Kawrakow d71e84bdc1 Use bf16 instead of fp16 block scales for q8_1 (#292) ... * WIP - not working * q8_0 without bells and wistles works * It works for q8_0 * Use bf16 instead of f16,int16 * q4_0_r8 * q5_0_r4 * q6_0_r4 * Also q4_1 and q5_1 * q8_0_r8 on avx2 --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>		2025-03-27 05:49:16 +01:00
..
cmake	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
include	Use bf16 instead of fp16 block scales for q8_1 (#292)	2025-03-27 05:49:16 +01:00
src	Use bf16 instead of fp16 block scales for q8_1 (#292)	2025-03-27 05:49:16 +01:00
.gitignore	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
CMakeLists.txt	Compile time option to use bf16 for qunts without MMQ kernels (#261)	2025-03-18 07:37:10 +01:00