Starred repositories
Horizontally Scalable Kubernetes Controllers: distribute reconciliation of Kubernetes objects across multiple controller instances
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agent RL)
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
Example models using DeepSpeed
A Datacenter Scale Distributed Inference Serving Framework
SGLang is a fast serving framework for large language models and vision language models.
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
Gateway API Inference Extension
CUDA Python: Performance meets Productivity
eBPF Developer Tutorial: Learning eBPF Step by Step with Examples
Production-ready platform for agentic workflow development.
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
Ongoing research training transformer models at scale
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
Cost-efficient and pluggable Infrastructure components for GenAI inference
Super-Efficient RLHF Training of LLMs with Parameter Reallocation
My learning notes/codes for ML SYS.
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
AI Inference Operator for Kubernetes. The easiest way to serve ML models in production. Supports VLMs, LLMs, embeddings, and speech-to-text.
verl: Volcano Engine Reinforcement Learning for LLMs
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
Model Context Protocol Servers