The new Python web framework by the authors of Two Scoops of Django

A fast and flexible implementation of Rigid Body Dynamics algorithms and their analytical derivatives

SPI LCD/OLED library which can be built for Arduino and Linux

A Quirky Assortment of CuTe Kernels

CUDA accelerated rasterization of gaussian splatting

Storing long contexts in tiny caches with self-study

A generalist Python node editor

Chrome extension for running Generative AI in your browser locally

Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of GPT-Fast, a simple, PyTorch-native generation codebase.

Google's Dawn WebGPU implementation, cross-compiled with Zig into a single static library

Make triton easier

A lightweight library for portable low-level GPU computation using WebGPU.

LLM training in simple, raw C/CUDA

Jupyter in the terminal.

Jupyter Notebooks in the terminal.

A good looking terminal emulator which mimics the old cathode display...

A curated list of awesome instruction tuning datasets, models, papers and repositories.

Firmware for the Synthstrom Audible Deluge

CMake files that provide WebGPU for native and web development, easy-to-integrate and unified across implementations.

Richard is gaining power

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

The official implementation for "Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising".

Lua bindings for gemma.cpp

A Python wrapper for gemma.cpp

lightweight, standalone C++ inference engine for Google's Gemma models.

Performance-portable, length-agnostic SIMD with runtime dispatch

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

Radically simple multiplayer / networked WebAssembly