Open Models Almanac
Methodsinference & servinginference quantization

single source · inference & serving

Promote expert weights from NVFP4 to FP8

An ablation that raises routed and shared expert weight precision from NVFP4 to FP8 to examine quantization-related behavior.

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 Routed/shared experts NVFP4→ FP8.

Filed under inference & serving › inference quantization