← all papers · overview

Large Language Model Partitioning For Low-latency Inference At The Edge

Abstract

Large Language Models (LLMs) based on autoregressive, decoder-only Transformers generate text one token at a time, where a token represents a discrete unit of text. As each newly produced token is appended to the partial output sequence, the length grows and so does the memory and compute load, due to the expanding key-value caches, which store intermediate representations of all previously genera

Related papers

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