TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

Teaching LLMs memory management for unbounded context 📚🦙

An Autonomous LLM Agent for Complex Task Solving

A series of code large language models developed by PKU-KCL

Build browser agents for real world tasks

Termux - a terminal emulator application for Android OS extendible by variety of packages.

Interact with your documents using the power of GPT, 100% privately, no data leaks

A curated list of free courses & certifications.

📚 Freely available programming books

OpenAI's Code Interpreter in your terminal, running locally

Learn the foundational skills of building full stack web applications.

openpilot is an open source driver assistance system. openpilot performs the functions of Automated Lane Centering and Adaptive Cruise Control for 250+ supported car makes and models.

Sparsity-aware deep learning inference runtime for CPUs

The Mojo Programming Language

Open 3D Engine (O3DE) is an Apache 2.0-licensed multi-platform 3D engine that enables developers and content creators to build AAA games, cinema-quality 3D worlds, and high-fidelity simulations without any fees or commercial obligations.

[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

一个基于 electron 的音乐软件

CasaOS - A simple, easy-to-use, elegant open-source Personal Cloud system.

Stable Diffusion web UI

The Ethereum Improvement Proposal repository

FalconHound is a blue team multi-tool. It allows you to utilize and enhance the power of BloodHound in a more automated fashion. It is designed to be used in conjunction with a SIEM or other log aggregation tool.