Giters

kuprel / min-dalle

min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Any plans to supporting multi-GPU inferencing and training?

Shawn-Shan opened this issue · comments

commented

First, I really really appreciate the effort on porting this to pytorch (saving me a lot of time learning JAX). But is there any plans to support multi-GPU inferencing and fine-tuning? It would really be helpful given how much compute these models need. Thanks!