Accelerate development and deployment of Gen AI with NVIDIA on Azure
summary
Claims day-zero model support (Phi 3 vision) and containerized deployments via the NVIDIA AI Enterprise Suite, shows NIMs running in Azure AI Studio with live demos: a Prompt Flow DAG calling a mixed 8B model, NIM-on gives ~4.5x token-latency and ~2x end-to-end gains versus NIM-off, software optimizations yield up to 5x throughput and 3x lower TCO on identical GPUs, a six-month container reports zero critical/high CVEs, and trial keys grant 1k–5k free inferences.
AI-written summary · about
chapters (9)
- 0:00Introduction and partnership
- 2:46Generative AI overview
- 4:48Nvidia enterprise agenda
- 7:26Introduction to Nims
- 11:05Enterprise-grade software
- 14:04Live demo: Nim performance
- 21:48Operationalizing AI in Azure
- 32:56Call to action and resources
- 35:44Q&A and closing
related talks
24mHow to build next-gen AI services with NVIDIA AI on Azure Cloud
28mHarnessing generative AI with NVIDIA AI and Microsoft Azure
22mAI @Scale
30mNVIDIA AI Enterprise Registry for AzureML deployments of AI Workflows
28mScaling agentic AI: From infrastructure to enterprise outcomes
28mDeveloper Essentials for the New Era of AI
59mBuild Next-Gen AI Apps with .NET and Azure
01h 29mRunning AI Application in Minutes w/ AI Templates