Neural Network Compression Framework for enhanced OpenVINO™ inference

On-device AI across mobile, embedded and edge for PyTorch

OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference

A curated list for Efficient Large Language Models

Sparse Inferencing for transformer based LLMs

Run Generative AI models with simple C++/Python API and using OpenVINO Runtime

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Serve, optimize and scale PyTorch models in production

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Code repo for the paper "SpinQuant LLM quantization with learned rotations"

📚 Jupyter notebook tutorials for OpenVINO™

An AI Hedge Fund Team

Repository of Vision Transformer with Deformable Attention (CVPR2022) and DAT++: Spatially Dynamic Vision Transformerwith Deformable Attention

Neighborhood Attention Extension. Bringing attention to a neighborhood near you!

🚀 😏 Near Real Time CPU Face detection using deep learning

A Leaflet extension to distort or "rubber sheet" images

scikit-learn: machine learning in Python