A modular graph-based Retrieval-Augmented Generation (RAG) system

OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

Intel® NPU Acceleration Library

Fast Multimodal LLM on Mobile Devices

An MLIR-based toolchain for AMD AI Engine-enabled devices.

An experimental modular OS written in Rust.

北京大学 2023 年秋计算机系统导论课程（ICS）作业、笔记、经验

Fast and memory-efficient exact attention

📖A curated list of Awesome LLM/VLM Inference Papers with codes: WINT8/4, Flash-Attention, Paged-Attention, Parallelism, etc. 🎉🎉

A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Open deep learning compiler stack for cpu, gpu and specialized accelerators

Universal LLM Deployment Engine with ML Compilation

High-speed Large Language Model Serving for Local Deployment

LLM inference in C/C++

Inference code for Llama models

[RUST] 模块化QQ机器人框架 （Based RICQ）

Algorithm and data structure articles for https://cp-algorithms.com (based on http://e-maxx.ru)

N-dimensional RTree implementation in C++

mimalloc is a compact general purpose allocator with excellent performance.

🌟 Wiki of OI / ICPC for everyone. （某大型游戏线上攻略，内含炫酷算术魔法）

Modern C++ Programming Course (C++03/11/14/17/20/23/26)

Run Windows apps such as Microsoft Office/Adobe in Linux (Ubuntu/Fedora) and GNOME/KDE as if they were a part of the native OS, including Nautilus integration.

List of Computer Science courses with video lectures.

🎓 Path to a free self-taught education in Computer Science!

贵校课程资料民间整理

Linux kernel source tree