mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-04-26 09:29:27 +00:00
334 B
334 B
🔀 #128 - Faster IQ4_XS_R4 on Zen4
| Author | ikawrakow |
|---|---|
| State | ❌ Closed |
| Created | 2024-12-08 |
| Updated | 2024-12-08 |
Description
We now get PP-512(LLaMA-3.1-8B) = 254 t/s on a Ryzen-7950X CPU, up from 224 t/s.