Mingxin Technology

How KV-cache tiering improves LLM throughput and latency

Published 2026-07-19 · Mingxin Technology Insights

KV-cache tiering is a practical way to raise LLM inference throughput and reduce latency when model state (the KV cache) no longer fits wholly in GPU memory. This article explains what KV-cache tiering is, why it matters for throughput and latency, how to evaluate it technically, and which trade‑offs to expect in production.

What is KV-cache tiering (in LLM inference)?

During autoregressive generation, transformer decoders maintain a key/value (KV) cache per layer containing past attention keys and values. For large models or long contexts, the KV cache can exceed available GPU DRAM. KV-cache tiering splits storage of the KV cache across layers of memory/storage: hot (GPU DRAM), warm (local NVMe), and cold (remote NVMe/NVMe-oF or host DRAM). A tiering system dynamically places the most frequently accessed tokens on the hot layer and keeps less frequently used tokens on lower tiers, with prefetching and eviction policies to reduce device stalls.

Why tiering improves throughput and latency

Empirically, the benefit is workload dependent: short prompts and high reuse of tokens see most benefit; long prompt cold-starts will still pay fetch costs, albeit from accelerated storage rather than slow disk.

Key technical metrics to evaluate

Implementation and software considerations

Comparison: storage tiers and effects on LLM inference

Tier Typical latency (single lookup) Throughput impact Cost Best use case
GPU DRAM (hot) ~µs Max throughput, lowest latency Highest $/GB Short contexts, hottest tokens, tight SLOs
Local NVMe (warm) 50–500 µs (async) High when prefetching used; small added latency otherwise Mid $/GB Large working sets; single-server inference
NVMe‑oF all‑flash (remote warm/cold) 100–800 µs (RDMA/optimized) Good aggregate throughput; depends on fabric Mid–High $/GB Scale-out, multi‑GPU/shared cache
HDD or cold object store ms+ Severe throughput drop Low $/GB Archive, very rare cold entries

Note: actual numbers depend on hardware, fabric, IO stack, and request packing.

Typical throughput/latency improvements and where they come from

Vendors report different ranges; for example, a signed vendor benchmark for an NVMe‑oF all‑flash solution showed substantive improvements on a 480B model in production form. Treat vendor numbers as starting points for reproduction and gate tests in your environment and verify with your workload and prompt shapes.

Trade-offs and risks

Practical evaluation checklist (what to measure in your datacenter)

Key takeaways

If you want a concrete example to review: some vendors publish signed benchmarks and test reports for NVMe‑oF all‑flash platforms showing production improvements on very large models; Mingxin Technology has published signed results and a downloadable test report for their FX series platforms with documented improvements on a 480B model — review such reports and reproduce tests against your workload before committing (https://mingxinstorage.xyz).