3 lessons
What Is Inference Engineering
Why serving a trained model is a completely different engineering problem from training one, and what "inference engineering" actually covers.
Autoregressive Decoding, Step by Step
How a transformer actually produces one token at a time — the prefill pass, the decode loop, and why the two phases have opposite performance characteristics.
The KV Cache
The single most important data structure in LLM serving — what it stores, why it's so large, and why managing it well or badly determines your entire system's throughput.