Multi-DNN Inference of Sparse Models on Edge SoCs

• URL: http://arxiv.org/abs/2603.09642v1
• Date: Tue, 10 Mar 2026 13:16:59 GMT
• Title: Multi-DNN Inference of Sparse Models on Edge SoCs
• Abstract summary: We introduce model stitching for multi-DNN inference systems, which creates model variants by recombining subgraphs from sparse models without re-training.<n>We show experimentally that SparseLoom reduces SLO violation rates by up to 74%, improves throughput by up to 2.31x, and lowers memory overhead by an average of 28% compared to state-of-the-art multi-DNN inference systems.
• Score: 5.172498227474015
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern edge applications increasingly require multi-DNN inference systems to execute tasks on heterogeneous processors, gaining performance from both concurrent execution and from matching each model to the most suited accelerator. However, existing systems support only a single model (or a few sparse variants) per task, which impedes the efficiency of this matching and results in high Service Level Objective violation rates. We introduce model stitching for multi-DNN inference systems, which creates model variants by recombining subgraphs from sparse models without re-training. We present a demonstrator system, SparseLoom, that shows model stitching can be deployed to SoCs. We show experimentally that SparseLoom reduces SLO violation rates by up to 74%, improves throughput by up to 2.31x, and lowers memory overhead by an average of 28% compared to state-of-the-art multi-DNN inference systems.

Related papers

• A2R: An Asymmetric Two-Stage Reasoning Framework for Parallel Reasoning [57.727084580884075]
  Asymmetric Two-Stage Reasoning framework designed to bridge gap between a model's potential and its actual performance.<n>A2R-Efficient is a "small-to-big" variant that combines a Qwen3-4B explorer with a Qwen3-8B synthesizer.<n>Results show A2R is not only a performance-boosting framework but also an efficient and practical solution for real-world applications.
  arXiv  Detail & Related papers  (2025-09-26T08:27:03Z)
• Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer [17.463052541838504]
  Fine-tuned models often struggle outside their specific domains and exhibit considerable redundancy.<n>Recent studies suggest that combining a pruned fine-tuned model with the original pre-trained model can mitigate interference when merging model parameters across tasks.<n>We introduce a novel method called Neural Pruning (NPS-Pruning) for slimming down fine-tuned models.
  arXiv  Detail & Related papers  (2025-05-24T14:27:20Z)
• SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models [21.933379266533098]
  Large Language Models (LLMs) present a critical trade-off between inference quality and computational cost.<n>Existing serving strategies often employ fixed model scales or static two-stage speculative decoding.<n>This paper introduces systemname, a novel framework that reimagines LLM inference as an adaptive routing problem.
  arXiv  Detail & Related papers  (2025-05-12T15:46:28Z)
• MASS: MoErging through Adaptive Subspace Selection [55.03293736484465]
  We present MASS (MoErging through Adaptive Subspace Selection), a new approach to model merging.<n> MASS stores only the most salient singular components for each task and merges them into a shared model.<n>We evaluate MASS on CLIP-based image classification using ViT-B-16, ViT-B-32 and ViT-L-14 for benchmarks of 8, 14 and 20 tasks respectively.
  arXiv  Detail & Related papers  (2025-04-06T08:49:52Z)
• MSA-CNN: A Lightweight Multi-Scale CNN with Attention for Sleep Stage Classification [14.221889446444433]
  We introduce Multi-Scale and Attention Convolutional Neural Network (MSA-CNN), a lightweight architecture featuring as few as 10,000 parameters.<n>Model complexity is further reduced by separating temporal and spatial feature extraction and using cost-effective global spatial convolutions.<n>Our evaluation, based on repeated cross-validation and re-evaluation of all baseline models, demonstrated that the large MSA-CNN outperformed all baseline models on all three datasets in terms of accuracy and Cohen's kappa.
  arXiv  Detail & Related papers  (2025-01-06T11:46:02Z)
• SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery [54.866490321241905]
  Model merging-based multitask learning (MTL) offers a promising approach for performing MTL by merging multiple expert models. In this paper, we examine the merged model's representation distribution and uncover a critical issue of "representation bias" This bias arises from a significant distribution gap between the representations of the merged and expert models, leading to the suboptimal performance of the merged MTL model.
  arXiv  Detail & Related papers  (2024-10-18T11:49:40Z)
• GroupMamba: Efficient Group-Based Visual State Space Model [66.35608254724566]
  State-space models (SSMs) have recently shown promise in capturing long-range dependencies with subquadratic computational complexity.<n>However, purely SSM-based models face critical challenges related to stability and achieving state-of-the-art performance in computer vision tasks.<n>Our paper addresses the challenges of scaling SSM-based models for computer vision, particularly the instability and inefficiency of large model sizes.
  arXiv  Detail & Related papers  (2024-07-18T17:59:58Z)
• Reusing Convolutional Neural Network Models through Modularization and Composition [22.823870645316397]
  We propose two modularization approaches named CNNSplitter and GradSplitter. CNNSplitter decomposes a trained convolutional neural network (CNN) model into $N$ small reusable modules. The resulting modules can be reused to patch existing CNN models or build new CNN models through composition.
  arXiv  Detail & Related papers  (2023-11-08T03:18:49Z)
• MGAS: Multi-Granularity Architecture Search for Trade-Off Between Model Effectiveness and Efficiency [10.641875933652647]
  We introduce multi-granularity architecture search (MGAS) to discover both effective and efficient neural networks. We learn discretization functions specific to each granularity level to adaptively determine the unit remaining ratio according to the evolving architecture. Extensive experiments on CIFAR-10, CIFAR-100 and ImageNet demonstrate that MGAS outperforms other state-of-the-art methods in achieving a better trade-off between model performance and model size.
  arXiv  Detail & Related papers  (2023-10-23T16:32:18Z)
• Sparse-DySta: Sparsity-Aware Dynamic and Static Scheduling for Sparse Multi-DNN Workloads [65.47816359465155]
  Running multiple deep neural networks (DNNs) in parallel has become an emerging workload in both edge devices. We propose Dysta, a novel scheduler that utilizes both static sparsity patterns and dynamic sparsity information for the sparse multi-DNN scheduling. Our proposed approach outperforms the state-of-the-art methods with up to 10% decrease in latency constraint violation rate and nearly 4X reduction in average normalized turnaround time.
  arXiv  Detail & Related papers  (2023-10-17T09:25:17Z)
• SqueezeLLM: Dense-and-Sparse Quantization [80.32162537942138]
  Main bottleneck for generative inference with LLMs is memory bandwidth, rather than compute, for single batch inference. We introduce SqueezeLLM, a post-training quantization framework that enables lossless compression to ultra-low precisions of up to 3-bit. Our framework incorporates two novel ideas: (i) sensitivity-based non-uniform quantization, which searches for the optimal bit precision assignment based on second-order information; and (ii) the Dense-and-Sparse decomposition that stores outliers and sensitive weight values in an efficient sparse format.
  arXiv  Detail & Related papers  (2023-06-13T08:57:54Z)
• ANNETTE: Accurate Neural Network Execution Time Estimation with Stacked Models [56.21470608621633]
  We propose a time estimation framework to decouple the architectural search from the target hardware. The proposed methodology extracts a set of models from micro- kernel and multi-layer benchmarks and generates a stacked model for mapping and network execution time estimation. We compare estimation accuracy and fidelity of the generated mixed models, statistical models with the roofline model, and a refined roofline model for evaluation.
  arXiv  Detail & Related papers  (2021-05-07T11:39:05Z)
• Single-Layer Graph Convolutional Networks For Recommendation [17.3621098912528]
  Graph Convolutional Networks (GCNs) have received significant attention and achieved start-of-the-art performances on recommendation tasks. Existing GCN models tend to perform recursion aggregations among all related nodes, which arises severe computational burden. We propose a single GCN layer to aggregate information from the neighbors filtered by DA similarity and then generates the node representations.
  arXiv  Detail & Related papers  (2020-06-07T14:38:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.