diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-10-16 14:13:03 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-10-16 14:13:03 +0300 |
| commit | 993ca95e9e3108f0352fa2a3384cab0775c7f7c1 (patch) | |
| tree | 5fd1e52f04382acf4e3ed1226e4fe8084c06dd1e /examples/quantize-stats/quantize-stats.cpp | |
| parent | ff23008ed4f73c2c7091e7333495e36c268156bc (diff) | |
iq4_ks: faster dot product on Metal (#90)
TG-128(LLaMA-3.1-8B) goes to 52.5 t/s up from 48.4 t/s.
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'examples/quantize-stats/quantize-stats.cpp')
0 files changed, 0 insertions, 0 deletions