Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

Block-scaled NVFP4 KV-cache quantization

NVFP4 KV-cache storage using E2M1 values and an E4M3 scale for each 16-element block.

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.

Filed under inference & serving › inference quantization