diff options
author | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-07-15 13:46:07 +0300 |
---|---|---|
committer | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-07-15 13:46:07 +0300 |
commit | e4dc3babb59da45a60dd3fdf1a9a45e1e9390f37 (patch) | |
tree | 34c88b410dcfb041977e6ee827a4ca194c1abe23 /ggml-cuda | |
parent | a4bbd36905b9ac2c2a5f1ded6d1e29fbd5cf4020 (diff) |
iq1bn(no lookup): somewhat better
We now have for Bitnet-3B:
| threads | test | t/s |
| ------: | ------------: | ---------------: |
| 16 | pp512 | 308.97 ± 1.89 |
| 16 | tg128 | 58.80 ± 0.07 |
| 8 | tg128 | 49.79 ± 1.23 |
| 4 | tg128 | 28.85 ± 0.02 |
| 2 | tg128 | 15.39 ± 0.01 |
Diffstat (limited to 'ggml-cuda')
0 files changed, 0 insertions, 0 deletions