single mention · inference & serving
KV-cache offloading
Offloads KV cache; the evidence does not specify the destination or policy.
The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See KV cache management for the methods filed beside it.
Also called KV cache offload.
Filed under inference & serving › KV cache management
Explainer · 02 · 35 minServing a large reasoning model at low costA token gets cheaper as more requests share each forward pass, until the latency promise or the KV-cache budget stops the batch from growingExplainer · I4 · 31 minDisaggregation and the KV-cache system: scheduling, prefix reuse and tiered memoryReading a cached prefix back from another tier usually costs far less than recomputing it; the price is in keeping it: memory held for hours, a route back to it, and for hybrid models a saved state at the right boundary