Aman Gupta 1a679828f3 cuda: top-k MoE should always fire (#28432)		2026-09-23 08:26:05 +03:00
..
cmake	CUDA: replace GGML_FA_ALL_QUANTS with GGML_FA_QUANTS, more control over what is compiled (#28079)	2026-09-09 12:50:08 +02:00
include	sycl : pinned memory use right device context instead of 0 (#28895)	2026-09-21 13:58:59 +03:00
src	cuda: top-k MoE should always fire (#28432)	2026-09-23 08:26:05 +03:00
.gitignore
CMakeLists.txt	ggml : bump version to 0.24.0 (ggml/1627)	2026-09-14 16:45:33 +03:00