Kimi Linear: An Expressive, Efficient Attention Architecture (arxiviq.substack.com)

1 points by che_shr_cat 12mo ago ↗ HN

0 comments

[ 4.8 ms ] story [ 11.3 ms ] thread

No comments yet.

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

Source · Live DB stats