CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.

A playable, color-customizable twist on Pong Wars. Play/pause, reset, live theme picker, all in one file.

A collection of GTSAM factors and optimizers for point cloud SLAM

Smart coding template for Python

An implementation of the CSM(Conversation Speech Model) for Apple Silicon using MLX.

A generative world for general-purpose robotics & embodied AI learning.

[ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

A playbook for systematically maximizing the performance of deep learning models.

Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.

MLX: An array framework for Apple silicon

Inference code for Llama models

Intermediate Graphics Library (IGL) is a cross-platform library that commands the GPU. It provides a single low-level cross-platform interface on top of various graphics APIs (e.g. OpenGL, Metal an…

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

Fast Segment Anything

Examples and guides for using the OpenAI API

Soccer playing robot representing Canada from University of Toronto

Native Ethernet library for Teensy 4.1

Roadmap to become a Visual-SLAM developer in 2026

The GUDHI library is a generic open source C++ library, with a Python interface, for Topological Data Analysis (TDA) and Higher Dimensional Geometry Understanding.

A set of jupyter notebooks for the practice of TDA with the python Gudhi library together with popular machine learning and data sciences libraries.

A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8…

Stable Diffusion with Core ML on Apple Silicon

Robust Speech Recognition via Large-Scale Weak Supervision

Object detection with multi-level representations generated from deep high-resolution representation learning (HRNetV2h). This is an official implementation for our TPAMI paper "Deep High-Resolutio…

Code repository for paper Instance Segmentation for Autonomous Log Grasping in Forestry Operations

Explicitly incorporating spatial information to recurrent networks for agriculture

Deep Learning tools and applications for NVIDIA AGX platforms.

Neural Networks: Zero to Hero

High performance motor control