Fast markdown preview server with live reload and theme support.

A PyTorch repo for data loading and utilities to be shared by the PyTorch domain libraries.

PyTorch-native post-training at scale

A minimal tensor processing unit (TPU), inspired by Google's TPU V2 and V1

A statically typed lisp, without a GC, for real-time applications.

[SIGMOD 2026] F3: The Open-Source Data File Format for the Future

A JAX-native LLM Post-Training Library

SkyRL: A Modular Full-stack RL Library for LLMs

Post-training with Tinker

Rust GUI components for building fantastic cross-platform desktop application by using GPUI.

Run docker-compose with help from Nix/NixOS

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

Regular expression manipulation library

Wireless, Low-Profile Split Keyboard Based on Choc Switches

Friends of OLMo and their links.

Open-source media request and discovery manager for Jellyfin, Plex, and Emby.

Kimi K2 is the large language model series developed by Moonshot AI team

NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process communication and coordination overheads by allowing programmer…

💫 Toolkit to help you get started with Spec-Driven Development

A zero-to-one guide on scaling modern transformers with n-dimensional parallelism.

Landing repository for the paper "Predicting the Order of Upcoming Tokens Improves Language Modeling"

Miryoku is an ergonomic, minimal, orthogonal, and universal keyboard layout.

Visualize keymaps that use advanced features like hold-taps and combos, with automatic parsing

Flash-Muon: An Efficient Implementation of Muon Optimizer

Tile primitives for speedy kernels

Puzzles for learning Triton

✨ A Swiss Army Knife for Zsh - Unix Shell

Fast, collaborative live terminal sharing over the web

FSRS Optimizer Package

Represent large sets and maps compactly with finite state transducers.