Skip to content
ai

ONNX

Open Neural Network Exchange

Definition

ONNX is an open format for representing machine learning models that enables interoperability between training frameworks (PyTorch, TensorFlow) and inference runtimes (ONNX Runtime, TensorRT). Models exported to ONNX can be optimized and deployed across diverse hardware targets including CPUs, GPUs, and edge devices without framework-specific dependencies.

Can this ship? Are we exposed? Can you prove it?

Every CISO is asking these three questions. We answer them with facts, not guesses, from repository to runtime.