Cover Image

Leyline: KV Cache Directives for Agentic Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ma, Bole, Eitzinger, Jan, Koestler, Harald
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

Irminsul: MLA-Native Position-Independent Caching for Agentic LLM Serving
by: Ma, Bole, et al.
Published: (2026)

Diagnosing Overhead in Dispatch Operations: Cross-architecture Observatory
by: Ma, Bole, et al.
Published: (2026)

The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures
by: Ma, Bole, et al.
Published: (2026)

Move the Query, Not the Cache: Characterizing Cross-Instance Latent Attention Redistribution Across GPU Fabrics
by: Ma, Bole, et al.
Published: (2026)

ShadowServe: Interference-Free KV Cache Fetching for Distributed Prefix Caching
by: Xiang, Xingyu, et al.
Published: (2025)

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

MatKV: Trading Compute for Flash Storage in LLM Inference
by: Shin, Kun-Woo, et al.
Published: (2025)

Efficient Multi-Adapter LLM Serving via Cross-Model KV-Cache Reuse with Activated LoRA
by: Li, Allison, et al.
Published: (2025)

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

OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
by: Zhou, Zhongzhu, et al.
Published: (2026)

KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference
by: Zhang, Huawei, et al.
Published: (2025)

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

InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management
by: Lee, Wonbeom, et al.
Published: (2024)

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

Compiler-First State Space Duality and Portable $O(1)$ Autoregressive Caching for Inference
by: Santoni, Cosmo
Published: (2026)

Marconi: Prefix Caching for the Era of Hybrid LLMs
by: Pan, Rui, et al.
Published: (2024)

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

FlowKV: A Disaggregated Inference Framework with Low-Latency KV Cache Transfer and Load-Aware Scheduling
by: Li, Weiqing, et al.
Published: (2025)

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

A Survey on Large Language Model Acceleration based on KV Cache Management
by: Li, Haoyang, et al.
Published: (2024)

KVPR: Efficient LLM Inference with I/O-Aware KV Cache Partial Recomputation
by: Jiang, Chaoyi, et al.
Published: (2024)

KV-Runahead: Scalable Causal LLM Inference by Parallel Key-Value Cache Generation
by: Cho, Minsik, et al.
Published: (2024)

ForkKV: Scaling Multi-LoRA Agent Serving via Copy-on-Write Disaggregated KV Cache
by: Wang, Shao, et al.
Published: (2026)

Efficient and Scalable Agentic AI with Heterogeneous Systems
by: Asgar, Zain, et al.
Published: (2025)

InstGenIE: Generative Image Editing Made Efficient with Mask-aware Caching and Scheduling
by: Jiang, Xiaoxiao, et al.
Published: (2025)

Two-Timescale Model Caching and Resource Allocation for Edge-Enabled AI-Generated Content Services
by: Liu, Zhang, et al.
Published: (2024)

Efficient Remote KV Cache Reuse with GPU-native Video Codec
by: Mi, Liang, et al.
Published: (2026)

KVComp: A High-Performance, LLM-Aware, Lossy Compression Framework for KV Cache
by: Jiang, Bo, et al.
Published: (2025)

Hermes: Memory-Efficient Pipeline Inference for Large Models on Edge Devices
by: Han, Xueyuan, et al.
Published: (2024)

ARL-Tangram: Unleash the Resource Efficiency in Agentic Reinforcement Learning
by: Xiao, Bangjun, et al.
Published: (2026)

ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling
by: Yang, Yuchen, et al.
Published: (2026)

Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents
by: Zhang, Qizheng, et al.
Published: (2025)

FSD-Inference: Fully Serverless Distributed Inference with Scalable Cloud Communication
by: Oakley, Joe, et al.
Published: (2024)

PiKV: KV Cache Management System for Mixture of Experts
by: Liu, Dong, et al.
Published: (2025)

RollArt: Scaling Agentic RL Training via Disaggregated Infrastructure
by: Gao, Wei, et al.
Published: (2025)

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

Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey
by: Liu, Sicong, et al.
Published: (2025)

Stochastic Sparse Attention for Memory-Bound Inference
by: Lee, Kyle, et al.
Published: (2026)

Lodestar: An Online-Learning LLM Inference Router
by: Lim, Gangmuk, et al.
Published: (2026)

Symbiosis: Multi-Adapter Inference and Fine-Tuning
by: Gupta, Saransh, et al.
Published: (2025)