Fully-featured, beautiful web interface for vLLM - built with NextJS.

vLLM Documentation in Chinese Simplified / vLLM 中文文档

Enterprise-grade LLM automated deployment tool that makes AI servers truly "plug-and-play".

Modern AI chatbot supporting multiple LLMs. Switch between Gemini, Mistral, Llama, Claude and ChatGPT.

AI-based search done right

Ask Poddy: Run Open Source LLMs and Embeddings as OpenAI-Compatible Serverless Endpoints (Tutorial)

LLM Call Center,AI Call Center,大模型呼叫中心,大模型客服系统，可以对接市面上主流模型与私有模型：OpenAI,LLaMA,Kimi,通义千问,智谱AI,讯飞星火,Gemini,Xorbits Inference,Amazon Bedrock,火山引擎,腾讯混元,Claude,Bard,DeepSeek,Azure OpenAI,千帆大模型,Ollama,qwen,vLLM

Convert pdf and image files into markdown

Calculate the GPU resources needed for open source large language models (LLMs) during inference and training to determine appropriate hardware configurations.

Enterprise-grade LLM routing microservice with multi-provider support, intelligent failover, and cost optimization.

[WIP] Real-Time Harmful Detection Pipeline Using vLLM

Visual Query Bot – Developed an interactive chat application that enables users to upload images, draw bounding boxes on specific regions, and ask targeted questions about those areas. Leveraged LangChain and LangGraph to build robust information retrieval agents for context-aware visual querying

LLMs Web Interface: A unified management platform for OpenAI, Gemini, Ollama, and vLLM. Features admin dashboard for visual configuration, streaming responses, function calling, token tracking, and LangChain/L