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, 19:45 UTC
[release] Add commands to clean up logs on TPU release node (#14642)
Kevin H. Luu committed
Mar 11, 2025 at 17:14 UTC
9f583e360c12acea5a10a859db92ad3717251de5
1 file changed
+2
.buildkite/release-pipeline.yaml
+2
@@ -57,6 +57,8 @@ steps:
57
agents:
58
queue: tpu_queue_postmerge
59
commands:
60
+ - "rm /var/log/syslog"
61
+ - "rm /var/log/kern.log"
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:$BUILDKITE_COMMIT --progress plain -f Dockerfile.tpu ."
63
- "docker push vllm/vllm-tpu:nightly"
64
- "docker push vllm/vllm-tpu:$BUILDKITE_COMMIT"