Intermediate · Systems

Serverless

Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.

TL;DR. A deployment model where the cloud provider runs your code on demand without managing servers.

Technical Definition

A deployment model where the cloud provider runs your code on demand without managing servers.

How it works

Serverless (AWS Lambda, Cloud Run, Vercel Functions) is great for spiky, lightweight inference and event-driven preprocessing. Cold starts and execution-time limits make it less suited for large LLM serving, though specialized 'serverless GPU' offerings are closing the gap.

Related Concepts

• Deployment — The process of moving a trained model into a production environment where it serves real users.
• Scalability — A system's ability to handle increasing load by adding resources.
• Containerization — Packaging an application with all its dependencies so it runs consistently across environments.