Kawrakow 4a6a6f17ee Alternative CUDA FA for SWA models (#754) ...

* Bounds for flash attention

* Add n_swa to FA parameters

* Fix it

* This seems very slightly better

* Using vec kernel when we have SWA

* Need also this

* f32 vec kernel

* This is slightly better

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

2025-09-04 08:42:18 +02:00

..

cmake

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

include

Fused FFN_UP+FFN_GATE op (#741)

2025-08-31 18:16:36 +03:00

src

Alternative CUDA FA for SWA models (#754)

2025-09-04 08:42:18 +02:00

.gitignore

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

CMakeLists.txt

Set default value of GGML_SCHED_MAX_COPIES to 1 (#751)

2025-09-02 07:04:39 +02:00