Fast and Cost-effective Speculative Edge-Cloud Decoding with Early Exits

• URL: http://arxiv.org/abs/2505.21594v1
• Date: Tue, 27 May 2025 14:55:16 GMT
• Title: Fast and Cost-effective Speculative Edge-Cloud Decoding with Early Exits
• Authors: Yeshwanth Venkatesha, Souvik Kundu, Priyadarshini Panda,
• Abstract summary: Large Language Models (LLMs) enable various applications on edge devices such as smartphones, wearables, and embodied robots.<n>LLMs can be deployed on-device, offering a cost-effective solution with reduced latency and improved privacy.<n>We propose a fast and cost-effective speculative edge-cloud decoding framework with a large target model on the server and a small draft model on the device.
• Score: 11.398891065175686
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) enable various applications on edge devices such as smartphones, wearables, and embodied robots. However, their deployment often depends on expensive cloud-based APIs, creating high operational costs, which limit access for smaller organizations and raise sustainability concerns. Certain LLMs can be deployed on-device, offering a cost-effective solution with reduced latency and improved privacy. Yet, limited computing resources constrain the size and accuracy of models that can be deployed, necessitating a collaborative design between edge and cloud. We propose a fast and cost-effective speculative edge-cloud decoding framework with a large target model on the server and a small draft model on the device. By introducing early exits in the target model, tokens are generated mid-verification, allowing the client to preemptively draft subsequent tokens before final verification, thus utilizing idle time and enhancing parallelism between edge and cloud. Using an NVIDIA Jetson Nano (client) and an A100 GPU (server) with Vicuna-68M (draft) and Llama2-7B (target) models, our method achieves up to a 35% reduction in latency compared to cloud-based autoregressive decoding, with an additional 11% improvement from preemptive drafting. To demonstrate real-world applicability, we deploy our method on the Unitree Go2 quadruped robot using Vision-Language Model (VLM) based control, achieving a 21% speedup over traditional cloud-based autoregressive decoding. These results demonstrate the potential of our framework for real-time LLM and VLM applications on resource-constrained edge devices.

Related papers

• SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving [7.91607650966469]
  acronym is a framework that allows lightweight edge devices to draft multiple candidate tokens locally using diverse draft models.<n>A single, shared edge server verifies the tokens utilizing a more precise target model.<n>Our initial experiments with Jetson Orin Nano, Raspberry Pi 4B/5, and an edge server equipped with 4 Nvidia A100 GPUs indicate substantial benefits.
  arXiv  Detail & Related papers  (2025-06-11T04:55:54Z)
• DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence Drafting [59.57151419673759]
  Speculative decoding presents a draft-then-verify framework that reduces generation latency while maintaining output distribution fidelity.<n>We propose DuoDecoding, a novel approach that strategically deploys the draft and target models on the CPU and GPU respectively.<n>Our method incorporates a hardware-aware optimal draft budget to minimize idle times and employs dynamic multi-sequence drafting to enhance draft quality.
  arXiv  Detail & Related papers  (2025-03-02T08:27:48Z)
• 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)
• Mixture of Attentions For Speculative Decoding [17.344416130742232]
  Speculative decoding (SD) leverages smaller models to efficiently propose future tokens, which are then verified by the Large Language Models in parallel.<n>We identify several limitations of SD models including the lack of on-policyness during training and partial observability.<n>We propose a more grounded architecture for small models by introducing a Mixture of Attentions for SD.
  arXiv  Detail & Related papers  (2024-10-04T10:25:52Z)
• Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation [56.79064699832383]
  We establish a Cloud-Edge Elastic Model Adaptation (CEMA) paradigm in which the edge models only need to perform forward propagation. In our CEMA, to reduce the communication burden, we devise two criteria to exclude unnecessary samples from uploading to the cloud.
  arXiv  Detail & Related papers  (2024-02-27T08:47:19Z)
• ECLM: Efficient Edge-Cloud Collaborative Learning with Continuous Environment Adaptation [47.35179593006409]
  We propose ECLM, an edge-cloud collaborative learning framework for rapid model adaptation for dynamic edge environments. We show that ECLM significantly improves model performance (e.g., 18.89% accuracy increase) and resource efficiency (e.g. 7.12x communication cost reduction) in adapting models to dynamic edge environments.
  arXiv  Detail & Related papers  (2023-11-18T14:10:09Z)
• Streaming Video Analytics On The Edge With Asynchronous Cloud Support [2.7456483236562437]
  We propose a novel edge-cloud fusion algorithm that fuses edge and cloud predictions, achieving low latency and high accuracy. We focus on object detection in videos (applicable in many video analytics scenarios) and show that the fused edge-cloud predictions can outperform the accuracy of edge-only and cloud-only scenarios by as much as 50%.
  arXiv  Detail & Related papers  (2022-10-04T06:22:13Z)
• DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization [66.27399823422665]
  Device Model Generalization (DMG) is a practical yet under-investigated research topic for on-device machine learning applications.<n>We propose an efficient Device-cloUd collaborative parametErs generaTion framework DUET.
  arXiv  Detail & Related papers  (2022-09-12T13:26:26Z)
• Auto-Split: A General Framework of Collaborative Edge-Cloud AI [49.750972428032355]
  This paper describes the techniques and engineering practice behind Auto-Split, an edge-cloud collaborative prototype of Huawei Cloud. To the best of our knowledge, there is no existing industry product that provides the capability of Deep Neural Network (DNN) splitting.
  arXiv  Detail & Related papers  (2021-08-30T08:03:29Z)
• Cocktail: Leveraging Ensemble Learning for Optimized Model Serving in Public Cloud [9.149566952446058]
  We proposeCocktail, a costeffective ensembling-based model serving framework. A prototype implementation ofCocktailon the AWS EC2 platform and exhaustive evalua-tions using a variety of workloads demonstrate thatCocktailcan reduce deployment cost by 1.45x.
  arXiv  Detail & Related papers  (2021-06-09T19:23:58Z)
• Device-Cloud Collaborative Learning for Recommendation [50.01289274123047]
  We propose a novel MetaPatch learning approach on the device side to efficiently achieve "thousands of people with thousands of models" given a centralized cloud model. With billions of updated personalized device models, we propose a "model-over-models" distillation algorithm, namely MoMoDistill, to update the centralized cloud model.
  arXiv  Detail & Related papers  (2021-04-14T05:06:59Z)

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.