Model techniques map
Techniquesinference & servinginference kernel

specific method · filed under inference & serving

Per-SM accumulation buffers with deterministic global summation

Uses separate accumulation buffers per SM and then sums them deterministically across buffers.

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 allocate separate accumulation buffers for each SM, followed by a global deterministic summation across all buffers.

usedunclearin DeepSeek-V4DeepSeek

Filed alongside

Other methods under inference & serving :: inference kernel.