> ## Documentation Index
> Fetch the complete documentation index at: https://notes.kodekloud.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Course: AI Infrastructure: LLM-D, vLLM and GPUs

> Overview of AI infrastructure covering GPUs, model servers, caching, model parallelism, and orchestration for designing and operating scalable, low-latency AI systems.

Notes for the **AI Infrastructure: LLM-D, vLLM and GPUs** course: 14 lessons across 5 sections.

## An Introduction to AI Infrastructure

* [An Introduction to AI Infrastructure](/docs/AI-Infrastructure-LLM-D-vLLM-and-GPUs/An-Introduction-to-AI-Infrastructure/An-Introduction-to-AI-Infrastructure/page.md)

## From a GPU to a Model Server

* [From a GPU to a Model Server](/docs/AI-Infrastructure-LLM-D-vLLM-and-GPUs/From-a-GPU-to-a-Model-Server/From-a-GPU-to-a-Model-Server/page.md)
* [A Closer Look at the Model Server](/docs/AI-Infrastructure-LLM-D-vLLM-and-GPUs/From-a-GPU-to-a-Model-Server/A-Closer-Look-at-the-Model-Server/page.md)

## What Happens When You Interact with LLM

* [How a Model Writes Text](/docs/AI-Infrastructure-LLM-D-vLLM-and-GPUs/What-Happens-When-You-Interact-with-LLM/How-a-Model-Writes-Text/page.md)
* [The Pause and the Stream](/docs/AI-Infrastructure-LLM-D-vLLM-and-GPUs/What-Happens-When-You-Interact-with-LLM/The-Pause-and-the-Stream/page.md)
* [The Models Scratchpad](/docs/AI-Infrastructure-LLM-D-vLLM-and-GPUs/What-Happens-When-You-Interact-with-LLM/The-Models-Scratchpad/page.md)

## Why Serving Gets Hard

* [One GPU Many Users](/docs/AI-Infrastructure-LLM-D-vLLM-and-GPUs/Why-Serving-Gets-Hard/One-GPU-Many-Users/page.md)
* [Serving the Giants](/docs/AI-Infrastructure-LLM-D-vLLM-and-GPUs/Why-Serving-Gets-Hard/Serving-the-Giants/page.md)
* [Why Load Balancing Breaks](/docs/AI-Infrastructure-LLM-D-vLLM-and-GPUs/Why-Serving-Gets-Hard/Why-Load-Balancing-Breaks/page.md)

## Meet llm-d

* [Meet llm d](/docs/AI-Infrastructure-LLM-D-vLLM-and-GPUs/Meet-llm-d/Meet-llm-d/page.md)
* [Putting It to Work](/docs/AI-Infrastructure-LLM-D-vLLM-and-GPUs/Meet-llm-d/Putting-It-to-Work/page.md)
* [Inside the Cluster](/docs/AI-Infrastructure-LLM-D-vLLM-and-GPUs/Meet-llm-d/Inside-the-Cluster/page.md)
* [Your Next Move](/docs/AI-Infrastructure-LLM-D-vLLM-and-GPUs/Meet-llm-d/Your-Next-Move/page.md)
* [Try the vLLM Lab](/docs/AI-Infrastructure-LLM-D-vLLM-and-GPUs/Meet-llm-d/Try-the-vLLM-Lab/page.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.