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.
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
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
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.
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.· Proceedings of the ACM SIGCO...· 0 citations
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· Frontiers in Artificial Inte...· 0 citations