Skip to content
Commit 23266090 authored by Evie Wright's avatar Evie Wright Committed by Viet-Hoa Do
Browse files

Improve packing performance for quantized Int4 per-block 



Improves performance of ‘kai_rhs_pack_nxk_qsi4c32pnrx8_qsu4c32s1s0_neon’ by vectorizing row summation

Signed-off-by: Evie Wright's avatarEvie Wright <evie.wright@arm.com>

Approved-by: Anton Bondarenko's avatarAnton Bondarenko <anton.bondarenko@arm.com>
parent d18f620a
Pipeline #27629 passed with stages
in 8 minutes and 20 seconds
Hide whitespace changes
Inline Side-by-side
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment