Run Gemma with Ollama on Cloud Run
Deploy Google's Gemma 2B open model on Cloud Run using Ollama for CPU-based inference with this sample project, providing an accessible way to run smaller LLMs in a serverless environment.
Ollama
Recent posts
Building rebaseable container images with Docker from scratch
A hands-on look at how rebaseable container images are structured on Cloud Run, using Docker and FROM scratch.
Cutting context window pollution with silent test runners
Dumping verbose test logs into an AI coding agent wastes context window space. Wrapping test commands in a silent Make macro suppresses noise on success while preserving full stack traces on failure.
Preventing port conflicts in Git worktrees using directory hashing
Deterministic directory hashing calculates unique local port numbers from absolute filesystem paths, preventing port collisions in Git worktrees without manual configuration.