fix(api): run 2 uvicorn workers — a blocking LLM call in an async endpoint was freezing the single event loop (HTTP 000 outages)

feat(gpu): Ollama LLM server (qwen2.5:3b) for GPU inference + on-demand T4 with 15min auto-sleep

Deploy Auralynq RAG (Llama-3.3-70B via HF Inference Providers)