IPU Inference Toolkit Quick Start

• 1. Overview
  • 1.1. IPU inference architecture
• 2. Model compilation
  • 2.1. Model download
  • 2.2. Model conversion and compilation
• 3. Model runtime
  • 3.1. Run with PopRT Runtime
    • 3.1.1. Environment preparation
    • 3.1.2. Run with PopRT Runtime Python API
    • 3.1.3. Run with PopRT Runtime C++ API
  • 3.2. Deploy with Triton Inference Server
    • 3.2.1. Configuration of the generated model
    • 3.2.2. Activation of model service
    • 3.2.3. Verification services via gRPC
• 4. Trademarks & copyright