diff options
| author | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2024-09-14 10:29:44 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-09-14 10:29:44 +0300 |
| commit | 43b934b19fec38219299b6e03bc9479143b593fd (patch) | |
| tree | a7b20097661f2287e4c8e4129d6f2f04e2305d34 /ggml/src/ggml-cuda/concat.cuh | |
| parent | ec1cbc8884533a68d740bf874531b3ef56da12c7 (diff) | |
Quantization mixes tweaks (#53)
* Some tweaks for i-quants
Improve Gemma2 PPL while reducing size
* Some tweaks for iq2_k and iq3_k
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'ggml/src/ggml-cuda/concat.cuh')
0 files changed, 0 insertions, 0 deletions