diff options
| author | Matvey Soloviev <blackhole89@gmail.com> | 2023-03-17 05:48:39 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-03-17 06:48:39 +0200 |
| commit | 904d2a8d6acd667c9633138d45a361d40fbf76d0 (patch) | |
| tree | 01494c1704cc5c7e5d95ae01edfae3a5df104300 /ggml.h | |
| parent | 721311070e31464ac12bef9a4444093eb3eaebf7 (diff) | |
Q4_1 quantization (#193)
* Add AVX2 version of ggml_vec_dot_q4_1
* Small optimisations to q4_1 dot product (@Const-me)
* Rearrange Q4_1 quantization to work for multipart models. (Fix #152)
* Fix ggml_vec_mad_q4_1 too
* Fix non-vectorised q4_1 vec mul
Diffstat (limited to 'ggml.h')
0 files changed, 0 insertions, 0 deletions