Skip to content

[Bug]: Set LD_LIBRARY_PATH to include the 'standard' CUDA location #25766

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.

Sign up for GitHub

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

Merged
merged 1 commit into from
Sep 27, 2025
Merged

[Bug]: Set LD_LIBRARY_PATH to include the 'standard' CUDA location #25766

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions docker/Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -461,6 +461,12 @@ ENV CUDA_HOME=/usr/local/cuda
RUN export TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST:-9.0a+PTX}" \
&& bash install_python_libraries.sh

# CUDA image changed from /usr/local/nvidia to /usr/local/cuda in 12.8 but will
# return to /usr/local/nvidia in 13.0 to allow container providers to mount drivers
# consistently from the host (see https://github.com/vllm-project/vllm/issues/18859).
# Until then, add /usr/local/nvidia/lib64 before the image cuda path to allow override.
ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib64:${LD_LIBRARY_PATH}

#################### vLLM installation IMAGE ####################

#################### TEST IMAGE ####################
Expand Down