Cover Image

Samoyeds: Accelerating MoE Models with Structured Sparsity Leveraging Sparse Tensor Cores

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Chenpeng, Gu, Qiqi, Shi, Heng, Yao, Jianguo, Guan, Haibing
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing Operating Systems
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Do We Need Tensor Cores for Stencil Computations?
by: Gu, Qiqi, et al.
Published: (2026)

SPIDER: Unleashing Sparse Tensor Cores for Stencil Computation via Strided Swapping
by: GU, Qiqi, et al.
Published: (2025)

DualSparse-MoE: Coordinating Tensor/Neuron-Level Sparsity with Expert Partition and Reconstruction
by: Cai, Weilin, et al.
Published: (2025)

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

ContiguousKV: Accelerating LLM Prefill with Granularity-Aligned KV Cache Management
by: Zou, Jing, et al.
Published: (2026)

FastMig: Leveraging FastFreeze to Establish Robust Service Liquidity in Cloud 2.0
by: Manatura, Sorawit, et al.
Published: (2024)

EdgeWeaver: Accelerating IoT Application Development Across Edge-Cloud Continuum
by: Lertpongrujikorn, Pawissanutt, et al.
Published: (2026)

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

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

PhoenixOS: Concurrent OS-level GPU Checkpoint and Restore with Validated Speculation
by: Wei, Xingda, et al.
Published: (2024)

Toward Systems Foundations for Agentic Exploration
by: Xu, Jiakai, et al.
Published: (2025)

FALCON: Pinpointing and Mitigating Stragglers for Large-Scale Hybrid-Parallel Training
by: Wu, Tianyuan, et al.
Published: (2024)

Optimizing Task Scheduling in Heterogeneous Computing Environments: A Comparative Analysis of CPU, GPU, and ASIC Platforms Using E2C Simulator
by: Mohammadjafari, Ali, et al.
Published: (2024)

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

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

TrEnv-X: Transparently Share Serverless Execution Environments Across Different Functions and Nodes
by: Huang, Jialiang, et al.
Published: (2025)

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

OD-MoE: On-Demand Expert Loading for Cacheless Edge-Distributed MoE Inference
by: Wang, Liujianfu, 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)

Mitigating context switching in densely packed Linux clusters with Latency-Aware Group Scheduling
by: Isstaif, Al Amjad Tawfiq, et al.
Published: (2025)

DPC: A Distributed Page Cache over CXL
by: Bergman, Shai, et al.
Published: (2026)

EdgeFlow: Fast Cold Starts for LLMs on Mobile Devices
by: Yan, Yongsheng, et al.
Published: (2026)

Unlocking True Elasticity for the Cloud-Native Era with Dandelion
by: Kuchler, Tom, et al.
Published: (2025)

A Periodic Space of Distributed Computing: Vision & Framework
by: Salehi, Mohsen Amini, et al.
Published: (2026)

THEMIS: Time, Heterogeneity, and Energy Minded Scheduling for Fair Multi-Tenant Use in FPGAs
by: Karabulut, Emre, et al.
Published: (2024)

Formal Definitions and Performance Comparison of Consistency Models for Parallel File Systems
by: Wang, Chen, et al.
Published: (2024)

Mewz: Lightweight Execution Environment for WebAssembly with High Isolation and Portability using Unikernels
by: Ueda, Soichiro, et al.
Published: (2024)

Taming Serverless Cold Starts Through OS Co-Design
by: Holmes, Ben, et al.
Published: (2025)

Fix: externalizing network I/O in serverless computing
by: Deng, Yuhan, et al.
Published: (2025)

RAGDoll: Efficient Offloading-based Online RAG System on a Single GPU
by: Yu, Weiping, et al.
Published: (2025)

Performance Isolation and Semantic Determinism in Efficient GPU Spatial Sharing
by: Yang, Zhenyuan, et al.
Published: (2026)

Telepathic Datacenters: Fast RPCs using Shared CXL Memory
by: Mahar, Suyash, et al.
Published: (2024)

Equilibria: Fair Multi-Tenant CXL Memory Tiering At Scale
by: Zhao, Kaiyang, et al.
Published: (2026)

CvxCluster: Solving Large, Complex, Granular Resource Allocation Problems 100-1000x Faster
by: Nnorom Jr, Obi, et al.
Published: (2026)

Towards Efficient and Practical GPU Multitasking in the Era of LLM
by: Xing, Jiarong, et al.
Published: (2025)

Agent Centric Operating System -- a Comprehensive Review and Outlook for Operating System
by: Jia, Shian, et al.
Published: (2024)

GPUOS: A GPU Operating System Primitive for Transparent Operation Fusion
by: Yang, Yiwei, et al.
Published: (2026)

"Range as a Key" is the Key! Fast and Compact Cloud Block Store Index with RASK
by: Zhao, Haoru, et al.
Published: (2026)

LEFT-RS: A Lock-Free Fault-Tolerant Resource Sharing Protocol for Multicore Real-Time Systems
by: Chen, Nan, et al.
Published: (2025)

Funky: Cloud-Native FPGA Virtualization and Orchestration
by: Koshiba, Atsushi, et al.
Published: (2025)