Skip to content

ggml-cuda: overlap the MoE shared expert on a separate stream#36

Merged
roberteg16 merged 3 commits into
gfx11from
rogarcia.cuda-multistream-shexp
Jul 15, 2026
Merged

ggml-cuda: overlap the MoE shared expert on a separate stream#36
roberteg16 merged 3 commits into
gfx11from
rogarcia.cuda-multistream-shexp