This instructor-led live training in 台北 explores Huawei's AI stack, from the CANN SDK to the MindSpore framework. It helps beginners and intermediate professionals understand how these components integrate on Ascend hardware for lifecycle management and deployment.
This instructor-led training in 台北 covers deploying and optimizing CV and NLP models using the CANN SDK for Ascend hardware. Participants will learn to convert models, integrate them into live pipelines, and enhance inference performance for real-time detection and analysis.
This instructor-led, live training in 台北 equips advanced developers with the skills to build, deploy, and tune custom AI operators. Participants will master CANN TIK and Apache TVM integration, enabling advanced optimization and scheduling on Huawei Ascend hardware for real-world performance.
This instructor-led, live training in 台北 covers the core concepts and hands-on fundamentals of deploying AI models on Ascend edge devices using the CANN toolkit, helping participants build practical skills for compiling, optimizing, and managing constrained environments.
This live training in 台北 introduces the CANN toolkit for AI framework developers. Learn to set up environments, convert models, and deploy applications on Ascend hardware using MindSpore, TensorFlow, or PyTorch, covering the full workflow from training to inference.
Optimize AI workloads on Ascend, Biren, and Cambricon with this hands-on training in 台北. Learn to benchmark models, identify bottlenecks, and apply graph, kernel, and operator-level optimizations. Tune deployment pipelines to enhance throughput and latency across these leading platforms.
Optimize neural network inference performance on Ascend AI processors with this advanced, instructor-led training in 台北. Explore CANN's runtime architecture, leveraging the Graph Engine, TIK, and TVM for profiling, custom operator development, and memory bottleneck resolution.
Migrate CUDA applications to Chinese GPU architectures like Huawei Ascend and Biren in 台北. This instructor-led course guides advanced programmers through code translation and performance optimization, covering hands-on labs for porting CUDA codebases to new SDKs.