llama.cpp
metal : improve F32, F16 and BF16 mat-vec multiplication
#16057

Merged

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

ggerganov merged 2 commits into master from gg/metal-mul-mv-opt-2

github-actions added ggml

github-actions added Apple Metal

metal : improve F32, F16 and BF16 mat-vec multiplication

320f0296

metal : make the NSG a function constant in mul_mv kernels

64c6dcbe

ggerganov force pushed from 5fbb4854 to 64c6dcbe 4 days ago

ggerganov merged b213fce8 into master 4 days ago

Reviewers

No reviews

Assignees

No one assigned

Labels

ggml Apple Metal

Milestone

No milestone