KV Sharing, MHC, and Compressed Attention(magazine.sebastianraschka.com)
magazine.sebastianraschka.com
KV Sharing, MHC, and Compressed Attention
https://magazine.sebastianraschka.com/p/recent-developments-in-llm-architectures
3 comments
Has anyone seen a similar deep dive but that looks a little bit more closely at the infrastructure building blocks that power each of the components. I mean something a bit more physically grounded like how much compute would go to each portion to serve a Frontier Model?
cool stuff. my comp sci major feels almost completely redundant in this new vibecoding era and i feel like the only way to stay relevant as a programmer is to learn all these compute primitives and become an LLM systems guy.
Did you only learn to type some code during your comp sci major?