Iwan Kawrakow 2b58f31b36 FA: allow bf16 for V-cache with any supported K-cache ...

E.g., -ctk q8_0 -ctv q8_0 is slightly faster than
-ctk q8_0 -ctv q8_0 on Zen4 for not too long context lengths
(say, <= 4096).

2025-01-14 11:40:05 +02:00

..

cmake

Merge mainline llama.cpp (#3)

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

include

Be able to re-quantize MS BitNet I2_S models (#169)

2025-01-10 18:18:04 +02:00

src

FA: allow bf16 for V-cache with any supported K-cache

2025-01-14 11:40:05 +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