What is ONNX?

Open Neural Network Exchange: a common model format for exchanging models between frameworks and inference runtimes.

Field: AI Hardware & Software Stack

ONNX in the explanations

Questions that mention ONNX (2)

  1. Which describes ONNX?
  2. Why can inference runtimes such as TensorRT or ONNX Runtime run faster than using the training framework directly for inference?

Related terms

Computational graph Backpropagation Inference runtime GPU NPU (neural processing unit) AI compiler AI inference All-reduce Arithmetic intensity Attention mechanism

Back to the glossary