Kawrakow f30bcc1e17 iq2_k: CUDA dot product finally works ... Performance is pathetic: 140 t/s for LLaMA-3.1-8B vs 172 t/s for iq2_xs.		2024-08-01 09:38:06 +02:00
..
cmake	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
include	iq5_k: Basics	2024-08-01 09:38:06 +02:00
src	iq2_k: CUDA dot product finally works	2024-08-01 09:38:06 +02:00
.gitignore	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
CMakeLists.txt	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00