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 15, 04:45 UTC
[CI/Build] Push latest tag for cpu and neuron docker image (#19897)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
22quinn committed
Jun 23, 2025 at 14:15 UTC
a3bc76e4b565fd14f13710c696fe47787b008f1f
1 file changed
+2
.buildkite/release-pipeline.yaml
+2
@@ -102,6 +102,7 @@ steps:
102
commands:
103
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
104
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg GIT_REPO_CHECK=1 --tag public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:$(buildkite-agent meta-data get release-version) --tag public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:latest --progress plain --target vllm-openai -f docker/Dockerfile.cpu ."
105
+ - "docker push public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:latest"
106
- "docker push public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:$(buildkite-agent meta-data get release-version)"
107
env:
108
DOCKER_BUILDKIT: "1"
@@ -117,6 +118,7 @@ steps:
118
commands:
119
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
120
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg GIT_REPO_CHECK=1 --tag public.ecr.aws/q9t5s3a7/vllm-neuron-release-repo:$(buildkite-agent meta-data get release-version) --tag public.ecr.aws/q9t5s3a7/vllm-neuron-release-repo:latest --progress plain -f docker/Dockerfile.neuron ."
121
+ - "docker push public.ecr.aws/q9t5s3a7/vllm-neuron-release-repo:latest"
122
- "docker push public.ecr.aws/q9t5s3a7/vllm-neuron-release-repo:$(buildkite-agent meta-data get release-version)"
123
env:
124
DOCKER_BUILDKIT: "1"