3 Commits

Author	SHA1	Message	Date
Kawrakow	28d3e63805	Various fused ops around expert selection (#840) ... * Fuse sigmoid+add+grouped_topk+get_rows (CPU) * Fix CPU + CUDA but CUDA is somehow not 100% correct as I get a slightly different PPL (lower!) * Minor * Fuse sigmoid+add+topk+get_rows (CUDA) * Fuse sigmoid+add+topk+get_rows (CPU) * Fuse topk+view+get_rows+reshape+softmax (CPU) * Fuse topk+view+get_rows+reshape+softmax (CUDA) * cpu: turn off the openai topk fusing for now Something is not right and I don't see the bug. On the CPU one doesn't gain much if anything, so not a big loss. * Also fuse sum_rows and div --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>	2025-10-19 19:02:46 +03:00
Kawrakow	747f411da5	Grouped expert routing (CUDA) (#838) ... * WIP * cuda: grouped top_k * This is very slightly better --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>	2025-10-18 07:22:35 +03:00
Kawrakow	154e0d75fc	Merge mainline llama.cpp (#3) ... * Merging mainline - WIP * Merging mainline - WIP AVX2 and CUDA appear to work. CUDA performance seems slightly (~1-2%) lower as it is so often the case with llama.cpp/ggml after some "improvements" have been made. * Merging mainline - fix Metal * Remove check --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>	2024-07-27 07:55:01 +02:00