最初のトークンまでの LLM 時間を測定する

SELECT
  feature,
  model,
  COUNT(*) AS requests,
  approx_percentile_cont(time_to_first_token_ms, 0.50) AS p50_ttft_ms,
  approx_percentile_cont(time_to_first_token_ms, 0.95) AS p95_ttft_ms,
  approx_percentile_cont(latency_ms, 0.95) AS p95_total_latency_ms
FROM llm_requests
WHERE timestamp_utc >= now() - INTERVAL '7 days'
  AND status = 'success'
  AND time_to_first_token_ms IS NOT NULL
GROUP BY feature, model
HAVING COUNT(*) >= 30
ORDER BY p95_ttft_ms DESC;