AI & machine learning2024 · shared on Hacker News
New attention mechanisms that outperform standard multi-head attention
Explore New attention mechanisms that outperform standard multi-head attention, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Ysnats ·
New attention mechanisms that outperform standard multi-head attention
233 points49 comments
Yskidrow ·
How to Write a Fast Matrix Multiplication from Scratch with Tensor Cores (2024)
147 points17 comments
Ytosh ·
You Need to Pay Better Attention
5 points0 comments