llama.cpp
CUDA: size routed MoE MMQ N-tiles from typical expert width on RDNA3 (recreated)
#28552

Merged

Commits

CUDA: size routed MoE MMQ N-tiles from typical expert width on RDNA3 (#24546)

pwilkin committed 4 days ago
CUDA: pick MMQ tile size against ncols_opt set on the host side

pwilkin committed 4 days ago

Loading