gahow/aituner
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Conclude Qwen30 admission diagnosis

Browse Source
This commit is contained in:
Gahow Wang
2026-07-19 20:56:36 +08:00
parent 2970f74d67
commit 18c0b25ae7
3 changed files with 11 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.research/ongoing.md
View File

@@ -2,7 +2,7 @@
> 2026-07-17｜写给未参与项目的读者，可直接作为 presentation 讲稿。历史过程与复现信息见 `../runs/*/` 各 experiment card、`../docs/` 各 campaign 文档。
>
> **2026-07-19 update：** Qwen235 四类 workload matrix 已完成；Fixed-PD 出现 33.0--37.2% TPOT 与 30.7--34.6% E2E selection regret。当前发现 Q235 simulator 输入的 collective CSV 缺 TP8，并且旧 TP4 profile 未绑定真实 `allreduce_rms` fusion-limit dispatch。active ablation 见 [`experiments/qwen235-tp8-collective-profile-ablation-20260719.md`](experiments/qwen235-tp8-collective-profile-ablation-20260719.md)。
> **2026-07-19 update：** Qwen235 Fixed-PD 的错误排序在 exact real state composition 下已经翻正，主因是 simulator closed-loop batch state，而不是 collective。Qwen30 Fixed-PD 的 56--58% TTFT regret 也已定位：Frontier 将 decode service time 高估 4--8×，使 TP4 的 modeled concurrency 越过 MNS admission cap并产生虚假排队；去掉该等待后 Frontier 与真机都判定 TP4 topology 更快。详见 [`experiments/qwen30-fixed-pd-ttft-admission-diagnosis-20260719.md`](experiments/qwen30-fixed-pd-ttft-admission-diagnosis-20260719.md)。
## 一眼看懂