[Klaud Cold] Update minimaxm2.5-fp4-b200-vllm vLLM image to v0.22.0

[functionstackx]

Summary

Update vLLM image from v0.21.0 to v0.22.0

Recipes touched: minimaxm2.5-fp4-b200-vllm

Test plan

• full-sweep-enabled sweep passes.

🤖 Generated with Claude Code

---

Note

Low Risk
Single-container image tag bump for an existing benchmark config; no logic, auth, or sweep-parameter changes in the diff.

Overview
Bumps the minimaxm2.5-fp4-b200-vllm benchmark recipe to vllm/vllm-openai:v0.22.0 (from v0.21.0) in .github/configs/nvidia-master.yaml, with no other recipe fields changed in this diff.

Adds a matching perf-changelog.yaml entry for that config key so the image bump is tracked with PR #1611.

^{Reviewed by Cursor Bugbot for commit d8df04b. Bugbot is set up for automated code reviews on this repo. Configure here.}

[github-actions]

Thanks for the contribution! For vLLM & SGLang, please ensure that your recipes is similar to the official vLLM recipes and/or the SGLang cookbook

• https://docs.sglang.io/cookbook/intro
• https://recipes.vllm.ai/

If it is not, please create a PR first before we can merge your single node PR into the master branch. Let's ensure that the documentation is first class such that the entire ML community can benefit from your hard work! Thank you

• https://github.com/vllm-project/recipes
• https://github.com/sgl-project/sglang/tree/main/docs_new

PR authors are responsible for ensuring that after merging, all GitHub Action jobs fully pass. A lot of the time, failures are just flakes and simply re-running the failed jobs will fix it. If re-running failed jobs is attempted, PR authors are responsible for ensuring it passes. See GitHub's docs on re-running failed jobs: https://docs.github.com/en/actions/how-tos/manage-workflow-runs/re-run-workflows-and-jobs#re-running-failed-jobs-in-a-workflow

As a rule of thumb, generally, PR authors should request a review & get a PR approval from the respective companies' CODEOWNERS before requesting a review from core maintainers.

If additional help is needed, PR authors can reach out to core maintainers over Slack.

[github-actions]

Thanks for the contribution! For vLLM & SGLang, please ensure that your recipes is similar to the official vLLM recipes and/or the SGLang cookbook

• https://docs.sglang.io/cookbook/intro
• https://recipes.vllm.ai/

If it is not, please create a PR first before we can merge your single node PR into the master branch. Let's ensure that the documentation is first class such that the entire ML community can benefit from your hard work! Thank you

• https://github.com/vllm-project/recipes
• https://github.com/sgl-project/sglang/tree/main/docs_new

PR authors are responsible for ensuring that after merging, all GitHub Action jobs fully pass. A lot of the time, failures are just flakes and simply re-running the failed jobs will fix it. If re-running failed jobs is attempted, PR authors are responsible for ensuring it passes. See GitHub's docs on re-running failed jobs: https://docs.github.com/en/actions/how-tos/manage-workflow-runs/re-run-workflows-and-jobs#re-running-failed-jobs-in-a-workflow

As a rule of thumb, generally, PR authors should request a review & get a PR approval from the respective companies' CODEOWNERS before requesting a review from core maintainers.

If additional help is needed, PR authors can reach out to core maintainers over Slack.

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26696240354
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26696240354

[claude]

LGTM, straightforward vLLM image version bump.

Extended reasoning...

Overview

This PR bumps the vLLM image for the minimaxm2.5-fp4-b200-vllm recipe from v0.21.0 to v0.22.0 in .github/configs/nvidia-master.yaml, and adds a matching entry to perf-changelog.yaml.

Security risks

None. This is a config-only change pointing to a different published image tag of the same upstream vLLM project. No code paths, auth, crypto, or permissions are touched.

Level of scrutiny

Low. This is a mechanical, single-line image tag bump on a single recipe, accompanied by a corresponding changelog entry. The PR is labeled full-sweep-enabled so the sweep CI will validate that the new image actually works for this recipe before the change has any production impact.

Other factors

No bugs were found by the bug hunting system, the changelog entry is correctly scoped to only the affected recipe, and the format matches surrounding entries in perf-changelog.yaml. Author should ensure the full sweep passes per the test plan.

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26696241845
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26696241845

[functionstackx]

/reuse-sweep-run

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26699230256
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26699230256