EAServe: Encode-Aware Disaggregated Serving for Multimodal Large Language Models

Paper recorded by Signals 4 on 2026-09-25 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-25 on arXiv · recorded by Signals 4 on 2026-09-28

Category: cs.LG · 机器学习 · first seen 2026-09-28

Abstract

Disaggregating the two stages, Prefill and Decode, onto separate GPU pools is now a standard optimization for (text-only) LLM serving. However, multimodal LLMs (MLLMs), which add a third phase, Encode, pose new challenges for resource allocation. Encode turns images, video, or audio into embeddings that the language model can consume, yielding a three-stage Encode-Prefill-Decode (EPD) pipeline. Ex

Read on arXiv →