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