llama.cpp
ggml: aarch64: implement SVE kernels for q4_K_q8_K vector dot
#11227
Merged
Merged
ggml: aarch64: implement SVE kernels for q4_K_q8_K vector dot #11227
ggerganov
merged
2 commits into
ggml-org:master
from
fj-y-saito:feat-sve-q4_K_q8_K
Add SVE support for q4_K_q8_K
5f98b7c3
ggerganov
approved these changes
on 2025-01-14
Update ggml/src/ggml-cpu/ggml-cpu-quants.c
964f8117
Login to write a write a comment.
Login via GitHub