Iwan Kawrakow 0e8cfb3d78 FA: slightly faster V*softmax(K*Q)) on Zen4 ...

We now get 130.9 t/s for a context of 32k tokens.

2025-01-18 08:35:01 +02:00

..

cmake

Merge mainline llama.cpp (#3)

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

include

CPU Flash Attention improvements (#172)

2025-01-15 18:19:22 +02:00

src

FA: slightly faster V*softmax(K*Q)) on Zen4

2025-01-18 08:35:01 +02:00

.gitignore

Merge mainline llama.cpp (#3)

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

CMakeLists.txt

Move to c++17 projectwide (#80)

2024-10-04 14:43:26 +03:00