A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 6, 02:00 UTC
[release] Move the rest of release jobs to release queue (#38044)
Signed-off-by: khluu <khluu000@gmail.com>
Kevin H. Luu committed
Mar 24, 2026 at 16:40 UTC
af945615b599ec17a9a5b4a9533b9bb2dd29d584
1 file changed
+6
-6
.buildkite/release-pipeline.yaml
+6
-6
@@ -144,7 +144,7 @@ steps:
144
depends_on: ~
145
id: build-release-image-x86-ubuntu2404
146
agents:
147
- queue: cpu_queue_postmerge
147
+ queue: cpu_queue_release
148
commands:
149
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
150
- "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 UBUNTU_VERSION=24.04 --build-arg GDRCOPY_OS_VERSION=Ubuntu24_04 --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)-ubuntu2404 --target vllm-openai --progress plain -f docker/Dockerfile ."
@@ -156,7 +156,7 @@ steps:
156
depends_on: ~
157
id: build-release-image-arm64-ubuntu2404
158
agents:
159
- queue: arm64_cpu_queue_postmerge
159
+ queue: arm64_cpu_queue_release
160
commands:
161
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
162
- "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 UBUNTU_VERSION=24.04 --build-arg GDRCOPY_OS_VERSION=Ubuntu24_04 --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)-ubuntu2404 --target vllm-openai --progress plain -f docker/Dockerfile ."
@@ -166,7 +166,7 @@ steps:
166
depends_on: ~
167
id: build-release-image-x86-cuda-13-0-ubuntu2404
168
agents:
169
- queue: cpu_queue_postmerge
169
+ queue: cpu_queue_release
170
commands:
171
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
172
- "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 UBUNTU_VERSION=24.04 --build-arg GDRCOPY_OS_VERSION=Ubuntu24_04 --build-arg FLASHINFER_AOT_COMPILE=true --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-ubuntu24.04 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130-ubuntu2404 --target vllm-openai --progress plain -f docker/Dockerfile ."
@@ -178,7 +178,7 @@ steps:
178
depends_on: ~
179
id: build-release-image-arm64-cuda-13-0-ubuntu2404
180
agents:
181
- queue: arm64_cpu_queue_postmerge
181
+ queue: arm64_cpu_queue_release
182
commands:
183
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
184
- "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 UBUNTU_VERSION=24.04 --build-arg GDRCOPY_OS_VERSION=Ubuntu24_04 --build-arg FLASHINFER_AOT_COMPILE=true --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-ubuntu24.04 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130-ubuntu2404 --target vllm-openai --progress plain -f docker/Dockerfile ."
@@ -262,7 +262,7 @@ steps:
262
- build-release-image-arm64-ubuntu2404
263
id: create-multi-arch-manifest-ubuntu2404
264
agents:
265
- queue: small_cpu_queue_postmerge
265
+ queue: small_cpu_queue_release
266
commands:
267
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
268
- "docker manifest create public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-ubuntu2404 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64-ubuntu2404 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-aarch64-ubuntu2404 --amend"
@@ -274,7 +274,7 @@ steps:
274
- build-release-image-arm64-cuda-13-0-ubuntu2404
275
id: create-multi-arch-manifest-cuda-13-0-ubuntu2404
276
agents:
277
- queue: small_cpu_queue_postmerge
277
+ queue: small_cpu_queue_release
278
commands:
279
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
280
- "docker manifest create public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-cu130-ubuntu2404 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64-cu130-ubuntu2404 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-aarch64-cu130-ubuntu2404 --amend"