Image de couverture de livre

Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Design

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Mohan, Li, Pingzhi, Peng, Jie, Qiu, Mufan, Chen, Tianlong
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computation and Language Distributed, Parallel, and Cluster Computing
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Hexa-MoE: Efficient and Heterogeneous-aware Training for Mixture-of-Experts
par: Luo, Shuqing, et autres
Publié: (2024)

Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training and Inference
par: Luo, Shuqing, et autres
Publié: (2025)

GRACE-MoE: Grouping and Replication with Locality-Aware Routing for Efficient Distributed MoE Inference
par: Han, Yu, et autres
Publié: (2025)

Surviving Partial Rank Failures in Wide Expert-Parallel MoE Inference
par: Sun, Xun, et autres
Publié: (2026)

UniEP: Unified Expert-Parallel MoE MegaKernel for LLM Training
par: Zheng, Size, et autres
Publié: (2026)

OD-MoE: On-Demand Expert Loading for Cacheless Edge-Distributed MoE Inference
par: Wang, Liujianfu, et autres
Publié: (2025)

Stable-MoE: Lyapunov-based Token Routing for Distributed Mixture-of-Experts Training over Edge Networks
par: Shi, Long, et autres
Publié: (2025)

Staleness-Centric Optimizations for Parallel Diffusion MoE Inference
par: Luo, Jiajun, et autres
Publié: (2024)

EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference
par: Qian, Yulei, et autres
Publié: (2024)

Janus: Disaggregating Attention and Experts for Scalable MoE Inference
par: Zhang, Zhexiang, et autres
Publié: (2025)

EC2MoE: Adaptive End-Cloud Pipeline Collaboration Enabling Scalable Mixture-of-Experts Inference
par: Yang, Zheming, et autres
Publié: (2025)

Efficient MoE Inference with Fine-Grained Scheduling of Disaggregated Expert Parallelism
par: Pan, Xinglin, et autres
Publié: (2025)

MPipeMoE: Memory Efficient MoE for Pre-trained Models with Adaptive Pipeline Parallelism
par: Zhang, Zheng, et autres
Publié: (2025)

Expert-as-a-Service: Towards Efficient, Scalable, and Robust Large-scale MoE Serving
par: Liu, Ziming, et autres
Publié: (2025)

Parallel Collaborative ADMM Privacy Computing and Adaptive GPU Acceleration for Distributed Edge Networks
par: Xia, Mengchun, et autres
Publié: (2026)

Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert Placement
par: Wu, Tian, et autres
Publié: (2025)

MoE Parallel Folding: Heterogeneous Parallelism Mappings for Efficient Large-Scale MoE Model Training with Megatron Core
par: Liu, Dennis, et autres
Publié: (2025)

LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive Hashing
par: Nie, Xiaonan, et autres
Publié: (2024)

SP-MoE: Speculative Decoding and Prefetching for Accelerating MoE-based Model Inference
par: Chen, Liangkun, et autres
Publié: (2025)

DuoServe-MoE: Dual-Phase Expert Prefetch and Caching for LLM Inference QoS Assurance
par: Zhang, Yuning, et autres
Publié: (2025)

Efficient CPU-GPU Collaborative Inference for MoE-based LLMs on Memory-Limited Systems
par: Huang, En-Ming, et autres
Publié: (2025)

MoE-Compression: How the Compression Error of Experts Affects the Inference Accuracy of MoE Model?
par: Ma, Songkai, et autres
Publié: (2025)

Pro-Prophet: A Systematic Load Balancing Method for Efficient Parallel Training of Large-scale MoE Models
par: Wang, Wei, et autres
Publié: (2024)

MixServe: An Automatic Distributed Serving System for MoE Models with Hybrid Parallelism Based on Fused Communication Algorithm
par: Zhou, Bowen, et autres
Publié: (2026)

D$^{2}$MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving
par: Wang, Haodong, et autres
Publié: (2025)

MoE-SpeQ: Speculative Quantized Decoding with Proactive Expert Prefetching and Offloading for Mixture-of-Experts
par: Wang, Wenfeng, et autres
Publié: (2025)

HarMoEny: Efficient Multi-GPU Inference of MoE Models
par: Doucet, Zachary, et autres
Publié: (2025)

Accelerating Distributed MoE Training and Inference with Lina
par: Li, Jiamin, et autres
Publié: (2022)

Sparse Checkpointing for Fast and Reliable MoE Training
par: Gandhi, Swapnil, et autres
Publié: (2024)

HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference
par: Tang, Peng, et autres
Publié: (2024)

MoEntwine: Unleashing the Potential of Wafer-scale Chips for Large-scale Expert Parallel Inference
par: Tang, Xinru, et autres
Publié: (2025)

Fine-grained MoE Load Balancing with Linear Programming
par: Zhao, Chenqi, et autres
Publié: (2025)

Multi-Layer Scheduling for MoE-Based LLM Reasoning
par: Sun, Yifan, et autres
Publié: (2026)

LAER-MoE: Load-Adaptive Expert Re-layout for Efficient Mixture-of-Experts Training
par: Liu, Xinyi, et autres
Publié: (2026)

HierMoE: Accelerating MoE Training with Hierarchical Token Deduplication and Expert Swap
par: Lin, Wenxiang, et autres
Publié: (2025)

ReviveMoE: Fast Recovery for Hardware Failures in Large-Scale MoE LLM Inference Deployments
par: Li, Haley, et autres
Publié: (2026)

ReaLB: Real-Time Load Balancing for Multimodal MoE Inference
par: Wang, Yingping, et autres
Publié: (2026)

MemFine: Memory-Aware Fine-Grained Scheduling for MoE Training
par: Zhao, Lu, et autres
Publié: (2025)

eMoE: Task-aware Memory Efficient Mixture-of-Experts-Based (MoE) Model Inference
par: Tairin, Suraiya, et autres
Publié: (2025)

Efficient MoE Serving in the Memory-Bound Regime: Balance Activated Experts, Not Tokens
par: Yu, Yanpeng, et autres
Publié: (2025)