Files
ik_llama.cpp/ggml
Kawrakow 0c1d7383a5 iq2_k: better CUDA dot product
Almost on par with iq2_xs (168 t/s vs 172 t/s).
2024-08-01 09:38:06 +02:00
..
2024-07-27 07:55:01 +02:00
2024-08-01 09:38:06 +02:00
2024-08-01 09:38:06 +02:00
2024-07-27 07:55:01 +02:00
2024-07-27 07:55:01 +02:00