Deploying AI Models with CANN and Ascend AI Processors

• Experience with Python-based deep learning frameworks such as TensorFlow or PyTorch
• Understanding of neural network architectures and model training workflows
• Basic familiarity with Linux CLI and scripting

Audience

• AI engineers working with model deployment
• Machine learning practitioners targeting hardware acceleration
• Deep learning developers building inference solutions

CANN (Compute Architecture for Neural Networks) is Huawei’s AI compute stack for deploying and optimizing AI models on Ascend AI processors.

This instructor-led, live training (online or onsite) is aimed at intermediate-level AI developers and engineers who wish to deploy trained AI models efficiently to Huawei Ascend hardware using the CANN toolkit and tools such as MindSpore, TensorFlow, or PyTorch.

By the end of this training, participants will be able to:

• Understand the CANN architecture and its role in the AI deployment pipeline.
• Convert and adapt models from popular frameworks to Ascend-compatible formats.
• Use tools like ATC, OM model conversion, and MindSpore for edge and cloud inference.
• Diagnose deployment issues and optimize performance on Ascend hardware.

Format of the Course

• Interactive lecture and demonstration.
• Hands-on lab work using CANN tools and Ascend simulators or devices.
• Practical deployment scenarios based on real-world AI models.

Course Customization Options

• To request a customized training for this course, please contact us to arrange.

Introduction to CANN and Ascend AI Processors

• What is CANN? Role in Huawei’s AI compute stack
• Overview of Ascend processor architecture (310, 910, etc.)
• Supported AI frameworks and toolchain overview

Model Conversion and Compilation

• Using the ATC tool for model conversion (TensorFlow, PyTorch, ONNX)
• Creating and validating OM model files
• Handling unsupported operators and common conversion issues

Deploying with MindSpore and Other Frameworks

• Deploying models with MindSpore Lite
• Integrating OM models with Python APIs or C++ SDKs
• Working with Ascend Model Manager

Performance Optimization and Profiling

• Understanding AI Core, memory, and tiling optimizations
• Profiling model execution with CANN tools
• Best practices for improving inference speed and resource usage

Error Handling and Debugging

• Common deployment errors and their resolution
• Reading logs and using the error diagnosis tool
• Unit testing and functional validation of deployed models

Edge and Cloud Deployment Scenarios

• Deploying to Ascend 310 for edge applications
• Integration with cloud-based APIs and microservices
• Real-world case studies in computer vision and NLP

Summary and Next Steps