ort
ort copied to clipboard
Accelerate PyTorch models with ONNX Runtime
I wanted to test maxpool op using a training script. From the inputs given in a previous issue, I had disabled maxpool to AtenOp bindings so that the resulting graph...
I have tried using ort in training transformer . But it seems that no speed up is got. I wonder whether i have missed someting in configuration.
Do you know if ort works with Pytorch lightning? I am trying it but I am getting: raise new_exception(raised_exception) from raised_exception onnxruntime.training.ortmodule._fallback.ORTModuleTorchModelException: ORTModule does not support adding modules to it....