microsoft/onnxruntime

ONNX Runtime is a cross-platform, high-performance machine learning accelerator designed for both inference and training. It supports models from deep learning frameworks like PyTorch and TensorFlow, as well as classical machine learning libraries such as scikit-learn, and is compatible with various hardware, drivers, and operating systems. This project is ideal for developers and data scientists seeking to optimize ML model performance and accelerate training on multi-node NVIDIA GPUs.