Low-Rank Attention: Scaling Transformers Without the Quadratic Cost (lightcapai.medium.com)

1 points by WASDAai 1y ago ↗ HN

0 comments

[ 4.2 ms ] story [ 14.1 ms ] thread

No comments yet.

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

Source · Live DB stats