Model techniques map
Techniquesmodel architecturechannel mixermixture of expertsexpert routing

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.