-
Notifications
You must be signed in to change notification settings - Fork 3k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Build] onnxruntime_providers_shared not provided. #19191
Comments
It seems minimal_build and shared_lib are not supported altogether (https://github.com/microsoft/onnxruntime/blob/main/cmake/onnxruntime_providers_cpu.cmake#L220). +@skottmckay |
Minimal build works fine with a shared library in general as we build that way with the CPU EP, NNAPI, CoreML and XNNPACK EPs depending on the platform/package we're building. Minimal build however makes no sense with CUDA as the savings from doing a minimal build are tiny in comparison to the size of the CUDA kernels. Given that, we have never looked at enabling the CUDA setup (which builds a separate library for the CUDA EP) with a minimal build and it's not surprising it breaks. Please remove It is possible to do a reduced operators/types build, but you have to provide a config file listing what should be included. You don't seem to have that, so I'd also suggest removing |
I have the same thing when I use
|
@xadupre
Could you please provide how to resolve this issue? cc: @skottmckay |
The source are provided by default when github publishes a new releases but git dependencies are not included. To build a specific version, you need to clone the reposity and switch to the branch with tag 1.6.3. |
This issue has been automatically marked as stale due to inactivity and will be closed in 30 days if no further activity occurs. If further support is needed, please provide an update and/or more details. |
Describe the issue
I tried to build onnxruntime with CUDA support.
I'm using CUDA Toolkit 11.8.
But while generating CMake, got the following error.
Urgency
Urgent!!!
Target platform
Windows 10
Build script
build.bat ^
--config Release ^
--parallel 0 ^
--use_cuda ^
--cmake_generator="Visual Studio 17 2022" ^
--minimal_build ^
--enable_reduced_operator_type_support ^
--skip_tests ^
--cuda_home “C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8” ^
--cudnn_home “C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8” ^
--enable_cuda_line_info ^
--enable_pybind ^
--build_wheel ^
--build_csharp ^
--build_nuget ^
--build_nodejs ^
--build_shared_lib ^
--use_full_protobuf
Error / output
Visual Studio Version
Visual Studio 17 2022
GCC / Compiler Version
No response
The text was updated successfully, but these errors were encountered: