86e2bec04e
* Use new-new-mma also for MLA=3, and use mask bounds This gives us ~25% better PP at 32k tokens compared to main * This seems better --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com> |
||
|---|---|---|
| .. | ||
| cmake | ||
| include | ||
| src | ||
| .gitignore | ||
| CMakeLists.txt | ||