User Manual

• Introduction
  • Technical Background
  • Distribution Contents
    • Release Package
    • Docker Image
  • System Requirements
  • Getting Started
  • Support and Contact
• Quickstart
  • Setup
    • Release Package Ubuntu 24.04
    • Docker Image
  • Compile and Run the Model
• Model Preparation
  • Overview
  • Convert a TFLite model to TOSA and MLIR
  • Convert Torch Model to MLIR
  • Convert ONNX Model to MLIR
  • References
• Input Guide
  • Supported model formats for torq-compile
  • Input Structure for torq-run-module
    • Literal Inputs
    • Multiple Inputs
    • Feeding Input from Files
    • Converting Images to .npy or .bin
• Step-by-Step Model Deployment Examples
  • Prerequisites
  • Prepare Model (Convert to MLIR)
  • Compile for Device
    • Example: TFLite model (MobileNetV2)
    • Example: ONNX model
  • Run Inference on Torq
    • Using the Python Bindings
  • Compiling for Host (Simulation)
  • Handling Unsupported Operations
• Torq Runtime Python API (Beta)
  • Installation
  • Quick Start
  • API Reference
    • VMFBInferenceRunner
      • infer(inputs)
    • profile_vmfb_inference_time
    • run_vmfb
    • TensorInfo
    • Utility Functions
      • random_inputs_from_info(inputs_info)
  • Examples
    • Inspecting Model Inputs and Outputs
    • Profiling Inference Latency
    • Running with Custom Inputs
• Supported Operators
  • Activation related Operators
  • Element-Wise Operators
  • Composite Operators
  • Other Operators
• Profiling
  • Compile-Time Profiling
  • Runtime Profiling
  • Profiling with the Test Framework
    • Wall-time measurement
• Handling Unsupported Ops
  • CSS Fallback
  • Host Fallback
• Compiling Models for Custom Synaptics SoCs
  • NSS Subsystem Overview
  • Custom Hardware Configuration
    • Example Configurations
• Debug tips and tricks
• References
• Glossary
• Release Notes
  • Version 0.9.0
    • Key Features & Enhancements
    • Fixed Issues
    • Known Issues
    • Breaking Changes in This Release
    • Deprecated Features
    • Documentation