Kawrakow 6be3a488d3 CUDA FA: faster TG when GQA is 16 and head size is 128		2026-06-15 11:46:02 +00:00
..
cmake	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
include	MLA TP -khad: ggml_dequant_hadamard fused op + wv_b/wk_b_pp Hadamard fold (#1852)	2026-05-21 07:29:15 +03:00
src	CUDA FA: faster TG when GQA is 16 and head size is 128	2026-06-15 11:46:02 +00:00
.gitignore	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
CMakeLists.txt	ggml : default GGML_WIN_VER to 0x0A00 (Windows 10) (#1755)	2026-05-08 13:23:04 +03:00