Files
homelab-frontend/k8s
Admin Bot 44ec3502dc
CI / CI (pull_request) Failing after 2m13s
feat: add TTFT/ITL metrics for LLM inference
- RecordTTFT: Time-to-First-Token in milliseconds
- RecordITL: Inter-Token Latency in milliseconds
- RecordTokenCount: Track total tokens generated
- Prometheus exporter for /metrics endpoint
- Grafana dashboard ConfigMap (llm-metrics.json)
- ResponseWriterWrapper to capture metrics during LLM calls
- Metrics exported: llm_ttft_seconds, llm_itl_seconds, llm_tokens_total
2026-09-14 22:33:32 +09:00
..