Intel® Extension for Transformers
latest▼

Click link above to switch version

  • Getting Started
  • Installation
  • User Guide
    • Features
    • Neural Engine
      • Deploy and Integration
      • Compile an ONNX model to Engine IR
      • Quantize a ONNX model to engine low precision/int8 IR
      • Profiling
      • Engine Tuning
      • Graph Fusion
      • Pattern Recognize
      • Customized Operators Register
      • Add Customized Pattern
    • Kernels
  • Example
  • API
  • OpenSSF Badge
  • Security Policy
  • Release
  • Legal Information
  • Repo
Intel® Extension for Transformers
  • User Guide
  • Neural Engine
  • View page source

Neural Engine

Contents:

  • Deploy and Integration
  • Compile an ONNX model to Engine IR
  • Quantize a ONNX model to engine low precision/int8 IR
  • Profiling
  • Engine Tuning
  • Graph Fusion
  • Pattern Recognize
  • Customized Operators Register
  • Add Customized Pattern
Previous Next

© Copyright 2022, Intel® Extension for Transformers, Intel.

Built with Sphinx using a theme provided by Read the Docs.

Cookies | Privacy