Phase 18 — Exercises: Performance Engineering

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

1. From a profile showing low GPU util at small batch, name the likely cause and fix.
2. Use Little's Law to predict the batch size needed for a target throughput at a given ITL.
3. Design a fair benchmark comparing two configs (warmup, steady state, same traffic).

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.