Saved in:
Bibliographic Details
Main Authors: Manamperi, Lakshani, Pathirana, Disumi, Pathirana, Thiwanka, Premarathna, Nipun, Gunasekera, Kutila
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.20723
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913147602862080
author Manamperi, Lakshani
Pathirana, Disumi
Pathirana, Thiwanka
Premarathna, Nipun
Gunasekera, Kutila
author_facet Manamperi, Lakshani
Pathirana, Disumi
Pathirana, Thiwanka
Premarathna, Nipun
Gunasekera, Kutila
contents Deploying large deep neural networks on memory-constrained mobile devices is a central challenge in edge ML. While compression, pruning, and quantization reduce per-parameter cost, transformer-based models remain too large for the 3.3-7.4 GB RAM envelope of commodity Android handsets. We present the DNN pipeline scheduling subsystem of CROWDio, which achieves practical ONNX inference across resource-constrained Android workers without model modification, by distributing memory pressure across devices via five mechanisms: JIT deferred partition loading, a single-partition-resident constraint, a 4-tier affinity scheduler, a zlib-compressed tensor transport, and a streaming 1:1 dependency model. Evaluated on DistilBERT (Sanh et al., 2019) (approximately 67 M parameters, SST-2) across five Android handsets over ten runs, our system holds peak per-device RSS to 43+-2 MB and limits battery draw to 50+-3 mAh per run, while streaming concurrency cuts batch latency 34% below barrier synchronisation.
format Preprint
id arxiv_https___arxiv_org_abs_2605_20723
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds
Manamperi, Lakshani
Pathirana, Disumi
Pathirana, Thiwanka
Premarathna, Nipun
Gunasekera, Kutila
Machine Learning
I.2.6; C.2.4
Deploying large deep neural networks on memory-constrained mobile devices is a central challenge in edge ML. While compression, pruning, and quantization reduce per-parameter cost, transformer-based models remain too large for the 3.3-7.4 GB RAM envelope of commodity Android handsets. We present the DNN pipeline scheduling subsystem of CROWDio, which achieves practical ONNX inference across resource-constrained Android workers without model modification, by distributing memory pressure across devices via five mechanisms: JIT deferred partition loading, a single-partition-resident constraint, a 4-tier affinity scheduler, a zlib-compressed tensor transport, and a streaming 1:1 dependency model. Evaluated on DistilBERT (Sanh et al., 2019) (approximately 67 M parameters, SST-2) across five Android handsets over ten runs, our system holds peak per-device RSS to 43+-2 MB and limits battery draw to 50+-3 mAh per run, while streaming concurrency cuts batch latency 34% below barrier synchronisation.
title Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds
topic Machine Learning
I.2.6; C.2.4
url https://arxiv.org/abs/2605.20723