Skip to content
← Serving Engine Internals / 16
hardNewNVIDIAFireworks AITogether AI

More CUDA graph captures made decode faster but increased preemption. Diagnose the regression and choose a policy.

Compare three capture policies using a memory ledger and a matched workload. Recover the missing KV pages, then defend a policy against both capacity and latency constraints.

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

Compare three capture policies using a memory ledger and a matched workload. Recover the missing KV pages, then defend a policy against both capacity and latency constraints.

10 answers per topic instead of 5, plus saved progress and bookmarks · costs nothingor unlock all 136 remaining answers · ₹2,000 / $25

Every worked answer and derivation in all 12 topics, every concept page, and the full practice-test bank.

6 months · One payment · No auto-renewal

UP NEXT ON YOUR JOURNEY
Popular right nowWhy is batch-1 decode on a 70B model bandwidth-bound, and what is its latency floor on two H100s?Popular right nowDerive the FLOPs per token for a dense transformer from its config. Where does the 2N rule stop being accurate?Popular right nowWhy does prefill turn compute-bound after a few hundred tokens on an H100, and how long does a 4K-token prompt take on a 70B model?
FEDITOR'S NOTE

An average decode-step time cannot establish a serving improvement. Specify which request-level evidence you would retain before changing a capture policy.

DISCUSSION · 0

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