LLM 延迟 SLO 规划器

分享海报

@user_b26bd65e/llm-latency-slo-planner-b26bd65e

Define LLM latency service-level objectives, component budgets, percentiles, error budgets, and alerts. Use for streaming or non-streaming APIs, agent workflows, RAG pipelines, tool calls, capacity planning, or slow-response incidents.