Model techniques map
Techniquessoftware implementationkernel & quantization library

specific method · filed under software implementation

flash-moba

A named sparse-attention method; the evidence provides no further mechanism details.

source
1
model
1
labs adopt it
0
strongest
evaluated

How sources treat it

One count per evidence span, weakest treatment to strongest.

evaluated 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

more than 4× faster than the open-source Flash-Sparse-Attention and flash-moba

evaluatedevaluation onlyin MiniMax-M3MiniMax

Filed alongside

Other methods under software implementation :: kernel & quantization library.