Cover Image

ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Yuchen, Zhao, Yaru, Yang, Pu, Wang, Shaowei, Zhou, Zhi-Hua
Format:	Preprint
Published:	2026
Subjects:	Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference
by: Zhong, Shuzhang, et al.
Published: (2025)

ProMoE: Fast MoE-based LLM Serving using Proactive Caching
by: Song, Xiaoniu, et al.
Published: (2024)

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

MPipeMoE: Memory Efficient MoE for Pre-trained Models with Adaptive Pipeline Parallelism
by: Zhang, Zheng, et al.
Published: (2025)

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

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

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

Fine-grained MoE Load Balancing with Linear Programming
by: Zhao, Chenqi, et al.
Published: (2025)

Multi-Layer Scheduling for MoE-Based LLM Reasoning
by: Sun, Yifan, 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)

MixServe: An Automatic Distributed Serving System for MoE Models with Hybrid Parallelism Based on Fused Communication Algorithm
by: Zhou, Bowen, et al.
Published: (2026)

BrownoutServe: SLO-Aware Inference Serving under Bursty Workloads for MoE-based LLMs
by: Hu, Jianmin, et al.
Published: (2025)

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

MemFine: Memory-Aware Fine-Grained Scheduling for MoE Training
by: Zhao, Lu, et al.
Published: (2025)

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

MoE-Lens: Towards the Hardware Limit of High-Throughput MoE LLM Serving Under Resource Constraints
by: Yuan, Yichao, et al.
Published: (2025)

From Tokens to Layers: Redefining Stall-Free Scheduling for MoE Serving with Layered Prefill
by: Lee, Gunjun, et al.
Published: (2025)

UCCL-Zip: Lossless Compression Supercharged GPU Communication
by: Ma, Shuang, et al.
Published: (2026)

MoEless: Efficient MoE LLM Serving via Serverless Computing
by: Yu, Hanfei, et al.
Published: (2026)

Efficient MoE Serving in the Memory-Bound Regime: Balance Activated Experts, Not Tokens
by: Yu, Yanpeng, et al.
Published: (2025)

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

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

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

MoE Parallel Folding: Heterogeneous Parallelism Mappings for Efficient Large-Scale MoE Model Training with Megatron Core
by: Liu, Dennis, et al.
Published: (2025)

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

SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving
by: Guo, Yipin, et al.
Published: (2026)

A Scheduling Framework for Efficient MoE Inference on Edge GPU-NDP Systems
by: Wu, Qi, et al.
Published: (2026)

ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression
by: Fan, Ruibo, et al.
Published: (2026)

ViBE: Co-Optimizing Workload Skew and Hardware Variability for MoE Serving
by: Go, Seokjin, et al.
Published: (2026)

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

Sparse Checkpointing for Fast and Reliable MoE Training
by: Gandhi, Swapnil, et al.
Published: (2024)

MoDM: Efficient Serving for Image Generation via Mixture-of-Diffusion Models
by: Xia, Yuchen, et al.
Published: (2025)

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

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

ZipCCL: Efficient Lossless Data Compression of Communication Collectives for Accelerating LLM Training
by: Lin, Wenxiang, et al.
Published: (2026)

MoLink: Distributed and Efficient Serving Framework for Large Models
by: Jin, Lewei, et al.
Published: (2025)

Priority-Aware Preemptive Scheduling for Mixed-Priority Workloads in MoE Inference
by: Siavashi, Mohammad, et al.
Published: (2025)