llama.cpp

18a04f09 - hexagon: HMX flash-attention head_dim padding (support DK=DV=72) (#26539)

hexagon: HMX flash-attention head_dim padding (support DK=DV=72) (#26539) Allow HMX flash-attention to run with head_dim not a multiple of 64 (e.g. SigLIP head_dim=72), by operating on DK/DV rounded up to 64 with zero-filled tail lanes.