Research on Cloud-Edge Computing for LLM

Heejae Park; Seungyeop Song; Seongryool Wee; Laihyuk Park

doi:10.1109/ICTC66702.2025.11388211

Research on Cloud-Edge Computing for LLM

Heejae Park
, Seungyeop Song
, Seongryool Wee
, Laihyuk Park

Dept. of Computer Science and Engineering

Seoul National University of Science and Technology (SNUST)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Large Language Models (LLMs) offer remarkable capabilities across various natural language processing (NLP) tasks. However, their high computational complexity and significant memory requirements during the training and inference stages hinder their practical application. Cloud-edge computing has emerged as a promising paradigm to overcome these limitations by enabling the collaborative execution of LLM inference across cloud and edge servers. This paper surveys recent research on cloud-edge collaborative frameworks for LLMs, with a focus on system architecture, optimization objectives, and learning-based offloading strategies.

Original language	English
Title of host publication	2025 16th International Conference on Information and Communication Technology Convergence, ICTC 2025
Publisher	IEEE Computer Society
Pages	553-554
Number of pages	2
ISBN (Electronic)	9798331556785
DOIs	https://doi.org/10.1109/ICTC66702.2025.11388211
State	Published - 2025
Event	16th International Conference on Information and Communication Technology Convergence, ICTC 2025 - , Korea, Republic of Duration: 14 Oct 2025 → 17 Oct 2025

Publication series

Name	International Conference on ICT Convergence
ISSN (Print)	2162-1233
ISSN (Electronic)	2162-1241

Conference

Conference	16th International Conference on Information and Communication Technology Convergence, ICTC 2025
Country/Territory	Korea, Republic of
Period	14/10/25 → 17/10/25

Keywords

cloud-edge computing
LLM
task offloading

Access to Document

10.1109/ICTC66702.2025.11388211

Cite this

@inproceedings{7816a151dd234203bb019180d6ba1e8e,

title = "Research on Cloud-Edge Computing for LLM",

abstract = "Large Language Models (LLMs) offer remarkable capabilities across various natural language processing (NLP) tasks. However, their high computational complexity and significant memory requirements during the training and inference stages hinder their practical application. Cloud-edge computing has emerged as a promising paradigm to overcome these limitations by enabling the collaborative execution of LLM inference across cloud and edge servers. This paper surveys recent research on cloud-edge collaborative frameworks for LLMs, with a focus on system architecture, optimization objectives, and learning-based offloading strategies.",

keywords = "cloud-edge computing, LLM, task offloading",

author = "Heejae Park and Seungyeop Song and Seongryool Wee and Laihyuk Park",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 16th International Conference on Information and Communication Technology Convergence, ICTC 2025 ; Conference date: 14-10-2025 Through 17-10-2025",

year = "2025",

doi = "10.1109/ICTC66702.2025.11388211",

language = "English",

series = "International Conference on ICT Convergence",

publisher = "IEEE Computer Society",

pages = "553--554",

booktitle = "2025 16th International Conference on Information and Communication Technology Convergence, ICTC 2025",

}

Park, H, Song, S, Wee, S & Park, L 2025, Research on Cloud-Edge Computing for LLM. in 2025 16th International Conference on Information and Communication Technology Convergence, ICTC 2025. International Conference on ICT Convergence, IEEE Computer Society, pp. 553-554, 16th International Conference on Information and Communication Technology Convergence, ICTC 2025, Korea, Republic of, 14/10/25. https://doi.org/10.1109/ICTC66702.2025.11388211

Research on Cloud-Edge Computing for LLM. / Park, Heejae; Song, Seungyeop; Wee, Seongryool et al.
2025 16th International Conference on Information and Communication Technology Convergence, ICTC 2025. IEEE Computer Society, 2025. p. 553-554 (International Conference on ICT Convergence).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Research on Cloud-Edge Computing for LLM

AU - Park, Heejae

AU - Song, Seungyeop

AU - Wee, Seongryool

AU - Park, Laihyuk

PY - 2025

Y1 - 2025

N2 - Large Language Models (LLMs) offer remarkable capabilities across various natural language processing (NLP) tasks. However, their high computational complexity and significant memory requirements during the training and inference stages hinder their practical application. Cloud-edge computing has emerged as a promising paradigm to overcome these limitations by enabling the collaborative execution of LLM inference across cloud and edge servers. This paper surveys recent research on cloud-edge collaborative frameworks for LLMs, with a focus on system architecture, optimization objectives, and learning-based offloading strategies.

AB - Large Language Models (LLMs) offer remarkable capabilities across various natural language processing (NLP) tasks. However, their high computational complexity and significant memory requirements during the training and inference stages hinder their practical application. Cloud-edge computing has emerged as a promising paradigm to overcome these limitations by enabling the collaborative execution of LLM inference across cloud and edge servers. This paper surveys recent research on cloud-edge collaborative frameworks for LLMs, with a focus on system architecture, optimization objectives, and learning-based offloading strategies.

KW - cloud-edge computing

KW - LLM

KW - task offloading

UR - https://www.scopus.com/pages/publications/105035066275

U2 - 10.1109/ICTC66702.2025.11388211

DO - 10.1109/ICTC66702.2025.11388211

M3 - Conference contribution

AN - SCOPUS:105035066275

T3 - International Conference on ICT Convergence

SP - 553

EP - 554

BT - 2025 16th International Conference on Information and Communication Technology Convergence, ICTC 2025

PB - IEEE Computer Society

T2 - 16th International Conference on Information and Communication Technology Convergence, ICTC 2025

Y2 - 14 October 2025 through 17 October 2025

ER -

Research on Cloud-Edge Computing for LLM

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this