mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-04-29 02:41:47 +00:00
Quantize/dequantize, CUDA dequantize. PPL of LLaMA-3.1-8B is better than iq3_s and iq3_m.
723 KiB
723 KiB