xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-06-04 14:35:46 +08:00
Code Issues Packages Projects Releases Wiki Activity

Remove from dockerfile

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
mgoin 2025-07-09 13:02:10 -04:00
parent 721dcb2ebc
commit f1fd89a9bf
1 changed files with 0 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
docker/Dockerfile
View File

@ -164,7 +164,6 @@ RUN --mount=type=cache,target=/root/.cache/uv \
# see https://github.com/pytorch/pytorch/pull/123243 # 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' ARG torch_cuda_arch_list='7.0 7.5 8.0 8.9 9.0 10.0 12.0'
ENV TORCH_CUDA_ARCH_LIST=${torch_cuda_arch_list} ENV TORCH_CUDA_ARCH_LIST=${torch_cuda_arch_list}
ENV TORCH_NVCC_FLAGS="-Xfatbin -compress-all -compress-mode=size"
# Override the arch list for flash-attn to reduce the binary size # Override the arch list for flash-attn to reduce the binary size
ARG vllm_fa_cmake_gpu_arches='80-real;90-real' ARG vllm_fa_cmake_gpu_arches='80-real;90-real'
ENV VLLM_FA_CMAKE_GPU_ARCHES=${vllm_fa_cmake_gpu_arches} ENV VLLM_FA_CMAKE_GPU_ARCHES=${vllm_fa_cmake_gpu_arches}