Open Models Almanac
Methodsinference & servingKV cache management

single mention · inference & serving

Block-based KV cache

Splits stored KV context into blocks.

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 block-based key-value cache.

Filed under inference & serving › KV cache management