How to use and choose vLLM: For those who are fine with Ollama, and those who will prepare a GPU to install it

When you are looking for tools to run AI locally, this name almost always comes up after Ollama.vLLM."It's supposed to be ...

How to use Jev: Where to integrate non-generative decision models in production

There are three tasks I stopped doing after trying Jev.Adding "Please output only JSON" to the end of prompts. Writing retry ...
Good Men Project

LLM Proxy: What It Is and Why Production Teams Use One

As soon as AI stops being an experiment and starts being part of your product, a new need appears: a single place to see, control, and secure every model call your application makes. Scattered API ...