[Klaud Cold] Update qwen3.5-fp4-b200-sglang (+mtp) SGLang image to v0.5.14-cu130 / 将 qwen3.5-fp4-b200-sglang(+mtp) 的 SGLang 镜像 升级至 v0.5.14-cu130 - #2056
Conversation
….5.14-cu130 中文:将 qwen3.5-fp4-b200-sglang(+mtp) 的 SGLang 镜像 升级至 v0.5.14-cu130。 Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
7a1ac55 to
3b00bcd
Compare
|
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 For PR verification, add the 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 如需进行 PR 验证,请为此 PR 添加 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 |
There was a problem hiding this comment.
LGTM — mechanical SGLang image bump (v0.5.12 → v0.5.14) for the two qwen3.5-fp4-b200 recipes with matching perf-changelog entry.
Extended reasoning...
Overview
This PR bumps the SGLang image tag from lmsysorg/sglang:v0.5.12-cu130 to lmsysorg/sglang:v0.5.14-cu130 for two recipes (qwen3.5-fp4-b200-sglang and qwen3.5-fp4-b200-sglang-mtp) in configs/nvidia-master.yaml, and appends a matching entry to perf-changelog.yaml referencing this PR. Total footprint is two one-line tag changes plus one changelog entry.
Security risks
None. This is a container image tag pointing at an already-published upstream SGLang release; there is no new code, no auth/crypto touch, and no permission changes. The image comes from the same lmsysorg namespace already used across many recipes in the file.
Level of scrutiny
Low. This matches the standard [Klaud Cold] image-bump pattern already merged repeatedly on this repo (e.g., recent commit 3b00bcd for the same recipe, and PR #1980 for a similar bump). The PR carries the full-sweep-fail-fast label so the benchmark sweep will act as the correctness gate — any regression from the new SGLang version will show up there before merge.
Other factors
The bug-hunting system found no issues. The perf-changelog entry is well-formed and correctly lists both affected config-keys and links back to this PR. No outstanding reviewer comments beyond the automated recipe-reminder bot.
|
see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=28719979274 |
|
/reuse-sweep-run |
# Conflicts: # perf-changelog.yaml
Summary
Update SGLang image from lmsysorg/sglang:v0.5.12-cu130 to lmsysorg/sglang:v0.5.14-cu130
Recipes touched:
qwen3.5-fp4-b200-sglang,qwen3.5-fp4-b200-sglang-mtp中文说明
将 SGLang 镜像 从 lmsysorg/sglang:v0.5.12-cu130 升级至 lmsysorg/sglang:v0.5.14-cu130。涉及配置:
qwen3.5-fp4-b200-sglang、qwen3.5-fp4-b200-sglang-mtp。Test plan
🤖 Generated with Claude Code