llama.cpp
AVX IQ Quants
#7845
Merged
Overview
Commits
16
Changes
View On GitHub

AVX IQ Quants #7845

ggerganov merged 16 commits into ggml-org:master from avx_iq
netrunnereve
netrunnereve initial iq4_xs
0fd5a1bb
github-actions github-actions added ggml
netrunnereve fix ci
b7e17070
netrunnereve Merge branch 'ggerganov:master' into avx_iq
2f373280
mofosyne mofosyne added Review Complexity : High
netrunnereve iq4_nl
8d1d112a
netrunnereve iq1_m
5ff64adf
netrunnereve iq1_s
75370d77
netrunnereve iq2_xxs
65765c9e
netrunnereve Merge branch 'ggerganov:master' into avx_iq
520361f3
netrunnereve iq3_xxs
59261865
netrunnereve iq2_s
dcfee065
netrunnereve iq2_xs
eccc609e
netrunnereve iq3_s before sllv
39e816e5
netrunnereve iq3_s
99f666c1
netrunnereve iq3_s small fix
b57187fb
netrunnereve netrunnereve marked this pull request as ready for review 2 years ago
netrunnereve
netrunnereve commented on 2024-06-16
ggerganov
ggerganov approved these changes on 2024-06-16
netrunnereve
slaren
netrunnereve iq3_s sllv can be safely replaced with sse multiply
29e2a96d
ggerganov
netrunnereve Merge branch 'ggerganov:master' into avx_iq
a055767a
ggerganov ggerganov merged 7d5e8777 into master 2 years ago
netrunnereve netrunnereve deleted the avx_iq branch 2 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Review Complexity : High ggml
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum