A PyTorch native library for large model training

A generative world for general-purpose robotics & embodied AI learning.

中文的C++ Template的教学指南。与知名书籍C++ Templates不同，该系列教程将C++ Templates作为一门图灵完备的语言来讲授，以求帮助读者对Meta-Programming融会贯通。(正在施工中)

📚 Modern C++ Tutorial: C++11/14/17/20 On the Fly | https://changkun.de/modern-cpp/

Unified framework for robot learning built on NVIDIA Isaac Sim

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

C++ tensors with broadcasting and lazy computing

Realistic Robotic Manipulation Simulator and Benchmark with Progressive Reasoning Tasks

A lightweight C++ logging library

A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

Tile primitives for speedy kernels

A toolkit for developing and comparing reinforcement learning algorithms.

The official Meta Llama 3 GitHub site

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Generative Agents: Interactive Simulacra of Human Behavior

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models. ｜语音识别工具包，包含丰富的性能优越的开源预训练模型，支持语音识别、语音端点检测、文本后处理等，具备服务部署能力。

小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫

Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline model in a user-friendly interface.

A parser, editor and profiler tool for ONNX models.

Efficient Large Language Models: A Survey

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

CUDA Templates for Linear Algebra Subroutines

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

Agent framework and applications built upon Qwen, featuring Code Interpreter and Chrome browser extension.