Deeploy Documentation

Deeploy is an ONNX-to-C compiler that generates low-level optimized C Code for multi-cluster, heterogeneous SoCs. Its goal is to enable configurable deployment flows from a bottom-up compiler perspective, modeling target hardware in a fine-grained and modular manner.

Deeploy is developed as part of the PULP project, a joint effort between ETH Zurich and the University of Bologna.

Contents:

• Quickstart
  • Library Installation
    • Installing system dependencies
    • Bootstrapping pip
    • Installing Deeploy
  • Testing Framework Installation
  • Getting Started
• Tutorials
  • Neural Network Deeployment on the PULP Platform
    • Installation
    • Deeploy 101
    • Micro Llama on Siracusa
  • Debugging
    • Printing Tensor Values
• Library Structure
  • Deeploy
    • Targets
    • Extensions
• API Reference
  • Deeploy
    • Deeploy.AbstractDataTypes
    • Deeploy.CommonExtensions
    • Deeploy.DeeployTypes
    • Deeploy.EngineExtension
    • Deeploy.FutureExtension
    • Deeploy.MemoryLevelExtension
    • Deeploy.Targets
    • Deeploy.TilingExtension