
OpenLLM
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
Stars: 10939

OpenLLM is a platform that helps developers run any open-source Large Language Models (LLMs) as OpenAI-compatible API endpoints, locally and in the cloud. It supports a wide range of LLMs, provides state-of-the-art serving and inference performance, and simplifies cloud deployment via BentoML. Users can fine-tune, serve, deploy, and monitor any LLMs with ease using OpenLLM. The platform also supports various quantization techniques, serving fine-tuning layers, and multiple runtime implementations. OpenLLM seamlessly integrates with other tools like OpenAI Compatible Endpoints, LlamaIndex, LangChain, and Transformers Agents. It offers deployment options through Docker containers, BentoCloud, and provides a community for collaboration and contributions.
README:
OpenLLM allows developers to run any open-source LLMs (Llama 3.3, Qwen2.5, Phi3 and more) or custom models as OpenAI-compatible APIs with a single command. It features a built-in chat UI, state-of-the-art inference backends, and a simplified workflow for creating enterprise-grade cloud deployment with Docker, Kubernetes, and BentoCloud.
Understand the design philosophy of OpenLLM.
Run the following commands to install OpenLLM and explore it interactively.
pip install openllm # or pip3 install openllm
openllm hello
OpenLLM supports a wide range of state-of-the-art open-source LLMs. You can also add a model repository to run custom models with OpenLLM.
Model | Parameters | Required GPU | Start a Server |
---|---|---|---|
deepseek | r1 | 80Gx16 | openllm serve deepseek:r1 |
gemma2 | 2b | 12G | openllm serve gemma2:2b |
hermes-3 | deep-llama3-8b-3622 | 80G | openllm serve hermes-3:deep-llama3-8b-3622 |
jamba1.5 | mini-5e51 | 80Gx2 | openllm serve jamba1.5:mini-5e51 |
llama3.1 | 8b | 24G | openllm serve llama3.1:8b |
llama3.2 | 1b | 24G | openllm serve llama3.2:1b |
llama3.3 | 70b | 80Gx2 | openllm serve llama3.3:70b |
mistral | 8b | 24G | openllm serve mistral:8b |
mistral-large | 123b | 80Gx4 | openllm serve mistral-large:123b |
phi4 | 14b | 80G | openllm serve phi4:14b |
pixtral | 12b-2409 | 80G | openllm serve pixtral:12b-2409 |
qwen2.5 | 7b | 24G | openllm serve qwen2.5:7b |
qwen2.5-coder | 3b | 24G | openllm serve qwen2.5-coder:3b |
qwq | 32b | 80G | openllm serve qwq:32b |
For the full model list, see the OpenLLM models repository.
To start an LLM server locally, use the openllm serve
command and specify the model version.
[!NOTE] OpenLLM does not store model weights. A Hugging Face token (HF_TOKEN) is required for gated models.
- Create your Hugging Face token here.
- Request access to the gated model, such as meta-llama/Llama-3.2-1B-Instruct.
- Set your token as an environment variable by running:
export HF_TOKEN=<your token>
openllm serve llama3.2:1b
The server will be accessible at http://localhost:3000, providing OpenAI-compatible APIs for interaction. You can call the endpoints with different frameworks and tools that support OpenAI-compatible APIs. Typically, you may need to specify the following:
- The API host address: By default, the LLM is hosted at http://localhost:3000.
- The model name: The name can be different depending on the tool you use.
- The API key: The API key used for client authentication. This is optional.
Here are some examples:
OpenAI Python client
from openai import OpenAI
client = OpenAI(base_url='http://localhost:3000/v1', api_key='na')
# Use the following func to get the available models
# model_list = client.models.list()
# print(model_list)
chat_completion = client.chat.completions.create(
model="meta-llama/Llama-3.2-1B-Instruct",
messages=[
{
"role": "user",
"content": "Explain superconductors like I'm five years old"
}
],
stream=True,
)
for chunk in chat_completion:
print(chunk.choices[0].delta.content or "", end="")
LlamaIndex
from llama_index.llms.openai import OpenAI
llm = OpenAI(api_bese="http://localhost:3000/v1", model="meta-llama/Llama-3.2-1B-Instruct", api_key="dummy")
...
OpenLLM provides a chat UI at the /chat
endpoint for the launched LLM server at http://localhost:3000/chat.
To start a chat conversation in the CLI, use the openllm run
command and specify the model version.
openllm run llama3:8b
A model repository in OpenLLM represents a catalog of available LLMs that you can run. OpenLLM provides a default model repository that includes the latest open-source LLMs like Llama 3, Mistral, and Qwen2, hosted at this GitHub repository. To see all available models from the default and any added repository, use:
openllm model list
To ensure your local list of models is synchronized with the latest updates from all connected repositories, run:
openllm repo update
To review a model’s information, run:
openllm model get llama3.2:1b
You can contribute to the default model repository by adding new models that others can use. This involves creating and submitting a Bento of the LLM. For more information, check out this example pull request.
You can add your own repository to OpenLLM with custom models. To do so, follow the format in the default OpenLLM model repository with a bentos
directory to store custom LLMs. You need to build your Bentos with BentoML and submit them to your model repository.
First, prepare your custom models in a bentos
directory following the guidelines provided by BentoML to build Bentos. Check out the default model repository for an example and read the Developer Guide for details.
Then, register your custom model repository with OpenLLM:
openllm repo add <repo-name> <repo-url>
Note: Currently, OpenLLM only supports adding public repositories.
OpenLLM supports LLM cloud deployment via BentoML, the unified model serving framework, and BentoCloud, an AI inference platform for enterprise AI teams. BentoCloud provides fully-managed infrastructure optimized for LLM inference with autoscaling, model orchestration, observability, and many more, allowing you to run any AI model in the cloud.
Sign up for BentoCloud for free and log in. Then, run openllm deploy
to deploy a model to BentoCloud:
openllm deploy llama3.2:1b
[!NOTE] If you are deploying a gated model, make sure to set HF_TOKEN in enviroment variables.
Once the deployment is complete, you can run model inference on the BentoCloud console:
OpenLLM is actively maintained by the BentoML team. Feel free to reach out and join us in our pursuit to make LLMs more accessible and easy to use 👉 Join our Slack community!
As an open-source project, we welcome contributions of all kinds, such as new features, bug fixes, and documentation. Here are some of the ways to contribute:
- Repost a bug by creating a GitHub issue.
- Submit a pull request or help review other developers’ pull requests.
- Add an LLM to the OpenLLM default model repository so that other users can run your model. See the pull request template.
- Check out the Developer Guide to learn more.
This project uses the following open-source projects:
- bentoml/bentoml for production level model serving
- vllm-project/vllm for production level LLM backend
- blrchen/chatgpt-lite for a fancy Web Chat UI
- astral-sh/uv for blazing fast model requirements installing
We are grateful to the developers and contributors of these projects for their hard work and dedication.
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for OpenLLM
Similar Open Source Tools

OpenLLM
OpenLLM is a platform that helps developers run any open-source Large Language Models (LLMs) as OpenAI-compatible API endpoints, locally and in the cloud. It supports a wide range of LLMs, provides state-of-the-art serving and inference performance, and simplifies cloud deployment via BentoML. Users can fine-tune, serve, deploy, and monitor any LLMs with ease using OpenLLM. The platform also supports various quantization techniques, serving fine-tuning layers, and multiple runtime implementations. OpenLLM seamlessly integrates with other tools like OpenAI Compatible Endpoints, LlamaIndex, LangChain, and Transformers Agents. It offers deployment options through Docker containers, BentoCloud, and provides a community for collaboration and contributions.

agentok
Agentok Studio is a tool built upon AG2, a powerful agent framework from Microsoft, offering intuitive visual tools to streamline the creation and management of complex agent-based workflows. It simplifies the process for creators and developers by generating native Python code with minimal dependencies, enabling users to create self-contained code that can be executed anywhere. The tool is currently under development and not recommended for production use, but contributions are welcome from the community to enhance its capabilities and functionalities.

co-llm
Co-LLM (Collaborative Language Models) is a tool for learning to decode collaboratively with multiple language models. It provides a method for data processing, training, and inference using a collaborative approach. The tool involves steps such as formatting/tokenization, scoring logits, initializing Z vector, deferral training, and generating results using multiple models. Co-LLM supports training with different collaboration pairs and provides baseline training scripts for various models. In inference, it uses 'vllm' services to orchestrate models and generate results through API-like services. The tool is inspired by allenai/open-instruct and aims to improve decoding performance through collaborative learning.

weblinx
WebLINX is a Python library and dataset for real-world website navigation with multi-turn dialogue. The repository provides code for training models reported in the WebLINX paper, along with a comprehensive API to work with the dataset. It includes modules for data processing, model evaluation, and utility functions. The modeling directory contains code for processing, training, and evaluating models such as DMR, LLaMA, MindAct, Pix2Act, and Flan-T5. Users can install specific dependencies for HTML processing, video processing, model evaluation, and library development. The evaluation module provides metrics and functions for evaluating models, with ongoing work to improve documentation and functionality.

vidur
Vidur is a high-fidelity and extensible LLM inference simulator designed for capacity planning, deployment configuration optimization, testing new research ideas, and studying system performance of models under different workloads and configurations. It supports various models and devices, offers chrome trace exports, and can be set up using mamba, venv, or conda. Users can run the simulator with various parameters and monitor metrics using wandb. Contributions are welcome, subject to a Contributor License Agreement and adherence to the Microsoft Open Source Code of Conduct.

tracecat
Tracecat is an open-source automation platform for security teams. It's designed to be simple but powerful, with a focus on AI features and a practitioner-obsessed UI/UX. Tracecat can be used to automate a variety of tasks, including phishing email investigation, evidence collection, and remediation plan generation.

BentoML
BentoML is an open-source model serving library for building performant and scalable AI applications with Python. It comes with everything you need for serving optimization, model packaging, and production deployment.

agents
Polymarket Agents is a developer framework and set of utilities for building AI agents to trade autonomously on Polymarket. It integrates with Polymarket API, provides AI agent utilities for prediction markets, supports local and remote RAG, sources data from various services, and offers comprehensive LLM tools for prompt engineering. The architecture features modular components like APIs and scripts for managing local environments, server set-up, and CLI for end-user commands.

dify-google-cloud-terraform
This repository provides Terraform configurations to automatically set up Google Cloud resources and deploy Dify in a highly available configuration. It includes features such as serverless hosting, auto-scaling, and data persistence. Users need a Google Cloud account, Terraform, and gcloud CLI installed to use this tool. The configuration involves setting environment-specific values and creating a GCS bucket for managing Terraform state. The tool allows users to initialize Terraform, create Artifact Registry repository, build and push container images, plan and apply Terraform changes, and cleanup resources when needed.

NekoImageGallery
NekoImageGallery is an online AI image search engine that utilizes the Clip model and Qdrant vector database. It supports keyword search and similar image search. The tool generates 768-dimensional vectors for each image using the Clip model, supports OCR text search using PaddleOCR, and efficiently searches vectors using the Qdrant vector database. Users can deploy the tool locally or via Docker, with options for metadata storage using Qdrant database or local file storage. The tool provides API documentation through FastAPI's built-in Swagger UI and can be used for tasks like image search, text extraction, and vector search.

LLM-Pruner
LLM-Pruner is a tool for structural pruning of large language models, allowing task-agnostic compression while retaining multi-task solving ability. It supports automatic structural pruning of various LLMs with minimal human effort. The tool is efficient, requiring only 3 minutes for pruning and 3 hours for post-training. Supported LLMs include Llama-3.1, Llama-3, Llama-2, LLaMA, BLOOM, Vicuna, and Baichuan. Updates include support for new LLMs like GQA and BLOOM, as well as fine-tuning results achieving high accuracy. The tool provides step-by-step instructions for pruning, post-training, and evaluation, along with a Gradio interface for text generation. Limitations include issues with generating repetitive or nonsensical tokens in compressed models and manual operations for certain models.

humanoid-gym
Humanoid-Gym is a reinforcement learning framework designed for training locomotion skills for humanoid robots, focusing on zero-shot transfer from simulation to real-world environments. It integrates a sim-to-sim framework from Isaac Gym to Mujoco for verifying trained policies in different physical simulations. The codebase is verified with RobotEra's XBot-S and XBot-L humanoid robots. It offers comprehensive training guidelines, step-by-step configuration instructions, and execution scripts for easy deployment. The sim2sim support allows transferring trained policies to accurate simulated environments. The upcoming features include Denoising World Model Learning and Dexterous Hand Manipulation. Installation and usage guides are provided along with examples for training PPO policies and sim-to-sim transformations. The code structure includes environment and configuration files, with instructions on adding new environments. Troubleshooting tips are provided for common issues, along with a citation and acknowledgment section.

landingai-python
The LandingLens Python library contains the LandingLens development library and examples that show how to integrate your app with LandingLens in a variety of scenarios. The library allows users to acquire images from different sources, run inference on computer vision models deployed in LandingLens, and provides examples in Jupyter Notebooks and Python apps for various tasks such as object detection, home automation, satellite image analysis, license plate detection, and streaming video analysis.

open-cuak
Open CUAK (Computer Use Agent) is a platform for managing automation agents at scale, designed to run and manage thousands of automation agents with reliability. It allows for abundant productivity by ensuring scalability and profitability. The project aims to usher in a new era of work with equally distributed productivity, making it open-sourced for real businesses and real people. The core features include running operator-like automation workflows locally, vision-based automation, turning any browser into an operator-companion, utilizing a dedicated remote browser, and more.

OneKE
OneKE is a flexible dockerized system for schema-guided knowledge extraction, capable of extracting information from the web and raw PDF books across multiple domains like science and news. It employs a collaborative multi-agent approach and includes a user-customizable knowledge base to enable tailored extraction. OneKE offers various IE tasks support, data sources support, LLMs support, extraction method support, and knowledge base configuration. Users can start with examples using YAML, Python, or Web UI, and perform tasks like Named Entity Recognition, Relation Extraction, Event Extraction, Triple Extraction, and Open Domain IE. The tool supports different source formats like Plain Text, HTML, PDF, Word, TXT, and JSON files. Users can choose from various extraction models like OpenAI, DeepSeek, LLaMA, Qwen, ChatGLM, MiniCPM, and OneKE for information extraction tasks. Extraction methods include Schema Agent, Extraction Agent, and Reflection Agent. The tool also provides support for schema repository and case repository management, along with solutions for network issues. Contributors to the project include Ningyu Zhang, Haofen Wang, Yujie Luo, Xiangyuan Ru, Kangwei Liu, Lin Yuan, Mengshu Sun, Lei Liang, Zhiqiang Zhang, Jun Zhou, Lanning Wei, Da Zheng, and Huajun Chen.

Stellar-Chat
Stellar Chat is a multi-modal chat application that enables users to create custom agents and integrate with local language models and OpenAI models. It provides capabilities for generating images, visual recognition, text-to-speech, and speech-to-text functionalities. Users can engage in multimodal conversations, create custom agents, search messages and conversations, and integrate with various applications for enhanced productivity. The project is part of the '100 Commits' competition, challenging participants to make meaningful commits daily for 100 consecutive days.
For similar tasks

ai-on-gke
This repository contains assets related to AI/ML workloads on Google Kubernetes Engine (GKE). Run optimized AI/ML workloads with Google Kubernetes Engine (GKE) platform orchestration capabilities. A robust AI/ML platform considers the following layers: Infrastructure orchestration that support GPUs and TPUs for training and serving workloads at scale Flexible integration with distributed computing and data processing frameworks Support for multiple teams on the same infrastructure to maximize utilization of resources

ray
Ray is a unified framework for scaling AI and Python applications. It consists of a core distributed runtime and a set of AI libraries for simplifying ML compute, including Data, Train, Tune, RLlib, and Serve. Ray runs on any machine, cluster, cloud provider, and Kubernetes, and features a growing ecosystem of community integrations. With Ray, you can seamlessly scale the same code from a laptop to a cluster, making it easy to meet the compute-intensive demands of modern ML workloads.

labelbox-python
Labelbox is a data-centric AI platform for enterprises to develop, optimize, and use AI to solve problems and power new products and services. Enterprises use Labelbox to curate data, generate high-quality human feedback data for computer vision and LLMs, evaluate model performance, and automate tasks by combining AI and human-centric workflows. The academic & research community uses Labelbox for cutting-edge AI research.

djl
Deep Java Library (DJL) is an open-source, high-level, engine-agnostic Java framework for deep learning. It is designed to be easy to get started with and simple to use for Java developers. DJL provides a native Java development experience and allows users to integrate machine learning and deep learning models with their Java applications. The framework is deep learning engine agnostic, enabling users to switch engines at any point for optimal performance. DJL's ergonomic API interface guides users with best practices to accomplish deep learning tasks, such as running inference and training neural networks.

mlflow
MLflow is a platform to streamline machine learning development, including tracking experiments, packaging code into reproducible runs, and sharing and deploying models. MLflow offers a set of lightweight APIs that can be used with any existing machine learning application or library (TensorFlow, PyTorch, XGBoost, etc), wherever you currently run ML code (e.g. in notebooks, standalone applications or the cloud). MLflow's current components are:
* `MLflow Tracking

tt-metal
TT-NN is a python & C++ Neural Network OP library. It provides a low-level programming model, TT-Metalium, enabling kernel development for Tenstorrent hardware.

burn
Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.

awsome-distributed-training
This repository contains reference architectures and test cases for distributed model training with Amazon SageMaker Hyperpod, AWS ParallelCluster, AWS Batch, and Amazon EKS. The test cases cover different types and sizes of models as well as different frameworks and parallel optimizations (Pytorch DDP/FSDP, MegatronLM, NemoMegatron...).
For similar jobs

weave
Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack
LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

VisionCraft
The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

kaito
Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT
PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

tabby
Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

spear
SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick
Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.