FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Du, Hongchao, Wu, Shangyu, Kharlamova, Arina, Guan, Nan, Xue, Chun Jason
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915183271608320
author Du, Hongchao
Wu, Shangyu
Kharlamova, Arina
Guan, Nan
Xue, Chun Jason
author_facet Du, Hongchao
Wu, Shangyu
Kharlamova, Arina
Guan, Nan
Xue, Chun Jason
contents Large Language Models (LLMs) face challenges for on-device inference due to high memory demands. Traditional methods to reduce memory usage often compromise performance and lack adaptability. We propose FlexInfer, an optimized offloading framework for on-device inference, addressing these issues with techniques like asynchronous prefetching, balanced memory locking, and flexible tensor preservation. These strategies enhance memory efficiency and mitigate I/O bottlenecks, ensuring high performance within user-specified resource constraints. Experiments demonstrate that FlexInfer significantly improves throughput under limited resources, achieving up to 12.5 times better performance than existing methods and facilitating the deployment of large models on resource-constrained devices.
format Preprint
id arxiv_https___arxiv_org_abs_2503_03777
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference
Du, Hongchao
Wu, Shangyu
Kharlamova, Arina
Guan, Nan
Xue, Chun Jason
Operating Systems
Artificial Intelligence
Large Language Models (LLMs) face challenges for on-device inference due to high memory demands. Traditional methods to reduce memory usage often compromise performance and lack adaptability. We propose FlexInfer, an optimized offloading framework for on-device inference, addressing these issues with techniques like asynchronous prefetching, balanced memory locking, and flexible tensor preservation. These strategies enhance memory efficiency and mitigate I/O bottlenecks, ensuring high performance within user-specified resource constraints. Experiments demonstrate that FlexInfer significantly improves throughput under limited resources, achieving up to 12.5 times better performance than existing methods and facilitating the deployment of large models on resource-constrained devices.
title FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference
topic Operating Systems
Artificial Intelligence
url https://arxiv.org/abs/2503.03777