Kawrakow 09d4a8ad90 On Zen4 repack fp16 models to bf16_r16 when run-time-repacking is requested (#174) ...

This massively improves performance. As this is opt-in, we do not worry
about possible precision loss in the f16 -> bf16 conversion.

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

2025-01-21 19:19:38 +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

On Zen4 repack fp16 models to bf16_r16 when run-time-repacking is requested (#174)

2025-01-21 19:19:38 +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