← all papers · overview

Learning To Keep A Promise: Scaling Language Model Decoding Parallelism With Learned Asynchronous Decoding

Abstract

Decoding with autoregressive large language models (LLMs) traditionally occurs sequentially, generating one token after another. An emerging line of work explored parallel decoding by identifying and simultaneously generating semantically independent chunks of LLM responses. However, these techniques rely on hand-crafted heuristics tied to syntactic structures like lists and paragraphs, making the

Related papers

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