Will you support multi-GPU tensor parallelism in the future?
I run this model on cloud server so I can choose to rent multi-GPU,it takes more than 1 hour to generate a video in 1 GPU and it doesn't get faster when I use more GPU.So I hope that you can support multi-GPU tensor parallelism in the future.
We've fixed bugs, please update.
I have the same thing. Out of 15 minutes for 1xGPU I have 25 minutes for 2xGPU. Additionally, the video is of lower quality and is looped twice. Used fresh main branch
I miss that scale changed, but still same time on 2x GPU and looped video twice.
I have the same thing. Out of 15 minutes for 1xGPU I have 25 minutes for 2xGPU. Additionally, the video is of lower quality and is looped twice. Used fresh main branch
We have fixed it, please update!