Kawrakow 7cd62a3eb2 More principled CUDA DSA (#2315) ... * DSA(CUDA): Apply softmax inverse sum at the end * Just do V*softmax(K*Q) in f32 precision		2026-08-15 09:41:21 +02:00
..
cmake	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
include	DS4: faster long-context TG (#2201)	2026-07-30 13:13:42 +03:00
src	More principled CUDA DSA (#2315)	2026-08-15 09:41:21 +02:00
.gitignore	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
CMakeLists.txt	Chunked experts (CPU) (#2202)	2026-07-30 13:16:02 +03:00