specific method · filed under model architecture
Gated DeltaNet and Full Attention
Alternates Gated DeltaNet linear-attention layers with full-attention layers.
Also called Hybrid Attention Architecture.
- 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.
The model alternates between Gated DeltaNet layers (linear attention) and full attention layers in roughly a 3:1 ratio.
coremodel architecturein Qwen3.5-397B-A17BAlibaba
Filed alongside
Other methods under model architecture :: token mixer :: hybrid layer stacking.
Hybrid AttentionMamba-2, Mixture-of-Experts, and Selective Attention HybridHybrid Mamba-TransformerHybrid Mamba-AttentionGated DeltaNet and Gated AttentionHybrid Mamba-Transformer Mixture-of-Experts Layer LayoutDense Attention FallbackGated Attention and Sliding-Window Attention ConfigurationGated DeltaNet and Qwen Sparse Attentionhybrid Gated DeltaNet + sparse MoE architectureHybrid sparse mixture-of-experts Transformer architectureSearch-Based Sliding-Window Attention Pattern