aarnphm

three.js

JavaScript 3D Library.

zed

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

fish-shell

The user-friendly command line shell.

fabric

fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

uv

An extremely fast Python package installer and resolver, written in Rust.

pkl

A configuration as code language with rich validation and tooling.

OpenLLM

Run any open-source LLMs, such as Llama 3.1, Gemma, as OpenAI compatible API endpoint in the cloud.

livekit

End-to-end stack for WebRTC. SFU media server and SDKs.

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

ZLUDA

CUDA on AMD GPUs

llrt

LLRT (Low Latency Runtime) is an experimental, lightweight JavaScript runtime designed to address the growing demand for fast and efficient Serverless applications.

PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

gemma.cpp

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

gemma_pytorch

The official PyTorch implementation of Google's Gemma models

moondream

tiny vision language model

alphageometry

sql.js-httpvfs

Hosting read-only SQLite databases on static file hosters like Github Pages

react-strict-dom

React Strict DOM (RSD) is a subset of React DOM, imperative DOM, and CSS that supports web and native targets

s4

Structured state space sequence models

meditron

Meditron is a suite of open-source medical Large Language Models (LLMs).

TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

ipyflow

A reactive Python kernel for Jupyter notebooks.

sp1

A performant, 100% open-source, contributor-friendly zkVM.

yet-another-applied-llm-benchmark

A benchmark to evaluate language models on questions I've previously asked them to solve.

marlin

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

pubgrub

PubGrub version solving algorithm implemented in Rust

micromorph

A very tiny library for diffing DOM nodes

mscclpp

MSCCL++: A GPU-driven communication stack for scalable AI applications

jiter

Fast iterable JSON parser.