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 force remove for TPU logs (#14697)
Kevin H. Luu committed
Mar 12, 2025 at 15:35 UTC
ce20124671cf4580627089e02f391cc95747939f
1 file changed
+2
-2
.buildkite/release-pipeline.yaml
+2
-2
@@ -57,8 +57,8 @@ steps:
57
agents:
58
queue: tpu_queue_postmerge
59
commands:
60
- - "rm /var/log/syslog"
61
- - "rm /var/log/kern.log"
60
+ - "rm -f /var/log/syslog"
61
+ - "rm -f /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"