Optimal AzureML Triton Model Deployment using the Model Analyzer
, Developer Relations Manager, NVIDIA
, Program Manager, Azure Machine Learning, Microsoft
, Solutions Architect, NVIDIA
We'll discuss the Triton Model Analyzer tool and its role in generating the optimal model configuration that can be hosted on the AzureML. We'll cover optimizations of various hyperparameters, along with framework-specific optimizations that can be sweeped using Model Analyzer. The reports generated at the end help users deploy their model’s inference performance on AzureML and highlight the performance gains.