面向LLM服务的扁平化KV缓存存储架构
A Flat KV Cache Storage Architecture for LLM Serving
Xin Huang, Teng Ma, Zhuoran Li, Yibo Zhao, Zhaoshi Li, Qianchao Zhu, Wei Yang, Chenxi Wang 等 10 位作者
AI 速读 基于摘要
FlatCake将主机DRAM与NVMe SSD作为统一64位地址空间中的对等介质,按会话连续、层优先顺序直接放置不可变KV块,以缓解分层缓存在生产负载下的失效。
cs.DC · cs.OS
查看原文摘要
KV cache reuse accelerates LLM serving, but existing systems manage host DRAM and NVMe SSD as a tiered hierarchy where DRAM acts as an intermediate cache. Production LLM workloads break both premises of this hierarchy. First, bimodal reuse defeats DRAM temporal filtering, since workloads are dominated either by one-shot blocks with long reuse distances or by multi-gigabyte agentic sessions that exceed DRAM capacity, putting SSD on the critical read path. Second, DRAM staging and eviction-ordered layout bottleneck SSD restoration. Holding host staging buffers for in-flight prefixes causes contention under load that aborts prefetches, while incremental eviction scatters a session's blocks across the SSD and prevents large sequential reads. We present FlatCake, a flat KV storage architecture that exposes host DRAM and NVMe SSD as peer media in a unified 64-bit address space. Exploiting the fact that KV blocks are write-once, immutable, and reused together within a prompt or session, FlatCake places each block directly onto its target medium in session-contiguous, layer-major order at creation time and never migrates it. FlatCake streams coalesced SSD reads directly into a bounded GPU window via GPUDirect Storage and decouples DRAM and SSD request queues to prevent head-of-line blocking. We implement FlatCake in SGLang and compare it against host-staged (Mooncake) and GDS-enabled (Mooncake-GDS) tiered storage, as well as SSD-direct storage (Tutti). Across three production agentic, coding, and conversational traces with DeepSeek-V4-Flash, FlatCake reduces mean TTFT near the baselines' latency knees by $1.40\times$--$2.42\times$ over the fastest baseline. On the agentic Claude Code trace, FlatCake sustains a 91.6% cache hit rate under load (versus 71.1% for all three baselines) and delivers up to $2.16\times$ higher token throughput.