xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 04:54:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
Signed-off-by: Clayton Coleman <smarterclayton@gmail.com>
This commit is contained in:
Clayton Coleman 2025-09-27 13:36:28 -04:00 committed by GitHub
parent c0ec81836f
commit 5546acb463
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docker/Dockerfile
View File

@ -474,6 +474,12 @@ 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 ####################