Skip to content
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 is broken for CUDA 12.5 #2333

Open
krish07751 opened this issue Feb 2, 2025 · 6 comments
Open

Build is broken for CUDA 12.5 #2333

krish07751 opened this issue Feb 2, 2025 · 6 comments

Comments

@krish07751
Copy link

It seems thrust is broken for CUDA 12.5 and so does the build.
...
from /content/openpose/3rdparty/caffe/src/caffe/layers/cudnn_softmax_layer.cpp:4:
/usr/local/cuda/include/cub/util_device.cuh: In static member function ‘static typename AgentT::TempStorage& cub::CUB_200400___CUDA_ARCH_LIST___NS::detail::vsmem_helper_impl::get_temp_storage(cub::CUB_200400___CUDA_ARCH_LIST___NS::NullType&, cub::CUB_200400___CUDA_ARCH_LIST___NS::detail::vsmem_t&)’:
/usr/local/cuda/include/cub/util_device.cuh:160:63: error: ‘blockIdx’ was not declared in this scope
160 | static_cast<char*>(vsmem.gmem_ptr) + (vsmem_per_block * blockIdx.x));
| ^~~~~~~~
/usr/local/cuda/include/cub/util_device.cuh: In static member function ‘static bool cub::CUB_200400___CUDA_ARCH_LIST___NS::detail::vsmem_helper_impl::discard_temp_storage(typename AgentT::TempStorage&)’:
/usr/local/cuda/include/cub/util_device.cuh:201:38: error: ‘threadIdx’ was not declared in this scope
201 | const std::size_t linear_tid = threadIdx.x;
| ^~~~~~~~~
/usr/local/cuda/include/cub/util_device.cuh:202:50: error: ‘blockDim’ was not declared in this scope
202 | const std::size_t block_stride = line_size * blockDim.x;
| ^~~~~~~~
...

@Mobina-Zibandepour
Copy link

Mobina-Zibandepour commented Feb 2, 2025

I have the same problem and need help!
It seems that we must manually downgrade the CUDA and CuDNN in Google Colab, but it isn't easy work, and I faced several errors, so we are thankful to open pose developers to give hints on what to do in this situation or upgrade the Caffee version compatible to CUDA 12.5 and CUDNN 8.9.6 (the version is using in Google Colab now) .

@emurray2
Copy link

emurray2 commented Feb 4, 2025

Have you tried using Docker to downgrade to one of the recommended CUDA in Ubuntu 20?
https://gist.github.com/mwufi/6718b30761cd109f9aff04c5144eb885

@Mobina-Zibandepour
Copy link

Have you tried using Docker to downgrade to one of the recommended CUDA in Ubuntu 20? https://gist.github.com/mwufi/6718b30761cd109f9aff04c5144eb885

Thank you for your response and solution. I used the "fallback runtime version" of Google Colab, and now It works well.

@SumitxThokar
Copy link

SumitxThokar commented Feb 6, 2025

@Mobina-Zibandepour can you help me with how you solve this problem. I am also stuck with this same error?
Thankss.

@Mobina-Zibandepour
Copy link

@Mobina-Zibandepour can you help me with how you solve this problem. I am also stuck with this same error? Thankss.

Hi, If you are working on Colab, first you must start the runtime, then open the command palette and find the "fallback runtime version" With this command, you can again use Colab with the previous version.

@SumitxThokar
Copy link

thanks @Mobina-Zibandepour Hopefully this works.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants