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
This helps machine learning engineers and data scientists deploy and train their models more efficiently. It takes trained machine learning models from frameworks like PyTorch or TensorFlow, or classical ML libraries, and outputs faster predictions or quicker training times. It's for anyone building or running ML models who needs to optimize performance across different hardware.
About onnx-tensorrt
onnx/onnx-tensorrt
ONNX-TensorRT: TensorRT backend for ONNX
This project helps deep learning engineers and AI practitioners take ONNX neural network models and run them efficiently on NVIDIA GPUs using TensorRT. It takes an ONNX model as input and produces an optimized TensorRT engine that executes deep learning inferences at high speed. This tool is for those who need to deploy and accelerate AI models in production environments.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work