Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Venkatesha, Yeshwanth, Kundu, Souvik, Panda, Priyadarshini
Format:	Preprint
Published:	2025
Subjects:	Robotics Artificial Intelligence Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Assortment of Attention Heads: Accelerating Federated PEFT with Head Pruning and Strategic Client Selection
by: Venkatesha, Yeshwanth, et al.
Published: (2025)

Distributed Inference on Mobile Edge and Cloud: An Early Exit based Clustering Approach
by: Bajpai, Divya Jyoti, et al.
Published: (2024)

Thousand-GPU Large-Scale Training and Optimization Recipe for AI-Native Cloud Embodied Intelligence Infrastructure
by: Guo, Yongjian, et al.
Published: (2026)

Speculative Policy Orchestration: A Latency-Resilient Framework for Cloud-Robotic Manipulation
by: Nguyen, Chanh, et al.
Published: (2026)

Quantifying Energy and Cost Benefits of Hybrid Edge Cloud: Analysis of Traditional and Agentic Workloads
by: Alamouti, Siavash
Published: (2025)

SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
by: Abramovich, Talor, et al.
Published: (2026)

Nightjar: Dynamic Adaptive Speculative Decoding for Large Language Models Serving
by: Li, Rui, et al.
Published: (2025)

DistrEE: Distributed Early Exit of Deep Neural Network Inference on Edge Devices
by: Peng, Xian, et al.
Published: (2025)

Speculative Decoding in Decentralized LLM Inference: Turning Communication Latency into Computation Throughput
by: Song, Jingwei, et al.
Published: (2025)

FlowSpec: Continuous Pipelined Speculative Decoding for Efficient Distributed LLM Inference
by: Liu, Xing, et al.
Published: (2025)

Fast LLM Post-training via Decoupled and Fastest-of-N Speculation
by: Cheng, Rongxin, et al.
Published: (2025)

SpecBranch: Speculative Decoding via Hybrid Drafting and Rollback-Aware Branch Parallelism
by: Shen, Yuhao, et al.
Published: (2025)

Ghidorah: Fast LLM Inference on Edge with Speculative Decoding and Hetero-Core Parallelism
by: Wei, Jinhui, et al.
Published: (2025)

Striking the Right Balance between Compute and Copy: Improving LLM Inferencing Under Speculative Decoding
by: Ramachandran, Arun, et al.
Published: (2025)

SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting
by: Xu, Jiaming, et al.
Published: (2025)

A Pipelined Collaborative Speculative Decoding Framework for Efficient Edge-Cloud LLM Inference
by: Zhang, Yida, et al.
Published: (2026)

PipeSD: An Efficient Cloud-Edge Collaborative Pipeline Inference Framework with Speculative Decoding
by: Han, Yunhe, et al.
Published: (2026)

Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs
by: Pan, Rui, et al.
Published: (2025)

MLCommons Cloud Masking Benchmark with Early Stopping
by: Chennamsetti, Varshitha, et al.
Published: (2023)

UAV Marketplace Simulation Tool for BVLOS Operations
by: Şerefoğlu, Kıvanç, et al.
Published: (2025)

CA-AC-MPC: CUDA-Accelerated Actor-Critic Model Predictive Control
by: Buo, Antoonio, et al.
Published: (2026)

HPRM: High-Performance Robotic Middleware for Intelligent Autonomous Systems
by: Kwok, Jacky, et al.
Published: (2024)

RAPID: Redundancy-Aware and Compatibility-Optimal Edge-Cloud Partitioned Inference for Diverse VLA Models
by: Zheng, Zihao, et al.
Published: (2026)

Utility-Driven Speculative Decoding for Mixture-of-Experts
by: Saxena, Anish, et al.
Published: (2025)

SpecMemo: Speculative Decoding is in Your Pocket
by: Yildirim, Selin, et al.
Published: (2025)

FlexSpec: Frozen Drafts Meet Evolving Targets in Edge-Cloud Collaborative LLM Speculative Decoding
by: Li, Yuchen, et al.
Published: (2026)

Adaptive AI-based Decentralized Resource Management in the Cloud-Edge Continuum
by: Li, Lanpei, et al.
Published: (2025)

DGRAG: Distributed Graph-based Retrieval-Augmented Generation in Edge-Cloud Systems
by: Zhou, Wenqing, et al.
Published: (2025)

ECCENTRIC: Edge-Cloud Collaboration Framework for Distributed Inference Using Knowledge Adaptation
by: Kamani, Mohammad Mahdi, et al.
Published: (2025)

Reinforcement Learning-driven Data-intensive Workflow Scheduling for Volunteer Edge-Cloud
by: Mounesan, Motahare, et al.
Published: (2024)

BlazeAIoT: A Modular Multi-Layer Platform for Real-Time Distributed Robotics Across Edge, Fog, and Cloud Infrastructures
by: Melancon, Cedric, et al.
Published: (2026)

Distributed Inference on Mobile Edge and Cloud: A Data-Cartography based Clustering Approach
by: Bajpai, Divya Jyoti, et al.
Published: (2024)

Federated Learning for Collaborative Inference Systems: The Case of Early Exit Networks
by: Kaplan, Caelin, et al.
Published: (2024)

HLS4PC: A Parametrizable Framework For Accelerating Point-Based 3D Point Cloud Models on FPGA
by: Pal, Amur Saqib, et al.
Published: (2025)

Early-Exit meets Model-Distributed Inference at Edge Networks
by: Colocrese, Marco, et al.
Published: (2024)

ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency Scenarios
by: Hu, Xinyi, et al.
Published: (2026)

FlashRecovery: Fast and Low-Cost Recovery from Failures for Large-Scale Training of LLMs
by: Zhang, Haijun, et al.
Published: (2025)

SMART: When is it Actually Worth Expanding a Speculative Tree?
by: Wang, Lifu, et al.
Published: (2026)

ENOVA: Autoscaling towards Cost-effective and Stable Serverless LLM Serving
by: Huang, Tao, et al.
Published: (2024)

FogROS2-FT: Fault Tolerant Cloud Robotics
by: Chen, Kaiyuan, et al.
Published: (2024)