New theory extends speculative decoding acceptance beyond distribution-preserving sampling

baseten · x · 2026-10-01

Aaryam Sharma builds a theory for when speculative decoding draft tokens get accepted under non-standard regimes. Standard speculative sampling has an elegant formula: acceptance probability is 1 − TV(p, q). But production systems also run greedy decoding, relaxed acceptance, and tree-based acceptance, which previously had only conditions (argmax q = argmax p) rather than exact formulas. The thread develops unified theory for these cases.

Original post →

More from Infra

Infra channel →