Hacker News new | ask | show | jobs
by yorwba 18 hours ago
It's not the same KDA as used in Kimi Linear, though.
1 comments
GaggiX 18 hours ago
What's the difference? They are both called Kimi Delta Attention.
link
yorwba 15 hours ago
The differences are explained in section 2.1.1 of the Kimi K3 technical report: https://arxiv.org/pdf/2607.24653#page=4
link