implementation detail · filed under model architecture
Fixed Top-k routing with frozen bias
Uses fixed Top-k selection with a frozen bias at deployment, without quantile balancing.
Also called fixed Top- k selection with a frozen bias.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- default
How sources treat it
One count per evidence span, weakest treatment to strongest.
default 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
at deployment, routing is a fixed Top- k selection with a frozen bias, and no quantile
defaultinference servingin Kimi K3Moonshot AI
Filed alongside
Other methods under model architecture :: channel mixer :: mixture of experts :: expert routing.
Top-8 expert routingToken-level expert routingAnticipatory RoutingTop-4 expert routingDP-aware routingHash routingKeep RoutingLatent-space routingLoss-spike-triggered Anticipatory RoutingRouted expertsToken-choice routingToken-choice routing with softplus gatingTop-6 expert routingTop-k expert routing with softmax over selected experts