Files
ik_llama.cpp/ggml
Iwan Kawrakow bfef3dc584 iq3_k: AVX2 iqk_mul_mat
We get PP-512 = 196 t/s for LLaMA-3.1-8B on the Ryzen-5975WX.
2024-07-30 19:01:35 +03:00
..
2024-07-27 07:55:01 +02:00
2024-07-30 16:11:25 +03:00
2024-07-30 19:01:35 +03:00
2024-07-27 07:55:01 +02:00
2024-07-27 07:55:01 +02:00