| 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.
WHAT MAKES PROMPT-NOTES SPECIALPROMPT NOTES
Trying to keep up with the tech pace?
PROMPT-NOTES sparks your curiosity with short reads.
Dive deeper using the Prompt Me button.
SHORT READSEND POST TO CHAT WITHPrompt Me
1. Short Read
2. Select Topics
✓
✓
3. Deep Dive with Chat
Chat window
Featured
| 4 minutesMIN
LLM Inference under the hood - Part 2: Prefill, Decode, and Prompt Caching
How to understand the second part of the LLM inference pipeline, covering prefill, decode, and prompt caching.
| 4 minutesMIN
Goodbye Vector DBs - building a Local LLM Wiki with OKF and Hermes
How I migrated my macOS agent pipeline from heavy semantic search to a local, compounding LLM Wiki using Google's Open Knowledge Format.
| 4 minutesMIN
Re-imagine your org with AI
Implementing self-improving AI loops.
| 4 minutesMIN
Agentic OS - the tool to rule them all
How to manage too many AI tools