ggml : refactor llamafile_sgemm PPC code (llama/14673)

Browse Source

Remove un-necessary templates from class definition and packing functions
Reduce deeply nested conditionals, if-else switching in mnapck function
Replace repetitive code with inline functions in Packing functions

2 ~ 7% improvement in Q8 Model
15 ~ 50% improvement in Q4 Model

Signed-off-by: Shalini Salomi Bodapati <Shalini.Salomi.Bodapati@ibm.com>

...

This commit is contained in:

shalinib-ibm

2025-07-14 18:46:42 +05:30

committed by Georgi Gerganov

parent ebb0e9d0ed

commit ded2e3cf6d

1 changed files with 340 additions and 1091 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

1431

ggml/src/ggml-cpu/llamafile/sgemm.cpp

File diff suppressed because it is too large Load Diff