Self-Hosted Gemma 4 — AKS, vLLM & FastAPI Deployed a self-hosted Gemma 4 inference platform on Az...Self-Hosted Gemma 4 — AKS, vLLM & FastAPI Deployed a self-hosted Gemma 4 inference platform on Az...
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Self-Hosted Gemma 4 — AKS, vLLM & FastAPI Deployed a self-hosted Gemma 4 inference platform on Azure Kubernetes Service using vLLM and a Python FastAPI service. Integrated OpenCode as the agentic coding harness, creating a scalable internal LLM environment that could expose GPU-backed inference to AI applications. Your résumé also documents this Gemma/vLLM/FastAPI work on AKS. 
Post image
Back to feed
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started