[Klaud Cold] Update kimik2.5-fp4-b300-vllm vLLM image to v0.22.0

[functionstackx]

Summary

Update vLLM image from v0.21.0 to v0.22.0

Recipes touched: kimik2.5-fp4-b300-vllm

Test plan

• full-sweep-enabled sweep passes.

🤖 Generated with Claude Code

---

Note

Low Risk
Single-container image pin for an existing sweep config; no application, auth, or inference logic changes.

Overview
Bumps the Kimi K2.5 FP4 B300 vLLM benchmark recipe (kimik2.5-fp4-b300-vllm) from vllm/vllm-openai:v0.21.0 to v0.22.0 in .github/configs/nvidia-master.yaml. Model, runner, scenarios, and search space are unchanged; the in-file note still documents that B300 reuses the B200 recipe until B300-specific tuning exists.

perf-changelog.yaml gains an entry for this config key so the image bump is tracked with PR #1603.

^{Reviewed by Cursor Bugbot for commit 9dd46b7. 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=26696223312
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26696223312

[claude]

LGTM — single-line vLLM image pin bump (v0.21.0 → v0.22.0) for kimik2.5-fp4-b300-vllm with a matching perf-changelog entry.

Extended reasoning...

Overview

This PR bumps the container image for the kimik2.5-fp4-b300-vllm benchmark recipe from vllm/vllm-openai:v0.21.0 to v0.22.0 in .github/configs/nvidia-master.yaml, and adds a corresponding tracking entry in perf-changelog.yaml. Model, runner, scenarios, and search space are unchanged.

Security risks

None. This is a benchmark recipe configuration change — no auth, crypto, permissions, or production inference logic is touched. The image tag is the standard upstream vLLM publication.

Level of scrutiny

Minimal scrutiny required. This is a mechanical image version pin in a benchmark sweep config, following the exact pattern used throughout this repository for vLLM/SGLang version bumps. The full-sweep-enabled label indicates the sweep will validate runtime correctness automatically.

Other factors

The perf-changelog entry is well-formed and matches the established schema for the file. No outstanding reviewer comments to address.

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26696224570
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26696224570