| 4 minutesMIN
LLM Inference under the hood - Part 1: From Prompt to KV Cache
How to understand the first part of the LLM inference pipeline, from tokenization to KV cache.
All Articles
| 4 minutesMINLLM Inference under the hood - Part 2: Prefill, Decode, and Prompt CachingHow to understand the second part of the LLM inference pipeline, covering prefill, decode, and prompt caching.
| 4 minutesMINGoodbye Vector DBs - building a Local LLM Wiki with OKF and HermesHow I migrated my macOS agent pipeline from heavy semantic search to a local, compounding LLM Wiki using Google's Open Knowledge Format.
| 4 minutesMINRe-imagine your org with AIImplementing self-improving AI loops.
| 4 minutesMINAgentic OS - the tool to rule them allHow to manage too many AI tools
| 3 minutesMINArchitecture Integrity - across your reposLeveraging multi-agent swarm architectures to handle massive software repositories.
| 5 minutesMINRun AI Locally - it works!Running AI locally: options, pitfalls, and my experience