My learning notes for ML SYS.

slime is an LLM post-training framework for RL Scaling.

code for our ICCV 2021 paper "DeepCAD: A Deep Generative Network for Computer-Aided Design Models"

In-depth tutorials and examples on LLM training and inference infrastructure, such as, Pytorch, Fairscale, Nvidia AI Modules (cuDNN, tensorRT, Megatron-LM), HuggingFace.

Train your AI self, amplify you, bridge the world

2025 & 2026 New grad full-time roles in SWE, Quant, and PM.

An open-access book on numpy vectorization techniques, Nicolas P. Rougier, 2017

100 numpy exercises (with solutions)

A booklet on machine learning systems design with exercises. NOT the repo for the book "Designing Machine Learning Systems", which is `dmls-book`

This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning

适用于微信客户端4.0版本的wxauto

Windows版本微信客户端（非网页版）自动化，可实现简单的发送、接收微信消息，简单微信机器人

基于大模型搭建的聊天机器人，同时支持 企业微信、微信 公众号、飞书、钉钉 等接入，可选择GPT3.5/GPT4.0/Claude/文心一言/讯飞星火/通义千问/Gemini/GLM-4/Claude/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。

【禁止接入微信、QQ等腾讯系软件】可以接入第三方平台。基于LLM的更逼真的情感陪伴程序。More realistic emotional companionship program based LLM, meet the characters in your dream.

AI-WeChat-Mater 是一个开源项目，旨在将人工智能能力深度集成到微信生态系统中，提供自动化消息处理和智能交互功能。该项目支持多微信账号管理、智能AI对话、定时任务执行和全方位数据分析。

WeChatPadPro 是基于 WeChat Pad 的高级微信管理工具

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Production-ready platform for agentic workflow development.

Survey: A collection of AWESOME papers and resources on the large language model (LLM) related recommender system topics.

Paper list of multi-agent reinforcement learning (MARL)

SDAR (Synergy of Diffusion and AutoRegression), a large diffusion language model（1.7B, 4B, 8B, 30B）

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

An Open-Source Large-Scale Reinforcement Learning Project for Search Agents

A collection of full time roles in SWE, Quant, and PM for new grads.

verl: Volcano Engine Reinforcement Learning for LLMs

An end-to-end pipeline to optimize and host LLM for 100K parallel queries

A curated list of foundation models for vision and language tasks