[Klaud Cold] Update qwen3.5-fp4-b200-sglang-agentic-mtp SGLang image to nightly-dev-cu13-20260907-30705c00

[functionstackx]

Summary

Update SGLang image for the Qwen3.5-397B-A17B NVFP4 B200 AgentX MTP recipe from lmsysorg/sglang:v0.5.16-cu130 (v0.5.16 release) to lmsysorg/sglang:nightly-dev-cu13-20260907-30705c00 (2026-09-07 cu13 dev nightly).

• Tag verified on Docker Hub: last pushed 2026-09-07T01:43:42Z, digest sha256:19b8fa1223cc339c1eae7a5b703f1a8c2543b5b119155bf3d7efaef18f77f007
• Tag commit: sgl-project/sglang@30705c00 ("[Deepseek V4] Keep fp32 routing weights in the mxfp4 trtllm MoE")
• Same target tag as the FP8 sibling bump in [Klaud Cold] Update qwen3.5-fp8-b200-sglang-agentic-mtp SGLang image to nightly-dev-cu13-20260907-30705c00 #2861; follows the repo's nightly-dev-cu13-<date>-<hash> convention, matching the current cu130 pin.
• Recipe script, modelopt_fp4 / trtllm_mha / flashinfer_trtllm flags, NEXTN MTP settings, golden AL 3.39, and the TP2/TP4 concurrency and HiCache grids are unchanged; image-only bump.

Recipes touched: qwen3.5-fp4-b200-sglang-agentic-mtp

Test plan

• full-sweep-enabled sweep passes on cluster:b200-nscale.

🤖 Generated with Claude Code

---

Note

Low Risk
Benchmark config and changelog only; behavior change is limited to the pinned SGLang container for one recipe, with no auth or production runtime impact.

Overview
Updates the qwen3.5-fp4-b200-sglang-agentic-mtp benchmark recipe to use lmsysorg/sglang:nightly-dev-cu13-20260907-30705c00 instead of lmsysorg/sglang:v0.5.16-cu130 (cu13 dev nightly vs prior release pin). Engine flags, NEXTN MTP settings, golden acceptance length, and TP2/TP4 concurrency / HiCache search grids are left as-is.

Adds a matching perf-changelog entry for the agentic-coding scenario documenting the image digest, tag commit, and unchanged recipe parameters.

The same config hunk also drops dram-utilization: 0.80 from the minimaxm3-fp8-h200-vllm-agentic-mtp agentic-coding sweep block immediately above the Qwen recipe (not called out in the PR description).

^{Reviewed by Cursor Bugbot for commit 0a43cbe. Bugbot is set up for automated code reviews on this repo. Configure here.}

[github-actions]

Thanks for the contribution! Please reach out to respective companies' CODEOWNER to fill in the latest PR_REVIEW_CHECKLIST.md before pinging core maintainer on Slack for review. In order for the signoff PR check bot to trigger, you must follow the PR_REVIEW_CHECKLIST.md template correctly, including the phrase As a PR reviewer and CODEOWNER, I have reviewed this and have.

For PR verification, add the full-sweep-fail-fast label (strongly recommended) to this PR — the benchmark sweep only runs on labeled PRs. Use full-sweep-enabled only if you need matrix jobs to keep running past a failure.

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. See GitHub's docs on re-running failed jobs

---

感谢你的贡献！请联系相应公司的 CODEOWNER 填写最新的 PR_REVIEW_CHECKLIST.md，然后再在 Slack 上联系核心维护者进行审阅。为了触发 signoff PR 检查机器人，你必须正确遵循 PR_REVIEW_CHECKLIST.md 模板，包括保留英文语句 As a PR reviewer and CODEOWNER, I have reviewed this and have。

如需进行 PR 验证，请为此 PR 添加 full-sweep-fail-fast 标签（强烈推荐）— 基准测试 sweep 仅在带有标签的 PR 上运行。仅当需要矩阵任务在失败后继续运行时才使用 full-sweep-enabled。

PR 作者有责任确保合并后所有 GitHub Action 任务完全通过。 很多时候失败只是偶发抖动（flake），重新运行失败的任务即可解决。参见 GitHub 关于重新运行失败任务的文档

[github-actions]

Thanks for the contribution! Please reach out to respective companies' CODEOWNER to fill in the latest PR_REVIEW_CHECKLIST.md before pinging core maintainer on Slack for review. In order for the signoff PR check bot to trigger, you must follow the PR_REVIEW_CHECKLIST.md template correctly, including the phrase As a PR reviewer and CODEOWNER, I have reviewed this and have.

For PR verification, add the full-sweep-fail-fast label (strongly recommended) to this PR — the benchmark sweep only runs on labeled PRs. Use full-sweep-enabled only if you need matrix jobs to keep running past a failure.

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. See GitHub's docs on re-running failed jobs

---

感谢你的贡献！请联系相应公司的 CODEOWNER 填写最新的 PR_REVIEW_CHECKLIST.md，然后再在 Slack 上联系核心维护者进行审阅。为了触发 signoff PR 检查机器人，你必须正确遵循 PR_REVIEW_CHECKLIST.md 模板，包括保留英文语句 As a PR reviewer and CODEOWNER, I have reviewed this and have。

如需进行 PR 验证，请为此 PR 添加 full-sweep-fail-fast 标签（强烈推荐）— 基准测试 sweep 仅在带有标签的 PR 上运行。仅当需要矩阵任务在失败后继续运行时才使用 full-sweep-enabled。

PR 作者有责任确保合并后所有 GitHub Action 任务完全通过。 很多时候失败只是偶发抖动（flake），重新运行失败的任务即可解决。参见 GitHub 关于重新运行失败任务的文档

[claude]

🔴 The new changelog entry sets pr-link to the literal string "PRLINK_PLACEHOLDER", which is not the documented placeholder and will persist as garbage if the PR link is never manually fixed post-merge (docs/configuration-procedures.md:254 permits only TBD pre-merge, to be replaced with the real PR URL immediately after creation). Fix: use pr-link: TBD (or the actual PR URL once known) instead of a non-standard placeholder string, per the documented convention.

Extended reasoning...

docs/configuration-procedures.md line 254 states the only permitted placeholder before a PR exists is pr-link: TBD, replaced with the real URL right after PR creation. This diff instead writes pr-link: PRLINK_PLACEHOLDER (perf-changelog.yaml line 6929), a string that does not match any tooling or convention referenced in the docs. Since perf-changelog.yaml is append-only and byte-sensitive (never edited retroactively per AGENTS.md conventions), if this placeholder is not swept and replaced before/at merge, it becomes a permanent malformed record in the historical changelog, breaking any downstream tooling or scripts that parse pr-link fields expecting either a real GitHub URL or the TBD sentinel.

Verification: normal. perf-changelog.yaml:6929 sets pr-link: PRLINK_PLACEHOLDER on the newly appended entry. The repo's changelog gate rejects this value: utils/validate_perf_changelog.py:144-160 (validate_added_pr_link, invoked from compare_entries at line 206) requires an appended entry's link to be either the exact https://github.com/SemiAnalysisAI/InferenceX/pull/<pr_number> or a member of… | normal.…

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=34168717312
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=34168717312

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=34168717312
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=34168717312