Iwan Kawrakow dbe3b5837a Even better AVX2 implementation for q4_k_r4 ...

We now arrive at PP-512 = 328 t/s for LLaMA-3.1-8B on a
Ryzen-5975WX CPU, up from 291 t/s when I last measured
on 3c5f8722.
With FA and Q8_0 K-cache we get to 339.5 t/s.

2025-01-29 16:42:07 +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

Even better AVX2 implementation for q4_k_r4

2025-01-29 16:42:07 +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