Vanna Labs
  • Introduction
    • 👋Welcome
    • ✨Summary
  • Vision
    • 🏪The AI One-Stop-Shop
      • AI Models on Vanna
      • Applied ML on Vanna
    • 🤝Interoperability
    • ✅Computational Verifiability
    • 🌐Decentralization
    • 🛡️Censorship Resistance
  • Vanna Network
    • 🏗️Architecture
      • Data Preprocessing
      • Parallelized Inference Pre-Execution (PIPE)
      • Validation-Computation Separation (VCS)
      • Cryptoeconomic Security
      • Modular Design
    • ⚙️Inference Modes
      • Vanilla Inference
      • zkML Inference
      • zkFP Inference
      • opML Inference
      • TEE Inference
    • 💿Data Storage
      • Model Storage
      • Data Availability
    • 💻Portal
  • Build
    • 🛠️Getting started
      • Networks
      • Faucets
      • Model Storage
    • 💻Building dApps
      • Data Preprocessing
      • Inference API
      • Inference Example
    • 💾Models
      • Supported LLMs
  • 🔗Links
  • Key Concepts
    • 🧠AI x Blockchain
    • 📜Optimistic Rollups
    • 💾Data Availability
    • ⚡zkML
    • ☀️opML
Powered by GitBook
On this page
  1. Vanna Network

Architecture

High-level Vanna Network Architecture

PreviousCensorship ResistanceNextData Preprocessing

Last updated 1 year ago

Vanna is an EVM-compatible blockchain that can support native AI/ML inference directly computed, secured, and verified on-chain. The network will store both generic block data and inference transaction data onto a DA layer.

The Vanna Network also has its own decentralized filestore layer built off of an IPFS swarm. The CID hash from model storage is used as the model identifier on the Vanna Network for inference.

For a better understanding of the data flow of on-chain inference and how it works on the Vanna Network, take a look at the data flow diagram below.

For more details on our vision for an end-to-end inference process on-chain, check out the AI One-Stop-Shop section.

🏗️
🏪The AI One-Stop-Shop