22,580: GPT-2 to Kimi K3, explained 0 ▲ Bogdan Buduroiu 84 days ago · Tech · hide · Fediverse post MLA, KDA, MoE, NoPE all attack either bytes transferred or bytes resident. MLA shrinks KV per token, KDA replaces a O(n)O(n)O(n) cache with an O(1)O(1)O(1) state. Commenting on Bubbles has been removed. Why? If you want to talk about this post, write to the author, use the comments on their blog if it has them, or reply with a "RE:" post on your own blog. Suggestions? feedback@bubbles.town