Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

Rotation-based quantization mitigation

Applying rotation to mitigate an activation-related effect in the Mamba output-projection setting.

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 rotation.

Filed under inference & serving › inference quantization