diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-03-07 09:46:58 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-03-07 09:46:58 +0200 |
| commit | 3d85a1d66302989401f92a5ae347577b03cbdaa7 (patch) | |
| tree | 7d9ea15568de65954ebddbf71792ad781841fd7f /examples/save-load-state/save-load-state.cpp | |
| parent | c67a37b251fc22b0f8b8313ea5c76a73ff6ed49f (diff) | |
Better FlashMLA (#243)
* This is a better FA for TG
It should benefit MLA and GQA. Tested to work with
DeepSeek-Lite MLA, not yet for GQA.
For tg64@pp8192 it is ~13% faster than MLA without FA,
and 57% faster that the main branch FA.
* WIP
* Cleanup
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'examples/save-load-state/save-load-state.cpp')
0 files changed, 0 insertions, 0 deletions