vector-quantize-pytorch icon indicating copy to clipboard operation
vector-quantize-pytorch copied to clipboard

Published 20 hours ago • verified publisher icon lucidrains

Support half precision for VQ and FSQ

Open JunityZhan opened this issue 7 months ago • 6 comments

Hi, I notice it is not support other preicsion. I made this tiny change and I tried a simple sample and it works on fp16 and bf16. I noticed that there is a x = x.float(), I just comment it. I don't know if it is necessary. In my experiment, it just works fine, we can choose any precision into it.

JunityZhan avatar Jun 30 '24 15:06 JunityZhan