Stars
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
Development repository for the Triton language and compiler
A Python-level JIT compiler designed to make unmodified PyTorch programs faster.
TVM Documentation in Chinese Simplified / TVM 中文文档
Push acceptor for ephemeral and batch jobs.
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
🚀 The fast, Pythonic way to build MCP servers and clients
[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero
Production-ready platform for agentic workflow development.
An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.
A powerful flow control component enabling reliability, resilience and monitoring for microservices. (面向云原生微服务的高可用流控防护组件)
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
OS-Level Memory Layer for LLMs, AI Agents & Multi-Agent Systems with long-term, working, and external memory.
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
Model Context Protocol Servers
Train transformer language models with reinforcement learning.
verl: Volcano Engine Reinforcement Learning for LLMs
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
No fortress, purely open ground. OpenManus is Coming.
A framework for few-shot evaluation of language models.
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
😎 Awesome lists about all kinds of interesting topics