onnxruntime and onnx-tensorrt
ONNX Runtime is a general-purpose inference engine that supports multiple backends including TensorRT, while ONNX-TensorRT is specifically the TensorRT plugin/backend that enables ONNX Runtime to leverage NVIDIA's optimized inference engine—making them complements that work together rather than alternatives.
About onnxruntime
microsoft/onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Supports inference across diverse ML frameworks (PyTorch, TensorFlow, scikit-learn, XGBoost, LightGBM) through the ONNX standard, applying graph optimizations and hardware acceleration (CPUs, GPUs, NPUs) for optimal performance. Training acceleration targets PyTorch transformer models on multi-GPU setups with minimal code changes. Operates as a portable runtime layer abstracting hardware and framework differences across Windows, Linux, and macOS.
About onnx-tensorrt
onnx/onnx-tensorrt
ONNX-TensorRT: TensorRT backend for ONNX
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work