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