Chore windows build use python

.github/workflows/quality-gate.yml

@@ -10,6 +10,7 @@ jobs:
     runs-on: ${{ matrix.runs-on }}
     timeout-minutes: 1440
     strategy:
+      fail-fast: false
       matrix:
         include:
           - os: "windows"

cpp/Makefile

@@ -24,13 +24,14 @@ endif
 # Build the Cortex engine
 build:
 ifeq ($(OS),Windows_NT)
-	@powershell -Command "mkdir -p build; cd build; cmake -GNinja -DBUILD_CORTEX_TENSORRT-LLM=ON -DCMAKE_MSVC_DEBUG_INFORMATION_FORMAT=Embedded -DCMAKE_POLICY_CMP0141=NEW -DCMAKE_CXX_COMPILER_LAUNCHER=ccache -DCMAKE_C_COMPILER_LAUNCHER=ccache -DCMAKE_CUDA_COMPILER_LAUNCHER=ccache -DCMAKE_BUILD_TYPE='Release' -DBUILD_PYT='OFF' -DBUILD_PYBIND='OFF' -DNVTX_DISABLE='ON' -DCMAKE_CUDA_ARCHITECTURES='80-real;86-real;89-real' '-DENABLE_MULTI_DEVICE=0' '-DCMAKE_CUDA_COMPILER=C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.2/bin/nvcc.exe' -DBUILD_BENCHMARKS=OFF '-DBUILD_TESTS=OFF' -DTRT_LIB_DIR=C:/workspace/TensorRT-9.3.0.1//lib -DTRT_INCLUDE_DIR=C:/workspace/TensorRT-9.3.0.1//include  ..; cmake --build . --config Release -j2;"
+	@powershell -Command "cd ..; python .\scripts\build_wheel.py -a '80-real;86-real;89-real' --trt_root 'C:\workspace\TensorRT-9.3.0.1\' -D 'BUILD_CORTEX_TENSORRT-LLM=ON' --use_ccache"
 else
 	@mkdir -p build && cd build; \
 	cmake .. -GNinja -DBUILD_CORTEX_TENSORRT-LLM=ON -DCMAKE_CXX_COMPILER_LAUNCHER=sccache -DCMAKE_C_COMPILER_LAUNCHER=sccache -DCMAKE_CUDA_COMPILER_LAUNCHER=sccache -DCMAKE_BUILD_TYPE='Release' -DBUILD_PYT='OFF' -DBUILD_PYBIND='OFF' -DNVTX_DISABLE='ON' -DCMAKE_CUDA_ARCHITECTURES='80-real;86-real;89-real' '-DENABLE_MULTI_DEVICE=0' '-DCMAKE_CUDA_COMPILER=/usr/local/cuda/bin/nvcc' -DBUILD_BENCHMARKS=OFF '-DBUILD_TESTS=OFF' -DTRT_LIB_DIR=/usr/local/tensorrt/lib -DTRT_INCLUDE_DIR=/usr/local/tensorrt/include; \
 	cmake --build . --config Release;
 endif
 
+# Prepackage the Cortex engine
 pre-package:
 ifeq ($(OS),Windows_NT)
 	@powershell -Command "cd tensorrt_llm\cortex.tensorrt-llm\; mkdir -p cortex.tensorrt-llm; cp ..\..\build\tensorrt_llm\cortex.tensorrt-llm\engine.dll cortex.tensorrt-llm\;"