mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-03-02 10:00:07 +00:00
3a9926b932
Go to groups of 8 for iq3_kt. 2 x 8 = 16 bits for the magnitude plus 1 bpw for the sign. It goves a visible improvement in the PPL vs bpw plot, but that comes at the expense of much longer quantization time (7.5 minutes for LLaMA-3.1-8B on the Ryzen-5975WX). I also notices that the 3INST generator is not actually generating a Gaussian distribution. But going to a better generator means readjusting all the hyper-parameters, so leaving it for later.