You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
A distributed queue system for LLM tasks. Submit requests via OpenAI-compatible REST API from anywhere, process with Ollama on your local GPU (NVIDIA or Apple Silicon), and retrieve results. FastAPI server + SQLite queue + GPU worker architecture.