Stars
Python tool for converting files and office documents to Markdown.
A high-throughput and memory-efficient inference and serving engine for LLMs
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone
Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
Machine Learning Engineering Open Book
"Vibe-Trading: Your Personal Trading Agent"
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
An open source implementation of CLIP.
A straightforward method for training your LLM, from downloading data to generating text.
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
slime is an LLM post-training framework for RL Scaling.
My learning notes for ML SYS.
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
🌟100+ 原创 LLM / RL 原理图📚，《大模型算法》作者巨献！💥（100+ LLM/RL Algorithm Maps ）
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.
中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
A unified inference and post-training framework for accelerated video generation.
将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿，你的 AI 科研副导师。
科研写作助手 (Research Writing Assistant)
My Python scripts to make high-quality figures for publications in top AI conferences and journals.