general family · filed under model architecture
Gated DeltaNet–sparse MoE hybrid
An architecture pairing Gated Delta Networks with sparse Mixture-of-Experts; the evidence does not specify a distinct internal mechanism beyond that combination.
- sources
- 2
- model
- 1
- lab adopt it
- 1
- strongest
- core
How sources treat it
One count per evidence span, weakest treatment to strongest.
core 2
Documented in
Evidence
2 spans quoted from the sources, strongest treatment first.
Gated Delta Networks combined with sparse Mixture-of-Experts deliver high-throughput inference with minimal latency and cost overhead.
coremodel architecturein Qwen3.5-122B-A10BQwen
Gated Delta Networks combined with sparse Mixture-of-Experts deliver high-throughput inference with minimal latency and cost overhead.
coremodel architecturein Qwen3.5-35B-A3BQwen
Filed alongside
Other methods under model architecture :: token mixer :: linear attention & state space :: gated delta network.
Gated DeltaNetKimi Delta AttentionKDAGated DeltaNet with bounded sigmoid output gateGated DeltaNet with reduced KV-head configurationHybrid linear attentionKimi Delta Attention and Attention Residuals architectureKimi Delta Attention with input-dependent full-rank output gateKimi Delta Attention with lower-bounded log-decaySimpleGDN