Model techniques map
Techniquesinference & servinginference kernel

specific method · filed under inference & serving

Token-order preprocessing and cross-rank buffer isolation for deterministic MoE backward

Combines within-rank token-order preprocessing with buffer isolation across ranks.

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 design a token order pre-processing mechanism within each single rank, combined with buffer isolation across multiple ranks.

usedunclearin DeepSeek-V4DeepSeek

Filed alongside

Other methods under inference & serving :: inference kernel.