From 3c0ef769bace3d48b276c7233ed6f39fe03f95b7 Mon Sep 17 00:00:00 2001 From: Eli Uriegas <1700823+seemethere@users.noreply.github.com> Date: Wed, 27 Aug 2025 10:41:48 -0700 Subject: [PATCH] ci: Add arm64 docker build to release pipeline (#23210) Signed-off-by: Eli Uriegas Signed-off-by: Eli Uriegas <1700823+seemethere@users.noreply.github.com> --- .buildkite/release-pipeline.yaml | 38 +++++++++++++++++++++++++++----- 1 file changed, 32 insertions(+), 6 deletions(-) diff --git a/.buildkite/release-pipeline.yaml b/.buildkite/release-pipeline.yaml index f96c38bf57..86aae426c2 100644 --- a/.buildkite/release-pipeline.yaml +++ b/.buildkite/release-pipeline.yaml @@ -7,7 +7,7 @@ steps: 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=12.8.1 --build-arg torch_cuda_arch_list='8.7 9.0 10.0+PTX' --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=12.8.1 --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 ." - "mkdir artifacts" - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'" - "bash .buildkite/scripts/upload-wheels.sh" @@ -62,23 +62,49 @@ steps: env: DOCKER_BUILDKIT: "1" - - block: "Build release image" + - block: "Build release image (x86)" depends_on: ~ key: block-release-image-build - - label: "Build release image" + - label: "Build release image (x86)" depends_on: block-release-image-build - id: build-release-image + id: build-release-image-x86 agents: queue: cpu_queue_postmerge commands: - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7" - - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.8.1 --build-arg FLASHINFER_AOT_COMPILE=true --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT --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=12.8.1 --build-arg FLASHINFER_AOT_COMPILE=true --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)" + # re-tag to default image tag and push, just in case arm64 build fails + - "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m) public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT" - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT" + - label: "Build release image (arm64)" + depends_on: block-release-image-build + id: build-release-image-arm64 + agents: + 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=12.8.1 --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 push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)" + + # Add job to create multi-arch manifest + - label: "Create multi-arch manifest" + depends_on: + - build-release-image-x86 + - build-release-image-arm64 + id: create-multi-arch-manifest + agents: + queue: 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 manifest create public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-aarch64 --amend" + - "docker manifest push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT" + - label: "Annotate release workflow" depends_on: - - build-release-image + - create-multi-arch-manifest - build-wheel-cuda-12-8 - build-wheel-cuda-12-6 - build-wheel-cuda-11-8