Starred repositories
Multilingual Document Layout Parsing in a Single Vision-Language Model
verl: Volcano Engine Reinforcement Learning for LLMs
✔（已完结）超级全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】【大飞 大模型Agent】
Tongyi Deep Research, the Leading Open-source Deep Research Agent
[CVPR 2025] A Comprehensive Benchmark for Document Parsing and Evaluation
My learning notes for ML SYS.
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)
A high-throughput and memory-efficient inference and serving engine for LLMs
GameStream client for PCs (Windows, Mac, Linux, and Steam Link)
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition
UniTable: Towards a Unified Table Foundation Model
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
A Python web, show and edit markdown files
Toolkit for linearizing PDFs for LLM datasets/training
基于序列表格识别算法推理库，集成PP-Structure和modelscope等表格识别算法。
AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。
A quick guide (especially) for trending instruction finetuning datasets
Llama3、Llama3.1 中文后训练版仓库 - 微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档。
The RedPajama-Data repository contains code for preparing large datasets for training large language models.
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.
modern C++(C++20), simple, easy to use rpc framework