AI Dynamics

Global AI News Aggregator

LoRA vs Adapter: Performance and Memory Usage Comparison

By

@rasbt

–

Good question! On average: LoRA: 21.33 tokens/sec; Memory used: 14.59 GB
Adapter: 26.22 tokens/sec; Memory used: 14.59 GB

→ View original post on X — @rasbt,

Commentaires

Leave a Reply

Your email address will not be published. Required fields are marked *

MORE ARTICLES