SpecEdge: Scalable Edge-Assisted Serving Framework for Interactive LLMs

• URL: http://arxiv.org/abs/2505.17052v1
• Date: Fri, 16 May 2025 14:17:59 GMT
• Title: SpecEdge: Scalable Edge-Assisted Serving Framework for Interactive LLMs
• Authors: Jinwoo Park, Seunggeun Cho, Dongsu Han,
• Abstract summary: Large language models (LLMs) power many modern applications, but serving them at scale remains costly and resource-intensive.<n>We introduce SpecEdge, an edge-assisted inference framework that splits LLM workloads between edge and server GPU.<n> Experiments show SpecEdge enhances overall cost efficiency by 1.91x through achieving 2.22x server throughput, and reduces inter token latency by 11.24% compared to a server-only baseline.
• Score: 3.417027762559937
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) power many modern applications, but serving them at scale remains costly and resource-intensive. Current server-centric systems overlook consumer-grade GPUs at the edge. We introduce SpecEdge, an edge-assisted inference framework that splits LLM workloads between edge and server GPUs using a speculative decoding scheme, exchanging only token outputs over the network. SpecEdge employs proactive edge drafting to overlap edge token creation with server verification and pipeline-aware scheduling that interleaves multiple user requests to increase server-side throughput. Experiments show SpecEdge enhances overall cost efficiency by 1.91x through achieving 2.22x server throughput, and reduces inter token latency by 11.24% compared to a server-only baseline, introducing a scalable, cost-effective paradigm for LLM serving.

Related papers

• Nexus:Proactive Intra-GPU Disaggregation of Prefill and Decode in LLM Serving [4.309392302169281]
  Engine-level prefill-decode (PD) disaggregation avoids interference but incurs higher hardware and coordination overhead.<n>PD achieves up to 2.2x higher throughput, 20x lower TTFT, and 2.5x lower TBT than vLLM; outperforms SG by up to 2x; and matches or exceeds disaggregated vLLM.
  arXiv  Detail & Related papers  (2025-07-09T07:27:18Z)
• EdgeLoRA: An Efficient Multi-Tenant LLM Serving System on Edge Devices [7.596547050649462]
  This paper introduces EdgeLoRA, an efficient system for serving Large Language Models (LLMs) on edge devices in multi-tenant environments.<n> EdgeLoRA incorporates three key innovations: (1) an adaptive adapter selection mechanism to streamline the adapter configuration process; (2) heterogeneous memory management, leveraging intelligent adapter caching and pooling to mitigate memory operation overhead; and (3) batch LoRA inference, enabling efficient batch processing to significantly reduce computational latency.
  arXiv  Detail & Related papers  (2025-07-02T07:47:28Z)
• 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)
• ConServe: Harvesting GPUs for Low-Latency and High-Throughput Large Language Model Serving [15.01982917560918]
  This paper proposes to harvest stranded GPU resources for offline LLM inference tasks. We built ConServe, an LLM serving system that contains an execution engine that preempts running offline tasks. Our evaluation demonstrates that ConServe achieves strong performance isolation when co-serving online and offline tasks.
  arXiv  Detail & Related papers  (2024-10-02T04:12:13Z)
• Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference [19.167604927651073]
  Auto-regressive decoding of Large Language Models (LLMs) results in significant overheads in their hardware performance. We propose a novel parallel prompt decoding that requires only $0.0002$% trainable parameters, enabling efficient training on a single A100-40GB GPU in just 16 hours. Our approach demonstrates up to 2.49$times$ speedup and maintains a minimal memory overhead of just $0.0004$%.
  arXiv  Detail & Related papers  (2024-05-28T22:19:30Z)
• HiRE: High Recall Approximate Top-$k$ Estimation for Efficient LLM Inference [68.59839755875252]
  HiRE comprises of two novel components: (i) a compression scheme to cheaply predict top-$k$ rows/columns with high recall, followed by full computation restricted to the predicted subset, and (ii) DA-TOP-$k$: an efficient multi-device approximate top-$k$ operator. We demonstrate that on a one billion parameter model, HiRE applied to both the softmax as well as feedforward layers, achieves almost matching pretraining and downstream accuracy, and speeds up inference latency by $1.47times$ on a single TPUv5e device.
  arXiv  Detail & Related papers  (2024-02-14T18:04:36Z)
• 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)
• 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)
• Rediscovering Hashed Random Projections for Efficient Quantization of Contextualized Sentence Embeddings [113.38884267189871]
  Training and inference on edge devices often requires an efficient setup due to computational limitations. Pre-computing data representations and caching them on a server can mitigate extensive edge device computation. We propose a simple, yet effective approach that uses randomly hyperplane projections. We show that the embeddings remain effective for training models across various English and German sentence classification tasks that retain 94%--99% of their floating-point.
  arXiv  Detail & Related papers  (2023-03-13T10:53:00Z)
• NumS: Scalable Array Programming for the Cloud [82.827921577004]
  We present NumS, an array programming library which optimize NumPy-like expressions on task-based distributed systems. This is achieved through a novel scheduler called Load Simulated Hierarchical Scheduling (LSHS) We show that LSHS enhances performance on Ray by decreasing network load by a factor of 2x, requiring 4x less memory, and reducing execution time by 10x on the logistic regression problem.
  arXiv  Detail & Related papers  (2022-06-28T20:13:40Z)
• MAPLE-Edge: A Runtime Latency Predictor for Edge Devices [80.01591186546793]
  We propose MAPLE-Edge, an edge device-oriented extension of MAPLE, the state-of-the-art latency predictor for general purpose hardware. Compared to MAPLE, MAPLE-Edge can describe the runtime and target device platform using a much smaller set of CPU performance counters. We also demonstrate that unlike MAPLE which performs best when trained on a pool of devices sharing a common runtime, MAPLE-Edge can effectively generalize across runtimes.
  arXiv  Detail & Related papers  (2022-04-27T14:00:48Z)
• Multi-model Machine Learning Inference Serving with GPU Spatial Partitioning [7.05946599544139]
  High throughput machine learning (ML) inference servers are critical for online service applications. These servers must provide a bounded latency for each request to support consistent service-level objective (SLO) This paper proposes a new ML inference scheduling framework for multi-model ML inference servers.
  arXiv  Detail & Related papers  (2021-09-01T04:46:46Z)
• Hierarchical Quantized Federated Learning: Convergence Analysis and System Design [7.481427303081613]
  Federated learning is a collaborative machine to train deep neural networks without clients' private data. Previous works assume one central parameter either at the cloud or at the edge. This paper exploits the advantages of both cloud servers and considers Hierarchical Quantized Federated Learning system.
  arXiv  Detail & Related papers  (2021-03-26T05:48:36Z)
• EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference [82.1584439276834]
  Transformer-based language models such as BERT provide significant accuracy improvement for a multitude of natural language processing (NLP) tasks. We present EdgeBERT, an in-depth algorithm- hardware co-design for latency-aware energy optimization for multi-task NLP.
  arXiv  Detail & Related papers  (2020-11-28T19:21:47Z)

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.