Python API

The NVIDIA TensorRT-RTX Python API enables developers in Python-based development environments to parse models (for example, from ONNX) and generate and run TensorRT-RTX engine files. This API suits developers who want to experiment with TensorRT-RTX.

Interface - TensorRT-RTX Python API

See also

Building and running an engine

End-to-end walkthrough of common Python API usage patterns.

Working with dynamic shapes

Configuring optimization profiles and dynamic input dimensions.

Using runtime caching

Saving and loading the runtime cache for faster startups.

Operators reference

Full list of supported TensorRT-RTX operators.