rename to modules/nvidia_plugin/tests/unit/cuda/stl/atomic.cu
index 2a594dac5..eb1b59481 100644
--- a/modules/cuda_plugin/tests/unit/cuda/stl/atomic.cu
+++ b/modules/nvidia_plugin/tests/unit/cuda/stl/atomic.cu
@@ -7,7 +7,7 @@
 #include <cuda/runtime.hpp>
 #include <cuda/stl/atomic.cuh>
 
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 
 class AtomicTest : public testing::Test {
     void SetUp() override {}
diff --git a/modules/cuda_plugin/tests/unit/cuda/stl/mdspan.cu b/modules/nvidia_plugin/tests/unit/cuda/stl/mdspan.cu
similarity index 99%
rename from modules/cuda_plugin/tests/unit/cuda/stl/mdspan.cu
rename to modules/nvidia_plugin/tests/unit/cuda/stl/mdspan.cu
index 2b7e6508f..64756d04e 100644
--- a/modules/cuda_plugin/tests/unit/cuda/stl/mdspan.cu
+++ b/modules/nvidia_plugin/tests/unit/cuda/stl/mdspan.cu
@@ -7,7 +7,7 @@
 #include <cuda/runtime.hpp>
 #include <cuda/stl/mdspan.cuh>
 
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 
 class MDSpanTest : public testing::Test {
     void SetUp() override {}
diff --git a/modules/cuda_plugin/tests/unit/cuda/stl/mdvector.cu b/modules/nvidia_plugin/tests/unit/cuda/stl/mdvector.cu
similarity index 98%
rename from modules/cuda_plugin/tests/unit/cuda/stl/mdvector.cu
rename to modules/nvidia_plugin/tests/unit/cuda/stl/mdvector.cu
index 9230d897e..593a571f0 100644
--- a/modules/cuda_plugin/tests/unit/cuda/stl/mdvector.cu
+++ b/modules/nvidia_plugin/tests/unit/cuda/stl/mdvector.cu
@@ -7,7 +7,7 @@
 #include <cuda/runtime.hpp>
 #include <cuda/stl/mdvector.cuh>
 
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 
 class MDVectorTest : public testing::Test {
     void SetUp() override {}
diff --git a/modules/cuda_plugin/tests/unit/cuda/stl/span.cu b/modules/nvidia_plugin/tests/unit/cuda/stl/span.cu
similarity index 97%
rename from modules/cuda_plugin/tests/unit/cuda/stl/span.cu
rename to modules/nvidia_plugin/tests/unit/cuda/stl/span.cu
index ed0a46d7c..17228447a 100644
--- a/modules/cuda_plugin/tests/unit/cuda/stl/span.cu
+++ b/modules/nvidia_plugin/tests/unit/cuda/stl/span.cu
@@ -8,7 +8,7 @@
 #include <cuda/stl/atomic.cuh>
 #include <cuda/stl/span.cuh>
 
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 
 class SpanTest : public testing::Test {
     void SetUp() override {}
diff --git a/modules/cuda_plugin/tests/unit/cuda/stl/vector.cu b/modules/nvidia_plugin/tests/unit/cuda/stl/vector.cu
similarity index 98%
rename from modules/cuda_plugin/tests/unit/cuda/stl/vector.cu
rename to modules/nvidia_plugin/tests/unit/cuda/stl/vector.cu
index 5fe64f1c8..4c921f335 100644
--- a/modules/cuda_plugin/tests/unit/cuda/stl/vector.cu
+++ b/modules/nvidia_plugin/tests/unit/cuda/stl/vector.cu
@@ -7,7 +7,7 @@
 #include <cuda/runtime.hpp>
 #include <cuda/stl/vector.cuh>
 
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 
 class VectorTest : public testing::Test {
     void SetUp() override {}
diff --git a/modules/cuda_plugin/tests/unit/executable_network.cpp b/modules/nvidia_plugin/tests/unit/executable_network.cpp
similarity index 99%
rename from modules/cuda_plugin/tests/unit/executable_network.cpp
rename to modules/nvidia_plugin/tests/unit/executable_network.cpp
index 08543f97d..7c23eae67 100644
--- a/modules/cuda_plugin/tests/unit/executable_network.cpp
+++ b/modules/nvidia_plugin/tests/unit/executable_network.cpp
@@ -17,7 +17,7 @@
 
 #include "test_networks.hpp"
 
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 
 class ExecNetworkTest : public testing::Test {
     void SetUp() override {
diff --git a/modules/cuda_plugin/tests/unit/kernels/insert.cpp b/modules/nvidia_plugin/tests/unit/kernels/insert.cpp
similarity index 99%
rename from modules/cuda_plugin/tests/unit/kernels/insert.cpp
rename to modules/nvidia_plugin/tests/unit/kernels/insert.cpp
index 852e53ade..33c70a3b9 100644
--- a/modules/cuda_plugin/tests/unit/kernels/insert.cpp
+++ b/modules/nvidia_plugin/tests/unit/kernels/insert.cpp
@@ -7,7 +7,7 @@
 #include <cuda/runtime.hpp>
 #include <kernels/insert.hpp>
 
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 
 class InsertKernelTest : public testing::Test {
     void SetUp() override {}
diff --git a/modules/cuda_plugin/tests/unit/kernels/slice.cpp b/modules/nvidia_plugin/tests/unit/kernels/slice.cpp
similarity index 99%
rename from modules/cuda_plugin/tests/unit/kernels/slice.cpp
rename to modules/nvidia_plugin/tests/unit/kernels/slice.cpp
index 7256f1f55..398aaecb5 100644
--- a/modules/cuda_plugin/tests/unit/kernels/slice.cpp
+++ b/modules/nvidia_plugin/tests/unit/kernels/slice.cpp
@@ -8,7 +8,7 @@
 #include <kernels/slice.hpp>
 #include <kernels/tensor_helpers.hpp>
 
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 
 class SliceKernelTest : public testing::Test {
     void SetUp() override {}
diff --git a/modules/cuda_plugin/tests/unit/limits.cpp b/modules/nvidia_plugin/tests/unit/limits.cpp
similarity index 86%
rename from modules/cuda_plugin/tests/unit/limits.cpp
rename to modules/nvidia_plugin/tests/unit/limits.cpp
index fe4c02c5b..eeff52a75 100644
--- a/modules/cuda_plugin/tests/unit/limits.cpp
+++ b/modules/nvidia_plugin/tests/unit/limits.cpp
@@ -99,43 +99,43 @@ void run_zero_div_test() {
     static constexpr int length = 3;
     static constexpr size_t size_bytes = length * sizeof(T);
 
-    CUDAPlugin::ThreadContext threadContext{{}};
+    ov::nvidia_gpu::ThreadContext threadContext{{}};
     CUDA::Allocation in1_alloc = threadContext.stream().malloc(size_bytes);
     CUDA::Allocation in2_alloc = threadContext.stream().malloc(sizeof(T));
     CUDA::Allocation out_alloc = threadContext.stream().malloc(size_bytes);
     std::vector<cdevptr_t> inputs{in1_alloc, in2_alloc};
     std::vector<devptr_t> outputs{out_alloc};
 
-    CUDAPlugin::OperationBase::Ptr operation = [&] {
+    ov::nvidia_gpu::OperationBase::Ptr operation = [&] {
         CUDA::Device device{};
         const bool optimizeOption = false;
         const ngraph::element::Type ng_type = ngraph::element::from<T>();
         auto param1 = std::make_shared<ngraph::op::v0::Parameter>(ng_type, ngraph::PartialShape{length});
         auto param2 = std::make_shared<ngraph::op::v0::Parameter>(ng_type, ngraph::PartialShape{1});
         auto node = std::make_shared<ngraph::op::v1::Divide>(param1->output(0), param2->output(0));
-        auto& registry = CUDAPlugin::OperationRegistry::getInstance();
-        auto op = registry.createOperation(CUDAPlugin::CreationContext{device, optimizeOption},
+        auto& registry = ov::nvidia_gpu::OperationRegistry::getInstance();
+        auto op = registry.createOperation(ov::nvidia_gpu::CreationContext{device, optimizeOption},
                                            node,
-                                           std::vector<CUDAPlugin::TensorID>{CUDAPlugin::TensorID{0u}},
-                                           std::vector<CUDAPlugin::TensorID>{CUDAPlugin::TensorID{0u}});
+                                           std::vector<ov::nvidia_gpu::TensorID>{ov::nvidia_gpu::TensorID{0u}},
+                                           std::vector<ov::nvidia_gpu::TensorID>{ov::nvidia_gpu::TensorID{0u}});
         return op;
     }();
     ASSERT_TRUE(operation);
 
     std::vector<CUDA::DefaultAllocation> im_buffers;
 
-    CUDAPlugin::WorkbufferRequest wb_request{operation->GetWorkBufferRequest()};
+    ov::nvidia_gpu::WorkbufferRequest wb_request{operation->GetWorkBufferRequest()};
     for (const auto size : wb_request.immutable_sizes) {
         im_buffers.emplace_back(CUDA::DefaultStream::stream().malloc(size));
     }
 
-    CUDAPlugin::IOperationExec::Buffers init_buffers;
+    ov::nvidia_gpu::IOperationExec::Buffers init_buffers;
     for (const auto& buf : im_buffers) {
         init_buffers.emplace_back(buf);
     }
     operation->InitSharedImmutableWorkbuffers(init_buffers);
 
-    CUDAPlugin::Workbuffers workbuffers{};
+    ov::nvidia_gpu::Workbuffers workbuffers{};
     for (const auto& buf : im_buffers) {
         workbuffers.immutable_buffers.emplace_back(buf);
     }
@@ -149,10 +149,10 @@ void run_zero_div_test() {
 
     std::vector<std::shared_ptr<ngraph::runtime::Tensor>> emptyTensor;
     std::map<std::string, std::size_t> emptyMapping;
-    CUDAPlugin::CancellationToken token{};
-    CUDAPlugin::CudaGraph graph{CUDAPlugin::CreationContext{CUDA::Device{}, false}, {}};
-    CUDAPlugin::Profiler profiler{false, graph};
-    CUDAPlugin::InferenceRequestContext context{
+    ov::nvidia_gpu::CancellationToken token{};
+    ov::nvidia_gpu::CudaGraph graph{ov::nvidia_gpu::CreationContext{CUDA::Device{}, false}, {}};
+    ov::nvidia_gpu::Profiler profiler{false, graph};
+    ov::nvidia_gpu::InferenceRequestContext context{
         emptyTensor, emptyMapping, emptyTensor, emptyMapping, threadContext, token, profiler};
     auto& stream = context.getThreadContext().stream();
     stream.upload(in1_alloc, in1.data(), size_bytes);
diff --git a/modules/cuda_plugin/tests/unit/logical_not_benchmark.cpp b/modules/nvidia_plugin/tests/unit/logical_not_benchmark.cpp
similarity index 82%
rename from modules/cuda_plugin/tests/unit/logical_not_benchmark.cpp
rename to modules/nvidia_plugin/tests/unit/logical_not_benchmark.cpp
index 4eb2b7ba0..13b7a7f81 100644
--- a/modules/cuda_plugin/tests/unit/logical_not_benchmark.cpp
+++ b/modules/nvidia_plugin/tests/unit/logical_not_benchmark.cpp
@@ -24,23 +24,23 @@ using devptr_t = CUDA::DevicePointer<void*>;
 using cdevptr_t = CUDA::DevicePointer<const void*>;
 
 struct LogicalNotBenchmark : testing::Test {
-    using TensorID = CUDAPlugin::TensorID;
+    using TensorID = ov::nvidia_gpu::TensorID;
     using ElementType = std::uint8_t;
     static constexpr int length = 10 * 1024;
     static constexpr size_t size = length * sizeof(ElementType);
-    CUDAPlugin::ThreadContext threadContext{{}};
+    ov::nvidia_gpu::ThreadContext threadContext{{}};
     CUDA::Allocation in_alloc = threadContext.stream().malloc(size);
     CUDA::Allocation out_alloc = threadContext.stream().malloc(size);
     std::vector<cdevptr_t> inputs{in_alloc};
     std::vector<devptr_t> outputs{out_alloc};
     std::vector<std::shared_ptr<ngraph::runtime::Tensor>> emptyTensor;
     std::map<std::string, std::size_t> emptyMapping;
-    CUDAPlugin::OperationBase::Ptr operation = [this] {
+    ov::nvidia_gpu::OperationBase::Ptr operation = [this] {
         const bool optimizeOption = false;
         auto param = std::make_shared<ov::op::v0::Parameter>(ov::element::f32, ov::PartialShape{length});
         auto node = std::make_shared<ov::op::v1::LogicalNot>(param->output(0));
-        auto& registry = CUDAPlugin::OperationRegistry::getInstance();
-        auto op = registry.createOperation(CUDAPlugin::CreationContext{threadContext.device(), optimizeOption},
+        auto& registry = ov::nvidia_gpu::OperationRegistry::getInstance();
+        auto op = registry.createOperation(ov::nvidia_gpu::CreationContext{threadContext.device(), optimizeOption},
                                            node,
                                            std::vector<TensorID>{TensorID{0u}},
                                            std::vector<TensorID>{TensorID{0u}});
@@ -50,10 +50,10 @@ struct LogicalNotBenchmark : testing::Test {
 
 TEST_F(LogicalNotBenchmark, DISABLED_benchmark) {
     constexpr int kNumAttempts = 20;
-    CUDAPlugin::CancellationToken token{};
-    CUDAPlugin::CudaGraph graph{CUDAPlugin::CreationContext{CUDA::Device{}, false}, {}};
-    CUDAPlugin::Profiler profiler{false, graph};
-    CUDAPlugin::InferenceRequestContext context{
+    ov::nvidia_gpu::CancellationToken token{};
+    ov::nvidia_gpu::CudaGraph graph{ov::nvidia_gpu::CreationContext{CUDA::Device{}, false}, {}};
+    ov::nvidia_gpu::Profiler profiler{false, graph};
+    ov::nvidia_gpu::InferenceRequestContext context{
         emptyTensor, emptyMapping, emptyTensor, emptyMapping, threadContext, token, profiler};
     auto& stream = context.getThreadContext().stream();
     std::vector<ElementType> in(length);
@@ -64,7 +64,7 @@ TEST_F(LogicalNotBenchmark, DISABLED_benchmark) {
     auto gen = [&dist, &mersenne_engine]() { return dist(mersenne_engine); };
     std::generate(in.begin(), in.end(), gen);
     stream.upload(in_alloc, in.data(), size);
-    CUDAPlugin::Workbuffers workbuffers{};
+    ov::nvidia_gpu::Workbuffers workbuffers{};
     cudaEvent_t start;
     cudaEvent_t stop;
     cudaEventCreate(&start);
diff --git a/modules/cuda_plugin/tests/unit/memory_manager/cuda_device_mem_block_test.cpp b/modules/nvidia_plugin/tests/unit/memory_manager/cuda_device_mem_block_test.cpp
similarity index 96%
rename from modules/cuda_plugin/tests/unit/memory_manager/cuda_device_mem_block_test.cpp
rename to modules/nvidia_plugin/tests/unit/memory_manager/cuda_device_mem_block_test.cpp
index 1524e26a9..d594f60a3 100644
--- a/modules/cuda_plugin/tests/unit/memory_manager/cuda_device_mem_block_test.cpp
+++ b/modules/nvidia_plugin/tests/unit/memory_manager/cuda_device_mem_block_test.cpp
@@ -9,7 +9,7 @@
 #include "memory_manager/model/cuda_memory_model.hpp"
 
 TEST(DeviceMemBlock, ZeroSizeMemoryBlock) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     // "No constant tensors" edge case. MemoryModel is empty and
     // memory block size is zero.
@@ -42,7 +42,7 @@ TEST(DeviceMemBlock, ZeroSizeMemoryBlock) {
 }
 
 TEST(DeviceMemBlock, VerifyDevicePointers) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     const BufferID alloc_count = 5;
     const size_t allocation_size = 0x100;
@@ -69,7 +69,7 @@ TEST(DeviceMemBlock, VerifyDevicePointers) {
 }
 
 TEST(DeviceMemBlock, NullPtrIfTensorNotFound) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     const size_t block_size = 0x700;
     std::unordered_map<BufferID, ptrdiff_t> offsets = {
diff --git a/modules/cuda_plugin/tests/unit/memory_manager/cuda_immutable_memory_block_builder_test.cpp b/modules/nvidia_plugin/tests/unit/memory_manager/cuda_immutable_memory_block_builder_test.cpp
similarity index 95%
rename from modules/cuda_plugin/tests/unit/memory_manager/cuda_immutable_memory_block_builder_test.cpp
rename to modules/nvidia_plugin/tests/unit/memory_manager/cuda_immutable_memory_block_builder_test.cpp
index 867bac398..00d750030 100644
--- a/modules/cuda_plugin/tests/unit/memory_manager/cuda_immutable_memory_block_builder_test.cpp
+++ b/modules/nvidia_plugin/tests/unit/memory_manager/cuda_immutable_memory_block_builder_test.cpp
@@ -13,14 +13,14 @@
 #include "memory_manager/cuda_device_mem_block.hpp"
 
 TEST(ImmutableMemoryBlockBuilder, BuildEmpty) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     ImmutableMemoryBlockBuilder builder;
     EXPECT_NO_THROW(builder.build());
 }
 
 TEST(ImmutableMemoryBlockBuilder, Build) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     const BufferID t0_id = 1;
     const std::vector<uint8_t> t0_data(16, 0xA5);
@@ -53,7 +53,7 @@ TEST(ImmutableMemoryBlockBuilder, Build) {
 }
 
 TEST(ImmutableMemoryBlockBuilder, HandleDuplicateAllocation) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     ImmutableMemoryBlockBuilder builder;
 
@@ -76,7 +76,7 @@ TEST(ImmutableMemoryBlockBuilder, HandleDuplicateAllocation) {
 }
 
 TEST(ImmutableMemoryBlockBuilder, HandleZeroAllocationSize) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     ImmutableMemoryBlockBuilder builder;
 
@@ -94,7 +94,7 @@ TEST(ImmutableMemoryBlockBuilder, HandleZeroAllocationSize) {
 }
 
 TEST(ImmutableMemoryBlockBuilder, HandleNullDataPointer) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     ImmutableMemoryBlockBuilder builder;
 
diff --git a/modules/cuda_plugin/tests/unit/memory_manager/cuda_memory_manager_test.cpp b/modules/nvidia_plugin/tests/unit/memory_manager/cuda_memory_manager_test.cpp
similarity index 89%
rename from modules/cuda_plugin/tests/unit/memory_manager/cuda_memory_manager_test.cpp
rename to modules/nvidia_plugin/tests/unit/memory_manager/cuda_memory_manager_test.cpp
index 2f343ed69..2ba0168e3 100644
--- a/modules/cuda_plugin/tests/unit/memory_manager/cuda_memory_manager_test.cpp
+++ b/modules/nvidia_plugin/tests/unit/memory_manager/cuda_memory_manager_test.cpp
@@ -14,15 +14,15 @@
 #include "memory_manager/cuda_immutable_memory_block_builder.hpp"
 #include "memory_manager/model/cuda_memory_model_builder.hpp"
 
-class MemoryManagerTest : public testing::Test, public CUDAPlugin::IOperationMeta {
+class MemoryManagerTest : public testing::Test, public ov::nvidia_gpu::IOperationMeta {
 public:
-    using TensorID = CUDAPlugin::TensorID;
+    using TensorID = ov::nvidia_gpu::TensorID;
 
     void SetUp() override {
         // Allocate shared memory block for constant tensors
         {
             const std::vector<uint8_t> data(256, 0xA5);
-            CUDAPlugin::ImmutableMemoryBlockBuilder builder;
+            ov::nvidia_gpu::ImmutableMemoryBlockBuilder builder;
             for (auto id : sharedConstantIds_) {
                 builder.addAllocation(id.GetId(), &data[0], data.size());
             }
@@ -31,7 +31,7 @@ class MemoryManagerTest : public testing::Test, public CUDAPlugin::IOperationMet
 
         // Create MemoryModel for mutable tensors
         {
-            CUDAPlugin::MemoryModelBuilder builder;
+            ov::nvidia_gpu::MemoryModelBuilder builder;
             const size_t size = 1;
             for (int i = 0; i < mutableTensorIDs_.size(); ++i) {
                 builder.addAllocation(mutableTensorIDs_[i].GetId(), i, i + 2, size);
@@ -45,13 +45,13 @@ class MemoryManagerTest : public testing::Test, public CUDAPlugin::IOperationMet
     const std::vector<TensorID> mutableTensorIDs_ = {
         TensorID{101}, TensorID{104}, TensorID{103}, TensorID{105}, TensorID{120}, TensorID{121}};
 
-    std::shared_ptr<CUDAPlugin::DeviceMemBlock> immutableTensors_;
-    CUDAPlugin::MemoryModel::Ptr immutableMemoryModel_;
-    CUDAPlugin::MemoryModel::Ptr mutableMemoryModel_;
+    std::shared_ptr<ov::nvidia_gpu::DeviceMemBlock> immutableTensors_;
+    ov::nvidia_gpu::MemoryModel::Ptr immutableMemoryModel_;
+    ov::nvidia_gpu::MemoryModel::Ptr mutableMemoryModel_;
 
-public:  // CUDAPlugin::IOperationMeta
-    std::vector<CUDAPlugin::TensorID> inputIds_;
-    std::vector<CUDAPlugin::TensorID> outputIds_;
+public:  // ov::nvidia_gpu::IOperationMeta
+    std::vector<ov::nvidia_gpu::TensorID> inputIds_;
+    std::vector<ov::nvidia_gpu::TensorID> outputIds_;
     const std::string& GetName() const override {
         static std::string empty;
         return empty;
@@ -62,12 +62,12 @@ class MemoryManagerTest : public testing::Test, public CUDAPlugin::IOperationMet
         return empty;
     }
 
-    gsl::span<const CUDAPlugin::TensorID> GetInputIds() const override { return inputIds_; }
-    gsl::span<const CUDAPlugin::TensorID> GetOutputIds() const override { return outputIds_; }
+    gsl::span<const ov::nvidia_gpu::TensorID> GetInputIds() const override { return inputIds_; }
+    gsl::span<const ov::nvidia_gpu::TensorID> GetOutputIds() const override { return outputIds_; }
 };
 
 TEST_F(MemoryManagerTest, InputTensorPointersAndTheirOrder) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     auto memory_manager = std::make_unique<MemoryManager>(immutableTensors_, mutableMemoryModel_);
 
@@ -107,7 +107,7 @@ TEST_F(MemoryManagerTest, InputTensorPointersAndTheirOrder) {
 }
 
 TEST_F(MemoryManagerTest, OutputTensorPointersAndTheirOrder) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     auto memory_manager = std::make_unique<MemoryManager>(immutableTensors_, mutableMemoryModel_);
 
@@ -137,7 +137,7 @@ TEST_F(MemoryManagerTest, OutputTensorPointersAndTheirOrder) {
 }
 
 TEST_F(MemoryManagerTest, OperationHasNoInputs) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
     auto memory_manager = std::make_unique<MemoryManager>(immutableTensors_, mutableMemoryModel_);
     inputIds_ = {};
     auto allocation = CUDA::DefaultStream::stream().malloc(immutableTensors_->memoryModel()->deviceMemoryBlockSize() +
@@ -148,7 +148,7 @@ TEST_F(MemoryManagerTest, OperationHasNoInputs) {
 }
 
 TEST_F(MemoryManagerTest, OperationHasNoOutputs) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
     auto memory_manager = std::make_unique<MemoryManager>(immutableTensors_, mutableMemoryModel_);
     outputIds_ = {};
     auto allocation = CUDA::DefaultStream::stream().malloc(immutableTensors_->memoryModel()->deviceMemoryBlockSize() +
@@ -159,7 +159,7 @@ TEST_F(MemoryManagerTest, OperationHasNoOutputs) {
 }
 
 TEST_F(MemoryManagerTest, InvalidInputTensorID) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     const TensorID invalid_buffer_id{9999};
     ASSERT_EQ(0, std::count(sharedConstantIds_.begin(), sharedConstantIds_.end(), invalid_buffer_id));
@@ -181,7 +181,7 @@ TEST_F(MemoryManagerTest, InvalidInputTensorID) {
 }
 
 TEST_F(MemoryManagerTest, InvalidOutputTensorID) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     const TensorID invalid_buffer_id{9999};
     ASSERT_EQ(0, std::count(sharedConstantIds_.begin(), sharedConstantIds_.end(), invalid_buffer_id));
@@ -203,7 +203,7 @@ TEST_F(MemoryManagerTest, InvalidOutputTensorID) {
 }
 
 TEST_F(MemoryManagerTest, ConstantsCanNotBeOutputs) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     auto memory_manager = std::make_unique<MemoryManager>(immutableTensors_, mutableMemoryModel_);
     outputIds_ = mutableTensorIDs_;
diff --git a/modules/cuda_plugin/tests/unit/memory_manager/model/cuda_immutable_memory_model_builder_test.cpp b/modules/nvidia_plugin/tests/unit/memory_manager/model/cuda_immutable_memory_model_builder_test.cpp
similarity index 94%
rename from modules/cuda_plugin/tests/unit/memory_manager/model/cuda_immutable_memory_model_builder_test.cpp
rename to modules/nvidia_plugin/tests/unit/memory_manager/model/cuda_immutable_memory_model_builder_test.cpp
index eb4835892..74f0882c4 100644
--- a/modules/cuda_plugin/tests/unit/memory_manager/model/cuda_immutable_memory_model_builder_test.cpp
+++ b/modules/nvidia_plugin/tests/unit/memory_manager/model/cuda_immutable_memory_model_builder_test.cpp
@@ -11,7 +11,7 @@
 #include "memory_manager/model/details/cuda_memory_utils.hpp"
 
 TEST(ImmutableMemoryModelBuilder, BuildEmpty) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     ImmutableMemoryModelBuilder builder;
     MemoryModel::Ptr model = builder.build();
@@ -19,7 +19,7 @@ TEST(ImmutableMemoryModelBuilder, BuildEmpty) {
 }
 
 TEST(ImmutableMemoryModelBuilder, Build) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     BufferID id1 = 0;
     size_t size1 = 1;
@@ -57,7 +57,7 @@ TEST(ImmutableMemoryModelBuilder, Build) {
 }
 
 TEST(ImmutableMemoryModelBuilder, HandleDuplicateAllocation) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     ImmutableMemoryModelBuilder builder;
 
@@ -78,7 +78,7 @@ TEST(ImmutableMemoryModelBuilder, HandleDuplicateAllocation) {
 }
 
 TEST(ImmutableMemoryModelBuilder, HandleZeroAllocationSize) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     ImmutableMemoryModelBuilder builder;
 
diff --git a/modules/cuda_plugin/tests/unit/memory_manager/model/cuda_memory_model_builder_test.cpp b/modules/nvidia_plugin/tests/unit/memory_manager/model/cuda_memory_model_builder_test.cpp
similarity index 96%
rename from modules/cuda_plugin/tests/unit/memory_manager/model/cuda_memory_model_builder_test.cpp
rename to modules/nvidia_plugin/tests/unit/memory_manager/model/cuda_memory_model_builder_test.cpp
index a1d4e329c..87f1f4e8d 100644
--- a/modules/cuda_plugin/tests/unit/memory_manager/model/cuda_memory_model_builder_test.cpp
+++ b/modules/nvidia_plugin/tests/unit/memory_manager/model/cuda_memory_model_builder_test.cpp
@@ -60,7 +60,7 @@
   MemorySolver correctly.
  */
 TEST(MemoryModelBuilder, Build) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     MemoryModelBuilder builder;
     const size_t size = 1;
@@ -92,7 +92,7 @@ TEST(MemoryModelBuilder, Build) {
 }
 
 TEST(MemoryModelBuilder, HandleDuplicateAllocation) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     MemoryModelBuilder builder;
 
@@ -118,7 +118,7 @@ TEST(MemoryModelBuilder, HandleDuplicateAllocation) {
 }
 
 TEST(MemoryModelBuilder, HandleZeroAllocationSize) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     MemoryModelBuilder builder;
 
@@ -138,7 +138,7 @@ TEST(MemoryModelBuilder, HandleZeroAllocationSize) {
  * Just to clarify class behaviour.
  */
 TEST(MemoryModelBuilder, NoAllocations) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     MemoryModelBuilder builder;
     MemoryModel::Ptr model = builder.build();
diff --git a/modules/cuda_plugin/tests/unit/memory_manager/model/cuda_memory_model_test.cpp b/modules/nvidia_plugin/tests/unit/memory_manager/model/cuda_memory_model_test.cpp
similarity index 94%
rename from modules/cuda_plugin/tests/unit/memory_manager/model/cuda_memory_model_test.cpp
rename to modules/nvidia_plugin/tests/unit/memory_manager/model/cuda_memory_model_test.cpp
index 6820516e8..b9410ef43 100644
--- a/modules/cuda_plugin/tests/unit/memory_manager/model/cuda_memory_model_test.cpp
+++ b/modules/nvidia_plugin/tests/unit/memory_manager/model/cuda_memory_model_test.cpp
@@ -9,7 +9,7 @@
 #include <details/ie_exception.hpp>
 
 TEST(MemoryModel, Empty) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     constexpr size_t bsize = 0;
 
@@ -24,7 +24,7 @@ TEST(MemoryModel, Empty) {
 }
 
 TEST(MemoryModel, NotEmpty) {
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
 
     constexpr size_t bsize = 0x354700;
 
diff --git a/modules/cuda_plugin/tests/unit/memory_manager/model/details/cuda_memory_solver_test.cpp b/modules/nvidia_plugin/tests/unit/memory_manager/model/details/cuda_memory_solver_test.cpp
similarity index 88%
rename from modules/cuda_plugin/tests/unit/memory_manager/model/details/cuda_memory_solver_test.cpp
rename to modules/nvidia_plugin/tests/unit/memory_manager/model/details/cuda_memory_solver_test.cpp
index c31b3e7a1..685578bb8 100644
--- a/modules/cuda_plugin/tests/unit/memory_manager/model/details/cuda_memory_solver_test.cpp
+++ b/modules/nvidia_plugin/tests/unit/memory_manager/model/details/cuda_memory_solver_test.cpp
@@ -10,32 +10,32 @@
 
 #include "details/ie_exception.hpp"
 
-using Box = CUDAPlugin::MemorySolver::Box;
+using Box = ov::nvidia_gpu::MemorySolver::Box;
 
 TEST(MemSolverTest, CanConstruct) {
     {  // Empty vector<Box>
-        CUDAPlugin::MemorySolver ms(std::vector<Box>{});
+        ov::nvidia_gpu::MemorySolver ms(std::vector<Box>{});
     }
 
     {  // vector with default Box
-        CUDAPlugin::MemorySolver ms(std::vector<Box>{{}});
+        ov::nvidia_gpu::MemorySolver ms(std::vector<Box>{{}});
     }
 
     {  // vector with Box with non-default Box
-        CUDAPlugin::MemorySolver ms(std::vector<Box>{{1, 3, 3}});
+        ov::nvidia_gpu::MemorySolver ms(std::vector<Box>{{1, 3, 3}});
     }
 
     {  // vector with Box with size == 0
-        CUDAPlugin::MemorySolver ms(std::vector<Box>{{0, 0, 0}});
+        ov::nvidia_gpu::MemorySolver ms(std::vector<Box>{{0, 0, 0}});
     }
 
     {  // vector with Box with finish == -1
-        CUDAPlugin::MemorySolver ms(std::vector<Box>{{3, -1, 6}});
+        ov::nvidia_gpu::MemorySolver ms(std::vector<Box>{{3, -1, 6}});
     }
 
     // TODO: enable after implement TODO from src/mkldnn_plugin/mkldnn_memory_solver.cpp#L17
     //  {   // vector with Box with negative values
-    //      CUDAPlugin::MemorySolver ms(std::vector<Box> {{-5, -5, -5, -5}});
+    //      ov::nvidia_gpu::MemorySolver ms(std::vector<Box> {{-5, -5, -5, -5}});
     //  }
 }
 
@@ -49,7 +49,7 @@ TEST(MemSolverTest, GetOffset) {
         {n, ++n, 2, 3},  //      0  1  2  3  4
     };
 
-    CUDAPlugin::MemorySolver ms(boxes);
+    ov::nvidia_gpu::MemorySolver ms(boxes);
     ms.solve();
 
     //  The correct answer is [0, 2, 0, 2] or [2, 0, 2, 0].
@@ -68,7 +68,7 @@ TEST(MemSolverTest, GetOffsetThrowException) {
         {n, ++n, 2, id++},  //      0  1  2  3  4
     };
 
-    CUDAPlugin::MemorySolver ms(boxes);
+    ov::nvidia_gpu::MemorySolver ms(boxes);
     ms.solve();
 
     EXPECT_THROW(ms.getOffset(100), InferenceEngine::details::InferenceEngineException);
@@ -83,7 +83,7 @@ TEST(MemSolverTest, LinearAndEven) {
         {n, ++n, 2},  //  |__|____||____|__
     };                //      0  1  2  3
 
-    CUDAPlugin::MemorySolver ms(boxes);
+    ov::nvidia_gpu::MemorySolver ms(boxes);
     EXPECT_EQ(ms.solve(), 4);
     EXPECT_EQ(ms.maxDepth(), 4);
     EXPECT_EQ(ms.maxTopDepth(), 2);
@@ -98,7 +98,7 @@ TEST(MemSolverTest, LinearAndNotEven) {
         {n, ++n, 3},  //  |__|____||____|__
     };                //      0  1  2  3
 
-    CUDAPlugin::MemorySolver ms(boxes);
+    ov::nvidia_gpu::MemorySolver ms(boxes);
     EXPECT_EQ(ms.solve(), 5);
     EXPECT_EQ(ms.maxDepth(), 5);
     EXPECT_EQ(ms.maxTopDepth(), 2);
@@ -113,7 +113,7 @@ TEST(MemSolverTest, LinearWithEmptyExecIndexes) {
         {n, n += 2, 3},  //  |__|_______|___|_______|__
     };                   //      2  3  4  5  6  7  8
 
-    CUDAPlugin::MemorySolver ms(boxes);
+    ov::nvidia_gpu::MemorySolver ms(boxes);
     EXPECT_EQ(ms.solve(), 5);
     EXPECT_EQ(ms.maxDepth(), 5);
     EXPECT_EQ(ms.maxTopDepth(), 2);
@@ -128,7 +128,7 @@ TEST(MemSolverTest, DISABLED_Unefficiency) {
         {2, 3, 2},  //      2  3  4  5  6  7  8
     };
 
-    CUDAPlugin::MemorySolver ms(boxes);
+    ov::nvidia_gpu::MemorySolver ms(boxes);
     EXPECT_EQ(ms.solve(), 5);  // currently we have answer 6
     EXPECT_EQ(ms.maxDepth(), 5);
     EXPECT_EQ(ms.maxTopDepth(), 2);
@@ -143,7 +143,7 @@ TEST(MemSolverTest, OverlappingBoxes) {
         {2, 3, 2},  //      2  3  4  5  6  7  8
     };
 
-    CUDAPlugin::MemorySolver ms(boxes);
+    ov::nvidia_gpu::MemorySolver ms(boxes);
     EXPECT_EQ(ms.solve(), 6);
     EXPECT_EQ(ms.maxDepth(), 6);
     EXPECT_EQ(ms.maxTopDepth(), 2);
@@ -159,7 +159,7 @@ TEST(MemSolverTest, EndOnSeveralBegins) {
         {3, 4, 2},  //      0  1  2  3  4  5  6
     };
 
-    CUDAPlugin::MemorySolver ms(boxes);
+    ov::nvidia_gpu::MemorySolver ms(boxes);
     EXPECT_EQ(ms.solve(), 6);
     EXPECT_EQ(ms.maxDepth(), 6);
     EXPECT_EQ(ms.maxTopDepth(), 3);
@@ -175,7 +175,7 @@ TEST(MemSolverTest, ToEndBoxes) {
         {3, 4, 2},   //      0  1  2  3  4  5  6
     };
 
-    CUDAPlugin::MemorySolver ms(boxes);
+    ov::nvidia_gpu::MemorySolver ms(boxes);
     EXPECT_EQ(ms.solve(), 8);
     EXPECT_EQ(ms.maxDepth(), 8);
     EXPECT_EQ(ms.maxTopDepth(), 4);
@@ -191,7 +191,7 @@ TEST(MemSolverTest, LastAndToEndBox) {
         {3, 4, 2},   //      0  1  2  3  4  5  6
     };
 
-    CUDAPlugin::MemorySolver ms(boxes);
+    ov::nvidia_gpu::MemorySolver ms(boxes);
     EXPECT_EQ(ms.solve(), 6);
     EXPECT_EQ(ms.maxDepth(), 6);
     EXPECT_EQ(ms.maxTopDepth(), 3);
@@ -228,7 +228,7 @@ TEST(MemSolverTest, OptimalAlexnet) {
     for (const auto &sh : shapes) boxes.push_back({n, ++n, sh[0] * sh[1] * sh[2]});
 
     // For linear topology bottom score is reachable minRequired == maxDepth
-    CUDAPlugin::MemorySolver ms(boxes);
+    ov::nvidia_gpu::MemorySolver ms(boxes);
     EXPECT_EQ(ms.solve(), ms.maxDepth());
     EXPECT_EQ(ms.maxTopDepth(), 2);
 }
@@ -243,7 +243,7 @@ TEST(MemSolverTest, NoOverlapping) {
         {2, 4, 2, n++},  //      2  3  4  5  6  7  8
     };
 
-    CUDAPlugin::MemorySolver ms(boxes);
+    ov::nvidia_gpu::MemorySolver ms(boxes);
     ms.solve();
     // TODO: Current algorithm doesn't solve that case. Uncomment check to see inefficiency
     // EXPECT_EQ(ms.solve(), 5);
@@ -269,7 +269,7 @@ TEST(MemSolverTest, BestSolution1) {
         {6, 7, 3, n++},  //      2  3  4  5  6  7  8
     };
 
-    CUDAPlugin::MemorySolver ms(boxes);
+    ov::nvidia_gpu::MemorySolver ms(boxes);
     EXPECT_EQ(ms.solve(), 5);
 
     auto no_overlap = [&](Box box1, Box box2) -> bool {
diff --git a/modules/cuda_plugin/tests/unit/memory_manager/model/details/cuda_memory_utils_test.cpp b/modules/nvidia_plugin/tests/unit/memory_manager/model/details/cuda_memory_utils_test.cpp
similarity index 95%
rename from modules/cuda_plugin/tests/unit/memory_manager/model/details/cuda_memory_utils_test.cpp
rename to modules/nvidia_plugin/tests/unit/memory_manager/model/details/cuda_memory_utils_test.cpp
index 730767f37..82287aaa7 100644
--- a/modules/cuda_plugin/tests/unit/memory_manager/model/details/cuda_memory_utils_test.cpp
+++ b/modules/nvidia_plugin/tests/unit/memory_manager/model/details/cuda_memory_utils_test.cpp
@@ -9,7 +9,7 @@
 TEST(MemoryUtils, ApplyAllignment) {
     const size_t allignment = 256;
 
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
     ASSERT_EQ(applyAllignment(0), 0);
     ASSERT_EQ(applyAllignment(1), allignment);
 
diff --git a/modules/cuda_plugin/tests/unit/memory_pool.cpp b/modules/nvidia_plugin/tests/unit/memory_pool.cpp
similarity index 98%
rename from modules/cuda_plugin/tests/unit/memory_pool.cpp
rename to modules/nvidia_plugin/tests/unit/memory_pool.cpp
index bebcf139f..ccc9b5d1c 100644
--- a/modules/cuda_plugin/tests/unit/memory_pool.cpp
+++ b/modules/nvidia_plugin/tests/unit/memory_pool.cpp
@@ -14,7 +14,7 @@
 #include <threading/ie_executor_manager.hpp>
 #include <typeinfo>
 
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 
 class MemoryPoolTest : public testing::Test {
     void SetUp() override {}
diff --git a/modules/cuda_plugin/tests/unit/nodes/parameter_stub_node.hpp b/modules/nvidia_plugin/tests/unit/nodes/parameter_stub_node.hpp
similarity index 100%
rename from modules/cuda_plugin/tests/unit/nodes/parameter_stub_node.hpp
rename to modules/nvidia_plugin/tests/unit/nodes/parameter_stub_node.hpp
diff --git a/modules/cuda_plugin/tests/unit/nodes/result_stub_node.hpp b/modules/nvidia_plugin/tests/unit/nodes/result_stub_node.hpp
similarity index 100%
rename from modules/cuda_plugin/tests/unit/nodes/result_stub_node.hpp
rename to modules/nvidia_plugin/tests/unit/nodes/result_stub_node.hpp
diff --git a/modules/cuda_plugin/tests/unit/op_buffers_extractor_test.cpp b/modules/nvidia_plugin/tests/unit/op_buffers_extractor_test.cpp
similarity index 96%
rename from modules/cuda_plugin/tests/unit/op_buffers_extractor_test.cpp
rename to modules/nvidia_plugin/tests/unit/op_buffers_extractor_test.cpp
index 9ce1fe042..f49803395 100644
--- a/modules/cuda_plugin/tests/unit/op_buffers_extractor_test.cpp
+++ b/modules/nvidia_plugin/tests/unit/op_buffers_extractor_test.cpp
@@ -14,7 +14,7 @@
 #include <vector>
 
 /*
- * TODO: To be moved to functional tests once they are enabled for CUDAPlugin
+ * TODO: To be moved to functional tests once they are enabled for nvidia_gpu
  * */
 
 class OperationBufferExtractorTest : public testing::Test {
@@ -71,13 +71,13 @@ class OperationBufferExtractorTest : public testing::Test {
         ngraph_function_ = std::make_unique<ngraph::Function>(outputs, inputs, "SimpleGraph");
 
         exec_sequence_ = ngraph_function_->get_ordered_ops();
-        extractor_ = std::make_unique<CUDAPlugin::OperationBuffersExtractor>(exec_sequence_);
-        CUDAPlugin::WorkbufferRequest request{{128}, {256}};
+        extractor_ = std::make_unique<ov::nvidia_gpu::OperationBuffersExtractor>(exec_sequence_);
+        ov::nvidia_gpu::WorkbufferRequest request{{128}, {256}};
         buffer_indices_ = extractor_->processWorkbufferRequest(squeeze_id, request);
     }
 
 protected:
-    using TensorID = CUDAPlugin::TensorID;
+    using TensorID = ov::nvidia_gpu::TensorID;
 
     struct OpIndex {
         using Type = size_t;
@@ -133,8 +133,8 @@ class OperationBufferExtractorTest : public testing::Test {
 protected:
     std::unique_ptr<ngraph::Function> ngraph_function_;
     std::vector<std::shared_ptr<ov::Node>> exec_sequence_;
-    std::unique_ptr<CUDAPlugin::OperationBuffersExtractor> extractor_;
-    CUDAPlugin::WorkbufferIds buffer_indices_;
+    std::unique_ptr<ov::nvidia_gpu::OperationBuffersExtractor> extractor_;
+    ov::nvidia_gpu::WorkbufferIds buffer_indices_;
 };
 
 TEST_F(OperationBufferExtractorTest, CheckTestIntegrity) {
@@ -296,7 +296,7 @@ TEST_F(OperationBufferExtractorTest, CheckMutableWorkbufferIndices) {
 }
 
 TEST_F(OperationBufferExtractorTest, CheckImmutableWorkbufferIndices) {
-    using CUDAPlugin::WorkbufferRequest;
+    using ov::nvidia_gpu::WorkbufferRequest;
     using ::testing::ElementsAre;
     WorkbufferRequest request{{246}, {}};
     ASSERT_THAT(buffer_indices_.immutableIds, ElementsAre(OutputBufferIndex::Squeeze_Imutable_Workbuffer));
@@ -328,7 +328,7 @@ class OperationBufferExtractorConcatOptimizedTest : public testing::Test {
             std::make_shared<ngraph::opset1::Constant>(ov::element::f32, ov::Shape{1, 8, 16, 16}, adder_0_values);
         auto add_0 = std::make_shared<ngraph::opset1::Add>(multiplier, adder_0);
 
-        auto concat = std::make_shared<CUDAPlugin::nodes::ConcatOptimized>(ov::OutputVector{multiply, add_0}, 1);
+        auto concat = std::make_shared<ov::nvidia_gpu::nodes::ConcatOptimized>(ov::OutputVector{multiply, add_0}, 1);
 
         std::vector<float> adder_1_values = {0.55};
         auto adder_1 =
@@ -345,11 +345,11 @@ class OperationBufferExtractorConcatOptimizedTest : public testing::Test {
         ngraph_function_ = std::make_unique<ngraph::Function>(outputs, inputs, "ConcatOptimizedGraph");
 
         exec_sequence_ = ngraph_function_->get_ordered_ops();
-        extractor_ = std::make_unique<CUDAPlugin::OperationBuffersExtractor>(exec_sequence_);
+        extractor_ = std::make_unique<ov::nvidia_gpu::OperationBuffersExtractor>(exec_sequence_);
     }
 
 protected:
-    using TensorID = CUDAPlugin::TensorID;
+    using TensorID = ov::nvidia_gpu::TensorID;
 
     struct OpIndex {
         using Type = size_t;
@@ -397,12 +397,12 @@ class OperationBufferExtractorConcatOptimizedTest : public testing::Test {
 protected:
     std::unique_ptr<ngraph::Function> ngraph_function_;
     std::vector<std::shared_ptr<ov::Node>> exec_sequence_;
-    std::unique_ptr<CUDAPlugin::OperationBuffersExtractor> extractor_;
+    std::unique_ptr<ov::nvidia_gpu::OperationBuffersExtractor> extractor_;
 };
 
 TEST_F(OperationBufferExtractorConcatOptimizedTest, CheckTestIntegrity) {
     using namespace ngraph;
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
     EXPECT_TRUE(is_type<opset1::Parameter>(exec_sequence_.at(OpIndex::Parameter)));
     EXPECT_TRUE(is_type<opset1::Constant>(exec_sequence_.at(OpIndex::Constant_Multiplier)));
     EXPECT_TRUE(is_type<opset1::Constant>(exec_sequence_.at(OpIndex::Constant_Adder_0)));
@@ -466,7 +466,7 @@ class OperationBufferExtractorConcatOptimizedV2Test : public testing::Test {
             ov::element::i32, ov::Shape{4}, std::vector<int32_t>{1, 8, 16, 16});
         auto reshape0 = std::make_shared<ngraph::opset1::Reshape>(multiply, reshape_const, true);
 
-        auto concat = std::make_shared<CUDAPlugin::nodes::ConcatOptimized>(ov::OutputVector{reshape0, add_0}, 1);
+        auto concat = std::make_shared<ov::nvidia_gpu::nodes::ConcatOptimized>(ov::OutputVector{reshape0, add_0}, 1);
 
         std::vector<float> adder_1_values = {0.55};
         auto adder_1 =
@@ -483,11 +483,11 @@ class OperationBufferExtractorConcatOptimizedV2Test : public testing::Test {
         ngraph_function_ = std::make_unique<ngraph::Function>(outputs, inputs, "ConcatOptimizedGraph");
 
         exec_sequence_ = ngraph_function_->get_ordered_ops();
-        extractor_ = std::make_unique<CUDAPlugin::OperationBuffersExtractor>(exec_sequence_);
+        extractor_ = std::make_unique<ov::nvidia_gpu::OperationBuffersExtractor>(exec_sequence_);
     }
 
 protected:
-    using TensorID = CUDAPlugin::TensorID;
+    using TensorID = ov::nvidia_gpu::TensorID;
 
     struct OpIndex {
         using Type = size_t;
@@ -538,12 +538,12 @@ class OperationBufferExtractorConcatOptimizedV2Test : public testing::Test {
 protected:
     std::unique_ptr<ngraph::Function> ngraph_function_;
     std::vector<std::shared_ptr<ov::Node>> exec_sequence_;
-    std::unique_ptr<CUDAPlugin::OperationBuffersExtractor> extractor_;
+    std::unique_ptr<ov::nvidia_gpu::OperationBuffersExtractor> extractor_;
 };
 
 TEST_F(OperationBufferExtractorConcatOptimizedV2Test, CheckTestIntegrity) {
     using namespace ngraph;
-    using namespace CUDAPlugin;
+    using namespace ov::nvidia_gpu;
     EXPECT_TRUE(is_type<opset1::Parameter>(exec_sequence_.at(OpIndex::Parameter)));
     EXPECT_TRUE(is_type<opset1::Constant>(exec_sequence_.at(OpIndex::Constant_Multiplier)));
     EXPECT_TRUE(is_type<opset1::Constant>(exec_sequence_.at(OpIndex::Constant_Adder_0)));
diff --git a/modules/cuda_plugin/tests/unit/operation_registry.cpp b/modules/nvidia_plugin/tests/unit/operation_registry.cpp
similarity index 99%
rename from modules/cuda_plugin/tests/unit/operation_registry.cpp
rename to modules/nvidia_plugin/tests/unit/operation_registry.cpp
index b1d995eaf..39645f1c2 100644
--- a/modules/cuda_plugin/tests/unit/operation_registry.cpp
+++ b/modules/nvidia_plugin/tests/unit/operation_registry.cpp
@@ -11,7 +11,7 @@
 #include <typeinfo>
 #include <vector>
 
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 
 class OperationRegistryTest : public testing::Test {
     void SetUp() override {}
diff --git a/modules/cuda_plugin/tests/unit/parameter.cpp b/modules/nvidia_plugin/tests/unit/parameter.cpp
similarity index 92%
rename from modules/cuda_plugin/tests/unit/parameter.cpp
rename to modules/nvidia_plugin/tests/unit/parameter.cpp
index 05b292841..913b4cc50 100644
--- a/modules/cuda_plugin/tests/unit/parameter.cpp
+++ b/modules/nvidia_plugin/tests/unit/parameter.cpp
@@ -15,7 +15,7 @@
 #include "nodes/parameter_stub_node.hpp"
 
 using namespace InferenceEngine;
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 using devptr_t = DevicePointer<void*>;
 
 /**
@@ -47,8 +47,8 @@ struct ParameterTest : testing::Test {
         const bool optimizeOption = false;
         auto& registry{OperationRegistry::getInstance()};
         auto node = std::make_shared<ParameterStubNode>();
-        auto inputIDs = std::vector<CUDAPlugin::TensorID>{};
-        auto outputIDs = std::vector<CUDAPlugin::TensorID>{CUDAPlugin::TensorID{0}};
+        auto inputIDs = std::vector<ov::nvidia_gpu::TensorID>{};
+        auto outputIDs = std::vector<ov::nvidia_gpu::TensorID>{ov::nvidia_gpu::TensorID{0}};
         node->set_friendly_name(ParameterStubNode::type_info.name);
         ASSERT_TRUE(registry.hasOperation(node));
         operation = registry.createOperation(CreationContext{device, optimizeOption}, node, inputIDs, outputIDs);
@@ -98,8 +98,8 @@ TEST_F(ParameterTest, canExecuteSync) {
 
 TEST_F(ParameterTest, canExecuteAsync) {
     CancellationToken token{};
-    CUDAPlugin::CudaGraph graph{CreationContext{CUDA::Device{}, false}, {}};
-    CUDAPlugin::Profiler profiler{false, graph};
+    ov::nvidia_gpu::CudaGraph graph{CreationContext{CUDA::Device{}, false}, {}};
+    ov::nvidia_gpu::Profiler profiler{false, graph};
     InferenceRequestContext context{blobs, blobsMapping, emptyTensor, emptyMapping, threadContext, token, profiler};
     auto& stream = context.getThreadContext().stream();
     operation->Execute(context, inputs, outputs, {});
diff --git a/modules/cuda_plugin/tests/unit/plugin.cpp b/modules/nvidia_plugin/tests/unit/plugin.cpp
similarity index 99%
rename from modules/cuda_plugin/tests/unit/plugin.cpp
rename to modules/nvidia_plugin/tests/unit/plugin.cpp
index d19aea998..1378ebee1 100644
--- a/modules/cuda_plugin/tests/unit/plugin.cpp
+++ b/modules/nvidia_plugin/tests/unit/plugin.cpp
@@ -22,7 +22,7 @@
 #include "test_networks.hpp"
 
 using namespace InferenceEngine;
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 
 using devptr_t = DevicePointer<void*>;
 using cdevptr_t = DevicePointer<const void*>;
diff --git a/modules/cuda_plugin/tests/unit/pooling_tests.cpp b/modules/nvidia_plugin/tests/unit/pooling_tests.cpp
similarity index 99%
rename from modules/cuda_plugin/tests/unit/pooling_tests.cpp
rename to modules/nvidia_plugin/tests/unit/pooling_tests.cpp
index f5f80744f..3a83fd54d 100644
--- a/modules/cuda_plugin/tests/unit/pooling_tests.cpp
+++ b/modules/nvidia_plugin/tests/unit/pooling_tests.cpp
@@ -20,7 +20,7 @@
 #include <type_traits>
 
 using namespace InferenceEngine;
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 
 static const ov::Shape min_supported_pooling_shape{1, 1, 4, 4};
 static const ov::Shape dummy_kernel{2, 2};
diff --git a/modules/cuda_plugin/tests/unit/relu.cpp b/modules/nvidia_plugin/tests/unit/relu.cpp
similarity index 80%
rename from modules/cuda_plugin/tests/unit/relu.cpp
rename to modules/nvidia_plugin/tests/unit/relu.cpp
index 985acb123..7f15e1334 100644
--- a/modules/cuda_plugin/tests/unit/relu.cpp
+++ b/modules/nvidia_plugin/tests/unit/relu.cpp
@@ -23,7 +23,7 @@ auto assertToThrow(F&& f,
                    const std::experimental::source_location& loc = std::experimental::source_location::current()) {
     bool success = false;
     std::forward<F>(f)(success);
-    if (!success) CUDAPlugin::throwIEException("pathetic google test failed in non-void function", loc);
+    if (!success) ov::nvidia_gpu::throwIEException("pathetic google test failed in non-void function", loc);
 }
 
 #define TASSERT_TRUE(condition)                \
@@ -33,25 +33,25 @@ auto assertToThrow(F&& f,
     })
 
 struct ReluTest : testing::Test {
-    using TensorID = CUDAPlugin::TensorID;
+    using TensorID = ov::nvidia_gpu::TensorID;
     using ElementType = float;
     static constexpr int length = 5;
     static constexpr size_t size = length * sizeof(ElementType);
-    CUDAPlugin::ThreadContext threadContext{{}};
+    ov::nvidia_gpu::ThreadContext threadContext{{}};
     CUDA::Allocation inAlloc = threadContext.stream().malloc(size);
     CUDA::Allocation outAlloc = threadContext.stream().malloc(size);
     std::vector<cdevptr_t> inputs{inAlloc};
     std::vector<devptr_t> outputs{outAlloc};
     std::vector<std::shared_ptr<ngraph::runtime::Tensor>> emptyTensor;
     std::map<std::string, std::size_t> emptyMapping;
-    CUDAPlugin::OperationBase::Ptr operation = [this] {
+    ov::nvidia_gpu::OperationBase::Ptr operation = [this] {
         CUDA::Device device{};
         const bool optimizeOption = false;
         auto param = std::make_shared<ov::op::v0::Parameter>(ov::element::f32, ov::PartialShape{length});
         auto node = std::make_shared<ov::op::v0::Relu>(param->output(0));
-        auto& registry = CUDAPlugin::OperationRegistry::getInstance();
+        auto& registry = ov::nvidia_gpu::OperationRegistry::getInstance();
         TASSERT_TRUE(registry.hasOperation(node));
-        auto op = registry.createOperation(CUDAPlugin::CreationContext{device, optimizeOption},
+        auto op = registry.createOperation(ov::nvidia_gpu::CreationContext{device, optimizeOption},
                                            node,
                                            std::vector<TensorID>{TensorID{0u}},
                                            std::vector<TensorID>{TensorID{0u}});
@@ -61,10 +61,10 @@ struct ReluTest : testing::Test {
 };
 
 TEST_F(ReluTest, canExecuteSync) {
-    CUDAPlugin::CancellationToken token{};
-    CUDAPlugin::CudaGraph graph{CUDAPlugin::CreationContext{CUDA::Device{}, false}, {}};
-    CUDAPlugin::Profiler profiler{false, graph};
-    CUDAPlugin::InferenceRequestContext context{
+    ov::nvidia_gpu::CancellationToken token{};
+    ov::nvidia_gpu::CudaGraph graph{ov::nvidia_gpu::CreationContext{CUDA::Device{}, false}, {}};
+    ov::nvidia_gpu::Profiler profiler{false, graph};
+    ov::nvidia_gpu::InferenceRequestContext context{
         emptyTensor, emptyMapping, emptyTensor, emptyMapping, threadContext, token, profiler};
     auto& stream = context.getThreadContext().stream();
     std::array<ElementType, length> in{-1, 1, -5, 5, 0};
diff --git a/modules/cuda_plugin/tests/unit/result.cpp b/modules/nvidia_plugin/tests/unit/result.cpp
similarity index 99%
rename from modules/cuda_plugin/tests/unit/result.cpp
rename to modules/nvidia_plugin/tests/unit/result.cpp
index 65a03efeb..e0e4c3124 100644
--- a/modules/cuda_plugin/tests/unit/result.cpp
+++ b/modules/nvidia_plugin/tests/unit/result.cpp
@@ -18,7 +18,7 @@
 #include "nodes/result_stub_node.hpp"
 
 using namespace InferenceEngine;
-using namespace CUDAPlugin;
+using namespace ov::nvidia_gpu;
 using devptr_t = DevicePointer<void*>;
 using cdevptr_t = DevicePointer<const void*>;
 
diff --git a/modules/cuda_plugin/tests/unit/select_benchmark.cpp b/modules/nvidia_plugin/tests/unit/select_benchmark.cpp
similarity index 86%
rename from modules/cuda_plugin/tests/unit/select_benchmark.cpp
rename to modules/nvidia_plugin/tests/unit/select_benchmark.cpp
index bf77cecb7..2869f65ba 100644
--- a/modules/cuda_plugin/tests/unit/select_benchmark.cpp
+++ b/modules/nvidia_plugin/tests/unit/select_benchmark.cpp
@@ -35,7 +35,7 @@ struct SelectTest : testing::Test {
     const size_t elseBufferSize = bufferLength * sizeof(float);
     const size_t outputBufferSize = bufferLength * sizeof(float);
 
-    CUDAPlugin::ThreadContext threadContext{CUDA::Device{}};
+    ov::nvidia_gpu::ThreadContext threadContext{CUDA::Device{}};
     CUDA::Allocation conditionAlloc = threadContext.stream().malloc(conditionBufferSize);
     CUDA::Allocation thenAlloc = threadContext.stream().malloc(thenBufferSize);
     CUDA::Allocation elseAlloc = threadContext.stream().malloc(elseBufferSize);
@@ -54,13 +54,13 @@ struct SelectTest : testing::Test {
         return node;
     };
 
-    CUDAPlugin::OperationBase::Ptr operation = [this] {
+    ov::nvidia_gpu::OperationBase::Ptr operation = [this] {
         const bool optimizeOption = false;
-        auto& registry = CUDAPlugin::OperationRegistry::getInstance();
-        return registry.createOperation(CUDAPlugin::CreationContext{threadContext.device(), optimizeOption},
+        auto& registry = ov::nvidia_gpu::OperationRegistry::getInstance();
+        return registry.createOperation(ov::nvidia_gpu::CreationContext{threadContext.device(), optimizeOption},
                                         create_node(),
-                                        std::vector<CUDAPlugin::TensorID>{CUDAPlugin::TensorID{0u}},
-                                        std::vector<CUDAPlugin::TensorID>{CUDAPlugin::TensorID{0u}});
+                                        std::vector<ov::nvidia_gpu::TensorID>{ov::nvidia_gpu::TensorID{0u}},
+                                        std::vector<ov::nvidia_gpu::TensorID>{ov::nvidia_gpu::TensorID{0u}});
     }();
 };
 
@@ -87,10 +87,10 @@ void fillArrayWithRandomData(std::vector<T>& v) {
 TEST_F(SelectTest, DISABLED_benchmark) {
     using microseconds = std::chrono::duration<double, std::micro>;
     constexpr int kNumAttempts = 20000;
-    CUDAPlugin::CudaGraph graph{CUDAPlugin::CreationContext{CUDA::Device{}, false}, {}};
-    CUDAPlugin::CancellationToken token{};
-    CUDAPlugin::Profiler profiler{false, graph};
-    CUDAPlugin::InferenceRequestContext context{
+    ov::nvidia_gpu::CudaGraph graph{ov::nvidia_gpu::CreationContext{CUDA::Device{}, false}, {}};
+    ov::nvidia_gpu::CancellationToken token{};
+    ov::nvidia_gpu::Profiler profiler{false, graph};
+    ov::nvidia_gpu::InferenceRequestContext context{
         emptyTensor, emptyMapping, emptyTensor, emptyMapping, threadContext, token, profiler};
     auto& stream = context.getThreadContext().stream();
 
@@ -111,7 +111,7 @@ TEST_F(SelectTest, DISABLED_benchmark) {
     CUDA::Allocation thenOffsetAlloc = threadContext.stream().malloc(kOffsetBufferSize);
     CUDA::Allocation elseOffsetAlloc = threadContext.stream().malloc(kOffsetBufferSize);
     CUDA::Allocation outputSizesAlloc = threadContext.stream().malloc(kOffsetBufferSize);
-    CUDAPlugin::Workbuffers workbuffers{};
+    ov::nvidia_gpu::Workbuffers workbuffers{};
     workbuffers.immutable_buffers = {condOffsetAlloc, thenOffsetAlloc, elseOffsetAlloc, outputSizesAlloc};
     operation->InitSharedImmutableWorkbuffers({condOffsetAlloc, thenOffsetAlloc, elseOffsetAlloc, outputSizesAlloc});
 
diff --git a/modules/cuda_plugin/tests/unit/sigmoid_benchmark.cpp b/modules/nvidia_plugin/tests/unit/sigmoid_benchmark.cpp
similarity index 81%
rename from modules/cuda_plugin/tests/unit/sigmoid_benchmark.cpp
rename to modules/nvidia_plugin/tests/unit/sigmoid_benchmark.cpp
index 33aa800f6..53730921d 100644
--- a/modules/cuda_plugin/tests/unit/sigmoid_benchmark.cpp
+++ b/modules/nvidia_plugin/tests/unit/sigmoid_benchmark.cpp
@@ -25,23 +25,23 @@ using devptr_t = CUDA::DevicePointer<void*>;
 using cdevptr_t = CUDA::DevicePointer<const void*>;
 
 struct SigmoidTest : testing::Test {
-    using TensorID = CUDAPlugin::TensorID;
+    using TensorID = ov::nvidia_gpu::TensorID;
     using ElementType = float;
     static constexpr int length = 1024;
     static constexpr size_t size = length * sizeof(ElementType);
-    CUDAPlugin::ThreadContext threadContext{{}};
+    ov::nvidia_gpu::ThreadContext threadContext{{}};
     CUDA::Allocation inAlloc = threadContext.stream().malloc(size);
     CUDA::Allocation outAlloc = threadContext.stream().malloc(size);
     std::vector<cdevptr_t> inputs{inAlloc};
     std::vector<devptr_t> outputs{outAlloc};
     std::vector<std::shared_ptr<ngraph::runtime::Tensor>> emptyTensor;
     std::map<std::string, std::size_t> emptyMapping;
-    CUDAPlugin::OperationBase::Ptr operation = [this] {
+    ov::nvidia_gpu::OperationBase::Ptr operation = [this] {
         const bool optimizeOption = false;
         auto param = std::make_shared<ov::op::v0::Parameter>(ov::element::f32, ov::PartialShape{length});
         auto node = std::make_shared<ov::op::v0::Sigmoid>(param->output(0));
-        auto& registry = CUDAPlugin::OperationRegistry::getInstance();
-        auto op = registry.createOperation(CUDAPlugin::CreationContext{threadContext.device(), optimizeOption},
+        auto& registry = ov::nvidia_gpu::OperationRegistry::getInstance();
+        auto op = registry.createOperation(ov::nvidia_gpu::CreationContext{threadContext.device(), optimizeOption},
                                            node,
                                            std::vector<TensorID>{TensorID{0u}},
                                            std::vector<TensorID>{TensorID{0u}});
@@ -52,10 +52,10 @@ struct SigmoidTest : testing::Test {
 TEST_F(SigmoidTest, DISABLED_benchmark) {
     using microseconds = std::chrono::duration<double, std::micro>;
     constexpr int kNumAttempts = 20;
-    CUDAPlugin::CancellationToken token{};
-    CUDAPlugin::CudaGraph graph{CUDAPlugin::CreationContext{CUDA::Device{}, false}, {}};
-    CUDAPlugin::Profiler profiler{false, graph};
-    CUDAPlugin::InferenceRequestContext context{
+    ov::nvidia_gpu::CancellationToken token{};
+    ov::nvidia_gpu::CudaGraph graph{ov::nvidia_gpu::CreationContext{CUDA::Device{}, false}, {}};
+    ov::nvidia_gpu::Profiler profiler{false, graph};
+    ov::nvidia_gpu::InferenceRequestContext context{
         emptyTensor, emptyMapping, emptyTensor, emptyMapping, threadContext, token, profiler};
     auto& stream = context.getThreadContext().stream();
     std::array<ElementType, length> in;
@@ -65,7 +65,7 @@ TEST_F(SigmoidTest, DISABLED_benchmark) {
     auto gen = [&dist, &mersenne_engine]() { return 10.f * dist(mersenne_engine) / std::numeric_limits<int>::max(); };
     std::generate(in.begin(), in.end(), gen);
     stream.upload(inAlloc, in.data(), size);
-    CUDAPlugin::Workbuffers workbuffers{};
+    ov::nvidia_gpu::Workbuffers workbuffers{};
     auto start = std::chrono::steady_clock::now();
     for (int i = 0; i < kNumAttempts; i++) {
         operation->Execute(context, inputs, outputs, workbuffers);
diff --git a/modules/cuda_plugin/tests/unit/skip_tests_config.cpp b/modules/nvidia_plugin/tests/unit/skip_tests_config.cpp
similarity index 100%
rename from modules/cuda_plugin/tests/unit/skip_tests_config.cpp
rename to modules/nvidia_plugin/tests/unit/skip_tests_config.cpp
diff --git a/modules/cuda_plugin/tests/unit/strided_slice_benchmark.cpp b/modules/nvidia_plugin/tests/unit/strided_slice_benchmark.cpp
similarity index 85%
rename from modules/cuda_plugin/tests/unit/strided_slice_benchmark.cpp
rename to modules/nvidia_plugin/tests/unit/strided_slice_benchmark.cpp
index db7cd4529..7f682a670 100644
--- a/modules/cuda_plugin/tests/unit/strided_slice_benchmark.cpp
+++ b/modules/nvidia_plugin/tests/unit/strided_slice_benchmark.cpp
@@ -35,7 +35,7 @@ struct StridedSliceTest : testing::Test {
     const ov::Shape constTensorShape{3};
     const size_t constantTensorSize = ov::shape_size(constTensorShape) * sizeof(AuxilaryElementType);
 
-    CUDAPlugin::ThreadContext threadContext{{}};
+    ov::nvidia_gpu::ThreadContext threadContext{{}};
     CUDA::Allocation inAlloc = threadContext.stream().malloc(inputBufferSize);
     CUDA::Allocation inBeginAlloc = threadContext.stream().malloc(constantTensorSize);
     CUDA::Allocation inEndAlloc = threadContext.stream().malloc(constantTensorSize);
@@ -64,23 +64,23 @@ struct StridedSliceTest : testing::Test {
         return node;
     };
 
-    CUDAPlugin::OperationBase::Ptr operation = [this] {
+    ov::nvidia_gpu::OperationBase::Ptr operation = [this] {
         const bool optimizeOption = false;
-        auto& registry = CUDAPlugin::OperationRegistry::getInstance();
-        return registry.createOperation(CUDAPlugin::CreationContext{threadContext.device(), optimizeOption},
+        auto& registry = ov::nvidia_gpu::OperationRegistry::getInstance();
+        return registry.createOperation(ov::nvidia_gpu::CreationContext{threadContext.device(), optimizeOption},
                                         create_node(),
-                                        std::vector<CUDAPlugin::TensorID>{CUDAPlugin::TensorID{0u}},
-                                        std::vector<CUDAPlugin::TensorID>{CUDAPlugin::TensorID{0u}});
+                                        std::vector<ov::nvidia_gpu::TensorID>{ov::nvidia_gpu::TensorID{0u}},
+                                        std::vector<ov::nvidia_gpu::TensorID>{ov::nvidia_gpu::TensorID{0u}});
     }();
 };
 
 TEST_F(StridedSliceTest, DISABLED_benchmark) {
     using microseconds = std::chrono::duration<double, std::micro>;
     constexpr int kNumAttempts = 20000;
-    CUDAPlugin::CancellationToken token{};
-    CUDAPlugin::CudaGraph graph{CUDAPlugin::CreationContext{CUDA::Device{}, false}, {}};
-    CUDAPlugin::Profiler profiler{false, graph};
-    CUDAPlugin::InferenceRequestContext context{
+    ov::nvidia_gpu::CancellationToken token{};
+    ov::nvidia_gpu::CudaGraph graph{ov::nvidia_gpu::CreationContext{CUDA::Device{}, false}, {}};
+    ov::nvidia_gpu::Profiler profiler{false, graph};
+    ov::nvidia_gpu::InferenceRequestContext context{
         emptyTensor, emptyMapping, emptyTensor, emptyMapping, threadContext, token, profiler};
     auto& stream = context.getThreadContext().stream();
     std::vector<ElementType> in(inputBufferLength);
@@ -92,7 +92,7 @@ TEST_F(StridedSliceTest, DISABLED_benchmark) {
     stream.upload(inAlloc, in.data(), inputBufferSize);
     auto wb_request = operation->GetWorkBufferRequest();
     ASSERT_EQ(wb_request.immutable_sizes.size(), 5);
-    CUDAPlugin::Workbuffers workbuffers;
+    ov::nvidia_gpu::Workbuffers workbuffers;
     workbuffers.immutable_buffers = {srcShapeSizesAlloc, dstShapeSizesAlloc, inBeginAlloc, inEndAlloc, inStrideAlloc};
     operation->InitSharedImmutableWorkbuffers(
         {srcShapeSizesAlloc, dstShapeSizesAlloc, inBeginAlloc, inEndAlloc, inStrideAlloc});
diff --git a/modules/cuda_plugin/tests/unit/test_networks.hpp b/modules/nvidia_plugin/tests/unit/test_networks.hpp
similarity index 100%
rename from modules/cuda_plugin/tests/unit/test_networks.hpp
rename to modules/nvidia_plugin/tests/unit/test_networks.hpp
diff --git a/modules/cuda_plugin/tests/unit/typed_functor.cpp b/modules/nvidia_plugin/tests/unit/typed_functor.cpp
similarity index 95%
rename from modules/cuda_plugin/tests/unit/typed_functor.cpp
rename to modules/nvidia_plugin/tests/unit/typed_functor.cpp
index 8738f4564..61b3b79ce 100644
--- a/modules/cuda_plugin/tests/unit/typed_functor.cpp
+++ b/modules/nvidia_plugin/tests/unit/typed_functor.cpp
@@ -7,7 +7,7 @@
 #include <gmock/gmock.h>
 #include <gtest/gtest.h>
 
-using namespace CUDAPlugin::kernel;
+using namespace ov::nvidia_gpu::kernel;
 
 using TFuncPtr = void (*)();
 
diff --git a/modules/cuda_plugin/utils/check.sh b/modules/nvidia_plugin/utils/check.sh
similarity index 84%
rename from modules/cuda_plugin/utils/check.sh
rename to modules/nvidia_plugin/utils/check.sh
index 47d9b7256..18a34b9c4 100755
--- a/modules/cuda_plugin/utils/check.sh
+++ b/modules/nvidia_plugin/utils/check.sh
@@ -22,7 +22,7 @@ cd "$(git rev-parse --show-toplevel)"
 git diff --diff-filter=ACMR -U0 origin/master... | perl -ne '
   if (m|^\+\+\+ b/(.*)|) {
     $newname = $1;
-    if ($name =~ /^.+cuda_plugin.+((\.cpp)|(\.hpp)|(\.h)|(\.cu)|(\.cuh))$/) {
+    if ($name =~ /^.+nvidia_plugin.+((\.cpp)|(\.hpp)|(\.h)|(\.cu)|(\.cuh))$/) {
       print "clang-format'$ver'$lines -Werror -dry-run -style=file $name\n"
     }
     $name = $newname;
@@ -33,7 +33,7 @@ git diff --diff-filter=ACMR -U0 origin/master... | perl -ne '
     $lines = "$lines -lines=$1:$to"
   }
   END {
-    if ($name =~ /^.+cuda_plugin.+((\.cpp)|(\.hpp)|(\.h)|(\.cu)|(\.cuh))$/) {
+    if ($name =~ /^.+nvidia_plugin.+((\.cpp)|(\.hpp)|(\.h)|(\.cu)|(\.cuh))$/) {
       print "clang-format'$ver'$lines -Werror -dry-run -style=file $name\n"
     }
   }' | parallel
diff --git a/modules/cuda_plugin/utils/cuda-sanitizer.sh b/modules/nvidia_plugin/utils/cuda-sanitizer.sh
similarity index 97%
rename from modules/cuda_plugin/utils/cuda-sanitizer.sh
rename to modules/nvidia_plugin/utils/cuda-sanitizer.sh
index df43ae0fd..0814a84c8 100755
--- a/modules/cuda_plugin/utils/cuda-sanitizer.sh
+++ b/modules/nvidia_plugin/utils/cuda-sanitizer.sh
@@ -6,7 +6,7 @@ TESTED_TOOL_CMD_LINE=$@
 
 # =======================================================================================
 # common
-CUDASAN_KERNEL_FILTER="--filter kernel_substring=CUDAPlugin"
+CUDASAN_KERNEL_FILTER="--filter kernel_substring=nvidia_gpu"
 CUDASAN_COMMON_ARGS="--print-level=warn --print-limit=100 --error-exitcode=1"
 
 # =======================================================================================
diff --git a/modules/cuda_plugin/utils/format.sh b/modules/nvidia_plugin/utils/format.sh
similarity index 100%
rename from modules/cuda_plugin/utils/format.sh
rename to modules/nvidia_plugin/utils/format.sh
diff --git a/modules/cuda_plugin/utils/install-pre-push.sh b/modules/nvidia_plugin/utils/install-pre-push.sh
similarity index 100%
rename from modules/cuda_plugin/utils/install-pre-push.sh
rename to modules/nvidia_plugin/utils/install-pre-push.sh
diff --git a/modules/cuda_plugin/utils/lsan-suppressions.txt b/modules/nvidia_plugin/utils/lsan-suppressions.txt
similarity index 98%
rename from modules/cuda_plugin/utils/lsan-suppressions.txt
rename to modules/nvidia_plugin/utils/lsan-suppressions.txt
index 29be469a1..a32c77036 100644
--- a/modules/cuda_plugin/utils/lsan-suppressions.txt
+++ b/modules/nvidia_plugin/utils/lsan-suppressions.txt
@@ -31,7 +31,7 @@ leak:_pywrap_tensorflow_internal.so
 leak:site-packages/google/protobuf
 
 # ====================================================================================
-# THIS SECTION defines all other exceptions including those required by CUDAPlugin.
+# THIS SECTION defines all other exceptions including those required by nvidia_gpu.
 #
 
 # The folowing are reproduced running CudaUnitTests
diff --git a/modules/cuda_plugin/utils/openvino_patches/benchmark_app_phase1.patch b/modules/nvidia_plugin/utils/openvino_patches/benchmark_app_phase1.patch
similarity index 97%
rename from modules/cuda_plugin/utils/openvino_patches/benchmark_app_phase1.patch
rename to modules/nvidia_plugin/utils/openvino_patches/benchmark_app_phase1.patch
index a3af21897..f90cb64ec 100644
--- a/modules/cuda_plugin/utils/openvino_patches/benchmark_app_phase1.patch
+++ b/modules/nvidia_plugin/utils/openvino_patches/benchmark_app_phase1.patch
@@ -6,7 +6,7 @@ index b37495e5e..9dc5da800 100644
                HEADERS ${HDR}
                DEPENDENCIES format_reader ie_samples_utils
                OPENCV_DEPENDENCIES core)
-+add_dependencies(benchmark_app CUDAPlugin)
++add_dependencies(benchmark_app openvino_nvidia_gpu_plugin)
 diff --git a/inference-engine/samples/benchmark_app/benchmark_app.hpp b/inference-engine/samples/benchmark_app/benchmark_app.hpp
 index af18c908e..d55baa34c 100644
 --- a/inference-engine/samples/benchmark_app/benchmark_app.hpp
@@ -47,7 +47,7 @@ index cd7ddc641..c638f4f4e 100644
  
                  if (isFlagSetInCommandLine("nthreads"))
                      device_config[GNA_CONFIG_KEY(LIB_N_THREADS)] = std::to_string(FLAGS_nthreads);
-+            } else if (device == "CUDA") {
++            } else if (device == "NVIDIA") {
 +                setThroughputStreams();
 +                if (isFlagSetInCommandLine("op_bench")) {
 +                  device_config["CUDA_OPERATION_BENCHMARK"] = FLAGS_op_bench ?
diff --git a/modules/cuda_plugin/utils/openvino_patches/benchmark_app_phase2_tacotron2.patch b/modules/nvidia_plugin/utils/openvino_patches/benchmark_app_phase2_tacotron2.patch
similarity index 100%
rename from modules/cuda_plugin/utils/openvino_patches/benchmark_app_phase2_tacotron2.patch
rename to modules/nvidia_plugin/utils/openvino_patches/benchmark_app_phase2_tacotron2.patch
diff --git a/modules/cuda_plugin/utils/openvino_patches/hello_classification_phase2_2d_unet.patch b/modules/nvidia_plugin/utils/openvino_patches/hello_classification_phase2_2d_unet.patch
similarity index 98%
rename from modules/cuda_plugin/utils/openvino_patches/hello_classification_phase2_2d_unet.patch
rename to modules/nvidia_plugin/utils/openvino_patches/hello_classification_phase2_2d_unet.patch
index 0eb96c168..0634a7f67 100644
--- a/modules/cuda_plugin/utils/openvino_patches/hello_classification_phase2_2d_unet.patch
+++ b/modules/nvidia_plugin/utils/openvino_patches/hello_classification_phase2_2d_unet.patch
@@ -6,7 +6,7 @@ index 9b0509bab..40b298319 100644
                DEPENDENCIES ie_samples_utils
                OPENCV_DEPENDENCIES core imgcodecs)
  
-+add_dependencies(hello_classification CUDAPlugin)
++add_dependencies(hello_classification openvino_nvidia_gpu_plugin)
 diff --git a/inference-engine/samples/hello_classification/main.cpp b/inference-engine/samples/hello_classification/main.cpp
 index 858a87ead..25509e21d 100644
 --- a/inference-engine/samples/hello_classification/main.cpp
diff --git a/modules/cuda_plugin/utils/openvino_patches/hello_classification_phase2_3d_unet.patch b/modules/nvidia_plugin/utils/openvino_patches/hello_classification_phase2_3d_unet.patch
similarity index 99%
rename from modules/cuda_plugin/utils/openvino_patches/hello_classification_phase2_3d_unet.patch
rename to modules/nvidia_plugin/utils/openvino_patches/hello_classification_phase2_3d_unet.patch
index f42008e51..c68ded819 100644
--- a/modules/cuda_plugin/utils/openvino_patches/hello_classification_phase2_3d_unet.patch
+++ b/modules/nvidia_plugin/utils/openvino_patches/hello_classification_phase2_3d_unet.patch
@@ -12,7 +12,7 @@ index 9b0509bab..89cc77fe2 100644
                DEPENDENCIES ie_samples_utils
                OPENCV_DEPENDENCIES core imgcodecs)
  
-+add_dependencies(hello_classification CUDAPlugin)
++add_dependencies(hello_classification openvino_nvidia_gpu_plugin)
 diff --git a/inference-engine/samples/hello_classification/main.cpp b/inference-engine/samples/hello_classification/main.cpp
 index 858a87ead..5810ca510 100644
 --- a/inference-engine/samples/hello_classification/main.cpp
@@ -106,7 +106,7 @@ index 858a87ead..5810ca510 100644
          // ------------------------------------------
 -        ExecutableNetwork executable_network = ie.LoadNetwork(network, device_name);
 +        ExecutableNetwork executable_network =
-+            device_name == "CUDA" ? ie.LoadNetwork(network, device_name,
++            device_name == "NVIDIA" ? ie.LoadNetwork(network, device_name,
 +                                    {
 +                                        {{"CUDA_THROUGHPUT_STREAMS", "1"}},
 +                                    })
diff --git a/modules/cuda_plugin/utils/pre-push b/modules/nvidia_plugin/utils/pre-push
similarity index 79%
rename from modules/cuda_plugin/utils/pre-push
rename to modules/nvidia_plugin/utils/pre-push
index 95924472b..4100d310a 100755
--- a/modules/cuda_plugin/utils/pre-push
+++ b/modules/nvidia_plugin/utils/pre-push
@@ -6,7 +6,7 @@ if [ -z "$ROOT_DIR" ]; then
     cd ../..
     ROOT_DIR=$(eval $GET_ROOT_DIR)
 fi
-PRE_PUSH_IMPL_DIR=$ROOT_DIR/modules/cuda_plugin/utils
+PRE_PUSH_IMPL_DIR=$ROOT_DIR/modules/nvidia_plugin/utils
 cd $PRE_PUSH_IMPL_DIR
 ./pre-push-impl.sh
 exit $?
diff --git a/modules/cuda_plugin/utils/pre-push-impl.sh b/modules/nvidia_plugin/utils/pre-push-impl.sh
similarity index 98%
rename from modules/cuda_plugin/utils/pre-push-impl.sh
rename to modules/nvidia_plugin/utils/pre-push-impl.sh
index 518c637b4..41a5ea76b 100755
--- a/modules/cuda_plugin/utils/pre-push-impl.sh
+++ b/modules/nvidia_plugin/utils/pre-push-impl.sh
@@ -9,7 +9,7 @@ EXIT_CODE=0
 
 # if $OPENVINO_BUILD_PATH environment variable not set try to set it to
 # openvino/build assuming openvino directroy is in the same directrory
-# as openvino_cuda_plugin
+# as openvino_nvidia_gpu_plugin
 if [ -z "$OPENVINO_BUILD_PATH" ]; then
 
   export OPENVINO_BUILD_PATH=$(realpath ../../../../openvino/build)
diff --git a/modules/cuda_plugin/utils/shape-extractor/how_to_use.txt b/modules/nvidia_plugin/utils/shape-extractor/how_to_use.txt
similarity index 100%
rename from modules/cuda_plugin/utils/shape-extractor/how_to_use.txt
rename to modules/nvidia_plugin/utils/shape-extractor/how_to_use.txt
diff --git a/modules/cuda_plugin/utils/shape-extractor/main.py b/modules/nvidia_plugin/utils/shape-extractor/main.py
similarity index 100%
rename from modules/cuda_plugin/utils/shape-extractor/main.py
rename to modules/nvidia_plugin/utils/shape-extractor/main.py
diff --git a/modules/cuda_plugin/utils/shape-extractor/operation_table.jinja2 b/modules/nvidia_plugin/utils/shape-extractor/operation_table.jinja2
similarity index 100%
rename from modules/cuda_plugin/utils/shape-extractor/operation_table.jinja2
rename to modules/nvidia_plugin/utils/shape-extractor/operation_table.jinja2
diff --git a/modules/cuda_plugin/utils/shape-extractor/requirements.txt b/modules/nvidia_plugin/utils/shape-extractor/requirements.txt
similarity index 100%
rename from modules/cuda_plugin/utils/shape-extractor/requirements.txt
rename to modules/nvidia_plugin/utils/shape-extractor/requirements.txt
diff --git a/modules/cuda_plugin/utils/uninstall-pre-push.sh b/modules/nvidia_plugin/utils/uninstall-pre-push.sh
similarity index 100%
rename from modules/cuda_plugin/utils/uninstall-pre-push.sh
rename to modules/nvidia_plugin/utils/uninstall-pre-push.sh
diff --git a/modules/cuda_plugin/wheel/openvino_cuda/__init__.py b/modules/nvidia_plugin/wheel/openvino_nvidia/__init__.py
similarity index 59%
rename from modules/cuda_plugin/wheel/openvino_cuda/__init__.py
rename to modules/nvidia_plugin/wheel/openvino_nvidia/__init__.py
index 7b1216a11..495a67ad2 100644
--- a/modules/cuda_plugin/wheel/openvino_cuda/__init__.py
+++ b/modules/nvidia_plugin/wheel/openvino_nvidia/__init__.py
@@ -13,21 +13,21 @@ def _get_lib_file_extension() -> str:
         return "dylib"
 
 
-def _register_cuda_plugin():
+def _register_nvidia_plugin():
     import openvino
     openvino_package_dir = os.path.dirname(os.path.abspath(openvino.__file__))
     openvino_package_libs_dir = os.path.join(openvino_package_dir, "libs")
-    openvino_cuda_package_dir = os.path.dirname(os.path.abspath(__file__))
-    openvino_cuda_library = os.path.join(openvino_cuda_package_dir, f"../libCUDAPlugin.{_get_lib_file_extension()}")
+    openvino_nvidia_gpu_package_dir = os.path.dirname(os.path.abspath(__file__))
+    openvino_nvidia_gpu_library = os.path.join(openvino_nvidia_gpu_package_dir, f"../libopenvino_nvidia_gpu_plugin.{_get_lib_file_extension()}")
 
     xml_file = os.path.join(openvino_package_libs_dir, "plugins.xml")
     tree = ET.parse(xml_file)
     plugins = tree.find("plugins")
-    if all(plugin.get('name') != 'CUDA' for plugin in plugins.iter('plugin')):
-        plugins.append(ET.Element('plugin', {'name': 'CUDA', 'location': openvino_cuda_library}))
+    if all(plugin.get('name') != 'NVIDIA' for plugin in plugins.iter('plugin')):
+        plugins.append(ET.Element('plugin', {'name': 'NVIDIA', 'location': openvino_nvidia_gpu_library}))
         tree.write(xml_file)
 
 
-_register_cuda_plugin()
+_register_nvidia_plugin()
 
 __version__ = "2022.1.0"
diff --git a/modules/cuda_plugin/wheel/requirements-dev.txt b/modules/nvidia_plugin/wheel/requirements-dev.txt
similarity index 100%
rename from modules/cuda_plugin/wheel/requirements-dev.txt
rename to modules/nvidia_plugin/wheel/requirements-dev.txt
diff --git a/modules/cuda_plugin/wheel/requirements.txt b/modules/nvidia_plugin/wheel/requirements.txt
similarity index 100%
rename from modules/cuda_plugin/wheel/requirements.txt
rename to modules/nvidia_plugin/wheel/requirements.txt
diff --git a/modules/cuda_plugin/wheel/setup.py b/modules/nvidia_plugin/wheel/setup.py
similarity index 88%
rename from modules/cuda_plugin/wheel/setup.py
rename to modules/nvidia_plugin/wheel/setup.py
index 7e996cf7a..531bfa81f 100644
--- a/modules/cuda_plugin/wheel/setup.py
+++ b/modules/nvidia_plugin/wheel/setup.py
@@ -27,11 +27,11 @@
 if not any(pl in sys.platform for pl in platforms):
     sys.exit(f'Unsupported platform: {sys.platform}, expected: linux, win32, darwin')
 
-PACKAGE_NAME = config('WHEEL_PACKAGE_NAME', 'openvino-cuda')
+PACKAGE_NAME = config('WHEEL_PACKAGE_NAME', 'openvino-nvidia')
 OPENVINO_REPO_URI = config('OPENVINO_REPO_DOWNLOAD_URL', 'https://github.com/openvinotoolkit/openvino.git')
 WHEEL_VERSION = config('WHEEL_VERSION', '2022.1.0')
 OPENVINO_REPO_TAG = config('OPENVINO_REPO_TAG', WHEEL_VERSION)
-CUDA_PLUGIN_CMAKE_TARGET_NAME = 'CUDAPlugin'
+NVIDIA_PLUGIN_CMAKE_TARGET_NAME = 'openvino_nvidia_gpu_plugin'
 LIBS_RPATH = '$ORIGIN' if sys.platform == 'linux' else '@loader_path'
 OPENVINO_INSTALL_BUILD_DEPS_SCRIPT = "install_build_dependencies.sh"
 OPENVINO_SETUP_PY_PATH = "inference-engine/ie_bridges/python/wheel/setup.py"
@@ -193,9 +193,9 @@ def finalize_options(self):
         self.git_exec = shutil.which("git")
         self.cmake_exec = shutil.which("cmake")
         self.build_configuration_name = 'Debug' if self.debug else 'Release'
-        self.cuda_plugin_src_dir = os.path.abspath(os.path.dirname(__file__))
-        self.build_lib_dir = os.path.join(self.cuda_plugin_src_dir, "build/lib")
-        self.openvino_contrib_src_dir = os.path.normpath(os.path.join(self.cuda_plugin_src_dir, "../../.."))
+        self.nvidia_plugin_src_dir = os.path.abspath(os.path.dirname(__file__))
+        self.build_lib_dir = os.path.join(self.nvidia_plugin_src_dir, "build/lib")
+        self.openvino_contrib_src_dir = os.path.normpath(os.path.join(self.nvidia_plugin_src_dir, "../../.."))
         self.deps_dir = os.path.abspath(os.path.join(self.build_temp, "deps"))
         self.openvino_src_dir = os.path.join(self.deps_dir, "openvino")
         openvino_src_dir = self.openvino_src_dir
@@ -217,7 +217,7 @@ def run(self):
         self.configure_openvino_cmake()
         if self.force:
             self.build_openvino()
-        self.build_cuda_plugin()
+        self.build_nvidia_plugin()
         self.locate_built_lib()
 
     def clone_openvino_src(self):
@@ -261,7 +261,7 @@ def build_openvino(self):
     def get_build_env(self):
         build_env = os.environ.copy()
         build_env['BUILD_TYPE'] = self.build_configuration_name
-        build_env['BUILD_TARGETS'] = CUDA_PLUGIN_CMAKE_TARGET_NAME
+        build_env['BUILD_TARGETS'] = NVIDIA_PLUGIN_CMAKE_TARGET_NAME
         build_env['OPENVINO_HOME'] = self.openvino_src_dir
         build_env['OPENVINO_CONTRIB'] = self.openvino_contrib_src_dir
         build_env['OPENVINO_BUILD_PATH'] = self.openvino_build_dir
@@ -291,24 +291,24 @@ def get_build_env(self):
 
         return build_env
 
-    def build_cuda_plugin(self):
+    def build_nvidia_plugin(self):
         if not os.path.isdir(self.openvino_build_dir):
             self.mkpath(self.openvino_build_dir)
 
         build_env = self.get_build_env()
 
         self.announce("Building OpenVINO CUDA Plugin Project", level=3)
-        run_command([os.path.join(self.cuda_plugin_src_dir, "../build.sh"), '--build'],
-                    cwd=self.cuda_plugin_src_dir, env=build_env)
+        run_command([os.path.join(self.nvidia_plugin_src_dir, "../build.sh"), '--build'],
+                    cwd=self.nvidia_plugin_src_dir, env=build_env)
 
     def locate_built_lib(self):
         libs = []
         lib_ext = platform_specifics.get_lib_file_extension()
         bin_dir = os.path.join(self.openvino_src_dir, "bin")
-        for name in [CUDA_PLUGIN_CMAKE_TARGET_NAME]:
+        for name in [NVIDIA_PLUGIN_CMAKE_TARGET_NAME]:
             libs.extend(list(glob.iglob(f"{bin_dir}/**/*{name}*{lib_ext}", recursive=True)))
         if not libs:
-            raise Exception("CUDA Plugin library not found. Possibly build was failed or was written to unknown "
+            raise Exception("NVIDIA Plugin library not found. Possibly build was failed or was written to unknown "
                             "directory")
         self.mkpath(self.build_lib_dir)
         for lib in libs:
@@ -332,14 +332,14 @@ def run(self):
             self.build()
             self.install()
             self.install_openvino_package_and_other_dependencies()
-            self.register_cuda_plugin()
-            self.test_cuda_plugin()
-            openvino_cuda_library = f'{openvino_src_dir}/bin/intel64/Release/lib/libCUDAPlugin.{platform_specifics.get_lib_file_extension()}'
+            self.register_nvidia_plugin()
+            self.test_nvidia_plugin()
+            openvino_nvidia_gpu_library = f'{openvino_src_dir}/bin/intel64/Release/lib/libopenvino_nvidia_gpu_plugin.{platform_specifics.get_lib_file_extension()}'
             package_data.update({
-                '': [openvino_cuda_library]
+                '': [openvino_nvidia_gpu_library]
             })
         finally:
-            self.unregister_cuda_plugin()
+            self.unregister_nvidia_plugin()
 
     def install_openvino_package_and_other_dependencies(self):
         if self.force:
@@ -360,32 +360,32 @@ def get_openvino_package_dir(self):
         openvino_package_libs_dir = os.path.join(openvino_package_dir, "libs")
         return openvino_package_libs_dir
 
-    def register_cuda_plugin(self):
+    def register_nvidia_plugin(self):
         openvino_package_libs_dir = self.get_openvino_package_dir()
         self.copy_tree(self.build_dir, openvino_package_libs_dir)
-        openvino_cuda_library = os.path.join(openvino_package_libs_dir,
-                                             f"libCUDAPlugin.{platform_specifics.get_lib_file_extension()}")
+        openvino_nvidia_gpu_library = os.path.join(openvino_package_libs_dir,
+                                                   f"libopenvino_nvidia_gpu_plugin.{platform_specifics.get_lib_file_extension()}")
 
         xml_file = os.path.join(openvino_package_libs_dir, "plugins.xml")
         tree = ET.parse(xml_file)
         plugins = tree.find("plugins")
-        if all(plugin.get('name') != 'CUDA' for plugin in plugins.iter('plugin')):
-            plugins.append(ET.Element('plugin', {'name': 'CUDA', 'location': openvino_cuda_library}))
+        if all(plugin.get('name') != 'NVIDIA' for plugin in plugins.iter('plugin')):
+            plugins.append(ET.Element('plugin', {'name': 'NVIDIA', 'location': openvino_nvidia_gpu_library}))
             tree.write(xml_file)
 
-    def unregister_cuda_plugin(self):
+    def unregister_nvidia_plugin(self):
         openvino_package_libs_dir = self.get_openvino_package_dir()
 
         xml_file = os.path.join(openvino_package_libs_dir, "plugins.xml")
         tree = ET.parse(xml_file)
         plugins = tree.find("plugins")
         for plugin in plugins.iter('plugin'):
-            if plugin.get('name') == 'CUDA':
+            if plugin.get('name') == 'NVIDIA':
                 plugins.remove(plugin)
                 tree.write(xml_file)
                 break
 
-    def test_cuda_plugin(self):
+    def test_nvidia_plugin(self):
         from openvino.inference_engine import IECore
         test_model_convert_fp32 = """
             <?xml version="1.0"?>
@@ -421,14 +421,14 @@ def test_cuda_plugin(self):
         ie = IECore()
         net = ie.read_network(model=test_model_convert_fp32, weights=b'', init_from_buffer=True)
         try:
-            ie.load_network(network=net, device_name="CUDA")
+            ie.load_network(network=net, device_name="NVIDIA")
         except RuntimeError as e:
             recommendations_msg = ''
             if not self.force:
                 recommendations_msg = 'Try to uninstall the openvino package and run "setup.py install --force" ' \
                                       'to build OpenVINO libraries also.'
-            raise RuntimeError('The CUDA plugin loading test was failed. '
-                               'The CUDA plugin library is not compatible with OpenVINO libraries. '
+            raise RuntimeError('The NVIDIA GPU plugin loading test was failed. '
+                               'The NVIDIA GPU plugin library is not compatible with OpenVINO libraries. '
                                f'Possible ABI version mismatch. {recommendations_msg}') from e
 
 
@@ -440,16 +440,16 @@ def test_cuda_plugin(self):
     name=PACKAGE_NAME,
     license=config('WHEEL_LICENCE_TYPE', 'OSI Approved :: Apache Software License'),
     author=config('WHEEL_AUTHOR', 'Intel Corporation'),
-    description=config('WHEEL_DESC', 'CUDAPlugin for OpenVINO Inference Engine Python* API'),
+    description=config('WHEEL_DESC', 'NVIDIA Plugin for OpenVINO Inference Engine Python* API'),
     long_description=get_description(config('WHEEL_OVERVIEW',
                                             f'{os.path.abspath(os.path.dirname(__file__))}/../README.md')),
     long_description_content_type='text/markdown',
     download_url=config('WHEEL_DOWNLOAD_URL', 'https://github.com/openvinotoolkit/openvino/tags'),
     url=config('WHEEL_URL', 'https://docs.openvinotoolkit.org/latest/index.html'),
     libraries=[(PACKAGE_NAME, {'sources': []})],
-    packages=["openvino_cuda"],
+    packages=["openvino_nvidia"],
     package_dir={
-        "openvino_cuda": f"{os.path.abspath(os.path.dirname(__file__))}/openvino_cuda",
+        "openvino_nvidia": f"{os.path.abspath(os.path.dirname(__file__))}/openvino_nvidia",
     },
     package_data=package_data,
     cmdclass={