Skip to content

ggml-blas: refactor BLAS backend #18027

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
taronaeo wants to merge 15 commits into
base: master
Choose a base branch
from
+1,117 −223
Draft

ggml-blas: refactor BLAS backend #18027

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
f682374
ggml-blas: initial mmid impl
taronaeo Dec 11, 2025
19c8ec9
ggml-blas: fully working mmid
taronaeo Dec 11, 2025
1926e07
ggml-blas: code clean up
taronaeo Dec 11, 2025
61ee32d
tests: set tensor usage as weight for weight tensors
taronaeo Dec 14, 2025
9a14a09
ggml: rewrite ggml-blas
taronaeo Dec 14, 2025
aae6d1e
ggml-blas: fix invalid data access
taronaeo Dec 14, 2025
717531b
ggml-blas: add note
taronaeo Dec 14, 2025
4470579
ggml-blas: fix ne
taronaeo Dec 14, 2025
6dff031
ggml-blas: force dequant routine to use max logical cores
taronaeo Dec 14, 2025
e481be6
ggml-blas: move global blas n threads to set_n_threads
taronaeo Dec 14, 2025
7998d08
ggml-blas: bring back openmp
taronaeo Dec 14, 2025
75e506f
ggml-blas: clean up code
taronaeo Dec 14, 2025
10ce5e0
ggml-blas: more code formatting
taronaeo Dec 14, 2025
46dea5d
CODEOWNERS: add @taronaeo to blas backend [no ci]
taronaeo Dec 14, 2025
04ed19b
ggml-blas: further cleanup
taronaeo Dec 14, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions CODEOWNERS
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,7 @@
/ggml/cmake/ @ggerganov
/ggml/include/ @ggerganov
/ggml/src/ggml-common.h @ggerganov
/ggml/src/ggml-blas/ @taronaeo
/ggml/src/ggml-cpu/ @ggerganov
/ggml/src/ggml-cpu/spacemit/ @alex-spacemit
/ggml/src/ggml-cuda/fattn* @JohannesGaessler
Expand Down
Loading
Loading