Skip to content

[CI] Temporarily disable GB300 jobs (runner availability) - #31764

Merged
ch-wan merged 1 commit into
mainfrom
ci/disable-gb300-runner-availability
Jul 20, 2026
Merged

ch-wan merged 1 commit into
mainfrom
ci/disable-gb300-runner-availability

Conversation

@alisonshao

@alisonshao alisonshao commented Jul 20, 2026 •

Copy link
Copy Markdown
Collaborator

GB300 runners are temporarily offline. Comment out every job that requests a 4-gpu-gb300 runner so nothing queues against unavailable capacity. Each commented block carries a one-line reason; revert this PR to re-enable when the runners return.

Disabled

  • Baseline — pr-test.yml: base-c-test-4-gpu-gb300 job + its pr-test-finish needs: reference.
  • Nightly — nightly-test-nvidia.yml: nightly-test-perf-4-gpu-gb300 (the 4-model matrix: glm5-nvfp4 / qwen35-fp8 / deepseek-v4-pro-fp4 / kimi-k25-nvfp4) + its job_filter option + its needs: aggregation reference.
  • Release — release-whl-deepgemm.yml: the sm100-aarch64 (4-gpu-gb300) leg of the test-cu130 matrix (sm90 / sm100 legs unaffected).

Downstream needs: / job_filter references are commented too, so the workflows stay valid. No test files touched — the registry tags are unchanged, so re-enabling is a straight revert.


CI States

Latest PR Test (Base): 🚫 Run #29726507956
Latest PR Test (Extra): ❌ Run #29726507864

GB300 runners are temporarily offline. Comment out every job that requests a
gb300 runner so they don't queue against unavailable capacity:

- pr-test.yml: base-c-test-4-gpu-gb300 (baseline) + its pr-test-finish needs ref
- nightly-test-nvidia.yml: nightly-test-perf-4-gpu-gb300 (4-model matrix) + its
  job_filter option and needs aggregation ref
- release-whl-deepgemm.yml: the sm100-aarch64 (4-gpu-gb300) test-cu130 matrix leg

Each commented block carries a one-line reason; revert to re-enable when the
runners return.
@gemini-code-assist

Copy link
Copy Markdown
Contributor

Note

Gemini is unable to generate a review for this pull request due to the file types involved not being currently supported.

@alisonshao

Copy link
Copy Markdown
Collaborator Author

/tag-and-rerun-ci

@github-actions github-actions Bot added the run-ci CI: run the baseline test suite on this PR label Jul 20, 2026
@ch-wan
ch-wan merged commit 3f48245 into main Jul 20, 2026
116 of 142 checks passed
@ch-wan
ch-wan deleted the ci/disable-gb300-runner-availability branch July 20, 2026 08:19
Zhylkaaa pushed a commit to Zhylkaaa/sglang that referenced this pull request Jul 29, 2026
Chronostasys pushed a commit to MindLab-Research/sglang that referenced this pull request Aug 24, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

run-ci CI: run the baseline test suite on this PR

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants