Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- 2nd last
- ```
- 02:46.90 I slot- 0 launch_slo | task 859 | processing task, is_child = 0
- 02:54.24 I slot- 0 print_timi | task 859 | n_decoded = 123, tg = 40.88 t/s, tg_3s = 40.87 t/s
- 02:57.25 I slot- 0 print_timi | task 859 | n_decoded = 254, tg = 42.20 t/s, tg_3s = 43.53 t/s
- 03:00.33 I slot- 0 print_timi | task 859 | n_decoded = 395, tg = 43.43 t/s, tg_3s = 45.82 t/s
- 03:03.35 I slot- 0 print_timi | task 859 | n_decoded = 537, tg = 44.34 t/s, tg_3s = 47.10 t/s
- 03:06.35 I slot- 0 print_timi | task 859 | n_decoded = 706, tg = 46.72 t/s, tg_3s = 56.30 t/s
- 03:09.41 I slot- 0 print_timi | task 859 | n_decoded = 862, tg = 47.42 t/s, tg_3s = 50.86 t/s
- 03:12.43 I slot- 0 print_timi | task 859 | n_decoded = 999, tg = 47.14 t/s, tg_3s = 45.46 t/s
- 03:15.48 I slot- 0 print_timi | task 859 | n_decoded = 1110, tg = 45.77 t/s, tg_3s = 36.33 t/s
- 03:18.54 I slot- 0 print_timi | task 859 | n_decoded = 1279, tg = 46.85 t/s, tg_3s = 55.36 t/s
- 03:21.61 I slot- 0 print_timi | task 859 | n_decoded = 1459, tg = 48.03 t/s, tg_3s = 58.55 t/s
- 03:24.68 I slot- 0 print_timi | task 859 | n_decoded = 1640, tg = 49.03 t/s, tg_3s = 58.91 t/s
- 03:27.72 I slot- 0 print_timi | task 859 | n_decoded = 1809, tg = 49.58 t/s, tg_3s = 55.68 t/s
- 03:30.78 I slot- 0 print_timi | task 859 | n_decoded = 1949, tg = 49.28 t/s, tg_3s = 45.70 t/s
- 03:33.81 I slot- 0 print_timi | task 859 | n_decoded = 2083, tg = 48.92 t/s, tg_3s = 44.21 t/s
- 03:36.83 I slot- 0 print_timi | task 859 | n_decoded = 2229, tg = 48.88 t/s, tg_3s = 48.36 t/s
- 03:39.88 I slot- 0 print_timi | task 859 | n_decoded = 2372, tg = 48.76 t/s, tg_3s = 46.91 t/s
- 03:42.07 I slot- 0 print_timi | task 859 | prompt eval time = 4.3 s / 3725 tok ( 1.2 ms/tok, 859.4 t/s)
- 03:42.07 I slot- 0 print_timi | task 859 | eval time = 50.8 s / 2517 tok ( 20.2 ms/tok, 49.5 t/s)
- 03:42.07 I slot- 0 print_timi | task 859 | total time = 55.2 s / 6242 tok
- 03:42.07 I slot- 0 print_timi | task 859 | graphs reused = 1412
- 03:42.07 I slot- 0 print_timi | task 859 | draft acceptance = 19.2% (1867 / 9735 accepted), mean len = 3.9
- 03:42.07 I slot- 0 release | task 859 | stop processing: n_tokens = 70303, truncated = 0
- ```
- final response:
- ```
- 04:45.60 I slot- 0 print_timi | task 2091 | n_decoded = 117, tg = 38.90 t/s, tg_3s = 38.89 t/s
- 04:48.67 I slot- 0 print_timi | task 2091 | n_decoded = 336, tg = 55.28 t/s, tg_3s = 71.33 t/s
- 04:51.70 I slot- 0 print_timi | task 2091 | n_decoded = 460, tg = 50.50 t/s, tg_3s = 40.93 t/s
- 04:54.73 I slot- 0 print_timi | task 2091 | n_decoded = 626, tg = 51.58 t/s, tg_3s = 54.83 t/s
- 04:57.78 I slot- 0 print_timi | task 2091 | n_decoded = 762, tg = 50.16 t/s, tg_3s = 44.49 t/s
- 05:00.85 I slot- 0 print_timi | task 2091 | n_decoded = 898, tg = 49.17 t/s, tg_3s = 44.31 t/s
- 05:03.89 I slot- 0 print_timi | task 2091 | n_decoded = 1088, tg = 51.09 t/s, tg_3s = 62.66 t/s
- 05:06.89 I slot- 0 print_timi | task 2091 | n_decoded = 1278, tg = 52.60 t/s, tg_3s = 63.27 t/s
- 05:09.92 I slot- 0 print_timi | task 2091 | n_decoded = 1440, tg = 52.69 t/s, tg_3s = 53.40 t/s
- 05:12.98 I slot- 0 print_timi | task 2091 | n_decoded = 1702, tg = 56.01 t/s, tg_3s = 85.77 t/s
- 05:15.98 I slot- 0 print_timi | task 2091 | n_decoded = 1802, tg = 53.97 t/s, tg_3s = 33.33 t/s
- 05:17.88 I slot- 0 print_timi | task 2091 | prompt eval time = 1.4 s / 918 tok ( 1.5 ms/tok, 653.0 t/s)
- 05:17.88 I slot- 0 print_timi | task 2091 | eval time = 35.3 s / 1854 tok ( 19.0 ms/tok, 52.5 t/s)
- 05:17.88 I slot- 0 print_timi | task 2091 | total time = 36.7 s / 2772 tok
- 05:17.88 I slot- 0 print_timi | task 2091 | graphs reused = 2420
- 05:17.88 I slot- 0 print_timi | task 2091 | draft acceptance = 18.8% (1367 / 7290 accepted), mean len = 3.8
- 05:17.88 I slot- 0 release | task 2091 | stop processing: n_tokens = 42476, truncated = 0
- 05:18.37 I slot- 0 get_availa | task -1 | selected slot by LCP similarity, sim_best = 0.956 (> 0.100 thold), f_keep = 0.957
- 05:18.37 I slot- 0 launch_slo | task 2582 | processing task, is_child = 0
- 05:22.10 I slot- 0 print_timi | task 2582 | prompt eval time = 2.2 s / 1903 tok ( 1.1 ms/tok, 880.6 t/s)
- 05:22.10 I slot- 0 print_timi | task 2582 | eval time = 1.6 s / 85 tok ( 18.4 ms/tok, 54.2 t/s)
- 05:22.10 I slot- 0 print_timi | task 2582 | total time = 3.7 s / 1988 tok
- 05:22.10 I slot- 0 print_timi | task 2582 | graphs reused = 2440
- 05:22.10 I slot- 0 print_timi | task 2582 | draft acceptance = 20.3% ( 64 / 315 accepted), mean len = 4.0
- 05:22.10 I slot- 0 release | task 2582 | stop processing: n_tokens = 42607, truncated = 0
- ```
Advertisement
Add Comment
Please, Sign In to add comment