Add vLLM v0.18.1 source tree with KV transfer abort fix
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
255
third_party/vllm/.buildkite/image_build/image_build.sh
vendored
Executable file
255
third_party/vllm/.buildkite/image_build/image_build.sh
vendored
Executable file
@@ -0,0 +1,255 @@
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
|
||||
# replace invalid characters in Docker image tags and truncate to 128 chars
|
||||
clean_docker_tag() {
|
||||
local input="$1"
|
||||
echo "$input" | sed 's/[^a-zA-Z0-9._-]/_/g' | cut -c1-128
|
||||
}
|
||||
|
||||
print_usage_and_exit() {
|
||||
echo "Usage: $0 <registry> <repo> <commit> <branch> <image_tag> [<image_tag_latest>]"
|
||||
exit 1
|
||||
}
|
||||
|
||||
print_instance_info() {
|
||||
echo ""
|
||||
echo "=== Debug: Instance Information ==="
|
||||
# Get IMDSv2 token
|
||||
if TOKEN=$(curl -s -X PUT "http://169.254.169.254/latest/api/token" \
|
||||
-H "X-aws-ec2-metadata-token-ttl-seconds: 21600" 2>/dev/null); then
|
||||
AMI_ID=$(curl -s -H "X-aws-ec2-metadata-token: $TOKEN" \
|
||||
http://169.254.169.254/latest/meta-data/ami-id 2>/dev/null || echo "unknown")
|
||||
INSTANCE_TYPE=$(curl -s -H "X-aws-ec2-metadata-token: $TOKEN" \
|
||||
http://169.254.169.254/latest/meta-data/instance-type 2>/dev/null || echo "unknown")
|
||||
INSTANCE_ID=$(curl -s -H "X-aws-ec2-metadata-token: $TOKEN" \
|
||||
http://169.254.169.254/latest/meta-data/instance-id 2>/dev/null || echo "unknown")
|
||||
AZ=$(curl -s -H "X-aws-ec2-metadata-token: $TOKEN" \
|
||||
http://169.254.169.254/latest/meta-data/placement/availability-zone 2>/dev/null || echo "unknown")
|
||||
echo "AMI ID: ${AMI_ID}"
|
||||
echo "Instance Type: ${INSTANCE_TYPE}"
|
||||
echo "Instance ID: ${INSTANCE_ID}"
|
||||
echo "AZ: ${AZ}"
|
||||
else
|
||||
echo "Not running on EC2 or IMDS not available"
|
||||
fi
|
||||
# Check for warm cache AMI (marker file baked into custom AMI)
|
||||
if [[ -f /etc/vllm-ami-info ]]; then
|
||||
echo "Cache: warm (custom vLLM AMI)"
|
||||
cat /etc/vllm-ami-info
|
||||
else
|
||||
echo "Cache: cold (standard AMI)"
|
||||
fi
|
||||
echo "==================================="
|
||||
echo ""
|
||||
}
|
||||
|
||||
setup_buildx_builder() {
|
||||
echo "--- :buildkite: Setting up buildx builder"
|
||||
if [[ -S "${BUILDKIT_SOCKET}" ]]; then
|
||||
# Custom AMI with standalone buildkitd - use remote driver for warm cache
|
||||
echo "✅ Found local buildkitd socket at ${BUILDKIT_SOCKET}"
|
||||
echo "Using remote driver to connect to buildkitd (warm cache available)"
|
||||
if docker buildx inspect baked-vllm-builder >/dev/null 2>&1; then
|
||||
echo "Using existing baked-vllm-builder"
|
||||
docker buildx use baked-vllm-builder
|
||||
else
|
||||
echo "Creating baked-vllm-builder with remote driver"
|
||||
docker buildx create \
|
||||
--name baked-vllm-builder \
|
||||
--driver remote \
|
||||
--use \
|
||||
"unix://${BUILDKIT_SOCKET}"
|
||||
fi
|
||||
docker buildx inspect --bootstrap
|
||||
elif docker buildx inspect "${BUILDER_NAME}" >/dev/null 2>&1; then
|
||||
# Existing builder available
|
||||
echo "Using existing builder: ${BUILDER_NAME}"
|
||||
docker buildx use "${BUILDER_NAME}"
|
||||
docker buildx inspect --bootstrap
|
||||
else
|
||||
# No local buildkitd, no existing builder - create new docker-container builder
|
||||
echo "No local buildkitd found, using docker-container driver"
|
||||
docker buildx create --name "${BUILDER_NAME}" --driver docker-container --use
|
||||
docker buildx inspect --bootstrap
|
||||
fi
|
||||
|
||||
# builder info
|
||||
echo "Active builder:"
|
||||
docker buildx ls | grep -E '^\*|^NAME' || docker buildx ls
|
||||
}
|
||||
|
||||
check_and_skip_if_image_exists() {
|
||||
if [[ -n "${IMAGE_TAG:-}" ]]; then
|
||||
echo "--- :mag: Checking if image exists"
|
||||
if docker manifest inspect "${IMAGE_TAG}" >/dev/null 2>&1; then
|
||||
echo "Image already exists: ${IMAGE_TAG}"
|
||||
echo "Skipping build"
|
||||
exit 0
|
||||
fi
|
||||
echo "Image not found, proceeding with build"
|
||||
fi
|
||||
}
|
||||
|
||||
ecr_login() {
|
||||
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY"
|
||||
aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin 936637512419.dkr.ecr.us-east-1.amazonaws.com
|
||||
}
|
||||
|
||||
prepare_cache_tags() {
|
||||
# resolve and set: CACHE_TO, CACHE_FROM, CACHE_FROM_BASE_BRANCH, CACHE_FROM_MAIN
|
||||
TEST_CACHE_ECR="936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-test-cache"
|
||||
MAIN_CACHE_ECR="936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-postmerge-cache"
|
||||
|
||||
if [[ "$BUILDKITE_PULL_REQUEST" == "false" ]]; then
|
||||
if [[ "$BUILDKITE_BRANCH" == "main" ]]; then
|
||||
cache="${MAIN_CACHE_ECR}:latest"
|
||||
else
|
||||
clean_branch=$(clean_docker_tag "$BUILDKITE_BRANCH")
|
||||
cache="${TEST_CACHE_ECR}:${clean_branch}"
|
||||
fi
|
||||
CACHE_TO="$cache"
|
||||
CACHE_FROM="$cache"
|
||||
CACHE_FROM_BASE_BRANCH="$cache"
|
||||
else
|
||||
CACHE_TO="${TEST_CACHE_ECR}:pr-${BUILDKITE_PULL_REQUEST}"
|
||||
CACHE_FROM="${TEST_CACHE_ECR}:pr-${BUILDKITE_PULL_REQUEST}"
|
||||
if [[ "$BUILDKITE_PULL_REQUEST_BASE_BRANCH" == "main" ]]; then
|
||||
CACHE_FROM_BASE_BRANCH="${MAIN_CACHE_ECR}:latest"
|
||||
else
|
||||
clean_base=$(clean_docker_tag "$BUILDKITE_PULL_REQUEST_BASE_BRANCH")
|
||||
CACHE_FROM_BASE_BRANCH="${TEST_CACHE_ECR}:${clean_base}"
|
||||
fi
|
||||
fi
|
||||
|
||||
CACHE_FROM_MAIN="${MAIN_CACHE_ECR}:latest"
|
||||
export CACHE_TO CACHE_FROM CACHE_FROM_BASE_BRANCH CACHE_FROM_MAIN
|
||||
}
|
||||
|
||||
resolve_parent_commit() {
|
||||
if [[ -z "${PARENT_COMMIT:-}" ]]; then
|
||||
PARENT_COMMIT=$(git rev-parse HEAD~1 2>/dev/null || echo "")
|
||||
if [[ -n "${PARENT_COMMIT}" ]]; then
|
||||
echo "Computed parent commit for cache fallback: ${PARENT_COMMIT}"
|
||||
export PARENT_COMMIT
|
||||
else
|
||||
echo "Could not determine parent commit (may be first commit in repo)"
|
||||
fi
|
||||
else
|
||||
echo "Using provided PARENT_COMMIT: ${PARENT_COMMIT}"
|
||||
fi
|
||||
}
|
||||
|
||||
print_bake_config() {
|
||||
echo "--- :page_facing_up: Resolved bake configuration"
|
||||
# Write to a temp directory to avoid polluting the repo root (which is the
|
||||
# Docker build context). Files left in the repo root get COPY'd into the
|
||||
# image and can cause duplicate artifact uploads from downstream steps.
|
||||
local bake_tmp
|
||||
bake_tmp="$(mktemp -d)"
|
||||
BAKE_CONFIG_FILE="${bake_tmp}/bake-config-build-${BUILDKITE_BUILD_NUMBER:-local}.json"
|
||||
docker buildx bake -f "${VLLM_BAKE_FILE_PATH}" -f "${CI_HCL_PATH}" --print "${TARGET}" | tee "${BAKE_CONFIG_FILE}" || true
|
||||
echo "Saved bake config to ${BAKE_CONFIG_FILE}"
|
||||
echo "--- :arrow_down: Uploading bake config to Buildkite"
|
||||
(cd "$(dirname "${BAKE_CONFIG_FILE}")" && buildkite-agent artifact upload "$(basename "${BAKE_CONFIG_FILE}")")
|
||||
}
|
||||
|
||||
#################################
|
||||
# Main Script #
|
||||
#################################
|
||||
print_instance_info
|
||||
|
||||
if [[ $# -lt 5 ]]; then
|
||||
print_usage_and_exit
|
||||
fi
|
||||
|
||||
# input args
|
||||
REGISTRY=$1
|
||||
REPO=$2
|
||||
BUILDKITE_COMMIT=$3
|
||||
BRANCH=$4
|
||||
IMAGE_TAG=$5
|
||||
IMAGE_TAG_LATEST=${6:-} # only used for main branch, optional
|
||||
|
||||
# build config
|
||||
TARGET="test-ci"
|
||||
VLLM_BAKE_FILE_PATH="${VLLM_BAKE_FILE_PATH:-docker/docker-bake.hcl}"
|
||||
BUILDER_NAME="${BUILDER_NAME:-vllm-builder}"
|
||||
CI_HCL_URL="${CI_HCL_URL:-https://raw.githubusercontent.com/vllm-project/ci-infra/main/docker/ci.hcl}"
|
||||
CI_HCL_PATH="/tmp/ci.hcl"
|
||||
BUILDKIT_SOCKET="/run/buildkit/buildkitd.sock"
|
||||
|
||||
prepare_cache_tags
|
||||
ecr_login
|
||||
|
||||
# Environment info (for docs and human readers)
|
||||
# VLLM_CI_BRANCH - ci-infra branch to use (default: main)
|
||||
# VLLM_BAKE_FILE_PATH - Path to vLLM's bake file (default: docker/docker-bake.hcl)
|
||||
# BUILDER_NAME - Name for buildx builder (default: vllm-builder)
|
||||
#
|
||||
# Build configuration (exported as environment variables for bake):
|
||||
export BUILDKITE_COMMIT
|
||||
export PARENT_COMMIT
|
||||
export IMAGE_TAG
|
||||
export IMAGE_TAG_LATEST
|
||||
export CACHE_FROM
|
||||
export CACHE_FROM_BASE_BRANCH
|
||||
export CACHE_FROM_MAIN
|
||||
export CACHE_TO
|
||||
|
||||
# print args
|
||||
echo "--- :mag: Arguments"
|
||||
echo "REGISTRY: ${REGISTRY}"
|
||||
echo "REPO: ${REPO}"
|
||||
echo "BUILDKITE_COMMIT: ${BUILDKITE_COMMIT}"
|
||||
echo "BRANCH: ${BRANCH}"
|
||||
echo "IMAGE_TAG: ${IMAGE_TAG}"
|
||||
echo "IMAGE_TAG_LATEST: ${IMAGE_TAG_LATEST}"
|
||||
|
||||
# print build configuration
|
||||
echo "--- :mag: Build configuration"
|
||||
echo "TARGET: ${TARGET}"
|
||||
echo "vLLM bake file: ${VLLM_BAKE_FILE_PATH}"
|
||||
echo "BUILDER_NAME: ${BUILDER_NAME}"
|
||||
echo "CI_HCL_URL: ${CI_HCL_URL}"
|
||||
echo "BUILDKIT_SOCKET: ${BUILDKIT_SOCKET}"
|
||||
|
||||
echo "--- :mag: Cache tags"
|
||||
echo "CACHE_TO: ${CACHE_TO}"
|
||||
echo "CACHE_FROM: ${CACHE_FROM}"
|
||||
echo "CACHE_FROM_BASE_BRANCH: ${CACHE_FROM_BASE_BRANCH}"
|
||||
echo "CACHE_FROM_MAIN: ${CACHE_FROM_MAIN}"
|
||||
|
||||
check_and_skip_if_image_exists
|
||||
|
||||
echo "--- :docker: Setting up Docker buildx bake"
|
||||
echo "Target: ${TARGET}"
|
||||
echo "vLLM bake file: ${VLLM_BAKE_FILE_PATH}"
|
||||
echo "CI HCL path: ${CI_HCL_PATH}"
|
||||
|
||||
if [[ ! -f "${VLLM_BAKE_FILE_PATH}" ]]; then
|
||||
echo "Error: vLLM bake file not found at ${VLLM_BAKE_FILE_PATH}"
|
||||
echo "Make sure you're running from the vLLM repository root"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "--- :arrow_down: Downloading ci.hcl"
|
||||
curl -sSfL -o "${CI_HCL_PATH}" "${CI_HCL_URL}"
|
||||
echo "Downloaded to ${CI_HCL_PATH}"
|
||||
|
||||
if [[ ! -f "${CI_HCL_PATH}" ]]; then
|
||||
echo "Error: ci.hcl not found at ${CI_HCL_PATH}"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
setup_buildx_builder
|
||||
|
||||
resolve_parent_commit
|
||||
export PARENT_COMMIT
|
||||
|
||||
print_bake_config
|
||||
|
||||
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"
|
||||
58
third_party/vllm/.buildkite/image_build/image_build.yaml
vendored
Normal file
58
third_party/vllm/.buildkite/image_build/image_build.yaml
vendored
Normal file
@@ -0,0 +1,58 @@
|
||||
group: Abuild
|
||||
steps:
|
||||
- label: ":docker: Build image"
|
||||
key: image-build
|
||||
depends_on: []
|
||||
timeout_in_minutes: 600
|
||||
commands:
|
||||
- if [[ "$BUILDKITE_BRANCH" == "main" ]]; then .buildkite/image_build/image_build.sh $REGISTRY $REPO $BUILDKITE_COMMIT $BRANCH $IMAGE_TAG $IMAGE_TAG_LATEST; else .buildkite/image_build/image_build.sh $REGISTRY $REPO $BUILDKITE_COMMIT $BRANCH $IMAGE_TAG; fi
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: -1 # Agent was lost
|
||||
limit: 2
|
||||
- exit_status: -10 # Agent was lost
|
||||
limit: 2
|
||||
|
||||
- label: ":docker: Build CPU image"
|
||||
key: image-build-cpu
|
||||
depends_on: []
|
||||
commands:
|
||||
- .buildkite/image_build/image_build_cpu.sh $REGISTRY $REPO $BUILDKITE_COMMIT
|
||||
env:
|
||||
DOCKER_BUILDKIT: "1"
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: -1 # Agent was lost
|
||||
limit: 2
|
||||
- exit_status: -10 # Agent was lost
|
||||
limit: 2
|
||||
|
||||
- label: ":docker: Build HPU image"
|
||||
soft_fail: true
|
||||
depends_on: []
|
||||
key: image-build-hpu
|
||||
commands:
|
||||
- .buildkite/image_build/image_build_hpu.sh $REGISTRY $REPO $BUILDKITE_COMMIT
|
||||
env:
|
||||
DOCKER_BUILDKIT: "1"
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: -1 # Agent was lost
|
||||
limit: 2
|
||||
- exit_status: -10 # Agent was lost
|
||||
limit: 2
|
||||
|
||||
- label: ":docker: Build CPU arm64 image"
|
||||
key: cpu-arm64-image-build
|
||||
depends_on: []
|
||||
optional: true
|
||||
commands:
|
||||
- .buildkite/image_build/image_build_cpu_arm64.sh $REGISTRY $REPO $BUILDKITE_COMMIT
|
||||
env:
|
||||
DOCKER_BUILDKIT: "1"
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: -1 # Agent was lost
|
||||
limit: 2
|
||||
- exit_status: -10 # Agent was lost
|
||||
limit: 2
|
||||
34
third_party/vllm/.buildkite/image_build/image_build_cpu.sh
vendored
Executable file
34
third_party/vllm/.buildkite/image_build/image_build_cpu.sh
vendored
Executable file
@@ -0,0 +1,34 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
if [[ $# -lt 3 ]]; then
|
||||
echo "Usage: $0 <registry> <repo> <commit>"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
REGISTRY=$1
|
||||
REPO=$2
|
||||
BUILDKITE_COMMIT=$3
|
||||
|
||||
# authenticate with AWS ECR
|
||||
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY"
|
||||
|
||||
# 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
|
||||
echo "Image found"
|
||||
exit 0
|
||||
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
|
||||
33
third_party/vllm/.buildkite/image_build/image_build_cpu_arm64.sh
vendored
Executable file
33
third_party/vllm/.buildkite/image_build/image_build_cpu_arm64.sh
vendored
Executable file
@@ -0,0 +1,33 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
if [[ $# -lt 3 ]]; then
|
||||
echo "Usage: $0 <registry> <repo> <commit>"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
REGISTRY=$1
|
||||
REPO=$2
|
||||
BUILDKITE_COMMIT=$3
|
||||
|
||||
# authenticate with AWS ECR
|
||||
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY"
|
||||
|
||||
# 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
|
||||
echo "Image found"
|
||||
exit 0
|
||||
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
|
||||
34
third_party/vllm/.buildkite/image_build/image_build_hpu.sh
vendored
Executable file
34
third_party/vllm/.buildkite/image_build/image_build_hpu.sh
vendored
Executable file
@@ -0,0 +1,34 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
if [[ $# -lt 3 ]]; then
|
||||
echo "Usage: $0 <registry> <repo> <commit>"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
REGISTRY=$1
|
||||
REPO=$2
|
||||
BUILDKITE_COMMIT=$3
|
||||
|
||||
# authenticate with AWS ECR
|
||||
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY"
|
||||
|
||||
# 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
|
||||
echo "Image found"
|
||||
exit 0
|
||||
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
|
||||
Reference in New Issue
Block a user