Skip to content

GitLab

Unverified Commit 7281199a authored by Kevin H. Luu's avatar Kevin H. Luu Committed by GitHub
Browse files

[release] Move agent queue to Release cluster queues (#37783) 


Signed-off-by: default avatarkhluu <khluu000@gmail.com>
parent b2dd75eb
Hide whitespace changes
Inline Side-by-side
Showing with 24 additions and 24 deletions
.buildkite/release-pipeline.yaml
View file @ 7281199a
......@@ -12,7 +12,7 @@ steps:
depends_on: ~
id: build-wheel-arm64-cuda-12-9
agents:
queue: arm64_cpu_queue_postmerge
queue: arm64_cpu_queue_release
commands:
# #NOTE: torch_cuda_arch_list is derived from upstream PyTorch build files here:
# https://github.com/pytorch/pytorch/blob/main/.ci/aarch64_linux/aarch64_ci_build.sh#L7
......@@ -27,7 +27,7 @@ steps:
depends_on: ~
id: build-wheel-arm64-cuda-13-0
agents:
queue: arm64_cpu_queue_postmerge
queue: arm64_cpu_queue_release
commands:
# #NOTE: torch_cuda_arch_list is derived from upstream PyTorch build files here:
# https://github.com/pytorch/pytorch/blob/main/.ci/aarch64_linux/aarch64_ci_build.sh#L7
......@@ -42,7 +42,7 @@ steps:
depends_on: ~
id: build-wheel-arm64-cpu
agents:
queue: arm64_cpu_queue_postmerge
queue: arm64_cpu_queue_release
commands:
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg GIT_REPO_CHECK=1 --build-arg VLLM_BUILD_ACL=ON --tag vllm-ci:build-image --target vllm-build --progress plain -f docker/Dockerfile.cpu ."
- "mkdir artifacts"
......@@ -55,7 +55,7 @@ steps:
depends_on: ~
id: build-wheel-x86-cuda-12-9
agents:
queue: cpu_queue_postmerge
queue: cpu_queue_release
commands:
- "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=12.9.1 --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
- "mkdir artifacts"
......@@ -68,7 +68,7 @@ steps:
depends_on: ~
id: build-wheel-x86-cuda-13-0
agents:
queue: cpu_queue_postmerge
queue: cpu_queue_release
commands:
- "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 BUILD_BASE_IMAGE=nvidia/cuda:13.0.1-devel-ubuntu22.04 --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
- "mkdir artifacts"
......@@ -81,7 +81,7 @@ steps:
depends_on: ~
id: build-wheel-x86-cpu
agents:
queue: cpu_queue_postmerge
queue: cpu_queue_release
commands:
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg GIT_REPO_CHECK=1 --build-arg VLLM_CPU_X86=true --tag vllm-ci:build-image --target vllm-build --progress plain -f docker/Dockerfile.cpu ."
- "mkdir artifacts"
......@@ -97,7 +97,7 @@ steps:
depends_on: ~
id: build-release-image-x86
agents:
queue: cpu_queue_postmerge
queue: cpu_queue_release
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=12.9.1 --build-arg FLASHINFER_AOT_COMPILE=true --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m) --target vllm-openai --progress plain -f docker/Dockerfile ."
......@@ -110,7 +110,7 @@ steps:
depends_on: ~
id: build-release-image-arm64
agents:
queue: arm64_cpu_queue_postmerge
queue: arm64_cpu_queue_release
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=12.9.1 --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 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m) --target vllm-openai --progress plain -f docker/Dockerfile ."
......@@ -120,7 +120,7 @@ steps:
depends_on: ~
id: build-release-image-x86-cuda-13-0
agents:
queue: cpu_queue_postmerge
queue: cpu_queue_release
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=13.0.1 --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 ."
......@@ -133,7 +133,7 @@ steps:
depends_on: ~
id: build-release-image-arm64-cuda-13-0
agents:
queue: arm64_cpu_queue_postmerge
queue: arm64_cpu_queue_release
commands:
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
# compute capability 12.0 for RTX-50 series / RTX PRO 6000 Blackwell, 12.1 for DGX Spark
......@@ -149,7 +149,7 @@ steps:
- block-cpu-release-image-build
- input-release-version
agents:
queue: cpu_queue_postmerge
queue: cpu_queue_release
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 GIT_REPO_CHECK=1 --build-arg VLLM_CPU_X86=true --tag public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:$(buildkite-agent meta-data get release-version) --tag public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:latest --progress plain --target vllm-openai -f docker/Dockerfile.cpu ."
......@@ -167,7 +167,7 @@ steps:
- block-arm64-cpu-release-image-build
- input-release-version
agents:
queue: arm64_cpu_queue_postmerge
queue: arm64_cpu_queue_release
commands:
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg GIT_REPO_CHECK=1 --tag public.ecr.aws/q9t5s3a7/vllm-arm64-cpu-release-repo:$(buildkite-agent meta-data get release-version) --tag public.ecr.aws/q9t5s3a7/vllm-arm64-cpu-release-repo:latest --progress plain --target vllm-openai -f docker/Dockerfile.cpu ."
......@@ -185,7 +185,7 @@ steps:
- build-release-image-arm64
id: create-multi-arch-manifest
agents:
queue: small_cpu_queue_postmerge
queue: small_cpu_queue_release
commands:
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
- "docker manifest create public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-aarch64 --amend"
......@@ -196,7 +196,7 @@ steps:
- create-multi-arch-manifest
id: annotate-release-workflow
agents:
queue: small_cpu_queue_postmerge
queue: small_cpu_queue_release
commands:
- "bash .buildkite/scripts/annotate-release.sh"
......@@ -206,7 +206,7 @@ steps:
- build-release-image-arm64-cuda-13-0
id: create-multi-arch-manifest-cuda-13-0
agents:
queue: small_cpu_queue_postmerge
queue: small_cpu_queue_release
commands:
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
- "docker manifest create public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-cu130 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64-cu130 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-aarch64-cu130 --amend"
......@@ -217,7 +217,7 @@ steps:
- create-multi-arch-manifest
if: build.env("NIGHTLY") == "1"
agents:
queue: small_cpu_queue_postmerge
queue: small_cpu_queue_release
commands:
- "bash .buildkite/scripts/push-nightly-builds.sh"
# Clean up old nightly builds (keep only last 14)
......@@ -235,7 +235,7 @@ steps:
- create-multi-arch-manifest-cuda-13-0
if: build.env("NIGHTLY") == "1"
agents:
queue: small_cpu_queue_postmerge
queue: small_cpu_queue_release
commands:
- "bash .buildkite/scripts/push-nightly-builds.sh cu130"
# Clean up old nightly builds (keep only last 14)
......@@ -262,7 +262,7 @@ steps:
- block-upload-release-wheels
id: upload-release-wheels
agents:
queue: small_cpu_queue_postmerge
queue: small_cpu_queue_release
commands:
- "bash .buildkite/scripts/upload-release-wheels-pypi.sh"
......@@ -323,7 +323,7 @@ steps:
- step: input-rocm-config
allow_failure: true # Allow failure so non-UI builds can proceed (input step is skipped)
agents:
queue: cpu_queue_postmerge
queue: cpu_queue_release
commands:
# Set configuration and check cache
- |
......@@ -465,7 +465,7 @@ steps:
- step: build-rocm-base-wheels
allow_failure: false
agents:
queue: cpu_queue_postmerge
queue: cpu_queue_release
timeout_in_minutes: 180
commands:
# Download artifacts and prepare Docker image
......@@ -575,7 +575,7 @@ steps:
- step: build-rocm-vllm-wheel
allow_failure: false
agents:
queue: cpu_queue_postmerge
queue: cpu_queue_release
timeout_in_minutes: 60
commands:
# Download all wheel artifacts and run upload
......@@ -624,7 +624,7 @@ steps:
- step: input-release-version
allow_failure: true
agents:
queue: cpu_queue_postmerge
queue: cpu_queue_release
commands:
- "bash .buildkite/scripts/annotate-rocm-release.sh"
env:
......@@ -641,7 +641,7 @@ steps:
depends_on: block-generate-root-index-rocm-wheels
id: generate-root-index-rocm-wheels
agents:
queue: cpu_queue_postmerge
queue: cpu_queue_release
commands:
- "bash tools/vllm-rocm/generate-rocm-wheels-root-index.sh"
env:
......@@ -655,7 +655,7 @@ steps:
- step: build-rocm-base-wheels
allow_failure: false
agents:
queue: cpu_queue_postmerge
queue: cpu_queue_release
timeout_in_minutes: 60
commands:
- |
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment