LGMay 20

Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds

arXiv:2605.207238.1
Predicted impact top 93% in LG · last 90 daysOriginality Synthesis-oriented
AI Analysis

For edge ML practitioners, this system allows deployment of unmodified large DNNs on commodity smartphones with limited memory, though it is an incremental engineering solution.

CROWDio enables inference of large transformer models on memory-constrained Android devices by distributing memory pressure across devices, achieving peak per-device RSS of 43±2 MB and battery draw of 50±3 mAh per run on DistilBERT.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes