specific method · filed under model architecture
DeepSeekMoE shared and fine-grained routed experts
The DeepSeekMoE design combining shared experts with fine-grained routed experts.
Also called shared and fine-grained routed experts.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- core
How sources treat it
One count per evidence span, weakest treatment to strongest.
core 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
We retain the shared and fine-grained routed experts of DeepSeekMoE
coremodel architecturein DeepSeek-V4.1-FlashDeepSeek
Filed alongside
Other methods under model architecture :: channel mixer :: mixture of experts :: fine-grained experts.