llama.cpp
metal : use FA-vec kernel up to batch size 20
#13496
Merged

metal : use FA-vec kernel up to batch size 20 #13496

ggerganov merged 3 commits into master from gg/metal-fa-vec-bs20
ggerganov
ggerganov batched-bench : fix pp batch contents
f078c798
ggerganov metal : optimize multi-sequence FA vec kernel
fdfc7de7
ggerganov metal : use FA-vec kernel up to batch size 20
78d70223
github-actions github-actions added ggml
github-actions github-actions added Apple Metal
Base automatically changed from gg/metal-fa-vec-mask-opt to master 178 days ago
ggerganov ggerganov merged f0995d28 into master 178 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
No reviews
Assignees
No one assigned
Labels
Milestone