Public KG record
sparse attention
Recorded overview
Used in Chinese open frontier models to reduce computational complexity.
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Evidence coverage
The KG currently records 6 known information dimensions and has 13 undocumented dimensions, linked to 3 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- DeepSeek Sparse Attention — is a
- GLM-5.3-Flash — has feature
- MiniMax M3.1 Flash — uses
- Mistral Large 4 — uses