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

Freeze Qwen235 ablation operator profiles

Browse Source
This commit is contained in:
Gahow Wang
2026-07-19 17:11:26 +08:00
parent 4ca295af0b
commit 10567da523
2 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.research/experiments/qwen235-tp8-collective-profile-ablation-20260719.md
View File

@@ -54,6 +54,7 @@
- **Environment：** dash0 8×H20；`/tmp/wjh/venvs/vllm-0.20.0-cu129-profiler-v1`；model `/home/admin/cpfs/wjh/models/Qwen/Qwen3-235B-A22B-FP8`。
- **产物路径：** 待 review 后冻结；不得覆盖旧 campaign `/home/admin/cpfs/wjh/aituner/qwen235-v020-fourcase-20260719-r1`。
- **已知 deviation：** `--disable-custom-all-reduce` 只关闭 vLLM custom AR，不关闭编译器的 FlashInfer `allreduce_rms` fusion。真机 TP4/TP8 日志都显示自动选择 `trtllm` workspace；旧 TP4 profiler 没有记录/执行真实 fusion-limit piecewise dispatch。A1 因此必须同时重测 TP4 与 TP8，不能只追加 TP8 行。
- **执行异常：** 首次 simulator launch 误把 frozen operator profile root 写成 r1；原 A0 campaign 实际使用 r2。四个 Fixed-PD cells 因缺少 `attn_decode_in_mixed` predictor 均 fail-fast，未产生可用 metric。command diff 确认后停止后续运行，恢复 r2 并从 failed cells 重新执行；这些失败不计入 A1 surface。
## 结果