karl livesey blog

Code, Systems, and Side Quests

Personal notes on software, experiments, and everyday life from me.

transmission board

Latest Posts

Mar 29, 2026 · 22 min read

Why TurboQuant Actually Matters

TurboQuant is interesting because it attacks KV cache pressure and inference memory cost, which are often the real bottlenecks once a model has to serve long contexts in production.