specific method · filed under model architecture
DP-aware routing
Preserves KV-cache locality under data parallelism during large-scale MoE inference.
Also called DP-aware routing mechanism.
- source
- 1
- model
- 1
- 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 propose a DP-aware routing mechanism to preserve KV cache locality under Data Parallelism (DP) for large-scale MoE inference
usedinference servingin GLM-5Z.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 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