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

Last Week in AI
Last Week in AI
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
博客园_首页
雷峰网
雷峰网
IT之家
IT之家
I
InfoQ
酷 壳 – CoolShell
酷 壳 – CoolShell
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
B
Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园 - 【当耐特】
大猫的无限游戏
大猫的无限游戏
博客园 - 聂微东
Hugging Face - Blog
Hugging Face - Blog
A
About on SuperTechFans
月光博客
月光博客
P
Proofpoint News Feed
博客园 - 三生石上(FineUI控件)
J
Java Code Geeks
G
Google Developers Blog
小众软件
小众软件
宝玉的分享
宝玉的分享
Jina AI
Jina AI
V
Visual Studio Blog

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
Be Aware of Your Leaders
Shir Cohen, Rati Gelashvili, Lefteris Kokoris Kogias, Zekun Li, · 2021-10-03 · via cs.DC updates on arXiv.org

Advances in blockchains have influenced the State-Machine-Replication (SMR) world and many state-of-the-art blockchain-SMR solutions are based on two pillars: Chaining and Leader-rotation. A predetermined round-robin mechanism used for Leader-rotation, however, has an undesirable behavior: crashed parties become designated leaders infinitely often, slowing down overall system performance. In this paper, we provide a new Leader-Aware SMR framework that, among other desirable properties, formalizes a Leader-utilization requirement that bounds the number of rounds whose leaders are faulty in crash-only executions. We introduce Carousel, a novel, reputation-based Leader-rotation solution to achieve Leader-Aware SMR. The challenge in adaptive Leader-rotation is that it cannot rely on consensus to determine a leader, since consensus itself needs a leader. Carousel uses the available on-chain information to determine a leader locally and achieves Liveness despite this difficulty. A HotStuff implementation fitted with Carousel demonstrates drastic performance improvements: it increases throughput over 2x in faultless settings and provided a 20x throughput increase and 5x latency reduction in the presence of faults.