diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-05-15 08:15:08 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-05-15 08:15:08 +0300 |
| commit | 14ed9fb44da5212b4334277606e47c7040888a8a (patch) | |
| tree | cb6c72b821c35974128f38f485b1e739092b1f2c /src/llama.cpp | |
| parent | 0435b68e6d34b4987fee9d94a7221a146532ced1 (diff) | |
CUDA: quantized GEMM for for IQ2_KS, IQ2_K, IQ3_K (#418)
* MMQ for iq2_k
* This works
* MMQ for iq3_k
* MMQ for iq2_ks
* Fix iq2_ks
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'src/llama.cpp')
0 files changed, 0 insertions, 0 deletions