xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-06-04 18:09:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI] Add SM120 to the Dockerfile (#19794)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin 2025-06-26 08:23:56 +09:00 committed by GitHub
parent 2d7620c3eb
commit 296ce95d8e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docker/Dockerfile
View File

@ -77,7 +77,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
# can be useful for both `dev` and `test` # can be useful for both `dev` and `test`
# explicitly set the list to avoid issues with torch 2.2 # explicitly set the list to avoid issues with torch 2.2
# 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+PTX' 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}
# 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'
@ -244,7 +244,7 @@ RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist
# If we need to build FlashInfer wheel before its release: # If we need to build FlashInfer wheel before its release:
# $ # Note we remove 7.0 from the arch list compared to the list below, since FlashInfer only supports sm75+ # $ # Note we remove 7.0 from the arch list compared to the list below, since FlashInfer only supports sm75+
# $ export TORCH_CUDA_ARCH_LIST='7.5 8.0 8.9 9.0a 10.0a' # $ export TORCH_CUDA_ARCH_LIST='7.5 8.0 8.9 9.0a 10.0a 12.0'
# $ git clone https://github.com/flashinfer-ai/flashinfer.git --recursive # $ git clone https://github.com/flashinfer-ai/flashinfer.git --recursive
# $ cd flashinfer # $ cd flashinfer
# $ git checkout v0.2.6.post1 # $ git checkout v0.2.6.post1
@ -261,7 +261,7 @@ if [ "$TARGETPLATFORM" != "linux/arm64" ]; then \
if [[ "$CUDA_VERSION" == 12.8* ]]; then \ if [[ "$CUDA_VERSION" == 12.8* ]]; then \
uv pip install --system https://download.pytorch.org/whl/cu128/flashinfer/flashinfer_python-0.2.6.post1%2Bcu128torch2.7-cp39-abi3-linux_x86_64.whl; \ uv pip install --system https://download.pytorch.org/whl/cu128/flashinfer/flashinfer_python-0.2.6.post1%2Bcu128torch2.7-cp39-abi3-linux_x86_64.whl; \
else \ else \
export TORCH_CUDA_ARCH_LIST='7.5 8.0 8.9 9.0a 10.0a' && \ export TORCH_CUDA_ARCH_LIST='7.5 8.0 8.9 9.0a 10.0a 12.0' && \
git clone https://github.com/flashinfer-ai/flashinfer.git --single-branch --branch v0.2.6.post1 --recursive && \ git clone https://github.com/flashinfer-ai/flashinfer.git --single-branch --branch v0.2.6.post1 --recursive && \
# Needed to build AOT kernels # Needed to build AOT kernels
(cd flashinfer && \ (cd flashinfer && \