Admin Bot
e5a1f052a4
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
2026-09-15 15:14:13 +09:00
..
2026-09-09 00:00:07 +00:00
2026-09-09 00:00:07 +00:00
2026-08-21 20:46:45 -07:00
2026-08-21 20:46:45 -07:00
2026-08-21 20:46:45 -07:00
2026-08-21 20:46:45 -07:00
2026-09-15 15:14:13 +09:00
2026-08-21 20:46:45 -07:00
2026-08-21 20:46:45 -07:00
2026-09-13 23:37:33 +00:00
2026-08-21 20:46:45 -07:00
2026-09-13 23:37:33 +00:00
2026-08-21 20:46:45 -07:00
2026-09-09 00:31:10 +00:00
2026-09-09 00:31:10 +00:00
2026-08-21 20:46:45 -07:00
2026-08-21 20:46:45 -07:00