My learning notes/codes for ML SYS.

The best ChatGPT that $100 can buy.

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

AgentScope: Agent-Oriented Programming for Building LLM Applications

A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

AI Crash Course to help busy builders catch up to the public frontier of AI research in 2 weeks

[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)

Training setup for Langchain's Open Deep Research

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

Learning Deep Representations of Data Distributions

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

"Context engineering is the delicate art and science of filling the context window with just the right information for the next step." — Andrej Karpathy. A frontier, first-principles handbook inspi…

This repository contains a curated collection of 300+ case studies from over 80 companies, detailing practical applications and insights into machine learning (ML) system design. The contents are o…

Minimal reproduction of DeepSeek R1-Zero

CUDA Python: Performance meets Productivity

The data plane for agents. Arch is a models-native proxy server that handles the plumbing work in AI: agent routing & hand off, guardrails, zero-code logs and traces, unified access to LLMs from Op…

SoTA open-source TTS

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

This project provides a framework for deploying and running a Visual Language Model (VLM) as a batch processing job on Google Cloud Platform (GCP). It utilizes Docker for containerization, Google C…

This project provides a conversational agent that can answer questions about a codebase via CLI

Build Real-Time Knowledge Graphs for AI Agents

The personal finance app for everyone

Customizable, AI-driven virtual assistant designed to streamline customer service operations, handle common inquiries, and improve overall user satisfaction through automated and contextually aware…

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

🤖 𝗟𝗲𝗮𝗿𝗻 for 𝗳𝗿𝗲𝗲 how to 𝗯𝘂𝗶𝗹𝗱 an end-to-end 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻-𝗿𝗲𝗮𝗱𝘆 𝗟𝗟𝗠 & 𝗥𝗔𝗚 𝘀𝘆𝘀𝘁𝗲𝗺 using 𝗟𝗟𝗠𝗢𝗽𝘀 best practices: ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 12 𝘩𝘢𝘯𝘥𝘴-𝘰𝘯 𝘭𝘦𝘴𝘴𝘰𝘯𝘴

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

Improve your resumes with Resume Matcher. Get insights, keyword suggestions and tune your resumes to job descriptions.

Transform PDFs into AI podcasts for engaging on-the-go audio content.