Tag #llm-observability 1 post tagged llm-observability. ← All topics monitoring Model Monitoring for LLM Inference: Metrics Your APM Can't See Model monitoring for LLM APIs requires a different metric set than traditional ML. Here's the signal hierarchy — TTFT, KV cache hit rate, output length drift, refusal rate — wired up with OpenTelemetry and Prometheus. May 15, 2026