Article14 min read
What Actually Happens When You Send a Prompt to an LLM?
Follow one LLM request from the API gateway to the GPU and back. Learn what prefill, decode, and the KV cache do along the way.
Backend Engineering
How APIs, databases, caches, and messages work together in a reliable service.
Start here
Articles
Apply the ideas
System designs
System design
Core System Design Concepts: A Practical Guide
Learn the main ideas behind system design, including scale, data, failures, security, cost, and common architecture choices.