ggml-cpu: add x86 VNNI Q2_0 dot product -- 3x speed improvement for VNNI-compatible CPUs #26348
Michionlion
force pushed
from
4cc28ba1
to
915ffcfb
88 days ago
ggml-cpu: use VNNI for Q2_0 dot products
cdecb2fe
ggml-cpu: use VBMI for Q2_0 unpacking
9ff97f5a
CISC
commented
on 2026-10-21
CISC
requested a review
26 days ago
Update ggml/src/ggml-cpu/arch/x86/quants.c
58133076
am17an
approved these changes
on 2026-11-15
CISC
approved these changes
on 2026-11-15
CISC
merged
b54752df
into master 20 hours ago
Michionlion
deleted the fix/q2-0-x86-vnni branch 15 hours ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub