Kawrakow 286ce324ba Much faster IQ2_KS quantization (#1672) ... * Much faster iq2_ks quantization * Slightly better * Make the iq2_ks slow quantization path a compile time option		2026-04-22 11:00:07 +02:00
..
cmake	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
include	Fused fused_rms_norm + fused_rms_norm + add (#1627)	2026-04-13 13:24:39 +02:00
src	Much faster IQ2_KS quantization (#1672)	2026-04-22 11:00:07 +02:00
.gitignore	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
CMakeLists.txt	Enable all CPU-backend FA supported quants by default (#1549)	2026-03-29 14:36:09 +02:00