Fast inference engine for Transformer models

oneAPI Deep Neural Network Library (oneDNN)

Samples for Intel® oneAPI Toolkits

High-performance Spiking Neural Networks Library Written From Scratch with C++ and Python Interfaces.

LLM inference engine built with SYCL + oneDNN

OneDNN Verbose Toolkit

Deep Learning model with OneDNN

Graiphic Toolkits for LabVIEW provide advanced AI, GPU, and graph-oriented computing capabilities directly inside LabVIEW. Built on ONNX Runtime, they enable seamless integration of SOTA, Accelerator, and Deep Learning Toolkit for high-performance execution across CPUs, GPUs, and edge devices.

Bazel rules for Intel Open Image Denoise

Repository to build python image, based on ubuntu and CUDA

edge-optimized neural style transfer using Intel oneDNN

low-level Rust bindings to the oneDNN C API

Source of oneAPI Deep Neural Network Library (oneDNN)

high-level Rust bindings to the oneDNN C api

A header-only library for accelerating vector searches using Intel AMX (Advanced Matrix Extensions)

Demonstrate remote command and control techniques using chat platforms for security training and threat simulation.

C++ "more than perfect" library is a deep learning playground using Intel's oneDNN and SYCL.