[Klaud Cold] Update minimaxm2.5-fp8-mi300x-vllm vLLM ROCm image to v0.22.0

[functionstackx]

Summary

Update vLLM ROCm image from v0.21.0 to v0.22.0

Recipes touched: minimaxm2.5-fp8-mi300x-vllm

Test plan

• full-sweep-enabled sweep passes.

🤖 Generated with Claude Code

---

Note

Low Risk
Config-only Docker image tag bump for a single AMD benchmark recipe; no serving flags or search-space changes in this diff.

Overview
Bumps the MiniMax-M2.5 FP8 on MI300X vLLM benchmark recipe (minimaxm2.5-fp8-mi300x-vllm) from vllm/vllm-openai-rocm:v0.21.0 to v0.22.0 in .github/configs/amd-master.yaml. Model, runner, TP/concurrency search space, and scenarios are unchanged.

Adds a matching perf-changelog.yaml entry keyed to that config, noting the image update and linking PR #1618.

^{Reviewed by Cursor Bugbot for commit ce8f358. 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=26696255531
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26696255531

[claude]

LGTM — single-recipe vLLM ROCm image bump v0.21.0 → v0.22.0 with matching changelog entry.

Extended reasoning...

Overview

This PR updates the image tag for the minimaxm2.5-fp8-mi300x-vllm recipe in .github/configs/amd-master.yaml from vllm/vllm-openai-rocm:v0.21.0 to vllm/vllm-openai-rocm:v0.22.0, and adds the corresponding entry to perf-changelog.yaml.

Security risks

None. This is a YAML config change touching only an image tag and a human-readable changelog — no code, auth, or data paths are affected.

Level of scrutiny

Low. This is a mechanical, one-line image bump for a single recipe that follows the established pattern used throughout the file. The full-sweep-enabled label means the sweep will validate correctness end-to-end; if v0.22.0 has incompatibilities, the sweep will catch them before merge.

Other factors

The bug hunting system found no issues. The change is self-contained and easily revertible.

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26696256680
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26696256680