Image de couverture de livre

CRAFT: Fine-Grained Cost-Aware Expert Replication For Efficient Mixture-of-Experts Serving

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhao, Adrian, Cai, Zhenkun, Song, Zhenyu, Yu, Lingfan, Fan, Haozheng, Wu, Jun, Wang, Yida, Vijaykumar, Nandita
Format:	Preprint
Publié:	2026
Sujets:	Distributed, Parallel, and Cluster Computing Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Toward Cost-Efficient Serving of Mixture-of-Experts with Asynchrony
par: Wang, Shaoyu, et autres
Publié: (2025)

ExpertWeave: Efficiently Serving Expert-Specialized Fine-Tuned Adapters at Scale
par: Shi, Ge, et autres
Publié: (2025)

PALS: Power-Aware LLM Serving for Mixture-of-Experts Models
par: Hankendi, Can, et autres
Publié: (2026)

MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
par: Zhu, Ruidong, et autres
Publié: (2025)

MoETuner: Optimized Mixture of Expert Serving with Balanced Expert Placement and Token Routing
par: Go, Seokjin, et autres
Publié: (2025)

QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration
par: Imani, HamidReza, et autres
Publié: (2025)

SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models
par: Du, Zhixu, et autres
Publié: (2023)

ElasticMoE: An Efficient Auto Scaling Method for Mixture-of-Experts Models
par: Singh, Gursimran, et autres
Publié: (2025)

Elastic Mixture of Rank-Wise Experts for Knowledge Reuse in Federated Fine-Tuning
par: Wu, Yebo, et autres
Publié: (2025)

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference
par: Lin, Haoran, et autres
Publié: (2025)

Stateful Large Language Model Serving with Pensieve
par: Yu, Lingfan, et autres
Publié: (2023)

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

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

Accelerating Mixture-of-Experts Inference by Hiding Offloading Latency with Speculative Decoding
par: Wang, Zhibin, et autres
Publié: (2025)

Lancet: Accelerating Mixture-of-Experts Training via Whole Graph Computation-Communication Overlapping
par: Jiang, Chenyu, et autres
Publié: (2024)

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

FaaSMoE: A Serverless Framework for Multi-Tenant Mixture-of-Experts Serving
par: Wang, Minghe, et autres
Publié: (2026)

MoC-System: Efficient Fault Tolerance for Sparse Mixture-of-Experts Model Training
par: Cai, Weilin, et autres
Publié: (2024)

FedMoE-DA: Federated Mixture of Experts via Domain Aware Fine-grained Aggregation
par: Zhan, Ziwei, et autres
Publié: (2024)

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

Optimal Expert Selection for Distributed Mixture-of-Experts at the Wireless Edge
par: Qin, Shengling, et autres
Publié: (2025)

Scattered Mixture-of-Experts Implementation
par: Tan, Shawn, et autres
Publié: (2024)

Shortcut-connected Expert Parallelism for Accelerating Mixture-of-Experts
par: Cai, Weilin, et autres
Publié: (2024)

FASER: Fine-Grained Phase Management for Speculative Decoding in Dynamic LLM Serving
par: Chen, Wenyan, et autres
Publié: (2026)

MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems
par: Jiang, Yinsicheng, et autres
Publié: (2025)

MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems
par: Jiang, Yinsicheng, et autres
Publié: (2024)

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

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

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

MoDM: Efficient Serving for Image Generation via Mixture-of-Diffusion Models
par: Xia, Yuchen, et autres
Publié: (2025)

DiffServe: Efficiently Serving Text-to-Image Diffusion Models with Query-Aware Model Scaling
par: Ahmad, Sohaib, et autres
Publié: (2024)

FlowMoE: A Scalable Pipeline Scheduling Framework for Distributed Mixture-of-Experts Training
par: Gao, Yunqi, et autres
Publié: (2025)

SYMI: Efficient Mixture-of-Experts Training via Model and Optimizer State Decoupling
par: Skiadopoulos, Athinagoras, et autres
Publié: (2025)

HeterMoE: Efficient Training of Mixture-of-Experts Models on Heterogeneous GPUs
par: Wu, Yongji, et autres
Publié: (2025)

Harpagon: Minimizing DNN Serving Cost via Efficient Dispatching, Scheduling and Splitting
par: Zhao, Zhixin, et autres
Publié: (2024)

S-HPLB: Efficient LLM Attention Serving via Sparsity-Aware Head Parallelism Load Balance
par: Liu, Di, et autres
Publié: (2026)

DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling
par: Gao, Yubo, et autres
Publié: (2025)

Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading
par: Yu, Hanfei, et autres
Publié: (2025)

The Cost of Garbage Collection for State Machine Replication
par: Liang, Zhiying, et autres
Publié: (2024)

Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts
par: Zhang, Shulai, et autres
Publié: (2025)