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

Hugging Face - Blog
Hugging Face - Blog
WordPress大学
WordPress大学
Microsoft Azure Blog
Microsoft Azure Blog
F
Fortinet All Blogs
B
Blog RSS Feed
Last Week in AI
Last Week in AI
The Cloudflare Blog
大猫的无限游戏
大猫的无限游戏
人人都是产品经理
人人都是产品经理
P
Proofpoint News Feed
H
Hackread – Cybersecurity News, Data Breaches, AI and More
Microsoft Security Blog
Microsoft Security Blog
博
博客园 - 三生石上(FineUI控件)
Y
Y Combinator Blog
GbyAI
GbyAI
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
小众软件
小众软件
雷峰网
雷峰网
C
Check Point Blog
阮一峰的网络日志
阮一峰的网络日志
博
博客园 - 叶小钗
博
博客园 - 司徒正美
U
Unit 42
量
量子位

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
LA-IMR: Latency-Aware, Predictive In-Memory Routing and P...
[Submitted on 12 May 2025 (v1), last revised 14 Jul 2026 (this v · 2025-05-12 · via cs.DC updates on arXiv.org

View PDF HTML (experimental)

Abstract:Hybrid cloud-edge infrastructures now support latency-critical workloads ranging from autonomous vehicles and surgical robotics to immersive AR/VR. However, they continue to experience crippling long-tail latency spikes whenever bursty request streams exceed the capacity of heterogeneous edge and cloud tiers. To address these long-tail latency issues, we present Latency-Aware, Predictive In-Memory Routing and Proactive Autoscaling (LA-IMR). This control layer integrates a closed-form, utilization-driven latency model with event-driven scheduling, replica autoscaling, and edge-to-cloud offloading to mitigate 99th-percentile (P99) delays. Our analytic model decomposes end-to-end latency into processing, network, and queuing components, expressing inference latency as an affine power-law function of instance utilization. Once calibrated, it produces two complementary functions that drive: (i) millisecond-scale routing decisions for traffic offloading, and (ii) capacity planning that jointly determines replica pool sizes. LA-IMR enacts these decisions through a quality-differentiated, multi-queue scheduler and a custom-metric Kubernetes autoscaler that scales replicas proactively -- before queues build up -- rather than reactively based on lagging CPU metrics. Across representative vision workloads (YOLOv5m and EfficientDet) and bursty arrival traces, LA-IMR reduces P99 latency by up to 20.7 percent compared to traditional latency-only autoscaling, laying a principled foundation for next-generation, tail-tolerant cloud-edge inference services.

Submission history

From: Eunil Seo [view email]
[v1] Mon, 12 May 2025 10:12:24 UTC (3,884 KB)
[v2] Sun, 24 May 2026 14:55:51 UTC (3,812 KB)
[v3] Tue, 14 Jul 2026 14:46:46 UTC (3,878 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。