Open Models Almanac
Methodsinference & servingKV cache management

single mention · inference & serving

KV cache sharing

Shares KV cache to reduce the global cache footprint; the evidence does not specify the sharing scheme.

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