llama.cpp
metal : add tensor API flash attention kernel for F16 KV
#29570
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
4
Changes
View On
GitHub
metal : add tensor API flash attention kernel for F16 KV
#29570
ggerganov
merged 4 commits into
ggml-org:master
from
ethanhq:fa-tensor-api
metal : add tensor API flash attention kernel for F16 KV
18027f9d
ethanhq
requested a review
from
ggerganov
51 days ago
ethanhq
requested a review
51 days ago
github-actions
added
testing
github-actions
added
ggml
github-actions
added
Apple Metal
ggerganov
assigned
ggerganov
51 days ago
cont : add tensor FA kernels for DK=DV=512 and DK=576, DV=512
2733cfc9
cont : support attention sinks, ALiBi and logit softcap in the tensor…
2a83277e
cont : add tensor FA kernel for DK=192, DV=128
7f0d4d5e
jhen0409
approved these changes on 2026-09-30
ggerganov
approved these changes on 2026-10-02
ggerganov
merged
926862e5
into master
47 days ago
ggerganov
added
highlight
Login to write a write a comment.
Login via GitHub
Reviewers
ggerganov
jhen0409
Assignees
ggerganov
Labels
testing
ggml
Apple Metal
highlight
Milestone
No milestone
Login to write a write a comment.
Login via GitHub