Open Models Almanac
Methodsinference & servinginference quantization

single source · inference & serving

NVFP4 KV-cache quantization

KV-cache storage using NVFP4.

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 NVFP4 KV cache, NVFP4 KV caching.

Filed under inference & serving › inference quantization