Kawrakow 3b5da96073 Metal: much faster MoE prompt processing (#307) ... * MoE improvements on Metal This version beats mainline, there are things I don't understand: * Mianline has effectively gone to GEMV for MUL_MAT_ID. We can do the same, but we are 30% slower. Why? * Using actual GEMM, we beat mainline with ubtach size of 128. But then performance degrades. Why? * Some cleanup * Much better --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>		2025-04-03 07:15:49 +02:00
..
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	Metal: much faster MoE prompt processing (#307)	2025-04-03 07:15:49 +02:00
.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