Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

Flex_AWQ_SSZ

A named AWQ-related method used for scaling calibration; the evidence does not further establish its mechanism.

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