Model techniques map
Techniquesmodel architecturechannel mixermixture of expertsexpert routing

implementation detail · filed under model architecture

Top-4 expert routing

Selects the four highest-scoring experts for each token.

Also called top-4 expert selection, top-4 routed expert selection.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 2

Documented in

Evidence

2 spans quoted from the sources, strongest treatment first.

Each MoE layer uses 128 routed experts, 1 shared expert, and top-4 routed expert selection.

usedmodel architecturein MiniMax-M3MiniMax

top-4 expert routing

usedmodel architecturein MiniMax Sparse AttentionMiniMax

Filed alongside

Other methods under model architecture :: channel mixer :: mixture of experts :: expert routing.