search

lucidrains / audiolm-pytorch

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
MIT License
2.39k stars 255 forks source link

Change torch.no_grad() to torch.inference_mode() #206

Closed LWprogramming closed 1 year ago

LWprogramming commented 1 year ago

See https://discuss.pytorch.org/t/pytorch-torch-no-grad-vs-torch-inference-mode/134099?u=timgianitsos which exists as of torch version 1.9

lucidrains commented 1 year ago

@LWprogramming agree!