EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

[Cherry-pick]bmm_transpose to v011dev (#3995)

Browse Source 
### What this PR does / why we need it?
Add a custom op to acclerater the deepseek model. The fusion ops combine
the bmm and transpose together, which is applied to mla module.
Cherry-pick from this commtid c68ddc11ce53334fc9a17bad58342148cbf14e86

### Does this PR introduce _any_ user-facing change?
No

---------

Signed-off-by: hust17yixuan <303660421@qq.com>
This commit is contained in:
Wang Yixuan
2025-12-08 19:22:14 +08:00
committed by GitHub
parent 6391f0625f
commit d412565ec9
15 changed files with 1736 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
typos.toml
View File

@@ -19,7 +19,7 @@ locale = "en"
extend-ignore-identifiers-re = [".*Unc.*", ".*_thw",
".*UE8M0.*", ".*[UE4M3|ue4m3].*", ".*eles.*", ".*fo.*", ".*ba.*",
".*ot.*", ".*[Tt]h[rR].*"]
extend-ignore-words-re = ["CANN", "cann"]
extend-ignore-words-re = ["CANN", "cann","ND"]
extend-ignore-re = []
[default.extend-identifiers]