Repository navigation
[Klaud Cold] Update DeepSeek-V4.1-Flash FP4 H200 SGLang AgentX DSpark image to nightly-dev-cu13-20261028-586355a8 / [Klaud Cold] 将 DeepSeek-V4.1-Flash FP4 H200 SGLang AgentX DSpark 镜像更新至 nightly-dev-cu13-20261028-586355a8 - #4597
Klaud-Cold wants to merge 3 commits into
Conversation
…dev-cu13-20261028-586355a8 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
Thanks for the contribution!
中文感谢你的贡献!
|
|
Initial attempt · Passed · Run 40631236971 / attempt 1 · 2026-10-28 06:03 UTC
Note: All rows: Δ N/A: no matched baseline.
Next: Append the perf-changelog entry and dispatch the full AgentX final sweep (TP4/TP8 c1-c16 plus TP4 c16 GSM8K) on h200-dgxc. 中文初次尝试 · 已通过 · Run 40631236971 / attempt 1 · 2026-10-28 06:03 UTC |
|
parked · Session 1 is waiting on 40631236971. Recovery reruns preempted runs and starts the next session once they end. 中文parked · 第 1 个会话正在等待 40631236971。恢复流程会重跑被抢占的运行,并在运行结束后启动下一个会话。 |
|
resumed · The session ended before finishing; session 2 continues it in a new run of its planner. 中文resumed · 会话未完成即已结束;第 2 个会话将在其规划运行的新运行中继续。 |
…park image update Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
Final full sweep · Failed · Run 40641632969 / attempt 1 · 2026-10-28 08:27 UTC
Note: AgentX c1 TP4 EP1 a8dc9d: 2 request errors.
Next: Hugging Face rate limit is infrastructure, not the image: park and let recovery rerun the failed and cancelled jobs of run 40641632969 on the same head after 45 minutes as infrastructure retry 1. 中文最终完整 sweep · 失败 · Run 40641632969 / attempt 1 · 2026-10-28 08:27 UTC |
|
parked · Session 2 is waiting on 40641632969. Recovery reruns preempted runs and starts the next session once they end. 中文parked · 第 2 个会话正在等待 40641632969。恢复流程会重跑被抢占的运行,并在运行结束后启动下一个会话。 |
|
View unofficial run (performance): https://inferencex.semianalysis.com/inference?unofficialRun=40641632969 View unofficial run (accuracy): https://inferencex.semianalysis.com/evaluation?unofficialRun=40641632969 |
|
resumed · The session ended before finishing; session 3 continues it in a new run of its planner. 中文resumed · 会话未完成即已结束;第 3 个会话将在其规划运行的新运行中继续。 |
|
parked · Session 3 is waiting for recovery to rerun the failed jobs of 40641632969 after 2026-10-28 09:12 UTC. Recovery starts the next session once they end. 中文parked · 第 3 个会话正在等待恢复流程在 2026-10-28 09:12 UTC 后重跑 40641632969 的失败作业。运行结束后,恢复流程将启动下一个会话。 |
|
Final full sweep · Passed · Run 40641632969 / attempt 2 · 2026-10-28 11:14 UTC
Note: AgentX c1 TP4 EP1 a8dc9d: 2 request errors.
Next: Mark ready for maintainer review. 中文最终完整 sweep · 已通过 · Run 40641632969 / attempt 2 · 2026-10-28 11:14 UTC |
|
validated · Repairs: unknown · Runs: 40631236971, 40641608731, 40641632969 中文validated · 修复次数:未知 · 运行:40631236971, 40641608731, 40641632969 |
|
Claude finished @Klaud-Cold's task in 12s —— View job LGTM - no blocking issues found The PR pins the public Docker Hub image |
Goal: Update SGLang image from lmsysorg/sglang:nightly-dev-cu13-20261013-7224fce1 to lmsysorg/sglang:nightly-dev-cu13-20261028-586355a8.
Baseline: 2026-10-20 ·
lmsysorg/sglang:nightly-dev-cu13-20261013-7224fce1Mean latency · Sources: API 1, API 2, API 3, API 4
Stop: Close this PR at any time to stop this candidate now; Klaud cancels its runs and deletes its branch.
中文
**目标:**将 SGLang 镜像从 lmsysorg/sglang:nightly-dev-cu13-20261013-7224fce1 更新为 lmsysorg/sglang:nightly-dev-cu13-20261028-586355a8。
**基线:**2026-10-20 ·
lmsysorg/sglang:nightly-dev-cu13-20261013-7224fce1平均延迟 · 来源: API 1, API 2, API 3, API 4;数值及异常说明见上表。
**停止:**随时关闭此 PR 即可立即停止该候选:Klaud 会取消其运行并删除其分支。