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

WordPress大学
WordPress大学
G
Google Developers Blog
M
MIT News - Artificial intelligence
Vercel News
Vercel News
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
GbyAI
GbyAI
B
Blog RSS Feed
Blog — PlanetScale
Blog — PlanetScale
Microsoft Security Blog
Microsoft Security Blog
V
Visual Studio Blog
Stack Overflow Blog
Stack Overflow Blog
雷峰网
雷峰网
The Cloudflare Blog
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
F
Fortinet All Blogs
L
LangChain Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
A
About on SuperTechFans
T
The Blog of Author Tim Ferriss
B
Blog
J
Java Code Geeks
Hugging Face - Blog
Hugging Face - Blog
I
InfoQ
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com

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
An Edge-Cloud based Reference Architecture to support cog...
Antonio Salis, Angelo Marguglio, Gabriele De Luca, Sergio Gusmer · 2022-02-14 · via cs.DC updates on arXiv.org

Process Industry (PI e.g. Steel, Metals, Chemicals, Cement, Asphalt, Ceramics) is one of the leading sectors of the world economy, characterized however by intense environmental impact, and very high energy consumption. In spite of a traditional low innovation pace in PI, in the recent years a strong push at worldwide level towards the dual objective of improving the efficiency of plants and the quality of products, significantly reducing the consumption of electricity and CO2 emissions has taken momentum. Digital Technologies (namely Smart Embedded Systems, IoT, Data, AI and Edge-to-Cloud Technologies) are enabling drivers for a Twin Digital-Green Transition, as well as foundations for human centric, safe, comfortable and inclusive work places. Currently, digital sensors in plants produce a large amount of data which in most cases constitutes just a potential and not a real value for Process Industry, often locked-in in close proprietary systems and seldomly exploited. Digital technologies, with process modelling-simulation via digital twins, can build a bridge between the physical and the virtual worlds, bringing innovation with great efficiency and drastic reduction of waste. In accordance with the guidelines of Industrie 4.0, the H2020 funded CAPRI project aims to innovate the process industry, with a modular and scalable Reference Architecture, based on open source software, which can be implemented both in brownfield and greenfield scenarios. The ability to distribute processing between the edge, where the data is created, and the cloud, where the greatest computational resources are available, facilitates the development of integrated digital solutions with cognitive capabilities. The reference architecture is being validated in the asphalt, steel & pharma pilot plants, allowing the development of integrated planning solutions, with scheduling and control of the plants.