diff options
| author | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-05-29 08:00:59 +0300 |
|---|---|---|
| committer | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-06-22 12:02:49 +0300 |
| commit | 34befcaf6731a9a29bb5d7f3f2472e53c4151898 (patch) | |
| tree | 53a8dacb0527321f89b70d4694e3c74e53b6572c /examples/server/tests/features/environment.py | |
| parent | 4f53915dcb5037fa4c6fc45da2eab846ebc03d22 (diff) | |
iqk_mul_mat: AVX2 implementation for iq3_s
We get 3.14X for PP-512 (96.6 t/s). But for TG, we need to use
the original implementation in llama.cpp because the template is not able
to match the performance of the special-purpose implementation.
Diffstat (limited to 'examples/server/tests/features/environment.py')
0 files changed, 0 insertions, 0 deletions