tg_3s = 1.45 t/s 2145.32.929.222 I slot print_timing: id 0 | task 3365 | n_gen = 113, tg = 1.82 t/s, tg_3s = 2.46 t/s 2145.36.246.047 I slot print_timing: id 0 | task 3365 | n_gen = 121, tg = 1.85 t/s, tg_3s = 2.41 t/s 2145.39.537.056 I slot print_timing: id 0 | task 3365 | n_gen = 128, tg = 1.87 t/s, tg_3s = 2.13 t/s 2145.42.544.623 I slot print_timing: id 0 | task 3365 | n_gen = 134, tg = 1.87 t/s, tg_3s = 1.99 t/s 2145.45.942.341 I slot print_timing: id 0 | task 3365 | n_gen = 142, tg = 1.89 t/s, tg_3s = 2.35 t/s 2145.49.540.117 I slot print_timing: id 0 | task 3365 | n_gen = 147, tg = 1.87 t/s, tg_3s = 1.39 t/s 2145.52.602.978 I slot print_timing: id 0 | task 3365 | n_gen = 152, tg = 1.86 t/s, tg_3s = 1.63 t/s 2145.55.773.570 I slot print_timing: id 0 | task 3365 | n_gen = 158, tg = 1.86 t/s, tg_3s = 1.89 t/s 2145.58.907.219 I slot print_timing: id 0 | task 3365 | n_gen = 165, tg = 1.88 t/s, tg_3s = 2.23 t/s 2146.02.139.431 I slot print_timing: id 0 | task 3365 | n_gen = 172, tg = 1.89 t/s, tg_3s = 2.17 t/s 2146.05.213.245 I slot print_timing: id 0 | task 3365 | n_gen = 179, tg = 1.90 t/s, tg_3s = 2.28 t/s 2146.08.247.137 I slot print_timing: id 0 | task 3365 | n_gen = 186, tg = 1.91 t/s, tg_3s = 2.31 t/s 2146.10.185.375 I slot print_timing: id 0 | task 3365 | prompt eval time = 423.59 ms / 1 tokens ( 423.59 ms per token, 2.36 tokens per second) 2146.10.185.430 I slot print_timing: id 0 | task 3365 | eval time = 98660.06 ms / 190 tokens ( 522.01 ms per token, 1.92 tokens per second) 2146.10.185.450 I slot print_timing: id 0 | task 3365 | total time = 99083.65 ms / 191 tokens 2146.10.185.469 I slot print_timing: id 0 | task 3365 | graphs reused = 3468 2146.10.187.997 I slot release: id 0 | task 3365 | stop processing: n_tokens = 3634, truncated = 0 2147.16.002.880 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 1.000 (> 0.100 thold), f_keep = 0.948 2147.16.003.079 I slot launch_slot_: id 0 | task 3556 | processing task, is_child = 0 2147.16.003.104 W slot operator(): id 0 | task 3556 | need to evaluate at least 1 token for each active slot (n_past = 3445, task.n_tokens() = 3445) 2147.16.003.106 W slot operator(): id 0 | task 3556 | n_past was set to 3444 2148.11.980.637 I slot print_timing: id 0 | task 3556 | n_gen = 100, tg = 1.78 t/s, tg_3s = 1.80 t/s 2148.16.078.843 I slot print_timing: id 0 | task 3556 | n_gen = 104, tg = 1.73 t/s, tg_3s = 0.98 t/s 2148.19.454.023 I slot print_timing: id 0 | task 3556 | n_gen = 111, tg = 1.75 t/s, tg_3s = 2.07 t/s 2148.22.910.703 I slot print_timing: id 0 | task 3556 | n_gen = 115, tg = 1.71 t/s, tg_3s = 1.16 t/s 2148.26.281.874 I slot print_timing: id 0 | task 3556 | n_gen = 121, tg = 1.72 t/s, tg_3s = 1.78 t/s 2148.29.403.127 I slot print_timing: id 0 | task 3556 | n_gen = 126, tg = 1.71 t/s, tg_3s = 1.60 t/s 2148.32.662.258 I slot print_timing: id 0 | task 3556 | n_gen = 133, tg = 1.73 t/s, tg_3s = 2.15 t/s 2148.36.262.886 I slot print_timing: id 0 | task 3556 | n_gen = 140, tg = 1.74 t/s, tg_3s = 1.94 t/s 2148.39.341.827 I slot print_timing: id 0 | task 3556 | n_gen = 146, tg = 1.75 t/s, tg_3s = 1.95 t/s 2148.42.631.192 I slot print_timing: id 0 | task 3556 | n_gen = 153, tg = 1.76 t/s, tg_3s = 2.13 t/s 2148.45.813.904 I slot print_timing: id 0 | task 3556 | n_gen = 159, tg = 1.77 t/s, tg_3s = 1.89 t/s 2148.48.930.258 I slot print_timing: id 0 | task 3556 | n_gen = 166, tg = 1.78 t/s, tg_3s = 2.25 t/s 2148.52.233.320 I slot print_timing: id 0 | task 3556 | n_gen = 170, tg = 1.76 t/s, tg_3s = 1.21 t/s 2148.55.617.013 I slot print_timing: id 0 | task 3556 | n_gen = 176, tg = 1.76 t/s, tg_3s = 1.77 t/s 2148.59.517.583 I slot print_timing: id 0 | task 3556 | n_gen = 183, tg = 1.77 t/s, tg_3s = 1.79 t/s 2149.00.612.851 I slot print_timing: id 0 | task 3556 | prompt eval time = 423.86 ms / 1 tokens ( 423.86 ms per token, 2.36 tokens per second) 2149.00.612.911 I slot print_timing: id 0 | task 3556 | eval time = 104185.82 ms / 184 tokens ( 569.32 ms per token, 1.76 tokens per second) 2149.00.612.916 I slot print_timing: id 0 | task 3556 | total time = 104609.68 ms / 185 tokens 2149.00.612.919 I slot print_timing: id 0 | task 3556 | graphs reused = 3650 2149.00.615.144 I slot release: id 0 | task 3556 | stop processing: n_tokens = 3628, truncated = 0 2149.05.567.844 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 1.000 (> 0.100 thold), f_keep = 0.950 2149.05.567.972 I slot launch_slot_: id 0 | task 3741 | processing task, is_child = 0 2149.05.567.989 W slot operator(): id 0 | task 3741 | need to evaluate at least 1 token for each active slot (n_past = 3445, task.n_tokens() = 3445) 2149.05.567.991 W slot operator(): id 0 | task 3741 | n_past was set to 3444 2150.12.160.692 I slot print_timing: id 0 | task 3741 | n_gen = 100, tg = 1.50 t/s, tg_3s = 1.51 t/s 2150.15.793.593 I slot print_timing: id 0 | task 3741 | n_gen = 108, tg = 1.54 t/s, tg_3s = 2.20 t/s 2150.18.976.307 I slot print_timing: id 0 | task 3741 | n_gen = 115, tg = 1.57 t/s, tg_3s = 2.20 t/s 2150.22.205.297 I slot print_timing: id 0 | task 3741 | n_gen = 120, tg = 1.56 t/s, tg_3s = 1.55 t/s 2150.25.532.675 I slot print_timing: id 0 | task 3741 | n_gen = 127, tg = 1.59 t/s, tg_3s = 2.10 t/s 2150.29.664.571 I slot print_timing: id 0 | task 3741 | n_gen = 134, tg = 1.59 t/s, tg_3s = 1.69 t/s 2150.32.743.816 I slot print_timing: id 0 | task 3741 | n_gen = 139, tg = 1.59 t/s, tg_3s = 1.62 t/s 2150.36.188.942 I slot print_timing: id 0 | task 3741 | n_gen = 145, tg = 1.60 t/s, tg_3s = 1.74 t/s 2150.39.761.078 I slot print_timing: id 0 | task 3741 | n_gen = 151, tg = 1.60 t/s, tg_3s = 1.68 t/s 2150.43.078.606 I slot print_timing: id 0 | task 3741 | n_gen = 156, tg = 1.60 t/s, tg_3s = 1.51 t/s 2150.46.216.021 I slot print_timing: id 0 | task 3741 | n_gen = 161, tg = 1.60 t/s, tg_3s = 1.59 t/s 2150.50.680.917 I slot print_timing: id 0 | task 3741 | n_gen = 167, tg = 1.59 t/s, tg_3s = 1.34 t/s 2150.54.517.697 I slot print_timing: id 0 | task 3741 | n_gen = 173, tg = 1.59 t/s, tg_3s = 1.56 t/s 2150.58.031.314 I slot print_timing: id 0 | task 3741 | n_gen = 180, tg = 1.60 t/s, tg_3s = 1.99 t/s 2151.01.450.078 I slot print_timing: id 0 | task 3741 | n_gen = 186, tg = 1.60 t/s, tg_3s = 1.76 t/s 2151.04.794.625 I slot print_timing: id 0 | task 3741 | n_gen = 191, tg = 1.60 t/s, tg_3s = 1.49 t/s 2151.08.088.740 I slot print_timing: id 0 | task 3741 | n_gen = 197, tg = 1.61 t/s, tg_3s = 1.82 t/s 2151.11.512.408 I slot print_timing: id 0 | task 3741 | n_gen = 203, tg = 1.61 t/s, tg_3s = 1.75 t/s 2151.14.912.095 I slot print_timing: id 0 | task 3741 | n_gen = 211, tg = 1.63 t/s, tg_3s = 2.35 t/s 2151.18.015.454 I slot print_timing: id 0 | task 3741 | n_gen = 217, tg = 1.64 t/s, tg_3s = 1.93 t/s 2151.21.557.232 I slot print_timing: id 0 | task 3741 | n_gen = 223, tg = 1.64 t/s, tg_3s = 1.69 t/s 2151.23.476.555 I slot print_timing: id 0 | task 3741 | prompt eval time = 578.59 ms / 1 tokens ( 578.59 ms per token, 1.73 tokens per second) 2151.23.476.657 I slot print_timing: id 0 | task 3741 | eval time = 137329.85 ms / 226 tokens ( 610.35 ms per token, 1.64 tokens per second) 2151.23.476.689 I slot print_timing: id 0 | task 3741 | total time = 137908.44 ms / 227 tokens 2151.23.476.710 I slot print_timing: id 0 | task 3741 | graphs reused = 3874 2151.23.478.776 I slot release: id 0 | task 3741 | stop processing: n_tokens = 3670, truncated = 0