Open Models Almanac
Methodsinference & servingcontext management

single mention · inference & serving

Memory compression

Summarizes active history when context use exceeds a threshold, archives the full history to retrievable memory, and replaces active context with the summary.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See context management for the methods filed beside it.

Also called memory compression (context consolidation).

Filed under inference & serving › context management