llama.cpp
Q5: Slightly faster AVX2 implementation
#1197
Merged
Overview
Commits
1
Changes
View On GitHub

Q5: Slightly faster AVX2 implementation #1197

ggerganov merged 1 commit into ggml-org:master from sw:q5-avx
sw
sw Q5: Slightly faster AVX2 implementation
8569b35b
ggerganov
ggerganov approved these changes on 2023-04-26
ggerganov ggerganov merged 0b2da205 into master 2 years ago
sw sw deleted the q5-avx branch 2 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum