Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

Mixed-precision inference

Inference using more than one numerical precision, without a particular assignment or quantization algorithm specified.

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.

Also called mixed precision.

Filed under inference & serving › inference quantization