This repository was archived by the owner on Feb 7, 2025. It is now read-only.
This repository was archived by the owner on Feb 7, 2025. It is now read-only.
Add torch.no_grad() decorator to sampling methods #243
Metadata
Metadata
Assignees
Labels
No labels
Type
Fields
Give feedbackNo fields configured for issues without a type.
In the inferers, it is not necessary to use the gradients during the sampling. Suggest to use the same approach used for get_likelihood and add @torch.no_grad() decorator to the function