Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

Backbone-coupled MTP KV-cache precision

An MTP configuration in which KV-cache precision follows the backbone rather than being selected independently.

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

Filed under inference & serving › inference quantization