Fast and Flexible Inference on Open-Source AI Models at Scale - BRK117

Fast and Flexible Inference on Open-Source AI Models at Scale - BRK117

Microsoft Ignite via YouTube Direct link

0:00 - Use cases: hybrid model architecture, LLMS agents, data boundary control

1 of 9

1 of 9

0:00 - Use cases: hybrid model architecture, LLMS agents, data boundary control

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Fast and Flexible Inference on Open-Source AI Models at Scale - BRK117

Automatically move to the next video in the Classroom when playback concludes

  1. 1 0:00 - Use cases: hybrid model architecture, LLMS agents, data boundary control
  2. 2 00:09:09 - Introduction to GPU-intensive workloads like physics and video processing
  3. 3 00:11:47 - Docker Compose for AI agents and simplified cloud deployment
  4. 4 00:16:00 - Live testing of the dashboard generator and log streaming visualization
  5. 5 00:20:31 - AKS investment areas: scale, security, cost optimization and AI support
  6. 6 00:25:04 - Enhanced workload scheduling and configuration for AI workloads
  7. 7 00:30:25 - Inference traffic management using Gateway API and Ignite demo preview
  8. 8 00:35:11 - RBC’s CI/CD pipeline accelerating secure GPU resource provisioning
  9. 9 00:38:01 - RBC strategy: building Canada’s largest AI farm within compliance boundaries

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.