Open Models Almanac
Methodsinference & servingKV cache management

single mention · inference & serving

Preallocated static KV cache

Preallocates a static KV cache to keep decode state stable across steps.

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.

Filed under inference & serving › KV cache management