llama.cpp
ggml: aarch64: implement SVE kernels for q8_0_q8_0, q4_0_q8_0 vector dot
#7433

Merged

ggml: aarch64: implement SVE kernels for q8_0_q8_0, q4_0_q8_0 vector dot #7433

ggerganov merged 2 commits into ggml-org:master from msy-kato:feat-sve-q4_0_q8_0-q8_0_q8_0

github-actions added build

github-actions added ggml

mofosyne added Review Complexity : High

Add SVE support for q4_0_q8_0 q8_0_q8_0

19531ac4

remove ifdef

d28bfd5e

msy-kato force pushed to d28bfd5e 1 year ago

ggerganov approved these changes on 2024-05-23

ggerganov merged faa0e697 into master 1 year ago

Reviewers

ggerganov

Assignees

No one assigned

Labels

build Review Complexity : High ggml

Milestone

No milestone