Supported Model Formats

Melange supports three model formats for on-device deployment. Choose the format that best matches your training framework.

Supported Formats

Choosing a Format

• PyTorch users: Use PyTorch Exported Program (.pt2). Requires PyTorch >= 2.1.0.
• TensorFlow / Keras / scikit-learn users: Convert to ONNX format.
• Legacy PyTorch projects: TorchScript (.pt) is still supported but will be removed in a future release.

Input Requirements

Regardless of format, all models require:

1. NumPy input files (.npy): Sample inputs that define the expected tensor shapes and data types.
2. Fixed input shapes: NPU compilation hard-codes input shapes for maximum throughput. Even if your original model supports dynamic sizes, the Melange-compiled model will accept only the exact shape provided during upload.

Verifying Input Order and Shapes

Melange compiles your model into a static hardware graph. This means consistent input order and input shapes are mandatory for execution.

Why Order Matters

The internal computation graph expects data in specific slots (e.g., input_zero at index 0, input_one at index 1). If you swap them during upload or inference, the model will produce garbage results or crash.

Inspecting with Netron

We recommend using Netron to visualize your model's input signature:

1. Open your model (.pt2, .onnx, or .pt) in Netron.
2. Locate the Input Nodes at the top of the graph.
3. Note the vertical order: the top-most input is Index 0, the next is Index 1, and so on.

---

Next Steps

• PyTorch Export: Export PyTorch models to .pt2 or .pt
• ONNX Models: Convert TensorFlow, Keras, and scikit-learn models
• Pre-built Models: Use ready-to-run models from Dashboard or Hugging Face