Files
ik_llama.cpp/iqk_mul_mat.cpp
Kawrakow 0fe0d54be6 iqk_mul_mat: add IQ4_NL also on NEON
PPL seems somewhat higher? For llama-v2-7B iwe are still
~0.04 higher compared to hat we expect after ~30 batches.
2024-06-22 12:02:52 +03:00

196 KiB