xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 22:05:44 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI] Fix FlashInfer AOT in release docker image (#25730)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
This commit is contained in:
Michael Goin 2025-09-26 17:11:40 -04:00 committed by simon-mo
parent c2fa2d4dc9
commit 5aa5811a16
2 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.buildkite/release-pipeline.yaml
View File

@ -76,7 +76,7 @@ steps:
queue: arm64_cpu_queue_postmerge
commands:
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.9.1 --build-arg torch_cuda_arch_list='8.7 9.0 10.0+PTX 12.0' --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m) --target vllm-openai --progress plain -f docker/Dockerfile ."
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.9.1 --build-arg FLASHINFER_AOT_COMPILE=true --build-arg torch_cuda_arch_list='8.7 9.0 10.0+PTX 12.0' --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m) --target vllm-openai --progress plain -f docker/Dockerfile ."
- "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)"
# Add job to create multi-arch manifest

3
docker/Dockerfile
View File

@ -404,6 +404,9 @@ RUN --mount=type=cache,target=/root/.cache/uv bash - <<'BASH'
FI_TORCH_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a 12.0"
fi
echo "🏗️ Installing FlashInfer with AOT compilation for arches: ${FI_TORCH_CUDA_ARCH_LIST}"
export FLASHINFER_CUDA_ARCH_LIST="${FI_TORCH_CUDA_ARCH_LIST}"
# HACK: We need these to run flashinfer.aot before installing flashinfer, get from the package in the future
uv pip install --system cuda-python==$(echo $CUDA_VERSION | cut -d. -f1,2) pynvml==$(echo $CUDA_VERSION | cut -d. -f1) nvidia-nvshmem-cu$(echo $CUDA_VERSION | cut -d. -f1)
# Build AOT kernels
TORCH_CUDA_ARCH_LIST="${FI_TORCH_CUDA_ARCH_LIST}" \
python3 -m flashinfer.aot