Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

Two-pass FP4 weight quantization with residual correction

A second FP4 channel corrects residual error left by the first-pass quantization.

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 two-pass FP4 weights.

Filed under inference & serving › inference quantization