Skip to content
← Inference Physics & Roofline / 19
hardNewMistral AINVIDIA

A distillation scorer runs out of memory on known student continuations. Do you need another decode engine?

Eight known continuations can create a 4 GiB vocabulary-output tensor before other allocations. Separate teacher-forced scoring from sampling, derive the peak, and choose a memory fix that preserves the intended supervision.

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

Eight known continuations can create a 4 GiB vocabulary-output tensor before other allocations. Separate teacher-forced scoring from sampling, derive the peak, and choose a memory fix that preserves the intended supervision.

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 trackA 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?Popular right nowWhy is batch-1 decode on a 70B model bandwidth-bound, and what is its latency floor on two H100s?Popular right nowDecode attention intensity is fixed at the query-to-KV head ratio. Derive that, then tell me what MLA does to it.
DISCUSSION · 0

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