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
- Insight into Cambricon’s AI chip portfolio
- MLU architecture and instruction pipeline details
- Overview of supported model types and applicable use cases
Setting Up the Development Toolchain
- Installation procedures for BANGPy and Neuware SDK
- Configuring the environment for Python and C++ development
- Ensuring model compatibility and handling preprocessing
Building Models with BANGPy
- Managing tensor structures and shapes
- Constructing computation graphs
- Implementing custom operation support within BANGPy
Deployment via Neuware Runtime
- Processes for converting and loading models
- Controlling execution and inference
- Best practices for edge and data center deployment
Enhancing Performance
- Optimizing memory mapping and layer tuning
- Utilizing execution tracing and profiling tools
- Identifying common bottlenecks and implementing fixes
Integrating MLUs into Applications
- Leveraging Neuware APIs for seamless application integration
- Supporting streaming and multi-model scenarios
- Handling hybrid CPU-MLU inference workflows
Comprehensive Project and Practical Use Case
- Lab session: Deploying a vision or NLP model
- Implementing edge inference with BANGPy integration
- Evaluating accuracy and throughput
Conclusion and Future Directions
Requirements
- Foundational knowledge of machine learning model architectures
- Proficiency in Python and/or C++
- Understanding of model deployment and acceleration principles
Target Audience
- Embedded AI developers
- ML engineers specializing in edge or datacenter deployments
- Developers working within the Chinese AI infrastructure ecosystem
Testimonials (1)
That we can cover advance topic and work with real-life example
