youngkingdom/vllm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[CI/Build] get rid of unused VLLM_FA_CMAKE_GPU_ARCHES (#21599)

Browse Source 
Signed-off-by: Daniele Trifirò <dtrifiro@redhat.com>
This commit is contained in:
Daniele
2025-07-31 09:00:08 +02:00
committed by GitHub
parent 9532a6d563
commit d2aab336ad
5 changed files with 2 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docker/Dockerfile
View File

@ -164,9 +164,6 @@ RUN --mount=type=cache,target=/root/.cache/uv \
# see https://github.com/pytorch/pytorch/pull/123243
ARG torch_cuda_arch_list='7.0 7.5 8.0 8.9 9.0 10.0 12.0'
ENV TORCH_CUDA_ARCH_LIST=${torch_cuda_arch_list}
# Override the arch list for flash-attn to reduce the binary size
ARG vllm_fa_cmake_gpu_arches='80-real;90-real'
ENV VLLM_FA_CMAKE_GPU_ARCHES=${vllm_fa_cmake_gpu_arches}
#################### BASE BUILD IMAGE ####################
#################### WHEEL BUILD IMAGE ####################

3
docker/Dockerfile.nightly_torch
View File

@ -114,9 +114,6 @@ RUN cat torch_build_versions.txt
# explicitly set the list to avoid issues with torch 2.2
# see https://github.com/pytorch/pytorch/pull/123243
# Override the arch list for flash-attn to reduce the binary size
ARG vllm_fa_cmake_gpu_arches='80-real;90-real'
ENV VLLM_FA_CMAKE_GPU_ARCHES=${vllm_fa_cmake_gpu_arches}
#################### BASE BUILD IMAGE ####################
#################### WHEEL BUILD IMAGE ####################