]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 9c9e4fc)
ggml : refactor llamafile_sgemm PPC code (#14673)
authorshalinib-ibm <redacted>
Mon, 14 Jul 2025 13:16:42 +0000 (18:46 +0530)
committerGitHub <redacted>
Mon, 14 Jul 2025 13:16:42 +0000 (16:16 +0300)
commit55c509daf51d25bfaee9c8b8ce6abff103d4473b
tree23116d58f83884d5f8edc5130309b9f4a3054024tree
parent9c9e4fc6354fc811efa06a8eb7a86d3315cec9c8commit | diff
ggml : refactor llamafile_sgemm PPC code (#14673)

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 <redacted>
ggml/src/ggml-cpu/llamafile/sgemm.cpp diff | blob | history
Packaging of ggml-org/llama.cpp