DeepSeek 为什么把缓存涨了 11 倍？长上下文需求暴涨，得交点「存储税」了
Ranking
Overall
78
Content
90
Popularity
N/A
No observed public metrics; popularity remains neutral/archived.
Merged summary
TL;DR - DeepSeek reportedly raised cache-hit API pricing by up to 11× as surging long-context workloads shifted inference bottlenecks from computation toward KV-cache storage, bandwidth, and data movement.
- DeepSeek compresses KV caches using CSA/HCA attention and tiers them across GPU memory, CPU memory, and NVMe storage.
- Heavy concurrency can cause cache thrashing, repeatedly evicting and reloading large states while GPUs stall on I/O.
- The price increase effectively charges a “storage tax” for growing persistence, scheduling, and transfer costs.
- Developers can reduce costs by keeping reusable prompt prefixes byte-for-byte stable and placing dynamic content later.
Sources (1)
DeepSeek 为什么把缓存涨了 11 倍？长上下文需求暴涨，得交点「存储税」了
Public signals
N/A
TL;DR - DeepSeek reportedly raised cache-hit API pricing by up to 11× as surging long-context workloads shifted inference bottlenecks from computation toward KV-cache storage, bandwidth, and data movement.
- DeepSeek compresses KV caches using CSA/HCA attention and tiers them across GPU memory, CPU memory, and NVMe storage.
- Heavy concurrency can cause cache thrashing, repeatedly evicting and reloading large states while GPUs stall on I/O.
- The price increase effectively charges a “storage tax” for growing persistence, scheduling, and transfer costs.
- Developers can reduce costs by keeping reusable prompt prefixes byte-for-byte stable and placing dynamic content later.