Batching-Aware Joint Model Onloading and Offloading for Hierarchical Multi-Task Inference

• URL: http://arxiv.org/abs/2508.13380v1
• Date: Mon, 18 Aug 2025 21:49:32 GMT
• Title: Batching-Aware Joint Model Onloading and Offloading for Hierarchical Multi-Task Inference
• Abstract summary: We propose a unified framework to jointly decide which multi-task models to deploy (onload) at clients and edge servers.<n>We introduce J3O, an alternating algorithm that selects models onload via Lagrangian-relaxed submodular optimization and determines optimal offloading.<n>Experiments show J3O consistently achieves over $97%$ of the optimal accuracy while incurring less than $15%$ of the runtime required by the optimal solver.
• Score: 16.974966624253156
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The growing demand for intelligent services on resource-constrained edge devices has spurred the development of collaborative inference systems that distribute workloads across end devices, edge servers, and the cloud. While most existing frameworks focus on single-task, single-model scenarios, many real-world applications (e.g., autonomous driving and augmented reality) require concurrent execution of diverse tasks including detection, segmentation, and depth estimation. In this work, we propose a unified framework to jointly decide which multi-task models to deploy (onload) at clients and edge servers, and how to route queries across the hierarchy (offload) to maximize overall inference accuracy under memory, compute, and communication constraints. We formulate this as a mixed-integer program and introduce J3O (Joint Optimization of Onloading and Offloading), an alternating algorithm that (i) greedily selects models to onload via Lagrangian-relaxed submodular optimization and (ii) determines optimal offloading via constrained linear programming. We further extend J3O to account for batching at the edge, maintaining scalability under heterogeneous task loads. Experiments show J3O consistently achieves over $97\%$ of the optimal accuracy while incurring less than $15\%$ of the runtime required by the optimal solver across multi-task benchmarks.

Related papers

• SPECTRE: Hybrid Ordinary-Parallel Speculative Serving for Resource-Efficient LLM Inference [11.392365535797586]
  LLM serving platforms are increasingly deployed as multi-model cloud systems, where user demand is often long-tailed.<n>We propose SPECTRE, a framework that reuses underutilized tail-model services as remote drafters for heavily loaded large-model services.<n>We show that SPECTRE consistently improves large-model serving throughput while causing only minor interference to the native workloads of tail-model services.
  arXiv  Detail & Related papers  (2026-05-04T01:27:45Z)
• Chimera: Latency- and Performance-Aware Multi-agent Serving for Heterogeneous LLMs [62.17306142810532]
  We present Chimera, a predictive scheduling system for multi-agent workflow serving on heterogeneous LLM clusters.<n>Chime traces the best latency, reducing end-to-end latency by 1.2--2.4$times$ and improving task performance by 8.0-9.5 percentage points on average over competitive baselines.
  arXiv  Detail & Related papers  (2026-03-23T17:01:42Z)
• Dora: QoE-Aware Hybrid Parallelism for Distributed Edge AI [18.668516218320736]
  We present Dora, a framework for QoE aware hybrid computation in distributed edge AI training and inference.<n>Dora achieves 1.1-6.3 times faster execution and reduces energy consumption by 21--82 percent, all while maintaining QoE under runtime dynamics.
  arXiv  Detail & Related papers  (2025-12-09T03:19:16Z)
• xLLM Technical Report [57.13120905321185]
  We introduce xLLM, an intelligent and efficient Large Language Model (LLM) inference framework.<n>xLLM builds a novel decoupled service-engine architecture.<n>xLLM-Engine co-optimizes system and algorithm designs to fully saturate computing resources.
  arXiv  Detail & Related papers  (2025-10-16T13:53:47Z)
• D$^{2}$MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving [14.607254882119507]
  Combination of experts (MoE) model is a sparse variant of large language models (LLMs)<n>Despite its benefits, MoE is still too expensive to deploy on resource-constrained edge devices.<n>We propose D$2$MoE, an algorithm-system co-design framework that matches diverse task requirements by dynamically allocating the most proper bit-width to each expert.
  arXiv  Detail & Related papers  (2025-04-17T05:37:35Z)
• PartialLoading: User Scheduling and Bandwidth Allocation for Parameter-sharing Edge Inference [32.58445942857626]
  We develop a parameter-sharing AI model loading framework for multi-user edge inference.<n>We exploit shared parameter blocks across models to maximize task throughput.<n>We show that the proposed framework significantly improves task throughput under deadline compared with user scheduling.
  arXiv  Detail & Related papers  (2025-03-29T05:58:07Z)
• Octo-planner: On-device Language Model for Planner-Action Agents [19.627197141903505]
  Planner-Action framework separates planning and action execution into two distinct components. Agent first responds to user queries by decomposing tasks into a sequence of sub-steps, which are then executed by the action agent. We employ model fine-tuning instead of in-context learning, reducing computational costs and energy consumption.
  arXiv  Detail & Related papers  (2024-06-26T05:40:10Z)
• Efficient Controllable Multi-Task Architectures [85.76598445904374]
  We propose a multi-task model consisting of a shared encoder and task-specific decoders where both encoder and decoder channel widths are slimmable. Our key idea is to control the task importance by varying the capacities of task-specific decoders, while controlling the total computational cost. This improves overall accuracy by allowing a stronger encoder for a given budget, increases control over computational cost, and delivers high-quality slimmed sub-architectures.
  arXiv  Detail & Related papers  (2023-08-22T19:09:56Z)
• Energy-efficient Task Adaptation for NLP Edge Inference Leveraging Heterogeneous Memory Architectures [68.91874045918112]
  adapter-ALBERT is an efficient model optimization for maximal data reuse across different tasks. We demonstrate the advantage of mapping the model to a heterogeneous on-chip memory architecture by performing simulations on a validated NLP edge accelerator.
  arXiv  Detail & Related papers  (2023-03-25T14:40:59Z)
• Controllable Dynamic Multi-Task Architectures [92.74372912009127]
  We propose a controllable multi-task network that dynamically adjusts its architecture and weights to match the desired task preference as well as the resource constraints. We propose a disentangled training of two hypernetworks, by exploiting task affinity and a novel branching regularized loss, to take input preferences and accordingly predict tree-structured models with adapted weights.
  arXiv  Detail & Related papers  (2022-03-28T17:56:40Z)
• Elastic Architecture Search for Diverse Tasks with Different Resources [87.23061200971912]
  We study a new challenging problem of efficient deployment for diverse tasks with different resources, where the resource constraint and task of interest corresponding to a group of classes are dynamically specified at testing time. Previous NAS approaches seek to design architectures for all classes simultaneously, which may not be optimal for some individual tasks. We present a novel and general framework, called Elastic Architecture Search (EAS), permitting instant specializations at runtime for diverse tasks with various resource constraints.
  arXiv  Detail & Related papers  (2021-08-03T00:54:27Z)
• HyperGrid: Efficient Multi-Task Transformers with Grid-wise Decomposable Hyper Projections [96.64246471034195]
  We propose textscHyperGrid, a new approach for highly effective multi-task learning. Our method helps bridge the gap between fine-tuning and multi-task learning approaches.
  arXiv  Detail & Related papers  (2020-07-12T02:49:16Z)
• Dynamic Multi-Robot Task Allocation under Uncertainty and Temporal Constraints [52.58352707495122]
  We present a multi-robot allocation algorithm that decouples the key computational challenges of sequential decision-making under uncertainty and multi-agent coordination. We validate our results over a wide range of simulations on two distinct domains: multi-arm conveyor belt pick-and-place and multi-drone delivery dispatch in a city.
  arXiv  Detail & Related papers  (2020-05-27T01:10:41Z)

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.