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 14 hours
Course Outline
Intro to Huawei's AI Ecosystem
- Ascend AI hardware: Overview of 310, 910, and 910B models
- Key components: MindSpore, CANN, and AscendCL
- Market positioning and foundational architecture concepts
The Function of CANN within Huawei's AI Stack
- CANN definition: SDK objectives and internal structure
- ATC, TBE, and AscendCL: Model compilation and execution processes
- How CANN enhances inference performance and deployment efficiency
MindSpore: Overview and Design
- Training and inference processes within MindSpore
- Graph mode, PyNative, and hardware abstraction layers
- Connecting to Ascend NPUs through the CANN backend
AI Lifecycle on Ascend: From Training to Deployment
- Building models in MindSpore or converting from external frameworks
- Model export and compilation via ATC
- Deploying on Ascend hardware using OM models and AscendCL
Benchmarking Against Other AI Stacks
- MindSpore vs. PyTorch and TensorFlow: Strategic focus and positioning
- Deployment processes on Ascend compared to GPU-centric architectures
- Potential benefits and constraints for enterprise applications
Enterprise Application Scenarios
- Applications in smart manufacturing, government AI initiatives, and telecommunications
- Considerations regarding scalability, regulatory compliance, and ecosystem support
- Hybrid cloud/on-premises deployment utilizing the Huawei stack
Recap and Future Actions
Requirements
- General awareness of AI processes or platform design
- Fundamental knowledge of model training and deployment procedures
- No previous practical experience with CANN or MindSpore is necessary
Target Audience
- AI platform assessors and infrastructure designers
- AI/ML DevOps specialists and pipeline integrators
- Technology leaders and strategic decision-makers
