Skip to content

AIGrid for Developers and Creators

✨ What Can You Do with OpenOS?

  • Connect Kubernetes clusters into a global compute network
  • Deploy your AI models (like LLMs or vision models) as reusable Blocks
  • Deploy multiple blocks on same GPU to save resources
  • Define workflows using vDAGs (virtual Directed Acyclic Graphs)
  • Share and re-use models, data, blocks and compute infrastructure
  • Use Python policies to control how the network behaves
  • Extend your Blocks with third-party tools via init containers
  • Collect and use metrics to make smart decisions and observe the network

🧰 Key Features

Feature What It Means
🌍 Global Clustering Connect clusters into a unified network
⚙️ Smart Scheduling Run AI tasks where resources are available
🛠️ Python Policies Use Python scripts to control the system
🧱 Modular Blocks Reusable building blocks for AI
🧠 Split LLMs Run parts of a model across machines
🧪 GPU Sharing Run multiple jobs on the same GPU
🔗 Distributed Graphs Define workflows across blocks and clusters
📦 Plug in Tools Bring your own frameworks, models, or services
📡 Send Tasks Easily Submit tasks through gRPC APIs
🔍 Observe Everything Track system performance with metrics

For the detailed breakdown of features visit this link

🚀 Getting Started

🧩 Essentials
AIGrid component semantic diagram
AIGrid component writeup
Paper
Concepts
Architecture
🧭 User Flow Guides
Network Creator & Admin Flow
Cluster Contributor & Admin Flow
Node Contributor Flow
Block Creator Flow
vDAG Creator Flow
End User (Inference Task Submitter) Flow
⚙️ Installation
Network Creation
Onboarding Cluster
Onboarding Node to a Cluster

🚀 Quickstart

  1. Creating a network

  2. Create your own network

  3. Add clusters and nodes
  4. Deploy AI models
  5. Connect external systems

  6. Split and run large models across multiple GPUs

  7. Joining a node to an already existing cluster

  8. Simple block deployment across multiple GPUs (Reference model considered: Mistral7B LLM)

  9. Simple block deployment on a single GPU (Sample model considered: YOLOv5

  10. Linking an externally deployed vLLM system to the block for serving

  11. Deploying a vDAG and submitting inference tasks to the vDAG

📚 Learn More

Section Link
📄 Concept Overview Concepts
🛠️ Setup Instructions Installation Guide
🧪 Tutorials Quickstart
🗂️ User Guides User Flows