llama.cpp
metal : optimize FA vec for large sequences and BS <= 8
#15566
Merged

metal : optimize FA vec for large sequences and BS <= 8 #15566

ggerganov merged 4 commits into master from gg/metal-fa-vec-opt-2
ggerganov
github-actions github-actions added examples
github-actions github-actions added ggml
github-actions github-actions added Apple Metal
Base automatically changed from gg/metal-mmid-opt to master 290 days ago
ggerganov metal : optmize FA vec for large heads and sequences
ef681866
ggerganov metal : adjust small-batch mul mv kernels
9c0fe8ed
ggerganov batched-bench : fix total speed computation
6d0b2222
ggerganov ggerganov force pushed from aed06a93 to 6d0b2222 290 days ago
ggerganov cont : add comments
a92bdd9a
ggerganov ggerganov merged b3964c1e into master 290 days ago
ggerganov ggerganov deleted the gg/metal-fa-vec-opt-2 branch 290 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
No reviews
Assignees
No one assigned
Labels
Milestone