Python API

The NVIDIA TensorRT Python API enables developers in Python-based development environments and those looking to experiment with TensorRT to easily parse models (such as from ONNX) and generate and run PLAN files.

Interface - TensorRT Python API

See also

Using the Python API

Developer guide with end-to-end examples for building and running engines.

Migrating from TensorRT 8.x to 10.x

API migration guide for upgrading from TensorRT 8.x.

Optimizing Performance

Best practices for benchmarking and optimizing inference performance.

Troubleshooting

Common errors, FAQs, and debugging guidance.

C++ API

The C++ equivalent of this API reference.