diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-04-01 10:31:06 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-04-01 10:31:06 +0200 |
| commit | 190e7866db1d87a5da8b2d2b8d6619092b2ec72c (patch) | |
| tree | 56bb72d89bdf4144d0e8a1fc11572f7928661da6 /ggml/src/ggml-impl.h | |
| parent | b07a337bfe033f00fdad3ad0e809eecd8f5f2d2c (diff) | |
Quantization improvements (2) (#302)
* iq3_k: slightly better quantization
Not much of a difference for most models, but this change
avoids what it looks like a catastrophic failure for DeepSeek-Lite
(PPL is now 7.041 vs 7.314 on main).
* Small improvement for type-1 quants
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'ggml/src/ggml-impl.h')
0 files changed, 0 insertions, 0 deletions