From 85c3f0fe0bee4078bcd4edea3009e3ccaa151b12 Mon Sep 17 00:00:00 2001 From: Yifan Li <109183385+yf711@users.noreply.github.com> Date: Tue, 24 Sep 2024 10:21:29 -0700 Subject: [PATCH] [TensorRT EP] [documentation] Set cuda 12 as default for ORT 1.19 (#21758) --- .../CUDA-ExecutionProvider.md | 2 ++ .../TensorRT-ExecutionProvider.md | 33 ++++++++++--------- docs/get-started/with-python.md | 10 +++--- docs/install/index.md | 10 +++--- 4 files changed, 30 insertions(+), 25 deletions(-) diff --git a/docs/execution-providers/CUDA-ExecutionProvider.md b/docs/execution-providers/CUDA-ExecutionProvider.md index 97374ff6e0..fb4851a822 100644 --- a/docs/execution-providers/CUDA-ExecutionProvider.md +++ b/docs/execution-providers/CUDA-ExecutionProvider.md @@ -35,6 +35,8 @@ Because of [Nvidia CUDA Minor Version Compatibility](https://docs.nvidia.com/dep ONNX Runtime built with cuDNN 8.x is not compatible with cuDNN 9.x, and vice versa. You can choose the package based on CUDA and cuDNN major versions that match your runtime environment (For example, PyTorch 2.3 uses cuDNN 8.x, while PyTorch 2.4 or later used cuDNN 9.x). +Note: starting ORT 1.19, **CUDA 12.x** becomes default version when distributing ONNX Runtime GPU packages. + ### CUDA 12.x To install CUDA 12 package, please look at [Install ORT](../install). diff --git a/docs/execution-providers/TensorRT-ExecutionProvider.md b/docs/execution-providers/TensorRT-ExecutionProvider.md index 8b2861d7fa..d6b9d76de6 100644 --- a/docs/execution-providers/TensorRT-ExecutionProvider.md +++ b/docs/execution-providers/TensorRT-ExecutionProvider.md @@ -27,21 +27,24 @@ See [Build instructions](../build/eps.md#tensorrt). ## Requirements -| ONNX Runtime | TensorRT | CUDA | -| :----------- | :------- | :--------- | -| 1.18-main | 10.0 | 11.8, 12.2 | -| 1.17 | 8.6 | 11.8, 12.2 | -| 1.16 | 8.6 | 11.8 | -| 1.15 | 8.6 | 11.8 | -| 1.14 | 8.5 | 11.6 | -| 1.12-1.13 | 8.4 | 11.4 | -| 1.11 | 8.2 | 11.4 | -| 1.10 | 8.0 | 11.4 | -| 1.9 | 8.0 | 11.4 | -| 1.7-1.8 | 7.2 | 11.0.3 | -| 1.5-1.6 | 7.1 | 10.2 | -| 1.2-1.4 | 7.0 | 10.1 | -| 1.0-1.1 | 6.0 | 10.0 | +Note: starting ORT 1.19, **CUDA 12** becomes default version when distributing ONNX Runtime GPU packages. + +| ONNX Runtime | TensorRT | CUDA | +| :----------- | :------- | :------------- | +| 1.19-main | 10.2 | **12.2**, 11.8 | +| 1.18 | 10.0 | 11.8, 12.2 | +| 1.17 | 8.6 | 11.8, 12.2 | +| 1.16 | 8.6 | 11.8 | +| 1.15 | 8.6 | 11.8 | +| 1.14 | 8.5 | 11.6 | +| 1.12-1.13 | 8.4 | 11.4 | +| 1.11 | 8.2 | 11.4 | +| 1.10 | 8.0 | 11.4 | +| 1.9 | 8.0 | 11.4 | +| 1.7-1.8 | 7.2 | 11.0.3 | +| 1.5-1.6 | 7.1 | 10.2 | +| 1.2-1.4 | 7.0 | 10.1 | +| 1.0-1.1 | 6.0 | 10.0 | For more details on CUDA/cuDNN versions, please see [CUDA EP requirements](./CUDA-ExecutionProvider.md#requirements). diff --git a/docs/get-started/with-python.md b/docs/get-started/with-python.md index c89d92e4ad..8311eb0917 100644 --- a/docs/get-started/with-python.md +++ b/docs/get-started/with-python.md @@ -28,20 +28,20 @@ Use the CPU package if you are running on Arm CPUs and/or macOS. pip install onnxruntime ``` -### Install ONNX Runtime GPU (CUDA 11.x) +### Install ONNX Runtime GPU (CUDA 12.x) -The default CUDA version for ORT is 11.8. +The default CUDA version for ORT is 12.2. ```bash pip install onnxruntime-gpu ``` -### Install ONNX Runtime GPU (CUDA 12.x) +### Install ONNX Runtime GPU (CUDA 11.8) -For Cuda 12.x, please use the following instructions to install from [ORT Azure Devops Feed](https://aiinfra.visualstudio.com/PublicPackages/_artifacts/feed/onnxruntime-cuda-12/PyPI/onnxruntime-gpu/overview) +For Cuda 11.8, please use the following instructions to install from [ORT Azure Devops Feed](https://aiinfra.visualstudio.com/PublicPackages/_artifacts/feed/onnxruntime-cuda-11/PyPI/onnxruntime-gpu/overview) ```bash -pip install onnxruntime-gpu --extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-12/pypi/simple/ +pip install onnxruntime-gpu --extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-11/pypi/simple/ ``` ## Install ONNX for model export diff --git a/docs/install/index.md b/docs/install/index.md index d9e14b1609..94cec0d9b3 100644 --- a/docs/install/index.md +++ b/docs/install/index.md @@ -94,16 +94,16 @@ pip install skl2onnx dotnet add package Microsoft.ML.OnnxRuntime ``` -#### Install ONNX Runtime GPU (CUDA 11.x) +#### Install ONNX Runtime GPU (CUDA 12.x) -The default CUDA version for ORT is 11.8 +The default CUDA version for ORT is 12.2 ```bash # GPU dotnet add package Microsoft.ML.OnnxRuntime.Gpu ``` -#### Install ONNX Runtime GPU (CUDA 12.x) +#### Install ONNX Runtime GPU (CUDA 11.8) 1. Project Setup @@ -116,8 +116,8 @@ a nuget.config file to your project in the same directory as your .csproj file. - + ```