What Serving an AI Model Actually Means (and Why vLLM Exists)
Serving an AI model means turning a file of weights into an API that answers questions. That's the whole job of an inference engineer, and this guide takes you from zero to your ow…
GDEKevin Davila
Software Engineer · Google Developer Expert
Software engineer with experience shipping solid products that solve real problems: mobile apps, bots and web platforms on architectures that hold.
Now going deep into AI on the road to becoming an Inference Engineer. I share the process: what I broke, what I measured and what I learned.
> Technical skill inventory:
[ Scrolls & chronicles ]Migration from Codea Bien
Serving an AI model means turning a file of weights into an API that answers questions. That's the whole job of an inference engineer, and this guide takes you from zero to your ow…
Before renting a single GPU, let's run a model on your own machine. Free, no account, 10 minutes. The goal isn't production: it's understanding the full request-to-tokens cycle, wh…
It's time for real hardware. We'll rent a 48 GB GPU, run our first commands, and shut it down without leaving money behind. Total chapter budget: ~$3. You buy nothing.
[ Guides & manuals ]Step-by-step series
From zero to your own vLLM server on a rented GPU: 8 hands-on chapters, for under $5, with measured numbers at every step.
The complete PoC: what I measured, what I broke and what it cost to serve an open-source model on a rented GPU.
Correr modelos de verdad: local, cuantización, VRAM, serving, medición y costos.
[ Inventory ]Built from first-hand experience
MOBILE // AI
Pet medical history: record the vet visit or photograph the prescription and Gemini extracts structured records with treatments and appointments.
[ Achievements ]Unlocked credentials
Google Developer Expert
GDE credential: recognized by Google as an expert and community contributor.
69 technical posts
Codea Bien: blog about Angular, Supabase and AI, now moving to kevindavila.dev.
Multiplatform
Product work on mobile, messaging and web: same data domain, three different worlds.
[ Talks & events ]Boss fights & keynotes
Calendar in the works. As a GDE I take part in community events and meetups: upcoming talks, recordings and slides will land here soon.
[ Contact channel ]
Got an interesting project, a talk to organize, or just want to trade notes on Web or AI? Let's talk.
> Alternative channels:
• GitHub: @kevindaviladev
• LinkedIn: /in/kevindaviladev