llama.cpp
metal: add the 128/96 flash attention kernels
#30209
Merged

metal: add the 128/96 flash attention kernels #30209

ServeurpersoCom
ServeurpersoCom metal: add the 128/96 flash attention kernels, accept every compiled …
dff01ea9
ServeurpersoCom ServeurpersoCom requested a review 40 days ago
github-actions github-actions added ggml
github-actions github-actions added Apple Metal
ServeurpersoCom ServeurpersoCom requested a review from ggerganov ggerganov 40 days ago
ggerganov
ggerganov approved these changes on 2026-10-09
ggerganov ggerganov added merge ready
CISC
CISC approved these changes on 2026-10-09
ServeurpersoCom ServeurpersoCom merged 1f8fa523 into master 40 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone