ONNX Runtime is a performance-focused complete scoring engine for Open Neural Network Exchange (ONNX) models, with an open extensible architecture to continually address the latest developments in AI and Deep Learning. ONNX Runtime stays up to date with the ONNX standard with complete implementation of all ONNX operators, and supports all ONNX releases (1.2+) with both future and backwards compatibility. Please refer to this page for ONNX opset compatibility details.

ONNX Runtime is a performance-focused complete scoring engine for Open Neural Network Exchange (ONNX) models, with an open extensible architecture to continually address the latest developments in AI and Deep Learning. ONNX Runtime stays up to date with the ONNX standard with complete implementation of all ONNX operators, and supports all ONNX releases (1.2+) with both future and backwards compatibility. Please refer to this page for ONNX opset compatibility details.

libopenraw is an ongoing project to provide a free software implementation for camera RAW files decoding. One of the main reason is that dcraw is not suited for easy integration into applications, and there is a need for an easy to use API to build free software digital image processing application.

The NVIDIA binary driver provides optimized hardware acceleration of OpenGL/GLX/EGL/GLES applications via a direct-rendering X Server for graphics cards using NVIDIA chip sets.

Provides librnd specific dialog boxes (e.g. fontsel) and top window GUI elements.

This library implements the basic OPRF (ristretto255, SHA-512) variant from the "Oblivious Pseudorandom Functions using Prime-Order Groups" Draft from the IRTF Crypto Forum Research Group (https://github.com/cfrg/draft-irtf-cfrg-voprf/). Additionally it implements a threshold OPRF based on "TOPPSS: Cost-minimal Password-Protected Secret Sharing based on Threshold OPRF" by Krawczyk et al (https://ia.cr/2017/363).