hardNewOpenAINVIDIATogether AI

Logits are identical, but a seeded request changes output after batch reordering. Repair the sampler's RNG contract.

A fixed global seed reproduces a launch order, not a request. Build a random-draw address that survives compaction, extra draft work and continuation, then state what it cannot guarantee.

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

A fixed global seed reproduces a launch order, not a request. Build a random-draw address that survives compaction, extra draft work and continuation, then state what it cannot guarantee.

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

Next in this trackA streaming client stops reading. Keep its output bounded without blocking the inference batch.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?

FEDITOR'S NOTE

Test random-stream ownership with fixed probabilities before involving a model. Forced-token replay can verify logits along a trajectory without testing how the sampler chooses that trajectory.

DISCUSSION · 0

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