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

• URL: http://arxiv.org/abs/2510.05109v2
• Date: Mon, 27 Oct 2025 14:17:43 GMT
• Title: Tiny but Mighty: A Software-Hardware Co-Design Approach for Efficient Multimodal Inference on Battery-Powered Small Devices
• Abstract summary: Large Multimodal Models (LMMs) are inherently modular, consisting of vision and audio encoders, projectors, and large language models.<n>Yet, they are almost always executed monolithically, which underutilizes the heterogeneous accelerators.<n>We present a hardware-software co-design inference framework for Large Multimodal Models (LMMs)<n>This framework breaks large models into modular components and scheduled to run on the most appropriate compute units.
• Score: 12.40080721078945
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large Multimodal Models (LMMs) are inherently modular, consisting of vision and audio encoders, projectors, and large language models. Yet, they are almost always executed monolithically, which underutilizes the heterogeneous accelerators (NPUs, GPUs, DSPs) in modern SoCs and leads to high end-to-end latency. In this paper, we present NANOMIND, a hardware--software co-design inference framework for Large Multimodal Models (LMMs) that breaks large models into modular ``bricks'' (vision, language, audio, etc.) and maps each to its ideal accelerator. The key insight is that large models can be broken into modular components and scheduled to run on the most appropriate compute units. It performs module-level dynamic offloading across accelerators on unified-memory SoCs. By combining customized hardware design, system-level scheduling, and optimized low-bit computation kernels, we demonstrate our framework with a compact, battery-powered device capable of running LMMs entirely on device. This prototype functions as a self-contained intelligent assistant that requires no network connectivity, while achieving higher throughput and superior power efficiency under strict resource constraints. The design further bypasses CPU bottlenecks and reduces redundant memory usage through token-aware buffer management and module-level coordination. Our system outperforms existing implementations in resource efficiency, cutting energy consumption by 42.3\% and GPU memory usage by 11.2\%. This enables a battery-powered device to run LLaVA-OneVision with a camera for nearly half a day and LLaMA-3-8B for voice interactions up to almost 20.8 hours.

Related papers

• PALS: Power-Aware LLM Serving for Mixture-of-Experts Models [7.28734124763028]
  Large language model (LLM) inference has become a dominant workload in modern data centers.<n>We present a power-aware runtime for LLM serving, PALS, that treats GPU power caps as a first-class control knob.<n> PALS improves energy efficiency by up to 26.3%, reduces runtime violations by 4x to 7x under power constraints, and tracks dynamic power budgets.
  arXiv  Detail & Related papers  (2026-05-20T17:19:20Z)
• ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling [56.88966608455977]
  ZipMoE exploits the synergy between the hardware properties of edge devices and the statistical redundancy inherent to MoE parameters.<n>ZipMoE achieves up to $72.77%$ inference latency reduction and up to $6.76times$ higher throughput than the state-of-the-art systems.
  arXiv  Detail & Related papers  (2026-01-29T02:51:59Z)
• NanoCockpit: Performance-optimized Application Framework for AI-based Autonomous Nanorobotics [50.594459728605734]
  Small form factor, i.e., a few 10s grams, severely limits onboard computational resources to sub-SI100milliwatt microcontroller units (MCUs)<n>Our framework achieves ideal end-to-end latency, i.e. zero overhead due to serialized tasks, delivering quantifiable improvements in closed-loop control performance.
  arXiv  Detail & Related papers  (2026-01-12T12:29:38Z)
• SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations [54.303301888915406]
  Mixture of Experts (MoE) models have emerged as the de facto architecture for scaling up language models without significantly increasing the computational cost.<n>We propose a memory-efficient algorithm to compute the forward and backward passes of MoEs with minimal activation caching.<n>We also propose a novel "token rounding" method that minimizes the wasted compute due to padding in Grouped GEMM kernels.
  arXiv  Detail & Related papers  (2025-12-16T04:39:10Z)
• FlashMoE: Fast Distributed MoE in a Single Kernel [1.866526462692252]
  FlashMoE is a fully GPU-resident MoE operator that fuses expert computation and inter-GPU communication into a single persistent GPU kernel.<n>We show that FlashMoE achieves up to 9x higher GPU utilization, 6x lower latency, 5.7x higher throughput, and 4x better overlap efficiency compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-06-05T06:29:14Z)
• MoE-Lens: Towards the Hardware Limit of High-Throughput MoE LLM Serving Under Resource Constraints [7.287566040274871]
  MoE-Lens is an inference system designed through holistic performance modeling for resource-constrained environments.<n>It captures the system execution mechanisms to identify the key hardware bottlenecks and accurately predict the achievable throughput.<n> evaluated on diverse MoE models and datasets, MoE-Lens outperforms the state-of-the-art solution by 4.6x on average (up to 25.5x)
  arXiv  Detail & Related papers  (2025-04-12T21:26:56Z)
• MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism [26.923312725688735]
  Mixture-of-Experts (MoE) showcases tremendous potential to scale large language models (LLMs) with enhanced performance and reduced computational complexity.<n>We present MegaScale-Infer, an efficient and cost-effective system for serving large-scale MoE models.
  arXiv  Detail & Related papers  (2025-04-03T04:20:44Z)
• Neuromorphic Principles for Efficient Large Language Models on Intel Loihi 2 [5.213433310722838]
  Large language models (LLMs) deliver impressive performance but require large amounts of energy.<n>We present a MatMul-free LLM architecture adapted for Intel's neuromorphic processor, Loihi 2.<n>Our approach leverages Loihi 2's support for low-precision, event-driven computation and stateful processing.
  arXiv  Detail & Related papers  (2025-02-12T02:40:44Z)
• MobileMamba: Lightweight Multi-Receptive Visual Mamba Network [51.33486891724516]
  Previous research on lightweight models has primarily focused on CNNs and Transformer-based designs. We propose the MobileMamba framework, which balances efficiency and performance. MobileMamba achieves up to 83.6% on Top-1, surpassing existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-11-24T18:01:05Z)
• MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs [55.95879347182669]
  MoE architecture is renowned for its ability to increase model capacity without a proportional increase in inference cost. MoE-Lightning introduces a novel CPU-GPU-I/O pipelining schedule, CGOPipe, with paged weights to achieve high resource utilization. MoE-Lightning can achieve up to 10.3x higher throughput than state-of-the-art offloading-enabled LLM inference systems for Mixtral 8x7B on a single T4 GPU (16GB)
  arXiv  Detail & Related papers  (2024-11-18T01:06:12Z)
• Rapid and Power-Aware Learned Optimization for Modular Receive Beamforming [27.09017677987757]
  Multiple-input multiple-output (MIMO) systems play a key role in wireless communication technologies.<n>We propose a power-oriented optimization algorithm for beamforming in modular hybrid systems.<n>We show how power efficient beamforming can be encouraged by the learned, via boosting computation with low-resolution phase shifts.
  arXiv  Detail & Related papers  (2024-08-01T10:19:25Z)
• vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving [53.972175896814505]
  Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests.
  arXiv  Detail & Related papers  (2024-07-22T14:37:58Z)
• Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment [56.44025052765861]
  Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs. We show a total speedup on CPUs for sparse-quantized LLaMA models of up to 8.6x.
  arXiv  Detail & Related papers  (2024-05-06T16:03:32Z)
• Distributed Inference and Fine-tuning of Large Language Models Over The Internet [91.00270820533272]
  Large language models (LLMs) are useful in many NLP tasks and become more capable with size. These models require high-end hardware, making them inaccessible to most researchers. We develop fault-tolerant inference algorithms and load-balancing protocols that automatically assign devices to maximize the total system throughput.
  arXiv  Detail & Related papers  (2023-12-13T18:52:49Z)
• FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs [57.12856172329322]
  We envision a decentralized system unlocking the potential vast untapped consumer-level GPU. This system faces critical challenges, including limited CPU and GPU memory, low network bandwidth, the variability of peer and device heterogeneity.
  arXiv  Detail & Related papers  (2023-09-03T13:27:56Z)

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.