Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention (arxiv.org)

1 points by FrontiersMind 6d ago ↗ HN

0 comments

[ 3.5 ms ] story [ 13.6 ms ] thread

No comments yet.

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

Source · Live DB stats