> ## Documentation Index
> Fetch the complete documentation index at: https://dragonwingdocs.qualcomm.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Export a PyTorch model to LiteRT

> Convert a PyTorch model to LiteRT format for deployment on Qualcomm Dragonwing IoT platforms using the PyTorch → ONNX → TensorFlow → LiteRT conversion path.

The recommended approach to convert a PyTorch model to LiteRT is a multi-step process:

**PyTorch → ONNX → TensorFlow (SavedModel) → LiteRT**

## Export the PyTorch model to ONNX

Use `torch.onnx.export` to convert the PyTorch model to ONNX format:

```python theme={null}
import torch

model.eval()
dummy_input = torch.randn(1, 3, 224, 224)
torch.onnx.export(
    model,
    dummy_input,
    "model.onnx",
    opset_version=13,
    input_names=["input"],
    output_names=["output"],
    do_constant_folding=True
)
```

## Convert ONNX to LiteRT

Once the model has been exported to ONNX, follow the instructions in [Export an ONNX model to LiteRT](../topic/export-onnx-model-to-litert) to complete the conversion to LiteRT format.