b2524
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).
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).