llama.cpp

b213fce8 - metal : improve F32, F16 and BF16 mat-vec multiplication (#16057)

metal : improve F32, F16 and BF16 mat-vec multiplication (#16057) * metal : improve F32, F16 and BF16 mat-vec multiplication ggml-ci * metal : make the NSG a function constant in mul_mv kernels ggml-ci