Iwan Kawrakow e640a9ed88 iq2k: Try make_qx_quants for the scale ...

Slightly better for LLaMA-3.1, Gemma-2, slightly worse for
Qwen2.5

2024-10-12 17:54:46 +03:00

..

cmake

Merge mainline llama.cpp (#3)

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

include

New SOTA quantization: 4.25 bpw IQ4_KS (#83)

2024-10-09 12:54:40 +03:00

src

iq2k: Try make_qx_quants for the scale

2024-10-12 17:54:46 +03:00

.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