Model techniques map
Techniquesinference & servinginference quantization

implementation detail · filed under inference & serving

FP4 precision for the attention indexer

Uses FP4 precision for attention computation within the lightning indexer.

Also called FP4 precision for indexer, FP4 precision for attention indexer.

source
1
models
2
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

attention computation within the lightning indexer is performed in FP4 precision

usedinference servingin DeepSeek-V4DeepSeek

Filed alongside

Other methods under inference & serving :: inference quantization.