Image de couverture de livre

Tiny but Mighty: A Software-Hardware Co-Design Approach for Efficient Multimodal Inference on Battery-Powered Small Devices

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Yilong, Zhang, Shuai, Zeng, Yijing, Zhang, Hao, Xiong, Xinmiao, Liu, Jingyu, Hu, Pan, Banerjee, Suman
Format:	Preprint
Publié:	2025
Sujets:	Distributed, Parallel, and Cluster Computing Artificial Intelligence Computation and Language Signal Processing
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Benchmarking Compound AI Applications for Hardware-Software Co-Design
par: Samuthrsindh, Paramuth, et autres
Publié: (2026)

TokenSim: Enabling Hardware and Software Exploration for Large Language Model Inference Systems
par: Wu, Feiyang, et autres
Publié: (2025)

PICO: Pipeline Inference Framework for Versatile CNNs on Diverse Mobile Devices
par: Yang, Xiang, et autres
Publié: (2022)

Distributed On-Device LLM Inference With Over-the-Air Computation
par: Zhang, Kai, et autres
Publié: (2025)

Exploring the Boundaries of On-Device Inference: When Tiny Falls Short, Go Hierarchical
par: Behera, Adarsh Prasad, et autres
Publié: (2024)

ReviveMoE: Fast Recovery for Hardware Failures in Large-Scale MoE LLM Inference Deployments
par: Li, Haley, et autres
Publié: (2026)

Multi-core & GPU-based Balanced Butterfly Counting in Signed Bipartite Graphs
par: Kiran, Mekala, et autres
Publié: (2026)

AdaOper: Energy-efficient and Responsive Concurrent DNN Inference on Mobile Devices
par: Lin, Zheng, et autres
Publié: (2024)

LIME:Accelerating Collaborative Lossless LLM Inference on Memory-Constrained Edge Devices
par: Sun, Mingyu, et autres
Publié: (2025)

Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning
par: An, Wei, et autres
Publié: (2024)

Arrow: Adaptive Scheduling Mechanisms for Disaggregated LLM Inference Architecture
par: Wu, Yu, et autres
Publié: (2025)

Adaptive Heuristics for Scheduling DNN Inferencing on Edge and Cloud for Personalized UAV Fleets
par: Raj, Suman, et autres
Publié: (2024)

Loki: A System for Serving ML Inference Pipelines with Hardware and Accuracy Scaling
par: Ahmad, Sohaib, et autres
Publié: (2024)

FlexPie: Accelerate Distributed Inference on Edge Devices with Flexible Combinatorial Optimization[Technical Report]
par: Zhang, Runhua, et autres
Publié: (2025)

Pico-Cloud: Cloud Infrastructure for Tiny Edge Devices
par: Guri, Mordechai
Publié: (2025)

SLO-Aware Scheduling for Large Language Model Inferences
par: Huang, Jinqi, et autres
Publié: (2025)

Power Aware Dynamic Reallocation For Inference
par: Jiang, Yiwei, et autres
Publié: (2026)

Optimizing Hardware Resource Partitioning and Job Allocations on Modern GPUs under Power Caps
par: Arima, Eishi, et autres
Publié: (2024)

CoCoI: Distributed Coded Inference System for Straggler Mitigation
par: Liu, Xing, et autres
Publié: (2025)

GPUArmor: A Hardware-Software Co-design for Efficient and Scalable Memory Safety on GPUs
par: Ziad, Mohamed Tarek Ibn, et autres
Publié: (2025)

Evaluating Multi-Instance DNN Inferencing on Multiple Accelerators of an Edge Device
par: Tayal, Mumuksh, et autres
Publié: (2025)

SLICE: SLO-Driven Scheduling for LLM Inference on Edge Computing Devices
par: Chow, Will
Publié: (2025)

Energy-aware Incremental OTA Update for Flash-based Batteryless IoT Devices
par: Wei, Wei, et autres
Publié: (2024)

Understanding the Performance and Power of LLM Inferencing on Edge Accelerators
par: Arya, Mayank, et autres
Publié: (2025)

xNVMe: Unleashing Storage Hardware-Software Co-design
par: Lund, Simon A. F., et autres
Publié: (2024)

Improved Decision Module Selection for Hierarchical Inference in Resource-Constrained Edge Devices
par: Behera, Adarsh Prasad, et autres
Publié: (2024)

Distributed Generative Inference of LLM at Internet Scales with Multi-Dimensional Communication Optimization
par: Chen, Jiu, et autres
Publié: (2026)

Extracting the Potential of Emerging Hardware Accelerators for Symmetric Eigenvalue Decomposition
par: Wang, Hansheng, et autres
Publié: (2024)

Cicada: A Pipeline-Efficient Approach to Serverless Inference with Decoupled Management
par: Wu, Z., et autres
Publié: (2025)

DynaSplit: A Hardware-Software Co-Design Framework for Energy-Aware Inference on Edge
par: May, Daniel, et autres
Publié: (2024)

MoA-Off: Adaptive Heterogeneous Modality-Aware Offloading with Edge-Cloud Collaboration for Efficient Multimodal LLM Inference
par: Yang, Zheming, et autres
Publié: (2025)

Joint Optimization of Offloading, Batching and DVFS for Multiuser Co-Inference
par: Xu, Yaodan, et autres
Publié: (2025)

LLM-CoOpt: A Co-Design and Optimization Framework for Efficient LLM Inference on Heterogeneous Platforms
par: Kong, Jie, et autres
Publié: (2026)

Adaptive Device-Edge Collaboration on DNN Inference in AIoT: A Digital Twin-Assisted Approach
par: Hu, Shisheng, et autres
Publié: (2024)

CoCoDiff: Optimizing Collective Communications for Distributed Diffusion Transformer Inference Under Ulysses Sequence Parallelism
par: Ma, Bin, et autres
Publié: (2026)

PIM-SHERPA: Software Method for On-device LLM Inference by Resolving PIM Memory Attribute and Layout Inconsistencies
par: Lee, Sunjung, et autres
Publié: (2026)

TT-Edge: A Hardware-Software Co-Design for Energy-Efficient Tensor-Train Decomposition on Edge AI
par: Kwak, Hyunseok, et autres
Publié: (2025)

ReaLB: Real-Time Load Balancing for Multimodal MoE Inference
par: Wang, Yingping, et autres
Publié: (2026)

Future-Proofing IoT: Unleashing the Power of AWS Greengrass in Propelling Smart Devices to New Heights
par: Kokkula, Sahasra, et autres
Publié: (2024)

SimDC: A High-Fidelity Device Simulation Platform for Device-Cloud Collaborative Computing
par: Pei, Ruiguang, et autres
Publié: (2025)