CUDA、cudnn和OnnxRuntime版本对应 |
您所在的位置:网站首页 › cuda和cudatoolkit版本对应 › CUDA、cudnn和OnnxRuntime版本对应 |
NVIDIA - CUDA | onnxruntime RequirementsPlease reference table below for official GPU packages dependencies for the ONNX Runtime inferencing package. Note that ONNX Runtime Training is aligned with PyTorch CUDA versions; refer to the Training tab on onnxruntime.ai for supported versions. Note: Because of CUDA Minor Version Compatibility, ONNX Runtime built with CUDA 11.8 should be compatible with any CUDA 11.x version. Please reference Nvidia CUDA Minor Version Compatibility. ONNX RuntimeCUDAcuDNNNotes1.1712.28.9.2.26 (Linux) 8.9.2.26 (Windows)The default CUDA version for ORT 1.17 is CUDA 11.8. To install CUDA 12 package, please look at Install ORT. Due to low demand on Java GPU package, only C++/C# Nuget and Python packages are released with CUDA 12.21.15 1.16 1.1711.88.2.4 (Linux) 8.5.0.96 (Windows)Tested with CUDA versions from 11.6 up to 11.8, and cuDNN from 8.2.4 up to 8.7.01.14 1.13.1 1.1311.68.2.4 (Linux) 8.5.0.96 (Windows)libcudart 11.4.43 libcufft 10.5.2.100 libcurand 10.2.5.120 libcublasLt 11.6.5.2 libcublas 11.6.5.2 libcudnn 8.2.41.12 1.1111.48.2.4 (Linux) 8.2.2.26 (Windows)libcudart 11.4.43 libcufft 10.5.2.100 libcurand 10.2.5.120 libcublasLt 11.6.5.2 libcublas 11.6.5.2 libcudnn 8.2.41.1011.48.2.4 (Linux) 8.2.2.26 (Windows)libcudart 11.4.43 libcufft 10.5.2.100 libcurand 10.2.5.120 libcublasLt 11.6.1.51 libcublas 11.6.1.51 libcudnn 8.2.41.911.48.2.4 (Linux) 8.2.2.26 (Windows)libcudart 11.4.43 libcufft 10.5.2.100 libcurand 10.2.5.120 libcublasLt 11.6.1.51 libcublas 11.6.1.51 libcudnn 8.2.41.811.0.38.0.4 (Linux) 8.0.2.39 (Windows)libcudart 11.0.221 libcufft 10.2.1.245 libcurand 10.2.1.245 libcublasLt 11.2.0.252 libcublas 11.2.0.252 libcudnn 8.0.41.711.0.38.0.4 (Linux) 8.0.2.39 (Windows)libcudart 11.0.221 libcufft 10.2.1.245 libcurand 10.2.1.245 libcublasLt 11.2.0.252 libcublas 11.2.0.252 libcudnn 8.0.41.5-1.610.28.0.3CUDA 11 can be built from source1.2-1.410.17.6.5Requires cublas10-10.2.1.243; cublas 10.1.x will not work1.0-1.110.07.6.4CUDA versions from 9.1 up to 10.1, and cuDNN versions from 7.1 up to 7.4 should also work with Visual Studio 2017For older versions, please reference the readme and build pages on the release branch. For Windows, Microsoft C and C++ (MSVC) runtime libraries is also required. |
今日新闻 |
推荐新闻 |
CopyRight 2018-2019 办公设备维修网 版权所有 豫ICP备15022753号-3 |