[Klaud Cold] Update qwen3.5-fp4-b200-sglang (+mtp) SGLang image to v0.5.12-cu130

[functionstackx]

Summary

Update SGLang image from nightly-dev-20260422-de962f32 (17d/13d old) to v0.5.12-cu130

Recipes touched: `qwen3.5-fp4-b200-sglang`, qwen3.5-fp4-b200-sglang-mtp

Test plan

• full-sweep-enabled sweep passes.

🤖 Generated with Claude Code

[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=26009978373
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26009978373

[claude]

LGTM, straightforward SGLang image bump to a stable release.

Extended reasoning...

Overview

This PR updates the SGLang image for two recipes (qwen3.5-fp4-b200-sglang and qwen3.5-fp4-b200-sglang-mtp) in .github/configs/nvidia-master.yaml from a nightly-dev build (nightly-dev-20260422-de962f32) to a stable release (v0.5.12-cu130), and adds a corresponding entry to perf-changelog.yaml.

Security risks

None. This is a config-only change that pins a vendor-published, stable image tag — a move from a nightly to a stable release is generally safer.

Level of scrutiny

Low. This is a mechanical version bump following the same pattern as PR #1458 (which bumped qwen3.5-fp8-h200-sglang to the same image). The full-sweep-enabled label ensures the change is exercised by CI before merge.

Other factors

The diff is two-line image string changes plus an additive changelog entry. No code paths, security-sensitive areas, or shared infrastructure are touched. The bug hunting system found no issues.

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26009980249
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26009980249

[functionstackx]

/reuse-sweep-run

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26045887497
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26045887497