From 8a9f9f762a47e24ed8b48a8472f6757346cb30ae Mon Sep 17 00:00:00 2001 From: "Kevin H. Luu" Date: Mon, 10 Aug 2026 16:38:22 -0700 Subject: [PATCH] [CI] Parallelize release image publishing (#51735) Signed-off-by: khluu Co-authored-by: OpenAI Codex --- .buildkite/release-pipeline.yaml | 12 +- .buildkite/scripts/publish-release-images.sh | 275 ++++++++++--------- 2 files changed, 162 insertions(+), 125 deletions(-) diff --git a/.buildkite/release-pipeline.yaml b/.buildkite/release-pipeline.yaml index de67095474..6b97bc57da 100644 --- a/.buildkite/release-pipeline.yaml +++ b/.buildkite/release-pipeline.yaml @@ -959,14 +959,22 @@ steps: - step: build-cpu-release-image-arm64 allow_failure: true - - label: "Publish release images to DockerHub" + - label: "Publish {{matrix}} release images to DockerHub" depends_on: - block-publish-release-images key: publish-release-images-dockerhub agents: queue: small_cpu_queue_release commands: - - "bash .buildkite/scripts/publish-release-images.sh" + - "bash .buildkite/scripts/publish-release-images.sh {{matrix}}" + matrix: + - "cuda-13-0" + - "cuda-12-9" + - "cuda-13-0-ubuntu-24-04" + - "cuda-12-9-ubuntu-24-04" + - "rocm" + - "xpu" + - "cpu" plugins: - docker-login#v3.0.0: username: vllmbot diff --git a/.buildkite/scripts/publish-release-images.sh b/.buildkite/scripts/publish-release-images.sh index 91b5c3ace1..dd54b1717e 100755 --- a/.buildkite/scripts/publish-release-images.sh +++ b/.buildkite/scripts/publish-release-images.sh @@ -2,12 +2,26 @@ # SPDX-License-Identifier: Apache-2.0 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project # -# Publish release Docker images from ECR to DockerHub. +# Publish a release Docker image family from ECR to DockerHub. # Pulls per-arch images, tags with latest and versioned tags, pushes them, # then creates and pushes multi-arch manifests. set -euo pipefail +TARGET="${1:-all}" +case "${TARGET}" in + cuda-13-0 | cuda-12-9 | cuda-13-0-ubuntu-24-04 | \ + cuda-12-9-ubuntu-24-04 | rocm | xpu | cpu | all) ;; + *) + echo "Usage: $0 {cuda-13-0|cuda-12-9|cuda-13-0-ubuntu-24-04|cuda-12-9-ubuntu-24-04|rocm|xpu|cpu|all}" + exit 2 + ;; +esac + +target_enabled() { + [ "${TARGET}" = "all" ] || [ "${TARGET}" = "$1" ] +} + RELEASE_VERSION=$(buildkite-agent meta-data get release-version --default "" | sed 's/^v//') if [ -z "${RELEASE_VERSION}" ]; then echo "ERROR: release-version metadata not set" @@ -15,12 +29,10 @@ if [ -z "${RELEASE_VERSION}" ]; then fi COMMIT="$BUILDKITE_COMMIT" -ROCM_BASE_CACHE_KEY=$(.buildkite/scripts/cache-rocm-base-wheels.sh key) echo "========================================" -echo "Publishing release images v${RELEASE_VERSION}" +echo "Publishing ${TARGET} release images v${RELEASE_VERSION}" echo " Commit: ${COMMIT}" -echo " ROCm base cache key: ${ROCM_BASE_CACHE_KEY}" echo "========================================" # Login to ECR to pull staging images @@ -29,122 +41,137 @@ aws ecr-public get-login-password --region us-east-1 | \ # ---- CUDA (default: 13.0) ---- -docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64 -docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64 +if target_enabled cuda-13-0; then + docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64 + docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64 -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64 vllm/vllm-openai:latest-x86_64 -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64 vllm/vllm-openai:v${RELEASE_VERSION}-x86_64 -docker push vllm/vllm-openai:latest-x86_64 -docker push vllm/vllm-openai:v${RELEASE_VERSION}-x86_64 + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64 vllm/vllm-openai:latest-x86_64 + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64 vllm/vllm-openai:v${RELEASE_VERSION}-x86_64 + docker push vllm/vllm-openai:latest-x86_64 + docker push vllm/vllm-openai:v${RELEASE_VERSION}-x86_64 -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64 vllm/vllm-openai:latest-aarch64 -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64 -docker push vllm/vllm-openai:latest-aarch64 -docker push vllm/vllm-openai:v${RELEASE_VERSION}-aarch64 + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64 vllm/vllm-openai:latest-aarch64 + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64 + docker push vllm/vllm-openai:latest-aarch64 + docker push vllm/vllm-openai:v${RELEASE_VERSION}-aarch64 -docker manifest rm vllm/vllm-openai:latest || true -docker manifest rm vllm/vllm-openai:v${RELEASE_VERSION} || true -docker manifest create vllm/vllm-openai:latest vllm/vllm-openai:latest-x86_64 vllm/vllm-openai:latest-aarch64 -docker manifest create vllm/vllm-openai:v${RELEASE_VERSION} vllm/vllm-openai:v${RELEASE_VERSION}-x86_64 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64 -docker manifest push vllm/vllm-openai:latest -docker manifest push vllm/vllm-openai:v${RELEASE_VERSION} + docker manifest rm vllm/vllm-openai:latest || true + docker manifest rm vllm/vllm-openai:v${RELEASE_VERSION} || true + docker manifest create vllm/vllm-openai:latest vllm/vllm-openai:latest-x86_64 vllm/vllm-openai:latest-aarch64 + docker manifest create vllm/vllm-openai:v${RELEASE_VERSION} vllm/vllm-openai:v${RELEASE_VERSION}-x86_64 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64 + docker manifest push vllm/vllm-openai:latest + docker manifest push vllm/vllm-openai:v${RELEASE_VERSION} +fi # ---- CUDA 12.9 ---- -docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-cu129 -docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64-cu129 +if target_enabled cuda-12-9; then + docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-cu129 + docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64-cu129 -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-cu129 vllm/vllm-openai:latest-x86_64-cu129 -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-cu129 vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-cu129 -docker push vllm/vllm-openai:latest-x86_64-cu129 -docker push vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-cu129 + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-cu129 vllm/vllm-openai:latest-x86_64-cu129 + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-cu129 vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-cu129 + docker push vllm/vllm-openai:latest-x86_64-cu129 + docker push vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-cu129 -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64-cu129 vllm/vllm-openai:latest-aarch64-cu129 -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64-cu129 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-cu129 -docker push vllm/vllm-openai:latest-aarch64-cu129 -docker push vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-cu129 + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64-cu129 vllm/vllm-openai:latest-aarch64-cu129 + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64-cu129 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-cu129 + docker push vllm/vllm-openai:latest-aarch64-cu129 + docker push vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-cu129 -docker manifest rm vllm/vllm-openai:latest-cu129 || true -docker manifest rm vllm/vllm-openai:v${RELEASE_VERSION}-cu129 || true -docker manifest create vllm/vllm-openai:latest-cu129 vllm/vllm-openai:latest-x86_64-cu129 vllm/vllm-openai:latest-aarch64-cu129 -docker manifest create vllm/vllm-openai:v${RELEASE_VERSION}-cu129 vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-cu129 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-cu129 -docker manifest push vllm/vllm-openai:latest-cu129 -docker manifest push vllm/vllm-openai:v${RELEASE_VERSION}-cu129 + docker manifest rm vllm/vllm-openai:latest-cu129 || true + docker manifest rm vllm/vllm-openai:v${RELEASE_VERSION}-cu129 || true + docker manifest create vllm/vllm-openai:latest-cu129 vllm/vllm-openai:latest-x86_64-cu129 vllm/vllm-openai:latest-aarch64-cu129 + docker manifest create vllm/vllm-openai:v${RELEASE_VERSION}-cu129 vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-cu129 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-cu129 + docker manifest push vllm/vllm-openai:latest-cu129 + docker manifest push vllm/vllm-openai:v${RELEASE_VERSION}-cu129 +fi # ---- Ubuntu 24.04 (CUDA 13.0) ---- -docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-ubuntu2404 -docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64-ubuntu2404 +if target_enabled cuda-13-0-ubuntu-24-04; then + docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-ubuntu2404 + docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64-ubuntu2404 -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-ubuntu2404 vllm/vllm-openai:latest-x86_64-ubuntu2404 -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-ubuntu2404 vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-ubuntu2404 -docker push vllm/vllm-openai:latest-x86_64-ubuntu2404 -docker push vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-ubuntu2404 + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-ubuntu2404 vllm/vllm-openai:latest-x86_64-ubuntu2404 + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-ubuntu2404 vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-ubuntu2404 + docker push vllm/vllm-openai:latest-x86_64-ubuntu2404 + docker push vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-ubuntu2404 -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64-ubuntu2404 vllm/vllm-openai:latest-aarch64-ubuntu2404 -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64-ubuntu2404 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-ubuntu2404 -docker push vllm/vllm-openai:latest-aarch64-ubuntu2404 -docker push vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-ubuntu2404 + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64-ubuntu2404 vllm/vllm-openai:latest-aarch64-ubuntu2404 + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64-ubuntu2404 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-ubuntu2404 + docker push vllm/vllm-openai:latest-aarch64-ubuntu2404 + docker push vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-ubuntu2404 -docker manifest rm vllm/vllm-openai:latest-ubuntu2404 || true -docker manifest rm vllm/vllm-openai:v${RELEASE_VERSION}-ubuntu2404 || true -docker manifest create vllm/vllm-openai:latest-ubuntu2404 vllm/vllm-openai:latest-x86_64-ubuntu2404 vllm/vllm-openai:latest-aarch64-ubuntu2404 -docker manifest create vllm/vllm-openai:v${RELEASE_VERSION}-ubuntu2404 vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-ubuntu2404 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-ubuntu2404 -docker manifest push vllm/vllm-openai:latest-ubuntu2404 -docker manifest push vllm/vllm-openai:v${RELEASE_VERSION}-ubuntu2404 + docker manifest rm vllm/vllm-openai:latest-ubuntu2404 || true + docker manifest rm vllm/vllm-openai:v${RELEASE_VERSION}-ubuntu2404 || true + docker manifest create vllm/vllm-openai:latest-ubuntu2404 vllm/vllm-openai:latest-x86_64-ubuntu2404 vllm/vllm-openai:latest-aarch64-ubuntu2404 + docker manifest create vllm/vllm-openai:v${RELEASE_VERSION}-ubuntu2404 vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-ubuntu2404 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-ubuntu2404 + docker manifest push vllm/vllm-openai:latest-ubuntu2404 + docker manifest push vllm/vllm-openai:v${RELEASE_VERSION}-ubuntu2404 +fi # ---- Ubuntu 24.04 (CUDA 12.9) ---- -docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-cu129-ubuntu2404 -docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64-cu129-ubuntu2404 +if target_enabled cuda-12-9-ubuntu-24-04; then + docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-cu129-ubuntu2404 + docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64-cu129-ubuntu2404 -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-cu129-ubuntu2404 vllm/vllm-openai:latest-x86_64-cu129-ubuntu2404 -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-cu129-ubuntu2404 vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-cu129-ubuntu2404 -docker push vllm/vllm-openai:latest-x86_64-cu129-ubuntu2404 -docker push vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-cu129-ubuntu2404 + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-cu129-ubuntu2404 vllm/vllm-openai:latest-x86_64-cu129-ubuntu2404 + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-cu129-ubuntu2404 vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-cu129-ubuntu2404 + docker push vllm/vllm-openai:latest-x86_64-cu129-ubuntu2404 + docker push vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-cu129-ubuntu2404 -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64-cu129-ubuntu2404 vllm/vllm-openai:latest-aarch64-cu129-ubuntu2404 -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64-cu129-ubuntu2404 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-cu129-ubuntu2404 -docker push vllm/vllm-openai:latest-aarch64-cu129-ubuntu2404 -docker push vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-cu129-ubuntu2404 + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64-cu129-ubuntu2404 vllm/vllm-openai:latest-aarch64-cu129-ubuntu2404 + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-aarch64-cu129-ubuntu2404 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-cu129-ubuntu2404 + docker push vllm/vllm-openai:latest-aarch64-cu129-ubuntu2404 + docker push vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-cu129-ubuntu2404 -docker manifest rm vllm/vllm-openai:latest-cu129-ubuntu2404 || true -docker manifest rm vllm/vllm-openai:v${RELEASE_VERSION}-cu129-ubuntu2404 || true -docker manifest create vllm/vllm-openai:latest-cu129-ubuntu2404 vllm/vllm-openai:latest-x86_64-cu129-ubuntu2404 vllm/vllm-openai:latest-aarch64-cu129-ubuntu2404 -docker manifest create vllm/vllm-openai:v${RELEASE_VERSION}-cu129-ubuntu2404 vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-cu129-ubuntu2404 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-cu129-ubuntu2404 -docker manifest push vllm/vllm-openai:latest-cu129-ubuntu2404 -docker manifest push vllm/vllm-openai:v${RELEASE_VERSION}-cu129-ubuntu2404 + docker manifest rm vllm/vllm-openai:latest-cu129-ubuntu2404 || true + docker manifest rm vllm/vllm-openai:v${RELEASE_VERSION}-cu129-ubuntu2404 || true + docker manifest create vllm/vllm-openai:latest-cu129-ubuntu2404 vllm/vllm-openai:latest-x86_64-cu129-ubuntu2404 vllm/vllm-openai:latest-aarch64-cu129-ubuntu2404 + docker manifest create vllm/vllm-openai:v${RELEASE_VERSION}-cu129-ubuntu2404 vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-cu129-ubuntu2404 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-cu129-ubuntu2404 + docker manifest push vllm/vllm-openai:latest-cu129-ubuntu2404 + docker manifest push vllm/vllm-openai:v${RELEASE_VERSION}-cu129-ubuntu2404 +fi # ---- ROCm ---- -docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-rocm -docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${ROCM_BASE_CACHE_KEY}-rocm-base +if target_enabled rocm; then + ROCM_BASE_CACHE_KEY=$(.buildkite/scripts/cache-rocm-base-wheels.sh key) + echo "ROCm base cache key: ${ROCM_BASE_CACHE_KEY}" -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-rocm vllm/vllm-openai-rocm:latest -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-rocm vllm/vllm-openai-rocm:v${RELEASE_VERSION} -docker push vllm/vllm-openai-rocm:latest -docker push vllm/vllm-openai-rocm:v${RELEASE_VERSION} + docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-rocm + docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${ROCM_BASE_CACHE_KEY}-rocm-base -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${ROCM_BASE_CACHE_KEY}-rocm-base vllm/vllm-openai-rocm:latest-base -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${ROCM_BASE_CACHE_KEY}-rocm-base vllm/vllm-openai-rocm:v${RELEASE_VERSION}-base -docker push vllm/vllm-openai-rocm:latest-base -docker push vllm/vllm-openai-rocm:v${RELEASE_VERSION}-base + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-rocm vllm/vllm-openai-rocm:latest + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-rocm vllm/vllm-openai-rocm:v${RELEASE_VERSION} + docker push vllm/vllm-openai-rocm:latest + docker push vllm/vllm-openai-rocm:v${RELEASE_VERSION} + + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${ROCM_BASE_CACHE_KEY}-rocm-base vllm/vllm-openai-rocm:latest-base + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${ROCM_BASE_CACHE_KEY}-rocm-base vllm/vllm-openai-rocm:v${RELEASE_VERSION}-base + docker push vllm/vllm-openai-rocm:latest-base + docker push vllm/vllm-openai-rocm:v${RELEASE_VERSION}-base +fi # ---- XPU ---- -docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-xpu +if target_enabled xpu; then + docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-xpu -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-xpu vllm/vllm-openai-xpu:latest-x86_64 -docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-xpu vllm/vllm-openai-xpu:v${RELEASE_VERSION}-x86_64 -docker push vllm/vllm-openai-xpu:latest-x86_64 -docker push vllm/vllm-openai-xpu:v${RELEASE_VERSION}-x86_64 + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-xpu vllm/vllm-openai-xpu:latest-x86_64 + docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${COMMIT}-x86_64-xpu vllm/vllm-openai-xpu:v${RELEASE_VERSION}-x86_64 + docker push vllm/vllm-openai-xpu:latest-x86_64 + docker push vllm/vllm-openai-xpu:v${RELEASE_VERSION}-x86_64 -docker manifest rm vllm/vllm-openai-xpu:latest || true -docker manifest rm vllm/vllm-openai-xpu:v${RELEASE_VERSION} || true -docker manifest create vllm/vllm-openai-xpu:latest vllm/vllm-openai-xpu:latest-x86_64 --amend -docker manifest create vllm/vllm-openai-xpu:v${RELEASE_VERSION} vllm/vllm-openai-xpu:v${RELEASE_VERSION}-x86_64 --amend -docker manifest push vllm/vllm-openai-xpu:latest -docker manifest push vllm/vllm-openai-xpu:v${RELEASE_VERSION} + docker manifest rm vllm/vllm-openai-xpu:latest || true + docker manifest rm vllm/vllm-openai-xpu:v${RELEASE_VERSION} || true + docker manifest create vllm/vllm-openai-xpu:latest vllm/vllm-openai-xpu:latest-x86_64 --amend + docker manifest create vllm/vllm-openai-xpu:v${RELEASE_VERSION} vllm/vllm-openai-xpu:v${RELEASE_VERSION}-x86_64 --amend + docker manifest push vllm/vllm-openai-xpu:latest + docker manifest push vllm/vllm-openai-xpu:v${RELEASE_VERSION} +fi # ---- CPU ---- # CPU images are behind separate block steps and may not have been built. @@ -153,44 +180,46 @@ docker manifest push vllm/vllm-openai-xpu:v${RELEASE_VERSION} # arch would leave `:latest-x86_64` pointing at the new release while the # `:latest` multi-arch manifest still resolves to the previous release. -CPU_X86_TAG=public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:v${RELEASE_VERSION} -CPU_ARM_TAG=public.ecr.aws/q9t5s3a7/vllm-arm64-cpu-release-repo:v${RELEASE_VERSION} +if target_enabled cpu; then + CPU_X86_TAG=public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:v${RELEASE_VERSION} + CPU_ARM_TAG=public.ecr.aws/q9t5s3a7/vllm-arm64-cpu-release-repo:v${RELEASE_VERSION} -CPU_X86_AVAILABLE=false -CPU_ARM_AVAILABLE=false -docker manifest inspect "${CPU_X86_TAG}" >/dev/null 2>&1 && CPU_X86_AVAILABLE=true -docker manifest inspect "${CPU_ARM_TAG}" >/dev/null 2>&1 && CPU_ARM_AVAILABLE=true + CPU_X86_AVAILABLE=false + CPU_ARM_AVAILABLE=false + docker manifest inspect "${CPU_X86_TAG}" >/dev/null 2>&1 && CPU_X86_AVAILABLE=true + docker manifest inspect "${CPU_ARM_TAG}" >/dev/null 2>&1 && CPU_ARM_AVAILABLE=true -if [ "$CPU_X86_AVAILABLE" = "true" ] && [ "$CPU_ARM_AVAILABLE" = "true" ]; then - docker pull "${CPU_X86_TAG}" - docker tag "${CPU_X86_TAG}" vllm/vllm-openai-cpu:latest-x86_64 - docker tag "${CPU_X86_TAG}" vllm/vllm-openai-cpu:v${RELEASE_VERSION}-x86_64 - docker push vllm/vllm-openai-cpu:latest-x86_64 - docker push vllm/vllm-openai-cpu:v${RELEASE_VERSION}-x86_64 + if [ "$CPU_X86_AVAILABLE" = "true" ] && [ "$CPU_ARM_AVAILABLE" = "true" ]; then + docker pull "${CPU_X86_TAG}" + docker tag "${CPU_X86_TAG}" vllm/vllm-openai-cpu:latest-x86_64 + docker tag "${CPU_X86_TAG}" vllm/vllm-openai-cpu:v${RELEASE_VERSION}-x86_64 + docker push vllm/vllm-openai-cpu:latest-x86_64 + docker push vllm/vllm-openai-cpu:v${RELEASE_VERSION}-x86_64 - docker pull "${CPU_ARM_TAG}" - docker tag "${CPU_ARM_TAG}" vllm/vllm-openai-cpu:latest-arm64 - docker tag "${CPU_ARM_TAG}" vllm/vllm-openai-cpu:v${RELEASE_VERSION}-arm64 - docker push vllm/vllm-openai-cpu:latest-arm64 - docker push vllm/vllm-openai-cpu:v${RELEASE_VERSION}-arm64 + docker pull "${CPU_ARM_TAG}" + docker tag "${CPU_ARM_TAG}" vllm/vllm-openai-cpu:latest-arm64 + docker tag "${CPU_ARM_TAG}" vllm/vllm-openai-cpu:v${RELEASE_VERSION}-arm64 + docker push vllm/vllm-openai-cpu:latest-arm64 + docker push vllm/vllm-openai-cpu:v${RELEASE_VERSION}-arm64 - docker manifest rm vllm/vllm-openai-cpu:latest || true - docker manifest rm vllm/vllm-openai-cpu:v${RELEASE_VERSION} || true - docker manifest create vllm/vllm-openai-cpu:latest vllm/vllm-openai-cpu:latest-x86_64 vllm/vllm-openai-cpu:latest-arm64 - docker manifest create vllm/vllm-openai-cpu:v${RELEASE_VERSION} vllm/vllm-openai-cpu:v${RELEASE_VERSION}-x86_64 vllm/vllm-openai-cpu:v${RELEASE_VERSION}-arm64 - docker manifest push vllm/vllm-openai-cpu:latest - docker manifest push vllm/vllm-openai-cpu:v${RELEASE_VERSION} -elif [ "$CPU_X86_AVAILABLE" = "false" ] && [ "$CPU_ARM_AVAILABLE" = "false" ]; then - echo "WARNING: Neither CPU image found in ECR, skipping CPU publish (ensure block-cpu-release-image-build and block-arm64-cpu-release-image-build were unblocked and the builds finished pushing)" -else - # Partial state: one arch built, the other did not. Fail loudly rather than - # ship a Docker Hub state where `:latest-${arch}` and `:latest` (multi-arch) - # disagree on which release they point at. - echo "ERROR: Partial CPU build detected (x86_64=${CPU_X86_AVAILABLE}, arm64=${CPU_ARM_AVAILABLE})." - echo " Refusing to publish to avoid split-tag drift between per-arch and multi-arch tags." - echo " Re-run the missing CPU build and retry, or manually publish if a single-arch release is intended." - exit 1 + docker manifest rm vllm/vllm-openai-cpu:latest || true + docker manifest rm vllm/vllm-openai-cpu:v${RELEASE_VERSION} || true + docker manifest create vllm/vllm-openai-cpu:latest vllm/vllm-openai-cpu:latest-x86_64 vllm/vllm-openai-cpu:latest-arm64 + docker manifest create vllm/vllm-openai-cpu:v${RELEASE_VERSION} vllm/vllm-openai-cpu:v${RELEASE_VERSION}-x86_64 vllm/vllm-openai-cpu:v${RELEASE_VERSION}-arm64 + docker manifest push vllm/vllm-openai-cpu:latest + docker manifest push vllm/vllm-openai-cpu:v${RELEASE_VERSION} + elif [ "$CPU_X86_AVAILABLE" = "false" ] && [ "$CPU_ARM_AVAILABLE" = "false" ]; then + echo "WARNING: Neither CPU image found in ECR, skipping CPU publish (ensure block-cpu-release-image-build and block-arm64-cpu-release-image-build were unblocked and the builds finished pushing)" + else + # Partial state: one arch built, the other did not. Fail loudly rather than + # ship a Docker Hub state where `:latest-${arch}` and `:latest` (multi-arch) + # disagree on which release they point at. + echo "ERROR: Partial CPU build detected (x86_64=${CPU_X86_AVAILABLE}, arm64=${CPU_ARM_AVAILABLE})." + echo " Refusing to publish to avoid split-tag drift between per-arch and multi-arch tags." + echo " Re-run the missing CPU build and retry, or manually publish if a single-arch release is intended." + exit 1 + fi fi echo "" -echo "Successfully published release images for v${RELEASE_VERSION}" +echo "Successfully published ${TARGET} release images for v${RELEASE_VERSION}"