# Xorbits Inference: Model Serving Made Easy 🤖

Xinference Enterprise · Self-hosting · Documentation

[![PyPI Latest Release](https://img.shields.io/pypi/v/xinference.svg?style=for-the-badge)](https://pypi.org/project/xinference/) [![License](https://img.shields.io/pypi/l/xinference.svg?style=for-the-badge)](https://github.com/xorbitsai/inference/blob/main/LICENSE) [![Build Status](https://img.shields.io/github/actions/workflow/status/xorbitsai/inference/python.yaml?branch=main&style=for-the-badge&label=GITHUB%20ACTIONS&logo=github)](https://actions-badge.atrox.dev/xorbitsai/inference/goto?ref=main) [![Docker Pulls](https://img.shields.io/docker/pulls/xprobe/xinference?style=for-the-badge&logo=docker)](https://hub.docker.com/r/xprobe/xinference) [![Discord](https://img.shields.io/badge/join_Discord-5462eb.svg?logo=discord&style=for-the-badge&logoColor=%23f5f5f5)](https://discord.gg/Xw9tszSkr5) [![Telegram](https://img.shields.io/badge/join_Telegram-26A5E4.svg?logo=telegram&style=for-the-badge&logoColor=white)](https://t.me/+nCNpwmySwk9iYmI1) [![Twitter](https://img.shields.io/twitter/follow/xorbitsio?logo=x&style=for-the-badge)](https://twitter.com/xorbitsio)

Xorbits Inference(Xinference) is a powerful and versatile library designed to serve language, speech recognition, and multimodal models. With Xorbits Inference, you can effortlessly deploy and serve your or state-of-the-art built-in models using just a single command. Whether you are a researcher, developer, or data scientist, Xorbits Inference empowers you to unleash the full potential of cutting-edge AI models.

👉 Join our Discord community! · Join our Telegram group!

## 🔥 Hot Topics ### Framework Enhancements - Agent-native Serving: Xinference integrates with [Xagent](https://github.com/xorbitsai/xagent) to enable dynamic planning, tool use, and autonomous multi-step reasoning — moving beyond static pipelines. - Auto batch: Multiple concurrent requests are automatically batched, significantly improving throughput: [#4197](https://github.com/xorbitsai/inference/pull/4197) - [Xllamacpp](https://github.com/xorbitsai/xllamacpp): New llama.cpp Python binding, maintained by Xinference team, supports continuous batching and is more production-ready.: [#2997](https://github.com/xorbitsai/inference/pull/2997) - Distributed inference: running models across workers: [#2877](https://github.com/xorbitsai/inference/pull/2877) - VLLM enhancement: Shared KV cache across multiple replicas: [#2732](https://github.com/xorbitsai/inference/pull/2732) ### New Models - Built-in support for VibeThinker series ([1.5B](https://huggingface.co/WeiboAI/VibeThinker-1.5B), [3B](https://huggingface.co/WeiboAI/VibeThinker-3B)): [#5085](https://github.com/xorbitsai/inference/pull/5085) - Built-in support for Nex-N2 series ([mini](https://huggingface.co/nex-agi/Nex-N2-mini), [Pro](https://huggingface.co/nex-agi/Nex-N2-Pro), [Pro-fp8](https://huggingface.co/nex-agi/Nex-N2-Pro-fp8)): [#5094](https://github.com/xorbitsai/inference/pull/5094) - Built-in support for [Unlimited-OCR](https://huggingface.co/baidu/Unlimited-OCR): [#5103](https://github.com/xorbitsai/inference/pull/5103) - Built-in support for [Ornith-1.0-35B](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B): [#5119](https://github.com/xorbitsai/inference/pull/5119) - Built-in support for [MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B): [#5010](https://github.com/xorbitsai/inference/pull/5010) - Built-in support for jina-embeddings-v5 series ([text-nano](https://huggingface.co/jinaai/jina-embeddings-v5-text-nano), [text-small](https://huggingface.co/jinaai/jina-embeddings-v5-text-small), [omni-nano](https://huggingface.co/jinaai/jina-embeddings-v5-omni-nano), [omni-small](https://huggingface.co/jinaai/jina-embeddings-v5-omni-small)): [#5018](https://github.com/xorbitsai/inference/pull/5018) - Built-in support for MiniCPM-V-4.6 series ([MiniCPM-V-4.6](https://huggingface.co/openbmb/MiniCPM-V-4.6), [MiniCPM-V-4.6-Thinking](https://huggingface.co/openbmb/MiniCPM-V-4.6-Thinking)): [#5025](https://github.com/xorbitsai/inference/pull/5025) - Built-in support for Tencent Hy-MT2 series ([1.8B](https://huggingface.co/tencent/Hy-MT2-1.8B), [7B](https://huggingface.co/tencent/Hy-MT2-7B), [30B-A3B](https://huggingface.co/tencent/Hy-MT2-30B-A3B)): [#5029](https://github.com/xorbitsai/inference/pull/5029) ### Integrations - [Xagent](https://github.com/xorbitsai/xagent): an enterprise agent platform for building and running AI agents with planning, memory, and tool use — not limited to rigid workflows. - [Dify](https://docs.dify.ai/advanced/model-configuration/xinference): an LLMOps platform that enables developers (and even non-developers) to quickly build useful applications based on large language models, ensuring they are visual, operable, and improvable. - [FastGPT](https://github.com/labring/FastGPT): a knowledge-based platform built on the LLM, offers out-of-the-box data processing and model invocation capabilities, allows for workflow orchestration through Flow visualization. - [RAGFlow](https://github.com/infiniflow/ragflow): is an open-source RAG engine based on deep document understanding. - [MaxKB](https://github.com/1Panel-dev/MaxKB): MaxKB = Max Knowledge Brain, it is a powerful and easy-to-use AI assistant that integrates Retrieval-Augmented Generation (RAG) pipelines, supports robust workflows, and provides advanced MCP tool-use capabilities. ## Key Features 🌟 **Model Serving Made Easy**: Simplify the process of serving large language, speech recognition, and multimodal models. You can set up and deploy your models for experimentation and production with a single command. ⚡️ **State-of-the-Art Models**: Experiment with cutting-edge built-in models using a single command. Inference provides access to state-of-the-art open-source models! 🖥 **Heterogeneous Hardware Utilization**: Make the most of your hardware resources with [ggml](https://github.com/ggerganov/ggml). Xorbits Inference intelligently utilizes heterogeneous hardware, including GPUs and CPUs, to accelerate your model inference tasks. ⚙️ **Flexible API and Interfaces**: Offer multiple interfaces for interacting with your models, supporting OpenAI compatible RESTful API (including Function Calling API), RPC, CLI and WebUI for seamless model management and interaction. 🌐 **Distributed Deployment**: Excel in distributed deployment scenarios, allowing the seamless distribution of model inference across multiple devices or machines. 🔌 **Built-in Integration with Third-Party Libraries**: Xorbits Inference seamlessly integrates with popular third-party libraries including [LangChain](https://python.langchain.com/docs/integrations/providers/xinference), [LlamaIndex](https://gpt-index.readthedocs.io/en/stable/examples/llm/XinferenceLocalDeployment.html#i-run-pip-install-xinference-all-in-a-terminal-window), [Dify](https://docs.dify.ai/advanced/model-configuration/xinference), and [Chatbox](https://chatboxai.app/). ## Why Xinference | Feature | Xinference | FastChat | OpenLLM | RayLLM | |------------------------------------------------|------------|----------|---------|--------| | OpenAI-Compatible RESTful API | ✅ | ✅ | ✅ | ✅ | | vLLM Integrations | ✅ | ✅ | ✅ | ✅ | | More Inference Engines (GGML, TensorRT) | ✅ | ❌ | ✅ | ✅ | | More Platforms (CPU, Metal) | ✅ | ✅ | ❌ | ❌ | | Multi-node Cluster Deployment | ✅ | ❌ | ❌ | ✅ | | Image Models (Text-to-Image) | ✅ | ✅ | ❌ | ❌ | | Text Embedding Models | ✅ | ❌ | ❌ | ❌ | | Multimodal Models | ✅ | ❌ | ❌ | ❌ | | Audio Models | ✅ | ❌ | ❌ | ❌ | | More OpenAI Functionalities (Function Calling) | ✅ | ❌ | ❌ | ❌ | ## Using Xinference - **Self-hosting Xinference Community Edition
** Quickly get Xinference running in your environment with this [starter guide](#getting-started). Use our [documentation](https://inference.readthedocs.io/) for further references and more in-depth instructions. - **Xinference for enterprise / organizations
** We provide additional enterprise-centric features. [send us an email](mailto:info@xinference.co?subject=[GitHub]Business%20License%20Inquiry) to discuss enterprise needs.
## Staying Ahead Star Xinference on GitHub and be instantly notified of new releases. ![star-us](assets/stay_ahead.gif) ## Getting Started * [Docs](https://inference.readthedocs.io/en/latest/index.html) * [Built-in Models](https://inference.readthedocs.io/en/latest/models/builtin/index.html) * [Custom Models](https://inference.readthedocs.io/en/latest/models/custom.html) * [Deployment Docs](https://inference.readthedocs.io/en/latest/getting_started/using_xinference.html) ### Docker Nvidia GPU users can start Xinference server using [Xinference Docker Image](https://inference.readthedocs.io/en/latest/getting_started/using_docker_image.html). Prior to executing the installation command, ensure that both [Docker](https://docs.docker.com/get-docker/) and [CUDA](https://developer.nvidia.com/cuda-downloads) are set up on your system. ```bash docker run --name xinference -d -p 9997:9997 -e XINFERENCE_HOME=/data -v :/data --gpus all xprobe/xinference:latest xinference-local -H 0.0.0.0 ``` ### K8s via helm Ensure that you have GPU support in your Kubernetes cluster, then install as follows. ``` # add repo helm repo add xinference https://xorbitsai.github.io/xinference-helm-charts # update indexes and query xinference versions helm repo update xinference helm search repo xinference/xinference --devel --versions # install xinference helm install xinference xinference/xinference -n xinference --version 0.0.1-v ``` For more customized installation methods on K8s, please refer to the [documentation](https://inference.readthedocs.io/en/latest/getting_started/using_kubernetes.html). ### Quick Start Install Xinference by using pip as follows. (For more options, see [Installation page](https://inference.readthedocs.io/en/latest/getting_started/installation.html).) ```bash pip install "xinference[all]" ``` To start a local instance of Xinference, run the following command: ```bash $ xinference-local ``` Once Xinference is running, there are multiple ways you can try it: via the web UI, via cURL, via the command line, or via the Xinference’s python client. Check out our [docs]( https://inference.readthedocs.io/en/latest/getting_started/using_xinference.html#run-xinference-locally) for the guide. ![web UI](assets/screenshot.png) ## Getting involved | Platform | Purpose | |-------------------------------------------------------------------------------------------------|---------------------------------------------| | [Github Issues](https://github.com/xorbitsai/inference/issues) | Reporting bugs and filing feature requests. | | [Discord](https://discord.gg/Xw9tszSkr5) | Collaborating with other Xinference users. | | [Telegram](https://t.me/+nCNpwmySwk9iYmI1) | Chatting with other Xinference users. | | [Twitter](https://twitter.com/xorbitsio) | Staying up-to-date on new features. | ## Citation If this work is helpful, please kindly cite as: ```bibtex @inproceedings{lu2024xinference, title = "Xinference: Making Large Model Serving Easy", author = "Lu, Weizheng and Xiong, Lingfeng and Zhang, Feng and Qin, Xuye and Chen, Yueguo", booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations", month = nov, year = "2024", address = "Miami, Florida, USA", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.emnlp-demo.30", pages = "291--300", } ``` ## Contributors

## Star History [![Star History Chart](https://api.star-history.com/svg?repos=xorbitsai/inference&type=Date)](https://star-history.com/#xorbitsai/inference&Date)