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, 18:30 UTC
[release] Tag vllm-cpu with latest upon new version released (#15193)
Kevin H. Luu committed
Mar 20, 2025 at 01:19 UTC
3d45e3d74961568ace12f01c4573150ed6010789
1 file changed
+1
-1
.buildkite/release-pipeline.yaml
+1
-1
@@ -82,7 +82,7 @@ steps:
82
queue: cpu_queue_postmerge
83
commands:
84
- "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
85
- - "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:$(buildkite-agent meta-data get release-version) --progress plain -f Dockerfile.cpu ."
85
+ - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg GIT_REPO_CHECK=1 --tag public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:$(buildkite-agent meta-data get release-version) --tag public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:latest --progress plain -f Dockerfile.cpu ."
86
- "docker push public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:$(buildkite-agent meta-data get release-version)"
87
env:
88
DOCKER_BUILDKIT: "1"