[Klaud Cold] Update minimaxm2.5-fp8-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-fp8-b200-vllm

Test plan

• full-sweep-enabled sweep passes.

🤖 Generated with Claude Code

---

Note

Low Risk
Config-only container image tag bump with no runtime code or scenario changes; impact is limited to benchmark/sweep behavior for one recipe.

Overview
Bumps the MiniMax-M2.5 FP8 B200 vLLM benchmark recipe (minimaxm2.5-fp8-b200-vllm) from vllm/vllm-openai:v0.21.0 to vllm/vllm-openai:v0.22.0 in .github/configs/nvidia-master.yaml. Model, runner, scenarios, and search spaces are unchanged.

Adds a matching perf-changelog.yaml entry for this config key, consistent with other recent v0.22.0 image updates on B200 vLLM recipes.

^{Reviewed by Cursor Bugbot for commit 199d540. 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]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26696231868
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26696231868

[claude]

LGTM, straightforward vLLM image version bump with corresponding changelog entry.

Extended reasoning...

Overview

This PR bumps the vLLM image for the minimaxm2.5-fp8-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. The change is two lines total (one substantive image change, plus a changelog block).

Security risks

None. This is a container image tag change for a benchmark recipe; no auth, crypto, permissions, or data-handling code is touched.

Level of scrutiny

Low. This is a mechanical config-only change following an established pattern used repeatedly in this repo for vLLM/SGLang image bumps. The full-sweep-enabled label triggers a sweep that will validate the new image works as expected before any results are used.

Other factors

No bugs were flagged by the bug hunting system. The changelog entry is correctly scoped to the single recipe touched and links back to this PR. Verification is handled by the full-sweep run gated on this PR.

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26696233215
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26696233215

[functionstackx]

/reuse-sweep-run

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26699338837
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26699338837