llama.cpp
metal : add quantized FA support
#10149
Merged

metal : add quantized FA support #10149

ggerganov merged 8 commits into master from gg/metal-fa-q
ggerganov
ggerganov metal : add quantized FA (vec) support
6c484f35
ggerganov metal : add quantized FA (non-vec) support
e9565ccf
ggerganov metal : fix support check
13b87f21
ggerganov ggerganov force pushed to 13b87f21 1 year ago
ggerganov metal : clean-up
dd0d9ed1
ggerganov ggerganov marked this pull request as ready for review 1 year ago
ggerganov metal : clean-up (cont)
1e129611
slaren
ggerganov
ggerganov metal : fix shared memory calc + reduce smem + comments
d805404e
ggerganov ggerganov force pushed to d805404e 1 year ago
ggerganov metal : float-correctness
73f378df
ggerganov metal : minor [no ci]
9c13f952
slaren
slaren approved these changes on 2024-11-05
ggerganov ggerganov merged a1eaf6a9 into master 1 year ago
ggerganov ggerganov deleted the gg/metal-fa-q branch 1 year ago
ddh0
ggerganov

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone