Skip to content

ggml-cpu : PQ2_0 AVX-512 VNNI gemm on 8-row tiles (+30-40% prompt processing) - #256

Merged
bri-prism merged 1 commit into
PrismML-Eng:prismfrom
lenny76:cpu-pq2_0-gemm-8rows
Sep 25, 2026
Merged

bri-prism merged 1 commit into
PrismML-Eng:prismfrom
lenny76:cpu-pq2_0-gemm-8rows

ggml-cpu : PQ2_0 AVX-512 VNNI gemm on tiles of 8 activation rows

941e5c5
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

Annotations

1 warning
labeler
succeeded Sep 23, 2026 in 12s