[build] fix cu130 related release pipeline steps and publish as nightly image (#32522)
Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
(cherry picked from commit 965765aef9)
This commit is contained in:
Shengqi Chen
committed by
Kevin H. Luu
Kevin H. Luu
parent
b17039bccc
commit
d68209402d
@@ -141,7 +141,7 @@ steps:
|
||||
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=13.0.2 --build-arg FLASHINFER_AOT_COMPILE=true --build-arg INSTALL_KV_CONNECTORS=true --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.2-devel-ubuntu22.04 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130 --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=13.0.1 --build-arg INSTALL_KV_CONNECTORS=true --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.1-devel-ubuntu22.04 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130 --target vllm-openai --progress plain -f docker/Dockerfile ."
|
||||
- "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130"
|
||||
# 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)-cu130 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-cu130"
|
||||
@@ -154,7 +154,8 @@ steps:
|
||||
queue: arm64_cpu_queue_postmerge
|
||||
commands:
|
||||
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
|
||||
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=13.0.2 --build-arg FLASHINFER_AOT_COMPILE=true --build-arg torch_cuda_arch_list='8.7 8.9 9.0 10.0+PTX 12.0' --build-arg INSTALL_KV_CONNECTORS=true --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.2-devel-ubuntu22.04 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130 --target vllm-openai --progress plain -f docker/Dockerfile ."
|
||||
# compute capability 12.0 for RTX-50 series / RTX PRO 6000 Blackwell, 12.1 for DGX Spark
|
||||
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=13.0.1 --build-arg torch_cuda_arch_list='8.7 8.9 9.0 10.0+PTX 12.0 12.1' --build-arg INSTALL_KV_CONNECTORS=true --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.1-devel-ubuntu22.04 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130 --target vllm-openai --progress plain -f docker/Dockerfile ."
|
||||
- "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130"
|
||||
|
||||
- label: "Create multi-arch manifest - CUDA 13.0"
|
||||
@@ -243,7 +244,6 @@ steps:
|
||||
# Build vLLM ROCm image using the base
|
||||
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg BASE_IMAGE=rocm/vllm-dev:base-$BUILDKITE_COMMIT --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-rocm --target vllm-openai --progress plain -f docker/Dockerfile.rocm ."
|
||||
- "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-rocm"
|
||||
|
||||
|
||||
- label: "Build and publish nightly multi-arch image to DockerHub"
|
||||
depends_on:
|
||||
@@ -252,17 +252,7 @@ steps:
|
||||
agents:
|
||||
queue: small_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 pull public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64"
|
||||
- "docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-aarch64"
|
||||
- "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64 vllm/vllm-openai:nightly-x86_64"
|
||||
- "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-aarch64 vllm/vllm-openai:nightly-aarch64"
|
||||
- "docker push vllm/vllm-openai:nightly-x86_64"
|
||||
- "docker push vllm/vllm-openai:nightly-aarch64"
|
||||
- "docker manifest create vllm/vllm-openai:nightly vllm/vllm-openai:nightly-x86_64 vllm/vllm-openai:nightly-aarch64 --amend"
|
||||
- "docker manifest create vllm/vllm-openai:nightly-$BUILDKITE_COMMIT vllm/vllm-openai:nightly-x86_64 vllm/vllm-openai:nightly-aarch64 --amend"
|
||||
- "docker manifest push vllm/vllm-openai:nightly"
|
||||
- "docker manifest push vllm/vllm-openai:nightly-$BUILDKITE_COMMIT"
|
||||
- "bash .buildkite/scripts/push-nightly-builds.sh"
|
||||
# Clean up old nightly builds (keep only last 14)
|
||||
- "bash .buildkite/scripts/cleanup-nightly-builds.sh"
|
||||
plugins:
|
||||
@@ -273,6 +263,25 @@ steps:
|
||||
DOCKER_BUILDKIT: "1"
|
||||
DOCKERHUB_USERNAME: "vllmbot"
|
||||
|
||||
- label: "Build and publish nightly multi-arch image to DockerHub - CUDA 13.0"
|
||||
depends_on:
|
||||
- create-multi-arch-manifest-cuda-13-0
|
||||
if: build.env("NIGHTLY") == "1"
|
||||
agents:
|
||||
queue: small_cpu_queue_postmerge
|
||||
commands:
|
||||
- "bash .buildkite/scripts/push-nightly-builds.sh cu130"
|
||||
# Clean up old nightly builds (keep only last 14)
|
||||
- "bash .buildkite/scripts/cleanup-nightly-builds.sh cu130-nightly-"
|
||||
plugins:
|
||||
- docker-login#v3.0.0:
|
||||
username: vllmbot
|
||||
password-env: DOCKERHUB_TOKEN
|
||||
env:
|
||||
DOCKER_BUILDKIT: "1"
|
||||
DOCKERHUB_USERNAME: "vllmbot"
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# ROCm Release Pipeline (x86_64 only)
|
||||
# =============================================================================
|
||||
|
||||
@@ -3,7 +3,14 @@
|
||||
set -ex
|
||||
|
||||
# Clean up old nightly builds from DockerHub, keeping only the last 14 builds
|
||||
# This script uses DockerHub API to list and delete old tags with "nightly-" prefix
|
||||
# This script uses DockerHub API to list and delete old tags with specified prefix
|
||||
# Usage: cleanup-nightly-builds.sh [TAG_PREFIX]
|
||||
# Example: cleanup-nightly-builds.sh "nightly-" or cleanup-nightly-builds.sh "cu130-nightly-"
|
||||
|
||||
# Get tag prefix from argument, default to "nightly-" if not provided
|
||||
TAG_PREFIX="${1:-nightly-}"
|
||||
|
||||
echo "Cleaning up tags with prefix: $TAG_PREFIX"
|
||||
|
||||
# DockerHub API endpoint for vllm/vllm-openai repository
|
||||
REPO_API_URL="https://hub.docker.com/v2/repositories/vllm/vllm-openai/tags"
|
||||
@@ -45,7 +52,7 @@ get_all_tags() {
|
||||
set -x
|
||||
|
||||
# Get both last_updated timestamp and tag name, separated by |
|
||||
local tags=$(echo "$response" | jq -r '.results[] | select(.name | startswith("nightly-")) | "\(.last_updated)|\(.name)"')
|
||||
local tags=$(echo "$response" | jq -r --arg prefix "$TAG_PREFIX" '.results[] | select(.name | startswith($prefix)) | "\(.last_updated)|\(.name)"')
|
||||
|
||||
if [ -z "$tags" ]; then
|
||||
break
|
||||
|
||||
36
.buildkite/scripts/push-nightly-builds.sh
Executable file
36
.buildkite/scripts/push-nightly-builds.sh
Executable file
@@ -0,0 +1,36 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -ex
|
||||
|
||||
# Get tag variant from argument, default to empty if not provided, should be something like "cu130".
|
||||
# Due to limits in cleanup script, we must move variants to use separate tags like "cu130-nightly",
|
||||
# otherwise they will be cleaned up together with the main "nightly" tags.
|
||||
|
||||
TAG_VARIANT="$1"
|
||||
if [ -n "$TAG_VARIANT" ]; then
|
||||
ORIG_TAG_SUFFIX="-$TAG_VARIANT"
|
||||
TAG_NAME="$TAG_VARIANT-nightly"
|
||||
else
|
||||
ORIG_TAG_SUFFIX=""
|
||||
TAG_NAME="nightly"
|
||||
fi
|
||||
|
||||
ORIG_TAG_NAME="$BUILDKITE_COMMIT"
|
||||
|
||||
echo "Pushing original tag $ORIG_TAG_NAME$ORIG_TAG_SUFFIX to new nightly tag name: $TAG_NAME"
|
||||
|
||||
# pull original arch-dependent images from AWS ECR Public
|
||||
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7
|
||||
docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:$ORIG_TAG_NAME-x86_64$ORIG_TAG_SUFFIX
|
||||
docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:$ORIG_TAG_NAME-aarch64$ORIG_TAG_SUFFIX
|
||||
# tag arch-dependent images
|
||||
docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$ORIG_TAG_NAME-x86_64$ORIG_TAG_SUFFIX vllm/vllm-openai:$TAG_NAME-x86_64
|
||||
docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$ORIG_TAG_NAME-aarch64$ORIG_TAG_SUFFIX vllm/vllm-openai:$TAG_NAME-aarch64
|
||||
# push arch-dependent images to DockerHub
|
||||
docker push vllm/vllm-openai:$TAG_NAME-x86_64
|
||||
docker push vllm/vllm-openai:$TAG_NAME-aarch64
|
||||
# push arch-independent manifest to DockerHub
|
||||
docker manifest create vllm/vllm-openai:$TAG_NAME vllm/vllm-openai:$TAG_NAME-x86_64 vllm/vllm-openai:$TAG_NAME-aarch64 --amend
|
||||
docker manifest create vllm/vllm-openai:$TAG_NAME-$BUILDKITE_COMMIT vllm/vllm-openai:$TAG_NAME-x86_64 vllm/vllm-openai:$TAG_NAME-aarch64 --amend
|
||||
docker manifest push vllm/vllm-openai:$TAG_NAME
|
||||
docker manifest push vllm/vllm-openai:$TAG_NAME-$BUILDKITE_COMMIT
|
||||
Reference in New Issue
Block a user