Close BC8 decode curve counterfactual
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
# 实验 EXP-DECODE-BATCH-GRID:BC-8 是否可由稳定 whole-layer b2--b8 curve 修复
|
||||
|
||||
> **状态:** TP4/b2 stability gate PASS,扩展 full grid
|
||||
> **状态:** COMPLETED;BC-8 排序工程修复成立,global curve merge 暂停
|
||||
>
|
||||
> Parent campaign:[`../frontier-simulator-gap-campaign-v0/README.md`](../frontier-simulator-gap-campaign-v0/README.md)
|
||||
|
||||
@@ -54,9 +54,10 @@
|
||||
## 复现信息
|
||||
|
||||
- **Frontier baseline:** `deadc4a321f0baaa534c6ebd17f974123733cdc2`;
|
||||
joint serving-path curves + structured-attention analysis branch。
|
||||
- **Remote:** 复用 dash1 的 clean detached experiment worktree;canonical
|
||||
checkout 的用户 dirty changes 不动。
|
||||
CPU replay 使用既有 joint serving-path curves,未合入 EXP-1 rejected patch。
|
||||
- **Remote:** dash1--dash4 共享 clean detached experiment worktree
|
||||
`ecc559938132851d61bf22daa55cea9658807dfa`;canonical checkout 的用户
|
||||
dirty changes 未改动。
|
||||
- **Known limits:** 固定 2048→128 state-matched workload;本实验只支持
|
||||
decode curve 与 BC-8,不外推到 chat prefill shape 或其它模型。
|
||||
|
||||
@@ -68,6 +69,34 @@
|
||||
`4.6263 ms` 和 `4.6201 ms`,跨 repeat CV=`0.067%`,稳定性 gate
|
||||
PASS,无需 repeat 3。median=`4.6232 ms`,比旧样本 `5.044 ms` 低
|
||||
`0.421 ms`;方向支持 H1,但未达到事前 `>=0.5 ms` 的强证据阈值。
|
||||
- **观察事实:** 旧 TP4/b2 的高方差主要是测量不稳定;是否足以修复
|
||||
BC-8 仍须 full b2--b8 curve 与 trace replay。
|
||||
- **Decision:** 待 GPU。
|
||||
- **Full grid:**
|
||||
|
||||
| Cell | fresh-process execute mean (ms) | median (ms) | initial CV |
|
||||
|---|---:|---:|---:|
|
||||
| TP2/b2 | 4.761 / 4.730 | 4.746 | 0.33% |
|
||||
| TP2/b4 | 5.294 / 5.607 | 5.451 | 2.87% |
|
||||
| TP2/b6 | 6.571 / 6.938 | 6.754 | 2.72% |
|
||||
| TP2/b8 | 5.967 / 6.309 | 6.138 | 2.78% |
|
||||
| TP4/b2 | 4.626 / 4.620 | 4.623 | 0.07% |
|
||||
| TP4/b4 | 4.516 / 4.727 | 4.622 | 2.27% |
|
||||
| TP4/b6 | 5.433 / 10.157 / 8.634 | 8.634 | 30.30% |
|
||||
| TP4/b8 | 4.898 / 5.047 | 4.972 | 1.50% |
|
||||
|
||||
- **TP4/b6 instability:** r2/r3 的 MoE 与 attention 基本不变,均值波动由
|
||||
同步 collective 长尾造成;三个 run 的 step p50 仍约 `5.18--5.49 ms`。
|
||||
依预注册规则追加 r3 并取三次中位数,但该 cell 不能视为稳定 deterministic
|
||||
service constant。
|
||||
- **BC-8 exact replay:** replay 仅访问 b1/b2,因此没有使用 b6 或任何
|
||||
插值/外推。TP4/b2 whole-layer override 将 TP4 sim TPOT
|
||||
`5.864→5.367 ms`,残差 `+1.414→+0.918 ms`(MNS16)和
|
||||
`+1.498→+1.001 ms`(MNS32);MNS16 完整排序从
|
||||
`TP2<TP1<TP4` 恢复为真实的 `TP2<TP4<TP1`。sim b>1 stage fraction
|
||||
`48.15%→37.47%`。
|
||||
- **7-cell support audit:** 最新 1h cells 的 decode batch 最大到
|
||||
`b6--b15`,而本实验 measured support 只到 b8;TP4/b6 又未通过
|
||||
deterministic-mean 稳定性。为避免重新引入 b8 constant extrapolation,
|
||||
不执行全局 7-cell injection,也不把整条 b2--b8 curve 合入默认 predictor。
|
||||
- **Decision:** H1 对 BC-8 成立,排序 gap 属于可工程修复的 TP4/b2
|
||||
whole-layer service residual;但绝对残差、MNS tie 和高 batch collective
|
||||
tail 仍需 event/distribution-aware 模型。建议先合入受作用域保护的 TP4/b2
|
||||
correction,再补 b9--b16 与 collective-tail telemetry 后开启 global merge。
|
||||
|
||||
Reference in New Issue
Block a user