Models 101
What Is a Model?
Description
Learn what an AI model is: a trained system that turns any input into a useful output by learning patterns from data, not by memorizing answers, with real-world examples across text, images, and business prediction.
Additional Resources
Blog: What is AI Inference?
Blog: AI Is No Longer About Training Bigger Models - It's About Inference at Scale
Different Types of AI
Description
Get an overview of the main types of AI systems in use today: predictive models, large language models, vision models, and decision-making systems, and learn what each one is designed to do.
Additional Resources
Blog: Generative AI terms
Blog: What is an AI chip
What Is an LLM & Dataflow Graph?
Description
Learn what a large language model is and how it works: from recognizing patterns in text to generating responses, and how dataflow graphs visualize the path data takes through a model from input to output.
Related Resources
Technology: Dataflow architecture
Blog: Solving the infrastructure crisis with dataflow
Prefill vs. Decode
Description
Learn how AI inference works in two distinct stages: prefill, where the model reads and processes your input, and decode, where it generates a response one token at a time, and why decode is often the bigger performance challenge.
Related Resources
Blog: What is AI Inference?
Blog: Why agentic inference needs hybrid hardware
Blog: Why tokens per second isn't all you need
Understanding Prefill & Decode for Disaggregated Inference
Description
Learn how large language models process inputs, what the prefill and decode stages involve, and why disaggregated inference uses different hardware for each to maximize throughput and efficiency.
Additional Resources
Blog: Why agentic inference needs hybrid hardware
Blog: Why dataflow matters
Product: RDU