Animation engine for explanatory math videos

real time face swap and one-click video deepfake with only a single image

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Prefect is a workflow orchestration framework for building resilient data pipelines in Python.

Automate browser based workflows with AI

PyTorch implementations of Generative Adversarial Networks.

🦉 Data Versioning and ML Experiments

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

The absolute trainer to light up AI agents.

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discr…

Game Agent Framework. Helping you create AIs / Bots that learn to play any game you own!

A flexible framework of neural networks for deep learning

Pythonic task management & command execution.

FFCV: Fast Forward Computer Vision (and other ML workloads!)

Robotics Toolbox for Python

DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)

pytorch implementation for "PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation" https://arxiv.org/abs/1612.00593

A large-scale face dataset for face parsing, recognition, generation and editing.

Simple SDF mesh generation in Python

Toolbox of models, callbacks, and datasets for AI/ML researchers.

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

NVIDIA Kaolin Wisp is a PyTorch library powered by NVIDIA Kaolin Core to work with neural fields (including NeRFs, NGLOD, instant-ngp and VQAD).

A PyTorch toolbox for domain generalization, domain adaptation and semi-supervised learning.

Toolkit to run Python benchmarks

Photometric optimization code for creating the FLAME texture space and other applications