Compiler-Assisted Speculative Sampling for Accelerated LLM Inference on Heterogeneous Edge Devices

• URL: http://arxiv.org/abs/2602.08060v2
• Date: Tue, 10 Feb 2026 10:08:09 GMT
• Title: Compiler-Assisted Speculative Sampling for Accelerated LLM Inference on Heterogeneous Edge Devices
• Abstract summary: LLM deployment on resource-constrained edge devices faces severe latency constraints.<n>This work uses an analytical cost model that explores heterogeneous hardware configurations and guides coarse-grained partitioning of LLM subgraphs.<n>The model predicts when speculative sampling and heterogeneous execution are jointly beneficial and is validated on an edge device featuring a hexacore Cortex-A CPU and a Mali GPU.
• Score: 37.04691997023527
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM deployment on resource-constrained edge devices faces severe latency constraints, particularly in real-time applications where delayed responses can compromise safety or usability. Among many approaches to mitigate the inefficiencies of sequential token-by-token generation, Speculative Decoding (SD) has emerged as a promising technique. However, SD at the edge is hindered by two major challenges: (1) integrating SD into a compiler-based workflow without sacrificing performance or programmability, and (2) exploiting the heterogeneous compute resources of modern SoCs through carefully designed partitioning strategies. This work addresses these challenges by using an analytical cost model that explores heterogeneous hardware configurations and guides coarse-grained partitioning of LLM subgraphs, particularly with edge-typical short input sequence lengths. The cost model predicts when speculative sampling and heterogeneous execution are jointly beneficial and is validated on an edge device featuring a hexacore Cortex-A CPU and a Mali GPU, revealing up to 1.68$\times$ speedup for translation tasks, closely matching analytic expectations.

Related papers

• SVD Contextual Sparsity Predictors for Fast LLM Inference [0.0]
  This paper presents a framework for accelerating inference of ReGLU-based feed-forward networks (FFNs) within large language models (LLMs)<n>Experiments demonstrate up to a 1.8x reduction in end-to-end decoding time while maintaining less than 1% degradation in benchmark scores on tasks involving complex math and code generation.
  arXiv  Detail & Related papers  (2026-03-14T20:36:13Z)
• GEMs: Breaking the Long-Sequence Barrier in Generative Recommendation with a Multi-Stream Decoder [54.64137490632567]
  We propose a novel and unified framework designed to capture users' sequences from long-term history.<n>Generative Multi-streamers ( GEMs) break user sequences into three streams.<n>Extensive experiments on large-scale industrial datasets demonstrate that GEMs significantly outperforms state-the-art methods in recommendation accuracy.
  arXiv  Detail & Related papers  (2026-02-14T06:42:56Z)
• Accelerate Speculative Decoding with Sparse Computation in Verification [49.74839681322316]
  Speculative decoding accelerates autoregressive language model inference by verifying multiple draft tokens in parallel.<n>Existing sparsification methods are designed primarily for standard token-by-token autoregressive decoding.<n>We propose a sparse verification framework that jointly sparsifies attention, FFN, and MoE components during the verification stage to reduce the dominant computation cost.
  arXiv  Detail & Related papers  (2025-12-26T07:53:41Z)
• OTARo: Once Tuning for All Precisions toward Robust On-Device LLMs [21.55040910903597]
  OTARo is a novel method that enables on-device Large Language Models to flexibly switch quantization precisions.<n>It achieves consistently strong and robust performance for all precisions.
  arXiv  Detail & Related papers  (2025-11-17T08:56:27Z)
• PT$^2$-LLM: Post-Training Ternarization for Large Language Models [52.4629647715623]
  Large Language Models (LLMs) have shown impressive capabilities across diverse tasks, but their large memory and compute demands hinder deployment.<n>We propose PT$2$-LLM, a post-training ternarization framework tailored for LLMs.<n>At its core is an Asymmetric Ternary Quantizer equipped with a two-stage refinement pipeline.
  arXiv  Detail & Related papers  (2025-09-27T03:01:48Z)
• Ringleader ASGD: The First Asynchronous SGD with Optimal Time Complexity under Data Heterogeneity [51.56484100374058]
  We introduce Ringleader ASGD, the first asynchronous algorithm that attains the theoretical lower bounds for parallel computation.<n>Our analysis further establishes that Ringleader ASGD remains optimal under arbitrary gradient and even time-varying speeds.
  arXiv  Detail & Related papers  (2025-09-26T19:19:15Z)
• Modality Agnostic Efficient Long Range Encoder [14.705955027331674]
  We address the challenge of long-context processing on a single device using generic implementations.<n>To overcome these limitations, we propose MAELRE, a unified and efficient transformer architecture.<n>We demonstrate that MAELRE achieves superior accuracy while reducing computational cost compared to existing long-context models.
  arXiv  Detail & Related papers  (2025-07-25T16:19:47Z)
• Optimization of DNN-based HSI Segmentation FPGA-based SoC for ADS: A Practical Approach [1.474723404975345]
  This work presents a set of optimization techniques for the practical co-design of a DNN-based HSI segmentation processor deployed on a FPGA-based SOC.<n> applied compression techniques significantly reduce the complexity of the designed DNN to 24.34% of the original operations and to 1.02% of the original number of parameters, achieving a 2.86x speed-up in the inference task without noticeable degradation of the segmentation accuracy.
  arXiv  Detail & Related papers  (2025-07-22T13:09:04Z)
• Fast Second-Order Online Kernel Learning through Incremental Matrix Sketching and Decomposition [44.61147231796296]
  Online Learning (OKL) has attracted considerable research interest due to its promising predictive performance in streaming environments.<n>Existing second-order OKL approaches suffer from at least quadratic time complexity with respect to the pre-set budget.<n>We propose FORKS, a fast incremental matrix sketching and decomposition approach tailored for second-order OKL.
  arXiv  Detail & Related papers  (2024-10-15T02:07:48Z)
• Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization [0.6445087473595953]
  Large language models (LLMs) demonstrate outstanding performance in various tasks in machine learning. deploying LLM inference poses challenges due to the high compute and memory requirements. We present Tender, an algorithm-hardware co-design solution that enables efficient deployment of LLM inference at low precision.
  arXiv  Detail & Related papers  (2024-06-16T09:51:55Z)
• Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences [60.489682735061415]
  We propose CHELA, which replaces state space models with short-long convolutions and implements linear attention in a divide-and-conquer manner. Our experiments on the Long Range Arena benchmark and language modeling tasks demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2024-06-12T12:12:38Z)

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.