Stars
Easy-to-understand AI learning resources for beginners.
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…
High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
《动手学大模型Dive into LLMs》系列编程实践教程
Next generation map vector tiles format
GeoView是一款开源、轻量、功能丰富的交互式遥感影像智能解译工具，致力于实现遥感领域深度学习模型在Web平台的快速部署。
GeoAI: Artificial Intelligence for Geospatial Data
"RAG-Anything: All-in-One RAG Framework"
Falcon: A Remote Sensing Vision-Language Foundation Model
Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.
ModelVerse是一个功能强大的大语言模型(LLM)一体化推训平台，致力于为AI开发者和研究者提供完整的模型生命周期管理解决方案。从模型管理到推理部署，从训练微调到性能评估，ModelVerse将复杂的AI工作流程简化为直观易用的一体化平台。
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
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.
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）
面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Turn any webpage/HTML/Vue/React and so on into desktop and mobile app under 5M with easy in few minutes. 轻松将任意网站/HTML/Vue/React等项目构建为轻量级(小于5M)多端桌面应用和手机应用仅需几分钟. https://ppofficial.netlify.app
Turn any webpage/HTML/Vue/React and so on into desktop and mobile app under 5M with easy in few minutes. 轻松将任意网站/HTML/Vue/React等项目构建为轻量级(小于5M)多端桌面应用和手机应用仅需几分钟. https://ppofficial.netlify.app
Geospatial library wheels for Python on Windows.
Dify-Plus 是 Dify 的企业级增强版，集成了基于 gin-vue-admin 的管理中心，并针对企业场景进行了功能优化。 🚀 Dify-Plus = 管理中心 + Dify 二开 。 特别说明： 本项目为开源社区的二次开发成果，严格遵循 Dify 原项目的版权许可协议，未涉及原项目许可的多租户功能及 logo 等版权信息。如有相关需求，请直接联系 Dify 官方获取授权与支持。
cube studio开源云原生一站式机器学习/深度学习/大模型AI平台，mlops算法链路全流程，算力租赁平台，notebook在线开发，拖拉拽任务流pipeline编排，多机多卡分布式训练，超参搜索，推理服务VGPU虚拟化，边缘计算，标注平台自动化标注，deepseek等大模型sft微调/奖励模型/强化学习训练，vllm/ollama/mindie大模型多机推理，私有知识库，AI模型市场…
Question and Answer based on Anything.
Search + Chat = SearChat(AI Chat with Search), Support OpenAI/Anthropic/VertexAI/Gemini, DeepResearch, SearXNG, Docker. AI对话式搜索引擎，支持DeepResearch, 支持OpenAI/Anthropic/VertexAI/Gemini接口、聚合搜索引擎SearXNG，…
Apache Paimon is a lake format that enables building a Realtime Lakehouse Architecture with Flink and Spark for both streaming and batch operations.
AirLLM 70B inference with single 4GB GPU