Anthropic's original performance take-home, now open for you to try!

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

iOS Objective-C headers as derived from runtime introspection

Fast GPT-2 inference written in Fortran

The ultimate cross-platform, bash-like shell

SEED-Voken: A Series of Powerful Visual Tokenizers

Watch Slippi replays in the browser

[ICLR 2025] CatVTON is a simple and efficient virtual try-on diffusion model with 1) Lightweight Network (899.06M parameters totally), 2) Parameter-Efficient Training (49.57M parameters trainable) …

Official inference repo for FLUX.1 models

Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

MLX: An array framework for Apple silicon

4M: Massively Multimodal Masked Modeling

High-Resolution Image Synthesis with Latent Diffusion Models

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

A natural language interface for computers

A feature-rich command-line audio/video downloader

Chat with MLX is a high-performance macOS application that connects your local documents to a personalized large language model (LLM).

Building a semantic search engine for Gmail using OpenAI embedding's model + Pinecone vector storage

Master programming by recreating your favorite technologies from scratch.

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.