Short name describing what triggered the graph break
can’t handle functions not implemented in python
Values or code snippet captured at the break point
{fn}
Explanation of why the graph break was triggered
Dynamo can only handle functions defined in python
Hints on how to resolve the graph break
torch.compile regiontensor.is_inference() and torch.is_inference_mode_enabled() in your compile code. This is primarily used in conjunction with torch.inference_mode. Consider using torch.no_grad instead because torch.no_grad leads to same improvements as inference_mode when torch.compile is used.