- 11 Dec, 2023 1 commit
-
-
Li Zhang authored
* disable attention mask when not needed * fix for sm<80 and float data type
-
- 04 Dec, 2023 1 commit
-
-
Li Zhang authored
* Unify prefill and decode passes * dynamic split-fuse * refactor * correct input count calculation * remove unused * lint * lint * fix msvc build * fix msvc build * fix msvc build * fix msvc build * fix msvc build * fix msvc build * fix msvc build * fix msvc build * fix msvc build
-