Copertina

Accelerating MoE Model Inference with Expert Sharding

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Balmau, Oana, Kermarrec, Anne-Marie, Pires, Rafael, Santo, André Loureiro Espírito, de Vos, Martijn, Vujasinovic, Milos
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

HarMoEny: Efficient Multi-GPU Inference of MoE Models
di: Doucet, Zachary, et al.
Pubblicazione: (2025)

Decentralized Learning Made Easy with DecentralizePy
di: Dhasade, Akash, et al.
Pubblicazione: (2023)

Get More for Less in Decentralized Learning Systems
di: Dhasade, Akash, et al.
Pubblicazione: (2023)

PeerSwap: A Peer-Sampler with Randomness Guarantees
di: Guerraoui, Rachid, et al.
Pubblicazione: (2024)

Harnessing Increased Client Participation with Cohort-Parallel Federated Learning
di: Dhasade, Akash, et al.
Pubblicazione: (2024)

OD-MoE: On-Demand Expert Loading for Cacheless Edge-Distributed MoE Inference
di: Wang, Liujianfu, et al.
Pubblicazione: (2025)

Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert Placement
di: Wu, Tian, et al.
Pubblicazione: (2025)

SP-MoE: Speculative Decoding and Prefetching for Accelerating MoE-based Model Inference
di: Chen, Liangkun, et al.
Pubblicazione: (2025)

Boosting Asynchronous Decentralized Learning with Model Fragmentation
di: Biswas, Sayan, et al.
Pubblicazione: (2024)

Accelerating Distributed MoE Training and Inference with Lina
di: Li, Jiamin, et al.
Pubblicazione: (2022)

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

Practical Federated Learning without a Server
di: Dhasade, Akash, et al.
Pubblicazione: (2025)

Decentralized Learning Made Practical with Client Sampling
di: de Vos, Martijn, et al.
Pubblicazione: (2023)

EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference
di: Qian, Yulei, et al.
Pubblicazione: (2024)

MinatoLoader: Accelerating Machine Learning Training Through Efficient Data Preprocessing
di: Nouaji, Rahma, et al.
Pubblicazione: (2025)

Surviving Partial Rank Failures in Wide Expert-Parallel MoE Inference
di: Sun, Xun, et al.
Pubblicazione: (2026)

MoE-Compression: How the Compression Error of Experts Affects the Inference Accuracy of MoE Model?
di: Ma, Songkai, et al.
Pubblicazione: (2025)

Fair Decentralized Learning
di: Biswas, Sayan, et al.
Pubblicazione: (2024)

Energy-Aware Decentralized Learning with Intermittent Model Training
di: Dhasade, Akash, et al.
Pubblicazione: (2024)

Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training and Inference
di: Luo, Shuqing, et al.
Pubblicazione: (2025)

GRACE-MoE: Grouping and Replication with Locality-Aware Routing for Efficient Distributed MoE Inference
di: Han, Yu, et al.
Pubblicazione: (2025)

A Pragmatic Approach to Learned Indexing in RocksDB: Targeted Optimizations with Minimal System Modification
di: Vashisth, Shubham, et al.
Pubblicazione: (2026)

DuoServe-MoE: Dual-Phase Expert Prefetch and Caching for LLM Inference QoS Assurance
di: Zhang, Yuning, et al.
Pubblicazione: (2025)

HierMoE: Accelerating MoE Training with Hierarchical Token Deduplication and Expert Swap
di: Lin, Wenxiang, et al.
Pubblicazione: (2025)

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

Efficient Federated Search for Retrieval-Augmented Generation using Lightweight Routing
di: Dhasade, Akash, et al.
Pubblicazione: (2025)

Hexa-MoE: Efficient and Heterogeneous-aware Training for Mixture-of-Experts
di: Luo, Shuqing, et al.
Pubblicazione: (2024)

Staleness-Centric Optimizations for Parallel Diffusion MoE Inference
di: Luo, Jiajun, et al.
Pubblicazione: (2024)

Efficient MoE Inference with Fine-Grained Scheduling of Disaggregated Expert Parallelism
di: Pan, Xinglin, et al.
Pubblicazione: (2025)

eMoE: Task-aware Memory Efficient Mixture-of-Experts-Based (MoE) Model Inference
di: Tairin, Suraiya, et al.
Pubblicazione: (2025)

UniEP: Unified Expert-Parallel MoE MegaKernel for LLM Training
di: Zheng, Size, et al.
Pubblicazione: (2026)

ExpertFlow: Adaptive Expert Scheduling and Memory Coordination for Efficient MoE Inference
di: Shen, Zixu, et al.
Pubblicazione: (2025)

HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference
di: Tang, Peng, et al.
Pubblicazione: (2024)

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

ReaLB: Real-Time Load Balancing for Multimodal MoE Inference
di: Wang, Yingping, et al.
Pubblicazione: (2026)

ReviveMoE: Fast Recovery for Hardware Failures in Large-Scale MoE LLM Inference Deployments
di: Li, Haley, et al.
Pubblicazione: (2026)

Expert-as-a-Service: Towards Efficient, Scalable, and Robust Large-scale MoE Serving
di: Liu, Ziming, et al.
Pubblicazione: (2025)

Lynx: Enabling Efficient MoE Inference through Dynamic Batch-Aware Expert Selection
di: Gupta, Vima, et al.
Pubblicazione: (2024)

Noiseless Privacy-Preserving Decentralized Learning
di: Biswas, Sayan, et al.
Pubblicazione: (2024)

MoE-Gen: High-Throughput MoE Inference on a Single GPU with Module-Based Batching
di: Xu, Tairan, et al.
Pubblicazione: (2025)