← Back to context Comment by yorwba 14 hours ago It's not the same KDA as used in Kimi Linear, though. 2 comments yorwba Reply GaggiX 14 hours ago What's the difference? They are both called Kimi Delta Attention. yorwba 10 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
GaggiX 14 hours ago What's the difference? They are both called Kimi Delta Attention. yorwba 10 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
yorwba 10 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
What's the difference? They are both called Kimi Delta Attention.
The differences are explained in section 2.1.1 of the Kimi K3 technical report: https://arxiv.org/pdf/2607.24653#page=4