ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-25 23:54:10 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
fc781beec006496ded0b672b3d9276e19b5c6ab1
ik_llama.cpp/include
History
Iwan Kawrakow e1b922d3f3 Adding q8_0_r4 
We get PP-512(LLaMA-3.1-8B) = 268 t/s on a Ryzen-7950X compared
to 175.6 t/s for Q8_0.
2024-12-02 19:22:04 +02:00
..
llama.h
Adding q8_0_r4
2024-12-02 19:22:04 +02:00