[CI] Annotate built Docker image tags on the Buildkite build page (#48101)

Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Kevin H. Luu
2026-07-09 22:02:40 +08:00
committed by GitHub
co-authored by Claude Opus 4.8
parent 85b3a7264b
commit 299d2b5655
8 changed files with 124 additions and 77 deletions
+8
View File
@@ -79,12 +79,18 @@ setup_buildx_builder() {
docker buildx ls | grep -E '^\*|^NAME' || docker buildx ls
}
annotate_image_tags() {
.buildkite/scripts/annotate-image-build.sh \
"${IMAGE_TAG:-}" "${IMAGE_TAG_LATEST:-}"
}
check_and_skip_if_image_exists() {
if [[ -n "${IMAGE_TAG:-}" ]]; then
echo "--- :mag: Checking if image exists"
if docker manifest inspect "${IMAGE_TAG}" >/dev/null 2>&1; then
echo "Image already exists: ${IMAGE_TAG}"
echo "Skipping build"
annotate_image_tags
exit 0
fi
echo "Image not found, proceeding with build"
@@ -254,3 +260,5 @@ echo "--- :docker: Building ${TARGET}"
docker --debug buildx bake -f "${VLLM_BAKE_FILE_PATH}" -f "${CI_HCL_PATH}" --progress plain "${TARGET}"
echo "--- :white_check_mark: Build complete"
annotate_image_tags
+19 -19
View File
@@ -9,30 +9,30 @@ fi
REGISTRY=$1
REPO=$2
BUILDKITE_COMMIT=$3
IMAGE="$REGISTRY/$REPO:$BUILDKITE_COMMIT-arm64"
# authenticate with AWS ECR
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY" || true
# skip build if image already exists
if [[ -z $(docker manifest inspect "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-arm64) ]]; then
echo "Image not found, proceeding with build..."
else
if docker manifest inspect "$IMAGE" >/dev/null 2>&1; then
echo "Image found"
exit 0
else
echo "Image not found, proceeding with build..."
# build for arm64 GPU targets: Grace/GH200 (sm_90) and DGX Spark/GB10
# (sm_121, family-covered by 12.0 under CUDA 13)
docker build --file docker/Dockerfile \
--platform linux/arm64 \
--build-arg max_jobs=16 \
--build-arg nvcc_threads=4 \
--build-arg torch_cuda_arch_list="9.0 12.0" \
--build-arg USE_SCCACHE=1 \
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
--tag "$IMAGE" \
--target test \
--progress plain .
# push
docker push "$IMAGE"
fi
# build for arm64 GPU targets: Grace/GH200 (sm_90) and DGX Spark/GB10
# (sm_121, family-covered by 12.0 under CUDA 13)
docker build --file docker/Dockerfile \
--platform linux/arm64 \
--build-arg max_jobs=16 \
--build-arg nvcc_threads=4 \
--build-arg torch_cuda_arch_list="9.0 12.0" \
--build-arg USE_SCCACHE=1 \
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
--tag "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-arm64 \
--target test \
--progress plain .
# push
docker push "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-arm64
.buildkite/scripts/annotate-image-build.sh "$IMAGE"
+15 -15
View File
@@ -9,26 +9,26 @@ fi
REGISTRY=$1
REPO=$2
BUILDKITE_COMMIT=$3
IMAGE="$REGISTRY/$REPO:$BUILDKITE_COMMIT-cpu"
# authenticate with AWS ECR
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY" || true
# skip build if image already exists
if [[ -z $(docker manifest inspect "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-cpu) ]]; then
echo "Image not found, proceeding with build..."
else
if docker manifest inspect "$IMAGE" >/dev/null 2>&1; then
echo "Image found"
exit 0
else
echo "Image not found, proceeding with build..."
# build
docker build --file docker/Dockerfile.cpu \
--build-arg max_jobs=16 \
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
--build-arg VLLM_CPU_X86=true \
--tag "$IMAGE" \
--target vllm-test \
--progress plain .
# push
docker push "$IMAGE"
fi
# build
docker build --file docker/Dockerfile.cpu \
--build-arg max_jobs=16 \
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
--build-arg VLLM_CPU_X86=true \
--tag "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-cpu \
--target vllm-test \
--progress plain .
# push
docker push "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-cpu
.buildkite/scripts/annotate-image-build.sh "$IMAGE"
+14 -14
View File
@@ -9,25 +9,25 @@ fi
REGISTRY=$1
REPO=$2
BUILDKITE_COMMIT=$3
IMAGE="$REGISTRY/$REPO:$BUILDKITE_COMMIT-arm64-cpu"
# authenticate with AWS ECR
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY" || true
# skip build if image already exists
if [[ -z $(docker manifest inspect "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-arm64-cpu) ]]; then
echo "Image not found, proceeding with build..."
else
if docker manifest inspect "$IMAGE" >/dev/null 2>&1; then
echo "Image found"
exit 0
else
echo "Image not found, proceeding with build..."
# build
docker build --file docker/Dockerfile.cpu \
--build-arg max_jobs=16 \
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
--tag "$IMAGE" \
--target vllm-test \
--progress plain .
# push
docker push "$IMAGE"
fi
# build
docker build --file docker/Dockerfile.cpu \
--build-arg max_jobs=16 \
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
--tag "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-arm64-cpu \
--target vllm-test \
--progress plain .
# push
docker push "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-arm64-cpu
.buildkite/scripts/annotate-image-build.sh "$IMAGE"
+15 -15
View File
@@ -9,26 +9,26 @@ fi
REGISTRY=$1
REPO=$2
BUILDKITE_COMMIT=$3
IMAGE="$REGISTRY/$REPO:$BUILDKITE_COMMIT-hpu"
# authenticate with AWS ECR
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY" || true
# skip build if image already exists
if [[ -z $(docker manifest inspect "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-hpu) ]]; then
echo "Image not found, proceeding with build..."
else
if docker manifest inspect "$IMAGE" >/dev/null 2>&1; then
echo "Image found"
exit 0
else
echo "Image not found, proceeding with build..."
# build
docker build \
--file tests/pytorch_ci_hud_benchmark/Dockerfile.hpu \
--build-arg max_jobs=16 \
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
--tag "$IMAGE" \
--progress plain \
https://github.com/vllm-project/vllm-gaudi.git
# push
docker push "$IMAGE"
fi
# build
docker build \
--file tests/pytorch_ci_hud_benchmark/Dockerfile.hpu \
--build-arg max_jobs=16 \
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
--tag "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-hpu \
--progress plain \
https://github.com/vllm-project/vllm-gaudi.git
# push
docker push "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-hpu
.buildkite/scripts/annotate-image-build.sh "$IMAGE"
@@ -40,6 +40,7 @@ docker buildx ls
echo "--- :mag: Checking if image already exists"
if docker manifest inspect "$IMAGE_TAG" >/dev/null 2>&1; then
echo "Image found: $IMAGE_TAG — skipping build"
.buildkite/scripts/annotate-image-build.sh "$IMAGE_TAG"
exit 0
fi
echo "Image not found, proceeding with build..."
@@ -66,3 +67,5 @@ docker buildx build --file docker/Dockerfile \
--progress plain .
echo "--- :white_check_mark: Torch nightly image build complete: $IMAGE_TAG"
.buildkite/scripts/annotate-image-build.sh "$IMAGE_TAG"
+14 -14
View File
@@ -9,26 +9,26 @@ fi
REGISTRY=$1
REPO=$2
BUILDKITE_COMMIT=$3
IMAGE="$REGISTRY/$REPO:$BUILDKITE_COMMIT-xpu"
# authenticate with AWS ECR
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY" || true
aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin 936637512419.dkr.ecr.us-east-1.amazonaws.com || true
# skip build if image already exists
if ! docker manifest inspect "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-xpu &> /dev/null; then
echo "Image not found, proceeding with build..."
else
if docker manifest inspect "$IMAGE" &> /dev/null; then
echo "Image found"
exit 0
else
echo "Image not found, proceeding with build..."
# build
docker build \
--file docker/Dockerfile.xpu \
--build-arg max_jobs=16 \
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
--tag "$IMAGE" \
--progress plain .
# push
docker push "$IMAGE"
fi
# build
docker build \
--file docker/Dockerfile.xpu \
--build-arg max_jobs=16 \
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
--tag "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-xpu \
--progress plain .
# push
docker push "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-xpu
.buildkite/scripts/annotate-image-build.sh "$IMAGE"
+36
View File
@@ -0,0 +1,36 @@
#!/bin/bash
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
#
# Append the Docker image tag(s) an image-build step pushed to a Buildkite
# annotation, so the built image tags show up on the build page instead of
# being buried in the job logs.
#
# Usage: annotate-image-build.sh <image_tag> [<image_tag> ...]
set -euo pipefail
# buildkite-agent only exists on Buildkite agents; no-op elsewhere so the
# image build scripts stay runnable locally.
if ! command -v buildkite-agent >/dev/null 2>&1; then
echo "buildkite-agent not found; skipping image tag annotation"
exit 0
fi
label="${BUILDKITE_LABEL:-Image build}"
content=""
for image in "$@"; do
[[ -n "$image" ]] || continue
content+="- **${label}**: \`${image}\`"$'\n'
done
if [[ -z "$content" ]]; then
echo "No image tags provided; nothing to annotate"
exit 0
fi
# Best-effort: a flaky annotation must never fail an otherwise successful
# (and expensive) image build.
if ! printf '%s' "$content" | \
buildkite-agent annotate --append --style 'info' --context 'docker-images'; then
echo "warning: failed to annotate build with image tags"
fi