A high-performance YOLO inference library written in Rust with ONNX Runtime support. Provides a fast, safe, and efficient interface for running YOLO models with an API designed to match the Ultralytics Python package.
Features:
- Rust-based implementation for maximum performance
- ONNX Runtime backend for cross-platform inference
- Python bindings for seamless integration
- GPU acceleration support (CUDA, TensorRT)