This document is relevant for: Inf1

nosearch:

ONNX FAQ (archived)

Warning

This FAQ is archived and is no longer maintained. It recommends torch_neuron.trace, which is part of the retired torch-neuron (Inf1) framework. For current PyTorch support, see TorchNeuron.

Can I use ONNX models with Neuron ? If not, what should I do?

AWS Neuron does not directly support compilation of models in the ONNX file format. The recommended way to compile a model that is in the ONNX file format is to first convert the model to PyTorch using a publicly available tool like onnx2pytorch . Once the ONNX model is converted to PyTorch, it can then be compiled with the torch_neuron.trace() function to produce a model that can run on Neuron.

This document is relevant for: Inf1