Cherry pick [ROCm] [CI] [Release] Rocm wheel pipeline with sccache #32264

Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
This commit is contained in:
TJian
2026-01-16 02:56:18 +08:00
committed by Kevin H. Luu
parent 0e31fc7996
commit c2a37a3cf8
10 changed files with 1343 additions and 25 deletions

View File

@@ -214,3 +214,365 @@ steps:
env:
DOCKER_BUILDKIT: "1"
DOCKERHUB_USERNAME: "vllmbot"
# =============================================================================
# ROCm Release Pipeline (x86_64 only)
# =============================================================================
#
# vLLM version is determined by the Buildkite checkout (like CUDA pipeline).
# To build a specific version, trigger the build from that branch/tag.
#
# Environment variables for ROCm builds (set via Buildkite UI or schedule):
# ROCM_PYTHON_VERSION: Python version (default: 3.12)
# PYTORCH_ROCM_ARCH: GPU architectures (default: gfx90a;gfx942;gfx950;gfx1100;gfx1101;gfx1200;gfx1201;gfx1150;gfx1151)
# ROCM_UPLOAD_WHEELS: Upload to S3 (default: false for nightly, true for releases)
# ROCM_FORCE_REBUILD: Force rebuild base wheels, ignore S3 cache (default: false)
#
# Note: ROCm version is determined by BASE_IMAGE in docker/Dockerfile.rocm_base
# (currently rocm/dev-ubuntu-22.04:7.1-complete)
#
# =============================================================================
# ROCm Input Step - Collect build configuration (manual trigger only)
- input: "ROCm Wheel Release Build Configuration"
key: input-rocm-config
depends_on: ~
if: build.source == "ui"
fields:
- text: "Python Version"
key: "rocm-python-version"
default: "3.12"
hint: "Python version (e.g., 3.12)"
- text: "GPU Architectures"
key: "rocm-pytorch-rocm-arch"
default: "gfx90a;gfx942;gfx950;gfx1100;gfx1101;gfx1200;gfx1201;gfx1150;gfx1151"
hint: "Semicolon-separated GPU architectures"
- select: "Upload Wheels to S3"
key: "rocm-upload-wheels"
default: "true"
options:
- label: "No - Build only (nightly/dev)"
value: "false"
- label: "Yes - Upload to S3 (release)"
value: "true"
- select: "Force Rebuild Base Wheels"
key: "rocm-force-rebuild"
default: "false"
hint: "Ignore S3 cache and rebuild base wheels from scratch"
options:
- label: "No - Use cached wheels if available"
value: "false"
- label: "Yes - Rebuild even if cache exists"
value: "true"
# ROCm Job 1: Build ROCm Base Wheels (with S3 caching)
- label: ":rocm: Build ROCm Base Wheels"
id: build-rocm-base-wheels
depends_on:
- step: input-rocm-config
allow_failure: true # Allow failure so non-UI builds can proceed (input step is skipped)
agents:
queue: cpu_queue_postmerge
commands:
# Set configuration and check cache
- |
set -euo pipefail
# Get values from meta-data (set by input step) or use defaults
PYTHON_VERSION="$$(buildkite-agent meta-data get rocm-python-version 2>/dev/null || echo '')"
export PYTHON_VERSION="$${PYTHON_VERSION:-3.12}"
PYTORCH_ROCM_ARCH="$$(buildkite-agent meta-data get rocm-pytorch-rocm-arch 2>/dev/null || echo '')"
export PYTORCH_ROCM_ARCH="$${PYTORCH_ROCM_ARCH:-gfx90a;gfx942;gfx950;gfx1100;gfx1101;gfx1200;gfx1201;gfx1150;gfx1151}"
# Check for force rebuild flag
ROCM_FORCE_REBUILD="$${ROCM_FORCE_REBUILD:-}"
if [ -z "$${ROCM_FORCE_REBUILD}" ]; then
ROCM_FORCE_REBUILD="$$(buildkite-agent meta-data get rocm-force-rebuild 2>/dev/null || echo '')"
fi
echo "========================================"
echo "ROCm Base Wheels Build Configuration"
echo "========================================"
echo " PYTHON_VERSION: $${PYTHON_VERSION}"
echo " PYTORCH_ROCM_ARCH: $${PYTORCH_ROCM_ARCH}"
echo " ROCM_FORCE_REBUILD: $${ROCM_FORCE_REBUILD:-false}"
echo "========================================"
# Save resolved config for later jobs
buildkite-agent meta-data set "rocm-python-version" "$${PYTHON_VERSION}"
buildkite-agent meta-data set "rocm-pytorch-rocm-arch" "$${PYTORCH_ROCM_ARCH}"
# Check S3 cache for pre-built wheels
CACHE_KEY=$$(.buildkite/scripts/cache-rocm-base-wheels.sh key)
CACHE_PATH=$$(.buildkite/scripts/cache-rocm-base-wheels.sh path)
echo ""
echo "Cache key: $${CACHE_KEY}"
echo "Cache path: $${CACHE_PATH}"
# Save cache key for downstream jobs
buildkite-agent meta-data set "rocm-cache-key" "$${CACHE_KEY}"
CACHE_STATUS="miss"
if [ "$${ROCM_FORCE_REBUILD}" != "true" ]; then
CACHE_STATUS=$$(.buildkite/scripts/cache-rocm-base-wheels.sh check)
else
echo "Force rebuild requested, skipping cache check"
fi
if [ "$${CACHE_STATUS}" = "hit" ]; then
echo ""
echo "CACHE HIT! Downloading pre-built wheels..."
echo ""
.buildkite/scripts/cache-rocm-base-wheels.sh download
# Set the S3 path for the cached Docker image (for Job 2 to download)
S3_ARTIFACT_PATH="s3://$${S3_BUCKET}/rocm/cache/$${CACHE_KEY}"
buildkite-agent meta-data set "rocm-docker-image-s3-path" "$${S3_ARTIFACT_PATH}/rocm-base-image.tar.gz"
# Mark that we used cache (for Docker image handling)
buildkite-agent meta-data set "rocm-used-cache" "true"
echo ""
echo "Cache download complete. Skipping Docker build."
echo "Docker image will be downloaded from: $${S3_ARTIFACT_PATH}/rocm-base-image.tar.gz"
else
echo ""
echo "CACHE MISS. Building from scratch..."
echo ""
# Build full base image (for later vLLM build)
DOCKER_BUILDKIT=1 docker buildx build \
--file docker/Dockerfile.rocm_base \
--tag rocm/vllm-dev:base-$${BUILDKITE_BUILD_NUMBER} \
--build-arg PYTORCH_ROCM_ARCH="$${PYTORCH_ROCM_ARCH}" \
--build-arg PYTHON_VERSION="$${PYTHON_VERSION}" \
--build-arg USE_SCCACHE=1 \
--build-arg SCCACHE_BUCKET_NAME=vllm-build-sccache \
--build-arg SCCACHE_REGION_NAME=us-west-2 \
--build-arg SCCACHE_S3_NO_CREDENTIALS=0 \
--load \
.
# Build debs_wheel_release stage for wheel extraction
DOCKER_BUILDKIT=1 docker buildx build \
--file docker/Dockerfile.rocm_base \
--tag rocm-base-debs:$${BUILDKITE_BUILD_NUMBER} \
--target debs_wheel_release \
--build-arg PYTORCH_ROCM_ARCH="$${PYTORCH_ROCM_ARCH}" \
--build-arg PYTHON_VERSION="$${PYTHON_VERSION}" \
--build-arg USE_SCCACHE=1 \
--build-arg SCCACHE_BUCKET_NAME=vllm-build-sccache \
--build-arg SCCACHE_REGION_NAME=us-west-2 \
--build-arg SCCACHE_S3_NO_CREDENTIALS=0 \
--load \
.
# Extract wheels from Docker image
mkdir -p artifacts/rocm-base-wheels
container_id=$$(docker create rocm-base-debs:$${BUILDKITE_BUILD_NUMBER})
docker cp $${container_id}:/app/debs/. artifacts/rocm-base-wheels/
docker rm $${container_id}
echo "Extracted base wheels:"
ls -lh artifacts/rocm-base-wheels/
# Upload wheels to S3 cache for future builds
echo ""
echo "Uploading wheels to S3 cache..."
.buildkite/scripts/cache-rocm-base-wheels.sh upload
# Export base Docker image for reuse in vLLM build
mkdir -p artifacts/rocm-docker-image
docker save rocm/vllm-dev:base-$${BUILDKITE_BUILD_NUMBER} | gzip > artifacts/rocm-docker-image/rocm-base-image.tar.gz
echo "Docker image size:"
ls -lh artifacts/rocm-docker-image/
# Upload large Docker image to S3 (also cached by cache key)
S3_ARTIFACT_PATH="s3://$${S3_BUCKET}/rocm/cache/$${CACHE_KEY}"
echo "Uploading Docker image to $${S3_ARTIFACT_PATH}/"
aws s3 cp artifacts/rocm-docker-image/rocm-base-image.tar.gz "$${S3_ARTIFACT_PATH}/rocm-base-image.tar.gz"
# Save the S3 path for downstream jobs
buildkite-agent meta-data set "rocm-docker-image-s3-path" "$${S3_ARTIFACT_PATH}/rocm-base-image.tar.gz"
# Mark that we did NOT use cache
buildkite-agent meta-data set "rocm-used-cache" "false"
echo ""
echo "Build complete. Wheels cached for future builds."
fi
artifact_paths:
- "artifacts/rocm-base-wheels/*.whl"
env:
DOCKER_BUILDKIT: "1"
S3_BUCKET: "vllm-wheels"
# ROCm Job 2: Build vLLM ROCm Wheel
- label: ":python: Build vLLM ROCm Wheel"
id: build-rocm-vllm-wheel
depends_on:
- step: build-rocm-base-wheels
allow_failure: false
agents:
queue: cpu_queue_postmerge
timeout_in_minutes: 180
commands:
# Download artifacts and prepare Docker image
- |
set -euo pipefail
# Ensure git tags are up-to-date (Buildkite's default fetch doesn't update tags)
# This fixes version detection when tags are moved/force-pushed
echo "Fetching latest tags from origin..."
git fetch --tags --force origin
# Log tag information for debugging version detection
echo "========================================"
echo "Git Tag Verification"
echo "========================================"
echo "Current HEAD: $(git rev-parse HEAD)"
echo "git describe --tags: $(git describe --tags 2>/dev/null || echo 'No tags found')"
echo ""
echo "Recent tags (pointing to commits near HEAD):"
git tag -l --sort=-creatordate | head -5
echo "setuptools_scm version detection:"
pip install -q setuptools_scm 2>/dev/null || true
python3 -c "import setuptools_scm; print(' Detected version:', setuptools_scm.get_version())" 2>/dev/null || echo " (setuptools_scm not available in this environment)"
echo "========================================"
# Download wheel artifacts from current build
echo "Downloading wheel artifacts from current build"
buildkite-agent artifact download "artifacts/rocm-base-wheels/*.whl" .
# Download Docker image from S3 (too large for Buildkite artifacts)
DOCKER_IMAGE_S3_PATH="$$(buildkite-agent meta-data get rocm-docker-image-s3-path 2>/dev/null || echo '')"
if [ -z "$${DOCKER_IMAGE_S3_PATH}" ]; then
echo "ERROR: rocm-docker-image-s3-path metadata not found"
echo "This should have been set by the build-rocm-base-wheels job"
exit 1
fi
echo "Downloading Docker image from $${DOCKER_IMAGE_S3_PATH}"
mkdir -p artifacts/rocm-docker-image
aws s3 cp "$${DOCKER_IMAGE_S3_PATH}" artifacts/rocm-docker-image/rocm-base-image.tar.gz
# Load base Docker image and capture the tag
echo "Loading base Docker image..."
LOAD_OUTPUT=$$(gunzip -c artifacts/rocm-docker-image/rocm-base-image.tar.gz | docker load)
echo "$${LOAD_OUTPUT}"
# Extract the actual loaded image tag from "Loaded image: <tag>" output
# This avoids picking up stale images (like rocm/vllm-dev:nightly) already on the agent
BASE_IMAGE_TAG=$$(echo "$${LOAD_OUTPUT}" | grep "Loaded image:" | sed 's/Loaded image: //')
if [ -z "$${BASE_IMAGE_TAG}" ]; then
echo "ERROR: Failed to extract image tag from docker load output"
echo "Load output was: $${LOAD_OUTPUT}"
exit 1
fi
echo "Loaded base image: $${BASE_IMAGE_TAG}"
# Prepare base wheels for Docker build context
mkdir -p docker/context/base-wheels
touch docker/context/base-wheels/.keep
cp artifacts/rocm-base-wheels/*.whl docker/context/base-wheels/
echo "Base wheels for vLLM build:"
ls -lh docker/context/base-wheels/
# Get GPU architectures from meta-data
PYTORCH_ROCM_ARCH="$$(buildkite-agent meta-data get rocm-pytorch-rocm-arch 2>/dev/null || echo '')"
PYTORCH_ROCM_ARCH="$${PYTORCH_ROCM_ARCH:-gfx90a;gfx942;gfx950;gfx1100;gfx1101;gfx1200;gfx1201;gfx1150;gfx1151}"
echo "========================================"
echo "Building vLLM wheel with:"
echo " BUILDKITE_COMMIT: $${BUILDKITE_COMMIT}"
echo " BUILDKITE_BRANCH: $${BUILDKITE_BRANCH}"
echo " PYTORCH_ROCM_ARCH: $${PYTORCH_ROCM_ARCH}"
echo " BASE_IMAGE: $${BASE_IMAGE_TAG}"
echo "========================================"
# Build vLLM wheel using local checkout (REMOTE_VLLM=0)
DOCKER_BUILDKIT=1 docker build \
--file docker/Dockerfile.rocm \
--target export_vllm_wheel_release \
--output type=local,dest=rocm-dist \
--build-arg BASE_IMAGE="$${BASE_IMAGE_TAG}" \
--build-arg ARG_PYTORCH_ROCM_ARCH="$${PYTORCH_ROCM_ARCH}" \
--build-arg REMOTE_VLLM=0 \
--build-arg GIT_REPO_CHECK=1 \
--build-arg USE_SCCACHE=1 \
--build-arg SCCACHE_BUCKET_NAME=vllm-build-sccache \
--build-arg SCCACHE_REGION_NAME=us-west-2 \
--build-arg SCCACHE_S3_NO_CREDENTIALS=0 \
.
echo "Built vLLM wheel:"
ls -lh rocm-dist/*.whl
# Copy wheel to artifacts directory
mkdir -p artifacts/rocm-vllm-wheel
cp rocm-dist/*.whl artifacts/rocm-vllm-wheel/
echo "Final vLLM wheel:"
ls -lh artifacts/rocm-vllm-wheel/
artifact_paths:
- "artifacts/rocm-vllm-wheel/*.whl"
env:
DOCKER_BUILDKIT: "1"
S3_BUCKET: "vllm-wheels"
# ROCm Job 3: Upload Wheels to S3
- label: ":s3: Upload ROCm Wheels to S3"
id: upload-rocm-wheels
depends_on:
- step: build-rocm-vllm-wheel
allow_failure: false
agents:
queue: cpu_queue_postmerge
timeout_in_minutes: 60
commands:
# Download all wheel artifacts and run upload
- |
set -euo pipefail
# Check if upload is enabled (from env var, meta-data, or release branch)
ROCM_UPLOAD_WHEELS="$${ROCM_UPLOAD_WHEELS:-}"
if [ -z "$${ROCM_UPLOAD_WHEELS}" ]; then
# Try to get from meta-data (input form)
ROCM_UPLOAD_WHEELS="$$(buildkite-agent meta-data get rocm-upload-wheels 2>/dev/null || echo '')"
fi
echo "========================================"
echo "Upload check:"
echo " ROCM_UPLOAD_WHEELS: $${ROCM_UPLOAD_WHEELS}"
echo " BUILDKITE_BRANCH: $${BUILDKITE_BRANCH}"
echo "========================================"
# Skip upload if not enabled
if [ "$${ROCM_UPLOAD_WHEELS}" != "true" ]; then
echo "Skipping S3 upload (ROCM_UPLOAD_WHEELS != true, NIGHTLY != 1, not a release branch)"
echo "To enable upload, set 'Upload Wheels to S3' to 'Yes' in the build configuration"
exit 0
fi
echo "Upload enabled, proceeding..."
# Download artifacts from current build
echo "Downloading artifacts from current build"
buildkite-agent artifact download "artifacts/rocm-base-wheels/*.whl" .
buildkite-agent artifact download "artifacts/rocm-vllm-wheel/*.whl" .
# Run upload script
bash .buildkite/scripts/upload-rocm-wheels.sh
env:
DOCKER_BUILDKIT: "1"
S3_BUCKET: "vllm-wheels"
# ROCm Job 4: Annotate ROCm Wheel Release
- label: ":memo: Annotate ROCm wheel release"
id: annotate-rocm-release
depends_on:
- step: upload-rocm-wheels
allow_failure: true
agents:
queue: cpu_queue_postmerge
commands:
- "bash .buildkite/scripts/annotate-rocm-release.sh"
env:
S3_BUCKET: "vllm-wheels"