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
Cambricon and MLU Architecture Overview
- Exploring Cambricon’s AI chip portfolio
- Understanding MLU architecture and instruction pipelines
- Identifying supported model types and relevant use cases
Setting Up the Development Toolchain
- Installing BANGPy and the Neuware SDK
- Configuring the environment for Python and C++
- Managing model compatibility and preprocessing steps
Model Development with BANGPy
- Handling tensor structures and shape management
- Constructing computation graphs
- Implementing custom operation support within BANGPy
Deployment via Neuware Runtime
- Converting and loading models effectively
- Controlling execution and inference processes
- Best practices for edge and data center deployment
Optimizing Performance
- Applying memory mapping and layer tuning techniques
- Utilizing execution tracing and profiling tools
- Identifying and resolving common performance bottlenecks
Application Integration with MLUs
- Leveraging Neuware APIs for seamless application integration
- Implementing streaming and multi-model support
- Designing hybrid CPU-MLU inference scenarios
End-to-End Project and Use Case
- Lab session: Deploying a vision or NLP model
- Implementing edge inference with BANGPy integration
- Validating accuracy and throughput metrics
Course Summary and Future Steps
Requirements
- A solid grasp of machine learning model architectures
- Proficiency in Python and/or C++
- Working knowledge of model deployment and acceleration principles
Target Audience
- Embedded AI developers
- ML engineers focused on edge or data center deployments
- Developers utilizing Chinese AI infrastructure
Testimonials (1)
That we can cover advance topic and work with real-life example
