xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 07:14:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI/Build] Fix FlashInfer double build in Dockerfile (#20651)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin 2025-07-10 08:41:56 +09:00 committed by GitHub
parent 7c12a765aa
commit b7d9e9416f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
docker/Dockerfile
View File

@ -387,30 +387,26 @@ RUN --mount=type=cache,target=/root/.cache/uv bash - <<'BASH'
if [[ "$CUDA_VERSION" == 12.8* ]]; then
uv pip install --system ${FLASHINFER_CUDA128_INDEX_URL}/${FLASHINFER_CUDA128_WHEEL}
else
export TORCH_CUDA_ARCH_LIST='7.5 8.0 8.9 9.0a 10.0a 12.0'
git clone ${FLASHINFER_GIT_REPO} --single-branch --branch ${FLASHINFER_GIT_REF} --recursive
# Needed to build AOT kernels
(cd flashinfer && \
python3 -m flashinfer.aot && \
uv pip install --system --no-build-isolation . \
)
rm -rf flashinfer
# Default arches (skipping 10.0a and 12.0 since these need 12.8)
# Exclude CUDA arches for older versions (11.x and 12.0-12.7)
# TODO: Update this to allow setting TORCH_CUDA_ARCH_LIST as a build arg.
TORCH_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a"
if [[ "${CUDA_VERSION}" == 11.* ]]; then
TORCH_CUDA_ARCH_LIST="7.5 8.0 8.9"
FI_TORCH_CUDA_ARCH_LIST="7.5 8.0 8.9"
elif [[ "${CUDA_VERSION}" == 12.[0-7]* ]]; then
FI_TORCH_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a"
else
# CUDA 12.8+ supports 10.0a and 12.0
FI_TORCH_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a 12.0"
fi
echo "🏗️ Building FlashInfer for arches: ${TORCH_CUDA_ARCH_LIST}"
echo "🏗️ Building FlashInfer for arches: ${FI_TORCH_CUDA_ARCH_LIST}"
git clone --depth 1 --recursive --shallow-submodules \
--branch v0.2.6.post1 \
https://github.com/flashinfer-ai/flashinfer.git flashinfer
--branch ${FLASHINFER_GIT_REF} \
${FLASHINFER_GIT_REPO} flashinfer
# Needed to build AOT kernels
pushd flashinfer
python3 -m flashinfer.aot
TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST}" \
TORCH_CUDA_ARCH_LIST="${FI_TORCH_CUDA_ARCH_LIST}" \
uv pip install --system --no-build-isolation .
popd