hardNewNVIDIATogether AIFireworks AI

Design the contract between an engine's scheduler and an external KV store. Who owns a block while it loads or saves?

Moving KV in and out of an engine is the easy part. The interview is about the questions the scheduler may ask, when a load may stall the whole batch, and who is allowed to free a block that a copy is still touching.

Updated Oct 2026 · Worked answers on inference mechanisms, with calculations, implementation details, and follow-up questions.

10 answers per topic instead of 5, plus saved progress and bookmarks · costs nothingor unlock all 213 remaining answers · $25

Every worked answer and derivation in all 12 topics, every concept page, the full practice-test bank, and every code drill’s edge-case tests and reference solution.

6 months · One payment · No auto-renewal

UP NEXT ON YOUR JOURNEY

Next in this trackAfter enabling CPU KV offload, requests that hit the host tier have worse TTFT than requests that miss. Find out why.Next in this trackDeepSeek says V4.1-Flash keeps 890 bytes of KV per token. vLLM allocates 1,056. Reconcile the two numbers.Next in this track64 requests share a 2,000-token system prompt and hit a cold replica at once. How many times is the prefix computed?

DISCUSSION · 0

Nobody has commented on this answer. Add a correction or another way to work it.