Kawrakow fb4cff3458 iq3_k: Basics ... Quantize/dequantize, CUDA dequantize. PPL of LLaMA-3.1-8B is better than iq3_s and iq3_m.		2024-08-01 09:38:06 +02:00
..
llama.h	iq3_k: Basics	2024-08-01 09:38:06 +02:00