llama.cpp
A faster version for Q4_1 x Q8_0 dot products
#1083
Merged

A faster version for Q4_1 x Q8_0 dot products #1083

ggerganov merged 2 commits into master from faster_q41_q80_dot_product
ikawrakow
ikawrakow ikawrakow requested a review from ggerganov ggerganov 2 years ago
ikawrakow ikawrakow added performance
ggerganov
ggerganov ggerganov added high priority
sw
pubby
A faster version for Q4_1 x Q8_0 dot products
66a865b8
Cleaning up
c542d5a7
ikawrakow ikawrakow force pushed from b51101ad to c542d5a7 2 years ago
ggerganov
ggerganov approved these changes on 2023-04-21
ggerganov ggerganov merged 1bfc153e into master 2 years ago
ggerganov ggerganov deleted the faster_q41_q80_dot_product branch 2 years ago
ggerganov ggerganov assigned ikawrakow ikawrakow 2 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
Labels
Milestone