DashAttention: Differentiable and Adaptable Sparse Hierarchical Attention (arxiv.org)

9 points by cmogni1 1mo ago ↗ HN

0 comments

[ 2.7 ms ] story [ 15.1 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats