Highlights
- Pro
Stars
[NeurIPS 2025] MMaDA - Open-Sourced Multimodal Large Diffusion Language Models
Official PyTorch implementation for "Large Language Diffusion Models"
Build high-performance AI models with modular building blocks
Implementation of MoE Mamba from the paper: "MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts" in Pytorch and Zeta
A *VERY experimental* web and desktop client for Jellyfin written in Rust
CUDA and Triton implementations of Flash Attention with SoftmaxN.
Library and utility for displaying and configuring Wayland outputs
Hackable and optimized Transformers building blocks, supporting a composable construction.
An experiment in scalable routing as an encrypted IPv6 overlay network
Breaking the WASM/JS communication performance barrier
Async-friendly WebTransport implementation in Rust
Official implementation of "GPT or BERT: why not both?"
Zero-cost ultra-high-performance declarative DOM library using FRP signals for Rust!
Cycle-tracking garbage collector library for Rust
A scalable, distributed, collaborative, document-graph database, for the realtime web
A GraphQL server library implemented in Rust
SIP Stack Rust library for building SIP applications
GrapheneOS rooted and served via its own OTA server on GitHub pages
Rust WebTransport library for native and WASM