Q4/Q8 Tiled Gemm Optimization. #16999
Q4/Q8 Tiled Gemm Optimization.
52fb79b9
shalinib-ibm
force pushed
from
b663ced4
to
6cdfffd6
74 days ago
shalinib-ibm
force pushed
from
6cdfffd6
to
2c1171b3
74 days ago
shalinib-ibm
force pushed
from
2c1171b3
to
03539089
74 days ago
shalinib-ibm
force pushed
from
03539089
to
c33dffb9
74 days ago
shalinib-ibm
force pushed
from
c33dffb9
to
88a9f0b4
73 days ago
shalinib-ibm
force pushed
from
88a9f0b4
to
38077cda
73 days ago
Remove dymanic memory allocation during rutime
f72387fb
shalinib-ibm
force pushed
from
38077cda
to
f72387fb
73 days ago
ggerganov
approved these changes
on 2025-12-03
taronaeo
approved these changes
on 2025-12-04
Update ggml/src/ggml-cpu/llamafile/sgemm-ppc.h
d7759323
taronaeo
merged
3a0d1053
into master 71 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub