Copertina

Lattica: A Decentralized Cross-NAT Communication Framework for Scalable AI Inference and Training

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yang, Ween, Liu, Jason, Wang, Suli, Song, Xinyuan, Ai, Lynn, Yang, Eric, Shi, Bill
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Distributed, Parallel, and Cluster Computing
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Speculative Decoding in Decentralized LLM Inference: Turning Communication Latency into Computation Throughput
di: Song, Jingwei, et al.
Pubblicazione: (2025)

Parallax: Efficient LLM Inference Service over Decentralized Environment
di: Tong, Chris, et al.
Pubblicazione: (2025)

Beyond A Single AI Cluster: A Survey of Decentralized LLM Training
di: Dong, Haotian, et al.
Pubblicazione: (2025)

DFedSat: Communication-Efficient and Robust Decentralized Federated Learning for LEO Satellite Constellations
di: Yang, Minghao, et al.
Pubblicazione: (2024)

Cross-region Model Training with Communication-Computation Overlapping and Delay Compensation
di: Zhu, Ying, et al.
Pubblicazione: (2025)

ParaGAN: A Scalable Distributed Training Framework for Generative Adversarial Networks
di: Shi, Ziji, et al.
Pubblicazione: (2024)

DistFlow: A Fully Distributed RL Framework for Scalable and Efficient LLM Post-Training
di: Wang, Zhixin, et al.
Pubblicazione: (2025)

DeServe: Towards Affordable Offline LLM Inference via Decentralization
di: Wu, Linyu, et al.
Pubblicazione: (2025)

Janus: Disaggregating Attention and Experts for Scalable MoE Inference
di: Zhang, Zhexiang, et al.
Pubblicazione: (2025)

ACE-Sync: An Adaptive Cloud-Edge Synchronization Framework for Communication-Efficient Large-Scale Distributed Model Training
di: Yang, Yi, et al.
Pubblicazione: (2025)

ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning
di: Song, Jingwei, et al.
Pubblicazione: (2026)

PICO: Pipeline Inference Framework for Versatile CNNs on Diverse Mobile Devices
di: Yang, Xiang, et al.
Pubblicazione: (2022)

PolyLink: A Blockchain Based Decentralized Edge AI Platform for LLM Inference
di: Liu, Hongbo, et al.
Pubblicazione: (2025)

Federated Inference for Heterogeneous LLM Communication and Collaboration
di: Chen, Zihan, et al.
Pubblicazione: (2026)

Decentralized LLM Inference over Edge Networks with Energy Harvesting
di: Khoshsirat, Aria, et al.
Pubblicazione: (2024)

Enhancing Memory Efficiency in Large Language Model Training Through Chronos-aware Pipeline Parallelism
di: Lin, Xinyuan, et al.
Pubblicazione: (2025)

Decentralized AI: Permissionless LLM Inference on POKT Network
di: Olshansky, Daniel, et al.
Pubblicazione: (2024)

DiFache: Efficient and Scalable Caching on Disaggregated Memory using Decentralized Coherence
di: Zhang, Hanze, et al.
Pubblicazione: (2025)

BurstEngine: an Efficient Distributed Framework for Training Transformers on Extremely Long Sequences of over 1M Tokens
di: Sun, Ao, et al.
Pubblicazione: (2025)

EC2MoE: Adaptive End-Cloud Pipeline Collaboration Enabling Scalable Mixture-of-Experts Inference
di: Yang, Zheming, et al.
Pubblicazione: (2025)

FedCod: An Efficient Communication Protocol for Cross-Silo Federated Learning with Coding
di: Yan, Peishen, et al.
Pubblicazione: (2024)

BeACONS: A Blockchain-enabled Authentication and Communications Network for Scalable IoV
di: Shi, Qi, et al.
Pubblicazione: (2024)

Unleashing Scalable Context Parallelism for Foundation Models Pre-Training via FCP
di: Zhao, Yilong, et al.
Pubblicazione: (2026)

FlowMoE: A Scalable Pipeline Scheduling Framework for Distributed Mixture-of-Experts Training
di: Gao, Yunqi, et al.
Pubblicazione: (2025)

PROBE: Co-Balancing Computation and Communication in MoE Inference via Real-Time Predictive Prefetching
di: Zhu, Qianchao, et al.
Pubblicazione: (2026)

RainCloud: Decentralized Coordination and Communication in Heterogeneous IoT Swarms
di: Loisel, Filip, et al.
Pubblicazione: (2024)

Graph-based Gossiping for Communication Efficiency in Decentralized Federated Learning
di: Nguyen, Huong, et al.
Pubblicazione: (2025)

Towards Communication-Efficient Decentralized Federated Graph Learning over Non-IID Data
di: Wang, Shilong, et al.
Pubblicazione: (2025)

SWARM+: Scalable and Resilient Multi-Agent Consensus for Fully-Decentralized Data-Aware Workload Management
di: Thareja, Komal, et al.
Pubblicazione: (2026)

ElasWave: An Elastic-Native System for Scalable Hybrid-Parallel Training
di: Kang, Xueze, et al.
Pubblicazione: (2025)

Distributed Generative Inference of LLM at Internet Scales with Multi-Dimensional Communication Optimization
di: Chen, Jiu, et al.
Pubblicazione: (2026)

LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive Hashing
di: Nie, Xiaonan, et al.
Pubblicazione: (2024)

Evaluation Framework for Centralized and Decentralized Aggregation Algorithm in Federated Systems
di: Chongder, Sumit
Pubblicazione: (2025)

The Evolution of Decentralized Systems: From Gray's Framework to Blockchain and Beyond
di: Dong, Zhongli, et al.
Pubblicazione: (2026)

Ripple: Scalable Incremental GNN Inferencing on Large Streaming Graphs
di: Naman, Pranjal, et al.
Pubblicazione: (2025)

AI Inference as Relocatable Electricity Demand: A Latency-Constrained Energy-Geography Framework
di: Luo, Xubin, et al.
Pubblicazione: (2026)

SpecInF: Exploiting Idle GPU Resources in Distributed DL Training via Speculative Inference Filling
di: Lv, Cunchi, et al.
Pubblicazione: (2025)

SDFLMQ: A Semi-Decentralized Federated Learning Framework over MQTT
di: Ali-Pour, Amir, et al.
Pubblicazione: (2025)

MOPAR: A Model Partitioning Framework for Deep Learning Inference Services on Serverless Platforms
di: Duan, Jiaang, et al.
Pubblicazione: (2024)

Poplar: Efficient Scaling of Distributed DNN Training on Heterogeneous GPU Clusters
di: Zhang, WenZheng, et al.
Pubblicazione: (2024)