
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.

llm-foundry
LLM Foundry is a codebase for training, finetuning, evaluating, and deploying LLMs for inference with Composer and the MosaicML platform. It is designed to be easy-to-use, efficient _and_ flexible, enabling rapid experimentation with the latest techniques. You'll find in this repo: * `llmfoundry/` - source code for models, datasets, callbacks, utilities, etc. * `scripts/` - scripts to run LLM workloads * `data_prep/` - convert text data from original sources to StreamingDataset format * `train/` - train or finetune HuggingFace and MPT models from 125M - 70B parameters * `train/benchmarking` - profile training throughput and MFU * `inference/` - convert models to HuggingFace or ONNX format, and generate responses * `inference/benchmarking` - profile inference latency and throughput * `eval/` - evaluate LLMs on academic (or custom) in-context-learning tasks * `mcli/` - launch any of these workloads using MCLI and the MosaicML platform * `TUTORIAL.md` - a deeper dive into the repo, example workflows, and FAQs

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.

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.

magika
Magika is a novel AI-powered file type detection tool that relies on deep learning to provide accurate detection. It employs a custom, highly optimized model to enable precise file identification within milliseconds. Trained on a dataset of ~100M samples across 200+ content types, achieving an average ~99% accuracy. Used at scale by Google to improve user safety by routing files to security scanners. Available as a command line tool in Rust, Python API, and bindings for Rust, JavaScript/TypeScript, and GoLang.

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.

jina
Jina is a tool that allows users to build multimodal AI services and pipelines using cloud-native technologies. It provides a Pythonic experience for serving ML models and transitioning from local deployment to advanced orchestration frameworks like Docker-Compose, Kubernetes, or Jina AI Cloud. Users can build and serve models for any data type and deep learning framework, design high-performance services with easy scaling, serve LLM models while streaming their output, integrate with Docker containers via Executor Hub, and host on CPU/GPU using Jina AI Cloud. Jina also offers advanced orchestration and scaling capabilities, a smooth transition to the cloud, and easy scalability and concurrency features for applications. Users can deploy to their own cloud or system with Kubernetes and Docker Compose integration, and even deploy to JCloud for autoscaling and monitoring.

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.

KlicStudio
Klic Studio is a versatile audio and video localization and enhancement solution developed by Krillin AI. This minimalist yet powerful tool integrates video translation, dubbing, and voice cloning, supporting both landscape and portrait formats. With an end-to-end workflow, users can transform raw materials into beautifully ready-to-use cross-platform content with just a few clicks. The tool offers features like video acquisition, accurate speech recognition, intelligent segmentation, terminology replacement, professional translation, voice cloning, video composition, and cross-platform support. It also supports various speech recognition services, large language models, and TTS text-to-speech services. Users can easily deploy the tool using Docker and configure it for different tasks like subtitle translation, large model translation, and optional voice services.

lerobot
LeRobot is a state-of-the-art AI library for real-world robotics in PyTorch. It aims to provide models, datasets, and tools to lower the barrier to entry to robotics, focusing on imitation learning and reinforcement learning. LeRobot offers pretrained models, datasets with human-collected demonstrations, and simulation environments. It plans to support real-world robotics on affordable and capable robots. The library hosts pretrained models and datasets on the Hugging Face community page.

slidev-ai
Slidev AI is a web app that leverages LLM (Large Language Model) technology to make creating Slidev-based online presentations elegant and effortless. It is designed to help engineers and academics quickly produce content-focused, minimalist PPTs that are easily shareable online. This project serves as a reference implementation for OpenMCP agent development, a production-ready presentation generation solution, and a template for creating domain-specific AI agents.

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.

ArcticTraining
ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs). It offers modular trainer designs, simplified code structures, and integrated pipelines for creating and cleaning synthetic data, enabling users to enhance LLM capabilities like code generation and complex reasoning with greater efficiency and flexibility.

KrillinAI
KrillinAI is a video subtitle translation and dubbing tool based on AI large models, featuring speech recognition, intelligent sentence segmentation, professional translation, and one-click deployment of the entire process. It provides a one-stop workflow from video downloading to the final product, empowering cross-language cultural communication with AI. The tool supports multiple languages for input and translation, integrates features like automatic dependency installation, video downloading from platforms like YouTube and Bilibili, high-speed subtitle recognition, intelligent subtitle segmentation and alignment, custom vocabulary replacement, professional-level translation engine, and diverse external service selection for speech and large model services.

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.
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.