# SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning

> Research article (2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2021) · cited 364× · AI/ML

**Wikidata**: [openalex:W3159727696](https://www.wikidata.org/wiki/openalex:W3159727696)  
**Source**: https://4ort.xyz/entity/spatten-efficient-sparse-attention-architecture-with-cascade-token-and-head-pruning