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
GbyAI
GbyAI
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Apple Machine Learning Research
Apple Machine Learning Research
大猫的无限游戏
大猫的无限游戏
阮一峰的网络日志
阮一峰的网络日志
Last Week in AI
Last Week in AI
V
Visual Studio Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
The Cloudflare Blog
博客园 - 【当耐特】
博客园 - 叶小钗
量子位
博客园 - 聂微东
S
SegmentFault 最新的问题
美团技术团队
Hugging Face - Blog
Hugging Face - 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
月光博客
月光博客
宝玉的分享
宝玉的分享
小众软件
小众软件
罗磊的独立博客
有赞技术团队
有赞技术团队
Stack Overflow Blog
Stack Overflow 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
Stateless Snowflake: A Cloud-Agnostic Distributed ID Gene...
Manideep Reddy Chinthareddy · 2025-12-12 · via cs.DC updates on arXiv.org

Snowflake-style distributed ID generators are the industry standard for producing k-ordered, unique identifiers at scale. However, the traditional requirement for manually assigned or centrally coordinated worker IDs introduces significant friction in modern container-orchestrated environments (e.g., Kubernetes), where workloads are ephemeral and autoscaled. In such systems, maintaining stable worker identities requires complex stateful sets or external coordination services (e.g., ZooKeeper), negating the operational benefits of stateless microservices. This paper presents a cloud-agnostic, container-native ID generation protocol that eliminates the dependency on explicit worker IDs. By deriving node uniqueness deterministically from ephemeral network properties - specifically the container's private IPv4 address - the proposed method removes the need for centralized coordination. We introduce a modified bit-allocation scheme (1-41-16-6) that accommodates 16 bits of network-derived entropy while preserving strict monotonicity. We validate the approach across AWS, GCP, and Azure environments. Evaluation results demonstrate that while the design has a theoretical single-node ceiling of approximately 64,000 TPS, in practical microservice deployments the network I/O dominates latency, resulting in end-to-end performance (approximately 31,000 TPS on a 3-node cluster) comparable to classic stateful generators while offering effectively unbounded horizontal scalability.