[Klaud Cold] Update qwen3.8next-fp4-b300-sglang-agentic-mtp SGLang image to dev-cu13-qwen38-next-local (2026-09-07, digest-pinned)

[functionstackx]

Summary

Move the B300 Qwen3.8-Flash-Next NVFP4 AgentX MTP recipe from the mutable model-branch tag lmsysorg/sglang:qwen38flashnext to the newest Qwen3.8-Flash-Next model-branch build, lmsysorg/sglang:dev-cu13-qwen38-next-local@sha256:9d2a843c706c74bc259c0d9abf360551eb2734e1e7d255ab012a6965f10480b6, pinned by digest. Same move as the H100/H200 siblings in #2876 / #2877.

• Why not an upstream nightly: Qwen3.8-Flash-Next's architecture (Qwen4ExpForConditionalGeneration) is not in SGLang main, v0.5.19, or today's nightly nightly-dev-cu13-20260907-30705c00. It exists only on SGLang model branches shipped as dev images.
• Old tag: qwen38flashnext was last re-pushed 2026-09-03T20:54:46Z (digest sha256:5ae58167...), so nodes may have been running different builds depending on squash-cache age. The digest pin removes that ambiguity.
• New image: dev-cu13-qwen38-next-local, Docker Hub last pushed 2026-09-07T11:12:42Z, digest sha256:9d2a843c706c74bc259c0d9abf360551eb2734e1e7d255ab012a6965f10480b6. Provenance is a model branch, not upstream main; this sweep is the validation.
• benchmarks/single_node/agentic/qwen3.8next_fp4_b300_sglang_mtp.sh is unchanged; serve flags, golden AL, and grid unchanged.

Recipes touched: qwen3.8next-fp4-b300-sglang-agentic-mtp

Test plan

• full-sweep-enabled sweep passes on the B300 runner.

🤖 Generated with Claude Code

---

Note

Low Risk
Config and changelog only for a benchmark recipe; no application, auth, or serving logic changes.

Overview
Updates the qwen3.8next-fp4-b300-sglang-agentic-mtp benchmark recipe to use the digest-pinned SGLang model-branch image lmsysorg/sglang:dev-cu13-qwen38-next-local@sha256:9d2a843c… instead of the mutable qwen38flashnext tag, matching the H100/H200 updates in earlier PRs.

Runner is repointed from retired cluster:b300-nv to cluster:b300-dsxe so agentic-coding sweeps can schedule; that forces a full curve rerun on DSXE, not an append-only image bump. Serve script, flags, and concurrency grid are unchanged. perf-changelog.yaml documents both moves.

^{Reviewed by Cursor Bugbot for commit a50e00e. Bugbot is set up for automated code reviews on this repo. Configure here.}

Update

The recipe pinned runner: cluster:b300-nv, a fleet retired in #2826 (launcher and runner labels removed), so the first sweep could never be scheduled. Repointed to cluster:b300-dsxe, the same move #2829 makes for the GLM-5.2 B300 sibling. Because the runner changed this is not an append-only bump; the whole curve reruns on DSXE.

[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]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=34177012062
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=34177012062

[claude]

🔴 The new entry's pr-link is the literal string "PRLINK_PLACEHOLDER", which is not a value the changelog tooling recognizes: utils/validate_perf_changelog.py's PR_LINK_PLACEHOLDERS only accepts "XXX" or "https://github.com/SemiAnalysisAI/InferenceX/pull/XXX", so validate_added_pr_link raises ChangelogValidationError and the CI gate fails; the merge-prep step (utils/prepare_perf_changelog_merge.py canonicalize_appended_links) also rejects it with "unexpected pr-link" instead of rewriting it to the real PR URL, so this PR cannot pass the changelog gate or be auto-fixed at merge as the repo conventions assume. Fix: use one of the accepted placeholders ("XXX" or the pull/XXX form) for the pr-link field of any newly appended entry.

Extended reasoning...

utils/validate_perf_changelog.py:144-160 validate_added_pr_link(link, pr_number) computes expected = f".../pull/{pr_number}" and raises unless link is in PR_LINK_PLACEHOLDERS ({"XXX", ".../pull/XXX"}) or equals expected. compare_entries (line ~206) calls this for every added entry, and main() is the CI entry point, so any PR run of the gate against this changelog entry (pr-link: PRLINK_PLACEHOLDER) fails validation. Separately, utils/prepare_perf_changelog_merge.py:109-113 canonicalize_appended_links checks if link not in PR_LINK_PLACEHOLDERS: raise ChangelogValidationError(f"appended entry {index+1} has unexpected pr-link {link!r}"), so the merge-with-reuse tooling that is supposed to rewrite placeholders to the real PR URL also fails on this exact string instead of silently fixing it, contradicting the repo's documented merge flow.

Verification: normal. The appended perf-changelog.yaml entry ends with pr-link: PRLINK_PLACEHOLDER. The recognized set at utils/validate_perf_changelog.py:24-27 is PR_LINK_PLACEHOLDERS = {"XXX", "https://github.com/SemiAnalysisAI/InferenceX/pull/XXX"}; "PRLINK_PLACEHOLDER" is not in it. utils/prepare_perf_changelog_merge.py canonicalize_appended_links (lines ~110-114): link =…

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=34177251254
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=34177251254

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=34177251254
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=34177251254