On 10x Better Scalability: KV Stores Scale Up KV Cache

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Weiping, Jiarui, Ye, Mengke, He, Liu, Junfeng, Luo, Siqiang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914170727825408
author Yu, Weiping
Jiarui, Ye
Mengke, He
Liu, Junfeng
Luo, Siqiang
author_facet Yu, Weiping
Jiarui, Ye
Mengke, He
Liu, Junfeng
Luo, Siqiang
contents Large language models (LLMs) rely on Key-Value (KV) cache to reduce time-to-first-token (TTFT) latency, but existing disk-based KV cache systems using file-per-object layouts suffer from severe scalability bottlenecks due to file system metadata overhead, I/O inefficiency, and poor spatial locality. This paper presents SGLANG-LSM, a database-inspired system that leverages Log-Structured Merge-tree (LSM-tree) architectures for scalable KV cache management. SGLANG-LSM implements a layered system design with three coordinated components: (1) a prefix-preserving storage engine that maintains token sequence locality while efficiently storing large KV cache tensors through key-value separation, (2) an adaptive controller that dynamically optimizes LSM-tree configurations based on shifting workload characteristics, and (3) runtime services including batch operations and automatic resource management for production deployment. Evaluation on large-scale dynamic workloads demonstrates that SGLANG-LSM significantly improves cache hits by up to 143% and reduces TTFT by up to 24% compared to state-of-the-art systems, representing the first systematic application of database storage architectures to large-scale LLM cache management.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16138
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On 10x Better Scalability: KV Stores Scale Up KV Cache
Yu, Weiping
Jiarui, Ye
Mengke, He
Liu, Junfeng
Luo, Siqiang
Databases
Large language models (LLMs) rely on Key-Value (KV) cache to reduce time-to-first-token (TTFT) latency, but existing disk-based KV cache systems using file-per-object layouts suffer from severe scalability bottlenecks due to file system metadata overhead, I/O inefficiency, and poor spatial locality. This paper presents SGLANG-LSM, a database-inspired system that leverages Log-Structured Merge-tree (LSM-tree) architectures for scalable KV cache management. SGLANG-LSM implements a layered system design with three coordinated components: (1) a prefix-preserving storage engine that maintains token sequence locality while efficiently storing large KV cache tensors through key-value separation, (2) an adaptive controller that dynamically optimizes LSM-tree configurations based on shifting workload characteristics, and (3) runtime services including batch operations and automatic resource management for production deployment. Evaluation on large-scale dynamic workloads demonstrates that SGLANG-LSM significantly improves cache hits by up to 143% and reduces TTFT by up to 24% compared to state-of-the-art systems, representing the first systematic application of database storage architectures to large-scale LLM cache management.
title On 10x Better Scalability: KV Stores Scale Up KV Cache
topic Databases
url https://arxiv.org/abs/2511.16138