Phase 16 — Exercises: Serving APIs & Parsers

Work these after the labs. They escalate from "explain it" to "design it" — staff-level means you can do the last ones cold.

1. Why are streaming tool-call parsers hard (partial JSON across deltas)?
2. How does a chat template turn messages into a single token sequence?
3. What must be true for vLLM to be a drop-in OpenAI replacement?

Self-grading

For each: could you (a) explain it to a teammate in 2 minutes, and (b) point to the exact upstream/ file that proves your answer? If not, re-read the matching anchor in 01-deep-dive.md.