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
M
MIT News - Artificial intelligence
MyScale Blog
MyScale Blog
博客园_首页
G
Google Developers Blog
博客园 - 【当耐特】
美团技术团队
博客园 - 聂微东
Stack Overflow Blog
Stack Overflow Blog
Vercel News
Vercel News
小众软件
小众软件
博客园 - 司徒正美
雷峰网
雷峰网
T
Tailwind CSS Blog
V
V2EX
博客园 - 三生石上(FineUI控件)
F
Fortinet All Blogs
罗磊的独立博客
量子位
P
Proofpoint News Feed
Microsoft Azure Blog
Microsoft Azure Blog
月光博客
月光博客
A
About on SuperTechFans
Hugging Face - Blog
Hugging Face - 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
Object as a Service (OaaS): Enabling Object Abstraction i...
Pawissanutt Lertpongrujikorn, Mohsen Amini Salehi · 2022-06-11 · via cs.DC updates on arXiv.org

Function as a Service (FaaS) paradigm is becoming widespread and is envisioned as the next generation of cloud systems that mitigate the burden for programmers and cloud solution architects. However, the FaaS abstraction only makes the cloud resource management aspects transparent but does not deal with the application data aspects. As such, developers have to undergo the burden of managing the application data, often via separate cloud services (e.g., AWS S3). Similarly, the FaaS abstraction does not natively support function workflow, hence, the developers often have to work with workflow orchestration services (e.g., AWS Step Functions) to build workflows. Moreover, they have to explicitly navigate the data throughout the workflow. To overcome these problems of FaaS, we design a higher-level cloud programming abstraction that hides the complexities and mitigate the burden of developing cloud-native application development. We borrow the notion of object from object-oriented programming and propose a new abstraction level atop the function abstraction, known as Object as a Service (OaaS). OaaS encapsulates the application data and function into the object abstraction and relieves the developers from resource and data management burdens. It also unlocks opportunities for built-in optimization features, such as software reusability, data locality, and caching. OaaS natively supports dataflow programming such that developers define a workflow of functions transparently without getting involved in data navigation, synchronization, and parallelism aspects. We implemented a prototype of the OaaS platform and evaluated it under real-world settings against state-of-the-art platforms regarding the imposed overhead, scalability, and ease of use. The results demonstrate that OaaS streamlines cloud programming and offers scalability with an insignificant overhead to the underlying cloud system.