Covers LLM inference fundamentals, model size and precision considerations, and the runtime ecosystem for local language-model execution. The associated lab runs a supported local LLM using FastFlowLM, submits prompts, and observes response generation and resource behavior.
{Lecture, Lab}
1 . Running LLMs on AMD Ryzen AI Platforms
2 . Running LLMs on the Ryzen AI NPU with FastFlowLM - Lab
