Skip to content

[Build] Build CUDA 11.8 Visual Studio limitation #25182

Open
@AndreyOrb

Description

@AndreyOrb

Describe the issue

Well, this commit together with some other issue (that no one could predict) turned out to be a problem.

Here's the problem:
There's still a general support for CUDA 11.8 in ORT, but because of this limitation, only Visual Studio 2019 or Visual Studio 2022 v17.9.2 (or less) can still compile the CUDA 11.8

In my case, I must be able to build ORT with both CUDA 11.8 and CUDA 12.x (as separate ORT builds, of course).

From different resources (microsoft, microsoft) I learned that several VS versions with the same major version can be installed.
Then, I will probably have to run build.bat from the correct VS CMD (unverified).

For now, the easiest way for me to solve the problem was to add back "Visual Studio 16 2019" in build_args.py.
This way, I can build ORT with CUDA 11.8 using --cmake_generator "Visual Studio 16 2019" --compile_no_warning_as_error

Urgency

Not urgent

Target platform

Windows

Build script

.\build.bat --config Debug --build_shared_lib --parallel --use_cuda --cuda_home "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8" --cudnn_home "C:\Program Files\NVIDI
A GPU Computing Toolkit\cuDNN\cudnn-windows-x86_64-8.9.0.131_cuda11-archive" --cuda_version 11.8 --use_tensorrt --tensorrt_home "C:\Program Files\NVIDIA GPU Computing Toolkit\TensorRT\TensorRT-10.9.0.34.Windows.win10.cuda-11.8\TensorRT-10.9.0.34" --use_tensorrt_oss_parser --cmake_generator "Visual Studio 16 2019" --compile_no_warning_as_error --cmake_path E:\3rdParties\cmake-4.0.3\build\bin\Release\cmake.exe --skip_tests --enable_cuda_line_info --use_mimalloc --cmake_extra_defines onnxruntime_BUILD_UNIT_TESTS=OFF --skip_tests

Error / output

Build will fail with Visual Studio 2022 v17.10 because it has no backward compatibility for CUDA 11.8

Visual Studio Version

Visual Studio 2022 v17.10

GCC / Compiler Version

No response

Metadata

Metadata

Assignees

No one assigned

    Labels

    buildbuild issues; typically submitted using templateep:CUDAissues related to the CUDA execution provider

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions