Dolphin for iOS, reborn

Pokemon Emerald in WebAssembly

Linux payload implementing HV exploits to run a custom bootloader

CUDA Tile programming in Julia

My toolbox for HDMI CEC handling

Unlock vGPU functionality for consumer grade GPUs.

A GPU cluster manager that configures and orchestrates inference engines like vLLM and SGLang for high-performance AI model deployment.

CUDA Tile IR is an MLIR-based intermediate representation and compiler infrastructure for CUDA kernel optimization, focusing on tile-based computation patterns and optimizations targeting NVIDIA te…

Run frontier AI locally.

cuTile is a programming model for writing parallel kernels for NVIDIA GPUs

OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data

A Research UNIX V2 beta from 1972 brought back to life

Sources for the book "Machine Learning in Production"

Swift framework to interact with Python.

Simple, unified interface to multiple Generative AI providers

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

An annotated implementation of the Transformer paper.

LLM training in simple, raw C/CUDA

Distribute and run LLMs with a single file.

Inference Llama 2 in one file of pure C

The Mojo Programming Language

The simplest, fastest repository for training/finetuning medium-sized GPTs.

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

The Modular Platform (includes MAX & Mojo)

Use any linux distribution inside your terminal. Enable both backward and forward compatibility with software and freedom to use whatever distribution you’re more comfortable with. Mirror available…

Awesome-LLM: a curated list of Large Language Model