diff options
| author | Justine Tunney <jtunney@gmail.com> | 2024-03-25 01:39:56 -0400 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-03-25 07:39:56 +0200 |
| commit | 7733f0c76081b2a69b5f8b192db2db7c43629d58 (patch) | |
| tree | 2a78e3e47fbd4d768d61f46d06c5c2815640595e /retrieval | |
| parent | a32b77c4b2c1808654d0b952f26c37d73d2e746b (diff) | |
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).
Diffstat (limited to 'retrieval')
0 files changed, 0 insertions, 0 deletions