微调、训练与数据
Megatron-LM
NVIDIA/Megatron-LM
Ongoing research training transformer models at scale
★ 17.2K⑂ 4.3KPython
ToolAI.io · GitHub 频道
GitHub 上的新 AI 项目
一个基于事实的 LLM、智能体、MCP、RAG 和 AI 开发项目索引；每个条目均包含许可证、设置、下载、截图及相关资源。
公开仓库数据
项目索引
MCP 与工具调用
Synapse
zai-org/Synapse
Self-hosted AI workspace with shareable AI teammates, shared conversations, memory, and governed access to plugins, MCP tools, and local devices.
★ 331⑂ 24TypeScript
推理、部署与运行时
checkpoint-engine
MoonshotAI/checkpoint-engine
Checkpoint-engine is a simple middleware to update model weights in LLM inference engines
★ 982⑂ 100Python
机器人与边缘 AI
edgeai-for-beginners
microsoft/edgeai-for-beginners
This course is designed to guide beginners through the exciting world of Edge AI, covering fundamental concepts, popular models, inference techniques, device-specific applications, model optimization, and the development of intelligent Edge AI agents.
★ 1.6K⑂ 362Jupyter Notebook
AI 应用与自动化
ResearchStudio
microsoft/ResearchStudio
ResearchStudio: Our AI co-author, from research problem to final publication.
★ 1.8K⑂ 103Python
LLM 与基础模型
PaddleFormers
PaddlePaddle/PaddleFormers
PaddleFormers is an easy-to-use library of pre-trained large language model zoo based on PaddlePaddle.
★ 13K⑂ 2.2KPython
推理、部署与运行时
Paddle-Lite
PaddlePaddle/Paddle-Lite
PaddlePaddle High Performance Deep Learning Inference Engine for Mobile and Edge (飞桨高性能深度学习端侧推理引擎）
★ 7.3K⑂ 1.6KC++
AI 编程与开发者工具
PaddleScience
PaddlePaddle/PaddleScience
PaddleScience is SDK and library for developing AI-driven scientific computing applications based on PaddlePaddle.
★ 448⑂ 236Python
MCP 与工具调用
MiniMax-MCP
MiniMax-AI/MiniMax-MCP
Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
★ 1.5K⑂ 272Python
智能体与多智能体
OpenRoom
MiniMax-AI/OpenRoom
A browser-based desktop where AI Agent operates every app through natural language.
★ 1.2K⑂ 162TypeScript
多模态 AI
GLM-V
zai-org/GLM-V
GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
★ 2.4K⑂ 174Python
多模态 AI
HunyuanImage-3.0
Tencent-Hunyuan/HunyuanImage-3.0
HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation
★ 3.2K⑂ 175Python
第 10 / 25 页 · 295 个项目