Understanding Huawei’s AI Compute Stack: From CANN to MindSpore Training Course

The Huawei Ascend series comprises specialized AI processors engineered for high-throughput inference and model training workloads.

This live, instructor-led session, available online or onsite, is tailored for intermediate AI engineers and data scientists aiming to build and refine neural network models using the Huawei Ascend platform alongside the CANN toolkit.

Upon completion, participants will gain the capability to:

• Configure and prepare the CANN development environment.
• Construct AI applications leveraging MindSpore and CloudMatrix workflows.
• Enhance Ascend NPU performance through custom operators and tiling techniques.
• Deploy models into edge or cloud-based infrastructures.

Course Format

• Engaging lectures combined with open discussions.
• Practical application of Huawei Ascend and the CANN toolkit within sample projects.
• Structured exercises emphasizing model construction, training, and deployment.

Customization Opportunities

• For training tailored to your specific infrastructure or datasets, please reach out to us to discuss arrangements.

This live training session Thailand guides intermediate AI developers through the process of deploying models on Ascend processors using the CANN toolkit. The course covers converting frameworks like PyTorch and TensorFlow, optimizing performance, and troubleshooting issues to ensure efficient edge and cloud inference.

CANN (Compute Architecture for Neural Networks) serves as Huawei’s essential AI computing toolkit, designed to compile, optimize, and deploy AI models on Ascend AI processors.

This instructor-led, live training (available online or onsite) is tailored for beginner-level AI developers seeking to understand how CANN integrates into the model lifecycle, from training through to deployment, and how it collaborates with frameworks such as MindSpore, TensorFlow, and PyTorch.

Upon completion of this training, participants will be equipped to:

• Grasp the purpose and underlying architecture of the CANN toolkit.
• Configure a development environment utilizing CANN and MindSpore.
• Convert and deploy a simple AI model onto Ascend hardware.
• Acquire foundational knowledge to support future CANN optimization or integration projects.

Course Format

• Interactive lectures and facilitated discussions.
• Hands-on labs focused on simple model deployment.
• Detailed walkthroughs of the CANN toolchain and its integration points.

Course Customization Options

• To request a customized training solution for this course, please reach out to us to arrange the details.

Huawei’s Ascend CANN toolkit facilitates high-performance AI inference on edge hardware, including the Ascend 310. Designed for environments with limited compute and memory resources, CANN offers the critical utilities needed to compile, optimize, and deploy models effectively.

This live, instructor-led session (available online or onsite) is tailored for intermediate AI developers and integrators looking to refine model deployment and optimization on Ascend edge devices using the CANN ecosystem.

Upon completing this training, participants will possess the skills to:

• Prep and transform AI models for the Ascend 310 utilizing CANN utilities.
• Construct efficient inference workflows using MindSpore Lite and AscendCL.
• Enhance model efficiency within restricted compute and memory landscapes.
• Implement and oversee AI applications in practical edge scenarios.

Course Structure

• Engaging lectures paired with live demonstrations.
• Practical lab exercises focusing on edge-specific models and use cases.
• Real-time deployment showcases on virtual or physical edge infrastructure.

Customization Possibilities

• To arrange a tailored training experience for this course, please reach out to our team.

The CANN SDK (Compute Architecture for Neural Networks) serves as Huawei's core AI computing infrastructure, empowering developers to refine and maximize the performance of neural networks deployed on Ascend AI processors.

This live, instructor-led training (available online or onsite) is designed for advanced AI developers and system engineers seeking to elevate inference performance. It leverages CANN's comprehensive toolset, including the Graph Engine, TIK, and capabilities for custom operator development.

Upon completion, participants will be equipped to:

• Comprehend the CANN runtime architecture and its performance lifecycle.
• Leverage profiling tools and the Graph Engine for deep performance analysis and optimization.
• Develop and optimize custom operators utilizing TIK and TVM.
• Address memory bottlenecks and enhance overall model throughput.

Course Format

• Engaging lectures paired with open discussions.
• Practical labs featuring real-time profiling and operator tuning.
• Optimization exercises based on complex edge-case deployment scenarios.

Customization Opportunities

• Please reach out to us to discuss arranging a customized training experience for this course.

The CANN SDK (Compute Architecture for Neural Networks) offers robust deployment and optimization capabilities for real-time AI applications in computer vision and NLP, particularly when targeting Huawei Ascend hardware.

Designed as an instructor-led, live training experience available online or onsite, this course is tailored for intermediate-level AI practitioners looking to build, deploy, and optimize vision and language models for production environments using the CANN SDK.

Upon completing this training, participants will be equipped to:

• Deploy and fine-tune CV and NLP models leveraging CANN and AscendCL.
• Utilize CANN tools to convert models and seamlessly integrate them into live pipelines.
• Enhance inference performance for tasks such as object detection, classification, and sentiment analysis.
• Construct real-time CV/NLP pipelines suitable for edge or cloud-based deployment scenarios.

Course Format

• Engaging lectures paired with live demonstrations.
• Practical hands-on labs focused on model deployment and performance profiling.
• Designing live pipelines using authentic CV and NLP use cases.

Customization Options

• To arrange a customized version of this training, please get in touch with our team.

CANN TIK (Tensor Instruction Kernel) and Apache TVM enable advanced optimization and customization of AI model operators for Huawei Ascend hardware.

This instructor-led, live training (online or onsite) is aimed at advanced-level system developers who wish to build, deploy, and tune custom operators for AI models using CANN’s TIK programming model and TVM compiler integration.

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

• Write and test custom AI operators using the TIK DSL for Ascend processors.
• Integrate custom ops into the CANN runtime and execution graph.
• Use TVM for operator scheduling, auto-tuning, and benchmarking.
• Debug and optimize instruction-level performance for custom computation patterns.

Format of the Course

• Interactive lecture and demonstration.
• Hands-on coding of operators using TIK and TVM pipelines.
• Testing and tuning on Ascend hardware or simulators.

Course Customization Options

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