Skip to content
Conference Open access

Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization

Jul 2026 · Annual Meeting of the Association for Computational Linguistics · pp. 38450-38476 · 16 citations · ⚡ 1 influential · 185 references
Computer Science

TL;DR

This work systematizes a rapidly evolving area, providing a foundation for understanding and innovating KV cache designs in modern LLM serving infrastructure.

Abstract

Despite the rapid advancements of large language models (LLMs), LLM serving systems remain memory-intensive and costly. The key-value (KV) cache, which stores KV tensors during autoregressive decoding, is crucial for enabling low-latency, high-throughput LLM inference serving. In this survey, we focus on system-aware KV infrastructure for serving LLMs (abbreviated as sKis). We revisit recent work from a system behavior perspective, organizing existing efforts into three dimensions: execution and scheduling (temporal), placement and migration (spatial), and representation and retention (structural). Furthermore, we analyze cross-behavior co-design affinity and behavior-objective links, highlighting future opportunities. Our work systematizes a rapidly evolving area, providing a foundation for understanding and innovating KV cache designs in modern LLM serving infrastructure.

Read PDF

Similar papers

Book Open access Aug 2026

DynamoServe: A Distributed Tiered Memory System for Multi-tenant LLM Serving

The rapid adoption of large language models (LLMs) has increased the need for efficient multi-tenant inference systems that maximize GPU utilization. However, existing frameworks struggle to scale due to the high memory demands of model weights and key-value (KV) caches. We present DynamoServe, a multi-tenant LLM serving framework that addresses these challenges through three key innovations: (1) leveraging stranded GPU memory to offload model weights and KV caches, (2) mitigating resource fragmentation in multi-workload environments, and (3) improving memory locality through coordinated data placement and demand-driven weight migration across GPUs. Together, these techniques enable high-throughput, low-latency inference. Experiments on state-of-the-art models show that DynamoServe significantly improves memory efficiency without sacrificing latency.

Diman Zad Tootaghaj, Khaled Diab, Bob Lantz et al. · 0 citations
Preprint Aug 2026

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching

OasisKV is presented, a memory-centric LLM inference system design that alleviates HBM capacity pressure by decoupling full KV-cache storage from HBM during LLM decoding and observes that future important tokens can be predicted accurately in advance using lookahead tokens drafted by speculative decoding (SD).

Can Xiao, Sukmin Cho, Junbong We et al. · 0 citations
Preprint Jul 2026

InferScale: GPU-Native KV Injection for Personalized LLM Serving

This work presents InferScale, a GPU-native LLM memory system that replaces repeated prompt prefilling with reusable KV state, and encodes each memory fact together with a small window of preceding conversation context while caching only the target fact's KV.

Peter Li, Prashant Pandey · 1 citation
Book Open access Aug 2026

Turbo: Efficiently Serving Long-Context Large Language Models with In-Network Aggregation

This work proposes Turbo, a first-of-its-kind in-network aggregation system that accelerates long-context inference by offloading query broadcast and attention aggregation to switches and introduces a rolling forward scheme that propagates states to enable cross-stage updates.

Ying Wan, Yuchen Xu, Chuwen Zhang et al. · 0 citations
Open access Aug 2026

AdaK: adaptive KV cache budget estimation framework for analyzing long-context large language model inference

Introduction The deployment of LLMs on resource-constrained hardware is hindered by the memory-intensive KV Cache mechanism. Methods We propose AdaK, an adaptive KV cache budget estimation framework with three strategies: entropy-based thresholding, task-aware lookup table, and a lightweight policy network. Results AdaK reveals estimated KV cache reductions of up to 17.9% relative to fixed-k = 2048 baselines across 16 settings on Qwen3-4B, Qwen3-8B, and Mistral-7B. Discussion AdaK's decoupled design enables safe budget estimation as a dynamic ceiling for downstream sparse attention kernels.

Tianjun Shao · 0 citations