Skip to content

NVIDIA’s deep learning stack on Windows: CUDA toolkit + cuDNN + TensorRT

License

Notifications You must be signed in to change notification settings

phineas-pta/NVIDIA-win

Repository files navigation

License Platform Cuda Cudnn Tensorrt Python VS Cmake

NVIDIA-win

how to install the NVIDIA’s deep learning stack on Windows: CUDA toolkit + cuDNN + TensorRT,
also various attempts to compile deep learning libraries with cuda

only for Windows 10/11 + recent RTX cards recommended

all comands here are for cmd, if u prefer pwsh must change to adapt

some values are censored with black box ███ so u have to fill in with your use case

1st of all: 👉👉👉 install CUDA toolkit + cuDNN + TensorRT 👈👈👈

my attempts to build various deep learning libraries:

  1. build onnxruntime
  2. build whisper.cpp with cuBLAS
  3. build CTranslate2 to use faster-whisper
  4. build triton to use xformers
  5. try out TensorRT-LLM
  6. build OpenCV with CUDA
  7. build Torch-TensorRT
  8. build llama.cpp with cuBLAS
  9. build Stan with OpenCL

all above guides are under CC-BY-4.0

more complicated tweaking with TensorRT (under GPLv3)

About

NVIDIA’s deep learning stack on Windows: CUDA toolkit + cuDNN + TensorRT

Topics

Resources

License

Stars

Watchers

Forks