Running Open-Source AI Models at Scale: Azure Container Apps, AKS, and On-Premise Deployments - Microsoft Ignite 2025
Microsoft Ignite BRK117: Deploy open-source AI models (Llama 3.3, Mistral) with Azure Container Apps serverless GPUs, AKS with Kaido workflows, and on-premise infrastructure. Cost reduction 60-85%, data sovereignty, and hybrid architectures with Azure Arc.