ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Scoreboard for ONNX Backend Compatibility

🍷 Gracefully claim weekly free games and monthly content from Epic Store.

ONNX neural network inference engine

Open standard for machine learning interoperability

Java version of LangChain

Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.

Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

A Rust library integrated with ONNXRuntime, providing a collection of Computer Vison and Vision-Language models.

🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools

Neural Network Compression Framework for enhanced OpenVINO™ inference

Speech-to-text, text-to-speech, and speaker recongition using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 servers, websocket server/client, C/C++, Python, Kotlin, C#, Go, NodeJS, Java, Swift

Machine learning framework for both deep learning and traditional algorithms

A model compilation solution for various hardware

Efficient CPU/GPU/Vulkan ML Runtimes for VapourSynth (with built-in support for waifu2x, DPIR, RealESRGANv2/v3, Real-CUGAN, RIFE, SCUNet and more!)

Visualizer for neural network, deep learning and machine learning models

Export Segment Anything Models to ONNX

A type-safe, lightweight, modern, and performant binding Java binding of Microsoft's ONNX Runtime

Represent trained machine learning models as Pyomo optimization formulations