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 13, 20:45 UTC
Remove the tpu docker image nightly build. (#27997)
Signed-off-by: Qiliang Cui <derrhein@gmail.com>
QiliangCui committed
Nov 3, 2025 at 16:35 UTC
7956b0c0bca8c2b778e6a0b18953b5a08e136c90
1 file changed
-18
.buildkite/release-pipeline.yaml
-18
@@ -116,24 +116,6 @@ steps:
116
commands:
117
- "bash .buildkite/scripts/annotate-release.sh"
118
119
- - label: "Build and publish TPU release image"
120
- depends_on: ~
121
- if: build.env("NIGHTLY") == "1"
122
- agents:
123
- queue: tpu_queue_postmerge
124
- commands:
125
- - "yes | docker system prune -a"
126
- - "git fetch --all"
127
- - "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:$BUILDKITE_COMMIT --progress plain -f docker/Dockerfile.tpu ."
128
- - "docker push vllm/vllm-tpu:nightly"
129
- - "docker push vllm/vllm-tpu:$BUILDKITE_COMMIT"
130
- plugins:
131
- - docker-login#v3.0.0:
132
- username: vllmbot
133
- password-env: DOCKERHUB_TOKEN
134
- env:
135
- DOCKER_BUILDKIT: "1"
136
-
119
- input: "Provide Release version here"
120
id: input-release-version
121
fields: