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, 12:15 UTC
[release] Add command to clean up Docker containers/images in TPU release machine (#17606)
Kevin H. Luu committed
May 2, 2025 at 18:54 UTC
3ec97e2cc5426fd843c4724a593ec17f331151c5
1 file changed
+1
.buildkite/release-pipeline.yaml
+1
@@ -57,6 +57,7 @@ steps:
57
agents:
58
queue: tpu_queue_postmerge
59
commands:
60
+ - "yes | docker system prune -a"
61
- "git fetch --all"
62
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --tag vllm/vllm-tpu:nightly --tag vllm/vllm-tpu:$BUILDKITE_COMMIT --progress plain -f docker/Dockerfile.tpu ."
63
- "docker push vllm/vllm-tpu:nightly"