[Klaud Cold] Update qwen3.5-fp8-h200-sglang SGLang image to v0.5.12-cu130

[functionstackx]

Summary

• Bumps qwen3.5-fp8-h200-sglang from lmsysorg/sglang:v0.5.9-cu129-amd64 (74d old) to lmsysorg/sglang:v0.5.12-cu130.
• The -mtp sibling is already at v0.5.12, so this PR only touches the non-mtp recipe.

Test plan

• Full sweep passes with full-sweep-enabled label.

🤖 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]

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]

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=26006206899
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26006206899

[claude]

LGTM, straightforward SGLang image version bump.

Extended reasoning...

Overview

This PR bumps the SGLang image for the qwen3.5-fp8-h200-sglang recipe from v0.5.9-cu129-amd64 to v0.5.12-cu130 in .github/configs/nvidia-master.yaml and adds a corresponding changelog entry in perf-changelog.yaml. The diff is two lines of config plus a six-line changelog stanza.

Security risks

None. This is a benchmarking image tag change for an internal recipe config; no auth, crypto, or permissions code is touched.

Level of scrutiny

Low. This is a mechanical version bump that follows the established pattern used by the recent sibling PRs (#1404, #1394, #1416) visible in recent commits. The PR has the full-sweep-enabled label, so CI will validate the recipe end-to-end. The author already notes the -mtp sibling is already on v0.5.12, so there is precedent for this image working in the broader ecosystem.

Other factors

The bug hunting system found no issues. The changelog entry's pr-link correctly points to #1458 and the config-keys field matches the actual key being modified.

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26006208374
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26006208374

[functionstackx]

/reuse-sweep-run

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26009035076
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26009035076