Native Sparse Attention (NSA)
arxiv.org ↗(2025) - trainable sparse attention combining coarse-grained compression with fine-grained selection; large speedups at 64K with no NLP-benchmark degradation.
AboutVisit arxiv.org ↗
(2025) - trainable sparse attention combining coarse-grained compression with fine-grained selection; large speedups at 64K with no NLP-benchmark degradation.
This entry links to an external website rather than a GitHub repository, so there's no README to display here.