---
title: "The Inference Stack — Model to GPU to Production"
description: "The layers of every LLM inference system: the model artifact, the runtime, the hardware and the production service, and how to diagnose across them."
canonical_url: "https://fanout.sh/inference-eng/curriculum/in-03"
md_url: "https://fanout.sh/inference-eng/curriculum/in-03.md"
access: "public"
---

# The Inference Stack — Model to GPU to Production

The layers of every LLM inference system: the model artifact, the runtime, the hardware and the production service, and how to diagnose across them.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md