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

博客园_首页
博客园 - 【当耐特】
IT之家
IT之家
M
MIT News - Artificial intelligence
酷 壳 – CoolShell
酷 壳 – CoolShell
Martin Fowler
Martin Fowler
V
Visual Studio Blog
F
Fortinet All Blogs
The Cloudflare Blog
Last Week in AI
Last Week in AI
博客园 - 司徒正美
G
Google Developers Blog
Vercel News
Vercel News
爱范儿
爱范儿
小众软件
小众软件
WordPress大学
WordPress大学
I
InfoQ
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
MongoDB | Blog
MongoDB | Blog
A
About on SuperTechFans
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
C
Check Point Blog
Apple Machine Learning Research
Apple Machine Learning Research
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

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
HammerHead: Leader Reputation for Dynamic Scheduling
Giorgos Tsimos, Anastasios Kichidis, Alberto Sonnino, Lefteris K · 2023-09-22 · via cs.DC updates on arXiv.org

The need for high throughput and censorship resistance in blockchain technology has led to research on DAG-based consensus. The Sui blockchain protocol uses a variant of the Bullshark consensus algorithm due to its lower latency, but this leader-based protocol causes performance issues when candidate leaders crash. In this paper, we explore the ideas pioneered by Carousel on providing Leader-Utilization and present HammerHead. Unlike Carousel, which is built with a chained and pipelined consensus protocol in mind, HammerHead does not need to worry about chain quality as it is directly provided by the DAG, but needs to make sure that even though validators might commit blocks in different views the safety and liveness is preserved. Our implementation of HammerHead shows a slight performance increase in a faultless setting, and a drastic 2x latency reduction and up to 40% throughput increase when suffering faults (100 validators, 33 faults).