AI model serving and LLM gateway on GPU Kubernetes by Ali SabirAI model serving and LLM gateway on GPU Kubernetes by Ali Sabir

AI model serving and LLM gateway on GPU Kubernetes

Ali Sabir

Ali Sabir

Like this project

Posted Oct 9, 2026

Built GPU Kubernetes model serving with KServe, an LLM gateway and MCP servers for AI agents, provisioned with Terraform and shipped via GitLab CI and Argo CD.