Melchi

How attention architectures evolved to keep KV cache from eating your GPU, and what that means if you self-host.

TL;DR — Compute is usually the largest line item on your cloud bill.

I’ve been doing some interesting work with the team at MFlow writing HTTP clients that consume financial data, and it’s been eye-opening to see how different API platforms choose to protect their resources.

TL;DR — A standard Linux container is an isolation boundary, not a security boundary.