Salvato in:
Dettagli Bibliografici
Autori principali: Yoon, JinYi, Lee, JiHo, He, Ting, Choi, Nakjung, Ji, Bo
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2508.04271
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908480172982272
author Yoon, JinYi
Lee, JiHo
He, Ting
Choi, Nakjung
Ji, Bo
author_facet Yoon, JinYi
Lee, JiHo
He, Ting
Choi, Nakjung
Ji, Bo
contents With the advancement of Artificial Intelligence (AI) towards multiple modalities (language, vision, speech, etc.), multi-modal models have increasingly been used across various applications (e.g., visual question answering or image generation/captioning). Despite the success of AI as a service for multi-modal applications, it relies heavily on clouds, which are constrained by bandwidth, latency, privacy concerns, and unavailability under network or server failures. While on-device AI becomes popular, supporting multiple tasks on edge devices imposes significant resource challenges. To address this, we introduce S2M3, a split-and-share multi-modal architecture for multi-task inference on edge devices. Inspired by the general-purpose nature of multi-modal models, which are composed of multiple modules (encoder, decoder, classifier, etc.), we propose to split multi-modal models at functional-level modules; and then share common modules to reuse them across tasks, thereby reducing resource usage. To address cross-model dependency arising from module sharing, we propose a greedy module-level placement with per-request parallel routing by prioritizing compute-intensive modules. Through experiments on a testbed consisting of 14 multi-modal models across 5 tasks and 10 benchmarks, we demonstrate that S2M3 can reduce memory usage by up to 50% and 62% in single-task and multi-task settings, respectively, without sacrificing accuracy. Furthermore, S2M3 achieves optimal placement in 89 out of 95 instances (93.7%) while reducing inference latency by up to 56.9% on resource-constrained devices, compared to cloud AI.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04271
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle S2M3: Split-and-Share Multi-Modal Models for Distributed Multi-Task Inference on the Edge
Yoon, JinYi
Lee, JiHo
He, Ting
Choi, Nakjung
Ji, Bo
Distributed, Parallel, and Cluster Computing
With the advancement of Artificial Intelligence (AI) towards multiple modalities (language, vision, speech, etc.), multi-modal models have increasingly been used across various applications (e.g., visual question answering or image generation/captioning). Despite the success of AI as a service for multi-modal applications, it relies heavily on clouds, which are constrained by bandwidth, latency, privacy concerns, and unavailability under network or server failures. While on-device AI becomes popular, supporting multiple tasks on edge devices imposes significant resource challenges. To address this, we introduce S2M3, a split-and-share multi-modal architecture for multi-task inference on edge devices. Inspired by the general-purpose nature of multi-modal models, which are composed of multiple modules (encoder, decoder, classifier, etc.), we propose to split multi-modal models at functional-level modules; and then share common modules to reuse them across tasks, thereby reducing resource usage. To address cross-model dependency arising from module sharing, we propose a greedy module-level placement with per-request parallel routing by prioritizing compute-intensive modules. Through experiments on a testbed consisting of 14 multi-modal models across 5 tasks and 10 benchmarks, we demonstrate that S2M3 can reduce memory usage by up to 50% and 62% in single-task and multi-task settings, respectively, without sacrificing accuracy. Furthermore, S2M3 achieves optimal placement in 89 out of 95 instances (93.7%) while reducing inference latency by up to 56.9% on resource-constrained devices, compared to cloud AI.
title S2M3: Split-and-Share Multi-Modal Models for Distributed Multi-Task Inference on the Edge
topic Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2508.04271