[Klaud Cold] Update minimaxm2.5-fp8-mi355x-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-mi355x-vllm

Test plan

• full-sweep-enabled sweep passes.

🤖 Generated with Claude Code

---

Note

Low Risk
Config-only container tag bump with no sweep or launch-script changes; risk is limited to v0.22.0 runtime behavior on MI355X until the full sweep passes.

Overview
Bumps the MiniMax-M2.5 FP8 on MI355X vLLM ROCm benchmark recipe from vllm/vllm-openai-rocm:v0.21.0 to v0.22.0 in .github/configs/amd-master.yaml for config key minimaxm2.5-fp8-mi355x-vllm. Model, runner, parallelism, and fixed-seq-len search space are unchanged.

Adds a matching perf-changelog.yaml entry documenting the image bump and linking PR #1617.

^{Reviewed by Cursor Bugbot for commit be53b33. 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=26696253616
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26696253616

[claude]

LGTM, simple vLLM ROCm image tag bump for a single recipe with matching changelog entry.

Extended reasoning...

Overview

This PR bumps the vLLM ROCm image tag from v0.21.0 to v0.22.0 for the minimaxm2.5-fp8-mi355x-vllm recipe in .github/configs/amd-master.yaml, and adds a corresponding entry to perf-changelog.yaml linking back to this PR.

Security risks

None. This is a YAML config tweak that swaps a container image tag for a published vLLM ROCm release. No code paths, auth, secrets, or permissions are touched.

Level of scrutiny

Low. Image tag bumps for sweep recipes are the most common type of change in this repo, and the full-sweep-enabled label triggers the sweep validation. Correctness is validated empirically by the sweep itself, not by static review.

Other factors

The bug hunting system found no issues. The change is self-contained, follows the established pattern used by sibling recipes (many of which already pin to v0.21.0 or other specific versions), and the changelog entry is properly formatted with the PR link.

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26696254552
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26696254552

[functionstackx]

/reuse-sweep-run

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26699223016
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26699223016