Skip to content

CUDA: batched+noncont MMQ, refactor bs>1 MoE code#13199

Merged
JohannesGaessler merged 1 commit intoggml-org:masterfrom
JohannesGaessler:cuda-moe-mmq-5
Apr 30, 2025
Merged

CUDA: batched+noncont MMQ, refactor bs>1 MoE code#13199
JohannesGaessler merged 1 commit intoggml-org:masterfrom
JohannesGaessler:cuda-moe-mmq-5

Commits

Commits on Apr 29, 2025