Post Content
Learn about optimized inference of generative AI foundation and reasoning models using ready-to-deploy NVIDIA NIM™ microservices and NVIDIA Dynamo on NVIDIA GPU compute instances within Azure services. Also explore NVIDIA NeMo™ microservices for model customization, evaluation, retrieval-augmented generation (RAG), and guard railing for content safety and leverage NVIDIA Blueprints for accelerating your AI development and deployment.
𝗦𝗽𝗲𝗮𝗸𝗲𝗿𝘀:
* Mike Hollinger
𝗦𝗲𝘀𝘀𝗶𝗼𝗻 𝗜𝗻𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻:
This is one of many sessions from the Microsoft Build 2025 event. View even more sessions on-demand and learn about Microsoft Build at https://build.microsoft.com
BRKFP257 | English (US)
#MSBuild
Chapters:
0:00 – Introduction to the Seminar
00:03:49 – Description of AI Deployment in Production Environments
00:13:00 – Problem-Solving Abilities of the System
00:15:54 – Deployment on Nvidia and Azure
00:17:21 – Introduction of Nvidia Dynamo for Inference Workloads
00:26:21 – Request for ascending order in songs
00:48:27 – Discussion on LLM Deployment Frameworks Read More Microsoft Developer
Gracey Hemstreet puts a huge run together to take the lead in Leogang! 