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.
@article{arxiv.2605.20723,
title = {Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds},
author = {Lakshani Manamperi and Disumi Pathirana and Thiwanka Pathirana and Nipun Premarathna and Kutila Gunasekera},
journal= {arXiv preprint arXiv:2605.20723},
year = {2026}
}
Comments
6 pages, 3 figures, 4 tables. Accepted at the ICML 2026 Workshop on Machine Learning for the Global South