Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

Weight-only post-training quantization for parallel drafters

Weight-only post-training quantization applied to parallel-drafter modules to improve drafting efficiency.

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 weight-only PTQ.

Filed under inference & serving › inference quantization