specific method · filed under model architecture
Anticipatory Routing
Computes and caches routing indices ahead of their use to decouple routing updates from backbone updates.
- sources
- 2
- models
- 2
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
optional 1used 1
Documented in
Evidence
2 spans quoted from the sources, strongest treatment first.
Anticipatory Routing (computing routing indices one step ahead to decouple backbone and routing updates)
usedtraining objectivein DeepSeek-V4DeepSeek
we "anticipatorily" compute and cache the routing indices to be used later at step
optionaloptimizationin DeepSeek-V4DeepSeek
Filed alongside
Other methods under model architecture :: channel mixer :: mixture of experts :: expert routing.
Top-8 expert routingToken-level expert routingTop-4 expert routingDP-aware routingFixed Top-k routing with frozen biasHash 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