Model techniques map
Techniquesinference & servinginference kernel

implementation detail · filed under inference & serving

Separate split-K outputs with deterministic reduction

Writes each split-K part separately and reduces the parts deterministically in a subsequent kernel.

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.

we output each split part separately and perform a deterministic reduction in a subsequent kernel

usedunclearin DeepSeek-V4DeepSeek

Filed alongside

Other methods under inference & serving :: inference kernel.