← 研踪 PaperTrailarXiv:2611.10178 · v1
The Storage View Of KV Cache: Characterizing Cache Behavior Across LLM Workloads
首次提交 2026-11-07 03:58
版本更新 2026-11-07 03:58
雷达观测 2026-11-10 10:11
摘要
Modern LLM serving increasingly extends KV caches beyond GPU memory into host DRAM, SSDs, and remote storage, yet these stores remain largely governed by workload-agnostic policies such as LRU and fixed TTLs. We ask what execution context is needed by storage to make retention, reclamation, and placement decisions across heterogeneous workloads. We characterize KV-cache reuse, lifetime, and footprint at block granularity across 11 production and public traces spanning chat, API serving, RAG, coding agents, tool-using agents, and multi-lineage workflows. We examine reuse sources, recurrence timing and frequency, useful lifetimes, and storage consumption. Across workloads, KV state takes two recurring forms. Single-session state is reused within one execution: its footprint grows as sessions deepen and accumulates across concurrent sessions; it can remain useful through long idle periods but loses value at session completion. Multi-session state recurs across sessions of the same workload, outlives individual sessions, and spans hot prefixes and a large infrequent tail. While prior systems often exploit application-, agent-, or workflow-specific knowledge, our results suggest that three generic signals (a workload identifier, a session identifier, and session completion) expose much of the structure needed for KV-storage management. Trace-driven comparisons show that workload-specific recurrence estimates retain up to 22% more within-session hits and reduce dead state by up to 40%; a session completion signal eliminates the fundamental idle-time reclamation tradeoff for single-session state; and session-aware reuse classification identifies shared state 4-700x more selectively than request-level access counts. These results motivate a small cross-layer interface for workload-aware KV storage without application-specific semantics.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-07 03:58 · 最新观测版本
The Storage View Of KV Cache: Characterizing Cache Behavior Across LLM Workloads
Modern LLM serving increasingly extends KV caches beyond GPU memory into host DRAM, SSDs, and remote storage, yet these stores remain largely governed by workload-agnostic policies such as LRU and fixed TTLs. We ask what execution context is needed by storage to make retention, reclamation, and placement decisions across heterogeneous workloads. We characterize KV-cache reuse, lifetime, and footprint at block granularity across 11 production and public traces spanning chat, API serving, RAG, coding agents, tool-using agents, and multi-lineage workflows. We examine reuse sources, recurrence timing and frequency, useful lifetimes, and storage consumption. Across workloads, KV state takes two recurring forms. Single-session state is reused within one execution: its footprint grows as sessions deepen and accumulates across concurrent sessions; it can remain useful through long idle periods but loses value at session completion. Multi-session state recurs across sessions of the same workload, outlives individual sessions, and spans hot prefixes and a large infrequent tail. While prior systems often exploit application-, agent-, or workflow-specific knowledge, our results suggest that three generic signals (a workload identifier, a session identifier, and session completion) expose much of the structure needed for KV-storage management. Trace-driven comparisons show that workload-specific recurrence estimates retain up to 22% more within-session hits and reduce dead state by up to 40%; a session completion signal eliminates the fundamental idle-time reclamation tradeoff for single-session state; and session-aware reuse classification identifies shared state 4-700x more selectively than request-level access counts. These results motivate a small cross-layer interface for workload-aware KV storage without application-specific semantics.
查看此版本解读 →查看此版本原文 ↗