Accelerate PyTorch model inferencing

ONNX Runtime can be used to accelerate PyTorch models 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

BERT

• Accelerate BERT model on CPU
• Accelerate BERT model on GPU
• Accelerate reduced size BERT model through quantization

GPT-2

• Accelerate GPT2 on CPU
• Accelerate GPT2 (with one step search) on CPU

RESNET-50

• Accelerate RESNET-50 model on CPU, GPU, and OpenVINO

---