[Klaud Cold] Update qwen3.5-fp8-b200-sglang (+mtp) SGLang image to v0.5.12-cu130

[functionstackx]

Summary

Update SGLang image from nightly-dev-20260422-de962f32 (18d/12d old) to v0.5.12-cu130

Recipes touched: `qwen3.5-fp8-b200-sglang`, qwen3.5-fp8-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=26009974487
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26009974487

[claude]

LGTM — straightforward SGLang image bump for two recipes with matching changelog entry.

Extended reasoning...

Overview

This PR updates the SGLang container image for the qwen3.5-fp8-b200-sglang and qwen3.5-fp8-b200-sglang-mtp recipes in .github/configs/nvidia-master.yaml, moving from a nightly-dev tag (~18d/12d old) to the pinned release v0.5.12-cu130. A matching entry is added to perf-changelog.yaml documenting the change and linking back to this PR.

Security risks

None. The change is limited to two YAML image tags and a changelog entry; no code paths, secrets, permissions, auth, or crypto are affected. The image reference points to the same lmsysorg/sglang registry already in use elsewhere in the file.

Level of scrutiny

Low. This is a mechanical config-only update following the exact same pattern as recent prior PRs (e.g., #1458 for the H200 variant, which appears immediately above the new changelog entry). The full-sweep-enabled label triggers the benchmark sweep, which is the appropriate validation gate for this kind of change.

Other factors

No prior reviewer comments to address beyond the standard recipe-reminder bot comment. The changelog entry is well-formed and consistent with adjacent entries. No bugs were flagged by the bug hunting system.

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26009976161
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26009976161

[functionstackx]

/reuse-sweep-run

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26045911898
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26045911898