Skip to content

Commit

Permalink
metal : add quantized FA support (ggerganov#10149)
Browse files Browse the repository at this point in the history 
* metal : add quantized FA (vec) support

ggml-ci

* metal : add quantized FA (non-vec) support

* metal : fix support check

ggml-ci

* metal : clean-up

* metal : clean-up (cont)

* metal : fix shared memory calc + reduce smem + comments

* metal : float-correctness

* metal : minor [no ci]
  • Loading branch information
@ggerganov @arthw
ggerganov authored and arthw committed Nov 18, 2024
1 parent 782b6c2 commit 465390d
Show file tree
Hide file tree
Showing 2 changed files with 568 additions and 192 deletions.
Loading

0 comments on commit 465390d

Please sign in to comment.