Files
ik_llama.cpp/ggml
Kawrakow 073eda985e Metal: FA and FlashMLA (#310)
* Metal: WIP to update Metal FA implementation

Dk=192, Dv=128 works, but not Dk = 576, Dv = 512

* Metal FA: go to float

* WIP

* Metal FA: MLA options now all work

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-04-03 17:54:25 +02:00
..
2024-07-27 07:55:01 +02:00
2025-04-03 17:54:25 +02:00
2024-07-27 07:55:01 +02:00