Blog

As part of my job over the past year, I’ve been deploying and evaluating LLMs locally on various hardware setups. Naturally, I became well versed in the open source tools and models available and various hardware options. So I decided to build my own homelab for local inference.

If you’re running LLMs locally, you’ve probably used Ollama or LM Studio. But they are effectively wrappers for llama.cpp. They’re convenient, but they impose limits that get in the way once you start trying to squeeze maximum performance out of your hardware.

Building a Docker image and pushing it to the registry with GitHub Actions is incredibily easy. Since Gitea Actions are designed to be compatible with GitHub Actions, this should be easy, right?

Even if you are not actively looking for a new job, it is a good idea to have an up to date resume. I’m using Overleaf’s GitHub integration and GitHub Actions to build PDF from my LaTeX resume and release it on GitHub

Over the years, this website was running on WordPress, Hugo, a custom React SPA, server-side rendered React, Gatsby, and now I’m back to Hugo.

If you are selfhosting Gitea on a single node Kubernetes cluster and want to enable git through SSH while keeping SSH connection to the cluster, this guide is for you.