Imagen de Portada

MatKV: Trading Compute for Flash Storage in LLM Inference

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shin, Kun-Woo, Park, Jay H., Oh, Moonwook, Jo, Yohan, Do, Jaeyoung, Lee, Sang-Won
Formato:	Preprint
Publicado:	2025
Materias:	Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Accelerating LLM Inference with Precomputed Query Storage
por: Park, Jay H., et al.
Publicado: (2025)

PrefillShare: A Shared Prefill Module for KV Reuse in Multi-LLM Disaggregated Serving
por: Woo, Sunghyeon, et al.
Publicado: (2026)

DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference
por: Wu, Yongtong, et al.
Publicado: (2026)

KV Cache Compression for Inference Efficiency in LLMs: A Review
por: Liu, Yanyu, et al.
Publicado: (2025)

FDC: Fast KV Dimensionality Compression for Efficient LLM Inference
por: Zhang, Zeyu, et al.
Publicado: (2024)

Understanding Bottlenecks for Efficiently Serving LLM Inference With KV Offloading
por: Meng, William, et al.
Publicado: (2025)

Distributed On-Device LLM Inference With Over-the-Air Computation
por: Zhang, Kai, et al.
Publicado: (2025)

WANSpec: Leveraging Global Compute Capacity for LLM Inference
por: Martin, Noah, et al.
Publicado: (2026)

Adaptive Multi-Objective Tiered Storage Configuration for KV Cache in LLM Service
por: Zheng, Xianzhe, et al.
Publicado: (2026)

Optimal Batch Allocation for Wireless Federated Learning
por: Song, Jaeyoung, et al.
Publicado: (2024)

Federated Inference for Heterogeneous LLM Communication and Collaboration
por: Chen, Zihan, et al.
Publicado: (2026)

Amoeba: Runtime Tensor Parallel Transformation for LLM Inference Services
por: Chen, Haoyu, et al.
Publicado: (2025)

EdgeShard: Efficient LLM Inference via Collaborative Edge Computing
por: Zhang, Mingjin, et al.
Publicado: (2024)

SLICE: SLO-Driven Scheduling for LLM Inference on Edge Computing Devices
por: Chow, Will
Publicado: (2025)

Fail-Closed Lowering of Resident KV Claims onto LLM Serving Runtimes
por: Stepanek, Lukas
Publicado: (2026)

RcLLM: Accelerating Generative Recommendation via Beyond-Prefix KV Caching
por: Zhao, Zhan, et al.
Publicado: (2026)

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

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference
por: Jeong, Bodon, et al.
Publicado: (2026)

DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving
por: Strati, Foteini, et al.
Publicado: (2024)

CacheFlow: Efficient LLM Serving with 3D-Parallel KV Cache Restoration
por: Nian, Sean, et al.
Publicado: (2026)

Asynchronous Federated Learning Using Outdated Local Updates Over TDMA Channel
por: Song, Jaeyoung, et al.
Publicado: (2024)

A Hierarchical Sharded Blockchain Balancing Performance and Availability
por: Jo, Yongrae, et al.
Publicado: (2025)

FlashFuser: Expanding the Scale of Kernel Fusion for Compute-Intensive Operators via Inter-Core Connection
por: Huang, Ziyu, et al.
Publicado: (2025)

Performance Models for a Two-tiered Storage System
por: Sasidharan, Aparna, et al.
Publicado: (2025)

Byzantine-Robust Decentralized Coordination of LLM Agents
por: Jo, Yongrae, et al.
Publicado: (2025)

TraCT: Disaggregated LLM Serving with CXL Shared Memory KV Cache at Rack-Scale
por: Yoon, Dongha, et al.
Publicado: (2025)

TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing
por: Bian, Zhuohang, et al.
Publicado: (2026)

FairKV: Balancing Per-Head KV Cache for Fast Multi-GPU Inference
por: Zhao, Bingzhe, et al.
Publicado: (2025)

Resident KV Claims: A Conformance Contract for Future Reuse under Active KV Pressure
por: Stepanek, Lukas
Publicado: (2026)

Action Deviation-Aware Inference for Low-Latency Wireless Robots
por: Park, Jeyoung, et al.
Publicado: (2025)

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

Characterizing Compute-Communication Overlap in GPU-Accelerated Distributed Deep Learning: Performance and Power Implications
por: Lee, Seonho, et al.
Publicado: (2025)

BanaServe: Unified KV Cache and Dynamic Module Migration for Balancing Disaggregated LLM Serving in AI Infrastructure
por: He, Yiyuan, et al.
Publicado: (2025)

Fine-Grained Energy Prediction For Parallellized LLM Inference With PIE-P
por: Dutt, Anurag, et al.
Publicado: (2025)

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

Genomic data processing with GenomeFlow
por: Park, Junseok, et al.
Publicado: (2025)

PackKV: Reducing KV Cache Memory Footprint through LLM-Aware Lossy Compression
por: Jiang, Bo, et al.
Publicado: (2025)

Flash-KMeans: Fast and Memory-Efficient Exact K-Means
por: Yang, Shuo, et al.
Publicado: (2026)

Litmus: Fair Pricing for Serverless Computing
por: Pei, Qi, et al.
Publicado: (2024)

PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference
por: Patel, Ishan, et al.
Publicado: (2026)