Iwan Kawrakow e9bb1a54ee iq2_bn: improve AVX2 implementation ...

We now get PP-512 = 753 t/s up from 680 t/s.

2024-09-09 12:38:36 +03:00

..

cmake

Merge mainline llama.cpp (#3)

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

include

Adding iq1_tn - 1.6875 bpw for TriLM ternary models

2024-09-08 17:56:15 +03:00

src

iq2_bn: improve AVX2 implementation

2024-09-09 12:38:36 +03:00

.gitignore

Merge mainline llama.cpp (#3)

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

CMakeLists.txt

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00