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.
Course Outline
Introduction to the Huawei AI Ecosystem
- Overview of Ascend AI hardware variants: 310, 910, and 910B
- Key components: MindSpore, CANN, and AscendCL
- Market positioning and core architectural principles
The Function of CANN within Huawei's AI Stack
- Defining CANN: SDK objectives and internal structural layers
- ATC, TBE, and AscendCL: processes for compiling and running models
- Strategies for inference optimization and deployment supported by CANN
MindSpore: Architecture and Capabilities
- Training and inference workflows within MindSpore
- Graph mode, PyNative, and mechanisms for hardware abstraction
- Connecting with Ascend NPUs through the CANN backend
AI Lifecycle on Ascend: From Training to Deployment
- Creating models in MindSpore or migrating from other frameworks
- Exporting and compiling models utilizing ATC
- Deploying on Ascend hardware via OM models and AscendCL
Benchmarking Against Other AI Stacks
- MindSpore vs. PyTorch and TensorFlow: differing focuses and market positioning
- Deployment workflows on Ascend compared to GPU-based ecosystems
- Opportunities and constraints for enterprise adoption
Enterprise Integration Case Studies
- Applications in smart manufacturing, government AI initiatives, and telecommunications
- Considerations for scalability, regulatory compliance, and ecosystem integration
- Hybrid cloud and on-premise deployments leveraging the Huawei stack
Recap and Recommended Path Forward
Requirements
- General awareness of AI workflows or platform architecture
- Foundational knowledge of model training and deployment processes
- No prior practical experience with CANN or MindSpore is necessary
Target Audience
- AI platform assessors and infrastructure architects
- AI/ML DevOps specialists and pipeline integration experts
- Technology leaders and strategic decision-makers
14 Hours
