kv cache

9 feeds in the directory cover this.

These blogs cover what I've learned so far, and I'll continue to add more as I explore new topics.

Shreyansh's personal website.

Notes on making LLMs run well on-device — MLX, Apple Silicon, tokenizers, and the seams where models meet real hardware.

Engineering's view on local frontier AI — what actually runs on hardware you control.

Moncef Abboud blog and posts.

Making, Breaking, Learning, Fixing.