diff options
| author | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-06-18 11:11:46 +0200 |
|---|---|---|
| committer | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-06-22 12:02:52 +0300 |
| commit | 2998ca9b14d9b2d4b184cf6d923cea8b07a6320a (patch) | |
| tree | fda5ae03fc580d72bac6637ffc7d60c7c9988432 /ggml-cuda/mmvq.cuh | |
| parent | 8c6276f6a1c6d9d82b5f0114d838fcc4f277234a (diff) | |
Bitnet(2.25 bpw): NEON
We get PP-512 = 192 t/s, TG-128 = 72 t/s
Diffstat (limited to 'ggml-cuda/mmvq.cuh')
0 files changed, 0 insertions, 0 deletions