ob-e6b-sampled10.summary.json 854 B

12345678910111213141516171819202122232425262728293031323334353637383940414243444546
  1. {
  2. "base": "http://10.0.0.1:8888",
  3. "reps": 10,
  4. "max_tokens": 512,
  5. "phases": {
  6. "c1-chat_sampled": {
  7. "start": "2026-09-24T04:17:23.954295Z",
  8. "end": "2026-09-24T04:20:00.953811Z",
  9. "decode_tps": {
  10. "median": 32.94109698650078,
  11. "min": 31.814322847795722,
  12. "max": 34.340794910076056,
  13. "stdev": 0.7821731664694492,
  14. "n": 10
  15. },
  16. "e2e_tps": {
  17. "median": 32.455461758138185,
  18. "min": 31.339047535547277,
  19. "max": 33.82351525521321,
  20. "stdev": 0.7597039245880556,
  21. "n": 10
  22. },
  23. "ttft_s": {
  24. "median": 0.26150519798102323,
  25. "min": 0.25250778600457124,
  26. "max": 0.27699748598388396,
  27. "stdev": 0.007931794277972156,
  28. "n": 10
  29. },
  30. "completion_tokens": [
  31. 512,
  32. 512,
  33. 512,
  34. 512,
  35. 512,
  36. 512,
  37. 512,
  38. 512,
  39. 512,
  40. 512
  41. ],
  42. "distinct_outputs": 10,
  43. "errors": []
  44. }
  45. }
  46. }