Accelerate PyTorch model inferencing

ONNX Runtime can be used to accelerate PyTorch models inferencing.

Contents

• Convert model to ONNX
• Accelerate PyTorch model inferencing

Convert model to ONNX

• Basic PyTorch export through torch.onnx
• Super-resolution with ONNX Runtime
• Export PyTorch model with custom ops

Accelerate PyTorch model inferencing

• Accelerate reduced size BERT model through quantization

---