Saved in:
Bibliographic Details
Main Authors: Wang, Zhaode, Yang, Jingbang, Qian, Xinyu, Xing, Shiwen, Jiang, Xiaotang, Lv, Chengfei, Zhang, Shengyu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.10443
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913890069118976
author Wang, Zhaode
Yang, Jingbang
Qian, Xinyu
Xing, Shiwen
Jiang, Xiaotang
Lv, Chengfei
Zhang, Shengyu
author_facet Wang, Zhaode
Yang, Jingbang
Qian, Xinyu
Xing, Shiwen
Jiang, Xiaotang
Lv, Chengfei
Zhang, Shengyu
contents Large language models (LLMs) have demonstrated exceptional performance across a variety of tasks. However, their substantial scale leads to significant computational resource consumption during inference, resulting in high costs. Consequently, edge device inference presents a promising solution. The primary challenges of edge inference include memory usage and inference speed. This paper introduces MNN-LLM, a framework specifically designed to accelerate the deployment of large language models on mobile devices. MNN-LLM addresses the runtime characteristics of LLMs through model quantization and DRAM-Flash hybrid storage, effectively reducing memory usage. It rearranges weights and inputs based on mobile CPU instruction sets and GPU characteristics while employing strategies such as multicore load balancing, mixed-precision floating-point operations, and geometric computations to enhance performance. Notably, MNN-LLM achieves up to a 8.6x speed increase compared to current mainstream LLM-specific frameworks.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10443
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MNN-LLM: A Generic Inference Engine for Fast Large Language Model Deployment on Mobile Devices
Wang, Zhaode
Yang, Jingbang
Qian, Xinyu
Xing, Shiwen
Jiang, Xiaotang
Lv, Chengfei
Zhang, Shengyu
Machine Learning
Large language models (LLMs) have demonstrated exceptional performance across a variety of tasks. However, their substantial scale leads to significant computational resource consumption during inference, resulting in high costs. Consequently, edge device inference presents a promising solution. The primary challenges of edge inference include memory usage and inference speed. This paper introduces MNN-LLM, a framework specifically designed to accelerate the deployment of large language models on mobile devices. MNN-LLM addresses the runtime characteristics of LLMs through model quantization and DRAM-Flash hybrid storage, effectively reducing memory usage. It rearranges weights and inputs based on mobile CPU instruction sets and GPU characteristics while employing strategies such as multicore load balancing, mixed-precision floating-point operations, and geometric computations to enhance performance. Notably, MNN-LLM achieves up to a 8.6x speed increase compared to current mainstream LLM-specific frameworks.
title MNN-LLM: A Generic Inference Engine for Fast Large Language Model Deployment on Mobile Devices
topic Machine Learning
url https://arxiv.org/abs/2506.10443