llama.cpp
arm64: optimize q4_k_q8_k kernel with i8mm
#13886
Merged

arm64: optimize q4_k_q8_k kernel with i8mm #13886

ggerganov merged 1 commit into ggml-org:master from cyb70289:q4k
cyb70289
cyb70289 arm64: optimize q4_k_q8_k kernel with i8mm
a85e6bcf
cyb70289 cyb70289 force pushed to a85e6bcf 1 year ago
github-actions github-actions added ggml
ggerganov
ggerganov approved these changes on 2025-05-29
ggerganov ggerganov merged 54a2c7a8 into master 1 year ago
cyb70289 cyb70289 deleted the q4k branch 1 year ago
hariharans29
hariharans29 commented on 2025-08-07
Nor7th
cyb70289

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone