Cover Image

Janus: Disaggregating Attention and Experts for Scalable MoE Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Zhexiang, Wang, Ye, Zhao, Yumiao, Xiao, Jiayu, Yang, Qianjing, Wang, Xiangyu, Jiang, Jingzhe, Weng, Qizhen, Chen, Ruichuan, Shi, Shaohuai, Toosi, Adel N., Chen, Yin, Yu, Minchen
Format:	Preprint
Published:	2025
Subjects:	Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Multi-Layer Scheduling for MoE-Based LLM Reasoning
by: Sun, Yifan, et al.
Published: (2026)

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

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

Revealing the Challenges of Attention-FFN Disaggregation for Modern MoE Models and Hardware Systems
by: Liu, Guowei, et al.
Published: (2026)

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

CaraServe: CPU-Assisted and Rank-Aware LoRA Serving for Generative LLM Inference
by: Li, Suyi, et al.
Published: (2024)

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

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

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

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

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

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

Efficient Routing of Inference Requests across LLM Instances in Cloud-Edge Computing
by: Yu, Shibo, et al.
Published: (2025)

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

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

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

Resilience Evaluation of Kubernetes in Cloud-Edge Environments via Failure Injection
by: Chen, Zihao, et al.
Published: (2025)

Torpor: GPU-Enabled Serverless Computing for Low-Latency, Resource-Efficient Inference
by: Yu, Minchen, et al.
Published: (2023)

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

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

SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models
by: Du, Zhixu, et al.
Published: (2023)

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

λScale: Enabling Fast Scaling for Serverless Large Language Model Inference
by: Yu, Minchen, et al.
Published: (2025)

From Attention to Disaggregation: Tracing the Evolution of LLM Inference
by: Kumar, Madabattula Rajesh, et al.
Published: (2025)

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

Accelerating MoE Model Inference with Expert Sharding
by: Balmau, Oana, et al.
Published: (2025)

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

Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads
by: Hu, Cunchen, et al.
Published: (2024)

Stable-MoE: Lyapunov-based Token Routing for Distributed Mixture-of-Experts Training over Edge Networks
by: Shi, Long, et al.
Published: (2025)

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

How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving
by: Wu, Hanjiang, et al.
Published: (2026)

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

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

A Multi-Armed Bandit-Based Participant Selection Method for Federated Recommendation Systems
by: Liu, Jintao, et al.
Published: (2025)

CALVO: Improve Serving Efficiency for LLM Inferences with Intense Network Demands
by: Wang, Weiye, et al.
Published: (2026)

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

DisagMoE: Computation-Communication overlapped MoE Training via Disaggregated AF-Pipe Parallelism
by: Zeng, Zhichen, et al.
Published: (2026)

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

Lotus: Optimizing Disaggregated Transactions with Disaggregated Locks
by: Hu, Zhisheng, et al.
Published: (2025)