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, 09:45 UTC
[release] Change dockerhub username for TPU release (#18389)
Kevin H. Luu committed
May 19, 2025 at 23:49 UTC
d981396778d70726d7f9311ac54a18844b06d1a2
1 file changed
+1
-1
.buildkite/release-pipeline.yaml
+1
-1
@@ -64,7 +64,7 @@ steps:
64
- "docker push vllm/vllm-tpu:$BUILDKITE_COMMIT"
65
plugins:
66
- docker-login#v3.0.0:
67
- username: vllm
67
+ username: vllmbot
68
password-env: DOCKERHUB_TOKEN
69
env:
70
DOCKER_BUILDKIT: "1"