A Novel Hat-Shaped Device-Cloud Collaborative Inference Framework for Large Language Models

• URL: http://arxiv.org/abs/2503.18989v1
• Date: Sun, 23 Mar 2025 10:54:58 GMT
• Title: A Novel Hat-Shaped Device-Cloud Collaborative Inference Framework for Large Language Models
• Authors: Zuan Xie, Yang Xu, Hongli Xu, Yunming Liao, Zhiwei Yao,
• Abstract summary: Traditional cloud-based large language models (LLMs) meet high-accuracy requirements, but fall short of critical demands for low delay and enhanced privacy.<n>We propose HAT, a novel device-cloud collaborative inference framework that leverages the complementary strengths of U-shaped inference and speculative decoding.<n>We show that HAT achieves promising performance improvements, reducing TTFT by 41% to 54% and TBT by 41% to 77% compared to the baselines.
• Score: 12.644230479753476
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in large language models (LLMs) have catalyzed a substantial surge in demand for LLM services. While traditional cloud-based LLM services satisfy high-accuracy requirements, they fall short in meeting critical demands for low delay and enhanced privacy. To address these limitations, we propose HAT, a novel device-cloud collaborative inference framework that leverages the complementary strengths of U-shaped inference and speculative decoding. HAT partitions the LLM into three submodels, and the input and output submodels, stacked with a lightweight adapter network, are deployed as a small language model (SLM) on each end device. Meanwhile, the middle submodel, encompassing the majority of the LLM's decoder layers, is hosted in the cloud to perform speculative decoding with on-device SLMs. During inference, HAT exchanges hidden states (rather than raw tokens) of input or draft tokens between devices and the cloud, thereby incurring substantial communication delays. Besides, processing hidden states of long prompts will exacerbate computation delays in the cloud, further compromising inference efficiency. To improve efficiency, we introduce a prompt chunking mechanism that segments long prompts into shorter chunks, enabling parallel transmission and processing. Furthermore, HAT is implemented to dynamically determine optimal chunk sizes for devices handling long prompts, thereby improving overall inference speed. Extensive experiments are conducted on a physical testbed comprising 30 NVIDIA Jetson devices and a server with 8 NVIDIA A6000 GPUs. Experimental results demonstrate that HAT achieves promising performance improvements, reducing TTFT by 41% to 54% and TBT by 41% to 77% compared to the baselines.

Related papers

• Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding [51.711605076319216]
  Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities.<n>We introduce a novel block-wise approximate KV Cache mechanism tailored for bidirectional diffusion models, enabling cache reuse with negligible performance drop.<n>We propose a confidence-aware parallel decoding strategy that selectively decodes tokens exceeding a confidence threshold, mitigating dependency violations and maintaining generation quality.
  arXiv  Detail & Related papers  (2025-05-28T17:39:15Z)
• Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference [49.77734021302196]
  We propose a task-oriented feature compression (TOFC) method for multimodal understanding in a device-edge co-inference framework.<n>To enhance compression efficiency, multiple entropy models are adaptively selected based on the characteristics of the visual features.<n>Results show that TOFC achieves up to 60% reduction in data transmission overhead and 50% reduction in system latency.
  arXiv  Detail & Related papers  (2025-03-17T08:37:22Z)
• Are We There Yet? A Measurement Study of Efficiency for LLM Applications on Mobile Devices [5.926813659185372]
  Small-size large language models (LLMs) can run successfully on powerful mobile devices, though they exhibit quality limitations compared to larger models. Only small-size LLMs can run successfully on powerful mobile devices, though they exhibit quality limitations compared to larger models.
  arXiv  Detail & Related papers  (2025-03-10T16:27:17Z)
• Efficient Deployment of Large Language Models on Resource-constrained Devices [12.644230479753476]
  It is necessary to fine-tune Large Language Models (LLMs) on resource-constrained devices for various downstream tasks.<n>FedSpine is a framework that combines Efficient Fine-Tuning (PEFT) with structured pruning for efficient deployment of LLMs on resource-constrained devices.<n>We show that FedSpine can speed up fine-tuning by 1.4times$$$times and improve final accuracy by 0.4%-4.5% under the same sparsity level compared to other baselines.
  arXiv  Detail & Related papers  (2025-01-05T04:38:11Z)
• WDMoE: Wireless Distributed Mixture of Experts for Large Language Models [68.45482959423323]
  Large Language Models (LLMs) have achieved significant success in various natural language processing tasks. We propose a wireless distributed Mixture of Experts (WDMoE) architecture to enable collaborative deployment of LLMs across edge servers at the base station (BS) and mobile devices in wireless networks.
  arXiv  Detail & Related papers  (2024-11-11T02:48:00Z)
• CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaboration [1.6021932740447968]
  Large Language Models (LLMs) exhibit remarkable human-like predictive capabilities.<n>It is challenging to deploy LLMs to provide efficient and adaptive inference services at the edge.<n>This paper proposes a novel Cloud-Edge Collaboration framework for LLMs (CE-CoLLM) to tackle these challenges.
  arXiv  Detail & Related papers  (2024-11-05T06:00:27Z)
• WDMoE: Wireless Distributed Large Language Models with Mixture of Experts [65.57581050707738]
  We propose a wireless distributed Large Language Models (LLMs) paradigm based on Mixture of Experts (MoE) We decompose the MoE layer in LLMs by deploying the gating network and the preceding neural network layer at base station (BS) and mobile devices. We design an expert selection policy by taking into account both the performance of the model and the end-to-end latency.
  arXiv  Detail & Related papers  (2024-05-06T02:55:50Z)
• Cloud-Device Collaborative Learning for Multimodal Large Language Models [24.65882336700547]
  We introduce a Cloud-Device Collaborative Continual Adaptation framework to enhance the performance of compressed, device-deployed MLLMs. Our framework is structured into three key components: a device-to-cloud uplink for efficient data transmission, cloud-based knowledge adaptation, and an optimized cloud-to-device downlink for model deployment.
  arXiv  Detail & Related papers  (2023-12-26T18:46:14Z)
• Efficient LLM inference solution on Intel GPU [19.154403468201924]
  Transformer based Large Language Models (LLMs) have been widely used in many fields. We propose an efficient LLM inference solution with low latency and high throughput. Compared with the standard HuggingFace implementation, the proposed solution achieves up to 7x lower token latency and 27x higher throughput.
  arXiv  Detail & Related papers  (2023-12-19T05:40:43Z)
• Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt [96.24800696597707]
  We introduce a new perspective to optimize this trade-off by prompting compressed models. We propose a soft prompt learning method where we expose the compressed model to the prompt learning process. Our experimental analysis suggests our soft prompt strategy greatly improves the performance of the 8x compressed LLaMA-7B model.
  arXiv  Detail & Related papers  (2023-05-17T20:45:13Z)
• Adaptive Federated Pruning in Hierarchical Wireless Networks [69.6417645730093]
  Federated Learning (FL) is a privacy-preserving distributed learning framework where a server aggregates models updated by multiple devices without accessing their private datasets. In this paper, we introduce model pruning for HFL in wireless networks to reduce the neural network scale. We show that our proposed HFL with model pruning achieves similar learning accuracy compared with the HFL without model pruning and reduces about 50 percent communication cost.
  arXiv  Detail & Related papers  (2023-05-15T22:04:49Z)
• Fast Distributed Inference Serving for Large Language Models [12.703624317418237]
  We present FastServe, a distributed inference serving system for large language models (LLMs) FastServe exploits the autoregressive pattern of LLM inference to enable preemption at the granularity of each output token. We build a system prototype of FastServe and experimental results show that compared to the state-of-the-art solution vLLM, FastServe improves the throughput by up to 31.4x and 17.9x under the same average and tail latency requirements, respectively.
  arXiv  Detail & Related papers  (2023-05-10T06:17:50Z)
• Real-Time GPU-Accelerated Machine Learning Based Multiuser Detection for 5G and Beyond [70.81551587109833]
  nonlinear beamforming filters can significantly outperform linear approaches in stationary scenarios with massive connectivity. One of the main challenges comes from the real-time implementation of these algorithms. This paper explores the acceleration of APSM-based algorithms through massive parallelization.
  arXiv  Detail & Related papers  (2022-01-13T15:20:45Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)

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.