A high-throughput and memory-efficient inference and serving engine for LLMs

Let us control diffusion models!

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

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

The Modular Platform (includes MAX & Mojo)

MLX: An array framework for Apple silicon

Fast and memory-efficient exact attention

Mamba SSM architecture

Lightweight static analysis for many languages. Find bug variants with patterns that look like source code.

Code release for NeRF (Neural Radiance Fields)

More relighting!

Examples in the MLX framework

Unified framework for robot learning built on NVIDIA Isaac Sim

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

Speech To Speech: an effort for an open-sourced and modular GPT4-o

JAX-based neural network library

CUDA Python: Performance meets Productivity

AcadHomepage: A Modern and Responsive Academic Personal Homepage

Verified Rust for low-level systems code

Training PyTorch models with differential privacy

Diagram as Code Tool Written in Rust with Draggable Editing

Chai-1, SOTA model for biomolecular structure prediction

Time zone database and code

A framework for Privacy Preserving Machine Learning

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Production-grade 3D gaussian splatting with CPU/GPU support for Windows, Mac and Linux 🚀

Fast, Flexible and Portable Structured Generation

Buttercup finds and patches software vulnerabilities

MetaDrive: Lightweight driving simulator for everyone