MLX: An array framework for Apple silicon

Contexts Optical Compression

Public repository for Skills

The best ChatGPT that $100 can buy.

DSPy: The framework for programming—not prompting—language models

Executable lectures for Autumn 2025

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

Accessible large language models via k-bit quantization for PyTorch.

Modeling, training, eval, and inference code for OLMo

Ongoing research training transformer models at scale

Animation engine for explanatory math videos

A web app that generates code for efficiently approximating mathematical functions of one variable.

⏬ Dumb downloader that scrapes the web

The Abstraction and Reasoning Corpus

A Python framework for high performance GPU simulation and graphics

Hackers' Guide to Language Models

HFT Low latency Repository

Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry lead…

Generative Model Programming

General-purpose programming language and toolchain for maintaining robust, optimal, and reusable software.

Private Q&A and summarization of documents+images or chat with local GPT, 100% private, Apache 2.0. Supports LLaMa2, llama.cpp, and more. Demo: https://gpt.h2o.ai/

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

Solve puzzles. Improve your pytorch.

Find Jobs in Top Startups

Solve puzzles. Learn CUDA.

An unnecessarily tiny implementation of GPT-2 in NumPy.

Node process connecting your tinder account to GPT3 and let an AI talk for you.

Minimal deep learning library written from scratch in Python, using NumPy/CuPy.

Diem’s mission is to build a trusted and innovative financial network that empowers people and businesses around the world.