Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 21 hours
Course Outline
Introduction to Cambricon and MLU Architecture
- Snapshot of Cambricon’s AI chip lineup
- MLU architecture and instruction flow
- Compatible model types and typical applications
Setting Up the Development Toolchain
- Installing BANGPy and the Neuware SDK
- Configuring Python and C++ environments
- Ensuring model compatibility and preprocessing
Building Models with BANGPy
- Managing tensor structures and dimensions
- Constructing computation graphs
- Support for custom operations within BANGPy
Deployment via Neuware Runtime
- Model conversion and loading processes
- Controlling execution and inference
- Best practices for edge and data center deployment
Enhancing Performance
- Memory mapping and layer adjustment
- Tracing and profiling execution
- Identifying and resolving common bottlenecks
Embedding MLU into Applications
- Leveraging Neuware APIs for seamless integration
- Support for streaming and multi-model setups
- Scenarios involving hybrid CPU-MLU inference
End-to-End Project and Practical Application
- Workshop: Releasing a vision or NLP model
- Edge inference integrated with BANGPy
- Validating accuracy and throughput
Recap and Future Directions
Requirements
- A solid grasp of machine learning model architectures
- Practical experience with Python and/or C++
- Knowledge of model deployment and acceleration principles
Target Audience
- Embedded AI developers
- ML engineers targeting edge or datacenter environments
- Developers collaborating with Chinese AI infrastructure
Testimonials (1)
That we can cover advance topic and work with real-life example
