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

G
Google Developers Blog
Apple Machine Learning Research
Apple Machine Learning Research
小众软件
小众软件
Recent Announcements
Recent Announcements
阮一峰的网络日志
阮一峰的网络日志
IT之家
IT之家
A
About on SuperTechFans
量子位
Engineering at Meta
Engineering at Meta
B
Blog
The Cloudflare Blog
博客园 - 【当耐特】
Hugging Face - Blog
Hugging Face - Blog
Y
Y Combinator Blog
J
Java Code Geeks
D
DataBreaches.Net
aimingoo的专栏
aimingoo的专栏
T
Tailwind CSS Blog
H
Help Net Security
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
V
V2EX
Stack Overflow Blog
Stack Overflow Blog
C
Check Point Blog
酷 壳 – CoolShell
酷 壳 – CoolShell

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
kube-volttron: Rearchitecting the VOLTTRON Building Energ...
James Kempf · 2022-10-27 · via cs.DC updates on arXiv.org

Managing the energy consumption of the built environment is an important source of flexible load and decarbonization, enabling building managers and utilities to schedule consumption to avoid costly demand charges and peak times when carbon emissions from grid generated electricity are highest. A key technology component in building energy management is the building energy management system. Eclipse VOLTTRON is a legacy software platform which enables building energy management. It was developed for the US Department of Energy (DOE) at Pacific Northwest National Labs (PNNL) written in Python and based on a monolithic build-configure-and-run-in-place system architecture that predates cloud native architectural concepts. Yet the software architecture is componentized in a way that anticipates modular containerized applications, with software agents handling functions like data storage, web access, and communication with IoT devices over specific IoT protocols such as BACnet and Modbus. The agents communicate among themselves over a message bus. This paper describes a proof-of-concept prototype to rearchitect VOLTTRON into a collection of microservices suitable for deployment on the Kubernetes cloud native container orchestration platform. The agents are packaged in redistributable containers that perform specific functions and which can be configured when they are deployed. The deployment architecture consists of single Kubernetes cluster containing a central node, nominally in a cloud-based VM, where a microservice containing the database agent (called a "historian") and the web site agent for the service run, and gateway nodes running on sites in buildings where a microservice containing IoT protocol-specific agents handles control and data collection to and from devices, and communication back to the central node.