LLMOps for Production GenAI: Cost, Latency, and Release Gates

<p>Operate GenAI applications like production services: build a resilient model gateway with retries and circuit breakers, manage cost and latency budgets with prompt caching, gate releases on accuracy/safety/cost/latency, and plan incident response for model and API degradation &mdash; capped off with a hands-on budget-router lab.</p>

Tools: python, prompt caching, batch apis