惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

S
SegmentFault 最新的问题
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
B
Blog RSS Feed
Y
Y Combinator Blog
T
Tailwind CSS Blog
博
博客园 - 三生石上(FineUI控件)
J
Java Code Geeks
Stack Overflow Blog
Stack Overflow Blog
aimingoo的专栏
aimingoo的专栏
Jina AI
Jina AI
The GitHub Blog
The GitHub Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
A
About on SuperTechFans
H
Hackread – Cybersecurity News, Data Breaches, AI and More
D
Docker
酷 壳 – CoolShell
酷 壳 – CoolShell
C
Check Point Blog
M
MIT News - Artificial intelligence
Last Week in AI
Last Week in AI
V
V2EX
腾
腾讯CDC
F
Fortinet All Blogs
博
博客园 - 叶小钗
T
The Blog of Author Tim Ferriss

cs.DC updates on arXiv.org

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Progressive Semantic Communication for Efficient Edge-Cloud Vision-Language Models Efficient, VRAM-Constrained xLM Inference on Clients Folding Tensor and Sequence Parallelism for Memory-Efficient Transformer Training & Inference DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving RaMP: Runtime-Aware Megakernel Polymorphism for Mixture-of-Experts Spark Policy Toolkit: Semantic Contracts and Scalable Execution for Policy Learning in Spark Internet of Everything in the 6G Era: Paradigms, Enablers, Potentials and Future Directions PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference A Survey on Split Learning for LLM Fine-Tuning: Models, Systems, and Privacy Optimizations ITAS: A Multi-Agent Architecture for LLM-Based Intelligent Tutoring Latency and Cost of Multi-Agent Intelligent Tutoring at Scale TACO: Efficient Communication Compression of Intermediate Tensors for Scalable Tensor-Parallel LLM Training FreeScale: Distributed Training for Sequence Recommendation Models with Minimal Scaling Cost CommFuse: Hiding Tail Latency via Communication Decomposition and Fusion for Distributed LLM Training A Taxonomy and Resolution Strategy for Client-Level Disagreements in Federated Learning Usable Agent Discovery for Decentralized AI Systems Cloud to Edge: Benchmarking LLM Inference On Hardware-Accelerated Single-Board Computers Data-Free Contribution Estimation in Federated Learning using Gradient von Neumann Entropy Shard the Gradient, Scale the Model: Serverless Federated Aggregation via Gradient Partitioning Promoting Simple Agents: Ensemble Methods for Event-Log Prediction GraphLeap: Decoupling Graph Construction and Convolution for Vision GNN Acceleration on FPGA AGNT2: Autonomous Agent Economies on Interaction-Optimized Layer 2 Infrastructure FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels Stream-CQSA: Avoiding Out-of-Memory in Attention Computation via Flexible Workload Scheduling A Delta-Aware Orchestration Framework for Scalable Multi-Agent Edge Computing Federated Learning over Blockchain-Enabled Cloud Infrastructure Optimal Routing for Federated Learning over Dynamic Satellite Networks: Tractable or Not? Sherpa.ai Privacy-Preserving Multi-Party Entity Alignment without Intersection Disclosure for Noisy Identifiers
Speculation at a Distance: Where Edge-Cloud Speculative D...
[Submitted on 23 Jun 2026] · 2026-06-25 · via cs.DC updates on arXiv.org

View PDF HTML (experimental)

Abstract:Speculative decoding (SD) accelerates LLM inference by $1.5$-$3$ times when the draft and target models are co-located. This has motivated a distributed variant (DSD) that places the draft model on an edge device while the target stays in the cloud. We show with closed-form inequalities that DSD's per-request latency benefit is limited under WAN edge-cloud communication. If the server can host both models, co-located SD has lower latency and communication than synchronous DSD, with the same per-output FLOPs and model-weight memory. Pipelining can make DSD competitive with co-located SD only in low-RTT regimes where the round trip is shorter than the edge drafting time window; at WAN RTTs, the cloud round trip remains too large for pipelined DSD to beat co-located SD. Against cloud autoregressive decoding, DSD can reduce latency only inside a bounded window given the target-model speed, acceptance rate, and RTT. DSD is also infeasible against closed-source APIs without a verifier-only interface. The main case for DSD appears in multi-tenant capacity. Under cross-client overlap, offloading draft compute lets a saturated cloud server sustain $(1 + \gamma\,t_d/t_v)$ times more concurrent clients at the same per-client rate, where $\gamma$ is the speculation length and $t_d, t_v$ are the per-step draft and verification times. DSD should therefore be evaluated primarily by multi-tenant capacity and server throughput, not only by single-request latency.

Submission history

From: Yuan Lyu [view email]
[v1] Tue, 23 Jun 2026 18:55:18 UTC (100 KB)

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。