mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-04-28 18:32:04 +00:00
Quantize/dequantize, CUDA dequantize. PPL of LLaMA-3.1-8B is better than iq3_s and iq3_m.
56 KiB
56 KiB