In addition, for now, let's make sure to add a warning when a user runs predict with accelerators > 1:
“warning: you’re running .predict with devices > 1. predictions across multiple {self.accelerator}s is not yet supported.”
# prints like
“warning: you’re running .predict with devices > 1. predictions across multiple GPUs is not yet supported.”
We need to support distributed inference...
In addition, for now, let's make sure to add a warning when a user runs predict with accelerators > 1:
so that user could do: https://github.com/Lightning-AI/lightning/pull/15149#issuecomment-1282360328
cc @justusschock @kaushikb11 @awaelchli @akihironitta @rohitgr7 @Borda @carmocca