← all papers · overview

Cactus: Accelerating Auto-regressive Decoding With Constrained Acceptance Speculative Sampling

Abstract

Speculative sampling (SpS) has been successful in accelerating the decoding throughput of auto-regressive large language models by leveraging smaller draft models. SpS strictly enforces the generated distribution to match that of the verifier LLM. This is unnecessarily restrictive as slight variations of the verifier's distribution, such as sampling with top- or temperature, would also be acc

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).