Multi GPU support ?

[hekmon]

The DAT model can be very heavy, even on a 3090, when a lots of images needs to be upscalled. Is there any chance you could implements multi-gpu in order for a second card to be active ?

I have no clue how to use torch multi-gpu myself.

Thanks.

[Kiteretsu77]

I used pytorch lightning to implement the multi-gpu before, instead of torch multi-gpu you said. The challenge would be lied on the sync for the degradation model. However, I have to say that I also only use one 24 GB memory GPU to train the DAT model. You need to decrease the batch size such that it is trainable.