[Klaud Cold] Update kimik2.5-int4-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: kimik2.5-int4-mi300x-vllm

Test plan

• full-sweep-enabled sweep passes.

🤖 Generated with Claude Code

---

Note

Low Risk
Single-recipe container tag bump with no serving-flag or search-space edits; risk is limited to v0.22.0 runtime compatibility or perf shifts on MI300X for Kimi K2.5 INT4.

Overview
Bumps the Kimi K2.5 INT4 MI300X vLLM benchmark container from vllm/vllm-openai-rocm:v0.21.0 to v0.22.0 in .github/configs/amd-master.yaml for kimik2.5-int4-mi300x-vllm. Model, TP=8 fixed-seq-len sweeps, and other recipe fields are unchanged.

Adds a matching perf-changelog.yaml entry for config-key kimik2.5-int4-mi300x-vllm (PR #1615).

^{Reviewed by Cursor Bugbot for commit 51636bf. 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=26696248983
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26696248983

[claude]

LGTM — simple vLLM ROCm image version bump (v0.21.0 → v0.22.0) for a single recipe.

Extended reasoning...

Overview

This PR bumps the vLLM ROCm image for the kimik2.5-int4-mi300x-vllm recipe from v0.21.0 to v0.22.0 in .github/configs/amd-master.yaml, and adds a matching entry to perf-changelog.yaml. The full sweep CI label is applied to validate the bump.

Security risks

None. This is a config-only change pointing to a different version of an upstream public image tag. No credentials, auth, network, or code-execution paths are touched.

Level of scrutiny

Minimal scrutiny is appropriate. The pattern (image tag bump on a single recipe entry, plus a changelog row referencing the PR) matches the established convention in this repo, and the full-sweep-enabled label means the actual correctness of the bump will be validated by the CI sweep before merge.

Other factors

The bug hunting system found nothing, the diff is two lines plus a six-line changelog entry, and the changelog row is well-formed with the correct pr-link back to #1615.

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26696250618
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26696250618