dylanyunlong/project_6
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Compare commits

base: dylanyunlong:4189f44d27eaac712efd00e57cfdb1da88858a84
Branches Tags
dylanyunlong:main
...
compare: dylanyunlong:522e8376b6afde2361b731f45b486b3f90609357
Branches Tags
dylanyunlong:main

9 Commits
4189f44d27 ... 522e8376b6

Author SHA1 Message Date
root
522e8376b6 data: sub 694 (683分) 日志 + resolve merge 2026-08-16 15:28:08 +00:00
Claude
b7149f810a fix: decode MoE路径对齐base — F.linear+bmm替换pre-transpose+bmm 
base qwen3_5.py的decode路径（已验证可跑通竞赛）:
  F.linear(hidden, w13_sel.reshape(-1,H)) → view → act → bmm(w2_sel, act)

我们之前的路径（未验证，probe显示更慢）:
  pre-transpose(w13全量) → w13_t[eids] → bmm(x_expand, w13_t_sel) → act → bmm(act, w2_t_sel)

probe真机数据: loop matmul 19ms < torch.bmm 24ms
说明F.linear路径在BI-V100单token场景下更优

保持的corex加速:
  ✓ corex_moe_topk_softmax (topk+softmax fused)
  ✓ corex_moe_weight_gather (gather fused)
  ✓ corex_moe_exact_reduce (weighted sum fused)
  ✓ corex_moe_index_combine (prefill token routing fused)
 2026-08-15 14:56:40 +00:00
root
b187f52ced data: so import chain probe 2026-08-15 14:53:57 +00:00
root
924e48b502 data: so import chain probe 2026-08-15 14:49:42 +00:00
Claude
1700c35bd7 test: probe_so_import_chain.sh — 验证.so部署路径+import链+flag值+shape匹配 2026-08-15 14:48:47 +00:00
root
784dea96c0 data: base MoE forward + corex_moe签名 2026-08-15 14:39:03 +00:00
Claude
adf05b6bfb test: probe_base_moe_forward.sh — cat base qwen3_5.py的完整MoE forward + 所有corex_moe_*.so签名 2026-08-15 14:37:48 +00:00
Claude
7a8545f7c2 test: push_probe_results.sh — 真机commit probe结果到modelhub 2026-08-15 14:37:48 +00:00
root
437ad8aaa4 data: probe bridge output 2026-08-15 14:35:07 +00:00
1 changed files with 2928 additions and 0 deletions
Expand all files Collapse all files

2928
sub694rizhi.txt Normal file
View File

File diff suppressed because it is too large Load Diff