llama.cpp
ggml: aarch64: implement SVE kernels for q2_k_q8_k vector dot
#12064
Merged
Merged
ggml: aarch64: implement SVE kernels for q2_k_q8_k vector dot #12064
ggerganov
merged
5 commits into
ggml-org:master
from
Vithulep:Q2_k_SVE_Kernel
Added SVE Support for Q2_K Quantized Models
6cfedbe5
ggerganov
commented
on 2025-02-25
Use 4-space indentation in the switch cases
45bd8710
removed comments lines
417a6c97
ggerganov
commented
on 2025-02-27
Remove the loop Retain the curly bracess for better understanding of …
bfb0d1c1
Remove the comment like added for q3_k_q8_k kernel
dbe7af8b
ggerganov
approved these changes
on 2025-02-28
Login to write a write a comment.
Login via GitHub