llama.cpp
Q4/Q8 Tiled Gemm Optimization.
#16999
Merged

Q4/Q8 Tiled Gemm Optimization. #16999

taronaeo merged 3 commits into ggml-org:master from shalinib-ibm:q8_q4_opt
shalinib-ibm
shalinib-ibm Q4/Q8 Tiled Gemm Optimization.
52fb79b9
shalinib-ibm shalinib-ibm requested a review from ggerganov ggerganov 314 days ago
shalinib-ibm shalinib-ibm requested a review from slaren slaren 314 days ago
shalinib-ibm
github-actions github-actions added ggml
shalinib-ibm
ggerganov
ggerganov commented on 2025-11-05
shalinib-ibm shalinib-ibm requested a review from ggerganov ggerganov 311 days ago
shalinib-ibm shalinib-ibm force pushed 286 days ago
shalinib-ibm shalinib-ibm force pushed 286 days ago
shalinib-ibm shalinib-ibm force pushed 286 days ago
shalinib-ibm shalinib-ibm force pushed 286 days ago
shalinib-ibm
shalinib-ibm
taronaeo
shalinib-ibm shalinib-ibm force pushed 285 days ago
shalinib-ibm
shalinib-ibm shalinib-ibm force pushed 285 days ago
ggerganov
ggerganov commented on 2025-12-03
shalinib-ibm Remove dymanic memory allocation during rutime
f72387fb
shalinib-ibm shalinib-ibm force pushed to f72387fb 285 days ago
ggerganov
ggerganov approved these changes on 2025-12-03
shalinib-ibm
taronaeo
taronaeo approved these changes on 2025-12-04
shalinib-ibm Update ggml/src/ggml-cpu/llamafile/sgemm-ppc.h
d7759323
shalinib-ibm
taronaeo
taronaeo taronaeo merged 3a0d1053 into master 283 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone