ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-29 10:51:51 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
8ccceff4e96e89a8d3c87f62a7ca8cb97878f95d
ik_llama.cpp/github-data/pull_requests/144 - Slightly faster IQ4_K_R4 on AVX2_Zen4.md
Thomas 0451f10a42 Add GitHub data: filename sanitization (#640)
2025-07-23 13:31:53 +02:00

366 B
Raw Blame History

🔀 #144 - Slightly faster IQ4_K_R4 on AVX2/Zen4

Author ikawrakow
State ❌ Closed
Created 2024-12-16
Updated 2024-12-16

Description

We get PP-512(LLaMA-3.1-8B) = 251 t/s (Ryzen-7950X) or 249 t/s (Ryzen-5975WX), up from 232/227 t/s.

Reference in New Issue View Git Blame Copy Permalink