In this third part episode, Roberto Cervantes walks through the different considerations customers must think through when designing a highly available application built on the Azure Kubernetes Service.
In this second part episode, Fernando Mejia walks through everything you need to plan for in a Hybrid Cloud architecture for Azure Kubernetes Service.
This includes IP address concerns from on-premises to Azure, hub and spoke topology, as well as the different options you have in Azure Kubernetes Service.
ONNX Runtime inference engine is capable of executing ML models in different HW environments, taking advantage of the neural network acceleration capabilities.
Microsoft and Xilinx worked together to integrate ONNX Runtime with the VitisAI SW libraries for executing ONNX models in the Xilinx U250 FPGAs. We are happy to introduce the preview release of this capability today.
Video index:
[06:15] Demo by PeakSpeed for satellite imaging Orthorectification
The next step is deployment and, arguably, it’s the most important.
That final stage – the crucial cog in your machine learning or deep learning project – is model deployment. You need to be able to get the model to the end user, right? And here’s the irony – the majority of courses, influencers, and even experts – nobody espouses the value of model deployment
[00:00] – Introduction
[00:41] – Deployment options in Azure SQL Database, including elastic pool, single database and Managed Instance
[03:33] – DTU service tiers (Basic, Standard, Premium)
[07:08] – vCore service tiers (General Purpose, Hyperscale, Business Critical)
[08:08] – General Purpose tier: Provisioned vs Serverless
[09:16] – Compute Generation: Gen4 vs Gen5
[10:01] – Decision points for Provisioned vs Serverless compute tiers
[13:25] – Saving money with Azure Hybrid Use Benefits
[13:58] – Business Critical tier and read scale-out
[15:42] – Hyperscale tier
[21:03] – Summary of deployment options
[22:17] – Finalizing the creation of a new Azure SQL Database
[23:02] – Summary and wrap-up