biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[ci] fix wheel names for arm wheels (#24898)

Browse Source 
Signed-off-by: simon-mo <simon.mo@hey.com>
This commit is contained in:
Simon Mo
2025-09-15 14:39:08 -07:00
committed by GitHub
parent e757a629e7
commit fd2f10546c
5 changed files with 36 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
.buildkite/release-pipeline.yaml
View File

@@ -1,24 +1,22 @@
steps:
# aarch64 + CUDA builds. PyTorch 2.8 aarch64 + CUDA wheel is only available on CUDA 12.9
- label: "Build arm64 wheel - CUDA 12.9"
depends_on: ~
id: build-wheel-arm64-cuda-12-9
agents:
queue: arm64_cpu_queue_postmerge
commands:
# #NOTE: torch_cuda_arch_list is derived from upstream PyTorch build files here:
# https://github.com/pytorch/pytorch/blob/main/.ci/aarch64_linux/aarch64_ci_build.sh#L7
- "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' --tag vllm-ci:build-image --target build --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 VLLM_MAIN_CUDA_VERSION=12.9 --build-arg torch_cuda_arch_list='8.7 9.0 10.0+PTX 12.0' --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
- "mkdir artifacts"
- "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
- "bash .buildkite/scripts/upload-wheels.sh"
env:
DOCKER_BUILDKIT: "1"
- block: "Build CUDA 12.8 wheel"
key: block-build-cu128-wheel
- label: "Build wheel - CUDA 12.8"
depends_on: block-build-cu128-wheel
depends_on: ~
id: build-wheel-cuda-12-8
agents:
queue: cpu_queue_postmerge
@@ -30,12 +28,8 @@ steps:
env:
DOCKER_BUILDKIT: "1"
- block: "Build CUDA 12.6 wheel"
key: block-build-cu126-wheel
depends_on: ~
- label: "Build wheel - CUDA 12.6"
depends_on: block-build-cu126-wheel
depends_on: ~
id: build-wheel-cuda-12-6
agents:
queue: cpu_queue_postmerge
@@ -102,8 +96,6 @@ steps:
depends_on:
- create-multi-arch-manifest
- build-wheel-cuda-12-8
- build-wheel-cuda-12-6
- build-wheel-cuda-12-9
id: annotate-release-workflow
agents:
queue: cpu_queue_postmerge

29
.buildkite/scripts/annotate-release.sh
View File

@@ -14,18 +14,33 @@ buildkite-agent annotate --style 'info' --context 'release-workflow' << EOF
To download the wheel:
\`\`\`
aws s3 cp s3://vllm-wheels/${RELEASE_VERSION}/vllm-${RELEASE_VERSION}-cp38-abi3-manylinux1_x86_64.whl .
aws s3 cp s3://vllm-wheels/${RELEASE_VERSION}/vllm-${RELEASE_VERSION}-cp38-abi3-manylinux2014_aarch64.whl .
aws s3 cp s3://vllm-wheels/${RELEASE_VERSION}+cu126/vllm-${RELEASE_VERSION}+cu126-cp38-abi3-manylinux1_x86_64.whl .
aws s3 cp s3://vllm-wheels/${RELEASE_VERSION}+cu118/vllm-${RELEASE_VERSION}+cu118-cp38-abi3-manylinux1_x86_64.whl .
aws s3 cp s3://vllm-wheels/${RELEASE_VERSION}+cu129/vllm-${RELEASE_VERSION}+cu129-cp38-abi3-manylinux1_x86_64.whl .
\`\`\`
To download and upload the image:
\`\`\`
docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT}
docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT} vllm/vllm-openai
docker tag vllm/vllm-openai vllm/vllm-openai:latest
docker tag vllm/vllm-openai vllm/vllm-openai:v${RELEASE_VERSION}
docker push vllm/vllm-openai:latest
docker push vllm/vllm-openai:v${RELEASE_VERSION}
docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT}-x86_64
docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT}-aarch64
docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT}-x86_64 vllm/vllm-openai:x86_64
docker tag vllm/vllm-openai:x86_64 vllm/vllm-openai:latest-x86_64
docker tag vllm/vllm-openai:x86_64 vllm/vllm-openai:v${RELEASE_VERSION}-x86_64
docker push vllm/vllm-openai:latest-x86_64
docker push vllm/vllm-openai:v${RELEASE_VERSION}-x86_64
docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT}-aarch64 vllm/vllm-openai:aarch64
docker tag vllm/vllm-openai:aarch64 vllm/vllm-openai:latest-aarch64
docker tag vllm/vllm-openai:aarch64 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64
docker push vllm/vllm-openai:latest-aarch64
docker push vllm/vllm-openai:v${RELEASE_VERSION}-aarch64
docker manifest create vllm/vllm-openai:latest vllm/vllm-openai:latest-x86_64 vllm/vllm-openai:latest-aarch64 --amend
docker manifest create vllm/vllm-openai:v${RELEASE_VERSION} vllm/vllm-openai:v${RELEASE_VERSION}-x86_64 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64 --amend
docker manifest push vllm/vllm-openai:latest
docker manifest push vllm/vllm-openai:v${RELEASE_VERSION}
\`\`\`
EOF