Comment by yorwba 2 days ago It's not the same KDA as used in Kimi Linear, though. 2 comments yorwba Reply GaggiX 2 days ago What's the difference? They are both called Kimi Delta Attention. yorwba 1 day 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 2 days ago What's the difference? They are both called Kimi Delta Attention. yorwba 1 day 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 1 day 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