Stars
[NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.
[DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
Collect every awesome work about r1!
MineStudio: A Streamlined Package for Minecraft AI Agent Development
Code release for AdapMoE accepted by ICCAD 2024
Empowering RAG with a memory-based data interface for all-purpose applications!
The paper list of the 86-page SCIS cover paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.
MambaOut: Do We Really Need Mamba for Vision? (CVPR 2025)
📰 Must-read papers and blogs on Speculative Decoding ⚡️
🚀 Awesome System for Machine Learning ⚡️ AI System Papers and Industry Practice. ⚡️ System for Machine Learning, LLM (Large Language Model), GenAI (Generative AI). 🍻 OSDI, NSDI, SIGCOMM, SoCC, MLSy…
AI education materials for Chinese students, teachers and IT professionals.
OpenHuFu is an open-sourced data federation system to support collaborative queries over multi databases with security guarantee.
Basic implementation of [Neural Architecture Search with Reinforcement Learning](https://arxiv.org/abs/1611.01578).