Notes from Efficiently Serving LLMs
Course: Efficiently Serving LLMs Platform: DeepLearning.io Deep Learning Text Generation Input text is tokenized into numbers (called…
2026, Sep 26 — 2 minute readCourse: Efficiently Serving LLMs Platform: DeepLearning.io Deep Learning Text Generation Input text is tokenized into numbers (called…
2026, Sep 26 — 2 minute readAgentic Memory Evolution 1. Mem0 Mem0 uses a dedicated middleware layer to manage memory before and after an LLM call. The memory layer…
2026, Sep 20 — 4 minute readThe book starts off with the promise to be contradict the traditional approach to goal setting and higher purpose in life. But, what I found…
2026, Jun 27 — 1 minute readI built a small system to generate a daily blog digest using a local LLM and Notion. Here’s the technical walkthrough—kept simple and…
2026, Apr 30 — 2 minute readSMB Works… but My Container Won’t Start I hit a confusing problem. I could connect to an SMB share. Windows said everything was fine. But my…
2026, Feb 28 — 3 minute readI finished listening to the audiobook today. I imagine I would have had more highlights and notes if I had read it on Kindle instead. The…
2026, Jan 05 — 3 minute readKubernetes Jobs are great for one-off workloads — running tests, data processing, or batch scripts. But they come with a catch: as soon as…
2025, Oct 07 — 3 minute readI recently ran into a situation where I couldn’t use the usual magic from the library to authenticate my .NET app to Azure. I had to…
2025, Oct 02 — 3 minute readI recently finished Start with Why by Simon Sinek, and two ideas stayed with me long after I closed the book. The first is his “Golden…
2025, Sep 28 — 1 minute readHave you ever had two containers in the same Pod, but one absolutely needed to be running before the other could start? That was my…
2025, Sep 26 — 3 minute read