Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

SpinQuant R1 rotation preprocessing

Rotation preprocessing used to improve FP8 weight-quantization quality without runtime overhead.

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 SpinQuant R1 rotation.

Filed under inference & serving › inference quantization