MOBA: Mixture of Block Attention for Long-Context LLMs (arxiv.org)

1 points by ur-whale 3d ago ↗ HN

0 comments

[ 0.16 ms ] story [ 8.6 ms ] thread

No comments yet.

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

Source · Live DB stats