Dual AMD Radeon 9700 AI PRO - Building a 64GB LLM/AI Server with Llama.cpp

Dual AMD Radeon 9700 AI PRO - Building a 64GB LLM/AI Server with Llama.cpp

Donato Capitella via YouTube Direct link

00:00 Dual GPU Workstation Intro

1 of 17

1 of 17

00:00 Dual GPU Workstation Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Dual AMD Radeon 9700 AI PRO - Building a 64GB LLM/AI Server with Llama.cpp

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

  1. 1 00:00 Dual GPU Workstation Intro
  2. 2 02:23 Is this a Good GPU for AI?
  3. 3 05:30 Hardware Component List
  4. 4 06:54 Managing Airflow and Heat
  5. 5 07:49 Understanding PCIe Lane Splitting
  6. 6 10:31 Power Supply Requirements
  7. 7 11:35 OS and ROCm Installation
  8. 8 13:54 Installing GPU Monitoring Tools
  9. 9 16:08 Llama.cpp Toolboxes Overview
  10. 10 19:36 Vulkan vs ROCm
  11. 11 22:56 Setting Up the Toolboxes
  12. 12 25:56 Downloading Models from HF
  13. 13 29:29 Running LLMs via llama-cli and llama-server
  14. 14 34:37 Running llama-bench
  15. 15 37:26 Single vs Dual GPU Performance
  16. 16 42:21 Running Large Models on Dual GPUs
  17. 17 46:56 Summary and Future Plans

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.