llama.cpp

3d7ebf63 - Vulkan Mixture of Experts (MoE) support (#7628)

Vulkan Mixture of Experts (MoE) support (#7628) * Finish Vulkan mul_mat_id implementation * Add Vulkan sum_rows and div ops * Fix MUL_MAT_ID matrix matrix shader * Fix MUL_MAT_ID matrix vector shader dispatch size * Fix MUL_MAT_ID matrix vector shader and dispatch code * Update Vulkan CPU offload for MUL_MAT_ID * Fix crash when using split mode none and setting a main GPU