Cover Image

Shared Disk KV Cache Management for Efficient Multi-Instance Inference in RAG-Powered LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lee, Hyungwoo, Kim, Kihyun, Kim, Jinwoo, So, Jungmin, Cha, Myung-Hoon, Kim, Hong-Yeon, Kim, James J., Kim, Youngjae
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Cost-Efficient LLM Serving in the Cloud: VM Selection with KV Cache Offloading
by: Kim, Kihyun, et al.
Published: (2025)

DeepVM: Integrating Spot and On-Demand VMs for Cost-Efficient Deep Learning Clusters in the Cloud
by: Kim, Yoochan, et al.
Published: (2024)

Leveraging KV Similarity for Online Structured Pruning in LLMs
by: Lee, Jungmin, et al.
Published: (2025)

Investigating the Integrated Digital Interventions Delivered by a Therapeutic Companion Agent for Young Adults with Symptoms of Depression: A Proof-of-Concept Study
by: Yoo, Youngjae, et al.
Published: (2025)

LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents
by: Jeon, Hyesung, et al.
Published: (2026)

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

Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization
by: Kim, Minsu, et al.
Published: (2025)

Rigidity of smooth finite-time blow-up for equivariant self-dual Chern-Simons-Schrödinger equation
by: Kim, Kihyun
Published: (2022)

Electrochemical characteristics of Si/Mo multilayer anode for Li ion batteries
by: Myung-Hoon Kim
Published: (2007)

EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environments
by: Kim, Minsoo, et al.
Published: (2025)

Metal‐Free Submicron‐Hollow‐Fiber Conjugated Polymer Sponges for Efficient Pollutant Removal and Thermal Insulation
by: Songah Jeong, et al.
Published: (2026)

MoSKA: Mixture of Shared KV Attention for Efficient Long-Sequence LLM Inference
by: Rhee, Myunghyun, et al.
Published: (2025)

Reformulating KV Cache Eviction Problem for Long-Context LLM Inference
by: Mai, Tho, et al.
Published: (2026)

Multidimensional Analysis of Visitor Interaction With Museum Apps: Designing for Enhanced Museum Experiences
by: Jihyun Kim, et al.
Published: (2025)

LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation
by: Ahn, Jinwoo, et al.
Published: (2026)

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

Learning Where It Matters: Geometric Anchoring for Robust Preference Alignment
by: Cho, Youngjae, et al.
Published: (2026)

FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration
by: Jo, Dongwon, et al.
Published: (2025)

FibQuant: Universal Vector Quantization for Random-Access KV-Cache Compression
by: Lee, Namyoon, et al.
Published: (2026)

Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification
by: Yun, Jungmin, et al.
Published: (2024)

Scalable Processing-Near-Memory for 1M-Token LLM Inference: CXL-Enabled KV-Cache Management Beyond GPU Limits
by: Kim, Dowon, et al.
Published: (2025)

BERT-APC: A Reference-free Framework for Automatic Pitch Correction via Musical Context Inference
by: Kim, Sungjae, et al.
Published: (2025)

Simulation-Free Training of Neural ODEs on Paired Data
by: Kim, Semin, et al.
Published: (2024)

Light-Wave Engineering for Selective Polarization of a Single $\mathbf{Q}$ Valley in Transition Metal Dichalcogenides
by: Kim, Youngjae
Published: (2025)

Pseudospins revealed through the giant dynamical Franz-Keldysh effect in massless Dirac materials
by: Kim, Youngjae
Published: (2024)

Common Ownership and Auditor Sharing
by: Young Hoon Kim
Published: (2026)

Benign-to-Toxic Jailbreaking: Inducing Harmful Responses from Harmless Prompts
by: Kim, Hee-Seon, et al.
Published: (2025)

Making Sense of Korean Sentences: A Comprehensive Evaluation of LLMs through KoSEnd Dataset
by: Yu, Seunguk, et al.
Published: (2025)

KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction
by: Kim, Jang-Hyun, et al.
Published: (2025)

Construction of smooth chiral finite-time blow-up solutions to Calogero--Moser derivative nonlinear Schrödinger equation
by: Kim, Kihyun, et al.
Published: (2024)

Self-Abstraction Learning for Effective and Stable Training of Deep Neural Networks
by: Cho, Wonyong, et al.
Published: (2026)

Polynomial Context-Truncation Sensitivity in Autoregressive Language Models: Sequential Wyner-Ziv Bounds for KV Cache Compression
by: Kim, Munsik
Published: (2026)

Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment
by: Kim, Dongyoung, et al.
Published: (2024)

Beyond KV Caching: Shared Attention for Efficient LLMs
by: Liao, Bingli, et al.
Published: (2024)

On classification of global dynamics for energy-critical equivariant harmonic map heat flows and radial nonlinear heat equation
by: Kim, Kihyun, et al.
Published: (2024)

Rigidity results in multi-bubble dynamics for non-radial energy-critical heat equation
by: Kim, Kihyun, et al.
Published: (2026)

Construction of infinite time bubble tower solutions to critical wave maps equation
by: Hwang, Seunghwan, et al.
Published: (2026)

On classification of global dynamics for energy‐critical equivariant harmonic map heat flows and radial nonlinear heat equation
by: Kihyun Kim, et al.
Published: (2025)

Program Synthesis is $Σ_3^0$-Complete
by: Kim, Jinwoo
Published: (2024)

A Review of Image Retrieval Techniques: Data Augmentation and Adversarial Learning Approaches
by: Jinwoo, Kim
Published: (2024)