Get in Touch

Course Outline

Introduction to Cambricon and MLU Architecture

  • Overview of Cambricon’s AI chip portfolio
  • MLU architecture and instruction pipeline
  • Supported model types and application scenarios

Installing the Development Toolchain

  • Installation of BANGPy and Neuware SDK
  • Setting up environments for Python and C++
  • Model compatibility and preprocessing

Model Development with BANGPy

  • Tensor structure and shape management
  • Construction of computation graphs
  • Support for custom operations in BANGPy

Deploying with Neuware Runtime

  • Model conversion and loading procedures
  • Controlling execution and inference
  • Best practices for edge and data center deployment

Performance Optimization

  • Memory mapping and layer tuning
  • Execution tracing and profiling
  • Identifying common bottlenecks and implementing fixes

Integrating MLU into Applications

  • Utilizing Neuware APIs for seamless application integration
  • Support for streaming and multi-model workloads
  • Hybrid CPU-MLU inference scenarios

End-to-End Project and Use Case

  • Lab: Deploying a vision or NLP model
  • Edge inference integrated with BANGPy
  • Evaluating accuracy and throughput

Summary and Next Steps

Requirements

  • A solid grasp of machine learning model architectures
  • Proficiency in Python and/or C++
  • Knowledge of model deployment and acceleration principles

Target Audience

  • Embedded AI developers
  • ML engineers focusing on edge or data center deployment
  • Developers utilizing Chinese AI infrastructure
 21 Hours

Number of participants


Price per participant

Testimonials (1)

Upcoming Courses

Related Categories