Kawrakow 0459f595d7 CUDA: corectly detect if flash attention is supported (#875) ...

* Don't use vector kernels if K or V are quantized

* Correctly determine if FA is supported

* Also wmma

* Minor

---------

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

2025-10-29 13:56:16 +02:00

..

cmake

Merge mainline llama.cpp (#3)

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

include

Fused mul + multi_add op (#858)

2025-10-24 07:40:35 +03:00

src

CUDA: corectly detect if flash attention is supported (#875)

2025-10-29 13:56:16 +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