onnx/onnx-tensorrt

Health v2 · maintenance only

Adoption not part of the score

3228 stars · 548 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A C++ parser library and backend that converts ONNX models into TensorRT engines for high-performance GPU inference. It is maintained by NVIDIA and supports dynamic shapes and a wide range of ONNX operators.

Use cases

• run ONNX models with TensorRT for faster GPU inference
• convert ONNX models to TensorRT engines
• deploy deep learning models optimized for NVIDIA GPUs
• parse ONNX graphs into TensorRT networks
• benchmark ONNX model inference performance on NVIDIA hardware

When to choose

• you have ONNX models and want TensorRT-optimized inference on NVIDIA GPUs
• you need dynamic shapes and full-dimension network support
• you want an NVIDIA-maintained parser integrated with the TensorRT ecosystem

When to avoid

• you are not using NVIDIA GPUs or TensorRT
• your model uses ONNX operators not in the supported operator matrix
• you need a runtime-independent inference solution without a CUDA dependency

Facets

library · maturity active

parser machine-learning deep-learning llm-inference deep-learning machine-learning gpu-computing developer-tools cpp python windows onnx tensorrt nvidia model-inference model-conversion cuda inference-optimization linux gpu docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="onnx/onnx-tensorrt")