single mention · inference & serving
FP4 attention-indexer precision
Attention computation within the lightning indexer is performed in FP4 precision.
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 FP4 precision for indexer, FP4 precision for attention indexer.
Filed under inference & serving › inference quantization