0 0 0 C++

ggml : support AVX512VNNI (#6280)

This change causes some quants (e.g. Q4_0, Q8_0) to go faster on some
architectures (e.g. AMD Zen 4).

Justine Tunney committed 2y ago

7733f0c76081b2a69b5f8b192db2db7c43629d58

Parent: a32b77c

Committed by GitHub <noreply@github.com> on 3/25/2024, 5:39:56 AM