Skip to content
← Inference Physics & Roofline / 20
mediumNewOpenAIAnthropicxAI

A 0.6B policy's rollout step takes 22 s for 256 answers on a 273 GB/s device. What bounds it, and what shortens it?

Six hundred million parameters read in five milliseconds, yet one rollout step takes twenty-two seconds. The answer finds what the step really reads, why the longest answer sets its length, and which fixes move the number without biasing the reward.

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

Six hundred million parameters read in five milliseconds, yet one rollout step takes twenty-two seconds. The answer finds what the step really reads, why the longest answer sets its length, and which fixes move the number without biasing the reward.

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
DISCUSSION · 0

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