/Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/bc1b210bdeec/LFM2.5-24B-A2B-UD-Q2_K_XL.gguf --host 127.0.0.1 --port 8091 -c 16384 -np 4 -ngl 999 -fa on --jinja --seed 1234 --chat-template-kwargs "{\"enable_thinking\": false}" --no-webui -a quant 0.00.050.791 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.050.846 I srv llama_server: initializing ... 0.00.050.851 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.050.930 I srv init_listene: The UI is disabled 0.00.050.931 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.050.965 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.052.625 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/bc1b210bdeec/LFM2.5-24B-A2B-UD-Q2_K_XL.gguf' 0.00.757.853 I cmn init: llama threadpool init, n_threads = 8 0.00.826.148 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.00.828.575 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.828.585 I srv llama_server: model loaded 0.00.828.587 I srv llama_server: listening on http://127.0.0.1:8091 0.31.403.419 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.403.444 I slot launch_slot_: id 0 | task 1 | processing task, is_child = 0 0.31.403.445 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.403.455 I slot launch_slot_: id 1 | task 0 | processing task, is_child = 0 0.31.403.456 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.403.465 I slot launch_slot_: id 2 | task 3 | processing task, is_child = 0 0.31.403.465 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.403.475 I slot launch_slot_: id 3 | task 2 | processing task, is_child = 0 0.32.777.561 I slot print_timing: id 0 | task 1 | prompt eval time = 1312.24 ms / 123 tokens ( 10.67 ms per token, 93.73 tokens per second) 0.32.777.564 I slot print_timing: id 0 | task 1 | eval time = 61.83 ms / 2 tokens ( 61.83 ms per token, 16.17 tokens per second) 0.32.777.564 I slot print_timing: id 0 | task 1 | total time = 1374.08 ms / 125 tokens 0.32.777.565 I slot print_timing: id 0 | task 1 | graphs reused = 1 0.32.777.565 I slot print_timing: id 0 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.777.590 I slot release: id 0 | task 1 | stop processing: n_tokens = 124, truncated = 0 0.32.777.951 I slot print_timing: id 1 | task 0 | prompt eval time = 1312.68 ms / 112 tokens ( 11.72 ms per token, 85.32 tokens per second) 0.32.777.953 I slot print_timing: id 1 | task 0 | eval time = 61.78 ms / 2 tokens ( 61.78 ms per token, 16.19 tokens per second) 0.32.777.953 I slot print_timing: id 1 | task 0 | total time = 1374.46 ms / 114 tokens 0.32.777.954 I slot print_timing: id 1 | task 0 | graphs reused = 1 0.32.777.954 I slot print_timing: id 1 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.777.972 I slot release: id 1 | task 0 | stop processing: n_tokens = 113, truncated = 0 0.32.778.256 I slot print_timing: id 2 | task 3 | prompt eval time = 1313.11 ms / 117 tokens ( 11.22 ms per token, 89.10 tokens per second) 0.32.778.259 I slot print_timing: id 2 | task 3 | eval time = 61.66 ms / 2 tokens ( 61.66 ms per token, 16.22 tokens per second) 0.32.778.259 I slot print_timing: id 2 | task 3 | total time = 1374.76 ms / 119 tokens 0.32.778.259 I slot print_timing: id 2 | task 3 | graphs reused = 1 0.32.778.260 I slot print_timing: id 2 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.778.270 I slot release: id 2 | task 3 | stop processing: n_tokens = 118, truncated = 0 0.32.778.576 I slot print_timing: id 3 | task 2 | prompt eval time = 1313.55 ms / 131 tokens ( 10.03 ms per token, 99.73 tokens per second) 0.32.778.580 I slot print_timing: id 3 | task 2 | eval time = 61.53 ms / 2 tokens ( 61.53 ms per token, 16.25 tokens per second) 0.32.778.580 I slot print_timing: id 3 | task 2 | total time = 1375.08 ms / 133 tokens 0.32.778.581 I slot print_timing: id 3 | task 2 | graphs reused = 1 0.32.778.581 I slot print_timing: id 3 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.778.593 I slot release: id 3 | task 2 | stop processing: n_tokens = 132, truncated = 0 0.32.785.084 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.242 0.32.785.351 I slot launch_slot_: id 0 | task 7 | processing task, is_child = 0 0.32.786.318 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.254 0.32.786.353 I slot launch_slot_: id 2 | task 8 | processing task, is_child = 0 0.32.786.384 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.257 0.32.786.416 I slot launch_slot_: id 1 | task 9 | processing task, is_child = 0 0.32.786.434 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.220 0.32.786.461 I slot launch_slot_: id 3 | task 10 | processing task, is_child = 0 0.34.022.651 I slot print_timing: id 0 | task 7 | prompt eval time = 1196.02 ms / 110 tokens ( 10.87 ms per token, 91.97 tokens per second) 0.34.022.653 I slot print_timing: id 0 | task 7 | eval time = 40.16 ms / 2 tokens ( 40.16 ms per token, 24.90 tokens per second) 0.34.022.653 I slot print_timing: id 0 | task 7 | total time = 1236.18 ms / 112 tokens 0.34.022.654 I slot print_timing: id 0 | task 7 | graphs reused = 1 0.34.022.654 I slot print_timing: id 0 | task 7 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.022.674 I slot release: id 0 | task 7 | stop processing: n_tokens = 111, truncated = 0 0.34.022.953 I slot print_timing: id 1 | task 9 | prompt eval time = 1196.28 ms / 161 tokens ( 7.43 ms per token, 134.58 tokens per second) 0.34.022.955 I slot print_timing: id 1 | task 9 | eval time = 40.19 ms / 2 tokens ( 40.19 ms per token, 24.88 tokens per second) 0.34.022.956 I slot print_timing: id 1 | task 9 | total time = 1236.47 ms / 163 tokens 0.34.022.956 I slot print_timing: id 1 | task 9 | graphs reused = 1 0.34.022.956 I slot print_timing: id 1 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.022.972 I slot release: id 1 | task 9 | stop processing: n_tokens = 162, truncated = 0 0.34.023.263 I slot print_timing: id 2 | task 8 | prompt eval time = 1196.56 ms / 161 tokens ( 7.43 ms per token, 134.55 tokens per second) 0.34.023.265 I slot print_timing: id 2 | task 8 | eval time = 40.21 ms / 2 tokens ( 40.21 ms per token, 24.87 tokens per second) 0.34.023.266 I slot print_timing: id 2 | task 8 | total time = 1236.77 ms / 163 tokens 0.34.023.266 I slot print_timing: id 2 | task 8 | graphs reused = 1 0.34.023.266 I slot print_timing: id 2 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.023.283 I slot release: id 2 | task 8 | stop processing: n_tokens = 162, truncated = 0 0.34.023.601 I slot print_timing: id 3 | task 10 | prompt eval time = 1196.88 ms / 199 tokens ( 6.01 ms per token, 166.27 tokens per second) 0.34.023.604 I slot print_timing: id 3 | task 10 | eval time = 40.21 ms / 2 tokens ( 40.21 ms per token, 24.87 tokens per second) 0.34.023.607 I slot print_timing: id 3 | task 10 | total time = 1237.10 ms / 201 tokens 0.34.023.607 I slot print_timing: id 3 | task 10 | graphs reused = 1 0.34.023.607 I slot print_timing: id 3 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.023.632 I slot release: id 3 | task 10 | stop processing: n_tokens = 200, truncated = 0 0.34.027.931 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.270 0.34.028.347 I slot launch_slot_: id 0 | task 16 | processing task, is_child = 0 0.34.029.422 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.179 0.34.029.461 I slot launch_slot_: id 1 | task 17 | processing task, is_child = 0 0.34.029.496 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.179 0.34.029.527 I slot launch_slot_: id 2 | task 14 | processing task, is_child = 0 0.34.029.546 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.145 0.34.029.577 I slot launch_slot_: id 3 | task 15 | processing task, is_child = 0 0.35.049.725 I slot print_timing: id 0 | task 16 | prompt eval time = 979.93 ms / 119 tokens ( 8.23 ms per token, 121.44 tokens per second) 0.35.049.730 I slot print_timing: id 0 | task 16 | eval time = 40.21 ms / 2 tokens ( 40.21 ms per token, 24.87 tokens per second) 0.35.049.730 I slot print_timing: id 0 | task 16 | total time = 1020.14 ms / 121 tokens 0.35.049.731 I slot print_timing: id 0 | task 16 | graphs reused = 1 0.35.049.731 I slot print_timing: id 0 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.049.751 I slot release: id 0 | task 16 | stop processing: n_tokens = 120, truncated = 0 0.35.050.025 I slot print_timing: id 1 | task 17 | prompt eval time = 980.19 ms / 151 tokens ( 6.49 ms per token, 154.05 tokens per second) 0.35.050.027 I slot print_timing: id 1 | task 17 | eval time = 40.24 ms / 2 tokens ( 40.24 ms per token, 24.85 tokens per second) 0.35.050.028 I slot print_timing: id 1 | task 17 | total time = 1020.43 ms / 153 tokens 0.35.050.028 I slot print_timing: id 1 | task 17 | graphs reused = 1 0.35.050.028 I slot print_timing: id 1 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.050.043 I slot release: id 1 | task 17 | stop processing: n_tokens = 152, truncated = 0 0.35.050.402 I slot print_timing: id 2 | task 14 | prompt eval time = 980.56 ms / 116 tokens ( 8.45 ms per token, 118.30 tokens per second) 0.35.050.405 I slot print_timing: id 2 | task 14 | eval time = 40.23 ms / 2 tokens ( 40.23 ms per token, 24.85 tokens per second) 0.35.050.406 I slot print_timing: id 2 | task 14 | total time = 1020.79 ms / 118 tokens 0.35.050.406 I slot print_timing: id 2 | task 14 | graphs reused = 1 0.35.050.406 I slot print_timing: id 2 | task 14 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.050.420 I slot release: id 2 | task 14 | stop processing: n_tokens = 117, truncated = 0 0.35.050.721 I slot print_timing: id 3 | task 15 | prompt eval time = 980.88 ms / 127 tokens ( 7.72 ms per token, 129.48 tokens per second) 0.35.050.724 I slot print_timing: id 3 | task 15 | eval time = 40.23 ms / 2 tokens ( 40.23 ms per token, 24.86 tokens per second) 0.35.050.724 I slot print_timing: id 3 | task 15 | total time = 1021.10 ms / 129 tokens 0.35.050.725 I slot print_timing: id 3 | task 15 | graphs reused = 1 0.35.050.725 I slot print_timing: id 3 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.050.735 I slot release: id 3 | task 15 | stop processing: n_tokens = 128, truncated = 0 0.35.055.130 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.242 0.35.055.567 I slot launch_slot_: id 0 | task 21 | processing task, is_child = 0 0.35.056.657 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.191 0.35.056.691 I slot launch_slot_: id 1 | task 22 | processing task, is_child = 0 0.35.056.723 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.248 0.35.056.750 I slot launch_slot_: id 2 | task 23 | processing task, is_child = 0 0.35.056.768 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.227 0.35.056.796 I slot launch_slot_: id 3 | task 24 | processing task, is_child = 0 0.36.289.788 I slot print_timing: id 0 | task 21 | prompt eval time = 1193.05 ms / 135 tokens ( 8.84 ms per token, 113.16 tokens per second) 0.36.289.790 I slot print_timing: id 0 | task 21 | eval time = 39.93 ms / 2 tokens ( 39.93 ms per token, 25.04 tokens per second) 0.36.289.791 I slot print_timing: id 0 | task 21 | total time = 1232.98 ms / 137 tokens 0.36.289.791 I slot print_timing: id 0 | task 21 | graphs reused = 1 0.36.289.792 I slot print_timing: id 0 | task 21 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.289.814 I slot release: id 0 | task 21 | stop processing: n_tokens = 136, truncated = 0 0.36.290.179 I slot print_timing: id 1 | task 22 | prompt eval time = 1193.40 ms / 143 tokens ( 8.35 ms per token, 119.83 tokens per second) 0.36.290.182 I slot print_timing: id 1 | task 22 | eval time = 39.97 ms / 2 tokens ( 39.97 ms per token, 25.02 tokens per second) 0.36.290.182 I slot print_timing: id 1 | task 22 | total time = 1233.37 ms / 145 tokens 0.36.290.182 I slot print_timing: id 1 | task 22 | graphs reused = 1 0.36.290.183 I slot print_timing: id 1 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.290.196 I slot release: id 1 | task 22 | stop processing: n_tokens = 144, truncated = 0 0.36.290.492 I slot print_timing: id 2 | task 23 | prompt eval time = 1193.70 ms / 120 tokens ( 9.95 ms per token, 100.53 tokens per second) 0.36.290.494 I slot print_timing: id 2 | task 23 | eval time = 39.97 ms / 2 tokens ( 39.97 ms per token, 25.02 tokens per second) 0.36.290.494 I slot print_timing: id 2 | task 23 | total time = 1233.67 ms / 122 tokens 0.36.290.495 I slot print_timing: id 2 | task 23 | graphs reused = 1 0.36.290.495 I slot print_timing: id 2 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.290.506 I slot release: id 2 | task 23 | stop processing: n_tokens = 121, truncated = 0 0.36.290.802 I slot print_timing: id 3 | task 24 | prompt eval time = 1193.99 ms / 184 tokens ( 6.49 ms per token, 154.10 tokens per second) 0.36.290.809 I slot print_timing: id 3 | task 24 | eval time = 39.98 ms / 2 tokens ( 39.98 ms per token, 25.02 tokens per second) 0.36.290.809 I slot print_timing: id 3 | task 24 | total time = 1233.97 ms / 186 tokens 0.36.290.809 I slot print_timing: id 3 | task 24 | graphs reused = 1 0.36.290.809 I slot print_timing: id 3 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.290.833 I slot release: id 3 | task 24 | stop processing: n_tokens = 185, truncated = 0 0.36.295.158 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.213 0.36.295.762 I slot launch_slot_: id 0 | task 29 | processing task, is_child = 0 0.36.296.957 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.201 0.36.297.085 I slot launch_slot_: id 1 | task 30 | processing task, is_child = 0 0.36.297.118 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.240 0.36.297.145 I slot launch_slot_: id 2 | task 31 | processing task, is_child = 0 0.36.297.164 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.157 0.36.297.192 I slot launch_slot_: id 3 | task 28 | processing task, is_child = 0 0.37.558.928 I slot print_timing: id 0 | task 29 | prompt eval time = 1221.92 ms / 125 tokens ( 9.78 ms per token, 102.30 tokens per second) 0.37.558.930 I slot print_timing: id 0 | task 29 | eval time = 39.81 ms / 2 tokens ( 39.81 ms per token, 25.12 tokens per second) 0.37.558.931 I slot print_timing: id 0 | task 29 | total time = 1261.73 ms / 127 tokens 0.37.558.931 I slot print_timing: id 0 | task 29 | graphs reused = 1 0.37.558.932 I slot print_timing: id 0 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.558.951 I slot release: id 0 | task 29 | stop processing: n_tokens = 126, truncated = 0 0.37.559.228 I slot print_timing: id 1 | task 30 | prompt eval time = 1222.19 ms / 131 tokens ( 9.33 ms per token, 107.18 tokens per second) 0.37.559.230 I slot print_timing: id 1 | task 30 | eval time = 39.83 ms / 2 tokens ( 39.83 ms per token, 25.10 tokens per second) 0.37.559.231 I slot print_timing: id 1 | task 30 | total time = 1262.02 ms / 133 tokens 0.37.559.231 I slot print_timing: id 1 | task 30 | graphs reused = 1 0.37.559.231 I slot print_timing: id 1 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.559.244 I slot release: id 1 | task 30 | stop processing: n_tokens = 132, truncated = 0 0.37.559.531 I slot print_timing: id 2 | task 31 | prompt eval time = 1222.46 ms / 141 tokens ( 8.67 ms per token, 115.34 tokens per second) 0.37.559.534 I slot print_timing: id 2 | task 31 | eval time = 39.86 ms / 2 tokens ( 39.86 ms per token, 25.09 tokens per second) 0.37.559.535 I slot print_timing: id 2 | task 31 | total time = 1262.32 ms / 143 tokens 0.37.559.535 I slot print_timing: id 2 | task 31 | graphs reused = 1 0.37.559.535 I slot print_timing: id 2 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.559.547 I slot release: id 2 | task 31 | stop processing: n_tokens = 142, truncated = 0 0.37.559.844 I slot print_timing: id 3 | task 28 | prompt eval time = 1222.76 ms / 179 tokens ( 6.83 ms per token, 146.39 tokens per second) 0.37.559.852 I slot print_timing: id 3 | task 28 | eval time = 39.86 ms / 2 tokens ( 39.86 ms per token, 25.09 tokens per second) 0.37.559.852 I slot print_timing: id 3 | task 28 | total time = 1262.62 ms / 181 tokens 0.37.559.853 I slot print_timing: id 3 | task 28 | graphs reused = 1 0.37.559.853 I slot print_timing: id 3 | task 28 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.559.865 I slot release: id 3 | task 28 | stop processing: n_tokens = 180, truncated = 0 0.37.563.917 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.230 0.37.564.246 I slot launch_slot_: id 0 | task 36 | processing task, is_child = 0 0.37.565.303 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.220 0.37.565.332 I slot launch_slot_: id 1 | task 35 | processing task, is_child = 0 0.37.565.366 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.204 0.37.565.500 I slot launch_slot_: id 2 | task 37 | processing task, is_child = 0 0.37.565.519 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.167 0.37.565.547 I slot launch_slot_: id 3 | task 38 | processing task, is_child = 0 0.38.733.863 I slot print_timing: id 0 | task 36 | prompt eval time = 1128.53 ms / 143 tokens ( 7.89 ms per token, 126.71 tokens per second) 0.38.733.865 I slot print_timing: id 0 | task 36 | eval time = 39.78 ms / 2 tokens ( 39.78 ms per token, 25.14 tokens per second) 0.38.733.865 I slot print_timing: id 0 | task 36 | total time = 1168.31 ms / 145 tokens 0.38.733.866 I slot print_timing: id 0 | task 36 | graphs reused = 1 0.38.733.866 I slot print_timing: id 0 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.733.890 I slot release: id 0 | task 36 | stop processing: n_tokens = 144, truncated = 0 0.38.734.159 I slot print_timing: id 1 | task 35 | prompt eval time = 1128.79 ms / 113 tokens ( 9.99 ms per token, 100.11 tokens per second) 0.38.734.161 I slot print_timing: id 1 | task 35 | eval time = 39.80 ms / 2 tokens ( 39.80 ms per token, 25.12 tokens per second) 0.38.734.162 I slot print_timing: id 1 | task 35 | total time = 1168.60 ms / 115 tokens 0.38.734.162 I slot print_timing: id 1 | task 35 | graphs reused = 1 0.38.734.162 I slot print_timing: id 1 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.734.179 I slot release: id 1 | task 35 | stop processing: n_tokens = 114, truncated = 0 0.38.734.458 I slot print_timing: id 2 | task 37 | prompt eval time = 1129.06 ms / 122 tokens ( 9.25 ms per token, 108.05 tokens per second) 0.38.734.461 I slot print_timing: id 2 | task 37 | eval time = 39.83 ms / 2 tokens ( 39.83 ms per token, 25.11 tokens per second) 0.38.734.461 I slot print_timing: id 2 | task 37 | total time = 1168.88 ms / 124 tokens 0.38.734.462 I slot print_timing: id 2 | task 37 | graphs reused = 1 0.38.734.462 I slot print_timing: id 2 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.734.473 I slot release: id 2 | task 37 | stop processing: n_tokens = 123, truncated = 0 0.38.734.788 I slot print_timing: id 3 | task 38 | prompt eval time = 1129.34 ms / 145 tokens ( 7.79 ms per token, 128.39 tokens per second) 0.38.734.791 I slot print_timing: id 3 | task 38 | eval time = 39.86 ms / 2 tokens ( 39.86 ms per token, 25.09 tokens per second) 0.38.734.791 I slot print_timing: id 3 | task 38 | total time = 1169.21 ms / 147 tokens 0.38.734.791 I slot print_timing: id 3 | task 38 | graphs reused = 1 0.38.734.792 I slot print_timing: id 3 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.734.808 I slot release: id 3 | task 38 | stop processing: n_tokens = 146, truncated = 0 0.38.738.975 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.244 0.38.739.333 I slot launch_slot_: id 2 | task 42 | processing task, is_child = 0 0.38.740.279 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.201 0.38.740.313 I slot launch_slot_: id 0 | task 45 | processing task, is_child = 0 0.38.740.345 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.254 0.38.740.372 I slot launch_slot_: id 1 | task 44 | processing task, is_child = 0 0.38.740.390 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.199 0.38.740.418 I slot launch_slot_: id 3 | task 43 | processing task, is_child = 0 0.39.795.587 I slot print_timing: id 0 | task 45 | prompt eval time = 1015.29 ms / 110 tokens ( 9.23 ms per token, 108.34 tokens per second) 0.39.795.590 I slot print_timing: id 0 | task 45 | eval time = 39.88 ms / 2 tokens ( 39.88 ms per token, 25.08 tokens per second) 0.39.795.590 I slot print_timing: id 0 | task 45 | total time = 1055.16 ms / 112 tokens 0.39.795.590 I slot print_timing: id 0 | task 45 | graphs reused = 1 0.39.795.592 I slot print_timing: id 0 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.795.611 I slot release: id 0 | task 45 | stop processing: n_tokens = 111, truncated = 0 0.39.795.986 I slot print_timing: id 1 | task 44 | prompt eval time = 1015.64 ms / 146 tokens ( 6.96 ms per token, 143.75 tokens per second) 0.39.795.988 I slot print_timing: id 1 | task 44 | eval time = 39.91 ms / 2 tokens ( 39.91 ms per token, 25.06 tokens per second) 0.39.795.989 I slot print_timing: id 1 | task 44 | total time = 1055.55 ms / 148 tokens 0.39.795.989 I slot print_timing: id 1 | task 44 | graphs reused = 1 0.39.795.989 I slot print_timing: id 1 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.796.001 I slot release: id 1 | task 44 | stop processing: n_tokens = 147, truncated = 0 0.39.796.272 I slot print_timing: id 2 | task 42 | prompt eval time = 1015.92 ms / 115 tokens ( 8.83 ms per token, 113.20 tokens per second) 0.39.796.274 I slot print_timing: id 2 | task 42 | eval time = 39.91 ms / 2 tokens ( 39.91 ms per token, 25.06 tokens per second) 0.39.796.274 I slot print_timing: id 2 | task 42 | total time = 1055.83 ms / 117 tokens 0.39.796.274 I slot print_timing: id 2 | task 42 | graphs reused = 1 0.39.796.275 I slot print_timing: id 2 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.796.287 I slot release: id 2 | task 42 | stop processing: n_tokens = 116, truncated = 0 0.39.796.586 I slot print_timing: id 3 | task 43 | prompt eval time = 1016.22 ms / 123 tokens ( 8.26 ms per token, 121.04 tokens per second) 0.39.796.589 I slot print_timing: id 3 | task 43 | eval time = 39.91 ms / 2 tokens ( 39.91 ms per token, 25.06 tokens per second) 0.39.796.589 I slot print_timing: id 3 | task 43 | total time = 1056.13 ms / 125 tokens 0.39.796.590 I slot print_timing: id 3 | task 43 | graphs reused = 1 0.39.796.590 I slot print_timing: id 3 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.796.607 I slot release: id 3 | task 43 | stop processing: n_tokens = 124, truncated = 0 0.39.800.205 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.261 0.39.800.431 I slot launch_slot_: id 0 | task 50 | processing task, is_child = 0 0.39.801.333 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.284 0.39.801.362 I slot launch_slot_: id 2 | task 49 | processing task, is_child = 0 0.39.801.395 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.197 0.39.801.424 I slot launch_slot_: id 1 | task 51 | processing task, is_child = 0 0.39.801.442 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.234 0.39.801.585 I slot launch_slot_: id 3 | task 52 | processing task, is_child = 0 0.40.927.500 I slot print_timing: id 0 | task 50 | prompt eval time = 1085.49 ms / 137 tokens ( 7.92 ms per token, 126.21 tokens per second) 0.40.927.502 I slot print_timing: id 0 | task 50 | eval time = 40.41 ms / 2 tokens ( 40.41 ms per token, 24.74 tokens per second) 0.40.927.502 I slot print_timing: id 0 | task 50 | total time = 1125.90 ms / 139 tokens 0.40.927.503 I slot print_timing: id 0 | task 50 | graphs reused = 1 0.40.927.503 I slot print_timing: id 0 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.927.525 I slot release: id 0 | task 50 | stop processing: n_tokens = 138, truncated = 0 0.40.927.788 I slot print_timing: id 1 | task 51 | prompt eval time = 1085.75 ms / 103 tokens ( 10.54 ms per token, 94.87 tokens per second) 0.40.927.789 I slot print_timing: id 1 | task 51 | eval time = 40.44 ms / 2 tokens ( 40.44 ms per token, 24.73 tokens per second) 0.40.927.790 I slot print_timing: id 1 | task 51 | total time = 1126.19 ms / 105 tokens 0.40.927.790 I slot print_timing: id 1 | task 51 | graphs reused = 1 0.40.927.790 I slot print_timing: id 1 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.927.805 I slot release: id 1 | task 51 | stop processing: n_tokens = 104, truncated = 0 0.40.928.081 I slot print_timing: id 2 | task 49 | prompt eval time = 1086.05 ms / 131 tokens ( 8.29 ms per token, 120.62 tokens per second) 0.40.928.083 I slot print_timing: id 2 | task 49 | eval time = 40.42 ms / 2 tokens ( 40.42 ms per token, 24.74 tokens per second) 0.40.928.083 I slot print_timing: id 2 | task 49 | total time = 1126.47 ms / 133 tokens 0.40.928.083 I slot print_timing: id 2 | task 49 | graphs reused = 1 0.40.928.083 I slot print_timing: id 2 | task 49 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.928.095 I slot release: id 2 | task 49 | stop processing: n_tokens = 132, truncated = 0 0.40.928.391 I slot print_timing: id 3 | task 52 | prompt eval time = 1086.37 ms / 114 tokens ( 9.53 ms per token, 104.94 tokens per second) 0.40.928.394 I slot print_timing: id 3 | task 52 | eval time = 40.40 ms / 2 tokens ( 40.40 ms per token, 24.75 tokens per second) 0.40.928.394 I slot print_timing: id 3 | task 52 | total time = 1126.77 ms / 116 tokens 0.40.928.394 I slot print_timing: id 3 | task 52 | graphs reused = 1 0.40.928.395 I slot print_timing: id 3 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.928.412 I slot release: id 3 | task 52 | stop processing: n_tokens = 115, truncated = 0 0.40.933.056 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.210 0.40.933.497 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.40.934.374 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.279 0.40.934.410 I slot launch_slot_: id 1 | task 57 | processing task, is_child = 0 0.40.934.442 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.220 0.40.934.583 I slot launch_slot_: id 2 | task 58 | processing task, is_child = 0 0.40.934.601 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.252 0.40.934.628 I slot launch_slot_: id 3 | task 59 | processing task, is_child = 0 0.42.204.115 I slot print_timing: id 0 | task 56 | prompt eval time = 1229.39 ms / 132 tokens ( 9.31 ms per token, 107.37 tokens per second) 0.42.204.117 I slot print_timing: id 0 | task 56 | eval time = 40.09 ms / 2 tokens ( 40.09 ms per token, 24.95 tokens per second) 0.42.204.118 I slot print_timing: id 0 | task 56 | total time = 1269.48 ms / 134 tokens 0.42.204.118 I slot print_timing: id 0 | task 56 | graphs reused = 1 0.42.204.118 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.204.142 I slot release: id 0 | task 56 | stop processing: n_tokens = 133, truncated = 0 0.42.204.423 I slot print_timing: id 1 | task 57 | prompt eval time = 1229.66 ms / 168 tokens ( 7.32 ms per token, 136.62 tokens per second) 0.42.204.425 I slot print_timing: id 1 | task 57 | eval time = 40.12 ms / 2 tokens ( 40.12 ms per token, 24.93 tokens per second) 0.42.204.426 I slot print_timing: id 1 | task 57 | total time = 1269.78 ms / 170 tokens 0.42.204.426 I slot print_timing: id 1 | task 57 | graphs reused = 1 0.42.204.426 I slot print_timing: id 1 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.204.442 I slot release: id 1 | task 57 | stop processing: n_tokens = 169, truncated = 0 0.42.204.739 I slot print_timing: id 2 | task 58 | prompt eval time = 1229.94 ms / 186 tokens ( 6.61 ms per token, 151.23 tokens per second) 0.42.204.740 I slot print_timing: id 2 | task 58 | eval time = 40.14 ms / 2 tokens ( 40.14 ms per token, 24.91 tokens per second) 0.42.204.741 I slot print_timing: id 2 | task 58 | total time = 1270.09 ms / 188 tokens 0.42.204.741 I slot print_timing: id 2 | task 58 | graphs reused = 1 0.42.204.741 I slot print_timing: id 2 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.204.756 I slot release: id 2 | task 58 | stop processing: n_tokens = 187, truncated = 0 0.42.205.060 I slot print_timing: id 3 | task 59 | prompt eval time = 1230.26 ms / 178 tokens ( 6.91 ms per token, 144.68 tokens per second) 0.42.205.062 I slot print_timing: id 3 | task 59 | eval time = 40.13 ms / 2 tokens ( 40.13 ms per token, 24.92 tokens per second) 0.42.205.063 I slot print_timing: id 3 | task 59 | total time = 1270.40 ms / 180 tokens 0.42.205.063 I slot print_timing: id 3 | task 59 | graphs reused = 1 0.42.205.063 I slot print_timing: id 3 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.205.084 I slot release: id 3 | task 59 | stop processing: n_tokens = 179, truncated = 0 0.42.209.466 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.218 0.42.209.844 I slot launch_slot_: id 0 | task 63 | processing task, is_child = 0 0.42.211.204 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.172 0.42.211.239 I slot launch_slot_: id 1 | task 64 | processing task, is_child = 0 0.42.211.275 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.155 0.42.211.305 I slot launch_slot_: id 2 | task 65 | processing task, is_child = 0 0.42.211.324 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.162 0.42.211.474 I slot launch_slot_: id 3 | task 66 | processing task, is_child = 0 0.43.418.271 I slot print_timing: id 0 | task 63 | prompt eval time = 1166.83 ms / 124 tokens ( 9.41 ms per token, 106.27 tokens per second) 0.43.418.273 I slot print_timing: id 0 | task 63 | eval time = 39.96 ms / 2 tokens ( 39.96 ms per token, 25.03 tokens per second) 0.43.418.274 I slot print_timing: id 0 | task 63 | total time = 1206.79 ms / 126 tokens 0.43.418.274 I slot print_timing: id 0 | task 63 | graphs reused = 1 0.43.418.275 I slot print_timing: id 0 | task 63 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.418.293 I slot release: id 0 | task 63 | stop processing: n_tokens = 125, truncated = 0 0.43.418.559 I slot print_timing: id 1 | task 64 | prompt eval time = 1167.10 ms / 150 tokens ( 7.78 ms per token, 128.52 tokens per second) 0.43.418.561 I slot print_timing: id 1 | task 64 | eval time = 39.97 ms / 2 tokens ( 39.97 ms per token, 25.02 tokens per second) 0.43.418.561 I slot print_timing: id 1 | task 64 | total time = 1207.07 ms / 152 tokens 0.43.418.562 I slot print_timing: id 1 | task 64 | graphs reused = 1 0.43.418.562 I slot print_timing: id 1 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.418.578 I slot release: id 1 | task 64 | stop processing: n_tokens = 151, truncated = 0 0.43.418.858 I slot print_timing: id 2 | task 65 | prompt eval time = 1167.36 ms / 168 tokens ( 6.95 ms per token, 143.91 tokens per second) 0.43.418.860 I slot print_timing: id 2 | task 65 | eval time = 39.99 ms / 2 tokens ( 39.99 ms per token, 25.01 tokens per second) 0.43.418.862 I slot print_timing: id 2 | task 65 | total time = 1207.36 ms / 170 tokens 0.43.418.862 I slot print_timing: id 2 | task 65 | graphs reused = 1 0.43.418.862 I slot print_timing: id 2 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.418.878 I slot release: id 2 | task 65 | stop processing: n_tokens = 169, truncated = 0 0.43.419.182 I slot print_timing: id 3 | task 66 | prompt eval time = 1167.68 ms / 141 tokens ( 8.28 ms per token, 120.75 tokens per second) 0.43.419.184 I slot print_timing: id 3 | task 66 | eval time = 39.99 ms / 2 tokens ( 39.99 ms per token, 25.01 tokens per second) 0.43.419.184 I slot print_timing: id 3 | task 66 | total time = 1207.67 ms / 143 tokens 0.43.419.184 I slot print_timing: id 3 | task 66 | graphs reused = 1 0.43.419.185 I slot print_timing: id 3 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.419.193 I slot release: id 3 | task 66 | stop processing: n_tokens = 142, truncated = 0 0.43.423.210 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.240 0.43.423.431 I slot launch_slot_: id 0 | task 71 | processing task, is_child = 0 0.43.424.680 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.192 0.43.424.716 I slot launch_slot_: id 1 | task 70 | processing task, is_child = 0 0.43.424.750 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.172 0.43.424.782 I slot launch_slot_: id 2 | task 72 | processing task, is_child = 0 0.43.424.799 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.270 (> 0.100 thold), f_keep = 0.211 0.43.424.829 I slot launch_slot_: id 3 | task 73 | processing task, is_child = 0 0.44.705.978 I slot print_timing: id 0 | task 71 | prompt eval time = 1241.13 ms / 160 tokens ( 7.76 ms per token, 128.91 tokens per second) 0.44.705.980 I slot print_timing: id 0 | task 71 | eval time = 40.01 ms / 2 tokens ( 40.01 ms per token, 24.99 tokens per second) 0.44.705.981 I slot print_timing: id 0 | task 71 | total time = 1281.14 ms / 162 tokens 0.44.705.981 I slot print_timing: id 0 | task 71 | graphs reused = 1 0.44.705.982 I slot print_timing: id 0 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.706.005 I slot release: id 0 | task 71 | stop processing: n_tokens = 161, truncated = 0 0.44.706.372 I slot print_timing: id 1 | task 70 | prompt eval time = 1241.46 ms / 131 tokens ( 9.48 ms per token, 105.52 tokens per second) 0.44.706.374 I slot print_timing: id 1 | task 70 | eval time = 40.06 ms / 2 tokens ( 40.06 ms per token, 24.96 tokens per second) 0.44.706.375 I slot print_timing: id 1 | task 70 | total time = 1281.52 ms / 133 tokens 0.44.706.375 I slot print_timing: id 1 | task 70 | graphs reused = 1 0.44.706.375 I slot print_timing: id 1 | task 70 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.706.388 I slot release: id 1 | task 70 | stop processing: n_tokens = 132, truncated = 0 0.44.706.698 I slot print_timing: id 2 | task 72 | prompt eval time = 1241.73 ms / 164 tokens ( 7.57 ms per token, 132.07 tokens per second) 0.44.706.701 I slot print_timing: id 2 | task 72 | eval time = 40.10 ms / 2 tokens ( 40.10 ms per token, 24.94 tokens per second) 0.44.706.701 I slot print_timing: id 2 | task 72 | total time = 1281.83 ms / 166 tokens 0.44.706.702 I slot print_timing: id 2 | task 72 | graphs reused = 1 0.44.706.702 I slot print_timing: id 2 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.706.716 I slot release: id 2 | task 72 | stop processing: n_tokens = 165, truncated = 0 0.44.707.010 I slot print_timing: id 3 | task 73 | prompt eval time = 1242.09 ms / 111 tokens ( 11.19 ms per token, 89.37 tokens per second) 0.44.707.013 I slot print_timing: id 3 | task 73 | eval time = 40.04 ms / 2 tokens ( 40.04 ms per token, 24.98 tokens per second) 0.44.707.013 I slot print_timing: id 3 | task 73 | total time = 1282.13 ms / 113 tokens 0.44.707.013 I slot print_timing: id 3 | task 73 | graphs reused = 1 0.44.707.014 I slot print_timing: id 3 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.707.031 I slot release: id 3 | task 73 | stop processing: n_tokens = 112, truncated = 0 0.44.711.300 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.270 (> 0.100 thold), f_keep = 0.186 0.44.711.815 I slot launch_slot_: id 0 | task 77 | processing task, is_child = 0 0.44.712.779 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.220 0.44.712.812 I slot launch_slot_: id 1 | task 79 | processing task, is_child = 0 0.44.712.845 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.176 0.44.712.876 I slot launch_slot_: id 2 | task 80 | processing task, is_child = 0 0.44.712.893 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.259 0.44.712.921 I slot launch_slot_: id 3 | task 78 | processing task, is_child = 0 0.45.782.390 I slot print_timing: id 0 | task 77 | prompt eval time = 1029.33 ms / 111 tokens ( 9.27 ms per token, 107.84 tokens per second) 0.45.782.393 I slot print_timing: id 0 | task 77 | eval time = 40.13 ms / 2 tokens ( 40.13 ms per token, 24.92 tokens per second) 0.45.782.393 I slot print_timing: id 0 | task 77 | total time = 1069.46 ms / 113 tokens 0.45.782.394 I slot print_timing: id 0 | task 77 | graphs reused = 1 0.45.782.394 I slot print_timing: id 0 | task 77 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.782.413 I slot release: id 0 | task 77 | stop processing: n_tokens = 112, truncated = 0 0.45.782.695 I slot print_timing: id 1 | task 79 | prompt eval time = 1029.62 ms / 112 tokens ( 9.19 ms per token, 108.78 tokens per second) 0.45.782.698 I slot print_timing: id 1 | task 79 | eval time = 40.14 ms / 2 tokens ( 40.14 ms per token, 24.91 tokens per second) 0.45.782.699 I slot print_timing: id 1 | task 79 | total time = 1069.76 ms / 114 tokens 0.45.782.699 I slot print_timing: id 1 | task 79 | graphs reused = 1 0.45.782.699 I slot print_timing: id 1 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.782.716 I slot release: id 1 | task 79 | stop processing: n_tokens = 113, truncated = 0 0.45.783.001 I slot print_timing: id 2 | task 80 | prompt eval time = 1029.92 ms / 166 tokens ( 6.20 ms per token, 161.18 tokens per second) 0.45.783.003 I slot print_timing: id 2 | task 80 | eval time = 40.13 ms / 2 tokens ( 40.13 ms per token, 24.92 tokens per second) 0.45.783.003 I slot print_timing: id 2 | task 80 | total time = 1070.05 ms / 168 tokens 0.45.783.004 I slot print_timing: id 2 | task 80 | graphs reused = 1 0.45.783.004 I slot print_timing: id 2 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.783.017 I slot release: id 2 | task 80 | stop processing: n_tokens = 167, truncated = 0 0.45.783.340 I slot print_timing: id 3 | task 78 | prompt eval time = 1030.22 ms / 166 tokens ( 6.21 ms per token, 161.13 tokens per second) 0.45.783.344 I slot print_timing: id 3 | task 78 | eval time = 40.16 ms / 2 tokens ( 40.16 ms per token, 24.90 tokens per second) 0.45.783.344 I slot print_timing: id 3 | task 78 | total time = 1070.38 ms / 168 tokens 0.45.783.344 I slot print_timing: id 3 | task 78 | graphs reused = 1 0.45.783.344 I slot print_timing: id 3 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.783.364 I slot release: id 3 | task 78 | stop processing: n_tokens = 167, truncated = 0 0.45.787.762 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.259 0.45.788.185 I slot launch_slot_: id 0 | task 84 | processing task, is_child = 0 0.45.789.333 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.257 0.45.789.479 I slot launch_slot_: id 1 | task 86 | processing task, is_child = 0 0.45.789.517 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.174 0.45.789.546 I slot launch_slot_: id 2 | task 85 | processing task, is_child = 0 0.45.789.565 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.174 0.45.789.595 I slot launch_slot_: id 3 | task 87 | processing task, is_child = 0 0.46.807.178 I slot print_timing: id 0 | task 84 | prompt eval time = 977.50 ms / 133 tokens ( 7.35 ms per token, 136.06 tokens per second) 0.46.807.180 I slot print_timing: id 0 | task 84 | eval time = 40.08 ms / 2 tokens ( 40.08 ms per token, 24.95 tokens per second) 0.46.807.181 I slot print_timing: id 0 | task 84 | total time = 1017.58 ms / 135 tokens 0.46.807.182 I slot print_timing: id 0 | task 84 | graphs reused = 1 0.46.807.182 I slot print_timing: id 0 | task 84 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.807.210 I slot release: id 0 | task 84 | stop processing: n_tokens = 134, truncated = 0 0.46.807.494 I slot print_timing: id 1 | task 86 | prompt eval time = 977.78 ms / 127 tokens ( 7.70 ms per token, 129.89 tokens per second) 0.46.807.499 I slot print_timing: id 1 | task 86 | eval time = 40.10 ms / 2 tokens ( 40.10 ms per token, 24.93 tokens per second) 0.46.807.499 I slot print_timing: id 1 | task 86 | total time = 1017.88 ms / 129 tokens 0.46.807.500 I slot print_timing: id 1 | task 86 | graphs reused = 1 0.46.807.500 I slot print_timing: id 1 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.807.512 I slot release: id 1 | task 86 | stop processing: n_tokens = 128, truncated = 0 0.46.807.786 I slot print_timing: id 2 | task 85 | prompt eval time = 978.07 ms / 145 tokens ( 6.75 ms per token, 148.25 tokens per second) 0.46.807.788 I slot print_timing: id 2 | task 85 | eval time = 40.10 ms / 2 tokens ( 40.10 ms per token, 24.94 tokens per second) 0.46.807.789 I slot print_timing: id 2 | task 85 | total time = 1018.17 ms / 147 tokens 0.46.807.789 I slot print_timing: id 2 | task 85 | graphs reused = 1 0.46.807.789 I slot print_timing: id 2 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.807.799 I slot release: id 2 | task 85 | stop processing: n_tokens = 146, truncated = 0 0.46.808.092 I slot print_timing: id 3 | task 87 | prompt eval time = 978.38 ms / 122 tokens ( 8.02 ms per token, 124.70 tokens per second) 0.46.808.094 I slot print_timing: id 3 | task 87 | eval time = 40.08 ms / 2 tokens ( 40.08 ms per token, 24.95 tokens per second) 0.46.808.095 I slot print_timing: id 3 | task 87 | total time = 1018.46 ms / 124 tokens 0.46.808.095 I slot print_timing: id 3 | task 87 | graphs reused = 1 0.46.808.095 I slot print_timing: id 3 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.808.104 I slot release: id 3 | task 87 | stop processing: n_tokens = 123, truncated = 0 0.46.812.021 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.216 0.46.812.368 I slot launch_slot_: id 0 | task 91 | processing task, is_child = 0 0.46.813.325 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.234 0.46.813.469 I slot launch_slot_: id 1 | task 92 | processing task, is_child = 0 0.46.813.502 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.199 0.46.813.628 I slot launch_slot_: id 2 | task 93 | processing task, is_child = 0 0.46.813.648 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.236 0.46.813.769 I slot launch_slot_: id 3 | task 94 | processing task, is_child = 0 0.47.852.222 I slot print_timing: id 0 | task 91 | prompt eval time = 998.59 ms / 126 tokens ( 7.93 ms per token, 126.18 tokens per second) 0.47.852.224 I slot print_timing: id 0 | task 91 | eval time = 39.86 ms / 2 tokens ( 39.86 ms per token, 25.09 tokens per second) 0.47.852.225 I slot print_timing: id 0 | task 91 | total time = 1038.44 ms / 128 tokens 0.47.852.225 I slot print_timing: id 0 | task 91 | graphs reused = 1 0.47.852.226 I slot print_timing: id 0 | task 91 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.852.247 I slot release: id 0 | task 91 | stop processing: n_tokens = 127, truncated = 0 0.47.852.626 I slot print_timing: id 1 | task 92 | prompt eval time = 998.93 ms / 133 tokens ( 7.51 ms per token, 133.14 tokens per second) 0.47.852.628 I slot print_timing: id 1 | task 92 | eval time = 39.91 ms / 2 tokens ( 39.91 ms per token, 25.06 tokens per second) 0.47.852.629 I slot print_timing: id 1 | task 92 | total time = 1038.84 ms / 135 tokens 0.47.852.629 I slot print_timing: id 1 | task 92 | graphs reused = 1 0.47.852.629 I slot print_timing: id 1 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.852.645 I slot release: id 1 | task 92 | stop processing: n_tokens = 134, truncated = 0 0.47.852.935 I slot print_timing: id 2 | task 93 | prompt eval time = 999.22 ms / 146 tokens ( 6.84 ms per token, 146.11 tokens per second) 0.47.852.940 I slot print_timing: id 2 | task 93 | eval time = 39.92 ms / 2 tokens ( 39.92 ms per token, 25.05 tokens per second) 0.47.852.940 I slot print_timing: id 2 | task 93 | total time = 1039.14 ms / 148 tokens 0.47.852.941 I slot print_timing: id 2 | task 93 | graphs reused = 1 0.47.852.941 I slot print_timing: id 2 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.852.955 I slot release: id 2 | task 93 | stop processing: n_tokens = 147, truncated = 0 0.47.853.270 I slot print_timing: id 3 | task 94 | prompt eval time = 999.53 ms / 140 tokens ( 7.14 ms per token, 140.07 tokens per second) 0.47.853.271 I slot print_timing: id 3 | task 94 | eval time = 39.93 ms / 2 tokens ( 39.93 ms per token, 25.04 tokens per second) 0.47.853.272 I slot print_timing: id 3 | task 94 | total time = 1039.46 ms / 142 tokens 0.47.853.272 I slot print_timing: id 3 | task 94 | graphs reused = 1 0.47.853.272 I slot print_timing: id 3 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.853.296 I slot release: id 3 | task 94 | stop processing: n_tokens = 141, truncated = 0 0.47.856.785 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.228 0.47.856.999 I slot launch_slot_: id 0 | task 98 | processing task, is_child = 0 0.47.858.047 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.213 0.47.858.079 I slot launch_slot_: id 3 | task 99 | processing task, is_child = 0 0.47.858.112 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.224 0.47.858.142 I slot launch_slot_: id 1 | task 100 | processing task, is_child = 0 0.47.858.160 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.204 0.47.858.190 I slot launch_slot_: id 2 | task 101 | processing task, is_child = 0 0.48.945.189 I slot print_timing: id 0 | task 98 | prompt eval time = 1047.01 ms / 123 tokens ( 8.51 ms per token, 117.48 tokens per second) 0.48.945.191 I slot print_timing: id 0 | task 98 | eval time = 39.99 ms / 2 tokens ( 39.99 ms per token, 25.01 tokens per second) 0.48.945.191 I slot print_timing: id 0 | task 98 | total time = 1086.99 ms / 125 tokens 0.48.945.192 I slot print_timing: id 0 | task 98 | graphs reused = 1 0.48.945.192 I slot print_timing: id 0 | task 98 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.945.218 I slot release: id 0 | task 98 | stop processing: n_tokens = 124, truncated = 0 0.48.945.482 I slot print_timing: id 1 | task 100 | prompt eval time = 1047.27 ms / 120 tokens ( 8.73 ms per token, 114.58 tokens per second) 0.48.945.484 I slot print_timing: id 1 | task 100 | eval time = 40.01 ms / 2 tokens ( 40.01 ms per token, 24.99 tokens per second) 0.48.945.484 I slot print_timing: id 1 | task 100 | total time = 1087.27 ms / 122 tokens 0.48.945.484 I slot print_timing: id 1 | task 100 | graphs reused = 1 0.48.945.485 I slot print_timing: id 1 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.945.498 I slot release: id 1 | task 100 | stop processing: n_tokens = 121, truncated = 0 0.48.945.770 I slot print_timing: id 2 | task 101 | prompt eval time = 1047.54 ms / 110 tokens ( 9.52 ms per token, 105.01 tokens per second) 0.48.945.773 I slot print_timing: id 2 | task 101 | eval time = 40.01 ms / 2 tokens ( 40.01 ms per token, 25.00 tokens per second) 0.48.945.773 I slot print_timing: id 2 | task 101 | total time = 1087.55 ms / 112 tokens 0.48.945.773 I slot print_timing: id 2 | task 101 | graphs reused = 1 0.48.945.774 I slot print_timing: id 2 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.945.789 I slot release: id 2 | task 101 | stop processing: n_tokens = 111, truncated = 0 0.48.946.093 I slot print_timing: id 3 | task 99 | prompt eval time = 1047.87 ms / 171 tokens ( 6.13 ms per token, 163.19 tokens per second) 0.48.946.095 I slot print_timing: id 3 | task 99 | eval time = 39.99 ms / 2 tokens ( 39.99 ms per token, 25.00 tokens per second) 0.48.946.095 I slot print_timing: id 3 | task 99 | total time = 1087.86 ms / 173 tokens 0.48.946.095 I slot print_timing: id 3 | task 99 | graphs reused = 1 0.48.946.096 I slot print_timing: id 3 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.946.109 I slot release: id 3 | task 99 | stop processing: n_tokens = 172, truncated = 0 0.48.950.282 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.256 (> 0.100 thold), f_keep = 0.248 0.48.950.660 I slot launch_slot_: id 1 | task 105 | processing task, is_child = 0 0.48.951.507 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.125 (> 0.100 thold), f_keep = 0.234 0.48.951.542 I slot launch_slot_: id 0 | task 106 | processing task, is_child = 0 0.48.951.576 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.261 0.48.951.607 I slot launch_slot_: id 2 | task 107 | processing task, is_child = 0 0.48.951.626 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.169 0.48.951.789 I slot launch_slot_: id 3 | task 108 | processing task, is_child = 0 0.50.339.724 I slot print_timing: id 0 | task 106 | prompt eval time = 1347.71 ms / 232 tokens ( 5.81 ms per token, 172.14 tokens per second) 0.50.339.727 I slot print_timing: id 0 | task 106 | eval time = 40.22 ms / 2 tokens ( 40.22 ms per token, 24.86 tokens per second) 0.50.339.727 I slot print_timing: id 0 | task 106 | total time = 1387.93 ms / 234 tokens 0.50.339.728 I slot print_timing: id 0 | task 106 | graphs reused = 1 0.50.339.728 I slot print_timing: id 0 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.339.752 I slot release: id 0 | task 106 | stop processing: n_tokens = 233, truncated = 0 0.50.340.015 I slot print_timing: id 1 | task 105 | prompt eval time = 1347.97 ms / 117 tokens ( 11.52 ms per token, 86.80 tokens per second) 0.50.340.017 I slot print_timing: id 1 | task 105 | eval time = 40.24 ms / 2 tokens ( 40.24 ms per token, 24.85 tokens per second) 0.50.340.017 I slot print_timing: id 1 | task 105 | total time = 1388.21 ms / 119 tokens 0.50.340.017 I slot print_timing: id 1 | task 105 | graphs reused = 1 0.50.340.018 I slot print_timing: id 1 | task 105 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.340.029 I slot release: id 1 | task 105 | stop processing: n_tokens = 118, truncated = 0 0.50.340.307 I slot print_timing: id 2 | task 107 | prompt eval time = 1348.24 ms / 176 tokens ( 7.66 ms per token, 130.54 tokens per second) 0.50.340.310 I slot print_timing: id 2 | task 107 | eval time = 40.25 ms / 2 tokens ( 40.25 ms per token, 24.85 tokens per second) 0.50.340.310 I slot print_timing: id 2 | task 107 | total time = 1388.49 ms / 178 tokens 0.50.340.310 I slot print_timing: id 2 | task 107 | graphs reused = 1 0.50.340.311 I slot print_timing: id 2 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.340.326 I slot release: id 2 | task 107 | stop processing: n_tokens = 177, truncated = 0 0.50.340.603 I slot print_timing: id 3 | task 108 | prompt eval time = 1348.63 ms / 138 tokens ( 9.77 ms per token, 102.33 tokens per second) 0.50.340.606 I slot print_timing: id 3 | task 108 | eval time = 40.15 ms / 2 tokens ( 40.15 ms per token, 24.91 tokens per second) 0.50.340.606 I slot print_timing: id 3 | task 108 | total time = 1388.77 ms / 140 tokens 0.50.340.607 I slot print_timing: id 3 | task 108 | graphs reused = 1 0.50.340.607 I slot print_timing: id 3 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.340.619 I slot release: id 3 | task 108 | stop processing: n_tokens = 139, truncated = 0 0.50.344.810 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.263 0.50.345.235 I slot launch_slot_: id 1 | task 112 | processing task, is_child = 0 0.50.346.551 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.124 0.50.346.589 I slot launch_slot_: id 0 | task 113 | processing task, is_child = 0 0.50.346.626 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.164 0.50.346.659 I slot launch_slot_: id 2 | task 114 | processing task, is_child = 0 0.50.346.676 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.216 0.50.346.850 I slot launch_slot_: id 3 | task 115 | processing task, is_child = 0 0.51.839.495 I slot print_timing: id 0 | task 113 | prompt eval time = 1452.34 ms / 227 tokens ( 6.40 ms per token, 156.30 tokens per second) 0.51.839.497 I slot print_timing: id 0 | task 113 | eval time = 40.30 ms / 2 tokens ( 40.30 ms per token, 24.82 tokens per second) 0.51.839.497 I slot print_timing: id 0 | task 113 | total time = 1492.64 ms / 229 tokens 0.51.839.498 I slot print_timing: id 0 | task 113 | graphs reused = 1 0.51.839.498 I slot print_timing: id 0 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.839.526 I slot release: id 0 | task 113 | stop processing: n_tokens = 228, truncated = 0 0.51.839.904 I slot print_timing: id 1 | task 112 | prompt eval time = 1452.71 ms / 156 tokens ( 9.31 ms per token, 107.39 tokens per second) 0.51.839.906 I slot print_timing: id 1 | task 112 | eval time = 40.32 ms / 2 tokens ( 40.32 ms per token, 24.80 tokens per second) 0.51.839.907 I slot print_timing: id 1 | task 112 | total time = 1493.03 ms / 158 tokens 0.51.839.907 I slot print_timing: id 1 | task 112 | graphs reused = 1 0.51.839.907 I slot print_timing: id 1 | task 112 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.839.921 I slot release: id 1 | task 112 | stop processing: n_tokens = 157, truncated = 0 0.51.840.210 I slot print_timing: id 2 | task 114 | prompt eval time = 1452.97 ms / 158 tokens ( 9.20 ms per token, 108.74 tokens per second) 0.51.840.210 I slot print_timing: id 2 | task 114 | eval time = 40.35 ms / 2 tokens ( 40.35 ms per token, 24.78 tokens per second) 0.51.840.211 I slot print_timing: id 2 | task 114 | total time = 1493.33 ms / 160 tokens 0.51.840.211 I slot print_timing: id 2 | task 114 | graphs reused = 1 0.51.840.211 I slot print_timing: id 2 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.840.224 I slot release: id 2 | task 114 | stop processing: n_tokens = 159, truncated = 0 0.51.840.532 I slot print_timing: id 3 | task 115 | prompt eval time = 1453.48 ms / 143 tokens ( 10.16 ms per token, 98.38 tokens per second) 0.51.840.532 I slot print_timing: id 3 | task 115 | eval time = 40.15 ms / 2 tokens ( 40.15 ms per token, 24.90 tokens per second) 0.51.840.534 I slot print_timing: id 3 | task 115 | total time = 1493.63 ms / 145 tokens 0.51.840.535 I slot print_timing: id 3 | task 115 | graphs reused = 1 0.51.840.535 I slot print_timing: id 3 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.840.548 I slot release: id 3 | task 115 | stop processing: n_tokens = 144, truncated = 0 0.51.847.359 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.256 (> 0.100 thold), f_keep = 0.191 0.51.847.747 I slot launch_slot_: id 1 | task 119 | processing task, is_child = 0 0.51.848.864 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.153 (> 0.100 thold), f_keep = 0.127 0.51.849.026 I slot launch_slot_: id 0 | task 120 | processing task, is_child = 0 0.51.849.061 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.299 (> 0.100 thold), f_keep = 0.222 0.51.849.093 I slot launch_slot_: id 3 | task 121 | processing task, is_child = 0 0.51.849.111 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.182 0.51.849.143 I slot launch_slot_: id 2 | task 122 | processing task, is_child = 0 0.53.135.276 I slot print_timing: id 0 | task 120 | prompt eval time = 1245.98 ms / 189 tokens ( 6.59 ms per token, 151.69 tokens per second) 0.53.135.278 I slot print_timing: id 0 | task 120 | eval time = 40.15 ms / 2 tokens ( 40.15 ms per token, 24.91 tokens per second) 0.53.135.279 I slot print_timing: id 0 | task 120 | total time = 1286.13 ms / 191 tokens 0.53.135.279 I slot print_timing: id 0 | task 120 | graphs reused = 1 0.53.135.280 I slot print_timing: id 0 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.135.303 I slot release: id 0 | task 120 | stop processing: n_tokens = 190, truncated = 0 0.53.135.594 I slot print_timing: id 1 | task 119 | prompt eval time = 1246.25 ms / 117 tokens ( 10.65 ms per token, 93.88 tokens per second) 0.53.135.597 I slot print_timing: id 1 | task 119 | eval time = 40.18 ms / 2 tokens ( 40.18 ms per token, 24.89 tokens per second) 0.53.135.598 I slot print_timing: id 1 | task 119 | total time = 1286.43 ms / 119 tokens 0.53.135.598 I slot print_timing: id 1 | task 119 | graphs reused = 1 0.53.135.599 I slot print_timing: id 1 | task 119 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.135.614 I slot release: id 1 | task 119 | stop processing: n_tokens = 118, truncated = 0 0.53.135.911 I slot print_timing: id 2 | task 122 | prompt eval time = 1246.53 ms / 143 tokens ( 8.72 ms per token, 114.72 tokens per second) 0.53.135.913 I slot print_timing: id 2 | task 122 | eval time = 40.21 ms / 2 tokens ( 40.21 ms per token, 24.87 tokens per second) 0.53.135.913 I slot print_timing: id 2 | task 122 | total time = 1286.74 ms / 145 tokens 0.53.135.913 I slot print_timing: id 2 | task 122 | graphs reused = 1 0.53.135.914 I slot print_timing: id 2 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.135.933 I slot release: id 2 | task 122 | stop processing: n_tokens = 144, truncated = 0 0.53.136.212 I slot print_timing: id 3 | task 121 | prompt eval time = 1246.95 ms / 107 tokens ( 11.65 ms per token, 85.81 tokens per second) 0.53.136.214 I slot print_timing: id 3 | task 121 | eval time = 40.07 ms / 2 tokens ( 40.07 ms per token, 24.95 tokens per second) 0.53.136.215 I slot print_timing: id 3 | task 121 | total time = 1287.03 ms / 109 tokens 0.53.136.215 I slot print_timing: id 3 | task 121 | graphs reused = 1 0.53.136.215 I slot print_timing: id 3 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.136.228 I slot release: id 3 | task 121 | stop processing: n_tokens = 108, truncated = 0 0.53.140.573 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.153 0.53.141.016 I slot launch_slot_: id 0 | task 126 | processing task, is_child = 0 0.53.141.712 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.254 0.53.141.754 I slot launch_slot_: id 1 | task 127 | processing task, is_child = 0 0.53.141.787 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.201 0.53.141.816 I slot launch_slot_: id 2 | task 128 | processing task, is_child = 0 0.53.141.834 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.244 (> 0.100 thold), f_keep = 0.278 0.53.141.862 I slot launch_slot_: id 3 | task 129 | processing task, is_child = 0 0.54.329.558 I slot print_timing: id 0 | task 126 | prompt eval time = 1147.72 ms / 173 tokens ( 6.63 ms per token, 150.73 tokens per second) 0.54.329.560 I slot print_timing: id 0 | task 126 | eval time = 39.97 ms / 2 tokens ( 39.97 ms per token, 25.02 tokens per second) 0.54.329.561 I slot print_timing: id 0 | task 126 | total time = 1187.69 ms / 175 tokens 0.54.329.561 I slot print_timing: id 0 | task 126 | graphs reused = 1 0.54.329.562 I slot print_timing: id 0 | task 126 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.329.589 I slot release: id 0 | task 126 | stop processing: n_tokens = 174, truncated = 0 0.54.329.873 I slot print_timing: id 1 | task 127 | prompt eval time = 1147.97 ms / 110 tokens ( 10.44 ms per token, 95.82 tokens per second) 0.54.329.875 I slot print_timing: id 1 | task 127 | eval time = 40.02 ms / 2 tokens ( 40.02 ms per token, 24.99 tokens per second) 0.54.329.875 I slot print_timing: id 1 | task 127 | total time = 1187.99 ms / 112 tokens 0.54.329.875 I slot print_timing: id 1 | task 127 | graphs reused = 1 0.54.329.876 I slot print_timing: id 1 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.329.892 I slot release: id 1 | task 127 | stop processing: n_tokens = 111, truncated = 0 0.54.330.167 I slot print_timing: id 2 | task 128 | prompt eval time = 1148.24 ms / 138 tokens ( 8.32 ms per token, 120.18 tokens per second) 0.54.330.173 I slot print_timing: id 2 | task 128 | eval time = 40.03 ms / 2 tokens ( 40.03 ms per token, 24.98 tokens per second) 0.54.330.173 I slot print_timing: id 2 | task 128 | total time = 1188.27 ms / 140 tokens 0.54.330.173 I slot print_timing: id 2 | task 128 | graphs reused = 1 0.54.330.174 I slot print_timing: id 2 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.330.186 I slot release: id 2 | task 128 | stop processing: n_tokens = 139, truncated = 0 0.54.330.478 I slot print_timing: id 3 | task 129 | prompt eval time = 1148.55 ms / 123 tokens ( 9.34 ms per token, 107.09 tokens per second) 0.54.330.480 I slot print_timing: id 3 | task 129 | eval time = 40.03 ms / 2 tokens ( 40.03 ms per token, 24.98 tokens per second) 0.54.330.481 I slot print_timing: id 3 | task 129 | total time = 1188.57 ms / 125 tokens 0.54.330.481 I slot print_timing: id 3 | task 129 | graphs reused = 1 0.54.330.481 I slot print_timing: id 3 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.330.497 I slot release: id 3 | task 129 | stop processing: n_tokens = 124, truncated = 0 0.54.335.090 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.167 0.54.335.628 I slot launch_slot_: id 0 | task 136 | processing task, is_child = 0 0.54.336.612 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.270 0.54.336.779 I slot launch_slot_: id 1 | task 135 | processing task, is_child = 0 0.54.336.818 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.209 0.54.336.850 I slot launch_slot_: id 2 | task 134 | processing task, is_child = 0 0.54.336.867 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.234 0.54.336.895 I slot launch_slot_: id 3 | task 133 | processing task, is_child = 0 0.55.499.193 I slot print_timing: id 0 | task 136 | prompt eval time = 1121.89 ms / 136 tokens ( 8.25 ms per token, 121.22 tokens per second) 0.55.499.198 I slot print_timing: id 0 | task 136 | eval time = 40.40 ms / 2 tokens ( 40.40 ms per token, 24.75 tokens per second) 0.55.499.198 I slot print_timing: id 0 | task 136 | total time = 1162.29 ms / 138 tokens 0.55.499.199 I slot print_timing: id 0 | task 136 | graphs reused = 1 0.55.499.199 I slot print_timing: id 0 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.499.219 I slot release: id 0 | task 136 | stop processing: n_tokens = 137, truncated = 0 0.55.499.498 I slot print_timing: id 1 | task 135 | prompt eval time = 1122.15 ms / 122 tokens ( 9.20 ms per token, 108.72 tokens per second) 0.55.499.502 I slot print_timing: id 1 | task 135 | eval time = 40.43 ms / 2 tokens ( 40.43 ms per token, 24.74 tokens per second) 0.55.499.503 I slot print_timing: id 1 | task 135 | total time = 1162.58 ms / 124 tokens 0.55.499.503 I slot print_timing: id 1 | task 135 | graphs reused = 1 0.55.499.503 I slot print_timing: id 1 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.499.520 I slot release: id 1 | task 135 | stop processing: n_tokens = 123, truncated = 0 0.55.499.811 I slot print_timing: id 2 | task 134 | prompt eval time = 1122.43 ms / 161 tokens ( 6.97 ms per token, 143.44 tokens per second) 0.55.499.813 I slot print_timing: id 2 | task 134 | eval time = 40.44 ms / 2 tokens ( 40.44 ms per token, 24.73 tokens per second) 0.55.499.813 I slot print_timing: id 2 | task 134 | total time = 1162.88 ms / 163 tokens 0.55.499.813 I slot print_timing: id 2 | task 134 | graphs reused = 1 0.55.499.814 I slot print_timing: id 2 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.499.832 I slot release: id 2 | task 134 | stop processing: n_tokens = 162, truncated = 0 0.55.500.140 I slot print_timing: id 3 | task 133 | prompt eval time = 1122.83 ms / 134 tokens ( 8.38 ms per token, 119.34 tokens per second) 0.55.500.143 I slot print_timing: id 3 | task 133 | eval time = 40.36 ms / 2 tokens ( 40.36 ms per token, 24.78 tokens per second) 0.55.500.144 I slot print_timing: id 3 | task 133 | total time = 1163.18 ms / 136 tokens 0.55.500.144 I slot print_timing: id 3 | task 133 | graphs reused = 1 0.55.500.145 I slot print_timing: id 3 | task 133 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.500.155 I slot release: id 3 | task 133 | stop processing: n_tokens = 135, truncated = 0 0.55.503.977 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.212 0.55.504.415 I slot launch_slot_: id 0 | task 140 | processing task, is_child = 0 0.55.505.550 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.236 0.55.505.586 I slot launch_slot_: id 1 | task 141 | processing task, is_child = 0 0.55.505.620 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.179 0.55.505.651 I slot launch_slot_: id 2 | task 142 | processing task, is_child = 0 0.55.505.670 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.170 (> 0.100 thold), f_keep = 0.215 0.55.505.699 I slot launch_slot_: id 3 | task 143 | processing task, is_child = 0 0.56.766.338 I slot print_timing: id 0 | task 140 | prompt eval time = 1219.86 ms / 175 tokens ( 6.97 ms per token, 143.46 tokens per second) 0.56.766.341 I slot print_timing: id 0 | task 140 | eval time = 40.77 ms / 2 tokens ( 40.77 ms per token, 24.53 tokens per second) 0.56.766.341 I slot print_timing: id 0 | task 140 | total time = 1260.63 ms / 177 tokens 0.56.766.342 I slot print_timing: id 0 | task 140 | graphs reused = 1 0.56.766.342 I slot print_timing: id 0 | task 140 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.766.367 I slot release: id 0 | task 140 | stop processing: n_tokens = 176, truncated = 0 0.56.766.650 I slot print_timing: id 1 | task 141 | prompt eval time = 1220.21 ms / 181 tokens ( 6.74 ms per token, 148.34 tokens per second) 0.56.766.652 I slot print_timing: id 1 | task 141 | eval time = 40.72 ms / 2 tokens ( 40.72 ms per token, 24.56 tokens per second) 0.56.766.652 I slot print_timing: id 1 | task 141 | total time = 1260.93 ms / 183 tokens 0.56.766.652 I slot print_timing: id 1 | task 141 | graphs reused = 1 0.56.766.653 I slot print_timing: id 1 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.766.669 I slot release: id 1 | task 141 | stop processing: n_tokens = 182, truncated = 0 0.56.766.950 I slot print_timing: id 2 | task 142 | prompt eval time = 1220.62 ms / 131 tokens ( 9.32 ms per token, 107.32 tokens per second) 0.56.766.952 I slot print_timing: id 2 | task 142 | eval time = 40.60 ms / 2 tokens ( 40.60 ms per token, 24.63 tokens per second) 0.56.766.952 I slot print_timing: id 2 | task 142 | total time = 1261.22 ms / 133 tokens 0.56.766.953 I slot print_timing: id 2 | task 142 | graphs reused = 1 0.56.766.953 I slot print_timing: id 2 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.766.972 I slot release: id 2 | task 142 | stop processing: n_tokens = 132, truncated = 0 0.56.767.285 I slot print_timing: id 3 | task 143 | prompt eval time = 1221.13 ms / 171 tokens ( 7.14 ms per token, 140.03 tokens per second) 0.56.767.287 I slot print_timing: id 3 | task 143 | eval time = 40.41 ms / 2 tokens ( 40.41 ms per token, 24.75 tokens per second) 0.56.767.287 I slot print_timing: id 3 | task 143 | total time = 1261.54 ms / 173 tokens 0.56.767.288 I slot print_timing: id 3 | task 143 | graphs reused = 1 0.56.767.288 I slot print_timing: id 3 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.767.304 I slot release: id 3 | task 143 | stop processing: n_tokens = 172, truncated = 0 0.56.771.139 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.165 0.56.771.711 I slot launch_slot_: id 0 | task 147 | processing task, is_child = 0 0.56.772.912 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.159 0.56.773.078 I slot launch_slot_: id 1 | task 148 | processing task, is_child = 0 0.56.773.124 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.220 0.56.773.159 I slot launch_slot_: id 2 | task 149 | processing task, is_child = 0 0.56.773.178 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.169 0.56.773.326 I slot launch_slot_: id 3 | task 150 | processing task, is_child = 0 0.57.648.684 I slot print_timing: id 0 | task 147 | prompt eval time = 835.19 ms / 115 tokens ( 7.26 ms per token, 137.69 tokens per second) 0.57.648.686 I slot print_timing: id 0 | task 147 | eval time = 40.16 ms / 2 tokens ( 40.16 ms per token, 24.90 tokens per second) 0.57.648.687 I slot print_timing: id 0 | task 147 | total time = 875.35 ms / 117 tokens 0.57.648.687 I slot print_timing: id 0 | task 147 | graphs reused = 1 0.57.648.688 I slot print_timing: id 0 | task 147 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.648.709 I slot release: id 0 | task 147 | stop processing: n_tokens = 116, truncated = 0 0.57.649.069 I slot print_timing: id 1 | task 148 | prompt eval time = 835.53 ms / 116 tokens ( 7.20 ms per token, 138.83 tokens per second) 0.57.649.076 I slot print_timing: id 1 | task 148 | eval time = 40.19 ms / 2 tokens ( 40.19 ms per token, 24.88 tokens per second) 0.57.649.077 I slot print_timing: id 1 | task 148 | total time = 875.72 ms / 118 tokens 0.57.649.078 I slot print_timing: id 1 | task 148 | graphs reused = 1 0.57.649.078 I slot print_timing: id 1 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.649.090 I slot release: id 1 | task 148 | stop processing: n_tokens = 117, truncated = 0 0.57.649.354 I slot print_timing: id 2 | task 149 | prompt eval time = 835.80 ms / 125 tokens ( 6.69 ms per token, 149.56 tokens per second) 0.57.649.358 I slot print_timing: id 2 | task 149 | eval time = 40.20 ms / 2 tokens ( 40.20 ms per token, 24.88 tokens per second) 0.57.649.358 I slot print_timing: id 2 | task 149 | total time = 876.00 ms / 127 tokens 0.57.649.358 I slot print_timing: id 2 | task 149 | graphs reused = 1 0.57.649.359 I slot print_timing: id 2 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.649.369 I slot release: id 2 | task 149 | stop processing: n_tokens = 126, truncated = 0 0.57.649.662 I slot print_timing: id 3 | task 150 | prompt eval time = 836.13 ms / 123 tokens ( 6.80 ms per token, 147.11 tokens per second) 0.57.649.665 I slot print_timing: id 3 | task 150 | eval time = 40.16 ms / 2 tokens ( 40.16 ms per token, 24.90 tokens per second) 0.57.649.666 I slot print_timing: id 3 | task 150 | total time = 876.30 ms / 125 tokens 0.57.649.666 I slot print_timing: id 3 | task 150 | graphs reused = 1 0.57.649.667 I slot print_timing: id 3 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.649.675 I slot release: id 3 | task 150 | stop processing: n_tokens = 124, truncated = 0 0.57.653.241 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.250 0.57.653.486 I slot launch_slot_: id 0 | task 154 | processing task, is_child = 0 0.57.654.281 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.223 (> 0.100 thold), f_keep = 0.248 0.57.654.316 I slot launch_slot_: id 1 | task 155 | processing task, is_child = 0 0.57.654.349 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.242 0.57.654.487 I slot launch_slot_: id 3 | task 156 | processing task, is_child = 0 0.57.654.505 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.223 (> 0.100 thold), f_keep = 0.230 0.57.654.650 I slot launch_slot_: id 2 | task 157 | processing task, is_child = 0 0.58.553.005 I slot print_timing: id 0 | task 154 | prompt eval time = 858.04 ms / 143 tokens ( 6.00 ms per token, 166.66 tokens per second) 0.58.553.009 I slot print_timing: id 0 | task 154 | eval time = 40.31 ms / 2 tokens ( 40.31 ms per token, 24.81 tokens per second) 0.58.553.009 I slot print_timing: id 0 | task 154 | total time = 898.35 ms / 145 tokens 0.58.553.010 I slot print_timing: id 0 | task 154 | graphs reused = 1 0.58.553.010 I slot print_timing: id 0 | task 154 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.553.033 I slot release: id 0 | task 154 | stop processing: n_tokens = 144, truncated = 0 0.58.553.311 I slot print_timing: id 1 | task 155 | prompt eval time = 858.31 ms / 130 tokens ( 6.60 ms per token, 151.46 tokens per second) 0.58.553.315 I slot print_timing: id 1 | task 155 | eval time = 40.34 ms / 2 tokens ( 40.34 ms per token, 24.79 tokens per second) 0.58.553.316 I slot print_timing: id 1 | task 155 | total time = 898.64 ms / 132 tokens 0.58.553.316 I slot print_timing: id 1 | task 155 | graphs reused = 1 0.58.553.316 I slot print_timing: id 1 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.553.333 I slot release: id 1 | task 155 | stop processing: n_tokens = 131, truncated = 0 0.58.553.625 I slot print_timing: id 2 | task 157 | prompt eval time = 858.60 ms / 130 tokens ( 6.60 ms per token, 151.41 tokens per second) 0.58.553.627 I slot print_timing: id 2 | task 157 | eval time = 40.35 ms / 2 tokens ( 40.35 ms per token, 24.79 tokens per second) 0.58.553.627 I slot print_timing: id 2 | task 157 | total time = 898.95 ms / 132 tokens 0.58.553.627 I slot print_timing: id 2 | task 157 | graphs reused = 1 0.58.553.627 I slot print_timing: id 2 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.553.649 I slot release: id 2 | task 157 | stop processing: n_tokens = 131, truncated = 0 0.58.554.048 I slot print_timing: id 3 | task 156 | prompt eval time = 858.99 ms / 129 tokens ( 6.66 ms per token, 150.18 tokens per second) 0.58.554.050 I slot print_timing: id 3 | task 156 | eval time = 40.37 ms / 2 tokens ( 40.37 ms per token, 24.77 tokens per second) 0.58.554.051 I slot print_timing: id 3 | task 156 | total time = 899.36 ms / 131 tokens 0.58.554.051 I slot print_timing: id 3 | task 156 | graphs reused = 1 0.58.554.051 I slot print_timing: id 3 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.554.066 I slot release: id 3 | task 156 | stop processing: n_tokens = 130, truncated = 0 0.58.557.913 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.225 (> 0.100 thold), f_keep = 0.201 0.58.558.369 I slot launch_slot_: id 0 | task 161 | processing task, is_child = 0 0.58.559.425 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.286 (> 0.100 thold), f_keep = 0.231 0.58.559.463 I slot launch_slot_: id 3 | task 162 | processing task, is_child = 0 0.58.559.496 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.221 0.58.559.526 I slot launch_slot_: id 1 | task 163 | processing task, is_child = 0 0.58.559.544 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.221 0.58.559.573 I slot launch_slot_: id 2 | task 164 | processing task, is_child = 0 0.59.706.322 I slot print_timing: id 0 | task 161 | prompt eval time = 1106.82 ms / 129 tokens ( 8.58 ms per token, 116.55 tokens per second) 0.59.706.324 I slot print_timing: id 0 | task 161 | eval time = 39.92 ms / 2 tokens ( 39.92 ms per token, 25.05 tokens per second) 0.59.706.325 I slot print_timing: id 0 | task 161 | total time = 1146.74 ms / 131 tokens 0.59.706.325 I slot print_timing: id 0 | task 161 | graphs reused = 1 0.59.706.326 I slot print_timing: id 0 | task 161 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.706.354 I slot release: id 0 | task 161 | stop processing: n_tokens = 130, truncated = 0 0.59.706.653 I slot print_timing: id 1 | task 163 | prompt eval time = 1107.10 ms / 161 tokens ( 6.88 ms per token, 145.43 tokens per second) 0.59.706.655 I slot print_timing: id 1 | task 163 | eval time = 39.96 ms / 2 tokens ( 39.96 ms per token, 25.03 tokens per second) 0.59.706.656 I slot print_timing: id 1 | task 163 | total time = 1147.06 ms / 163 tokens 0.59.706.656 I slot print_timing: id 1 | task 163 | graphs reused = 1 0.59.706.656 I slot print_timing: id 1 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.706.673 I slot release: id 1 | task 163 | stop processing: n_tokens = 162, truncated = 0 0.59.706.957 I slot print_timing: id 2 | task 164 | prompt eval time = 1107.37 ms / 124 tokens ( 8.93 ms per token, 111.98 tokens per second) 0.59.706.959 I slot print_timing: id 2 | task 164 | eval time = 39.98 ms / 2 tokens ( 39.98 ms per token, 25.01 tokens per second) 0.59.706.960 I slot print_timing: id 2 | task 164 | total time = 1147.35 ms / 126 tokens 0.59.706.960 I slot print_timing: id 2 | task 164 | graphs reused = 1 0.59.706.960 I slot print_timing: id 2 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.706.971 I slot release: id 2 | task 164 | stop processing: n_tokens = 125, truncated = 0 0.59.707.275 I slot print_timing: id 3 | task 162 | prompt eval time = 1107.67 ms / 105 tokens ( 10.55 ms per token, 94.79 tokens per second) 0.59.707.282 I slot print_timing: id 3 | task 162 | eval time = 39.98 ms / 2 tokens ( 39.98 ms per token, 25.01 tokens per second) 0.59.707.282 I slot print_timing: id 3 | task 162 | total time = 1147.66 ms / 107 tokens 0.59.707.282 I slot print_timing: id 3 | task 162 | graphs reused = 1 0.59.707.283 I slot print_timing: id 3 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.707.291 I slot release: id 3 | task 162 | stop processing: n_tokens = 106, truncated = 0 0.59.711.146 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.223 0.59.711.530 I slot launch_slot_: id 0 | task 168 | processing task, is_child = 0 0.59.712.310 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.283 0.59.712.346 I slot launch_slot_: id 3 | task 169 | processing task, is_child = 0 0.59.712.379 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.179 0.59.712.517 I slot launch_slot_: id 1 | task 170 | processing task, is_child = 0 0.59.712.536 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.232 0.59.712.565 I slot launch_slot_: id 2 | task 171 | processing task, is_child = 0 1.00.915.322 I slot print_timing: id 0 | task 168 | prompt eval time = 1162.75 ms / 169 tokens ( 6.88 ms per token, 145.35 tokens per second) 1.00.915.325 I slot print_timing: id 0 | task 168 | eval time = 40.00 ms / 2 tokens ( 40.00 ms per token, 25.00 tokens per second) 1.00.915.325 I slot print_timing: id 0 | task 168 | total time = 1202.75 ms / 171 tokens 1.00.915.326 I slot print_timing: id 0 | task 168 | graphs reused = 1 1.00.915.326 I slot print_timing: id 0 | task 168 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.915.348 I slot release: id 0 | task 168 | stop processing: n_tokens = 170, truncated = 0 1.00.915.631 I slot print_timing: id 1 | task 170 | prompt eval time = 1163.03 ms / 143 tokens ( 8.13 ms per token, 122.96 tokens per second) 1.00.915.633 I slot print_timing: id 1 | task 170 | eval time = 40.02 ms / 2 tokens ( 40.02 ms per token, 24.99 tokens per second) 1.00.915.633 I slot print_timing: id 1 | task 170 | total time = 1203.05 ms / 145 tokens 1.00.915.633 I slot print_timing: id 1 | task 170 | graphs reused = 1 1.00.915.634 I slot print_timing: id 1 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.915.648 I slot release: id 1 | task 170 | stop processing: n_tokens = 144, truncated = 0 1.00.915.935 I slot print_timing: id 2 | task 171 | prompt eval time = 1163.32 ms / 155 tokens ( 7.51 ms per token, 133.24 tokens per second) 1.00.915.937 I slot print_timing: id 2 | task 171 | eval time = 40.03 ms / 2 tokens ( 40.03 ms per token, 24.98 tokens per second) 1.00.915.938 I slot print_timing: id 2 | task 171 | total time = 1203.34 ms / 157 tokens 1.00.915.938 I slot print_timing: id 2 | task 171 | graphs reused = 1 1.00.915.938 I slot print_timing: id 2 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.915.955 I slot release: id 2 | task 171 | stop processing: n_tokens = 156, truncated = 0 1.00.916.237 I slot print_timing: id 3 | task 169 | prompt eval time = 1163.61 ms / 113 tokens ( 10.30 ms per token, 97.11 tokens per second) 1.00.916.239 I slot print_timing: id 3 | task 169 | eval time = 40.03 ms / 2 tokens ( 40.03 ms per token, 24.98 tokens per second) 1.00.916.239 I slot print_timing: id 3 | task 169 | total time = 1203.64 ms / 115 tokens 1.00.916.239 I slot print_timing: id 3 | task 169 | graphs reused = 1 1.00.916.240 I slot print_timing: id 3 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.916.256 I slot release: id 3 | task 169 | stop processing: n_tokens = 114, truncated = 0 1.00.920.504 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.171 1.00.921.009 I slot launch_slot_: id 0 | task 175 | processing task, is_child = 0 1.00.921.849 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.263 1.00.921.898 I slot launch_slot_: id 3 | task 176 | processing task, is_child = 0 1.00.921.933 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.201 1.00.921.963 I slot launch_slot_: id 1 | task 177 | processing task, is_child = 0 1.00.921.982 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.186 1.00.922.011 I slot launch_slot_: id 2 | task 178 | processing task, is_child = 0 1.01.961.277 I slot print_timing: id 0 | task 175 | prompt eval time = 999.46 ms / 111 tokens ( 9.00 ms per token, 111.06 tokens per second) 1.01.961.280 I slot print_timing: id 0 | task 175 | eval time = 39.80 ms / 2 tokens ( 39.80 ms per token, 25.13 tokens per second) 1.01.961.280 I slot print_timing: id 0 | task 175 | total time = 1039.26 ms / 113 tokens 1.01.961.281 I slot print_timing: id 0 | task 175 | graphs reused = 1 1.01.961.281 I slot print_timing: id 0 | task 175 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.961.299 I slot release: id 0 | task 175 | stop processing: n_tokens = 112, truncated = 0 1.01.961.586 I slot print_timing: id 1 | task 177 | prompt eval time = 999.73 ms / 150 tokens ( 6.66 ms per token, 150.04 tokens per second) 1.01.961.587 I slot print_timing: id 1 | task 177 | eval time = 39.82 ms / 2 tokens ( 39.82 ms per token, 25.11 tokens per second) 1.01.961.588 I slot print_timing: id 1 | task 177 | total time = 1039.55 ms / 152 tokens 1.01.961.588 I slot print_timing: id 1 | task 177 | graphs reused = 1 1.01.961.589 I slot print_timing: id 1 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.961.602 I slot release: id 1 | task 177 | stop processing: n_tokens = 151, truncated = 0 1.01.961.884 I slot print_timing: id 2 | task 178 | prompt eval time = 1000.02 ms / 138 tokens ( 7.25 ms per token, 138.00 tokens per second) 1.01.961.886 I slot print_timing: id 2 | task 178 | eval time = 39.82 ms / 2 tokens ( 39.82 ms per token, 25.11 tokens per second) 1.01.961.886 I slot print_timing: id 2 | task 178 | total time = 1039.84 ms / 140 tokens 1.01.961.887 I slot print_timing: id 2 | task 178 | graphs reused = 1 1.01.961.887 I slot print_timing: id 2 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.961.901 I slot release: id 2 | task 178 | stop processing: n_tokens = 139, truncated = 0 1.01.962.175 I slot print_timing: id 3 | task 176 | prompt eval time = 1000.32 ms / 113 tokens ( 8.85 ms per token, 112.96 tokens per second) 1.01.962.177 I slot print_timing: id 3 | task 176 | eval time = 39.80 ms / 2 tokens ( 39.80 ms per token, 25.13 tokens per second) 1.01.962.177 I slot print_timing: id 3 | task 176 | total time = 1040.12 ms / 115 tokens 1.01.962.178 I slot print_timing: id 3 | task 176 | graphs reused = 1 1.01.962.178 I slot print_timing: id 3 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.962.187 I slot release: id 3 | task 176 | stop processing: n_tokens = 114, truncated = 0 1.01.965.963 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.259 1.01.966.188 I slot launch_slot_: id 0 | task 182 | processing task, is_child = 0 1.01.967.017 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.192 1.01.967.052 I slot launch_slot_: id 1 | task 183 | processing task, is_child = 0 1.01.967.085 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.209 1.01.967.223 I slot launch_slot_: id 2 | task 184 | processing task, is_child = 0 1.01.967.241 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.263 (> 0.100 thold), f_keep = 0.263 1.01.967.271 I slot launch_slot_: id 3 | task 185 | processing task, is_child = 0 1.03.075.964 I slot print_timing: id 0 | task 182 | prompt eval time = 1068.41 ms / 153 tokens ( 6.98 ms per token, 143.20 tokens per second) 1.03.075.969 I slot print_timing: id 0 | task 182 | eval time = 40.27 ms / 2 tokens ( 40.27 ms per token, 24.83 tokens per second) 1.03.075.970 I slot print_timing: id 0 | task 182 | total time = 1108.69 ms / 155 tokens 1.03.075.970 I slot print_timing: id 0 | task 182 | graphs reused = 1 1.03.075.970 I slot print_timing: id 0 | task 182 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.075.990 I slot release: id 0 | task 182 | stop processing: n_tokens = 154, truncated = 0 1.03.076.250 I slot print_timing: id 1 | task 183 | prompt eval time = 1068.67 ms / 126 tokens ( 8.48 ms per token, 117.90 tokens per second) 1.03.076.252 I slot print_timing: id 1 | task 183 | eval time = 40.29 ms / 2 tokens ( 40.29 ms per token, 24.82 tokens per second) 1.03.076.253 I slot print_timing: id 1 | task 183 | total time = 1108.97 ms / 128 tokens 1.03.076.253 I slot print_timing: id 1 | task 183 | graphs reused = 1 1.03.076.254 I slot print_timing: id 1 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.076.268 I slot release: id 1 | task 183 | stop processing: n_tokens = 127, truncated = 0 1.03.076.537 I slot print_timing: id 2 | task 184 | prompt eval time = 1068.94 ms / 131 tokens ( 8.16 ms per token, 122.55 tokens per second) 1.03.076.539 I slot print_timing: id 2 | task 184 | eval time = 40.30 ms / 2 tokens ( 40.30 ms per token, 24.81 tokens per second) 1.03.076.539 I slot print_timing: id 2 | task 184 | total time = 1109.24 ms / 133 tokens 1.03.076.539 I slot print_timing: id 2 | task 184 | graphs reused = 1 1.03.076.540 I slot print_timing: id 2 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.076.554 I slot release: id 2 | task 184 | stop processing: n_tokens = 132, truncated = 0 1.03.076.845 I slot print_timing: id 3 | task 185 | prompt eval time = 1069.27 ms / 114 tokens ( 9.38 ms per token, 106.61 tokens per second) 1.03.076.847 I slot print_timing: id 3 | task 185 | eval time = 40.27 ms / 2 tokens ( 40.27 ms per token, 24.83 tokens per second) 1.03.076.847 I slot print_timing: id 3 | task 185 | total time = 1109.54 ms / 116 tokens 1.03.076.847 I slot print_timing: id 3 | task 185 | graphs reused = 1 1.03.076.848 I slot print_timing: id 3 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.076.865 I slot release: id 3 | task 185 | stop processing: n_tokens = 115, truncated = 0 1.03.081.398 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.261 1.03.081.614 I slot launch_slot_: id 3 | task 189 | processing task, is_child = 0 1.03.082.762 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.185 (> 0.100 thold), f_keep = 0.188 1.03.082.806 I slot launch_slot_: id 0 | task 190 | processing task, is_child = 0 1.03.082.851 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.227 1.03.082.884 I slot launch_slot_: id 2 | task 191 | processing task, is_child = 0 1.03.082.905 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.228 1.03.082.935 I slot launch_slot_: id 1 | task 192 | processing task, is_child = 0 1.04.304.216 I slot print_timing: id 0 | task 190 | prompt eval time = 1180.68 ms / 157 tokens ( 7.52 ms per token, 132.97 tokens per second) 1.04.304.218 I slot print_timing: id 0 | task 190 | eval time = 40.59 ms / 2 tokens ( 40.59 ms per token, 24.64 tokens per second) 1.04.304.218 I slot print_timing: id 0 | task 190 | total time = 1221.27 ms / 159 tokens 1.04.304.219 I slot print_timing: id 0 | task 190 | graphs reused = 1 1.04.304.219 I slot print_timing: id 0 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.304.245 I slot release: id 0 | task 190 | stop processing: n_tokens = 158, truncated = 0 1.04.304.537 I slot print_timing: id 1 | task 192 | prompt eval time = 1181.00 ms / 170 tokens ( 6.95 ms per token, 143.95 tokens per second) 1.04.304.543 I slot print_timing: id 1 | task 192 | eval time = 40.58 ms / 2 tokens ( 40.58 ms per token, 24.64 tokens per second) 1.04.304.544 I slot print_timing: id 1 | task 192 | total time = 1221.58 ms / 172 tokens 1.04.304.544 I slot print_timing: id 1 | task 192 | graphs reused = 1 1.04.304.544 I slot print_timing: id 1 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.304.560 I slot release: id 1 | task 192 | stop processing: n_tokens = 171, truncated = 0 1.04.304.834 I slot print_timing: id 2 | task 191 | prompt eval time = 1181.26 ms / 130 tokens ( 9.09 ms per token, 110.05 tokens per second) 1.04.304.838 I slot print_timing: id 2 | task 191 | eval time = 40.60 ms / 2 tokens ( 40.60 ms per token, 24.63 tokens per second) 1.04.304.838 I slot print_timing: id 2 | task 191 | total time = 1221.86 ms / 132 tokens 1.04.304.838 I slot print_timing: id 2 | task 191 | graphs reused = 1 1.04.304.839 I slot print_timing: id 2 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.304.858 I slot release: id 2 | task 191 | stop processing: n_tokens = 131, truncated = 0 1.04.305.170 I slot print_timing: id 3 | task 189 | prompt eval time = 1181.58 ms / 119 tokens ( 9.93 ms per token, 100.71 tokens per second) 1.04.305.173 I slot print_timing: id 3 | task 189 | eval time = 40.60 ms / 2 tokens ( 40.60 ms per token, 24.63 tokens per second) 1.04.305.173 I slot print_timing: id 3 | task 189 | total time = 1222.18 ms / 121 tokens 1.04.305.174 I slot print_timing: id 3 | task 189 | graphs reused = 1 1.04.305.174 I slot print_timing: id 3 | task 189 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.305.190 I slot release: id 3 | task 189 | stop processing: n_tokens = 120, truncated = 0 1.04.309.406 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.184 1.04.309.910 I slot launch_slot_: id 0 | task 198 | processing task, is_child = 0 1.04.310.894 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.170 1.04.310.929 I slot launch_slot_: id 1 | task 196 | processing task, is_child = 0 1.04.310.964 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.221 1.04.311.114 I slot launch_slot_: id 2 | task 197 | processing task, is_child = 0 1.04.311.133 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.159 (> 0.100 thold), f_keep = 0.242 1.04.311.172 I slot launch_slot_: id 3 | task 199 | processing task, is_child = 0 1.05.592.515 I slot print_timing: id 0 | task 198 | prompt eval time = 1241.44 ms / 110 tokens ( 11.29 ms per token, 88.61 tokens per second) 1.05.592.517 I slot print_timing: id 0 | task 198 | eval time = 39.89 ms / 2 tokens ( 39.89 ms per token, 25.07 tokens per second) 1.05.592.517 I slot print_timing: id 0 | task 198 | total time = 1281.33 ms / 112 tokens 1.05.592.518 I slot print_timing: id 0 | task 198 | graphs reused = 1 1.05.592.518 I slot print_timing: id 0 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.592.537 I slot release: id 0 | task 198 | stop processing: n_tokens = 111, truncated = 0 1.05.592.833 I slot print_timing: id 1 | task 196 | prompt eval time = 1241.74 ms / 155 tokens ( 8.01 ms per token, 124.83 tokens per second) 1.05.592.839 I slot print_timing: id 1 | task 196 | eval time = 39.91 ms / 2 tokens ( 39.91 ms per token, 25.06 tokens per second) 1.05.592.840 I slot print_timing: id 1 | task 196 | total time = 1281.64 ms / 157 tokens 1.05.592.840 I slot print_timing: id 1 | task 196 | graphs reused = 1 1.05.592.840 I slot print_timing: id 1 | task 196 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.592.865 I slot release: id 1 | task 196 | stop processing: n_tokens = 156, truncated = 0 1.05.593.139 I slot print_timing: id 2 | task 197 | prompt eval time = 1242.00 ms / 135 tokens ( 9.20 ms per token, 108.70 tokens per second) 1.05.593.141 I slot print_timing: id 2 | task 197 | eval time = 39.93 ms / 2 tokens ( 39.93 ms per token, 25.04 tokens per second) 1.05.593.141 I slot print_timing: id 2 | task 197 | total time = 1281.94 ms / 137 tokens 1.05.593.142 I slot print_timing: id 2 | task 197 | graphs reused = 1 1.05.593.142 I slot print_timing: id 2 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.593.155 I slot release: id 2 | task 197 | stop processing: n_tokens = 136, truncated = 0 1.05.593.477 I slot print_timing: id 3 | task 199 | prompt eval time = 1242.31 ms / 182 tokens ( 6.83 ms per token, 146.50 tokens per second) 1.05.593.479 I slot print_timing: id 3 | task 199 | eval time = 39.95 ms / 2 tokens ( 39.95 ms per token, 25.03 tokens per second) 1.05.593.480 I slot print_timing: id 3 | task 199 | total time = 1282.26 ms / 184 tokens 1.05.593.480 I slot print_timing: id 3 | task 199 | graphs reused = 1 1.05.593.480 I slot print_timing: id 3 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.593.494 I slot release: id 3 | task 199 | stop processing: n_tokens = 183, truncated = 0 1.05.598.678 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.261 1.05.598.899 I slot launch_slot_: id 0 | task 204 | processing task, is_child = 0 1.05.600.051 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.186 1.05.600.086 I slot launch_slot_: id 1 | task 205 | processing task, is_child = 0 1.05.600.122 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.213 1.05.600.287 I slot launch_slot_: id 2 | task 203 | processing task, is_child = 0 1.05.600.307 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.158 1.05.600.337 I slot launch_slot_: id 3 | task 206 | processing task, is_child = 0 1.06.710.421 I slot print_timing: id 0 | task 204 | prompt eval time = 1069.99 ms / 134 tokens ( 7.99 ms per token, 125.23 tokens per second) 1.06.710.427 I slot print_timing: id 0 | task 204 | eval time = 40.09 ms / 2 tokens ( 40.09 ms per token, 24.95 tokens per second) 1.06.710.428 I slot print_timing: id 0 | task 204 | total time = 1110.08 ms / 136 tokens 1.06.710.428 I slot print_timing: id 0 | task 204 | graphs reused = 1 1.06.710.429 I slot print_timing: id 0 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.710.449 I slot release: id 0 | task 204 | stop processing: n_tokens = 135, truncated = 0 1.06.710.743 I slot print_timing: id 1 | task 205 | prompt eval time = 1070.26 ms / 136 tokens ( 7.87 ms per token, 127.07 tokens per second) 1.06.710.744 I slot print_timing: id 1 | task 205 | eval time = 40.13 ms / 2 tokens ( 40.13 ms per token, 24.92 tokens per second) 1.06.710.745 I slot print_timing: id 1 | task 205 | total time = 1110.38 ms / 138 tokens 1.06.710.745 I slot print_timing: id 1 | task 205 | graphs reused = 1 1.06.710.745 I slot print_timing: id 1 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.710.759 I slot release: id 1 | task 205 | stop processing: n_tokens = 137, truncated = 0 1.06.711.056 I slot print_timing: id 2 | task 203 | prompt eval time = 1070.53 ms / 117 tokens ( 9.15 ms per token, 109.29 tokens per second) 1.06.711.059 I slot print_timing: id 2 | task 203 | eval time = 40.16 ms / 2 tokens ( 40.16 ms per token, 24.90 tokens per second) 1.06.711.059 I slot print_timing: id 2 | task 203 | total time = 1110.68 ms / 119 tokens 1.06.711.059 I slot print_timing: id 2 | task 203 | graphs reused = 1 1.06.711.060 I slot print_timing: id 2 | task 203 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.711.076 I slot release: id 2 | task 203 | stop processing: n_tokens = 118, truncated = 0 1.06.711.370 I slot print_timing: id 3 | task 206 | prompt eval time = 1070.91 ms / 160 tokens ( 6.69 ms per token, 149.40 tokens per second) 1.06.711.374 I slot print_timing: id 3 | task 206 | eval time = 40.07 ms / 2 tokens ( 40.07 ms per token, 24.96 tokens per second) 1.06.711.374 I slot print_timing: id 3 | task 206 | total time = 1110.98 ms / 162 tokens 1.06.711.374 I slot print_timing: id 3 | task 206 | graphs reused = 1 1.06.711.375 I slot print_timing: id 3 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.711.392 I slot release: id 3 | task 206 | stop processing: n_tokens = 161, truncated = 0 1.06.715.598 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.215 1.06.716.019 I slot launch_slot_: id 0 | task 210 | processing task, is_child = 0 1.06.717.195 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.254 1.06.717.230 I slot launch_slot_: id 2 | task 211 | processing task, is_child = 0 1.06.717.266 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.212 1.06.717.414 I slot launch_slot_: id 1 | task 212 | processing task, is_child = 0 1.06.717.434 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.180 1.06.717.467 I slot launch_slot_: id 3 | task 213 | processing task, is_child = 0 1.07.880.803 I slot print_timing: id 0 | task 210 | prompt eval time = 1123.37 ms / 151 tokens ( 7.44 ms per token, 134.42 tokens per second) 1.07.880.806 I slot print_timing: id 0 | task 210 | eval time = 39.96 ms / 2 tokens ( 39.96 ms per token, 25.02 tokens per second) 1.07.880.806 I slot print_timing: id 0 | task 210 | total time = 1163.33 ms / 153 tokens 1.07.880.806 I slot print_timing: id 0 | task 210 | graphs reused = 1 1.07.880.807 I slot print_timing: id 0 | task 210 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.880.827 I slot release: id 0 | task 210 | stop processing: n_tokens = 152, truncated = 0 1.07.881.129 I slot print_timing: id 1 | task 212 | prompt eval time = 1123.65 ms / 118 tokens ( 9.52 ms per token, 105.01 tokens per second) 1.07.881.132 I slot print_timing: id 1 | task 212 | eval time = 39.99 ms / 2 tokens ( 39.99 ms per token, 25.01 tokens per second) 1.07.881.133 I slot print_timing: id 1 | task 212 | total time = 1163.64 ms / 120 tokens 1.07.881.133 I slot print_timing: id 1 | task 212 | graphs reused = 1 1.07.881.134 I slot print_timing: id 1 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.881.149 I slot release: id 1 | task 212 | stop processing: n_tokens = 119, truncated = 0 1.07.881.431 I slot print_timing: id 2 | task 211 | prompt eval time = 1123.93 ms / 124 tokens ( 9.06 ms per token, 110.33 tokens per second) 1.07.881.433 I slot print_timing: id 2 | task 211 | eval time = 40.01 ms / 2 tokens ( 40.01 ms per token, 24.99 tokens per second) 1.07.881.433 I slot print_timing: id 2 | task 211 | total time = 1163.94 ms / 126 tokens 1.07.881.434 I slot print_timing: id 2 | task 211 | graphs reused = 1 1.07.881.434 I slot print_timing: id 2 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.881.447 I slot release: id 2 | task 211 | stop processing: n_tokens = 125, truncated = 0 1.07.881.736 I slot print_timing: id 3 | task 213 | prompt eval time = 1124.21 ms / 156 tokens ( 7.21 ms per token, 138.76 tokens per second) 1.07.881.738 I slot print_timing: id 3 | task 213 | eval time = 40.03 ms / 2 tokens ( 40.03 ms per token, 24.98 tokens per second) 1.07.881.738 I slot print_timing: id 3 | task 213 | total time = 1164.23 ms / 158 tokens 1.07.881.739 I slot print_timing: id 3 | task 213 | graphs reused = 1 1.07.881.739 I slot print_timing: id 3 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.881.752 I slot release: id 3 | task 213 | stop processing: n_tokens = 157, truncated = 0 1.07.885.086 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.191 1.07.885.588 I slot launch_slot_: id 0 | task 218 | processing task, is_child = 0 1.07.886.704 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.244 1.07.886.747 I slot launch_slot_: id 1 | task 217 | processing task, is_child = 0 1.07.886.785 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.232 1.07.886.819 I slot launch_slot_: id 2 | task 219 | processing task, is_child = 0 1.07.886.837 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.185 1.07.886.868 I slot launch_slot_: id 3 | task 220 | processing task, is_child = 0 1.09.067.815 I slot print_timing: id 0 | task 218 | prompt eval time = 1140.77 ms / 149 tokens ( 7.66 ms per token, 130.61 tokens per second) 1.09.067.818 I slot print_timing: id 0 | task 218 | eval time = 40.17 ms / 2 tokens ( 40.17 ms per token, 24.90 tokens per second) 1.09.067.818 I slot print_timing: id 0 | task 218 | total time = 1180.94 ms / 151 tokens 1.09.067.819 I slot print_timing: id 0 | task 218 | graphs reused = 1 1.09.067.819 I slot print_timing: id 0 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.067.842 I slot release: id 0 | task 218 | stop processing: n_tokens = 150, truncated = 0 1.09.068.119 I slot print_timing: id 1 | task 217 | prompt eval time = 1141.13 ms / 162 tokens ( 7.04 ms per token, 141.96 tokens per second) 1.09.068.121 I slot print_timing: id 1 | task 217 | eval time = 40.09 ms / 2 tokens ( 40.09 ms per token, 24.94 tokens per second) 1.09.068.121 I slot print_timing: id 1 | task 217 | total time = 1181.22 ms / 164 tokens 1.09.068.122 I slot print_timing: id 1 | task 217 | graphs reused = 1 1.09.068.122 I slot print_timing: id 1 | task 217 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.068.158 I slot release: id 1 | task 217 | stop processing: n_tokens = 163, truncated = 0 1.09.068.439 I slot print_timing: id 2 | task 219 | prompt eval time = 1141.41 ms / 154 tokens ( 7.41 ms per token, 134.92 tokens per second) 1.09.068.442 I slot print_timing: id 2 | task 219 | eval time = 40.12 ms / 2 tokens ( 40.12 ms per token, 24.92 tokens per second) 1.09.068.443 I slot print_timing: id 2 | task 219 | total time = 1181.53 ms / 156 tokens 1.09.068.443 I slot print_timing: id 2 | task 219 | graphs reused = 1 1.09.068.443 I slot print_timing: id 2 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.068.457 I slot release: id 2 | task 219 | stop processing: n_tokens = 155, truncated = 0 1.09.068.747 I slot print_timing: id 3 | task 220 | prompt eval time = 1141.71 ms / 156 tokens ( 7.32 ms per token, 136.64 tokens per second) 1.09.068.755 I slot print_timing: id 3 | task 220 | eval time = 40.11 ms / 2 tokens ( 40.11 ms per token, 24.93 tokens per second) 1.09.068.756 I slot print_timing: id 3 | task 220 | total time = 1181.82 ms / 158 tokens 1.09.068.756 I slot print_timing: id 3 | task 220 | graphs reused = 1 1.09.068.756 I slot print_timing: id 3 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.068.769 I slot release: id 3 | task 220 | stop processing: n_tokens = 157, truncated = 0 1.09.073.275 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.193 1.09.073.747 I slot launch_slot_: id 0 | task 227 | processing task, is_child = 0 1.09.075.064 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.178 1.09.075.219 I slot launch_slot_: id 1 | task 224 | processing task, is_child = 0 1.09.075.256 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.187 1.09.075.289 I slot launch_slot_: id 2 | task 225 | processing task, is_child = 0 1.09.075.314 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.185 1.09.075.348 I slot launch_slot_: id 3 | task 226 | processing task, is_child = 0 1.10.152.033 I slot print_timing: id 0 | task 227 | prompt eval time = 1036.28 ms / 115 tokens ( 9.01 ms per token, 110.97 tokens per second) 1.10.152.036 I slot print_timing: id 0 | task 227 | eval time = 40.40 ms / 2 tokens ( 40.40 ms per token, 24.75 tokens per second) 1.10.152.036 I slot print_timing: id 0 | task 227 | total time = 1076.68 ms / 117 tokens 1.10.152.037 I slot print_timing: id 0 | task 227 | graphs reused = 1 1.10.152.037 I slot print_timing: id 0 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.152.055 I slot release: id 0 | task 227 | stop processing: n_tokens = 116, truncated = 0 1.10.152.343 I slot print_timing: id 1 | task 224 | prompt eval time = 1036.57 ms / 103 tokens ( 10.06 ms per token, 99.37 tokens per second) 1.10.152.345 I slot print_timing: id 1 | task 224 | eval time = 40.41 ms / 2 tokens ( 40.41 ms per token, 24.75 tokens per second) 1.10.152.346 I slot print_timing: id 1 | task 224 | total time = 1076.98 ms / 105 tokens 1.10.152.346 I slot print_timing: id 1 | task 224 | graphs reused = 1 1.10.152.346 I slot print_timing: id 1 | task 224 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.152.360 I slot release: id 1 | task 224 | stop processing: n_tokens = 104, truncated = 0 1.10.152.721 I slot print_timing: id 2 | task 225 | prompt eval time = 1036.94 ms / 108 tokens ( 9.60 ms per token, 104.15 tokens per second) 1.10.152.724 I slot print_timing: id 2 | task 225 | eval time = 40.41 ms / 2 tokens ( 40.41 ms per token, 24.75 tokens per second) 1.10.152.725 I slot print_timing: id 2 | task 225 | total time = 1077.35 ms / 110 tokens 1.10.152.725 I slot print_timing: id 2 | task 225 | graphs reused = 1 1.10.152.725 I slot print_timing: id 2 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.152.738 I slot release: id 2 | task 225 | stop processing: n_tokens = 109, truncated = 0 1.10.153.123 I slot print_timing: id 3 | task 226 | prompt eval time = 1037.33 ms / 186 tokens ( 5.58 ms per token, 179.31 tokens per second) 1.10.153.126 I slot print_timing: id 3 | task 226 | eval time = 40.41 ms / 2 tokens ( 40.41 ms per token, 24.75 tokens per second) 1.10.153.126 I slot print_timing: id 3 | task 226 | total time = 1077.74 ms / 188 tokens 1.10.153.126 I slot print_timing: id 3 | task 226 | graphs reused = 1 1.10.153.127 I slot print_timing: id 3 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.153.147 I slot release: id 3 | task 226 | stop processing: n_tokens = 187, truncated = 0 1.10.157.944 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.250 1.10.158.234 I slot launch_slot_: id 0 | task 231 | processing task, is_child = 0 1.10.159.094 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.279 1.10.159.129 I slot launch_slot_: id 1 | task 234 | processing task, is_child = 0 1.10.159.165 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.266 1.10.159.305 I slot launch_slot_: id 2 | task 233 | processing task, is_child = 0 1.10.159.327 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.155 1.10.159.361 I slot launch_slot_: id 3 | task 232 | processing task, is_child = 0 1.11.290.574 I slot print_timing: id 0 | task 231 | prompt eval time = 1091.09 ms / 122 tokens ( 8.94 ms per token, 111.81 tokens per second) 1.11.290.577 I slot print_timing: id 0 | task 231 | eval time = 40.11 ms / 2 tokens ( 40.11 ms per token, 24.93 tokens per second) 1.11.290.578 I slot print_timing: id 0 | task 231 | total time = 1131.21 ms / 124 tokens 1.11.290.578 I slot print_timing: id 0 | task 231 | graphs reused = 1 1.11.290.578 I slot print_timing: id 0 | task 231 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.290.599 I slot release: id 0 | task 231 | stop processing: n_tokens = 123, truncated = 0 1.11.290.876 I slot print_timing: id 1 | task 234 | prompt eval time = 1091.36 ms / 163 tokens ( 6.70 ms per token, 149.35 tokens per second) 1.11.290.877 I slot print_timing: id 1 | task 234 | eval time = 40.14 ms / 2 tokens ( 40.14 ms per token, 24.91 tokens per second) 1.11.290.878 I slot print_timing: id 1 | task 234 | total time = 1131.50 ms / 165 tokens 1.11.290.878 I slot print_timing: id 1 | task 234 | graphs reused = 1 1.11.290.878 I slot print_timing: id 1 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.290.893 I slot release: id 1 | task 234 | stop processing: n_tokens = 164, truncated = 0 1.11.291.185 I slot print_timing: id 2 | task 233 | prompt eval time = 1091.66 ms / 113 tokens ( 9.66 ms per token, 103.51 tokens per second) 1.11.291.188 I slot print_timing: id 2 | task 233 | eval time = 40.14 ms / 2 tokens ( 40.14 ms per token, 24.92 tokens per second) 1.11.291.189 I slot print_timing: id 2 | task 233 | total time = 1131.80 ms / 115 tokens 1.11.291.189 I slot print_timing: id 2 | task 233 | graphs reused = 1 1.11.291.189 I slot print_timing: id 2 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.291.201 I slot release: id 2 | task 233 | stop processing: n_tokens = 114, truncated = 0 1.11.291.486 I slot print_timing: id 3 | task 232 | prompt eval time = 1091.97 ms / 128 tokens ( 8.53 ms per token, 117.22 tokens per second) 1.11.291.490 I slot print_timing: id 3 | task 232 | eval time = 40.12 ms / 2 tokens ( 40.12 ms per token, 24.93 tokens per second) 1.11.291.490 I slot print_timing: id 3 | task 232 | total time = 1132.09 ms / 130 tokens 1.11.291.490 I slot print_timing: id 3 | task 232 | graphs reused = 1 1.11.291.491 I slot print_timing: id 3 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.291.507 I slot release: id 3 | task 232 | stop processing: n_tokens = 129, truncated = 0 1.11.296.395 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.236 1.11.296.821 I slot launch_slot_: id 0 | task 240 | processing task, is_child = 0 1.11.297.810 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.263 1.11.297.846 I slot launch_slot_: id 2 | task 238 | processing task, is_child = 0 1.11.297.883 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.240 (> 0.100 thold), f_keep = 0.177 1.11.297.915 I slot launch_slot_: id 1 | task 239 | processing task, is_child = 0 1.11.297.935 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.225 1.11.298.088 I slot launch_slot_: id 3 | task 241 | processing task, is_child = 0 1.12.305.187 I slot print_timing: id 0 | task 240 | prompt eval time = 966.88 ms / 127 tokens ( 7.61 ms per token, 131.35 tokens per second) 1.12.305.190 I slot print_timing: id 0 | task 240 | eval time = 40.20 ms / 2 tokens ( 40.20 ms per token, 24.87 tokens per second) 1.12.305.190 I slot print_timing: id 0 | task 240 | total time = 1007.09 ms / 129 tokens 1.12.305.191 I slot print_timing: id 0 | task 240 | graphs reused = 1 1.12.305.191 I slot print_timing: id 0 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.305.213 I slot release: id 0 | task 240 | stop processing: n_tokens = 128, truncated = 0 1.12.305.490 I slot print_timing: id 1 | task 239 | prompt eval time = 967.15 ms / 121 tokens ( 7.99 ms per token, 125.11 tokens per second) 1.12.305.492 I slot print_timing: id 1 | task 239 | eval time = 40.24 ms / 2 tokens ( 40.24 ms per token, 24.85 tokens per second) 1.12.305.492 I slot print_timing: id 1 | task 239 | total time = 1007.38 ms / 123 tokens 1.12.305.493 I slot print_timing: id 1 | task 239 | graphs reused = 1 1.12.305.493 I slot print_timing: id 1 | task 239 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.305.506 I slot release: id 1 | task 239 | stop processing: n_tokens = 122, truncated = 0 1.12.305.804 I slot print_timing: id 2 | task 238 | prompt eval time = 967.44 ms / 136 tokens ( 7.11 ms per token, 140.58 tokens per second) 1.12.305.806 I slot print_timing: id 2 | task 238 | eval time = 40.25 ms / 2 tokens ( 40.25 ms per token, 24.84 tokens per second) 1.12.305.806 I slot print_timing: id 2 | task 238 | total time = 1007.69 ms / 138 tokens 1.12.305.807 I slot print_timing: id 2 | task 238 | graphs reused = 1 1.12.305.807 I slot print_timing: id 2 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.305.820 I slot release: id 2 | task 238 | stop processing: n_tokens = 137, truncated = 0 1.12.306.122 I slot print_timing: id 3 | task 241 | prompt eval time = 967.74 ms / 139 tokens ( 6.96 ms per token, 143.63 tokens per second) 1.12.306.125 I slot print_timing: id 3 | task 241 | eval time = 40.26 ms / 2 tokens ( 40.26 ms per token, 24.84 tokens per second) 1.12.306.126 I slot print_timing: id 3 | task 241 | total time = 1008.00 ms / 141 tokens 1.12.306.126 I slot print_timing: id 3 | task 241 | graphs reused = 1 1.12.306.126 I slot print_timing: id 3 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.306.136 I slot release: id 3 | task 241 | stop processing: n_tokens = 140, truncated = 0 1.12.310.311 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.227 1.12.310.705 I slot launch_slot_: id 0 | task 245 | processing task, is_child = 0 1.12.311.834 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.238 1.12.311.979 I slot launch_slot_: id 1 | task 246 | processing task, is_child = 0 1.12.312.016 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.212 1.12.312.049 I slot launch_slot_: id 2 | task 247 | processing task, is_child = 0 1.12.312.074 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.207 1.12.312.107 I slot launch_slot_: id 3 | task 248 | processing task, is_child = 0 1.13.570.656 I slot print_timing: id 0 | task 245 | prompt eval time = 1218.17 ms / 120 tokens ( 10.15 ms per token, 98.51 tokens per second) 1.13.570.658 I slot print_timing: id 0 | task 245 | eval time = 40.37 ms / 2 tokens ( 40.37 ms per token, 24.77 tokens per second) 1.13.570.659 I slot print_timing: id 0 | task 245 | total time = 1258.54 ms / 122 tokens 1.13.570.659 I slot print_timing: id 0 | task 245 | graphs reused = 1 1.13.570.659 I slot print_timing: id 0 | task 245 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.570.677 I slot release: id 0 | task 245 | stop processing: n_tokens = 121, truncated = 0 1.13.570.975 I slot print_timing: id 1 | task 246 | prompt eval time = 1218.47 ms / 159 tokens ( 7.66 ms per token, 130.49 tokens per second) 1.13.570.977 I slot print_timing: id 1 | task 246 | eval time = 40.38 ms / 2 tokens ( 40.38 ms per token, 24.77 tokens per second) 1.13.570.977 I slot print_timing: id 1 | task 246 | total time = 1258.85 ms / 161 tokens 1.13.570.978 I slot print_timing: id 1 | task 246 | graphs reused = 1 1.13.570.978 I slot print_timing: id 1 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.570.993 I slot release: id 1 | task 246 | stop processing: n_tokens = 160, truncated = 0 1.13.571.260 I slot print_timing: id 2 | task 247 | prompt eval time = 1218.74 ms / 142 tokens ( 8.58 ms per token, 116.51 tokens per second) 1.13.571.262 I slot print_timing: id 2 | task 247 | eval time = 40.38 ms / 2 tokens ( 40.38 ms per token, 24.76 tokens per second) 1.13.571.263 I slot print_timing: id 2 | task 247 | total time = 1259.13 ms / 144 tokens 1.13.571.263 I slot print_timing: id 2 | task 247 | graphs reused = 1 1.13.571.263 I slot print_timing: id 2 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.571.282 I slot release: id 2 | task 247 | stop processing: n_tokens = 143, truncated = 0 1.13.571.569 I slot print_timing: id 3 | task 248 | prompt eval time = 1219.07 ms / 170 tokens ( 7.17 ms per token, 139.45 tokens per second) 1.13.571.572 I slot print_timing: id 3 | task 248 | eval time = 40.36 ms / 2 tokens ( 40.36 ms per token, 24.78 tokens per second) 1.13.571.574 I slot print_timing: id 3 | task 248 | total time = 1259.42 ms / 172 tokens 1.13.571.574 I slot print_timing: id 3 | task 248 | graphs reused = 1 1.13.571.574 I slot print_timing: id 3 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.571.594 I slot release: id 3 | task 248 | stop processing: n_tokens = 171, truncated = 0 1.13.575.910 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.240 1.13.576.331 I slot launch_slot_: id 0 | task 252 | processing task, is_child = 0 1.13.577.591 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.181 1.13.577.750 I slot launch_slot_: id 1 | task 253 | processing task, is_child = 0 1.13.577.788 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.203 1.13.577.935 I slot launch_slot_: id 2 | task 254 | processing task, is_child = 0 1.13.577.958 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.170 1.13.577.992 I slot launch_slot_: id 3 | task 255 | processing task, is_child = 0 1.14.879.246 I slot print_timing: id 0 | task 252 | prompt eval time = 1261.24 ms / 103 tokens ( 12.25 ms per token, 81.67 tokens per second) 1.14.879.249 I slot print_timing: id 0 | task 252 | eval time = 40.01 ms / 2 tokens ( 40.01 ms per token, 25.00 tokens per second) 1.14.879.249 I slot print_timing: id 0 | task 252 | total time = 1301.24 ms / 105 tokens 1.14.879.250 I slot print_timing: id 0 | task 252 | graphs reused = 1 1.14.879.250 I slot print_timing: id 0 | task 252 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.879.269 I slot release: id 0 | task 252 | stop processing: n_tokens = 104, truncated = 0 1.14.879.555 I slot print_timing: id 1 | task 253 | prompt eval time = 1261.53 ms / 134 tokens ( 9.41 ms per token, 106.22 tokens per second) 1.14.879.557 I slot print_timing: id 1 | task 253 | eval time = 40.02 ms / 2 tokens ( 40.02 ms per token, 24.99 tokens per second) 1.14.879.557 I slot print_timing: id 1 | task 253 | total time = 1301.55 ms / 136 tokens 1.14.879.557 I slot print_timing: id 1 | task 253 | graphs reused = 1 1.14.879.558 I slot print_timing: id 1 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.879.574 I slot release: id 1 | task 253 | stop processing: n_tokens = 135, truncated = 0 1.14.879.855 I slot print_timing: id 2 | task 254 | prompt eval time = 1261.83 ms / 184 tokens ( 6.86 ms per token, 145.82 tokens per second) 1.14.879.858 I slot print_timing: id 2 | task 254 | eval time = 40.01 ms / 2 tokens ( 40.01 ms per token, 25.00 tokens per second) 1.14.879.859 I slot print_timing: id 2 | task 254 | total time = 1301.83 ms / 186 tokens 1.14.879.859 I slot print_timing: id 2 | task 254 | graphs reused = 1 1.14.879.859 I slot print_timing: id 2 | task 254 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.879.886 I slot release: id 2 | task 254 | stop processing: n_tokens = 185, truncated = 0 1.14.880.162 I slot print_timing: id 3 | task 255 | prompt eval time = 1262.17 ms / 158 tokens ( 7.99 ms per token, 125.18 tokens per second) 1.14.880.164 I slot print_timing: id 3 | task 255 | eval time = 39.96 ms / 2 tokens ( 39.96 ms per token, 25.03 tokens per second) 1.14.880.164 I slot print_timing: id 3 | task 255 | total time = 1302.13 ms / 160 tokens 1.14.880.165 I slot print_timing: id 3 | task 255 | graphs reused = 1 1.14.880.165 I slot print_timing: id 3 | task 255 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.880.180 I slot release: id 3 | task 255 | stop processing: n_tokens = 159, truncated = 0 1.14.883.351 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.279 1.14.883.572 I slot launch_slot_: id 0 | task 259 | processing task, is_child = 0 1.14.884.933 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.215 1.14.884.973 I slot launch_slot_: id 1 | task 260 | processing task, is_child = 0 1.15.496.477 I slot print_timing: id 0 | task 259 | prompt eval time = 562.28 ms / 125 tokens ( 4.50 ms per token, 222.31 tokens per second) 1.15.496.480 I slot print_timing: id 0 | task 259 | eval time = 49.18 ms / 2 tokens ( 49.18 ms per token, 20.33 tokens per second) 1.15.496.481 I slot print_timing: id 0 | task 259 | total time = 611.46 ms / 127 tokens 1.15.496.481 I slot print_timing: id 0 | task 259 | graphs reused = 1 1.15.496.481 I slot print_timing: id 0 | task 259 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.496.500 I slot release: id 0 | task 259 | stop processing: n_tokens = 126, truncated = 0 1.15.496.799 I slot print_timing: id 1 | task 260 | prompt eval time = 562.66 ms / 145 tokens ( 3.88 ms per token, 257.70 tokens per second) 1.15.496.804 I slot print_timing: id 1 | task 260 | eval time = 49.11 ms / 2 tokens ( 49.11 ms per token, 20.36 tokens per second) 1.15.496.804 I slot print_timing: id 1 | task 260 | total time = 611.77 ms / 147 tokens 1.15.496.804 I slot print_timing: id 1 | task 260 | graphs reused = 1 1.15.496.805 I slot print_timing: id 1 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.496.816 I slot release: id 1 | task 260 | stop processing: n_tokens = 146, truncated = 0 1.15.510.202 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 185, t_last = 340163478368 1.15.510.254 I slot launch_slot_: id 2 | task 265 | processing task, is_child = 0 1.15.510.953 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 159, t_last = 340163478662 1.15.510.994 I slot launch_slot_: id 3 | task 264 | processing task, is_child = 0 1.17.183.350 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 126, t_last = 340164094982 1.17.183.420 I slot launch_slot_: id 0 | task 267 | processing task, is_child = 0 1.17.183.443 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 146, t_last = 340164095298 1.17.183.475 I slot launch_slot_: id 1 | task 268 | processing task, is_child = 0 1.20.175.449 I slot print_timing: id 2 | task 265 | prompt processing, n_tokens = 1155, progress = 1.00, t = 4.57 s / 252.73 tokens per second 1.20.175.629 I slot print_timing: id 3 | task 264 | prompt processing, n_tokens = 924, progress = 0.80, t = 4.57 s / 202.18 tokens per second 1.21.939.619 I slot print_timing: id 0 | task 267 | prompt processing, n_tokens = 1144, progress = 1.00, t = 4.76 s / 240.55 tokens per second 1.21.939.826 I slot print_timing: id 1 | task 268 | prompt processing, n_tokens = 1129, progress = 1.00, t = 4.76 s / 237.40 tokens per second 1.21.940.007 I slot print_timing: id 3 | task 264 | prompt processing, n_tokens = 1149, progress = 1.00, t = 6.43 s / 178.74 tokens per second 1.25.992.049 I slot print_timing: id 2 | task 265 | n_gen = 100, tg = 24.43 t/s, tg_3s = 24.68 t/s 1.26.031.219 I slot print_timing: id 0 | task 267 | n_gen = 100, tg = 24.88 t/s, tg_3s = 25.14 t/s 1.26.031.669 I slot print_timing: id 1 | task 268 | n_gen = 100, tg = 24.88 t/s, tg_3s = 25.14 t/s 1.26.032.813 I slot print_timing: id 3 | task 264 | n_gen = 100, tg = 24.88 t/s, tg_3s = 25.13 t/s 1.29.016.658 I slot print_timing: id 2 | task 265 | n_gen = 175, tg = 24.59 t/s, tg_3s = 24.80 t/s 1.29.055.853 I slot print_timing: id 0 | task 267 | n_gen = 175, tg = 24.85 t/s, tg_3s = 24.80 t/s 1.29.056.415 I slot print_timing: id 1 | task 268 | n_gen = 175, tg = 24.85 t/s, tg_3s = 24.80 t/s 1.29.057.535 I slot print_timing: id 3 | task 264 | n_gen = 175, tg = 24.84 t/s, tg_3s = 24.80 t/s 1.30.587.516 I slot print_timing: id 0 | task 267 | prompt eval time = 4869.32 ms / 1148 tokens ( 4.24 ms per token, 235.76 tokens per second) 1.30.587.523 I slot print_timing: id 0 | task 267 | eval time = 8534.70 ms / 213 tokens ( 40.26 ms per token, 24.84 tokens per second) 1.30.587.524 I slot print_timing: id 0 | task 267 | total time = 13404.03 ms / 1361 tokens 1.30.587.525 I slot print_timing: id 0 | task 267 | graphs reused = 211 1.30.587.526 I slot print_timing: id 0 | task 267 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.587.627 I slot release: id 0 | task 267 | stop processing: n_tokens = 1360, truncated = 0 1.30.624.233 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.785 1.30.624.267 I slot launch_slot_: id 0 | task 485 | processing task, is_child = 0 1.32.031.517 I slot print_timing: id 2 | task 265 | n_gen = 230, tg = 22.69 t/s, tg_3s = 18.24 t/s 1.32.071.407 I slot print_timing: id 1 | task 268 | n_gen = 230, tg = 22.86 t/s, tg_3s = 18.24 t/s 1.32.072.537 I slot print_timing: id 3 | task 264 | n_gen = 230, tg = 22.86 t/s, tg_3s = 18.24 t/s 1.35.056.148 I slot print_timing: id 2 | task 265 | n_gen = 305, tg = 23.18 t/s, tg_3s = 24.80 t/s 1.35.095.911 I slot print_timing: id 1 | task 268 | n_gen = 305, tg = 23.31 t/s, tg_3s = 24.80 t/s 1.35.097.079 I slot print_timing: id 3 | task 264 | n_gen = 305, tg = 23.31 t/s, tg_3s = 24.80 t/s 1.35.539.499 I slot print_timing: id 0 | task 485 | n_gen = 100, tg = 24.82 t/s, tg_3s = 25.07 t/s 1.38.080.204 I slot print_timing: id 2 | task 265 | n_gen = 380, tg = 23.48 t/s, tg_3s = 24.80 t/s 1.38.119.965 I slot print_timing: id 1 | task 268 | n_gen = 380, tg = 23.59 t/s, tg_3s = 24.80 t/s 1.38.121.117 I slot print_timing: id 3 | task 264 | n_gen = 380, tg = 23.59 t/s, tg_3s = 24.80 t/s 1.38.563.191 I slot print_timing: id 0 | task 485 | n_gen = 175, tg = 24.81 t/s, tg_3s = 24.80 t/s 1.38.885.301 I slot print_timing: id 1 | task 268 | prompt eval time = 4869.67 ms / 1133 tokens ( 4.30 ms per token, 232.66 tokens per second) 1.38.885.308 I slot print_timing: id 1 | task 268 | eval time = 16832.12 ms / 399 tokens ( 42.29 ms per token, 23.65 tokens per second) 1.38.885.309 I slot print_timing: id 1 | task 268 | total time = 21701.79 ms / 1532 tokens 1.38.885.310 I slot print_timing: id 1 | task 268 | graphs reused = 392 1.38.885.310 I slot print_timing: id 1 | task 268 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.885.417 I slot release: id 1 | task 268 | stop processing: n_tokens = 1531, truncated = 0 1.38.929.042 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.698 1.38.929.083 I slot launch_slot_: id 1 | task 672 | processing task, is_child = 0 1.41.095.600 I slot print_timing: id 2 | task 265 | n_gen = 432, tg = 22.50 t/s, tg_3s = 17.24 t/s 1.41.136.605 I slot print_timing: id 3 | task 264 | n_gen = 432, tg = 22.59 t/s, tg_3s = 17.24 t/s 1.41.579.702 I slot print_timing: id 0 | task 485 | n_gen = 227, tg = 22.53 t/s, tg_3s = 17.24 t/s 1.43.966.024 I slot print_timing: id 1 | task 672 | n_gen = 100, tg = 24.67 t/s, tg_3s = 24.92 t/s 1.44.128.089 I slot print_timing: id 2 | task 265 | n_gen = 507, tg = 22.80 t/s, tg_3s = 24.73 t/s 1.44.168.990 I slot print_timing: id 3 | task 264 | n_gen = 507, tg = 22.88 t/s, tg_3s = 24.73 t/s 1.44.612.252 I slot print_timing: id 0 | task 485 | n_gen = 302, tg = 23.04 t/s, tg_3s = 24.73 t/s 1.46.993.451 I slot print_timing: id 1 | task 672 | n_gen = 175, tg = 24.71 t/s, tg_3s = 24.77 t/s 1.47.155.108 I slot print_timing: id 2 | task 265 | n_gen = 582, tg = 23.04 t/s, tg_3s = 24.78 t/s 1.47.195.795 I slot print_timing: id 3 | task 264 | n_gen = 582, tg = 23.11 t/s, tg_3s = 24.78 t/s 1.47.637.888 I slot print_timing: id 0 | task 485 | n_gen = 377, tg = 23.37 t/s, tg_3s = 24.79 t/s 1.50.029.540 I slot print_timing: id 1 | task 672 | n_gen = 250, tg = 24.71 t/s, tg_3s = 24.70 t/s 1.50.191.879 I slot print_timing: id 2 | task 265 | n_gen = 657, tg = 23.22 t/s, tg_3s = 24.70 t/s 1.50.232.996 I slot print_timing: id 3 | task 264 | n_gen = 657, tg = 23.28 t/s, tg_3s = 24.69 t/s 1.50.675.695 I slot print_timing: id 0 | task 485 | n_gen = 452, tg = 23.58 t/s, tg_3s = 24.69 t/s 1.52.455.175 I slot print_timing: id 3 | task 264 | prompt eval time = 6542.88 ms / 1153 tokens ( 5.67 ms per token, 176.22 tokens per second) 1.52.455.180 I slot print_timing: id 3 | task 264 | eval time = 30401.23 ms / 712 tokens ( 42.76 ms per token, 23.39 tokens per second) 1.52.455.181 I slot print_timing: id 3 | task 264 | total time = 36944.11 ms / 1865 tokens 1.52.455.181 I slot print_timing: id 3 | task 264 | graphs reused = 699 1.52.455.182 I slot print_timing: id 3 | task 264 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.455.284 I slot release: id 3 | task 264 | stop processing: n_tokens = 1864, truncated = 0 1.52.490.738 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.573 1.52.490.769 I slot launch_slot_: id 3 | task 986 | processing task, is_child = 0 1.53.033.538 I slot print_timing: id 1 | task 672 | n_gen = 314, tg = 23.93 t/s, tg_3s = 21.30 t/s 1.53.193.408 I slot print_timing: id 2 | task 265 | n_gen = 721, tg = 23.04 t/s, tg_3s = 21.32 t/s 1.53.682.414 I slot print_timing: id 0 | task 485 | n_gen = 516, tg = 23.27 t/s, tg_3s = 21.29 t/s 1.54.250.722 I slot print_timing: id 0 | task 485 | prompt eval time = 925.77 ms / 539 tokens ( 1.72 ms per token, 582.22 tokens per second) 1.54.250.726 I slot print_timing: id 0 | task 485 | eval time = 22700.68 ms / 530 tokens ( 42.91 ms per token, 23.30 tokens per second) 1.54.250.727 I slot print_timing: id 0 | task 485 | total time = 23626.45 ms / 1069 tokens 1.54.250.728 I slot print_timing: id 0 | task 485 | graphs reused = 729 1.54.250.728 I slot print_timing: id 0 | task 485 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.250.825 I slot release: id 0 | task 485 | stop processing: n_tokens = 1700, truncated = 0 1.54.287.899 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.628 1.54.287.935 I slot launch_slot_: id 0 | task 1021 | processing task, is_child = 0 1.56.037.085 I slot print_timing: id 1 | task 672 | n_gen = 372, tg = 23.07 t/s, tg_3s = 19.31 t/s 1.56.199.804 I slot print_timing: id 2 | task 265 | n_gen = 779, tg = 22.71 t/s, tg_3s = 19.29 t/s 1.57.655.772 I slot print_timing: id 3 | task 986 | n_gen = 100, tg = 21.23 t/s, tg_3s = 21.45 t/s 1.59.026.741 I slot print_timing: id 0 | task 1021 | n_gen = 100, tg = 24.76 t/s, tg_3s = 25.01 t/s 1.59.067.536 I slot print_timing: id 1 | task 672 | n_gen = 447, tg = 23.33 t/s, tg_3s = 24.75 t/s 1.59.228.984 I slot print_timing: id 2 | task 265 | n_gen = 854, tg = 22.88 t/s, tg_3s = 24.76 t/s 2.00.686.557 I slot print_timing: id 3 | task 986 | n_gen = 175, tg = 22.62 t/s, tg_3s = 24.75 t/s 2.02.066.864 I slot print_timing: id 0 | task 1021 | n_gen = 175, tg = 24.72 t/s, tg_3s = 24.67 t/s 2.02.108.059 I slot print_timing: id 1 | task 672 | n_gen = 522, tg = 23.52 t/s, tg_3s = 24.67 t/s 2.02.230.554 I slot print_timing: id 2 | task 265 | n_gen = 928, tg = 23.01 t/s, tg_3s = 24.65 t/s 2.03.694.402 I slot print_timing: id 3 | task 986 | n_gen = 249, tg = 23.17 t/s, tg_3s = 24.60 t/s 2.05.073.401 I slot print_timing: id 0 | task 1021 | n_gen = 249, tg = 24.69 t/s, tg_3s = 24.61 t/s 2.05.114.437 I slot print_timing: id 1 | task 672 | n_gen = 596, tg = 23.65 t/s, tg_3s = 24.61 t/s 2.05.236.438 I slot print_timing: id 2 | task 265 | n_gen = 1002, tg = 23.12 t/s, tg_3s = 24.62 t/s 2.06.133.226 I slot print_timing: id 2 | task 265 | prompt eval time = 6428.56 ms / 1159 tokens ( 5.55 ms per token, 180.29 tokens per second) 2.06.133.230 I slot print_timing: id 2 | task 265 | eval time = 44193.62 ms / 1024 tokens ( 43.20 ms per token, 23.15 tokens per second) 2.06.133.231 I slot print_timing: id 2 | task 265 | total time = 50622.18 ms / 2183 tokens 2.06.133.232 I slot print_timing: id 2 | task 265 | graphs reused = 1002 2.06.133.233 I slot print_timing: id 2 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.133.335 I slot release: id 2 | task 265 | stop processing: n_tokens = 2182, truncated = 0 2.06.176.242 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.489 2.06.182.206 I slot launch_slot_: id 2 | task 1299 | processing task, is_child = 0 2.07.084.083 I slot print_timing: id 3 | task 986 | n_gen = 312, tg = 22.07 t/s, tg_3s = 18.59 t/s 2.08.091.251 I slot print_timing: id 0 | task 1021 | n_gen = 302, tg = 23.04 t/s, tg_3s = 17.56 t/s 2.08.132.521 I slot print_timing: id 1 | task 672 | n_gen = 649, tg = 23.00 t/s, tg_3s = 17.56 t/s 2.10.111.521 I slot print_timing: id 3 | task 986 | n_gen = 386, tg = 22.49 t/s, tg_3s = 24.44 t/s 2.11.118.101 I slot print_timing: id 0 | task 1021 | n_gen = 377, tg = 23.37 t/s, tg_3s = 24.78 t/s 2.11.159.210 I slot print_timing: id 1 | task 672 | n_gen = 724, tg = 23.17 t/s, tg_3s = 24.78 t/s 2.11.159.702 I slot print_timing: id 2 | task 1299 | n_gen = 100, tg = 24.75 t/s, tg_3s = 25.00 t/s 2.13.143.069 I slot print_timing: id 3 | task 986 | n_gen = 461, tg = 22.83 t/s, tg_3s = 24.74 t/s 2.14.152.367 I slot print_timing: id 0 | task 1021 | n_gen = 452, tg = 23.58 t/s, tg_3s = 24.72 t/s 2.14.193.209 I slot print_timing: id 1 | task 672 | n_gen = 799, tg = 23.31 t/s, tg_3s = 24.72 t/s 2.14.193.793 I slot print_timing: id 2 | task 1299 | n_gen = 175, tg = 24.74 t/s, tg_3s = 24.72 t/s 2.15.447.397 I slot print_timing: id 3 | task 986 | prompt eval time = 502.33 ms / 257 tokens ( 1.95 ms per token, 511.61 tokens per second) 2.15.447.402 I slot print_timing: id 3 | task 986 | eval time = 22454.28 ms / 518 tokens ( 43.43 ms per token, 23.02 tokens per second) 2.15.447.402 I slot print_timing: id 3 | task 986 | total time = 22956.62 ms / 775 tokens 2.15.447.403 I slot print_timing: id 3 | task 986 | graphs reused = 1206 2.15.447.404 I slot print_timing: id 3 | task 986 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.447.502 I slot release: id 3 | task 986 | stop processing: n_tokens = 1698, truncated = 0 2.15.482.814 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.629 2.15.482.858 I slot launch_slot_: id 3 | task 1509 | processing task, is_child = 0 2.17.152.585 I slot print_timing: id 0 | task 1021 | n_gen = 515, tg = 23.23 t/s, tg_3s = 21.00 t/s 2.17.193.605 I slot print_timing: id 1 | task 672 | n_gen = 862, tg = 23.12 t/s, tg_3s = 21.00 t/s 2.17.194.123 I slot print_timing: id 2 | task 1299 | n_gen = 238, tg = 23.62 t/s, tg_3s = 21.00 t/s 2.20.035.771 I slot print_timing: id 3 | task 1509 | n_gen = 100, tg = 24.63 t/s, tg_3s = 24.88 t/s 2.20.155.666 I slot print_timing: id 0 | task 1021 | n_gen = 589, tg = 23.40 t/s, tg_3s = 24.64 t/s 2.20.196.848 I slot print_timing: id 1 | task 672 | n_gen = 936, tg = 23.23 t/s, tg_3s = 24.64 t/s 2.20.197.339 I slot print_timing: id 2 | task 1299 | n_gen = 312, tg = 23.86 t/s, tg_3s = 24.64 t/s 2.21.128.990 I slot print_timing: id 2 | task 1299 | prompt eval time = 978.24 ms / 543 tokens ( 1.80 ms per token, 555.08 tokens per second) 2.21.128.995 I slot print_timing: id 2 | task 1299 | eval time = 13968.52 ms / 335 tokens ( 41.82 ms per token, 23.91 tokens per second) 2.21.128.996 I slot print_timing: id 2 | task 1299 | total time = 14946.76 ms / 878 tokens 2.21.129.000 I slot print_timing: id 2 | task 1299 | graphs reused = 1330 2.21.129.001 I slot print_timing: id 2 | task 1299 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.129.141 I slot release: id 2 | task 1299 | stop processing: n_tokens = 1520, truncated = 0 2.21.172.217 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.703 2.21.172.252 I slot launch_slot_: id 2 | task 1639 | processing task, is_child = 0 2.23.069.387 I slot print_timing: id 3 | task 1509 | n_gen = 158, tg = 22.26 t/s, tg_3s = 19.12 t/s 2.23.189.107 I slot print_timing: id 0 | task 1021 | n_gen = 647, tg = 22.94 t/s, tg_3s = 19.12 t/s 2.23.230.235 I slot print_timing: id 1 | task 672 | n_gen = 994, tg = 22.95 t/s, tg_3s = 19.12 t/s 2.24.447.855 I slot print_timing: id 1 | task 672 | prompt eval time = 1024.04 ms / 563 tokens ( 1.82 ms per token, 549.78 tokens per second) 2.24.447.862 I slot print_timing: id 1 | task 672 | eval time = 44494.72 ms / 1024 tokens ( 43.49 ms per token, 22.99 tokens per second) 2.24.447.863 I slot print_timing: id 1 | task 672 | total time = 45518.76 ms / 1587 tokens 2.24.447.864 I slot print_timing: id 1 | task 672 | graphs reused = 1391 2.24.447.865 I slot print_timing: id 1 | task 672 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.447.970 I slot release: id 1 | task 672 | stop processing: n_tokens = 2203, truncated = 0 2.24.491.112 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.485 2.24.497.119 I slot launch_slot_: id 1 | task 1705 | processing task, is_child = 0 2.26.088.425 I slot print_timing: id 3 | task 1509 | n_gen = 216, tg = 21.35 t/s, tg_3s = 19.21 t/s 2.26.207.416 I slot print_timing: id 0 | task 1021 | n_gen = 705, tg = 22.58 t/s, tg_3s = 19.22 t/s 2.26.611.157 I slot print_timing: id 2 | task 1639 | n_gen = 100, tg = 21.17 t/s, tg_3s = 21.38 t/s 2.27.535.812 I slot print_timing: id 0 | task 1021 | prompt eval time = 740.49 ms / 500 tokens ( 1.48 ms per token, 675.23 tokens per second) 2.27.535.818 I slot print_timing: id 0 | task 1021 | eval time = 32507.38 ms / 738 tokens ( 44.11 ms per token, 22.67 tokens per second) 2.27.535.819 I slot print_timing: id 0 | task 1021 | total time = 33247.87 ms / 1238 tokens 2.27.535.820 I slot print_timing: id 0 | task 1021 | graphs reused = 1447 2.27.535.821 I slot print_timing: id 0 | task 1021 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.535.919 I slot release: id 0 | task 1021 | stop processing: n_tokens = 1892, truncated = 0 2.27.572.616 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.564 2.27.572.666 I slot launch_slot_: id 0 | task 1766 | processing task, is_child = 0 2.29.107.610 I slot print_timing: id 3 | task 1509 | n_gen = 275, tg = 20.93 t/s, tg_3s = 19.54 t/s 2.29.627.604 I slot print_timing: id 2 | task 1639 | n_gen = 159, tg = 20.54 t/s, tg_3s = 19.56 t/s 2.29.868.045 I slot print_timing: id 1 | task 1705 | n_gen = 100, tg = 21.40 t/s, tg_3s = 21.61 t/s 2.32.122.591 I slot print_timing: id 3 | task 1509 | n_gen = 350, tg = 21.67 t/s, tg_3s = 24.88 t/s 2.32.281.992 I slot print_timing: id 0 | task 1766 | n_gen = 100, tg = 24.89 t/s, tg_3s = 25.14 t/s 2.32.645.472 I slot print_timing: id 2 | task 1639 | n_gen = 234, tg = 21.75 t/s, tg_3s = 24.85 t/s 2.32.886.617 I slot print_timing: id 1 | task 1705 | n_gen = 175, tg = 22.76 t/s, tg_3s = 24.85 t/s 2.35.149.235 I slot print_timing: id 3 | task 1509 | n_gen = 425, tg = 22.16 t/s, tg_3s = 24.78 t/s 2.35.309.373 I slot print_timing: id 0 | task 1766 | n_gen = 175, tg = 24.84 t/s, tg_3s = 24.77 t/s 2.35.673.021 I slot print_timing: id 2 | task 1639 | n_gen = 309, tg = 22.42 t/s, tg_3s = 24.77 t/s 2.35.913.852 I slot print_timing: id 1 | task 1705 | n_gen = 250, tg = 23.33 t/s, tg_3s = 24.78 t/s 2.38.172.726 I slot print_timing: id 3 | task 1509 | n_gen = 500, tg = 22.52 t/s, tg_3s = 24.81 t/s 2.38.332.498 I slot print_timing: id 0 | task 1766 | n_gen = 250, tg = 24.83 t/s, tg_3s = 24.81 t/s 2.38.697.176 I slot print_timing: id 2 | task 1639 | n_gen = 384, tg = 22.85 t/s, tg_3s = 24.80 t/s 2.38.938.788 I slot print_timing: id 1 | task 1705 | n_gen = 325, tg = 23.65 t/s, tg_3s = 24.79 t/s 2.39.745.794 I slot print_timing: id 1 | task 1705 | prompt eval time = 744.08 ms / 481 tokens ( 1.55 ms per token, 646.44 tokens per second) 2.39.745.801 I slot print_timing: id 1 | task 1705 | eval time = 14504.59 ms / 345 tokens ( 42.16 ms per token, 23.72 tokens per second) 2.39.745.802 I slot print_timing: id 1 | task 1705 | total time = 15248.66 ms / 826 tokens 2.39.745.802 I slot print_timing: id 1 | task 1705 | graphs reused = 1730 2.39.745.803 I slot print_timing: id 1 | task 1705 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.745.913 I slot release: id 1 | task 1705 | stop processing: n_tokens = 1489, truncated = 0 2.39.789.504 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.717 2.39.789.541 I slot launch_slot_: id 1 | task 2054 | processing task, is_child = 0 2.41.206.585 I slot print_timing: id 3 | task 1509 | n_gen = 559, tg = 22.15 t/s, tg_3s = 19.45 t/s 2.41.365.999 I slot print_timing: id 0 | task 1766 | n_gen = 309, tg = 23.58 t/s, tg_3s = 19.45 t/s 2.41.728.860 I slot print_timing: id 2 | task 1639 | n_gen = 443, tg = 22.33 t/s, tg_3s = 19.46 t/s 2.44.227.495 I slot print_timing: id 3 | task 1509 | n_gen = 634, tg = 22.44 t/s, tg_3s = 24.83 t/s 2.44.386.221 I slot print_timing: id 0 | task 1766 | n_gen = 384, tg = 23.82 t/s, tg_3s = 24.83 t/s 2.44.506.852 I slot print_timing: id 1 | task 2054 | n_gen = 100, tg = 24.87 t/s, tg_3s = 25.12 t/s 2.44.747.804 I slot print_timing: id 2 | task 1639 | n_gen = 518, tg = 22.66 t/s, tg_3s = 24.84 t/s 2.44.828.350 I slot print_timing: id 2 | task 1639 | prompt eval time = 762.26 ms / 498 tokens ( 1.53 ms per token, 653.32 tokens per second) 2.44.828.357 I slot print_timing: id 2 | task 1639 | eval time = 22893.83 ms / 520 tokens ( 44.11 ms per token, 22.67 tokens per second) 2.44.828.358 I slot print_timing: id 2 | task 1639 | total time = 23656.09 ms / 1018 tokens 2.44.828.359 I slot print_timing: id 2 | task 1639 | graphs reused = 1835 2.44.828.360 I slot print_timing: id 2 | task 1639 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.828.484 I slot release: id 2 | task 1639 | stop processing: n_tokens = 1687, truncated = 0 2.44.871.498 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.633 2.44.871.550 I slot launch_slot_: id 2 | task 2165 | processing task, is_child = 0 2.46.165.253 I slot print_timing: id 3 | task 1509 | prompt eval time = 533.38 ms / 287 tokens ( 1.86 ms per token, 538.08 tokens per second) 2.46.165.258 I slot print_timing: id 3 | task 1509 | eval time = 30149.01 ms / 665 tokens ( 45.41 ms per token, 22.02 tokens per second) 2.46.165.259 I slot print_timing: id 3 | task 1509 | total time = 30682.38 ms / 952 tokens 2.46.165.260 I slot print_timing: id 3 | task 1509 | graphs reused = 1847 2.46.165.261 I slot print_timing: id 3 | task 1509 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.165.367 I slot release: id 3 | task 1509 | stop processing: n_tokens = 1875, truncated = 0 2.46.200.603 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.570 2.46.200.642 I slot launch_slot_: id 3 | task 2182 | processing task, is_child = 0 2.47.407.518 I slot print_timing: id 0 | task 1766 | n_gen = 431, tg = 22.51 t/s, tg_3s = 15.56 t/s 2.47.528.906 I slot print_timing: id 1 | task 2054 | n_gen = 147, tg = 20.85 t/s, tg_3s = 15.55 t/s 2.50.066.835 I slot print_timing: id 2 | task 2165 | n_gen = 100, tg = 22.32 t/s, tg_3s = 22.55 t/s 2.50.427.917 I slot print_timing: id 0 | task 1766 | n_gen = 506, tg = 22.83 t/s, tg_3s = 24.83 t/s 2.50.549.603 I slot print_timing: id 1 | task 2054 | n_gen = 222, tg = 22.05 t/s, tg_3s = 24.83 t/s 2.50.711.930 I slot print_timing: id 3 | task 2182 | n_gen = 100, tg = 24.80 t/s, tg_3s = 25.05 t/s 2.51.436.122 I slot print_timing: id 0 | task 1766 | prompt eval time = 731.70 ms / 488 tokens ( 1.50 ms per token, 666.94 tokens per second) 2.51.436.128 I slot print_timing: id 0 | task 1766 | eval time = 23131.75 ms / 531 tokens ( 43.64 ms per token, 22.91 tokens per second) 2.51.436.129 I slot print_timing: id 0 | task 1766 | total time = 23863.45 ms / 1019 tokens 2.51.436.133 I slot print_timing: id 0 | task 1766 | graphs reused = 1963 2.51.436.134 I slot print_timing: id 0 | task 1766 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.436.238 I slot release: id 0 | task 1766 | stop processing: n_tokens = 1673, truncated = 0 2.51.473.144 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.638 2.51.473.189 I slot launch_slot_: id 0 | task 2303 | processing task, is_child = 0 2.53.079.542 I slot print_timing: id 2 | task 2165 | n_gen = 159, tg = 21.21 t/s, tg_3s = 19.58 t/s 2.53.561.288 I slot print_timing: id 1 | task 2054 | n_gen = 281, tg = 21.48 t/s, tg_3s = 19.59 t/s 2.53.723.146 I slot print_timing: id 3 | task 2182 | n_gen = 159, tg = 22.56 t/s, tg_3s = 19.59 t/s 2.56.099.845 I slot print_timing: id 2 | task 2165 | n_gen = 234, tg = 22.26 t/s, tg_3s = 24.83 t/s 2.56.179.294 I slot print_timing: id 0 | task 2303 | n_gen = 100, tg = 24.79 t/s, tg_3s = 25.04 t/s 2.56.582.321 I slot print_timing: id 1 | task 2054 | n_gen = 356, tg = 22.11 t/s, tg_3s = 24.83 t/s 2.56.744.534 I slot print_timing: id 3 | task 2182 | n_gen = 234, tg = 23.24 t/s, tg_3s = 24.82 t/s 2.58.631.688 I slot print_timing: id 1 | task 2054 | prompt eval time = 735.91 ms / 473 tokens ( 1.56 ms per token, 642.74 tokens per second) 2.58.631.692 I slot print_timing: id 1 | task 2054 | eval time = 18106.22 ms / 407 tokens ( 44.60 ms per token, 22.42 tokens per second) 2.58.631.694 I slot print_timing: id 1 | task 2054 | total time = 18842.14 ms / 880 tokens 2.58.631.695 I slot print_timing: id 1 | task 2054 | graphs reused = 2122 2.58.631.696 I slot print_timing: id 1 | task 2054 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.631.793 I slot release: id 1 | task 2054 | stop processing: n_tokens = 1543, truncated = 0 2.58.674.955 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.692 2.58.674.991 I slot launch_slot_: id 1 | task 2467 | processing task, is_child = 0 2.59.369.714 I slot print_timing: id 0 | task 2303 | n_gen = 163, tg = 22.55 t/s, tg_3s = 19.75 t/s 2.59.369.992 I slot print_timing: id 2 | task 2165 | n_gen = 299, tg = 21.69 t/s, tg_3s = 19.88 t/s 2.59.765.011 I slot print_timing: id 3 | task 2182 | n_gen = 292, tg = 22.31 t/s, tg_3s = 19.20 t/s 3.02.390.807 I slot print_timing: id 0 | task 2303 | n_gen = 237, tg = 23.12 t/s, tg_3s = 24.49 t/s 3.02.391.846 I slot print_timing: id 2 | task 2165 | n_gen = 373, tg = 22.20 t/s, tg_3s = 24.49 t/s 3.02.796.450 I slot print_timing: id 3 | task 2182 | n_gen = 367, tg = 22.77 t/s, tg_3s = 24.74 t/s 3.03.441.781 I slot print_timing: id 1 | task 2467 | n_gen = 100, tg = 24.79 t/s, tg_3s = 25.04 t/s 3.05.420.565 I slot print_timing: id 0 | task 2303 | n_gen = 312, tg = 23.50 t/s, tg_3s = 24.75 t/s 3.05.421.775 I slot print_timing: id 2 | task 2165 | n_gen = 448, tg = 22.59 t/s, tg_3s = 24.75 t/s 3.05.826.248 I slot print_timing: id 3 | task 2182 | n_gen = 442, tg = 23.08 t/s, tg_3s = 24.75 t/s 3.06.470.284 I slot print_timing: id 1 | task 2467 | n_gen = 175, tg = 24.78 t/s, tg_3s = 24.76 t/s 3.08.452.650 I slot print_timing: id 0 | task 2303 | n_gen = 387, tg = 23.73 t/s, tg_3s = 24.74 t/s 3.08.453.678 I slot print_timing: id 2 | task 2165 | n_gen = 523, tg = 22.87 t/s, tg_3s = 24.74 t/s 3.08.815.928 I slot print_timing: id 0 | task 2303 | prompt eval time = 711.76 ms / 473 tokens ( 1.50 ms per token, 664.55 tokens per second) 3.08.815.936 I slot print_timing: id 0 | task 2303 | eval time = 16630.97 ms / 396 tokens ( 42.10 ms per token, 23.75 tokens per second) 3.08.815.936 I slot print_timing: id 0 | task 2303 | total time = 17342.73 ms / 869 tokens 3.08.815.937 I slot print_timing: id 0 | task 2303 | graphs reused = 2352 3.08.815.938 I slot print_timing: id 0 | task 2303 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.816.039 I slot release: id 0 | task 2303 | stop processing: n_tokens = 1523, truncated = 0 3.08.853.124 I slot print_timing: id 3 | task 2182 | n_gen = 517, tg = 23.31 t/s, tg_3s = 24.78 t/s 3.08.853.130 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.701 3.08.853.158 I slot launch_slot_: id 0 | task 2703 | processing task, is_child = 0 3.09.515.683 I slot print_timing: id 1 | task 2467 | n_gen = 235, tg = 23.24 t/s, tg_3s = 19.70 t/s 3.11.477.202 I slot print_timing: id 2 | task 2165 | n_gen = 582, tg = 22.48 t/s, tg_3s = 19.51 t/s 3.11.881.422 I slot print_timing: id 3 | task 2182 | n_gen = 576, tg = 22.85 t/s, tg_3s = 19.48 t/s 3.12.527.178 I slot print_timing: id 1 | task 2467 | n_gen = 309, tg = 23.55 t/s, tg_3s = 24.57 t/s 3.12.609.246 I slot print_timing: id 3 | task 2182 | prompt eval time = 518.84 ms / 267 tokens ( 1.94 ms per token, 514.61 tokens per second) 3.12.609.254 I slot print_timing: id 3 | task 2182 | eval time = 25889.74 ms / 594 tokens ( 43.66 ms per token, 22.90 tokens per second) 3.12.609.255 I slot print_timing: id 3 | task 2182 | total time = 26408.59 ms / 861 tokens 3.12.609.255 I slot print_timing: id 3 | task 2182 | graphs reused = 2427 3.12.609.256 I slot print_timing: id 3 | task 2182 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.609.359 I slot release: id 3 | task 2182 | stop processing: n_tokens = 1784, truncated = 0 3.12.644.667 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.599 3.12.644.711 I slot launch_slot_: id 3 | task 2782 | processing task, is_child = 0 3.13.943.505 I slot print_timing: id 0 | task 2703 | n_gen = 100, tg = 22.71 t/s, tg_3s = 22.94 t/s 3.14.226.151 I slot print_timing: id 1 | task 2467 | prompt eval time = 773.08 ms / 506 tokens ( 1.53 ms per token, 654.52 tokens per second) 3.14.226.158 I slot print_timing: id 1 | task 2467 | eval time = 14778.06 ms / 342 tokens ( 43.34 ms per token, 23.07 tokens per second) 3.14.226.159 I slot print_timing: id 1 | task 2467 | total time = 15551.14 ms / 848 tokens 3.14.226.159 I slot print_timing: id 1 | task 2467 | graphs reused = 2453 3.14.226.160 I slot print_timing: id 1 | task 2467 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.226.262 I slot release: id 1 | task 2467 | stop processing: n_tokens = 1511, truncated = 0 3.14.269.523 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.707 3.14.269.564 I slot launch_slot_: id 1 | task 2814 | processing task, is_child = 0 3.14.936.428 I slot print_timing: id 2 | task 2165 | n_gen = 643, tg = 21.91 t/s, tg_3s = 17.63 t/s 3.16.952.300 I slot print_timing: id 0 | task 2703 | n_gen = 158, tg = 21.31 t/s, tg_3s = 19.28 t/s 3.17.762.095 I slot print_timing: id 3 | task 2782 | n_gen = 100, tg = 21.24 t/s, tg_3s = 21.45 t/s 3.17.962.569 I slot print_timing: id 2 | task 2165 | n_gen = 717, tg = 22.15 t/s, tg_3s = 24.45 t/s 3.19.011.100 I slot print_timing: id 1 | task 2814 | n_gen = 100, tg = 24.77 t/s, tg_3s = 25.02 t/s 3.19.980.318 I slot print_timing: id 0 | task 2703 | n_gen = 233, tg = 22.32 t/s, tg_3s = 24.77 t/s 3.20.305.324 I slot print_timing: id 2 | task 2165 | prompt eval time = 759.85 ms / 496 tokens ( 1.53 ms per token, 652.76 tokens per second) 3.20.305.331 I slot print_timing: id 2 | task 2165 | eval time = 34673.92 ms / 775 tokens ( 44.80 ms per token, 22.32 tokens per second) 3.20.305.332 I slot print_timing: id 2 | task 2165 | total time = 35433.76 ms / 1271 tokens 3.20.305.333 I slot print_timing: id 2 | task 2165 | graphs reused = 2583 3.20.305.334 I slot print_timing: id 2 | task 2165 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.305.443 I slot release: id 2 | task 2165 | stop processing: n_tokens = 1940, truncated = 0 3.20.348.523 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.551 3.20.348.580 I slot launch_slot_: id 2 | task 2949 | processing task, is_child = 0 3.21.002.133 I slot print_timing: id 3 | task 2782 | n_gen = 165, tg = 20.76 t/s, tg_3s = 20.06 t/s 3.22.011.305 I slot print_timing: id 1 | task 2814 | n_gen = 158, tg = 22.44 t/s, tg_3s = 19.33 t/s 3.23.019.767 I slot print_timing: id 0 | task 2703 | n_gen = 292, tg = 21.66 t/s, tg_3s = 19.41 t/s 3.24.029.597 I slot print_timing: id 3 | task 2782 | n_gen = 239, tg = 21.78 t/s, tg_3s = 24.44 t/s 3.25.036.979 I slot print_timing: id 1 | task 2814 | n_gen = 233, tg = 23.15 t/s, tg_3s = 24.79 t/s 3.25.078.064 I slot print_timing: id 2 | task 2949 | n_gen = 100, tg = 24.75 t/s, tg_3s = 25.00 t/s 3.26.048.583 I slot print_timing: id 0 | task 2703 | n_gen = 367, tg = 22.23 t/s, tg_3s = 24.76 t/s 3.27.058.662 I slot print_timing: id 3 | task 2782 | n_gen = 314, tg = 22.42 t/s, tg_3s = 24.76 t/s 3.28.072.480 I slot print_timing: id 1 | task 2814 | n_gen = 308, tg = 23.51 t/s, tg_3s = 24.71 t/s 3.28.113.758 I slot print_timing: id 2 | task 2949 | n_gen = 175, tg = 24.73 t/s, tg_3s = 24.71 t/s 3.29.079.449 I slot print_timing: id 0 | task 2703 | n_gen = 442, tg = 22.62 t/s, tg_3s = 24.75 t/s 3.29.402.191 I slot print_timing: id 0 | task 2703 | prompt eval time = 730.72 ms / 487 tokens ( 1.50 ms per token, 666.46 tokens per second) 3.29.402.197 I slot print_timing: id 0 | task 2703 | eval time = 19818.30 ms / 450 tokens ( 44.14 ms per token, 22.66 tokens per second) 3.29.402.199 I slot print_timing: id 0 | task 2703 | total time = 20549.02 ms / 937 tokens 3.29.402.200 I slot print_timing: id 0 | task 2703 | graphs reused = 2787 3.29.402.201 I slot print_timing: id 0 | task 2703 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.402.299 I slot release: id 0 | task 2703 | stop processing: n_tokens = 1591, truncated = 0 3.29.439.417 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.671 3.29.439.450 I slot launch_slot_: id 0 | task 3159 | processing task, is_child = 0 3.30.226.357 I slot print_timing: id 3 | task 2782 | n_gen = 375, tg = 21.84 t/s, tg_3s = 19.26 t/s 3.30.611.304 I slot print_timing: id 1 | task 2814 | prompt eval time = 744.61 ms / 481 tokens ( 1.55 ms per token, 645.97 tokens per second) 3.30.611.311 I slot print_timing: id 1 | task 2814 | eval time = 15597.12 ms / 353 tokens ( 44.31 ms per token, 22.57 tokens per second) 3.30.611.312 I slot print_timing: id 1 | task 2814 | total time = 16341.73 ms / 834 tokens 3.30.611.313 I slot print_timing: id 1 | task 2814 | graphs reused = 2795 3.30.611.313 I slot print_timing: id 1 | task 2814 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.611.415 I slot release: id 1 | task 2814 | stop processing: n_tokens = 1497, truncated = 0 3.30.655.039 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.713 3.30.655.087 I slot launch_slot_: id 1 | task 3172 | processing task, is_child = 0 3.31.310.605 I slot print_timing: id 2 | task 2949 | n_gen = 221, tg = 21.50 t/s, tg_3s = 14.39 t/s 3.33.245.893 I slot print_timing: id 3 | task 2782 | n_gen = 433, tg = 21.44 t/s, tg_3s = 19.21 t/s 3.34.332.245 I slot print_timing: id 2 | task 2949 | n_gen = 295, tg = 22.18 t/s, tg_3s = 24.49 t/s 3.34.934.295 I slot print_timing: id 0 | task 3159 | n_gen = 100, tg = 21.33 t/s, tg_3s = 21.55 t/s 3.35.376.463 I slot print_timing: id 1 | task 3172 | n_gen = 100, tg = 24.82 t/s, tg_3s = 25.07 t/s 3.36.263.978 I slot print_timing: id 3 | task 2782 | n_gen = 508, tg = 21.89 t/s, tg_3s = 24.85 t/s 3.37.354.639 I slot print_timing: id 2 | task 2949 | n_gen = 370, tg = 22.67 t/s, tg_3s = 24.81 t/s 3.37.960.651 I slot print_timing: id 0 | task 3159 | n_gen = 175, tg = 22.70 t/s, tg_3s = 24.78 t/s 3.38.406.602 I slot print_timing: id 1 | task 3172 | n_gen = 175, tg = 24.79 t/s, tg_3s = 24.75 t/s 3.38.891.978 I slot print_timing: id 2 | task 2949 | prompt eval time = 729.67 ms / 468 tokens ( 1.56 ms per token, 641.38 tokens per second) 3.38.891.984 I slot print_timing: id 2 | task 2949 | eval time = 17813.72 ms / 408 tokens ( 43.77 ms per token, 22.85 tokens per second) 3.38.891.985 I slot print_timing: id 2 | task 2949 | total time = 18543.39 ms / 876 tokens 3.38.891.986 I slot print_timing: id 2 | task 2949 | graphs reused = 2979 3.38.891.986 I slot print_timing: id 2 | task 2949 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.892.089 I slot release: id 2 | task 2949 | stop processing: n_tokens = 1545, truncated = 0 3.38.935.044 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.691 3.38.935.077 I slot launch_slot_: id 2 | task 3362 | processing task, is_child = 0 3.39.586.744 I slot print_timing: id 3 | task 2782 | n_gen = 575, tg = 21.67 t/s, tg_3s = 20.16 t/s 3.40.994.647 I slot print_timing: id 0 | task 3159 | n_gen = 234, tg = 21.77 t/s, tg_3s = 19.45 t/s 3.41.437.871 I slot print_timing: id 1 | task 3172 | n_gen = 234, tg = 23.19 t/s, tg_3s = 19.46 t/s 3.42.605.791 I slot print_timing: id 3 | task 2782 | n_gen = 649, tg = 21.96 t/s, tg_3s = 24.51 t/s 3.43.655.410 I slot print_timing: id 2 | task 3362 | n_gen = 100, tg = 24.80 t/s, tg_3s = 25.05 t/s 3.44.017.541 I slot print_timing: id 0 | task 3159 | n_gen = 309, tg = 22.44 t/s, tg_3s = 24.81 t/s 3.44.462.488 I slot print_timing: id 1 | task 3172 | n_gen = 309, tg = 23.56 t/s, tg_3s = 24.80 t/s 3.45.633.778 I slot print_timing: id 3 | task 2782 | n_gen = 724, tg = 22.22 t/s, tg_3s = 24.77 t/s 3.46.684.296 I slot print_timing: id 2 | task 3362 | n_gen = 175, tg = 24.78 t/s, tg_3s = 24.76 t/s 3.47.046.371 I slot print_timing: id 0 | task 3159 | n_gen = 384, tg = 22.86 t/s, tg_3s = 24.76 t/s 3.47.490.655 I slot print_timing: id 1 | task 3172 | n_gen = 384, tg = 23.79 t/s, tg_3s = 24.77 t/s 3.48.420.589 I slot print_timing: id 3 | task 2782 | prompt eval time = 456.17 ms / 204 tokens ( 2.24 ms per token, 447.20 tokens per second) 3.48.420.594 I slot print_timing: id 3 | task 2782 | eval time = 35319.69 ms / 793 tokens ( 44.60 ms per token, 22.42 tokens per second) 3.48.420.595 I slot print_timing: id 3 | task 2782 | total time = 35775.86 ms / 997 tokens 3.48.420.596 I slot print_timing: id 3 | task 2782 | graphs reused = 3194 3.48.420.597 I slot print_timing: id 3 | task 2782 | graph reallocs = 0 / 0 (same size) / (changed size) 3.48.420.703 I slot release: id 3 | task 2782 | stop processing: n_tokens = 1920, truncated = 0 3.48.456.063 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.556 3.48.456.098 I slot launch_slot_: id 3 | task 3583 | processing task, is_child = 0 3.49.719.819 I slot print_timing: id 2 | task 3362 | n_gen = 241, tg = 23.86 t/s, tg_3s = 21.74 t/s 3.50.081.914 I slot print_timing: id 0 | task 3159 | n_gen = 450, tg = 22.69 t/s, tg_3s = 21.74 t/s 3.50.525.911 I slot print_timing: id 1 | task 3172 | n_gen = 450, tg = 23.46 t/s, tg_3s = 21.74 t/s 3.51.371.454 I slot print_timing: id 2 | task 3362 | prompt eval time = 728.00 ms / 467 tokens ( 1.56 ms per token, 641.49 tokens per second) 3.51.371.461 I slot print_timing: id 2 | task 3362 | eval time = 11708.37 ms / 282 tokens ( 41.67 ms per token, 24.00 tokens per second) 3.51.371.462 I slot print_timing: id 2 | task 3362 | total time = 12436.37 ms / 749 tokens 3.51.371.463 I slot print_timing: id 2 | task 3362 | graphs reused = 3254 3.51.371.464 I slot print_timing: id 2 | task 3362 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.371.562 I slot release: id 2 | task 3362 | stop processing: n_tokens = 1418, truncated = 0 3.51.414.300 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.753 3.51.414.342 I slot launch_slot_: id 2 | task 3648 | processing task, is_child = 0 3.53.102.321 I slot print_timing: id 0 | task 3159 | n_gen = 508, tg = 22.23 t/s, tg_3s = 19.20 t/s 3.53.545.057 I slot print_timing: id 1 | task 3172 | n_gen = 508, tg = 22.88 t/s, tg_3s = 19.21 t/s 3.53.586.267 I slot print_timing: id 3 | task 3583 | n_gen = 100, tg = 21.18 t/s, tg_3s = 21.39 t/s 3.56.133.230 I slot print_timing: id 0 | task 3159 | n_gen = 583, tg = 22.52 t/s, tg_3s = 24.75 t/s 3.56.174.820 I slot print_timing: id 2 | task 3648 | n_gen = 100, tg = 24.79 t/s, tg_3s = 25.04 t/s 3.56.578.375 I slot print_timing: id 1 | task 3172 | n_gen = 583, tg = 23.10 t/s, tg_3s = 24.73 t/s 3.56.619.871 I slot print_timing: id 3 | task 3583 | n_gen = 175, tg = 22.57 t/s, tg_3s = 24.72 t/s 3.59.171.078 I slot print_timing: id 0 | task 3159 | n_gen = 658, tg = 22.75 t/s, tg_3s = 24.69 t/s 3.59.212.687 I slot print_timing: id 2 | task 3648 | n_gen = 175, tg = 24.75 t/s, tg_3s = 24.69 t/s 3.59.617.258 I slot print_timing: id 1 | task 3172 | n_gen = 658, tg = 23.27 t/s, tg_3s = 24.68 t/s 3.59.659.121 I slot print_timing: id 3 | task 3583 | n_gen = 250, tg = 23.17 t/s, tg_3s = 24.68 t/s 4.02.207.887 I slot print_timing: id 0 | task 3159 | n_gen = 733, tg = 22.94 t/s, tg_3s = 24.70 t/s 4.02.249.252 I slot print_timing: id 2 | task 3648 | n_gen = 250, tg = 24.73 t/s, tg_3s = 24.70 t/s 4.02.652.322 I slot print_timing: id 1 | task 3172 | n_gen = 733, tg = 23.41 t/s, tg_3s = 24.71 t/s 4.02.693.960 I slot print_timing: id 3 | task 3583 | n_gen = 325, tg = 23.51 t/s, tg_3s = 24.71 t/s 4.04.632.252 I slot print_timing: id 1 | task 3172 | prompt eval time = 733.18 ms / 469 tokens ( 1.56 ms per token, 639.68 tokens per second) 4.04.632.259 I slot print_timing: id 1 | task 3172 | eval time = 33243.98 ms / 782 tokens ( 42.57 ms per token, 23.49 tokens per second) 4.04.632.260 I slot print_timing: id 1 | task 3172 | total time = 33977.15 ms / 1251 tokens 4.04.632.260 I slot print_timing: id 1 | task 3172 | graphs reused = 3560 4.04.632.261 I slot print_timing: id 1 | task 3172 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.632.361 I slot release: id 1 | task 3172 | stop processing: n_tokens = 1914, truncated = 0 4.04.675.481 I slot print_timing: id 3 | task 3583 | prompt eval time = 456.04 ms / 206 tokens ( 2.21 ms per token, 451.72 tokens per second) 4.04.675.486 I slot print_timing: id 3 | task 3583 | eval time = 15763.33 ms / 374 tokens ( 42.26 ms per token, 23.66 tokens per second) 4.04.675.487 I slot print_timing: id 3 | task 3583 | total time = 16219.37 ms / 580 tokens 4.04.675.488 I slot print_timing: id 3 | task 3583 | graphs reused = 3560 4.04.675.488 I slot print_timing: id 3 | task 3583 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.675.594 I slot release: id 3 | task 3583 | stop processing: n_tokens = 1503, truncated = 0 4.04.675.606 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.558 4.04.675.646 I slot launch_slot_: id 1 | task 3960 | processing task, is_child = 0 4.05.366.588 I slot print_timing: id 0 | task 3159 | n_gen = 795, tg = 22.64 t/s, tg_3s = 19.63 t/s 4.05.367.783 I slot print_timing: id 2 | task 3648 | n_gen = 311, tg = 23.51 t/s, tg_3s = 19.56 t/s 4.05.367.801 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.711 4.05.367.900 I slot launch_slot_: id 3 | task 3962 | processing task, is_child = 0 4.08.390.802 I slot print_timing: id 0 | task 3159 | n_gen = 858, tg = 22.50 t/s, tg_3s = 20.83 t/s 4.08.391.981 I slot print_timing: id 2 | task 3648 | n_gen = 374, tg = 23.01 t/s, tg_3s = 20.83 t/s 4.09.886.792 I slot print_timing: id 1 | task 3960 | n_gen = 100, tg = 24.54 t/s, tg_3s = 24.79 t/s 4.09.928.465 I slot print_timing: id 3 | task 3962 | n_gen = 100, tg = 24.71 t/s, tg_3s = 24.96 t/s 4.11.424.826 I slot print_timing: id 0 | task 3159 | n_gen = 933, tg = 22.66 t/s, tg_3s = 24.72 t/s 4.11.425.979 I slot print_timing: id 2 | task 3648 | n_gen = 449, tg = 23.28 t/s, tg_3s = 24.72 t/s 4.12.923.856 I slot print_timing: id 1 | task 3960 | n_gen = 175, tg = 24.61 t/s, tg_3s = 24.69 t/s 4.12.965.417 I slot print_timing: id 3 | task 3962 | n_gen = 175, tg = 24.71 t/s, tg_3s = 24.70 t/s 4.14.425.011 I slot print_timing: id 0 | task 3159 | n_gen = 1007, tg = 22.80 t/s, tg_3s = 24.67 t/s 4.14.426.196 I slot print_timing: id 2 | task 3648 | n_gen = 523, tg = 23.47 t/s, tg_3s = 24.66 t/s 4.15.115.718 I slot print_timing: id 0 | task 3159 | prompt eval time = 854.51 ms / 525 tokens ( 1.63 ms per token, 614.39 tokens per second) 4.15.115.724 I slot print_timing: id 0 | task 3159 | eval time = 44821.75 ms / 1024 tokens ( 43.81 ms per token, 22.82 tokens per second) 4.15.115.725 I slot print_timing: id 0 | task 3159 | total time = 45676.26 ms / 1549 tokens 4.15.115.726 I slot print_timing: id 0 | task 3159 | graphs reused = 3785 4.15.115.727 I slot print_timing: id 0 | task 3159 | graph reallocs = 0 / 0 (same size) / (changed size) 4.15.115.826 I slot release: id 0 | task 3159 | stop processing: n_tokens = 2203, truncated = 0 4.15.152.820 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.485 4.15.160.281 I slot launch_slot_: id 0 | task 4193 | processing task, is_child = 0 4.15.938.970 I slot print_timing: id 1 | task 3960 | n_gen = 233, tg = 23.00 t/s, tg_3s = 19.24 t/s 4.15.979.108 I slot print_timing: id 3 | task 3962 | n_gen = 233, tg = 23.07 t/s, tg_3s = 19.25 t/s 4.17.431.064 I slot print_timing: id 2 | task 3648 | n_gen = 581, tg = 22.97 t/s, tg_3s = 19.30 t/s 4.18.959.918 I slot print_timing: id 1 | task 3960 | n_gen = 308, tg = 23.42 t/s, tg_3s = 24.83 t/s 4.19.001.224 I slot print_timing: id 3 | task 3962 | n_gen = 308, tg = 23.47 t/s, tg_3s = 24.82 t/s 4.19.887.389 I slot print_timing: id 0 | task 4193 | n_gen = 100, tg = 24.81 t/s, tg_3s = 25.07 t/s 4.20.453.697 I slot print_timing: id 2 | task 3648 | n_gen = 656, tg = 23.17 t/s, tg_3s = 24.81 t/s 4.21.987.993 I slot print_timing: id 1 | task 3960 | n_gen = 383, tg = 23.67 t/s, tg_3s = 24.77 t/s 4.22.029.555 I slot print_timing: id 3 | task 3962 | n_gen = 383, tg = 23.72 t/s, tg_3s = 24.77 t/s 4.22.916.068 I slot print_timing: id 0 | task 4193 | n_gen = 175, tg = 24.79 t/s, tg_3s = 24.76 t/s 4.23.483.032 I slot print_timing: id 2 | task 3648 | n_gen = 731, tg = 23.32 t/s, tg_3s = 24.76 t/s 4.25.018.148 I slot print_timing: id 1 | task 3960 | n_gen = 458, tg = 23.84 t/s, tg_3s = 24.75 t/s 4.25.059.993 I slot print_timing: id 3 | task 3962 | n_gen = 458, tg = 23.88 t/s, tg_3s = 24.75 t/s 4.25.948.452 I slot print_timing: id 0 | task 4193 | n_gen = 250, tg = 24.77 t/s, tg_3s = 24.73 t/s 4.26.517.347 I slot print_timing: id 2 | task 3648 | n_gen = 806, tg = 23.44 t/s, tg_3s = 24.72 t/s 4.28.052.473 I slot print_timing: id 1 | task 3960 | n_gen = 533, tg = 23.96 t/s, tg_3s = 24.72 t/s 4.28.094.028 I slot print_timing: id 3 | task 3962 | n_gen = 533, tg = 24.00 t/s, tg_3s = 24.72 t/s 4.28.984.585 I slot print_timing: id 0 | task 4193 | n_gen = 325, tg = 24.76 t/s, tg_3s = 24.70 t/s 4.29.556.947 I slot print_timing: id 2 | task 3648 | n_gen = 881, tg = 23.54 t/s, tg_3s = 24.67 t/s 4.31.059.151 I slot print_timing: id 1 | task 3960 | n_gen = 607, tg = 24.04 t/s, tg_3s = 24.61 t/s 4.31.101.044 I slot print_timing: id 3 | task 3962 | n_gen = 607, tg = 24.07 t/s, tg_3s = 24.61 t/s 4.31.789.068 I slot print_timing: id 0 | task 4193 | prompt eval time = 737.49 ms / 494 tokens ( 1.49 ms per token, 669.84 tokens per second) 4.31.789.071 I slot print_timing: id 0 | task 4193 | eval time = 15891.28 ms / 394 tokens ( 40.44 ms per token, 24.73 tokens per second) 4.31.789.072 I slot print_timing: id 0 | task 4193 | total time = 16628.77 ms / 888 tokens 4.31.789.073 I slot print_timing: id 0 | task 4193 | graphs reused = 4176 4.31.789.074 I slot print_timing: id 0 | task 4193 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.789.171 I slot release: id 0 | task 4193 | stop processing: n_tokens = 1530, truncated = 0 4.31.826.269 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.698 4.31.826.300 I slot launch_slot_: id 0 | task 4590 | processing task, is_child = 0 4.32.560.123 I slot print_timing: id 2 | task 3648 | n_gen = 939, tg = 23.23 t/s, tg_3s = 19.31 t/s 4.34.067.309 I slot print_timing: id 1 | task 3960 | n_gen = 665, tg = 23.53 t/s, tg_3s = 19.28 t/s 4.34.108.903 I slot print_timing: id 3 | task 3962 | n_gen = 665, tg = 23.56 t/s, tg_3s = 19.28 t/s 4.34.312.286 I slot print_timing: id 3 | task 3962 | prompt eval time = 554.26 ms / 265 tokens ( 2.09 ms per token, 478.12 tokens per second) 4.34.312.293 I slot print_timing: id 3 | task 3962 | eval time = 28389.50 ms / 670 tokens ( 42.44 ms per token, 23.57 tokens per second) 4.34.312.294 I slot print_timing: id 3 | task 3962 | total time = 28943.75 ms / 935 tokens 4.34.312.294 I slot print_timing: id 3 | task 3962 | graphs reused = 4219 4.34.312.295 I slot print_timing: id 3 | task 3962 | graph reallocs = 0 / 0 (same size) / (changed size) 4.34.312.404 I slot release: id 3 | task 3962 | stop processing: n_tokens = 1858, truncated = 0 4.34.348.120 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.575 4.34.348.158 I slot launch_slot_: id 3 | task 4637 | processing task, is_child = 0 4.35.591.852 I slot print_timing: id 2 | task 3648 | n_gen = 1004, tg = 23.10 t/s, tg_3s = 21.44 t/s 4.36.403.803 I slot print_timing: id 2 | task 3648 | prompt eval time = 766.96 ms / 503 tokens ( 1.52 ms per token, 655.84 tokens per second) 4.36.403.810 I slot print_timing: id 2 | task 3648 | eval time = 44222.49 ms / 1024 tokens ( 43.23 ms per token, 23.13 tokens per second) 4.36.403.811 I slot print_timing: id 2 | task 3648 | total time = 44989.45 ms / 1527 tokens 4.36.403.812 I slot print_timing: id 2 | task 3648 | graphs reused = 4257 4.36.403.812 I slot print_timing: id 2 | task 3648 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.403.926 I slot release: id 2 | task 3648 | stop processing: n_tokens = 2196, truncated = 0 4.36.447.123 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.486 4.36.453.072 I slot launch_slot_: id 2 | task 4680 | processing task, is_child = 0 4.37.114.166 I slot print_timing: id 1 | task 3960 | n_gen = 715, tg = 22.84 t/s, tg_3s = 16.41 t/s 4.37.629.728 I slot print_timing: id 0 | task 4590 | n_gen = 100, tg = 19.53 t/s, tg_3s = 19.72 t/s 4.39.482.564 I slot print_timing: id 3 | task 4637 | n_gen = 100, tg = 21.22 t/s, tg_3s = 21.43 t/s 4.40.125.307 I slot print_timing: id 1 | task 3960 | n_gen = 789, tg = 22.99 t/s, tg_3s = 24.58 t/s 4.40.648.139 I slot print_timing: id 0 | task 4590 | n_gen = 175, tg = 21.51 t/s, tg_3s = 24.85 t/s 4.41.173.633 I slot print_timing: id 2 | task 4680 | n_gen = 100, tg = 24.86 t/s, tg_3s = 25.11 t/s 4.42.507.516 I slot print_timing: id 3 | task 4637 | n_gen = 175, tg = 22.62 t/s, tg_3s = 24.79 t/s 4.43.152.888 I slot print_timing: id 1 | task 3960 | n_gen = 864, tg = 23.14 t/s, tg_3s = 24.77 t/s 4.43.679.519 I slot print_timing: id 0 | task 4590 | n_gen = 250, tg = 22.39 t/s, tg_3s = 24.74 t/s 4.44.208.005 I slot print_timing: id 2 | task 4680 | n_gen = 175, tg = 24.80 t/s, tg_3s = 24.72 t/s 4.45.546.249 I slot print_timing: id 3 | task 4637 | n_gen = 250, tg = 23.21 t/s, tg_3s = 24.68 t/s 4.46.192.992 I slot print_timing: id 1 | task 3960 | n_gen = 939, tg = 23.25 t/s, tg_3s = 24.67 t/s 4.46.679.537 I slot print_timing: id 0 | task 4590 | n_gen = 324, tg = 22.88 t/s, tg_3s = 24.67 t/s 4.47.208.759 I slot print_timing: id 2 | task 4680 | n_gen = 249, tg = 24.75 t/s, tg_3s = 24.66 t/s 4.48.507.356 I slot print_timing: id 0 | task 4590 | prompt eval time = 733.27 ms / 488 tokens ( 1.50 ms per token, 665.51 tokens per second) 4.48.507.363 I slot print_timing: id 0 | task 4590 | eval time = 15947.77 ms / 369 tokens ( 43.34 ms per token, 23.08 tokens per second) 4.48.507.364 I slot print_timing: id 0 | task 4590 | total time = 16681.04 ms / 857 tokens 4.48.507.365 I slot print_timing: id 0 | task 4590 | graphs reused = 4535 4.48.507.366 I slot print_timing: id 0 | task 4590 | graph reallocs = 0 / 0 (same size) / (changed size) 4.48.507.450 I slot release: id 0 | task 4590 | stop processing: n_tokens = 1499, truncated = 0 4.48.544.043 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.713 4.48.544.072 I slot launch_slot_: id 0 | task 4964 | processing task, is_child = 0 4.49.225.163 I slot print_timing: id 1 | task 3960 | n_gen = 998, tg = 22.99 t/s, tg_3s = 19.46 t/s 4.49.227.804 I slot print_timing: id 3 | task 4637 | n_gen = 325, tg = 22.48 t/s, tg_3s = 20.37 t/s 4.50.248.430 I slot print_timing: id 2 | task 4680 | n_gen = 307, tg = 23.43 t/s, tg_3s = 19.08 t/s 4.50.329.135 I slot print_timing: id 1 | task 3960 | prompt eval time = 1172.25 ms / 512 tokens ( 2.29 ms per token, 436.77 tokens per second) 4.50.329.143 I slot print_timing: id 1 | task 3960 | eval time = 44476.82 ms / 1024 tokens ( 43.48 ms per token, 23.00 tokens per second) 4.50.329.146 I slot print_timing: id 1 | task 3960 | total time = 45649.07 ms / 1536 tokens 4.50.329.147 I slot print_timing: id 1 | task 3960 | graphs reused = 4560 4.50.329.148 I slot print_timing: id 1 | task 3960 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.329.269 I slot release: id 1 | task 3960 | stop processing: n_tokens = 2199, truncated = 0 4.50.372.915 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.486 4.50.378.810 I slot launch_slot_: id 1 | task 4993 | processing task, is_child = 0 4.52.238.208 I slot print_timing: id 3 | task 4637 | n_gen = 381, tg = 21.81 t/s, tg_3s = 18.60 t/s 4.53.250.093 I slot print_timing: id 2 | task 4680 | n_gen = 364, tg = 22.60 t/s, tg_3s = 18.99 t/s 4.54.013.906 I slot print_timing: id 0 | task 4964 | n_gen = 100, tg = 21.00 t/s, tg_3s = 21.22 t/s 4.55.142.054 I slot print_timing: id 1 | task 4993 | n_gen = 100, tg = 24.77 t/s, tg_3s = 25.02 t/s 4.55.263.819 I slot print_timing: id 3 | task 4637 | n_gen = 456, tg = 22.25 t/s, tg_3s = 24.79 t/s 4.56.268.298 I slot print_timing: id 2 | task 4680 | n_gen = 439, tg = 22.96 t/s, tg_3s = 24.85 t/s 4.57.033.472 I slot print_timing: id 0 | task 4964 | n_gen = 175, tg = 22.50 t/s, tg_3s = 24.84 t/s 4.58.165.235 I slot print_timing: id 1 | task 4993 | n_gen = 175, tg = 24.79 t/s, tg_3s = 24.81 t/s 4.58.287.121 I slot print_timing: id 3 | task 4637 | n_gen = 531, tg = 22.58 t/s, tg_3s = 24.81 t/s 4.59.297.210 I slot print_timing: id 2 | task 4680 | n_gen = 514, tg = 23.21 t/s, tg_3s = 24.76 t/s 5.00.064.944 I slot print_timing: id 0 | task 4964 | n_gen = 250, tg = 23.13 t/s, tg_3s = 24.74 t/s 5.01.036.512 I slot print_timing: id 2 | task 4680 | prompt eval time = 737.46 ms / 478 tokens ( 1.54 ms per token, 648.17 tokens per second) 5.01.036.519 I slot print_timing: id 2 | task 4680 | eval time = 23845.97 ms / 557 tokens ( 42.89 ms per token, 23.32 tokens per second) 5.01.036.520 I slot print_timing: id 2 | task 4680 | total time = 24583.43 ms / 1035 tokens 5.01.036.521 I slot print_timing: id 2 | task 4680 | graphs reused = 4803 5.01.036.522 I slot print_timing: id 2 | task 4680 | graph reallocs = 0 / 0 (same size) / (changed size) 5.01.036.626 I slot release: id 2 | task 4680 | stop processing: n_tokens = 1704, truncated = 0 5.01.079.420 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.627 5.01.079.455 I slot launch_slot_: id 2 | task 5242 | processing task, is_child = 0 5.01.732.554 I slot print_timing: id 1 | task 4993 | n_gen = 248, tg = 23.33 t/s, tg_3s = 20.46 t/s 5.01.732.838 I slot print_timing: id 3 | task 4637 | n_gen = 601, tg = 22.29 t/s, tg_3s = 20.32 t/s 5.02.091.210 I slot print_timing: id 3 | task 4637 | prompt eval time = 467.99 ms / 219 tokens ( 2.14 ms per token, 467.96 tokens per second) 5.02.091.219 I slot print_timing: id 3 | task 4637 | eval time = 27275.05 ms / 609 tokens ( 44.86 ms per token, 22.29 tokens per second) 5.02.091.220 I slot print_timing: id 3 | task 4637 | total time = 27743.04 ms / 828 tokens 5.02.091.221 I slot print_timing: id 3 | task 4637 | graphs reused = 4809 5.02.091.222 I slot print_timing: id 3 | task 4637 | graph reallocs = 0 / 0 (same size) / (changed size) 5.02.091.351 I slot release: id 3 | task 4637 | stop processing: n_tokens = 1751, truncated = 0 5.02.132.005 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.610 5.02.132.047 I slot launch_slot_: id 3 | task 5253 | processing task, is_child = 0 5.03.097.287 I slot print_timing: id 0 | task 4964 | n_gen = 299, tg = 21.60 t/s, tg_3s = 16.16 t/s 5.04.751.490 I slot print_timing: id 1 | task 4993 | n_gen = 312, tg = 22.86 t/s, tg_3s = 21.20 t/s 5.05.396.538 I slot print_timing: id 0 | task 4964 | prompt eval time = 756.37 ms / 510 tokens ( 1.48 ms per token, 674.27 tokens per second) 5.05.396.544 I slot print_timing: id 0 | task 4964 | eval time = 16096.09 ms / 356 tokens ( 45.34 ms per token, 22.06 tokens per second) 5.05.396.545 I slot print_timing: id 0 | task 4964 | total time = 16852.46 ms / 866 tokens 5.05.396.546 I slot print_timing: id 0 | task 4964 | graphs reused = 4877 5.05.396.546 I slot print_timing: id 0 | task 4964 | graph reallocs = 0 / 0 (same size) / (changed size) 5.05.396.644 I slot release: id 0 | task 4964 | stop processing: n_tokens = 1508, truncated = 0 5.05.433.687 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.708 5.05.433.719 I slot launch_slot_: id 0 | task 5326 | processing task, is_child = 0 5.07.039.716 I slot print_timing: id 2 | task 5242 | n_gen = 100, tg = 18.93 t/s, tg_3s = 19.12 t/s 5.07.443.208 I slot print_timing: id 3 | task 5253 | n_gen = 100, tg = 20.52 t/s, tg_3s = 20.72 t/s 5.07.764.375 I slot print_timing: id 1 | task 4993 | n_gen = 366, tg = 21.96 t/s, tg_3s = 17.92 t/s 5.10.058.621 I slot print_timing: id 2 | task 5242 | n_gen = 175, tg = 21.09 t/s, tg_3s = 24.84 t/s 5.10.378.373 I slot print_timing: id 0 | task 5326 | n_gen = 100, tg = 24.87 t/s, tg_3s = 25.12 t/s 5.10.460.219 I slot print_timing: id 3 | task 5253 | n_gen = 175, tg = 22.19 t/s, tg_3s = 24.86 t/s 5.10.781.721 I slot print_timing: id 1 | task 4993 | n_gen = 441, tg = 22.41 t/s, tg_3s = 24.86 t/s 5.11.305.259 I slot print_timing: id 1 | task 4993 | prompt eval time = 766.70 ms / 502 tokens ( 1.53 ms per token, 654.75 tokens per second) 5.11.305.269 I slot print_timing: id 1 | task 4993 | eval time = 20159.73 ms / 454 tokens ( 44.50 ms per token, 22.47 tokens per second) 5.11.305.270 I slot print_timing: id 1 | task 4993 | total time = 20926.44 ms / 956 tokens 5.11.305.271 I slot print_timing: id 1 | task 4993 | graphs reused = 4998 5.11.305.272 I slot print_timing: id 1 | task 4993 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.305.379 I slot release: id 1 | task 4993 | stop processing: n_tokens = 1619, truncated = 0 5.11.348.701 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.660 5.11.348.736 I slot launch_slot_: id 1 | task 5453 | processing task, is_child = 0 5.13.097.616 I slot print_timing: id 2 | task 5242 | n_gen = 233, tg = 20.55 t/s, tg_3s = 19.09 t/s 5.13.417.720 I slot print_timing: id 0 | task 5326 | n_gen = 158, tg = 22.36 t/s, tg_3s = 19.08 t/s 5.13.499.672 I slot print_timing: id 3 | task 5253 | n_gen = 233, tg = 21.32 t/s, tg_3s = 19.08 t/s 5.16.114.538 I slot print_timing: id 1 | task 5453 | n_gen = 100, tg = 24.80 t/s, tg_3s = 25.05 t/s 5.16.115.207 I slot print_timing: id 2 | task 5242 | n_gen = 308, tg = 21.46 t/s, tg_3s = 24.85 t/s 5.16.436.683 I slot print_timing: id 0 | task 5326 | n_gen = 233, tg = 23.11 t/s, tg_3s = 24.84 t/s 5.16.519.177 I slot print_timing: id 3 | task 5253 | n_gen = 308, tg = 22.08 t/s, tg_3s = 24.84 t/s 5.19.143.689 I slot print_timing: id 1 | task 5453 | n_gen = 175, tg = 24.78 t/s, tg_3s = 24.76 t/s 5.19.144.217 I slot print_timing: id 2 | task 5242 | n_gen = 383, tg = 22.04 t/s, tg_3s = 24.76 t/s 5.19.466.563 I slot print_timing: id 0 | task 5326 | n_gen = 308, tg = 23.49 t/s, tg_3s = 24.75 t/s 5.19.552.072 I slot print_timing: id 3 | task 5253 | n_gen = 383, tg = 22.56 t/s, tg_3s = 24.73 t/s 5.22.176.618 I slot print_timing: id 1 | task 5453 | n_gen = 250, tg = 24.77 t/s, tg_3s = 24.73 t/s 5.22.177.194 I slot print_timing: id 2 | task 5242 | n_gen = 458, tg = 22.44 t/s, tg_3s = 24.73 t/s 5.22.498.857 I slot print_timing: id 0 | task 5326 | n_gen = 383, tg = 23.72 t/s, tg_3s = 24.73 t/s 5.22.581.029 I slot print_timing: id 3 | task 5253 | n_gen = 458, tg = 22.89 t/s, tg_3s = 24.76 t/s 5.25.203.036 I slot print_timing: id 1 | task 5453 | n_gen = 325, tg = 24.77 t/s, tg_3s = 24.78 t/s 5.25.203.557 I slot print_timing: id 2 | task 5242 | n_gen = 533, tg = 22.74 t/s, tg_3s = 24.78 t/s 5.25.524.807 I slot print_timing: id 0 | task 5326 | n_gen = 458, tg = 23.89 t/s, tg_3s = 24.79 t/s 5.25.607.069 I slot print_timing: id 3 | task 5253 | n_gen = 533, tg = 23.14 t/s, tg_3s = 24.78 t/s 5.28.235.046 I slot print_timing: id 1 | task 5453 | n_gen = 400, tg = 24.76 t/s, tg_3s = 24.74 t/s 5.28.235.589 I slot print_timing: id 2 | task 5242 | n_gen = 608, tg = 22.97 t/s, tg_3s = 24.74 t/s 5.28.558.483 I slot print_timing: id 0 | task 5326 | n_gen = 533, tg = 24.01 t/s, tg_3s = 24.72 t/s 5.28.640.623 I slot print_timing: id 3 | task 5253 | n_gen = 608, tg = 23.33 t/s, tg_3s = 24.72 t/s 5.29.005.338 I slot print_timing: id 3 | task 5253 | prompt eval time = 485.54 ms / 231 tokens ( 2.10 ms per token, 475.76 tokens per second) 5.29.005.346 I slot print_timing: id 3 | task 5253 | eval time = 26387.74 ms / 617 tokens ( 42.84 ms per token, 23.34 tokens per second) 5.29.005.346 I slot print_timing: id 3 | task 5253 | total time = 26873.28 ms / 848 tokens 5.29.005.347 I slot print_timing: id 3 | task 5253 | graphs reused = 5414 5.29.005.348 I slot print_timing: id 3 | task 5253 | graph reallocs = 0 / 0 (same size) / (changed size) 5.29.005.445 I slot release: id 3 | task 5253 | stop processing: n_tokens = 1771, truncated = 0 5.29.040.936 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.603 5.29.040.972 I slot launch_slot_: id 3 | task 5875 | processing task, is_child = 0 5.31.267.748 I slot print_timing: id 1 | task 5453 | n_gen = 465, tg = 24.24 t/s, tg_3s = 21.43 t/s 5.31.268.365 I slot print_timing: id 2 | task 5242 | n_gen = 673, tg = 22.81 t/s, tg_3s = 21.43 t/s 5.31.592.096 I slot print_timing: id 0 | task 5326 | n_gen = 598, tg = 23.70 t/s, tg_3s = 21.43 t/s 5.33.535.211 I slot print_timing: id 3 | task 5875 | n_gen = 100, tg = 24.72 t/s, tg_3s = 24.97 t/s 5.33.573.963 I slot print_timing: id 0 | task 5326 | prompt eval time = 963.21 ms / 546 tokens ( 1.76 ms per token, 566.86 tokens per second) 5.33.573.967 I slot print_timing: id 0 | task 5326 | eval time = 27177.03 ms / 647 tokens ( 42.07 ms per token, 23.77 tokens per second) 5.33.573.967 I slot print_timing: id 0 | task 5326 | total time = 28140.24 ms / 1193 tokens 5.33.573.968 I slot print_timing: id 0 | task 5326 | graphs reused = 5512 5.33.573.969 I slot print_timing: id 0 | task 5326 | graph reallocs = 0 / 0 (same size) / (changed size) 5.33.574.072 I slot release: id 0 | task 5326 | stop processing: n_tokens = 1835, truncated = 0 5.33.611.041 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.582 5.33.611.072 I slot launch_slot_: id 0 | task 5979 | processing task, is_child = 0 5.34.281.948 I slot print_timing: id 1 | task 5453 | n_gen = 524, tg = 23.60 t/s, tg_3s = 19.57 t/s 5.34.282.278 I slot print_timing: id 2 | task 5242 | n_gen = 732, tg = 22.51 t/s, tg_3s = 19.58 t/s 5.36.571.900 I slot print_timing: id 3 | task 5875 | n_gen = 159, tg = 22.44 t/s, tg_3s = 19.43 t/s 5.37.297.915 I slot print_timing: id 1 | task 5453 | n_gen = 598, tg = 23.71 t/s, tg_3s = 24.54 t/s 5.37.298.507 I slot print_timing: id 2 | task 5242 | n_gen = 806, tg = 22.68 t/s, tg_3s = 24.53 t/s 5.38.349.202 I slot print_timing: id 0 | task 5979 | n_gen = 100, tg = 24.76 t/s, tg_3s = 25.01 t/s 5.39.603.394 I slot print_timing: id 3 | task 5875 | n_gen = 234, tg = 23.13 t/s, tg_3s = 24.74 t/s 5.40.330.097 I slot print_timing: id 1 | task 5453 | n_gen = 673, tg = 23.82 t/s, tg_3s = 24.73 t/s 5.40.330.712 I slot print_timing: id 2 | task 5242 | n_gen = 881, tg = 22.84 t/s, tg_3s = 24.73 t/s 5.41.382.702 I slot print_timing: id 0 | task 5979 | n_gen = 175, tg = 24.74 t/s, tg_3s = 24.72 t/s 5.42.606.562 I slot print_timing: id 3 | task 5875 | n_gen = 308, tg = 23.48 t/s, tg_3s = 24.64 t/s 5.43.336.123 I slot print_timing: id 1 | task 5453 | n_gen = 747, tg = 23.90 t/s, tg_3s = 24.62 t/s 5.43.336.794 I slot print_timing: id 2 | task 5242 | n_gen = 955, tg = 22.97 t/s, tg_3s = 24.62 t/s 5.44.392.647 I slot print_timing: id 0 | task 5979 | n_gen = 249, tg = 24.70 t/s, tg_3s = 24.59 t/s 5.45.614.596 I slot print_timing: id 3 | task 5875 | n_gen = 382, tg = 23.69 t/s, tg_3s = 24.60 t/s 5.46.142.453 I slot print_timing: id 2 | task 5242 | prompt eval time = 729.56 ms / 467 tokens ( 1.56 ms per token, 640.11 tokens per second) 5.46.142.457 I slot print_timing: id 2 | task 5242 | eval time = 44333.43 ms / 1024 tokens ( 43.34 ms per token, 23.08 tokens per second) 5.46.142.458 I slot print_timing: id 2 | task 5242 | total time = 45062.99 ms / 1491 tokens 5.46.142.459 I slot print_timing: id 2 | task 5242 | graphs reused = 5802 5.46.142.460 I slot print_timing: id 2 | task 5242 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.142.562 I slot release: id 2 | task 5242 | stop processing: n_tokens = 2160, truncated = 0 5.46.185.555 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.494 5.46.187.871 I slot launch_slot_: id 2 | task 6274 | processing task, is_child = 0 5.46.882.597 I slot print_timing: id 1 | task 5453 | n_gen = 818, tg = 23.50 t/s, tg_3s = 20.02 t/s 5.47.404.104 I slot print_timing: id 0 | task 5979 | n_gen = 306, tg = 23.36 t/s, tg_3s = 18.93 t/s 5.48.621.212 I slot print_timing: id 3 | task 5875 | n_gen = 439, tg = 22.94 t/s, tg_3s = 18.96 t/s 5.49.917.738 I slot print_timing: id 1 | task 5453 | n_gen = 892, tg = 23.57 t/s, tg_3s = 24.38 t/s 5.50.442.141 I slot print_timing: id 0 | task 5979 | n_gen = 381, tg = 23.61 t/s, tg_3s = 24.69 t/s 5.50.968.184 I slot print_timing: id 2 | task 6274 | n_gen = 100, tg = 24.70 t/s, tg_3s = 24.94 t/s 5.51.251.749 I slot print_timing: id 3 | task 5875 | prompt eval time = 489.06 ms / 235 tokens ( 2.08 ms per token, 480.51 tokens per second) 5.51.251.757 I slot print_timing: id 3 | task 5875 | eval time = 21721.71 ms / 504 tokens ( 43.18 ms per token, 23.16 tokens per second) 5.51.251.758 I slot print_timing: id 3 | task 5875 | total time = 22210.77 ms / 739 tokens 5.51.251.758 I slot print_timing: id 3 | task 5875 | graphs reused = 5906 5.51.251.759 I slot print_timing: id 3 | task 5875 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.251.865 I slot release: id 3 | task 5875 | stop processing: n_tokens = 1662, truncated = 0 5.51.287.203 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.643 5.51.287.232 I slot launch_slot_: id 3 | task 6384 | processing task, is_child = 0 5.52.798.735 I slot print_timing: id 1 | task 5453 | prompt eval time = 773.63 ms / 509 tokens ( 1.52 ms per token, 657.94 tokens per second) 5.52.798.739 I slot print_timing: id 1 | task 5453 | eval time = 40676.36 ms / 954 tokens ( 42.68 ms per token, 23.43 tokens per second) 5.52.798.740 I slot print_timing: id 1 | task 5453 | total time = 41449.99 ms / 1463 tokens 5.52.798.741 I slot print_timing: id 1 | task 5453 | graphs reused = 5931 5.52.798.742 I slot print_timing: id 1 | task 5453 | graph reallocs = 0 / 0 (same size) / (changed size) 5.52.798.838 I slot release: id 1 | task 5453 | stop processing: n_tokens = 2126, truncated = 0 5.52.842.352 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.502 5.52.842.394 I slot launch_slot_: id 1 | task 6414 | processing task, is_child = 0 5.53.510.998 I slot print_timing: id 0 | task 5979 | n_gen = 432, tg = 22.49 t/s, tg_3s = 16.62 t/s 5.53.989.202 I slot print_timing: id 2 | task 6274 | n_gen = 149, tg = 21.05 t/s, tg_3s = 16.22 t/s 5.56.407.505 I slot print_timing: id 3 | task 6384 | n_gen = 100, tg = 21.26 t/s, tg_3s = 21.47 t/s 5.56.526.515 I slot print_timing: id 0 | task 5979 | n_gen = 506, tg = 22.77 t/s, tg_3s = 24.54 t/s 5.57.011.029 I slot print_timing: id 2 | task 6274 | n_gen = 224, tg = 22.19 t/s, tg_3s = 24.82 t/s 5.57.573.526 I slot print_timing: id 1 | task 6414 | n_gen = 100, tg = 24.85 t/s, tg_3s = 25.10 t/s 5.59.428.541 I slot print_timing: id 3 | task 6384 | n_gen = 175, tg = 22.66 t/s, tg_3s = 24.83 t/s 5.59.548.168 I slot print_timing: id 0 | task 5979 | n_gen = 581, tg = 23.02 t/s, tg_3s = 24.82 t/s 6.00.032.714 I slot print_timing: id 2 | task 6274 | n_gen = 299, tg = 22.79 t/s, tg_3s = 24.82 t/s 6.00.597.856 I slot print_timing: id 1 | task 6414 | n_gen = 175, tg = 24.83 t/s, tg_3s = 24.80 t/s 6.02.454.213 I slot print_timing: id 3 | task 6384 | n_gen = 250, tg = 23.26 t/s, tg_3s = 24.79 t/s 6.02.573.733 I slot print_timing: id 0 | task 5979 | n_gen = 656, tg = 23.21 t/s, tg_3s = 24.79 t/s 6.03.060.821 I slot print_timing: id 2 | task 6274 | n_gen = 374, tg = 23.17 t/s, tg_3s = 24.77 t/s 6.03.626.276 I slot print_timing: id 1 | task 6414 | n_gen = 250, tg = 24.81 t/s, tg_3s = 24.77 t/s 6.05.486.810 I slot print_timing: id 3 | task 6384 | n_gen = 325, tg = 23.59 t/s, tg_3s = 24.73 t/s 6.05.606.471 I slot print_timing: id 0 | task 5979 | n_gen = 731, tg = 23.36 t/s, tg_3s = 24.73 t/s 6.06.091.490 I slot print_timing: id 2 | task 6274 | n_gen = 449, tg = 23.42 t/s, tg_3s = 24.75 t/s 6.06.657.283 I slot print_timing: id 1 | task 6414 | n_gen = 325, tg = 24.79 t/s, tg_3s = 24.74 t/s 6.08.522.221 I slot print_timing: id 3 | task 6384 | n_gen = 400, tg = 23.79 t/s, tg_3s = 24.71 t/s 6.08.641.554 I slot print_timing: id 0 | task 5979 | n_gen = 806, tg = 23.48 t/s, tg_3s = 24.71 t/s 6.08.926.332 I slot print_timing: id 3 | task 6384 | prompt eval time = 463.30 ms / 215 tokens ( 2.15 ms per token, 464.06 tokens per second) 6.08.926.339 I slot print_timing: id 3 | task 6384 | eval time = 17175.79 ms / 410 tokens ( 41.99 ms per token, 23.81 tokens per second) 6.08.926.340 I slot print_timing: id 3 | task 6384 | total time = 17639.09 ms / 625 tokens 6.08.926.341 I slot print_timing: id 3 | task 6384 | graphs reused = 6309 6.08.926.342 I slot print_timing: id 3 | task 6384 | graph reallocs = 0 / 0 (same size) / (changed size) 6.08.926.441 I slot release: id 3 | task 6384 | stop processing: n_tokens = 1548, truncated = 0 6.08.961.966 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.690 6.08.961.997 I slot launch_slot_: id 3 | task 6798 | processing task, is_child = 0 6.09.357.429 I slot print_timing: id 2 | task 6274 | n_gen = 521, tg = 23.22 t/s, tg_3s = 22.05 t/s 6.09.507.303 I slot print_timing: id 1 | task 6414 | prompt eval time = 747.01 ms / 484 tokens ( 1.54 ms per token, 647.92 tokens per second) 6.09.507.309 I slot print_timing: id 1 | task 6414 | eval time = 15917.89 ms / 386 tokens ( 41.35 ms per token, 24.19 tokens per second) 6.09.507.309 I slot print_timing: id 1 | task 6414 | total time = 16664.90 ms / 870 tokens 6.09.507.310 I slot print_timing: id 1 | task 6414 | graphs reused = 6310 6.09.507.310 I slot print_timing: id 1 | task 6414 | graph reallocs = 0 / 0 (same size) / (changed size) 6.09.507.378 I slot release: id 1 | task 6414 | stop processing: n_tokens = 1533, truncated = 0 6.09.548.239 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.697 6.09.548.261 I slot launch_slot_: id 1 | task 6804 | processing task, is_child = 0 6.11.667.717 I slot print_timing: id 0 | task 5979 | n_gen = 855, tg = 22.88 t/s, tg_3s = 16.19 t/s 6.12.395.996 I slot print_timing: id 2 | task 6274 | n_gen = 579, tg = 22.72 t/s, tg_3s = 19.09 t/s 6.14.096.085 I slot print_timing: id 3 | task 6798 | n_gen = 100, tg = 21.21 t/s, tg_3s = 21.42 t/s 6.14.297.641 I slot print_timing: id 1 | task 6804 | n_gen = 100, tg = 24.70 t/s, tg_3s = 24.94 t/s 6.14.701.149 I slot print_timing: id 0 | task 5979 | n_gen = 930, tg = 23.02 t/s, tg_3s = 24.72 t/s 6.15.432.284 I slot print_timing: id 2 | task 6274 | n_gen = 654, tg = 22.93 t/s, tg_3s = 24.70 t/s 6.16.284.647 I slot print_timing: id 2 | task 6274 | prompt eval time = 771.43 ms / 510 tokens ( 1.51 ms per token, 661.11 tokens per second) 6.16.284.655 I slot print_timing: id 2 | task 6274 | eval time = 29325.33 ms / 675 tokens ( 43.51 ms per token, 22.98 tokens per second) 6.16.284.656 I slot print_timing: id 2 | task 6274 | total time = 30096.76 ms / 1185 tokens 6.16.284.657 I slot print_timing: id 2 | task 6274 | graphs reused = 6456 6.16.284.658 I slot print_timing: id 2 | task 6274 | graph reallocs = 0 / 0 (same size) / (changed size) 6.16.284.762 I slot release: id 2 | task 6274 | stop processing: n_tokens = 1854, truncated = 0 6.16.327.616 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.576 6.16.327.646 I slot launch_slot_: id 2 | task 6956 | processing task, is_child = 0 6.17.107.328 I slot print_timing: id 3 | task 6798 | n_gen = 158, tg = 20.44 t/s, tg_3s = 19.26 t/s 6.17.307.992 I slot print_timing: id 1 | task 6804 | n_gen = 158, tg = 22.37 t/s, tg_3s = 19.27 t/s 6.17.717.519 I slot print_timing: id 0 | task 5979 | n_gen = 988, tg = 22.76 t/s, tg_3s = 19.23 t/s 6.19.181.521 I slot print_timing: id 0 | task 5979 | prompt eval time = 739.25 ms / 498 tokens ( 1.48 ms per token, 673.66 tokens per second) 6.19.181.527 I slot print_timing: id 0 | task 5979 | eval time = 44831.19 ms / 1024 tokens ( 43.82 ms per token, 22.82 tokens per second) 6.19.181.528 I slot print_timing: id 0 | task 5979 | total time = 45570.44 ms / 1522 tokens 6.19.181.529 I slot print_timing: id 0 | task 5979 | graphs reused = 6507 6.19.181.529 I slot print_timing: id 0 | task 5979 | graph reallocs = 0 / 0 (same size) / (changed size) 6.19.181.626 I slot release: id 0 | task 5979 | stop processing: n_tokens = 2194, truncated = 0 6.19.218.423 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.487 6.19.224.004 I slot launch_slot_: id 0 | task 7012 | processing task, is_child = 0 6.20.119.786 I slot print_timing: id 3 | task 6798 | n_gen = 216, tg = 20.11 t/s, tg_3s = 19.25 t/s 6.20.316.620 I slot print_timing: id 1 | task 6804 | n_gen = 216, tg = 21.44 t/s, tg_3s = 19.28 t/s 6.21.725.031 I slot print_timing: id 2 | task 6956 | n_gen = 100, tg = 21.25 t/s, tg_3s = 21.46 t/s 6.23.136.105 I slot print_timing: id 3 | task 6798 | n_gen = 291, tg = 21.15 t/s, tg_3s = 24.86 t/s 6.23.336.810 I slot print_timing: id 1 | task 6804 | n_gen = 291, tg = 22.23 t/s, tg_3s = 24.83 t/s 6.23.821.566 I slot print_timing: id 3 | task 6798 | prompt eval time = 465.51 ms / 218 tokens ( 2.14 ms per token, 468.30 tokens per second) 6.23.821.573 I slot print_timing: id 3 | task 6798 | eval time = 14394.05 ms / 308 tokens ( 46.89 ms per token, 21.33 tokens per second) 6.23.821.574 I slot print_timing: id 3 | task 6798 | total time = 14859.56 ms / 526 tokens 6.23.821.575 I slot print_timing: id 3 | task 6798 | graphs reused = 6603 6.23.821.576 I slot print_timing: id 3 | task 6798 | graph reallocs = 0 / 0 (same size) / (changed size) 6.23.821.684 I slot release: id 3 | task 6798 | stop processing: n_tokens = 1449, truncated = 0 6.23.857.313 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.737 6.23.857.346 I slot launch_slot_: id 3 | task 7112 | processing task, is_child = 0 6.24.349.556 I slot print_timing: id 0 | task 7012 | n_gen = 100, tg = 22.55 t/s, tg_3s = 22.78 t/s 6.24.752.710 I slot print_timing: id 2 | task 6956 | n_gen = 165, tg = 21.34 t/s, tg_3s = 21.47 t/s 6.26.368.061 I slot print_timing: id 1 | task 6804 | n_gen = 356, tg = 22.08 t/s, tg_3s = 21.44 t/s 6.26.771.805 I slot print_timing: id 1 | task 6804 | prompt eval time = 740.54 ms / 479 tokens ( 1.55 ms per token, 646.83 tokens per second) 6.26.771.812 I slot print_timing: id 1 | task 6804 | eval time = 16483.00 ms / 366 tokens ( 45.16 ms per token, 22.14 tokens per second) 6.26.771.813 I slot print_timing: id 1 | task 6804 | total time = 17223.54 ms / 845 tokens 6.26.771.814 I slot print_timing: id 1 | task 6804 | graphs reused = 6662 6.26.771.815 I slot print_timing: id 1 | task 6804 | graph reallocs = 0 / 0 (same size) / (changed size) 6.26.771.920 I slot release: id 1 | task 6804 | stop processing: n_tokens = 1508, truncated = 0 6.26.815.373 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.708 6.26.815.404 I slot launch_slot_: id 1 | task 7176 | processing task, is_child = 0 6.27.481.851 I slot print_timing: id 0 | task 7012 | n_gen = 162, tg = 21.40 t/s, tg_3s = 19.79 t/s 6.27.758.105 I slot print_timing: id 2 | task 6956 | n_gen = 223, tg = 20.76 t/s, tg_3s = 19.30 t/s 6.29.010.461 I slot print_timing: id 3 | task 7112 | n_gen = 100, tg = 21.24 t/s, tg_3s = 21.46 t/s 6.30.502.957 I slot print_timing: id 0 | task 7012 | n_gen = 236, tg = 22.29 t/s, tg_3s = 24.49 t/s 6.30.786.568 I slot print_timing: id 2 | task 6956 | n_gen = 298, tg = 21.65 t/s, tg_3s = 24.77 t/s 6.31.551.725 I slot print_timing: id 1 | task 7176 | n_gen = 100, tg = 24.80 t/s, tg_3s = 25.05 t/s 6.32.036.007 I slot print_timing: id 3 | task 7112 | n_gen = 175, tg = 22.64 t/s, tg_3s = 24.79 t/s 6.33.523.086 I slot print_timing: id 0 | task 7012 | n_gen = 311, tg = 22.86 t/s, tg_3s = 24.83 t/s 6.33.805.387 I slot print_timing: id 2 | task 6956 | n_gen = 373, tg = 22.22 t/s, tg_3s = 24.84 t/s 6.34.572.390 I slot print_timing: id 1 | task 7176 | n_gen = 175, tg = 24.81 t/s, tg_3s = 24.83 t/s 6.35.057.639 I slot print_timing: id 3 | task 7112 | n_gen = 250, tg = 23.26 t/s, tg_3s = 24.82 t/s 6.35.379.739 I slot print_timing: id 2 | task 6956 | prompt eval time = 738.62 ms / 481 tokens ( 1.54 ms per token, 651.21 tokens per second) 6.35.379.747 I slot print_timing: id 2 | task 6956 | eval time = 18313.47 ms / 412 tokens ( 44.56 ms per token, 22.44 tokens per second) 6.35.379.748 I slot print_timing: id 2 | task 6956 | total time = 19052.09 ms / 893 tokens 6.35.379.749 I slot print_timing: id 2 | task 6956 | graphs reused = 6854 6.35.379.749 I slot print_timing: id 2 | task 6956 | graph reallocs = 0 / 0 (same size) / (changed size) 6.35.379.850 I slot release: id 2 | task 6956 | stop processing: n_tokens = 1562, truncated = 0 6.35.422.566 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.684 6.35.422.601 I slot launch_slot_: id 2 | task 7374 | processing task, is_child = 0 6.36.540.130 I slot print_timing: id 0 | task 7012 | n_gen = 370, tg = 22.26 t/s, tg_3s = 19.56 t/s 6.36.831.540 I slot print_timing: id 0 | task 7012 | prompt eval time = 735.70 ms / 493 tokens ( 1.49 ms per token, 670.11 tokens per second) 6.36.831.547 I slot print_timing: id 0 | task 7012 | eval time = 16871.82 ms / 377 tokens ( 44.87 ms per token, 22.29 tokens per second) 6.36.831.547 I slot print_timing: id 0 | task 7012 | total time = 17607.52 ms / 870 tokens 6.36.831.548 I slot print_timing: id 0 | task 7012 | graphs reused = 6869 6.36.831.549 I slot print_timing: id 0 | task 7012 | graph reallocs = 0 / 0 (same size) / (changed size) 6.36.831.650 I slot release: id 0 | task 7012 | stop processing: n_tokens = 1542, truncated = 0 6.36.868.596 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.693 6.36.868.633 I slot launch_slot_: id 0 | task 7395 | processing task, is_child = 0 6.37.583.310 I slot print_timing: id 1 | task 7176 | n_gen = 218, tg = 21.65 t/s, tg_3s = 14.28 t/s 6.38.068.082 I slot print_timing: id 3 | task 7112 | n_gen = 293, tg = 21.29 t/s, tg_3s = 14.28 t/s 6.40.609.589 I slot print_timing: id 1 | task 7176 | n_gen = 293, tg = 22.38 t/s, tg_3s = 24.78 t/s 6.40.771.790 I slot print_timing: id 2 | task 7374 | n_gen = 100, tg = 21.40 t/s, tg_3s = 21.61 t/s 6.41.095.232 I slot print_timing: id 3 | task 7112 | n_gen = 368, tg = 21.92 t/s, tg_3s = 24.78 t/s 6.41.580.236 I slot print_timing: id 0 | task 7395 | n_gen = 100, tg = 24.77 t/s, tg_3s = 25.02 t/s 6.43.631.666 I slot print_timing: id 1 | task 7176 | n_gen = 368, tg = 22.83 t/s, tg_3s = 24.82 t/s 6.43.793.443 I slot print_timing: id 2 | task 7374 | n_gen = 175, tg = 22.75 t/s, tg_3s = 24.82 t/s 6.44.115.947 I slot print_timing: id 3 | task 7112 | n_gen = 443, tg = 22.36 t/s, tg_3s = 24.83 t/s 6.44.597.914 I slot print_timing: id 0 | task 7395 | n_gen = 175, tg = 24.80 t/s, tg_3s = 24.85 t/s 6.46.655.507 I slot print_timing: id 1 | task 7176 | n_gen = 443, tg = 23.15 t/s, tg_3s = 24.80 t/s 6.46.817.357 I slot print_timing: id 2 | task 7374 | n_gen = 250, tg = 23.33 t/s, tg_3s = 24.80 t/s 6.47.058.683 I slot print_timing: id 1 | task 7176 | prompt eval time = 744.19 ms / 485 tokens ( 1.53 ms per token, 651.72 tokens per second) 6.47.058.690 I slot print_timing: id 1 | task 7176 | eval time = 19499.08 ms / 453 tokens ( 43.14 ms per token, 23.18 tokens per second) 6.47.058.690 I slot print_timing: id 1 | task 7176 | total time = 20243.27 ms / 938 tokens 6.47.058.691 I slot print_timing: id 1 | task 7176 | graphs reused = 7103 6.47.058.697 I slot print_timing: id 1 | task 7176 | graph reallocs = 0 / 0 (same size) / (changed size) 6.47.058.802 I slot release: id 1 | task 7176 | stop processing: n_tokens = 1601, truncated = 0 6.47.101.909 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.667 6.47.101.952 I slot launch_slot_: id 1 | task 7634 | processing task, is_child = 0 6.47.762.170 I slot print_timing: id 0 | task 7395 | n_gen = 238, tg = 23.28 t/s, tg_3s = 19.91 t/s 6.47.762.737 I slot print_timing: id 3 | task 7112 | n_gen = 518, tg = 22.08 t/s, tg_3s = 20.57 t/s 6.49.849.925 I slot print_timing: id 2 | task 7374 | n_gen = 309, tg = 22.47 t/s, tg_3s = 19.46 t/s 6.50.777.528 I slot print_timing: id 0 | task 7395 | n_gen = 312, tg = 23.57 t/s, tg_3s = 24.54 t/s 6.50.779.128 I slot print_timing: id 3 | task 7112 | n_gen = 592, tg = 22.36 t/s, tg_3s = 24.53 t/s 6.51.824.396 I slot print_timing: id 1 | task 7634 | n_gen = 100, tg = 24.85 t/s, tg_3s = 25.10 t/s 6.52.874.468 I slot print_timing: id 2 | task 7374 | n_gen = 384, tg = 22.89 t/s, tg_3s = 24.80 t/s 6.53.801.160 I slot print_timing: id 0 | task 7395 | n_gen = 387, tg = 23.80 t/s, tg_3s = 24.80 t/s 6.53.802.803 I slot print_timing: id 3 | task 7112 | n_gen = 667, tg = 22.61 t/s, tg_3s = 24.80 t/s 6.54.853.021 I slot print_timing: id 1 | task 7634 | n_gen = 175, tg = 24.81 t/s, tg_3s = 24.76 t/s 6.54.934.363 I slot print_timing: id 2 | task 7374 | prompt eval time = 722.18 ms / 460 tokens ( 1.57 ms per token, 636.96 tokens per second) 6.54.934.370 I slot print_timing: id 2 | task 7374 | eval time = 18789.57 ms / 435 tokens ( 43.29 ms per token, 23.10 tokens per second) 6.54.934.371 I slot print_timing: id 2 | task 7374 | total time = 19511.75 ms / 895 tokens 6.54.934.372 I slot print_timing: id 2 | task 7374 | graphs reused = 7277 6.54.934.373 I slot print_timing: id 2 | task 7374 | graph reallocs = 0 / 0 (same size) / (changed size) 6.54.934.497 I slot release: id 2 | task 7374 | stop processing: n_tokens = 1564, truncated = 0 6.54.977.662 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.683 6.54.977.699 I slot launch_slot_: id 2 | task 7814 | processing task, is_child = 0 6.56.839.167 I slot print_timing: id 0 | task 7395 | n_gen = 446, tg = 23.11 t/s, tg_3s = 19.42 t/s 6.56.840.941 I slot print_timing: id 3 | task 7112 | n_gen = 726, tg = 22.31 t/s, tg_3s = 19.42 t/s 6.57.893.191 I slot print_timing: id 1 | task 7634 | n_gen = 234, tg = 23.18 t/s, tg_3s = 19.41 t/s 6.59.712.630 I slot print_timing: id 2 | task 7814 | n_gen = 100, tg = 24.70 t/s, tg_3s = 24.95 t/s 6.59.873.290 I slot print_timing: id 0 | task 7395 | n_gen = 521, tg = 23.33 t/s, tg_3s = 24.72 t/s 6.59.874.861 I slot print_timing: id 3 | task 7112 | n_gen = 801, tg = 22.52 t/s, tg_3s = 24.72 t/s 7.00.924.167 I slot print_timing: id 1 | task 7634 | n_gen = 309, tg = 23.54 t/s, tg_3s = 24.74 t/s 7.02.747.139 I slot print_timing: id 2 | task 7814 | n_gen = 175, tg = 24.71 t/s, tg_3s = 24.72 t/s 7.02.908.324 I slot print_timing: id 0 | task 7395 | n_gen = 596, tg = 23.49 t/s, tg_3s = 24.71 t/s 7.02.909.965 I slot print_timing: id 3 | task 7112 | n_gen = 876, tg = 22.69 t/s, tg_3s = 24.71 t/s 7.03.926.784 I slot print_timing: id 1 | task 7634 | n_gen = 383, tg = 23.75 t/s, tg_3s = 24.65 t/s 7.05.758.892 I slot print_timing: id 2 | task 7814 | n_gen = 249, tg = 24.67 t/s, tg_3s = 24.57 t/s 7.05.920.810 I slot print_timing: id 0 | task 7395 | n_gen = 670, tg = 23.61 t/s, tg_3s = 24.56 t/s 7.05.922.521 I slot print_timing: id 3 | task 7112 | n_gen = 950, tg = 22.83 t/s, tg_3s = 24.56 t/s 7.06.938.667 I slot print_timing: id 1 | task 7634 | n_gen = 457, tg = 23.88 t/s, tg_3s = 24.57 t/s 7.08.767.318 I slot print_timing: id 2 | task 7814 | n_gen = 323, tg = 24.65 t/s, tg_3s = 24.60 t/s 7.08.928.631 I slot print_timing: id 0 | task 7395 | n_gen = 744, tg = 23.70 t/s, tg_3s = 24.60 t/s 7.08.930.233 I slot print_timing: id 3 | task 7112 | prompt eval time = 493.14 ms / 242 tokens ( 2.04 ms per token, 490.73 tokens per second) 7.08.930.241 I slot print_timing: id 3 | task 7112 | eval time = 44579.74 ms / 1024 tokens ( 43.58 ms per token, 22.95 tokens per second) 7.08.930.241 I slot print_timing: id 3 | task 7112 | total time = 45072.88 ms / 1266 tokens 7.08.930.242 I slot print_timing: id 3 | task 7112 | graphs reused = 7601 7.08.930.243 I slot print_timing: id 3 | task 7112 | graph reallocs = 0 / 0 (same size) / (changed size) 7.08.930.358 I slot release: id 3 | task 7112 | stop processing: n_tokens = 2189, truncated = 0 7.08.965.872 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.488 7.08.971.740 I slot launch_slot_: id 3 | task 8144 | processing task, is_child = 0 7.09.947.013 I slot print_timing: id 1 | task 7634 | n_gen = 521, tg = 23.52 t/s, tg_3s = 21.27 t/s 7.11.767.886 I slot print_timing: id 2 | task 7814 | n_gen = 387, tg = 24.03 t/s, tg_3s = 21.33 t/s 7.11.968.848 I slot print_timing: id 0 | task 7395 | n_gen = 809, tg = 23.50 t/s, tg_3s = 21.38 t/s 7.12.979.062 I slot print_timing: id 1 | task 7634 | n_gen = 596, tg = 23.67 t/s, tg_3s = 24.74 t/s 7.13.262.461 I slot print_timing: id 0 | task 7395 | prompt eval time = 714.40 ms / 478 tokens ( 1.49 ms per token, 669.09 tokens per second) 7.13.262.468 I slot print_timing: id 0 | task 7395 | eval time = 35679.42 ms / 841 tokens ( 42.48 ms per token, 23.54 tokens per second) 7.13.262.469 I slot print_timing: id 0 | task 7395 | total time = 36393.82 ms / 1319 tokens 7.13.262.469 I slot print_timing: id 0 | task 7395 | graphs reused = 7694 7.13.262.470 I slot print_timing: id 0 | task 7395 | graph reallocs = 0 / 0 (same size) / (changed size) 7.13.262.579 I slot release: id 0 | task 7395 | stop processing: n_tokens = 1991, truncated = 0 7.13.300.194 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.536 7.13.300.230 I slot launch_slot_: id 0 | task 8242 | processing task, is_child = 0 7.14.095.101 I slot print_timing: id 3 | task 8144 | n_gen = 100, tg = 21.38 t/s, tg_3s = 21.60 t/s 7.14.780.700 I slot print_timing: id 2 | task 7814 | n_gen = 446, tg = 23.33 t/s, tg_3s = 19.58 t/s 7.15.997.541 I slot print_timing: id 1 | task 7634 | n_gen = 655, tg = 23.23 t/s, tg_3s = 19.55 t/s 7.17.131.434 I slot print_timing: id 3 | task 8144 | n_gen = 175, tg = 22.70 t/s, tg_3s = 24.70 t/s 7.17.816.175 I slot print_timing: id 2 | task 7814 | n_gen = 521, tg = 23.52 t/s, tg_3s = 24.71 t/s 7.18.016.702 I slot print_timing: id 0 | task 8242 | n_gen = 100, tg = 24.73 t/s, tg_3s = 24.98 t/s 7.19.027.156 I slot print_timing: id 1 | task 7634 | n_gen = 730, tg = 23.37 t/s, tg_3s = 24.76 t/s 7.19.834.917 I slot print_timing: id 3 | task 8144 | prompt eval time = 493.08 ms / 243 tokens ( 2.03 ms per token, 492.82 tokens per second) 7.19.834.924 I slot print_timing: id 3 | task 8144 | eval time = 10370.09 ms / 242 tokens ( 43.03 ms per token, 23.24 tokens per second) 7.19.834.925 I slot print_timing: id 3 | task 8144 | total time = 10863.17 ms / 485 tokens 7.19.834.926 I slot print_timing: id 3 | task 8144 | graphs reused = 7837 7.19.834.926 I slot print_timing: id 3 | task 8144 | graph reallocs = 0 / 0 (same size) / (changed size) 7.19.835.029 I slot release: id 3 | task 8144 | stop processing: n_tokens = 1408, truncated = 0 7.19.870.121 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.759 7.19.870.155 I slot launch_slot_: id 3 | task 8390 | processing task, is_child = 0 7.20.850.825 I slot print_timing: id 2 | task 7814 | n_gen = 587, tg = 23.30 t/s, tg_3s = 21.75 t/s 7.21.052.872 I slot print_timing: id 0 | task 8242 | n_gen = 166, tg = 23.44 t/s, tg_3s = 21.74 t/s 7.22.063.446 I slot print_timing: id 1 | task 7634 | n_gen = 796, tg = 23.23 t/s, tg_3s = 21.74 t/s 7.23.880.257 I slot print_timing: id 2 | task 7814 | n_gen = 662, tg = 23.46 t/s, tg_3s = 24.76 t/s 7.24.081.453 I slot print_timing: id 0 | task 8242 | n_gen = 241, tg = 23.84 t/s, tg_3s = 24.76 t/s 7.24.326.547 I slot print_timing: id 3 | task 8390 | n_gen = 100, tg = 24.79 t/s, tg_3s = 25.04 t/s 7.25.094.325 I slot print_timing: id 1 | task 7634 | n_gen = 871, tg = 23.35 t/s, tg_3s = 24.75 t/s 7.26.917.873 I slot print_timing: id 2 | task 7814 | n_gen = 737, tg = 23.58 t/s, tg_3s = 24.69 t/s 7.27.119.542 I slot print_timing: id 0 | task 8242 | n_gen = 316, tg = 24.03 t/s, tg_3s = 24.69 t/s 7.27.322.610 I slot print_timing: id 1 | task 7634 | prompt eval time = 738.01 ms / 475 tokens ( 1.55 ms per token, 643.62 tokens per second) 7.27.322.616 I slot print_timing: id 1 | task 7634 | eval time = 39482.64 ms / 926 tokens ( 42.68 ms per token, 23.43 tokens per second) 7.27.322.617 I slot print_timing: id 1 | task 7634 | total time = 40220.65 ms / 1401 tokens 7.27.322.618 I slot print_timing: id 1 | task 7634 | graphs reused = 8008 7.27.322.618 I slot print_timing: id 1 | task 7634 | graph reallocs = 0 / 0 (same size) / (changed size) 7.27.322.731 I slot release: id 1 | task 7634 | stop processing: n_tokens = 2064, truncated = 0 7.27.365.863 I slot print_timing: id 3 | task 8390 | n_gen = 175, tg = 24.74 t/s, tg_3s = 24.68 t/s 7.27.365.870 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.517 7.27.365.902 I slot launch_slot_: id 1 | task 8567 | processing task, is_child = 0 7.29.713.594 I slot print_timing: id 0 | task 8242 | prompt eval time = 712.98 ms / 476 tokens ( 1.50 ms per token, 667.62 tokens per second) 7.29.713.601 I slot print_timing: id 0 | task 8242 | eval time = 15700.37 ms / 362 tokens ( 43.49 ms per token, 22.99 tokens per second) 7.29.713.601 I slot print_timing: id 0 | task 8242 | total time = 16413.36 ms / 838 tokens 7.29.713.602 I slot print_timing: id 0 | task 8242 | graphs reused = 8044 7.29.713.603 I slot print_timing: id 0 | task 8242 | graph reallocs = 0 / 0 (same size) / (changed size) 7.29.713.700 I slot release: id 0 | task 8242 | stop processing: n_tokens = 1510, truncated = 0 7.29.750.815 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.707 7.29.750.851 I slot launch_slot_: id 0 | task 8609 | processing task, is_child = 0 7.30.402.867 I slot print_timing: id 2 | task 7814 | n_gen = 790, tg = 22.74 t/s, tg_3s = 15.21 t/s 7.30.403.202 I slot print_timing: id 3 | task 8390 | n_gen = 217, tg = 21.45 t/s, tg_3s = 13.83 t/s 7.31.280.643 I slot print_timing: id 3 | task 8390 | prompt eval time = 462.49 ms / 211 tokens ( 2.19 ms per token, 456.23 tokens per second) 7.31.280.650 I slot print_timing: id 3 | task 8390 | eval time = 10947.99 ms / 238 tokens ( 46.19 ms per token, 21.65 tokens per second) 7.31.280.651 I slot print_timing: id 3 | task 8390 | total time = 11410.48 ms / 449 tokens 7.31.280.652 I slot print_timing: id 3 | task 8390 | graphs reused = 8064 7.31.280.653 I slot print_timing: id 3 | task 8390 | graph reallocs = 0 / 0 (same size) / (changed size) 7.31.280.769 I slot release: id 3 | task 8390 | stop processing: n_tokens = 1372, truncated = 0 7.31.316.704 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.778 7.31.316.733 I slot launch_slot_: id 3 | task 8633 | processing task, is_child = 0 7.33.297.544 I slot print_timing: id 1 | task 8567 | n_gen = 100, tg = 19.51 t/s, tg_3s = 19.70 t/s 7.33.419.512 I slot print_timing: id 2 | task 7814 | n_gen = 853, tg = 22.59 t/s, tg_3s = 20.88 t/s 7.34.911.132 I slot print_timing: id 0 | task 8609 | n_gen = 100, tg = 22.30 t/s, tg_3s = 22.52 t/s 7.35.840.677 I slot print_timing: id 3 | task 8633 | n_gen = 100, tg = 24.78 t/s, tg_3s = 25.03 t/s 7.36.326.898 I slot print_timing: id 1 | task 8567 | n_gen = 175, tg = 21.47 t/s, tg_3s = 24.76 t/s 7.36.449.356 I slot print_timing: id 2 | task 7814 | n_gen = 928, tg = 22.75 t/s, tg_3s = 24.75 t/s 7.37.947.140 I slot print_timing: id 0 | task 8609 | n_gen = 175, tg = 23.27 t/s, tg_3s = 24.70 t/s 7.38.842.015 I slot print_timing: id 3 | task 8633 | n_gen = 174, tg = 24.73 t/s, tg_3s = 24.66 t/s 7.39.327.278 I slot print_timing: id 1 | task 8567 | n_gen = 249, tg = 22.33 t/s, tg_3s = 24.66 t/s 7.39.449.596 I slot print_timing: id 2 | task 7814 | n_gen = 1002, tg = 22.88 t/s, tg_3s = 24.66 t/s 7.40.258.943 I slot print_timing: id 2 | task 7814 | prompt eval time = 726.97 ms / 464 tokens ( 1.57 ms per token, 638.27 tokens per second) 7.40.258.950 I slot print_timing: id 2 | task 7814 | eval time = 44554.27 ms / 1022 tokens ( 43.64 ms per token, 22.92 tokens per second) 7.40.258.951 I slot print_timing: id 2 | task 7814 | total time = 45281.24 ms / 1486 tokens 7.40.258.952 I slot print_timing: id 2 | task 7814 | graphs reused = 8270 7.40.258.953 I slot print_timing: id 2 | task 7814 | graph reallocs = 0 / 0 (same size) / (changed size) 7.40.259.052 I slot release: id 2 | task 7814 | stop processing: n_tokens = 2155, truncated = 0 7.40.301.688 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.496 7.40.307.676 I slot launch_slot_: id 2 | task 8845 | processing task, is_child = 0 7.40.987.067 I slot print_timing: id 0 | task 8609 | n_gen = 234, tg = 22.16 t/s, tg_3s = 19.41 t/s 7.41.867.208 I slot print_timing: id 3 | task 8633 | n_gen = 232, tg = 23.05 t/s, tg_3s = 19.17 t/s 7.42.349.853 I slot print_timing: id 1 | task 8567 | n_gen = 307, tg = 21.66 t/s, tg_3s = 19.19 t/s 7.43.999.194 I slot print_timing: id 0 | task 8609 | n_gen = 308, tg = 22.69 t/s, tg_3s = 24.57 t/s 7.44.888.119 I slot print_timing: id 3 | task 8633 | n_gen = 307, tg = 23.46 t/s, tg_3s = 24.83 t/s 7.45.048.195 I slot print_timing: id 2 | task 8845 | n_gen = 100, tg = 24.85 t/s, tg_3s = 25.10 t/s 7.45.370.818 I slot print_timing: id 1 | task 8567 | n_gen = 382, tg = 22.22 t/s, tg_3s = 24.83 t/s 7.47.024.367 I slot print_timing: id 0 | task 8609 | n_gen = 383, tg = 23.08 t/s, tg_3s = 24.79 t/s 7.47.913.381 I slot print_timing: id 3 | task 8633 | n_gen = 382, tg = 23.71 t/s, tg_3s = 24.79 t/s 7.48.074.503 I slot print_timing: id 2 | task 8845 | n_gen = 175, tg = 24.82 t/s, tg_3s = 24.78 t/s 7.48.397.036 I slot print_timing: id 1 | task 8567 | n_gen = 457, tg = 22.60 t/s, tg_3s = 24.78 t/s 7.50.051.932 I slot print_timing: id 0 | task 8609 | n_gen = 458, tg = 23.34 t/s, tg_3s = 24.77 t/s 7.50.495.826 I slot print_timing: id 0 | task 8609 | prompt eval time = 719.92 ms / 483 tokens ( 1.49 ms per token, 670.91 tokens per second) 7.50.495.832 I slot print_timing: id 0 | task 8609 | eval time = 20025.05 ms / 469 tokens ( 42.79 ms per token, 23.37 tokens per second) 7.50.495.833 I slot print_timing: id 0 | task 8609 | total time = 20744.97 ms / 952 tokens 7.50.495.834 I slot print_timing: id 0 | task 8609 | graphs reused = 8502 7.50.495.834 I slot print_timing: id 0 | task 8609 | graph reallocs = 0 / 0 (same size) / (changed size) 7.50.495.931 I slot release: id 0 | task 8609 | stop processing: n_tokens = 1624, truncated = 0 7.50.532.842 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.658 7.50.532.881 I slot launch_slot_: id 0 | task 9083 | processing task, is_child = 0 7.51.201.387 I slot print_timing: id 2 | task 8845 | n_gen = 237, tg = 23.28 t/s, tg_3s = 19.83 t/s 7.51.201.682 I slot print_timing: id 3 | task 8633 | n_gen = 448, tg = 23.09 t/s, tg_3s = 20.07 t/s 7.51.429.559 I slot print_timing: id 1 | task 8567 | n_gen = 516, tg = 22.19 t/s, tg_3s = 19.46 t/s 7.52.561.842 I slot print_timing: id 2 | task 8845 | prompt eval time = 756.12 ms / 493 tokens ( 1.53 ms per token, 652.01 tokens per second) 7.52.561.849 I slot print_timing: id 2 | task 8845 | eval time = 11498.04 ms / 270 tokens ( 42.74 ms per token, 23.40 tokens per second) 7.52.561.851 I slot print_timing: id 2 | task 8845 | total time = 12254.16 ms / 763 tokens 7.52.561.852 I slot print_timing: id 2 | task 8845 | graphs reused = 8534 7.52.561.852 I slot print_timing: id 2 | task 8845 | graph reallocs = 0 / 0 (same size) / (changed size) 7.52.561.966 I slot release: id 2 | task 8845 | stop processing: n_tokens = 1432, truncated = 0 7.52.604.867 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.746 7.52.604.902 I slot launch_slot_: id 2 | task 9119 | processing task, is_child = 0 7.54.210.806 I slot print_timing: id 3 | task 8633 | n_gen = 506, tg = 22.58 t/s, tg_3s = 19.27 t/s 7.54.452.013 I slot print_timing: id 1 | task 8567 | n_gen = 575, tg = 21.88 t/s, tg_3s = 19.52 t/s 7.55.907.695 I slot print_timing: id 0 | task 9083 | n_gen = 100, tg = 21.35 t/s, tg_3s = 21.56 t/s 7.57.242.483 I slot print_timing: id 3 | task 8633 | n_gen = 581, tg = 22.84 t/s, tg_3s = 24.74 t/s 7.57.322.589 I slot print_timing: id 2 | task 9119 | n_gen = 100, tg = 24.76 t/s, tg_3s = 25.01 t/s 7.57.483.045 I slot print_timing: id 1 | task 8567 | n_gen = 650, tg = 22.18 t/s, tg_3s = 24.74 t/s 7.58.933.230 I slot print_timing: id 0 | task 9083 | n_gen = 175, tg = 22.71 t/s, tg_3s = 24.79 t/s 8.00.266.777 I slot print_timing: id 3 | task 8633 | n_gen = 656, tg = 23.05 t/s, tg_3s = 24.80 t/s 8.00.346.868 I slot print_timing: id 2 | task 9119 | n_gen = 175, tg = 24.78 t/s, tg_3s = 24.80 t/s 8.00.507.660 I slot print_timing: id 1 | task 8567 | n_gen = 725, tg = 22.42 t/s, tg_3s = 24.80 t/s 8.01.033.673 I slot print_timing: id 3 | task 8633 | prompt eval time = 528.64 ms / 279 tokens ( 1.89 ms per token, 527.77 tokens per second) 8.01.033.683 I slot print_timing: id 3 | task 8633 | eval time = 29188.28 ms / 675 tokens ( 43.31 ms per token, 23.09 tokens per second) 8.01.033.684 I slot print_timing: id 3 | task 8633 | total time = 29716.93 ms / 954 tokens 8.01.033.685 I slot print_timing: id 3 | task 8633 | graphs reused = 8723 8.01.033.686 I slot print_timing: id 3 | task 8633 | graph reallocs = 0 / 0 (same size) / (changed size) 8.01.033.807 I slot release: id 3 | task 8633 | stop processing: n_tokens = 1877, truncated = 0 8.01.069.548 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.569 8.01.069.584 I slot launch_slot_: id 3 | task 9314 | processing task, is_child = 0 8.01.942.950 I slot print_timing: id 0 | task 9083 | n_gen = 240, tg = 22.39 t/s, tg_3s = 21.60 t/s 8.03.357.181 I slot print_timing: id 2 | task 9119 | n_gen = 240, tg = 23.82 t/s, tg_3s = 21.59 t/s 8.03.518.525 I slot print_timing: id 1 | task 8567 | n_gen = 790, tg = 22.35 t/s, tg_3s = 21.59 t/s 8.04.973.278 I slot print_timing: id 0 | task 9083 | n_gen = 315, tg = 22.91 t/s, tg_3s = 24.75 t/s 8.05.540.919 I slot print_timing: id 3 | task 9314 | n_gen = 100, tg = 24.72 t/s, tg_3s = 24.97 t/s 8.06.388.473 I slot print_timing: id 2 | task 9119 | n_gen = 315, tg = 24.03 t/s, tg_3s = 24.74 t/s 8.06.549.722 I slot print_timing: id 1 | task 8567 | n_gen = 865, tg = 22.54 t/s, tg_3s = 24.74 t/s 8.08.010.818 I slot print_timing: id 0 | task 9083 | n_gen = 390, tg = 23.24 t/s, tg_3s = 24.69 t/s 8.08.498.079 I slot print_timing: id 2 | task 9119 | prompt eval time = 718.84 ms / 454 tokens ( 1.58 ms per token, 631.57 tokens per second) 8.08.498.087 I slot print_timing: id 2 | task 9119 | eval time = 15174.33 ms / 367 tokens ( 41.46 ms per token, 24.12 tokens per second) 8.08.498.087 I slot print_timing: id 2 | task 9119 | total time = 15893.17 ms / 821 tokens 8.08.498.088 I slot print_timing: id 2 | task 9119 | graphs reused = 8893 8.08.498.089 I slot print_timing: id 2 | task 9119 | graph reallocs = 0 / 0 (same size) / (changed size) 8.08.498.201 I slot release: id 2 | task 9119 | stop processing: n_tokens = 1490, truncated = 0 8.08.540.957 I slot print_timing: id 3 | task 9314 | n_gen = 174, tg = 24.70 t/s, tg_3s = 24.67 t/s 8.08.540.965 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.717 8.08.541.018 I slot launch_slot_: id 2 | task 9490 | processing task, is_child = 0 8.09.556.504 I slot print_timing: id 1 | task 8567 | n_gen = 922, tg = 22.28 t/s, tg_3s = 18.96 t/s 8.10.692.005 I slot print_timing: id 3 | task 9314 | prompt eval time = 467.17 ms / 223 tokens ( 2.09 ms per token, 477.34 tokens per second) 8.10.692.009 I slot print_timing: id 3 | task 9314 | eval time = 9155.24 ms / 210 tokens ( 43.80 ms per token, 22.83 tokens per second) 8.10.692.010 I slot print_timing: id 3 | task 9314 | total time = 9622.41 ms / 433 tokens 8.10.692.011 I slot print_timing: id 3 | task 9314 | graphs reused = 8926 8.10.692.011 I slot print_timing: id 3 | task 9314 | graph reallocs = 0 / 0 (same size) / (changed size) 8.10.692.113 I slot release: id 3 | task 9314 | stop processing: n_tokens = 1356, truncated = 0 8.10.727.886 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.788 8.10.727.920 I slot launch_slot_: id 3 | task 9528 | processing task, is_child = 0 8.11.127.167 I slot print_timing: id 0 | task 9083 | n_gen = 441, tg = 22.16 t/s, tg_3s = 16.37 t/s 8.12.575.738 I slot print_timing: id 1 | task 8567 | n_gen = 987, tg = 22.23 t/s, tg_3s = 21.53 t/s 8.13.711.631 I slot print_timing: id 2 | task 9490 | n_gen = 100, tg = 22.50 t/s, tg_3s = 22.72 t/s 8.14.075.452 I slot print_timing: id 1 | task 8567 | prompt eval time = 856.22 ms / 520 tokens ( 1.65 ms per token, 607.32 tokens per second) 8.14.075.460 I slot print_timing: id 1 | task 8567 | eval time = 45853.32 ms / 1024 tokens ( 44.82 ms per token, 22.31 tokens per second) 8.14.075.461 I slot print_timing: id 1 | task 8567 | total time = 46709.54 ms / 1544 tokens 8.14.075.462 I slot print_timing: id 1 | task 8567 | graphs reused = 8996 8.14.075.463 I slot print_timing: id 1 | task 8567 | graph reallocs = 0 / 0 (same size) / (changed size) 8.14.075.585 I slot release: id 1 | task 8567 | stop processing: n_tokens = 2207, truncated = 0 8.14.118.851 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.484 8.14.124.926 I slot launch_slot_: id 1 | task 9603 | processing task, is_child = 0 8.14.811.520 I slot print_timing: id 0 | task 9083 | n_gen = 515, tg = 21.83 t/s, tg_3s = 20.08 t/s 8.15.895.555 I slot print_timing: id 3 | task 9528 | n_gen = 100, tg = 21.08 t/s, tg_3s = 21.29 t/s 8.16.741.917 I slot print_timing: id 2 | task 9490 | n_gen = 158, tg = 21.13 t/s, tg_3s = 19.14 t/s 8.17.828.843 I slot print_timing: id 0 | task 9083 | n_gen = 589, tg = 22.14 t/s, tg_3s = 24.53 t/s 8.18.876.155 I slot print_timing: id 1 | task 9603 | n_gen = 100, tg = 24.84 t/s, tg_3s = 25.09 t/s 8.18.917.590 I slot print_timing: id 3 | task 9528 | n_gen = 175, tg = 22.54 t/s, tg_3s = 24.82 t/s 8.19.768.111 I slot print_timing: id 2 | task 9490 | n_gen = 233, tg = 22.19 t/s, tg_3s = 24.78 t/s 8.20.856.410 I slot print_timing: id 0 | task 9083 | n_gen = 664, tg = 22.41 t/s, tg_3s = 24.77 t/s 8.21.905.078 I slot print_timing: id 1 | task 9603 | n_gen = 175, tg = 24.80 t/s, tg_3s = 24.76 t/s 8.21.946.677 I slot print_timing: id 3 | task 9528 | n_gen = 250, tg = 23.17 t/s, tg_3s = 24.76 t/s 8.22.794.029 I slot print_timing: id 2 | task 9490 | n_gen = 308, tg = 22.77 t/s, tg_3s = 24.79 t/s 8.23.885.096 I slot print_timing: id 0 | task 9083 | n_gen = 739, tg = 22.63 t/s, tg_3s = 24.76 t/s 8.24.937.601 I slot print_timing: id 1 | task 9603 | n_gen = 250, tg = 24.78 t/s, tg_3s = 24.73 t/s 8.24.979.070 I slot print_timing: id 3 | task 9528 | n_gen = 325, tg = 23.51 t/s, tg_3s = 24.73 t/s 8.25.827.199 I slot print_timing: id 2 | task 9490 | n_gen = 383, tg = 23.13 t/s, tg_3s = 24.73 t/s 8.26.916.841 I slot print_timing: id 0 | task 9083 | n_gen = 814, tg = 22.81 t/s, tg_3s = 24.74 t/s 8.27.443.428 I slot print_timing: id 1 | task 9603 | prompt eval time = 764.91 ms / 497 tokens ( 1.54 ms per token, 649.75 tokens per second) 8.27.443.441 I slot print_timing: id 1 | task 9603 | eval time = 12553.57 ms / 312 tokens ( 40.37 ms per token, 24.77 tokens per second) 8.27.443.443 I slot print_timing: id 1 | task 9603 | total time = 13318.49 ms / 809 tokens 8.27.443.446 I slot print_timing: id 1 | task 9603 | graphs reused = 9305 8.27.443.447 I slot print_timing: id 1 | task 9603 | graph reallocs = 0 / 0 (same size) / (changed size) 8.27.443.551 I slot release: id 1 | task 9603 | stop processing: n_tokens = 1476, truncated = 0 8.27.487.141 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.724 8.27.487.173 I slot launch_slot_: id 1 | task 9918 | processing task, is_child = 0 8.28.172.535 I slot print_timing: id 3 | task 9528 | n_gen = 388, tg = 22.80 t/s, tg_3s = 19.73 t/s 8.28.850.336 I slot print_timing: id 2 | task 9490 | n_gen = 441, tg = 22.52 t/s, tg_3s = 19.19 t/s 8.29.941.309 I slot print_timing: id 0 | task 9083 | n_gen = 872, tg = 22.52 t/s, tg_3s = 19.18 t/s 8.30.184.428 I slot print_timing: id 2 | task 9490 | prompt eval time = 769.76 ms / 496 tokens ( 1.55 ms per token, 644.36 tokens per second) 8.30.184.435 I slot print_timing: id 2 | task 9490 | eval time = 20873.64 ms / 474 tokens ( 44.13 ms per token, 22.66 tokens per second) 8.30.184.436 I slot print_timing: id 2 | task 9490 | total time = 21643.40 ms / 970 tokens 8.30.184.437 I slot print_timing: id 2 | task 9490 | graphs reused = 9352 8.30.184.437 I slot print_timing: id 2 | task 9490 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.184.540 I slot release: id 2 | task 9490 | stop processing: n_tokens = 1639, truncated = 0 8.30.227.465 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.652 8.30.227.502 I slot launch_slot_: id 2 | task 9970 | processing task, is_child = 0 8.31.208.524 I slot print_timing: id 3 | task 9528 | n_gen = 446, tg = 22.24 t/s, tg_3s = 19.10 t/s 8.32.916.864 I slot print_timing: id 1 | task 9918 | n_gen = 100, tg = 21.22 t/s, tg_3s = 21.43 t/s 8.32.956.748 I slot print_timing: id 0 | task 9083 | n_gen = 930, tg = 22.29 t/s, tg_3s = 19.23 t/s 8.34.213.534 I slot print_timing: id 3 | task 9528 | n_gen = 520, tg = 22.55 t/s, tg_3s = 24.63 t/s 8.34.972.095 I slot print_timing: id 2 | task 9970 | n_gen = 100, tg = 24.73 t/s, tg_3s = 24.98 t/s 8.35.940.923 I slot print_timing: id 1 | task 9918 | n_gen = 175, tg = 22.63 t/s, tg_3s = 24.80 t/s 8.35.980.844 I slot print_timing: id 0 | task 9083 | n_gen = 1005, tg = 22.46 t/s, tg_3s = 24.80 t/s 8.36.749.327 I slot print_timing: id 0 | task 9083 | prompt eval time = 736.97 ms / 493 tokens ( 1.49 ms per token, 668.95 tokens per second) 8.36.749.331 I slot print_timing: id 0 | task 9083 | eval time = 45479.47 ms / 1024 tokens ( 44.46 ms per token, 22.49 tokens per second) 8.36.749.332 I slot print_timing: id 0 | task 9083 | total time = 46216.44 ms / 1517 tokens 8.36.749.332 I slot print_timing: id 0 | task 9083 | graphs reused = 9493 8.36.749.333 I slot print_timing: id 0 | task 9083 | graph reallocs = 0 / 0 (same size) / (changed size) 8.36.749.434 I slot release: id 0 | task 9083 | stop processing: n_tokens = 2189, truncated = 0 8.36.786.188 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.488 8.36.792.410 I slot launch_slot_: id 0 | task 10117 | processing task, is_child = 0 8.37.431.199 I slot print_timing: id 3 | task 9528 | n_gen = 585, tg = 22.26 t/s, tg_3s = 20.20 t/s 8.37.982.209 I slot print_timing: id 2 | task 9970 | n_gen = 159, tg = 22.53 t/s, tg_3s = 19.60 t/s 8.38.947.546 I slot print_timing: id 1 | task 9918 | n_gen = 234, tg = 21.78 t/s, tg_3s = 19.62 t/s 8.40.441.050 I slot print_timing: id 3 | task 9528 | n_gen = 659, tg = 22.50 t/s, tg_3s = 24.59 t/s 8.41.003.405 I slot print_timing: id 2 | task 9970 | n_gen = 234, tg = 23.22 t/s, tg_3s = 24.82 t/s 8.41.486.535 I slot print_timing: id 0 | task 10117 | n_gen = 100, tg = 24.83 t/s, tg_3s = 25.08 t/s 8.41.971.293 I slot print_timing: id 1 | task 9918 | n_gen = 309, tg = 22.45 t/s, tg_3s = 24.80 t/s 8.43.468.794 I slot print_timing: id 3 | task 9528 | n_gen = 734, tg = 22.71 t/s, tg_3s = 24.77 t/s 8.44.034.041 I slot print_timing: id 2 | task 9970 | n_gen = 309, tg = 23.57 t/s, tg_3s = 24.75 t/s 8.44.518.159 I slot print_timing: id 0 | task 10117 | n_gen = 175, tg = 24.79 t/s, tg_3s = 24.74 t/s 8.45.004.240 I slot print_timing: id 1 | task 9918 | n_gen = 384, tg = 22.86 t/s, tg_3s = 24.73 t/s 8.45.287.247 I slot print_timing: id 2 | task 9970 | prompt eval time = 740.74 ms / 482 tokens ( 1.54 ms per token, 650.70 tokens per second) 8.45.287.255 I slot print_timing: id 2 | task 9970 | eval time = 14318.99 ms / 340 tokens ( 42.24 ms per token, 23.67 tokens per second) 8.45.287.256 I slot print_timing: id 2 | task 9970 | total time = 15059.74 ms / 822 tokens 8.45.287.257 I slot print_timing: id 2 | task 9970 | graphs reused = 9685 8.45.287.257 I slot print_timing: id 2 | task 9970 | graph reallocs = 0 / 0 (same size) / (changed size) 8.45.287.363 I slot release: id 2 | task 9970 | stop processing: n_tokens = 1491, truncated = 0 8.45.330.348 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.881 (> 0.100 thold), f_keep = 0.716 8.45.330.385 I slot launch_slot_: id 2 | task 10314 | processing task, is_child = 0 8.46.505.319 I slot print_timing: id 3 | task 9528 | n_gen = 788, tg = 22.29 t/s, tg_3s = 17.78 t/s 8.47.553.387 I slot print_timing: id 0 | task 10117 | n_gen = 229, tg = 22.68 t/s, tg_3s = 17.79 t/s 8.48.038.474 I slot print_timing: id 1 | task 9918 | n_gen = 438, tg = 22.08 t/s, tg_3s = 17.80 t/s 8.49.536.825 I slot print_timing: id 3 | task 9528 | n_gen = 863, tg = 22.48 t/s, tg_3s = 24.74 t/s 8.50.306.034 I slot print_timing: id 2 | task 10314 | n_gen = 100, tg = 24.75 t/s, tg_3s = 25.00 t/s 8.50.588.656 I slot print_timing: id 0 | task 10117 | n_gen = 304, tg = 23.15 t/s, tg_3s = 24.71 t/s 8.51.075.152 I slot print_timing: id 1 | task 9918 | n_gen = 513, tg = 22.43 t/s, tg_3s = 24.70 t/s 8.52.540.183 I slot print_timing: id 3 | task 9528 | n_gen = 937, tg = 22.64 t/s, tg_3s = 24.64 t/s 8.53.310.264 I slot print_timing: id 2 | task 10314 | n_gen = 174, tg = 24.70 t/s, tg_3s = 24.63 t/s 8.53.594.335 I slot print_timing: id 0 | task 10117 | n_gen = 378, tg = 23.42 t/s, tg_3s = 24.62 t/s 8.54.082.311 I slot print_timing: id 1 | task 9918 | n_gen = 587, tg = 22.69 t/s, tg_3s = 24.61 t/s 8.55.545.750 I slot print_timing: id 3 | task 9528 | n_gen = 1011, tg = 22.77 t/s, tg_3s = 24.62 t/s 8.56.072.063 I slot print_timing: id 3 | task 9528 | prompt eval time = 470.15 ms / 220 tokens ( 2.14 ms per token, 467.93 tokens per second) 8.56.072.070 I slot print_timing: id 3 | task 9528 | eval time = 44873.98 ms / 1024 tokens ( 43.87 ms per token, 22.80 tokens per second) 8.56.072.070 I slot print_timing: id 3 | task 9528 | total time = 45344.13 ms / 1244 tokens 8.56.072.071 I slot print_timing: id 3 | task 9528 | graphs reused = 9924 8.56.072.072 I slot print_timing: id 3 | task 9528 | graph reallocs = 0 / 0 (same size) / (changed size) 8.56.072.180 I slot release: id 3 | task 9528 | stop processing: n_tokens = 2167, truncated = 0 8.56.107.609 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.493 8.56.113.360 I slot launch_slot_: id 3 | task 10560 | processing task, is_child = 0 8.56.504.979 I slot print_timing: id 2 | task 10314 | n_gen = 244, tg = 23.83 t/s, tg_3s = 21.91 t/s 8.56.614.940 I slot print_timing: id 0 | task 10117 | n_gen = 443, tg = 23.12 t/s, tg_3s = 21.52 t/s 8.56.773.077 I slot print_timing: id 0 | task 10117 | prompt eval time = 706.63 ms / 467 tokens ( 1.51 ms per token, 660.88 tokens per second) 8.56.773.079 I slot print_timing: id 0 | task 10117 | eval time = 19274.02 ms / 447 tokens ( 43.22 ms per token, 23.14 tokens per second) 8.56.773.080 I slot print_timing: id 0 | task 10117 | total time = 19980.65 ms / 914 tokens 8.56.773.081 I slot print_timing: id 0 | task 10117 | graphs reused = 9928 8.56.773.081 I slot print_timing: id 0 | task 10117 | graph reallocs = 0 / 0 (same size) / (changed size) 8.56.773.138 I slot release: id 0 | task 10117 | stop processing: n_tokens = 1586, truncated = 0 8.56.807.694 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.673 8.56.807.714 I slot launch_slot_: id 0 | task 10569 | processing task, is_child = 0 8.57.423.437 I slot print_timing: id 1 | task 9918 | n_gen = 646, tg = 22.11 t/s, tg_3s = 17.66 t/s 8.59.511.895 I slot print_timing: id 2 | task 10314 | n_gen = 303, tg = 22.87 t/s, tg_3s = 19.62 t/s 9.00.437.069 I slot print_timing: id 1 | task 9918 | n_gen = 720, tg = 22.34 t/s, tg_3s = 24.56 t/s 9.01.161.504 I slot print_timing: id 3 | task 10560 | n_gen = 100, tg = 21.58 t/s, tg_3s = 21.80 t/s 9.01.481.879 I slot print_timing: id 0 | task 10569 | n_gen = 100, tg = 24.81 t/s, tg_3s = 25.06 t/s 9.02.206.230 I slot print_timing: id 2 | task 10314 | prompt eval time = 975.82 ms / 542 tokens ( 1.80 ms per token, 555.43 tokens per second) 9.02.206.237 I slot print_timing: id 2 | task 10314 | eval time = 15900.01 ms / 370 tokens ( 43.09 ms per token, 23.21 tokens per second) 9.02.206.238 I slot print_timing: id 2 | task 10314 | total time = 16875.84 ms / 912 tokens 9.02.206.239 I slot print_timing: id 2 | task 10314 | graphs reused = 10045 9.02.206.240 I slot print_timing: id 2 | task 10314 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.206.349 I slot release: id 2 | task 10314 | stop processing: n_tokens = 1581, truncated = 0 9.02.249.004 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.676 9.02.249.034 I slot launch_slot_: id 2 | task 10690 | processing task, is_child = 0 9.03.454.050 I slot print_timing: id 1 | task 9918 | n_gen = 779, tg = 22.10 t/s, tg_3s = 19.56 t/s 9.03.616.585 I slot print_timing: id 1 | task 9918 | prompt eval time = 763.20 ms / 496 tokens ( 1.54 ms per token, 649.90 tokens per second) 9.03.616.592 I slot print_timing: id 1 | task 9918 | eval time = 35366.21 ms / 783 tokens ( 45.23 ms per token, 22.11 tokens per second) 9.03.616.595 I slot print_timing: id 1 | task 9918 | total time = 36129.41 ms / 1279 tokens 9.03.616.595 I slot print_timing: id 1 | task 9918 | graphs reused = 10060 9.03.616.596 I slot print_timing: id 1 | task 9918 | graph reallocs = 0 / 0 (same size) / (changed size) 9.03.616.713 I slot release: id 1 | task 9918 | stop processing: n_tokens = 1946, truncated = 0 9.03.659.539 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.549 9.03.659.578 I slot launch_slot_: id 1 | task 10710 | processing task, is_child = 0 9.04.318.388 I slot print_timing: id 3 | task 10560 | n_gen = 147, tg = 18.85 t/s, tg_3s = 14.89 t/s 9.04.514.765 I slot print_timing: id 0 | task 10569 | n_gen = 143, tg = 20.22 t/s, tg_3s = 14.18 t/s 9.07.331.035 I slot print_timing: id 3 | task 10560 | n_gen = 221, tg = 20.45 t/s, tg_3s = 24.56 t/s 9.07.530.949 I slot print_timing: id 0 | task 10569 | n_gen = 218, tg = 21.61 t/s, tg_3s = 24.87 t/s 9.07.612.691 I slot print_timing: id 2 | task 10690 | n_gen = 100, tg = 21.34 t/s, tg_3s = 21.56 t/s 9.08.377.608 I slot print_timing: id 1 | task 10710 | n_gen = 100, tg = 24.86 t/s, tg_3s = 25.11 t/s 9.10.352.214 I slot print_timing: id 3 | task 10560 | n_gen = 296, tg = 21.41 t/s, tg_3s = 24.82 t/s 9.10.552.034 I slot print_timing: id 0 | task 10569 | n_gen = 293, tg = 22.36 t/s, tg_3s = 24.83 t/s 9.10.633.606 I slot print_timing: id 2 | task 10690 | n_gen = 175, tg = 22.72 t/s, tg_3s = 24.83 t/s 9.11.361.375 I slot print_timing: id 3 | task 10560 | prompt eval time = 461.60 ms / 211 tokens ( 2.19 ms per token, 457.11 tokens per second) 9.11.361.382 I slot print_timing: id 3 | task 10560 | eval time = 14786.40 ms / 321 tokens ( 46.21 ms per token, 21.64 tokens per second) 9.11.361.383 I slot print_timing: id 3 | task 10560 | total time = 15248.00 ms / 532 tokens 9.11.361.384 I slot print_timing: id 3 | task 10560 | graphs reused = 10232 9.11.361.385 I slot print_timing: id 3 | task 10560 | graph reallocs = 0 / 0 (same size) / (changed size) 9.11.361.482 I slot release: id 3 | task 10560 | stop processing: n_tokens = 1455, truncated = 0 9.11.396.290 I slot print_timing: id 1 | task 10710 | n_gen = 175, tg = 24.85 t/s, tg_3s = 24.85 t/s 9.11.396.913 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.734 9.11.396.945 I slot launch_slot_: id 3 | task 10887 | processing task, is_child = 0 9.13.285.071 I slot print_timing: id 0 | task 10569 | prompt eval time = 683.88 ms / 451 tokens ( 1.52 ms per token, 659.47 tokens per second) 9.13.285.078 I slot print_timing: id 0 | task 10569 | eval time = 15793.47 ms / 351 tokens ( 45.12 ms per token, 22.16 tokens per second) 9.13.285.079 I slot print_timing: id 0 | task 10569 | total time = 16477.35 ms / 802 tokens 9.13.285.080 I slot print_timing: id 0 | task 10569 | graphs reused = 10266 9.13.285.080 I slot print_timing: id 0 | task 10569 | graph reallocs = 0 / 0 (same size) / (changed size) 9.13.285.175 I slot release: id 0 | task 10569 | stop processing: n_tokens = 1474, truncated = 0 9.13.322.150 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.725 9.13.322.187 I slot launch_slot_: id 0 | task 10926 | processing task, is_child = 0 9.13.960.530 I slot print_timing: id 2 | task 10690 | n_gen = 233, tg = 21.12 t/s, tg_3s = 17.43 t/s 9.14.426.207 I slot print_timing: id 1 | task 10710 | n_gen = 225, tg = 22.33 t/s, tg_3s = 16.50 t/s 9.15.998.776 I slot print_timing: id 1 | task 10710 | prompt eval time = 735.95 ms / 474 tokens ( 1.55 ms per token, 644.07 tokens per second) 9.15.998.783 I slot print_timing: id 1 | task 10710 | eval time = 11603.24 ms / 264 tokens ( 44.12 ms per token, 22.67 tokens per second) 9.15.998.784 I slot print_timing: id 1 | task 10710 | total time = 12339.18 ms / 738 tokens 9.15.998.785 I slot print_timing: id 1 | task 10710 | graphs reused = 10315 9.15.998.786 I slot print_timing: id 1 | task 10710 | graph reallocs = 0 / 0 (same size) / (changed size) 9.15.998.911 I slot release: id 1 | task 10710 | stop processing: n_tokens = 1405, truncated = 0 9.16.042.484 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.760 9.16.042.525 I slot launch_slot_: id 1 | task 10979 | processing task, is_child = 0 9.16.999.491 I slot print_timing: id 2 | task 10690 | n_gen = 291, tg = 20.68 t/s, tg_3s = 19.09 t/s 9.17.164.133 I slot print_timing: id 3 | task 10887 | n_gen = 100, tg = 18.69 t/s, tg_3s = 18.88 t/s 9.18.696.989 I slot print_timing: id 0 | task 10926 | n_gen = 100, tg = 21.21 t/s, tg_3s = 21.42 t/s 9.20.021.425 I slot print_timing: id 2 | task 10690 | n_gen = 366, tg = 21.41 t/s, tg_3s = 24.82 t/s 9.20.182.180 I slot print_timing: id 3 | task 10887 | n_gen = 175, tg = 20.93 t/s, tg_3s = 24.85 t/s 9.20.786.708 I slot print_timing: id 1 | task 10979 | n_gen = 100, tg = 24.83 t/s, tg_3s = 25.08 t/s 9.21.710.374 I slot print_timing: id 0 | task 10926 | n_gen = 175, tg = 22.65 t/s, tg_3s = 24.89 t/s 9.23.040.159 I slot print_timing: id 2 | task 10690 | n_gen = 441, tg = 21.93 t/s, tg_3s = 24.84 t/s 9.23.202.386 I slot print_timing: id 3 | task 10887 | n_gen = 250, tg = 21.97 t/s, tg_3s = 24.83 t/s 9.23.808.588 I slot print_timing: id 1 | task 10979 | n_gen = 175, tg = 24.82 t/s, tg_3s = 24.82 t/s 9.24.741.061 I slot print_timing: id 0 | task 10926 | n_gen = 250, tg = 23.24 t/s, tg_3s = 24.75 t/s 9.25.796.897 I slot print_timing: id 2 | task 10690 | prompt eval time = 724.67 ms / 460 tokens ( 1.58 ms per token, 634.77 tokens per second) 9.25.796.902 I slot print_timing: id 2 | task 10690 | eval time = 22823.18 ms / 509 tokens ( 44.93 ms per token, 22.26 tokens per second) 9.25.796.903 I slot print_timing: id 2 | task 10690 | total time = 23547.85 ms / 969 tokens 9.25.796.904 I slot print_timing: id 2 | task 10690 | graphs reused = 10536 9.25.796.905 I slot print_timing: id 2 | task 10690 | graph reallocs = 0 / 0 (same size) / (changed size) 9.25.797.032 I slot release: id 2 | task 10690 | stop processing: n_tokens = 1664, truncated = 0 9.25.840.714 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.642 9.25.840.750 I slot launch_slot_: id 2 | task 11206 | processing task, is_child = 0 9.26.492.831 I slot print_timing: id 3 | task 10887 | n_gen = 316, tg = 21.54 t/s, tg_3s = 20.06 t/s 9.26.847.992 I slot print_timing: id 1 | task 10979 | n_gen = 234, tg = 23.19 t/s, tg_3s = 19.41 t/s 9.27.781.173 I slot print_timing: id 0 | task 10926 | n_gen = 309, tg = 22.40 t/s, tg_3s = 19.41 t/s 9.29.516.783 I slot print_timing: id 3 | task 10887 | n_gen = 390, tg = 22.04 t/s, tg_3s = 24.47 t/s 9.29.877.052 I slot print_timing: id 1 | task 10979 | n_gen = 309, tg = 23.55 t/s, tg_3s = 24.76 t/s 9.30.564.952 I slot print_timing: id 2 | task 11206 | n_gen = 100, tg = 24.78 t/s, tg_3s = 25.03 t/s 9.30.805.670 I slot print_timing: id 0 | task 10926 | n_gen = 384, tg = 22.83 t/s, tg_3s = 24.80 t/s 9.32.541.015 I slot print_timing: id 3 | task 10887 | n_gen = 465, tg = 22.45 t/s, tg_3s = 24.80 t/s 9.32.900.868 I slot print_timing: id 1 | task 10979 | n_gen = 384, tg = 23.79 t/s, tg_3s = 24.80 t/s 9.33.061.420 I slot print_timing: id 1 | task 10979 | prompt eval time = 756.83 ms / 487 tokens ( 1.55 ms per token, 643.47 tokens per second) 9.33.061.423 I slot print_timing: id 1 | task 10979 | eval time = 16262.06 ms / 388 tokens ( 42.02 ms per token, 23.80 tokens per second) 9.33.061.425 I slot print_timing: id 1 | task 10979 | total time = 17018.89 ms / 875 tokens 9.33.061.426 I slot print_timing: id 1 | task 10979 | graphs reused = 10695 9.33.061.427 I slot print_timing: id 1 | task 10979 | graph reallocs = 0 / 0 (same size) / (changed size) 9.33.061.545 I slot release: id 1 | task 10979 | stop processing: n_tokens = 1542, truncated = 0 9.33.104.642 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.693 9.33.104.675 I slot launch_slot_: id 1 | task 11371 | processing task, is_child = 0 9.33.800.348 I slot print_timing: id 2 | task 11206 | n_gen = 164, tg = 22.54 t/s, tg_3s = 19.78 t/s 9.33.877.689 I slot print_timing: id 0 | task 10926 | n_gen = 443, tg = 22.27 t/s, tg_3s = 19.21 t/s 9.35.575.830 I slot print_timing: id 3 | task 10887 | n_gen = 523, tg = 22.02 t/s, tg_3s = 19.11 t/s 9.36.823.442 I slot print_timing: id 2 | task 11206 | n_gen = 238, tg = 23.11 t/s, tg_3s = 24.48 t/s 9.36.902.653 I slot print_timing: id 0 | task 10926 | n_gen = 518, tg = 22.60 t/s, tg_3s = 24.79 t/s 9.37.867.361 I slot print_timing: id 1 | task 11371 | n_gen = 100, tg = 24.82 t/s, tg_3s = 25.07 t/s 9.38.592.456 I slot print_timing: id 3 | task 10887 | n_gen = 598, tg = 22.34 t/s, tg_3s = 24.86 t/s 9.39.637.017 I slot print_timing: id 3 | task 10887 | prompt eval time = 471.41 ms / 225 tokens ( 2.10 ms per token, 477.30 tokens per second) 9.39.637.025 I slot print_timing: id 3 | task 10887 | eval time = 27768.66 ms / 624 tokens ( 44.57 ms per token, 22.44 tokens per second) 9.39.637.026 I slot print_timing: id 3 | task 10887 | total time = 28240.06 ms / 849 tokens 9.39.637.027 I slot print_timing: id 3 | task 10887 | graphs reused = 10837 9.39.637.027 I slot print_timing: id 3 | task 10887 | graph reallocs = 0 / 0 (same size) / (changed size) 9.39.637.130 I slot release: id 3 | task 10887 | stop processing: n_tokens = 1772, truncated = 0 9.39.672.277 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.603 9.39.672.310 I slot launch_slot_: id 3 | task 11518 | processing task, is_child = 0 9.40.090.270 I slot print_timing: id 0 | task 10926 | n_gen = 588, tg = 22.52 t/s, tg_3s = 21.96 t/s 9.40.090.791 I slot print_timing: id 2 | task 11206 | n_gen = 310, tg = 22.85 t/s, tg_3s = 22.04 t/s 9.40.768.719 I slot print_timing: id 2 | task 11206 | prompt eval time = 728.51 ms / 462 tokens ( 1.58 ms per token, 634.17 tokens per second) 9.40.768.726 I slot print_timing: id 2 | task 11206 | eval time = 14199.45 ms / 326 tokens ( 43.69 ms per token, 22.89 tokens per second) 9.40.768.727 I slot print_timing: id 2 | task 11206 | total time = 14927.96 ms / 788 tokens 9.40.768.727 I slot print_timing: id 2 | task 11206 | graphs reused = 10851 9.40.768.728 I slot print_timing: id 2 | task 11206 | graph reallocs = 0 / 0 (same size) / (changed size) 9.40.768.840 I slot release: id 2 | task 11206 | stop processing: n_tokens = 1483, truncated = 0 9.40.810.994 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.721 9.40.811.031 I slot launch_slot_: id 2 | task 11537 | processing task, is_child = 0 9.41.457.541 I slot print_timing: id 1 | task 11371 | n_gen = 164, tg = 21.51 t/s, tg_3s = 17.83 t/s 9.42.468.285 I slot print_timing: id 0 | task 10926 | prompt eval time = 706.58 ms / 468 tokens ( 1.51 ms per token, 662.35 tokens per second) 9.42.468.292 I slot print_timing: id 0 | task 10926 | eval time = 28439.51 ms / 630 tokens ( 45.21 ms per token, 22.12 tokens per second) 9.42.468.293 I slot print_timing: id 0 | task 10926 | total time = 29146.09 ms / 1098 tokens 9.42.468.294 I slot print_timing: id 0 | task 10926 | graphs reused = 10873 9.42.468.294 I slot print_timing: id 0 | task 10926 | graph reallocs = 0 / 0 (same size) / (changed size) 9.42.468.388 I slot release: id 0 | task 10926 | stop processing: n_tokens = 1770, truncated = 0 9.42.505.138 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.603 9.42.505.175 I slot launch_slot_: id 0 | task 11564 | processing task, is_child = 0 9.44.461.603 I slot print_timing: id 1 | task 11371 | n_gen = 222, tg = 20.88 t/s, tg_3s = 19.31 t/s 9.45.427.299 I slot print_timing: id 3 | task 11518 | n_gen = 100, tg = 18.80 t/s, tg_3s = 18.99 t/s 9.46.149.629 I slot print_timing: id 2 | task 11537 | n_gen = 100, tg = 21.45 t/s, tg_3s = 21.66 t/s 9.47.192.586 I slot print_timing: id 0 | task 11564 | n_gen = 100, tg = 24.87 t/s, tg_3s = 25.12 t/s 9.47.474.061 I slot print_timing: id 1 | task 11371 | n_gen = 297, tg = 21.77 t/s, tg_3s = 24.90 t/s 9.48.439.366 I slot print_timing: id 3 | task 11518 | n_gen = 175, tg = 21.02 t/s, tg_3s = 24.90 t/s 9.49.161.580 I slot print_timing: id 2 | task 11537 | n_gen = 175, tg = 22.81 t/s, tg_3s = 24.90 t/s 9.50.208.032 I slot print_timing: id 0 | task 11564 | n_gen = 175, tg = 24.87 t/s, tg_3s = 24.87 t/s 9.50.491.088 I slot print_timing: id 1 | task 11371 | n_gen = 372, tg = 22.33 t/s, tg_3s = 24.86 t/s 9.51.461.058 I slot print_timing: id 3 | task 11518 | n_gen = 250, tg = 22.04 t/s, tg_3s = 24.82 t/s 9.52.185.893 I slot print_timing: id 2 | task 11537 | n_gen = 250, tg = 23.38 t/s, tg_3s = 24.80 t/s 9.53.229.621 I slot print_timing: id 0 | task 11564 | n_gen = 250, tg = 24.86 t/s, tg_3s = 24.82 t/s 9.53.511.262 I slot print_timing: id 1 | task 11371 | n_gen = 447, tg = 22.72 t/s, tg_3s = 24.83 t/s 9.53.992.432 I slot print_timing: id 1 | task 11371 | prompt eval time = 773.30 ms / 510 tokens ( 1.52 ms per token, 659.51 tokens per second) 9.53.992.439 I slot print_timing: id 1 | task 11371 | eval time = 20114.44 ms / 459 tokens ( 43.92 ms per token, 22.77 tokens per second) 9.53.992.440 I slot print_timing: id 1 | task 11371 | total time = 20887.75 ms / 969 tokens 9.53.992.441 I slot print_timing: id 1 | task 11371 | graphs reused = 11140 9.53.992.442 I slot print_timing: id 1 | task 11371 | graph reallocs = 0 / 0 (same size) / (changed size) 9.53.992.565 I slot release: id 1 | task 11371 | stop processing: n_tokens = 1636, truncated = 0 9.54.035.656 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.653 9.54.035.697 I slot launch_slot_: id 1 | task 11836 | processing task, is_child = 0 9.54.693.230 I slot print_timing: id 3 | task 11518 | n_gen = 315, tg = 21.61 t/s, tg_3s = 20.11 t/s 9.55.207.098 I slot print_timing: id 2 | task 11537 | n_gen = 309, tg = 22.53 t/s, tg_3s = 19.53 t/s 9.56.257.265 I slot print_timing: id 0 | task 11564 | n_gen = 309, tg = 23.61 t/s, tg_3s = 19.49 t/s 9.57.710.308 I slot print_timing: id 3 | task 11518 | n_gen = 389, tg = 22.11 t/s, tg_3s = 24.53 t/s 9.58.233.002 I slot print_timing: id 2 | task 11537 | n_gen = 384, tg = 22.94 t/s, tg_3s = 24.79 t/s 9.58.756.437 I slot print_timing: id 1 | task 11836 | n_gen = 100, tg = 24.84 t/s, tg_3s = 25.09 t/s 9.59.280.572 I slot print_timing: id 0 | task 11564 | n_gen = 384, tg = 23.83 t/s, tg_3s = 24.81 t/s 10.00.736.206 I slot print_timing: id 3 | task 11518 | n_gen = 464, tg = 22.50 t/s, tg_3s = 24.79 t/s 10.01.259.800 I slot print_timing: id 2 | task 11537 | n_gen = 459, tg = 23.22 t/s, tg_3s = 24.78 t/s 10.01.785.587 I slot print_timing: id 1 | task 11836 | n_gen = 175, tg = 24.81 t/s, tg_3s = 24.76 t/s 10.01.866.300 I slot print_timing: id 0 | task 11564 | prompt eval time = 706.50 ms / 469 tokens ( 1.51 ms per token, 663.83 tokens per second) 10.01.866.306 I slot print_timing: id 0 | task 11564 | eval time = 18654.62 ms / 448 tokens ( 41.73 ms per token, 23.96 tokens per second) 10.01.866.307 I slot print_timing: id 0 | task 11564 | total time = 19361.12 ms / 917 tokens 10.01.866.308 I slot print_timing: id 0 | task 11564 | graphs reused = 11314 10.01.866.308 I slot print_timing: id 0 | task 11564 | graph reallocs = 0 / 0 (same size) / (changed size) 10.01.866.411 I slot release: id 0 | task 11564 | stop processing: n_tokens = 1589, truncated = 0 10.01.903.751 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.672 10.01.903.791 I slot launch_slot_: id 0 | task 12016 | processing task, is_child = 0 10.03.770.486 I slot print_timing: id 3 | task 11518 | n_gen = 523, tg = 22.11 t/s, tg_3s = 19.44 t/s 10.04.294.500 I slot print_timing: id 2 | task 11537 | n_gen = 518, tg = 22.71 t/s, tg_3s = 19.44 t/s 10.04.817.744 I slot print_timing: id 1 | task 11836 | n_gen = 234, tg = 23.19 t/s, tg_3s = 19.46 t/s 10.06.623.889 I slot print_timing: id 0 | task 12016 | n_gen = 100, tg = 24.85 t/s, tg_3s = 25.10 t/s 10.06.784.991 I slot print_timing: id 3 | task 11518 | n_gen = 598, tg = 22.42 t/s, tg_3s = 24.88 t/s 10.07.307.476 I slot print_timing: id 2 | task 11537 | n_gen = 593, tg = 22.97 t/s, tg_3s = 24.89 t/s 10.07.831.985 I slot print_timing: id 1 | task 11836 | n_gen = 309, tg = 23.58 t/s, tg_3s = 24.88 t/s 10.09.124.916 I slot print_timing: id 3 | task 11518 | prompt eval time = 488.55 ms / 234 tokens ( 2.09 ms per token, 478.97 tokens per second) 10.09.124.923 I slot print_timing: id 3 | task 11518 | eval time = 28964.05 ms / 656 tokens ( 44.22 ms per token, 22.61 tokens per second) 10.09.124.924 I slot print_timing: id 3 | task 11518 | total time = 29452.60 ms / 890 tokens 10.09.124.925 I slot print_timing: id 3 | task 11518 | graphs reused = 11474 10.09.124.926 I slot print_timing: id 3 | task 11518 | graph reallocs = 0 / 0 (same size) / (changed size) 10.09.125.029 I slot release: id 3 | task 11518 | stop processing: n_tokens = 1813, truncated = 0 10.09.160.169 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.589 10.09.160.198 I slot launch_slot_: id 3 | task 12181 | processing task, is_child = 0 10.09.690.541 I slot print_timing: id 0 | task 12016 | n_gen = 165, tg = 23.26 t/s, tg_3s = 21.20 t/s 10.10.337.705 I slot print_timing: id 2 | task 11537 | n_gen = 657, tg = 22.77 t/s, tg_3s = 21.12 t/s 10.10.861.495 I slot print_timing: id 1 | task 11836 | n_gen = 373, tg = 23.12 t/s, tg_3s = 21.13 t/s 10.12.714.290 I slot print_timing: id 0 | task 12016 | n_gen = 240, tg = 23.72 t/s, tg_3s = 24.80 t/s 10.13.360.408 I slot print_timing: id 2 | task 11537 | n_gen = 732, tg = 22.97 t/s, tg_3s = 24.81 t/s 10.13.683.261 I slot print_timing: id 3 | task 12181 | n_gen = 100, tg = 24.80 t/s, tg_3s = 25.05 t/s 10.13.883.387 I slot print_timing: id 1 | task 11836 | n_gen = 448, tg = 23.39 t/s, tg_3s = 24.82 t/s 10.15.734.861 I slot print_timing: id 0 | task 12016 | n_gen = 315, tg = 23.98 t/s, tg_3s = 24.83 t/s 10.16.380.154 I slot print_timing: id 2 | task 11537 | n_gen = 807, tg = 23.13 t/s, tg_3s = 24.84 t/s 10.16.703.451 I slot print_timing: id 3 | task 12181 | n_gen = 175, tg = 24.81 t/s, tg_3s = 24.83 t/s 10.16.903.603 I slot print_timing: id 1 | task 11836 | n_gen = 523, tg = 23.59 t/s, tg_3s = 24.83 t/s 10.18.757.329 I slot print_timing: id 0 | task 12016 | n_gen = 390, tg = 24.14 t/s, tg_3s = 24.81 t/s 10.19.404.532 I slot print_timing: id 2 | task 11537 | n_gen = 882, tg = 23.26 t/s, tg_3s = 24.80 t/s 10.19.728.507 I slot print_timing: id 3 | task 12181 | n_gen = 250, tg = 24.81 t/s, tg_3s = 24.79 t/s 10.19.930.318 I slot print_timing: id 1 | task 11836 | n_gen = 598, tg = 23.73 t/s, tg_3s = 24.78 t/s 10.21.354.031 I slot print_timing: id 2 | task 11537 | prompt eval time = 722.67 ms / 456 tokens ( 1.58 ms per token, 630.99 tokens per second) 10.21.354.036 I slot print_timing: id 2 | task 11537 | eval time = 39820.32 ms / 930 tokens ( 42.86 ms per token, 23.33 tokens per second) 10.21.354.037 I slot print_timing: id 2 | task 11537 | total time = 40542.99 ms / 1386 tokens 10.21.354.038 I slot print_timing: id 2 | task 11537 | graphs reused = 11761 10.21.354.038 I slot print_timing: id 2 | task 11537 | graph reallocs = 0 / 0 (same size) / (changed size) 10.21.354.159 I slot release: id 2 | task 11537 | stop processing: n_tokens = 2081, truncated = 0 10.21.397.325 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.513 10.21.397.366 I slot launch_slot_: id 2 | task 12474 | processing task, is_child = 0 10.22.047.101 I slot print_timing: id 0 | task 12016 | n_gen = 456, tg = 23.45 t/s, tg_3s = 20.06 t/s 10.22.729.367 I slot print_timing: id 3 | task 12181 | n_gen = 308, tg = 23.55 t/s, tg_3s = 19.33 t/s 10.22.932.702 I slot print_timing: id 1 | task 11836 | n_gen = 656, tg = 23.26 t/s, tg_3s = 19.32 t/s 10.23.498.379 I slot print_timing: id 1 | task 11836 | prompt eval time = 735.25 ms / 470 tokens ( 1.56 ms per token, 639.23 tokens per second) 10.23.498.383 I slot print_timing: id 1 | task 11836 | eval time = 28727.42 ms / 670 tokens ( 42.94 ms per token, 23.29 tokens per second) 10.23.498.389 I slot print_timing: id 1 | task 11836 | total time = 29462.67 ms / 1140 tokens 10.23.498.390 I slot print_timing: id 1 | task 11836 | graphs reused = 11793 10.23.498.392 I slot print_timing: id 1 | task 11836 | graph reallocs = 0 / 0 (same size) / (changed size) 10.23.498.518 I slot release: id 1 | task 11836 | stop processing: n_tokens = 1807, truncated = 0 10.23.542.259 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.591 10.23.542.298 I slot launch_slot_: id 1 | task 12512 | processing task, is_child = 0 10.25.051.992 I slot print_timing: id 0 | task 12016 | n_gen = 513, tg = 22.84 t/s, tg_3s = 18.97 t/s 10.25.741.538 I slot print_timing: id 3 | task 12181 | n_gen = 366, tg = 22.74 t/s, tg_3s = 19.26 t/s 10.26.793.981 I slot print_timing: id 2 | task 12474 | n_gen = 100, tg = 21.20 t/s, tg_3s = 21.41 t/s 10.28.086.955 I slot print_timing: id 0 | task 12016 | n_gen = 588, tg = 23.07 t/s, tg_3s = 24.71 t/s 10.28.288.880 I slot print_timing: id 1 | task 12512 | n_gen = 100, tg = 24.71 t/s, tg_3s = 24.96 t/s 10.28.772.773 I slot print_timing: id 3 | task 12181 | n_gen = 441, tg = 23.06 t/s, tg_3s = 24.74 t/s 10.29.822.680 I slot print_timing: id 2 | task 12474 | n_gen = 175, tg = 22.60 t/s, tg_3s = 24.76 t/s 10.31.116.116 I slot print_timing: id 0 | task 12016 | n_gen = 663, tg = 23.25 t/s, tg_3s = 24.76 t/s 10.31.318.713 I slot print_timing: id 1 | task 12512 | n_gen = 175, tg = 24.73 t/s, tg_3s = 24.75 t/s 10.31.804.654 I slot print_timing: id 3 | task 12181 | n_gen = 516, tg = 23.29 t/s, tg_3s = 24.74 t/s 10.32.855.072 I slot print_timing: id 2 | task 12474 | n_gen = 250, tg = 23.20 t/s, tg_3s = 24.73 t/s 10.34.145.885 I slot print_timing: id 0 | task 12016 | n_gen = 738, tg = 23.39 t/s, tg_3s = 24.75 t/s 10.34.348.549 I slot print_timing: id 1 | task 12512 | n_gen = 250, tg = 24.74 t/s, tg_3s = 24.75 t/s 10.34.836.063 I slot print_timing: id 3 | task 12181 | n_gen = 591, tg = 23.46 t/s, tg_3s = 24.74 t/s 10.35.887.056 I slot print_timing: id 2 | task 12474 | n_gen = 325, tg = 23.54 t/s, tg_3s = 24.74 t/s 10.37.182.742 I slot print_timing: id 0 | task 12016 | n_gen = 813, tg = 23.51 t/s, tg_3s = 24.70 t/s 10.37.385.739 I slot print_timing: id 1 | task 12512 | n_gen = 325, tg = 24.73 t/s, tg_3s = 24.69 t/s 10.37.874.800 I slot print_timing: id 3 | task 12181 | n_gen = 666, tg = 23.60 t/s, tg_3s = 24.68 t/s 10.38.888.838 I slot print_timing: id 2 | task 12474 | n_gen = 399, tg = 23.74 t/s, tg_3s = 24.65 t/s 10.40.190.427 I slot print_timing: id 0 | task 12016 | n_gen = 887, tg = 23.59 t/s, tg_3s = 24.60 t/s 10.40.394.024 I slot print_timing: id 1 | task 12512 | n_gen = 399, tg = 24.70 t/s, tg_3s = 24.60 t/s 10.40.882.552 I slot print_timing: id 3 | task 12181 | n_gen = 740, tg = 23.69 t/s, tg_3s = 24.60 t/s 10.41.895.361 I slot print_timing: id 2 | task 12474 | n_gen = 473, tg = 23.87 t/s, tg_3s = 24.61 t/s 10.42.340.769 I slot print_timing: id 2 | task 12474 | prompt eval time = 726.55 ms / 462 tokens ( 1.57 ms per token, 635.88 tokens per second) 10.42.340.777 I slot print_timing: id 2 | task 12474 | eval time = 20216.85 ms / 484 tokens ( 41.86 ms per token, 23.89 tokens per second) 10.42.340.777 I slot print_timing: id 2 | task 12474 | total time = 20943.39 ms / 946 tokens 10.42.340.778 I slot print_timing: id 2 | task 12474 | graphs reused = 12236 10.42.340.779 I slot print_timing: id 2 | task 12474 | graph reallocs = 0 / 0 (same size) / (changed size) 10.42.340.890 I slot release: id 2 | task 12474 | stop processing: n_tokens = 1641, truncated = 0 10.42.383.855 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.651 10.42.383.900 I slot launch_slot_: id 2 | task 12962 | processing task, is_child = 0 10.43.225.000 I slot print_timing: id 0 | task 12016 | n_gen = 946, tg = 23.28 t/s, tg_3s = 19.44 t/s 10.43.396.997 I slot print_timing: id 1 | task 12512 | n_gen = 457, tg = 23.86 t/s, tg_3s = 19.31 t/s 10.43.885.752 I slot print_timing: id 3 | task 12181 | n_gen = 798, tg = 23.31 t/s, tg_3s = 19.31 t/s 10.46.200.977 I slot print_timing: id 0 | task 12016 | prompt eval time = 736.19 ms / 494 tokens ( 1.49 ms per token, 671.02 tokens per second) 10.46.200.986 I slot print_timing: id 0 | task 12016 | eval time = 43560.99 ms / 1019 tokens ( 42.79 ms per token, 23.37 tokens per second) 10.46.200.987 I slot print_timing: id 0 | task 12016 | total time = 44297.18 ms / 1513 tokens 10.46.200.988 I slot print_timing: id 0 | task 12016 | graphs reused = 12311 10.46.200.988 I slot print_timing: id 0 | task 12016 | graph reallocs = 0 / 0 (same size) / (changed size) 10.46.201.084 I slot release: id 0 | task 12016 | stop processing: n_tokens = 2185, truncated = 0 10.46.238.281 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.489 10.46.244.091 I slot launch_slot_: id 0 | task 13042 | processing task, is_child = 0 10.46.919.265 I slot print_timing: id 1 | task 12512 | n_gen = 528, tg = 23.28 t/s, tg_3s = 20.16 t/s 10.46.919.848 I slot print_timing: id 3 | task 12181 | n_gen = 857, tg = 22.99 t/s, tg_3s = 19.45 t/s 10.47.810.324 I slot print_timing: id 2 | task 12962 | n_gen = 100, tg = 21.04 t/s, tg_3s = 21.25 t/s 10.48.824.253 I slot print_timing: id 1 | task 12512 | prompt eval time = 740.49 ms / 476 tokens ( 1.56 ms per token, 642.82 tokens per second) 10.48.824.258 I slot print_timing: id 1 | task 12512 | eval time = 24541.46 ms / 574 tokens ( 42.83 ms per token, 23.35 tokens per second) 10.48.824.259 I slot print_timing: id 1 | task 12512 | total time = 25281.95 ms / 1050 tokens 10.48.824.260 I slot print_timing: id 1 | task 12512 | graphs reused = 12356 10.48.824.260 I slot print_timing: id 1 | task 12512 | graph reallocs = 0 / 0 (same size) / (changed size) 10.48.824.347 I slot release: id 1 | task 12512 | stop processing: n_tokens = 1717, truncated = 0 10.48.866.689 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.622 10.48.866.725 I slot launch_slot_: id 1 | task 13091 | processing task, is_child = 0 10.49.929.536 I slot print_timing: id 3 | task 12181 | n_gen = 914, tg = 22.69 t/s, tg_3s = 18.94 t/s 10.50.827.188 I slot print_timing: id 2 | task 12962 | n_gen = 158, tg = 20.33 t/s, tg_3s = 19.23 t/s 10.51.676.626 I slot print_timing: id 0 | task 13042 | n_gen = 100, tg = 21.11 t/s, tg_3s = 21.33 t/s 10.52.933.769 I slot print_timing: id 3 | task 12181 | n_gen = 988, tg = 22.82 t/s, tg_3s = 24.63 t/s 10.53.624.093 I slot print_timing: id 1 | task 13091 | n_gen = 100, tg = 24.66 t/s, tg_3s = 24.91 t/s 10.53.827.629 I slot print_timing: id 2 | task 12962 | n_gen = 232, tg = 21.54 t/s, tg_3s = 24.66 t/s 10.54.397.401 I slot print_timing: id 3 | task 12181 | prompt eval time = 531.21 ms / 285 tokens ( 1.86 ms per token, 536.52 tokens per second) 10.54.397.408 I slot print_timing: id 3 | task 12181 | eval time = 44705.99 ms / 1024 tokens ( 43.70 ms per token, 22.88 tokens per second) 10.54.397.409 I slot print_timing: id 3 | task 12181 | total time = 45237.19 ms / 1309 tokens 10.54.397.409 I slot print_timing: id 3 | task 12181 | graphs reused = 12473 10.54.397.410 I slot print_timing: id 3 | task 12181 | graph reallocs = 0 / 0 (same size) / (changed size) 10.54.397.515 I slot release: id 3 | task 12181 | stop processing: n_tokens = 2232, truncated = 0 10.54.432.930 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.478 10.54.438.805 I slot launch_slot_: id 3 | task 13213 | processing task, is_child = 0 10.54.857.222 I slot print_timing: id 0 | task 13042 | n_gen = 169, tg = 21.35 t/s, tg_3s = 21.69 t/s 10.56.655.515 I slot print_timing: id 1 | task 13091 | n_gen = 165, tg = 23.28 t/s, tg_3s = 21.44 t/s 10.56.857.975 I slot print_timing: id 2 | task 12962 | n_gen = 297, tg = 21.52 t/s, tg_3s = 21.45 t/s 10.57.866.280 I slot print_timing: id 0 | task 13042 | n_gen = 243, tg = 22.25 t/s, tg_3s = 24.59 t/s 10.58.914.849 I slot print_timing: id 3 | task 13213 | n_gen = 100, tg = 24.83 t/s, tg_3s = 25.08 t/s 10.59.677.312 I slot print_timing: id 1 | task 13091 | n_gen = 240, tg = 23.74 t/s, tg_3s = 24.82 t/s 10.59.878.983 I slot print_timing: id 2 | task 12962 | n_gen = 372, tg = 22.12 t/s, tg_3s = 24.83 t/s 11.00.888.440 I slot print_timing: id 0 | task 13042 | n_gen = 318, tg = 22.80 t/s, tg_3s = 24.82 t/s 11.01.939.364 I slot print_timing: id 3 | task 13213 | n_gen = 175, tg = 24.82 t/s, tg_3s = 24.80 t/s 11.02.703.238 I slot print_timing: id 1 | task 13091 | n_gen = 315, tg = 23.98 t/s, tg_3s = 24.79 t/s 11.02.905.297 I slot print_timing: id 2 | task 12962 | n_gen = 447, tg = 22.53 t/s, tg_3s = 24.78 t/s 11.03.912.053 I slot print_timing: id 0 | task 13042 | n_gen = 393, tg = 23.16 t/s, tg_3s = 24.80 t/s 11.04.717.841 I slot print_timing: id 2 | task 12962 | prompt eval time = 721.35 ms / 454 tokens ( 1.59 ms per token, 629.37 tokens per second) 11.04.717.846 I slot print_timing: id 2 | task 12962 | eval time = 21612.57 ms / 492 tokens ( 44.02 ms per token, 22.72 tokens per second) 11.04.717.852 I slot print_timing: id 2 | task 12962 | total time = 22333.92 ms / 946 tokens 11.04.717.861 I slot print_timing: id 2 | task 12962 | graphs reused = 12714 11.04.717.861 I slot print_timing: id 2 | task 12962 | graph reallocs = 0 / 0 (same size) / (changed size) 11.04.717.976 I slot release: id 2 | task 12962 | stop processing: n_tokens = 1641, truncated = 0 11.04.760.772 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.651 11.04.760.807 I slot launch_slot_: id 2 | task 13460 | processing task, is_child = 0 11.05.413.757 I slot print_timing: id 3 | task 13213 | n_gen = 246, tg = 23.36 t/s, tg_3s = 20.44 t/s 11.05.730.449 I slot print_timing: id 1 | task 13091 | n_gen = 374, tg = 23.14 t/s, tg_3s = 19.49 t/s 11.05.857.652 I slot print_timing: id 1 | task 13091 | prompt eval time = 743.08 ms / 482 tokens ( 1.54 ms per token, 648.65 tokens per second) 11.05.857.659 I slot print_timing: id 1 | task 13091 | eval time = 16247.83 ms / 377 tokens ( 43.21 ms per token, 23.14 tokens per second) 11.05.857.660 I slot print_timing: id 1 | task 13091 | total time = 16990.92 ms / 859 tokens 11.05.857.661 I slot print_timing: id 1 | task 13091 | graphs reused = 12722 11.05.857.662 I slot print_timing: id 1 | task 13091 | graph reallocs = 0 / 0 (same size) / (changed size) 11.05.857.780 I slot release: id 1 | task 13091 | stop processing: n_tokens = 1526, truncated = 0 11.05.901.251 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.700 11.05.901.292 I slot launch_slot_: id 1 | task 13473 | processing task, is_child = 0 11.06.939.605 I slot print_timing: id 0 | task 13042 | n_gen = 435, tg = 21.75 t/s, tg_3s = 13.87 t/s 11.08.440.563 I slot print_timing: id 3 | task 13213 | n_gen = 303, tg = 22.35 t/s, tg_3s = 18.83 t/s 11.09.967.706 I slot print_timing: id 0 | task 13042 | n_gen = 510, tg = 22.15 t/s, tg_3s = 24.77 t/s 11.10.170.372 I slot print_timing: id 2 | task 13460 | n_gen = 100, tg = 21.15 t/s, tg_3s = 21.37 t/s 11.10.653.667 I slot print_timing: id 1 | task 13473 | n_gen = 100, tg = 24.80 t/s, tg_3s = 25.05 t/s 11.11.459.413 I slot print_timing: id 3 | task 13213 | n_gen = 378, tg = 22.80 t/s, tg_3s = 24.84 t/s 11.12.990.552 I slot print_timing: id 0 | task 13042 | n_gen = 585, tg = 22.46 t/s, tg_3s = 24.81 t/s 11.13.193.787 I slot print_timing: id 2 | task 13460 | n_gen = 175, tg = 22.59 t/s, tg_3s = 24.81 t/s 11.13.677.104 I slot print_timing: id 1 | task 13473 | n_gen = 175, tg = 24.80 t/s, tg_3s = 24.81 t/s 11.14.488.929 I slot print_timing: id 3 | task 13213 | prompt eval time = 488.98 ms / 236 tokens ( 2.07 ms per token, 482.64 tokens per second) 11.14.488.936 I slot print_timing: id 3 | task 13213 | eval time = 19561.13 ms / 453 tokens ( 43.28 ms per token, 23.11 tokens per second) 11.14.488.937 I slot print_timing: id 3 | task 13213 | total time = 20050.11 ms / 689 tokens 11.14.488.938 I slot print_timing: id 3 | task 13213 | graphs reused = 12914 11.14.488.938 I slot print_timing: id 3 | task 13213 | graph reallocs = 0 / 0 (same size) / (changed size) 11.14.489.035 I slot release: id 3 | task 13213 | stop processing: n_tokens = 1612, truncated = 0 11.14.524.598 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.663 11.14.524.634 I slot launch_slot_: id 3 | task 13671 | processing task, is_child = 0 11.15.998.630 I slot print_timing: id 0 | task 13042 | n_gen = 650, tg = 22.37 t/s, tg_3s = 21.61 t/s 11.16.202.456 I slot print_timing: id 2 | task 13460 | n_gen = 240, tg = 22.31 t/s, tg_3s = 21.60 t/s 11.16.688.013 I slot print_timing: id 1 | task 13473 | n_gen = 240, tg = 23.84 t/s, tg_3s = 21.59 t/s 11.18.997.277 I slot print_timing: id 3 | task 13671 | n_gen = 100, tg = 24.71 t/s, tg_3s = 24.96 t/s 11.19.036.277 I slot print_timing: id 0 | task 13042 | n_gen = 725, tg = 22.59 t/s, tg_3s = 24.69 t/s 11.19.238.939 I slot print_timing: id 2 | task 13460 | n_gen = 315, tg = 22.84 t/s, tg_3s = 24.70 t/s 11.19.721.806 I slot print_timing: id 1 | task 13473 | n_gen = 315, tg = 24.04 t/s, tg_3s = 24.72 t/s 11.22.019.674 I slot print_timing: id 3 | task 13671 | n_gen = 175, tg = 24.76 t/s, tg_3s = 24.81 t/s 11.22.058.261 I slot print_timing: id 0 | task 13042 | n_gen = 800, tg = 22.78 t/s, tg_3s = 24.82 t/s 11.22.260.662 I slot print_timing: id 2 | task 13460 | n_gen = 390, tg = 23.20 t/s, tg_3s = 24.82 t/s 11.22.742.953 I slot print_timing: id 1 | task 13473 | n_gen = 390, tg = 24.19 t/s, tg_3s = 24.83 t/s 11.24.194.479 I slot print_timing: id 0 | task 13042 | prompt eval time = 743.60 ms / 506 tokens ( 1.47 ms per token, 680.48 tokens per second) 11.24.194.484 I slot print_timing: id 0 | task 13042 | eval time = 37206.78 ms / 853 tokens ( 43.67 ms per token, 22.90 tokens per second) 11.24.194.485 I slot print_timing: id 0 | task 13042 | total time = 37950.38 ms / 1359 tokens 11.24.194.486 I slot print_timing: id 0 | task 13042 | graphs reused = 13141 11.24.194.486 I slot print_timing: id 0 | task 13042 | graph reallocs = 0 / 0 (same size) / (changed size) 11.24.194.594 I slot release: id 0 | task 13042 | stop processing: n_tokens = 2031, truncated = 0 11.24.231.608 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.526 11.24.231.654 I slot launch_slot_: id 0 | task 13903 | processing task, is_child = 0 11.25.045.749 I slot print_timing: id 3 | task 13671 | n_gen = 234, tg = 23.17 t/s, tg_3s = 19.50 t/s 11.25.289.597 I slot print_timing: id 2 | task 13460 | n_gen = 449, tg = 22.63 t/s, tg_3s = 19.48 t/s 11.25.773.451 I slot print_timing: id 1 | task 13473 | n_gen = 449, tg = 23.44 t/s, tg_3s = 19.47 t/s 11.28.030.077 I slot print_timing: id 3 | task 13671 | prompt eval time = 466.44 ms / 221 tokens ( 2.11 ms per token, 473.80 tokens per second) 11.28.030.085 I slot print_timing: id 3 | task 13671 | eval time = 13039.00 ms / 308 tokens ( 42.47 ms per token, 23.54 tokens per second) 11.28.030.087 I slot print_timing: id 3 | task 13671 | total time = 13505.43 ms / 529 tokens 11.28.030.088 I slot print_timing: id 3 | task 13671 | graphs reused = 13217 11.28.030.089 I slot print_timing: id 3 | task 13671 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.030.187 I slot release: id 3 | task 13671 | stop processing: n_tokens = 1452, truncated = 0 11.28.065.528 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.736 11.28.065.557 I slot launch_slot_: id 3 | task 13983 | processing task, is_child = 0 11.28.468.311 I slot print_timing: id 2 | task 13460 | n_gen = 519, tg = 22.54 t/s, tg_3s = 22.02 t/s 11.28.538.090 I slot print_timing: id 2 | task 13460 | prompt eval time = 729.26 ms / 466 tokens ( 1.56 ms per token, 639.00 tokens per second) 11.28.538.095 I slot print_timing: id 2 | task 13460 | eval time = 23048.02 ms / 520 tokens ( 44.41 ms per token, 22.52 tokens per second) 11.28.538.096 I slot print_timing: id 2 | task 13460 | total time = 23777.28 ms / 986 tokens 11.28.538.096 I slot print_timing: id 2 | task 13460 | graphs reused = 13217 11.28.538.097 I slot print_timing: id 2 | task 13460 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.538.155 I slot release: id 2 | task 13460 | stop processing: n_tokens = 1681, truncated = 0 11.28.578.563 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.635 11.28.578.587 I slot launch_slot_: id 2 | task 13987 | processing task, is_child = 0 11.29.202.294 I slot print_timing: id 1 | task 13473 | n_gen = 510, tg = 22.58 t/s, tg_3s = 17.79 t/s 11.29.963.565 I slot print_timing: id 0 | task 13903 | n_gen = 100, tg = 19.80 t/s, tg_3s = 20.00 t/s 11.32.223.023 I slot print_timing: id 1 | task 13473 | n_gen = 584, tg = 22.81 t/s, tg_3s = 24.50 t/s 11.32.986.756 I slot print_timing: id 0 | task 13903 | n_gen = 175, tg = 21.69 t/s, tg_3s = 24.81 t/s 11.33.149.707 I slot print_timing: id 3 | task 13983 | n_gen = 100, tg = 21.47 t/s, tg_3s = 21.69 t/s 11.33.270.042 I slot print_timing: id 2 | task 13987 | n_gen = 100, tg = 24.80 t/s, tg_3s = 25.06 t/s 11.34.198.031 I slot print_timing: id 1 | task 13473 | prompt eval time = 760.66 ms / 494 tokens ( 1.54 ms per token, 649.43 tokens per second) 11.34.198.039 I slot print_timing: id 1 | task 13473 | eval time = 27536.07 ms / 633 tokens ( 43.57 ms per token, 22.95 tokens per second) 11.34.198.040 I slot print_timing: id 1 | task 13473 | total time = 28296.73 ms / 1127 tokens 11.34.198.040 I slot print_timing: id 1 | task 13473 | graphs reused = 13337 11.34.198.041 I slot print_timing: id 1 | task 13473 | graph reallocs = 0 / 0 (same size) / (changed size) 11.34.198.177 I slot release: id 1 | task 13473 | stop processing: n_tokens = 1794, truncated = 0 11.34.241.421 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.595 11.34.241.457 I slot launch_slot_: id 1 | task 14113 | processing task, is_child = 0 11.35.989.317 I slot print_timing: id 0 | task 13903 | n_gen = 233, tg = 21.04 t/s, tg_3s = 19.32 t/s 11.36.152.939 I slot print_timing: id 3 | task 13983 | n_gen = 158, tg = 20.62 t/s, tg_3s = 19.31 t/s 11.36.273.686 I slot print_timing: id 2 | task 13987 | n_gen = 158, tg = 22.45 t/s, tg_3s = 19.31 t/s 11.38.969.665 I slot print_timing: id 1 | task 14113 | n_gen = 100, tg = 24.79 t/s, tg_3s = 25.04 t/s 11.39.009.537 I slot print_timing: id 0 | task 13903 | n_gen = 308, tg = 21.86 t/s, tg_3s = 24.83 t/s 11.39.172.714 I slot print_timing: id 3 | task 13983 | n_gen = 233, tg = 21.82 t/s, tg_3s = 24.84 t/s 11.39.293.522 I slot print_timing: id 2 | task 13987 | n_gen = 233, tg = 23.17 t/s, tg_3s = 24.84 t/s 11.39.939.828 I slot print_timing: id 2 | task 13987 | prompt eval time = 700.30 ms / 446 tokens ( 1.57 ms per token, 636.87 tokens per second) 11.39.939.835 I slot print_timing: id 2 | task 13987 | eval time = 10660.94 ms / 249 tokens ( 42.99 ms per token, 23.26 tokens per second) 11.39.939.836 I slot print_timing: id 2 | task 13987 | total time = 11361.23 ms / 695 tokens 11.39.939.837 I slot print_timing: id 2 | task 13987 | graphs reused = 13459 11.39.939.838 I slot print_timing: id 2 | task 13987 | graph reallocs = 0 / 0 (same size) / (changed size) 11.39.939.940 I slot release: id 2 | task 13987 | stop processing: n_tokens = 1390, truncated = 0 11.39.983.024 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.768 11.39.983.070 I slot launch_slot_: id 2 | task 14240 | processing task, is_child = 0 11.42.000.081 I slot print_timing: id 1 | task 14113 | n_gen = 158, tg = 22.35 t/s, tg_3s = 19.14 t/s 11.42.039.995 I slot print_timing: id 0 | task 13903 | n_gen = 366, tg = 21.38 t/s, tg_3s = 19.14 t/s 11.42.202.869 I slot print_timing: id 3 | task 13983 | n_gen = 291, tg = 21.22 t/s, tg_3s = 19.14 t/s 11.44.746.668 I slot print_timing: id 2 | task 14240 | n_gen = 100, tg = 24.79 t/s, tg_3s = 25.04 t/s 11.45.028.205 I slot print_timing: id 1 | task 14113 | n_gen = 233, tg = 23.08 t/s, tg_3s = 24.77 t/s 11.45.068.179 I slot print_timing: id 0 | task 13903 | n_gen = 441, tg = 21.89 t/s, tg_3s = 24.77 t/s 11.45.230.825 I slot print_timing: id 3 | task 13983 | n_gen = 366, tg = 21.87 t/s, tg_3s = 24.77 t/s 11.45.553.925 I slot print_timing: id 3 | task 13983 | prompt eval time = 472.88 ms / 228 tokens ( 2.07 ms per token, 482.15 tokens per second) 11.45.553.933 I slot print_timing: id 3 | task 13983 | eval time = 17015.47 ms / 374 tokens ( 45.62 ms per token, 21.92 tokens per second) 11.45.553.934 I slot print_timing: id 3 | task 13983 | total time = 17488.36 ms / 602 tokens 11.45.553.934 I slot print_timing: id 3 | task 13983 | graphs reused = 13576 11.45.553.935 I slot print_timing: id 3 | task 13983 | graph reallocs = 0 / 0 (same size) / (changed size) 11.45.554.045 I slot release: id 3 | task 13983 | stop processing: n_tokens = 1525, truncated = 0 11.45.589.415 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.700 11.45.589.444 I slot launch_slot_: id 3 | task 14363 | processing task, is_child = 0 11.47.779.242 I slot print_timing: id 2 | task 14240 | n_gen = 165, tg = 23.34 t/s, tg_3s = 21.43 t/s 11.48.060.839 I slot print_timing: id 1 | task 14113 | n_gen = 298, tg = 22.70 t/s, tg_3s = 21.43 t/s 11.48.100.434 I slot print_timing: id 0 | task 13903 | n_gen = 506, tg = 21.83 t/s, tg_3s = 21.44 t/s 11.50.083.728 I slot print_timing: id 3 | task 14363 | n_gen = 100, tg = 24.71 t/s, tg_3s = 24.96 t/s 11.50.809.032 I slot print_timing: id 2 | task 14240 | n_gen = 240, tg = 23.77 t/s, tg_3s = 24.75 t/s 11.51.090.756 I slot print_timing: id 1 | task 14113 | n_gen = 373, tg = 23.08 t/s, tg_3s = 24.75 t/s 11.51.130.387 I slot print_timing: id 0 | task 13903 | n_gen = 581, tg = 22.17 t/s, tg_3s = 24.75 t/s 11.51.130.898 I slot print_timing: id 1 | task 14113 | prompt eval time = 734.92 ms / 471 tokens ( 1.56 ms per token, 640.89 tokens per second) 11.51.130.901 I slot print_timing: id 1 | task 14113 | eval time = 16154.52 ms / 374 tokens ( 43.31 ms per token, 23.09 tokens per second) 11.51.130.903 I slot print_timing: id 1 | task 14113 | total time = 16889.44 ms / 845 tokens 11.51.130.904 I slot print_timing: id 1 | task 14113 | graphs reused = 13700 11.51.130.904 I slot print_timing: id 1 | task 14113 | graph reallocs = 0 / 0 (same size) / (changed size) 11.51.131.006 I slot release: id 1 | task 14113 | stop processing: n_tokens = 1512, truncated = 0 11.51.173.820 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.706 11.51.173.855 I slot launch_slot_: id 1 | task 14492 | processing task, is_child = 0 11.53.103.785 I slot print_timing: id 3 | task 14363 | n_gen = 158, tg = 22.34 t/s, tg_3s = 19.20 t/s 11.53.829.701 I slot print_timing: id 2 | task 14240 | n_gen = 298, tg = 22.71 t/s, tg_3s = 19.20 t/s 11.54.154.860 I slot print_timing: id 0 | task 13903 | n_gen = 639, tg = 21.86 t/s, tg_3s = 19.18 t/s 11.54.438.157 I slot print_timing: id 0 | task 13903 | prompt eval time = 733.07 ms / 489 tokens ( 1.50 ms per token, 667.06 tokens per second) 11.54.438.164 I slot print_timing: id 0 | task 13903 | eval time = 29473.42 ms / 646 tokens ( 45.70 ms per token, 21.88 tokens per second) 11.54.438.165 I slot print_timing: id 0 | task 13903 | total time = 30206.49 ms / 1135 tokens 11.54.438.165 I slot print_timing: id 0 | task 13903 | graphs reused = 13760 11.54.438.166 I slot print_timing: id 0 | task 13903 | graph reallocs = 0 / 0 (same size) / (changed size) 11.54.438.269 I slot release: id 0 | task 13903 | stop processing: n_tokens = 1807, truncated = 0 11.54.475.196 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.591 11.54.475.240 I slot launch_slot_: id 0 | task 14558 | processing task, is_child = 0 11.56.124.016 I slot print_timing: id 3 | task 14363 | n_gen = 217, tg = 21.50 t/s, tg_3s = 19.53 t/s 11.56.568.134 I slot print_timing: id 1 | task 14492 | n_gen = 100, tg = 21.37 t/s, tg_3s = 21.58 t/s 11.56.851.885 I slot print_timing: id 2 | task 14240 | n_gen = 357, tg = 22.11 t/s, tg_3s = 19.52 t/s 11.59.156.912 I slot print_timing: id 3 | task 14363 | n_gen = 292, tg = 22.25 t/s, tg_3s = 24.73 t/s 11.59.195.645 I slot print_timing: id 0 | task 14558 | n_gen = 100, tg = 24.69 t/s, tg_3s = 24.94 t/s 11.59.599.744 I slot print_timing: id 1 | task 14492 | n_gen = 175, tg = 22.70 t/s, tg_3s = 24.74 t/s 11.59.883.066 I slot print_timing: id 2 | task 14240 | n_gen = 432, tg = 22.53 t/s, tg_3s = 24.74 t/s 12.02.183.111 I slot print_timing: id 3 | task 14363 | n_gen = 367, tg = 22.72 t/s, tg_3s = 24.78 t/s 12.02.221.900 I slot print_timing: id 0 | task 14558 | n_gen = 175, tg = 24.73 t/s, tg_3s = 24.78 t/s 12.02.626.310 I slot print_timing: id 1 | task 14492 | n_gen = 250, tg = 23.29 t/s, tg_3s = 24.78 t/s 12.02.910.732 I slot print_timing: id 2 | task 14240 | n_gen = 507, tg = 22.84 t/s, tg_3s = 24.77 t/s 12.05.211.727 I slot print_timing: id 3 | task 14363 | n_gen = 442, tg = 23.05 t/s, tg_3s = 24.76 t/s 12.05.250.279 I slot print_timing: id 0 | task 14558 | n_gen = 250, tg = 24.74 t/s, tg_3s = 24.77 t/s 12.05.654.833 I slot print_timing: id 1 | task 14492 | n_gen = 325, tg = 23.61 t/s, tg_3s = 24.76 t/s 12.05.938.745 I slot print_timing: id 2 | task 14240 | n_gen = 582, tg = 23.07 t/s, tg_3s = 24.77 t/s 12.06.101.081 I slot print_timing: id 3 | task 14363 | prompt eval time = 487.74 ms / 234 tokens ( 2.08 ms per token, 479.76 tokens per second) 12.06.101.088 I slot print_timing: id 3 | task 14363 | eval time = 20023.89 ms / 464 tokens ( 43.25 ms per token, 23.12 tokens per second) 12.06.101.089 I slot print_timing: id 3 | task 14363 | total time = 20511.63 ms / 698 tokens 12.06.101.090 I slot print_timing: id 3 | task 14363 | graphs reused = 14029 12.06.101.090 I slot print_timing: id 3 | task 14363 | graph reallocs = 0 / 0 (same size) / (changed size) 12.06.101.203 I slot release: id 3 | task 14363 | stop processing: n_tokens = 1621, truncated = 0 12.06.136.270 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.659 12.06.136.302 I slot launch_slot_: id 3 | task 14832 | processing task, is_child = 0 12.08.288.812 I slot print_timing: id 0 | task 14558 | n_gen = 315, tg = 23.96 t/s, tg_3s = 21.39 t/s 12.08.694.382 I slot print_timing: id 1 | task 14492 | n_gen = 390, tg = 23.21 t/s, tg_3s = 21.38 t/s 12.08.978.454 I slot print_timing: id 2 | task 14240 | n_gen = 647, tg = 22.89 t/s, tg_3s = 21.38 t/s 12.10.638.978 I slot print_timing: id 3 | task 14832 | n_gen = 100, tg = 24.66 t/s, tg_3s = 24.90 t/s 12.11.325.830 I slot print_timing: id 0 | task 14558 | n_gen = 390, tg = 24.10 t/s, tg_3s = 24.70 t/s 12.11.731.236 I slot print_timing: id 1 | task 14492 | n_gen = 465, tg = 23.44 t/s, tg_3s = 24.70 t/s 12.11.932.809 I slot print_timing: id 0 | task 14558 | prompt eval time = 710.10 ms / 474 tokens ( 1.50 ms per token, 667.51 tokens per second) 12.11.932.813 I slot print_timing: id 0 | task 14558 | eval time = 16747.46 ms / 405 tokens ( 41.45 ms per token, 24.12 tokens per second) 12.11.932.815 I slot print_timing: id 0 | task 14558 | total time = 17457.56 ms / 879 tokens 12.11.932.816 I slot print_timing: id 0 | task 14558 | graphs reused = 14159 12.11.932.816 I slot print_timing: id 0 | task 14558 | graph reallocs = 0 / 0 (same size) / (changed size) 12.11.932.919 I slot release: id 0 | task 14558 | stop processing: n_tokens = 1551, truncated = 0 12.11.969.865 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.689 12.11.969.901 I slot launch_slot_: id 0 | task 14967 | processing task, is_child = 0 12.12.600.430 I slot print_timing: id 2 | task 14240 | n_gen = 722, tg = 22.64 t/s, tg_3s = 20.71 t/s 12.12.868.333 I slot print_timing: id 1 | task 14492 | prompt eval time = 760.87 ms / 491 tokens ( 1.55 ms per token, 645.31 tokens per second) 12.12.868.336 I slot print_timing: id 1 | task 14492 | eval time = 20933.60 ms / 478 tokens ( 43.89 ms per token, 22.79 tokens per second) 12.12.868.336 I slot print_timing: id 1 | task 14492 | total time = 21694.47 ms / 969 tokens 12.12.868.337 I slot print_timing: id 1 | task 14492 | graphs reused = 14164 12.12.868.337 I slot print_timing: id 1 | task 14492 | graph reallocs = 0 / 0 (same size) / (changed size) 12.12.868.398 I slot release: id 1 | task 14492 | stop processing: n_tokens = 1636, truncated = 0 12.12.909.590 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.653 12.12.909.618 I slot launch_slot_: id 1 | task 14976 | processing task, is_child = 0 12.13.677.475 I slot print_timing: id 3 | task 14832 | n_gen = 143, tg = 20.13 t/s, tg_3s = 14.15 t/s 12.15.613.930 I slot print_timing: id 2 | task 14240 | n_gen = 779, tg = 22.32 t/s, tg_3s = 18.91 t/s 12.16.703.231 I slot print_timing: id 3 | task 14832 | n_gen = 218, tg = 21.53 t/s, tg_3s = 24.79 t/s 12.17.348.846 I slot print_timing: id 0 | task 14967 | n_gen = 100, tg = 21.15 t/s, tg_3s = 21.37 t/s 12.17.673.752 I slot print_timing: id 1 | task 14976 | n_gen = 100, tg = 24.77 t/s, tg_3s = 25.02 t/s 12.18.653.240 I slot print_timing: id 2 | task 14240 | n_gen = 854, tg = 22.51 t/s, tg_3s = 24.68 t/s 12.19.708.761 I slot print_timing: id 3 | task 14832 | n_gen = 292, tg = 22.24 t/s, tg_3s = 24.62 t/s 12.20.195.693 I slot print_timing: id 3 | task 14832 | prompt eval time = 487.27 ms / 236 tokens ( 2.06 ms per token, 484.34 tokens per second) 12.20.195.700 I slot print_timing: id 3 | task 14832 | eval time = 13572.11 ms / 304 tokens ( 44.79 ms per token, 22.33 tokens per second) 12.20.195.701 I slot print_timing: id 3 | task 14832 | total time = 14059.38 ms / 540 tokens 12.20.195.702 I slot print_timing: id 3 | task 14832 | graphs reused = 14323 12.20.195.703 I slot print_timing: id 3 | task 14832 | graph reallocs = 0 / 0 (same size) / (changed size) 12.20.195.815 I slot release: id 3 | task 14832 | stop processing: n_tokens = 1463, truncated = 0 12.20.231.720 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.730 12.20.231.761 I slot launch_slot_: id 3 | task 15141 | processing task, is_child = 0 12.20.620.078 I slot print_timing: id 0 | task 14967 | n_gen = 172, tg = 21.50 t/s, tg_3s = 22.01 t/s 12.20.689.794 I slot print_timing: id 1 | task 14976 | n_gen = 165, tg = 23.39 t/s, tg_3s = 21.55 t/s 12.21.658.300 I slot print_timing: id 2 | task 14240 | n_gen = 919, tg = 22.44 t/s, tg_3s = 21.63 t/s 12.23.647.011 I slot print_timing: id 0 | task 14967 | n_gen = 246, tg = 22.32 t/s, tg_3s = 24.45 t/s 12.23.728.600 I slot print_timing: id 1 | task 14976 | n_gen = 240, tg = 23.78 t/s, tg_3s = 24.68 t/s 12.24.662.764 I slot print_timing: id 2 | task 14240 | n_gen = 993, tg = 22.59 t/s, tg_3s = 24.63 t/s 12.24.703.973 I slot print_timing: id 3 | task 15141 | n_gen = 100, tg = 24.67 t/s, tg_3s = 24.92 t/s 12.25.922.353 I slot print_timing: id 2 | task 14240 | prompt eval time = 770.40 ms / 508 tokens ( 1.52 ms per token, 659.40 tokens per second) 12.25.922.357 I slot print_timing: id 2 | task 14240 | eval time = 45168.87 ms / 1024 tokens ( 44.15 ms per token, 22.65 tokens per second) 12.25.922.358 I slot print_timing: id 2 | task 14240 | total time = 45939.27 ms / 1532 tokens 12.25.922.359 I slot print_timing: id 2 | task 14240 | graphs reused = 14451 12.25.922.360 I slot print_timing: id 2 | task 14240 | graph reallocs = 0 / 0 (same size) / (changed size) 12.25.922.465 I slot release: id 2 | task 14240 | stop processing: n_tokens = 2227, truncated = 0 12.25.965.443 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.891 (> 0.100 thold), f_keep = 0.480 12.25.971.947 I slot launch_slot_: id 2 | task 15274 | processing task, is_child = 0 12.26.659.532 I slot print_timing: id 0 | task 14967 | n_gen = 304, tg = 21.66 t/s, tg_3s = 19.25 t/s 12.26.736.076 I slot print_timing: id 1 | task 14976 | n_gen = 297, tg = 22.67 t/s, tg_3s = 18.95 t/s 12.27.742.606 I slot print_timing: id 3 | task 15141 | n_gen = 158, tg = 22.26 t/s, tg_3s = 19.09 t/s 12.29.681.314 I slot print_timing: id 0 | task 14967 | n_gen = 378, tg = 22.16 t/s, tg_3s = 24.49 t/s 12.29.762.916 I slot print_timing: id 1 | task 14976 | n_gen = 372, tg = 23.06 t/s, tg_3s = 24.78 t/s 12.30.729.822 I slot print_timing: id 2 | task 15274 | n_gen = 100, tg = 24.79 t/s, tg_3s = 25.04 t/s 12.30.770.720 I slot print_timing: id 3 | task 15141 | n_gen = 233, tg = 23.01 t/s, tg_3s = 24.77 t/s 12.31.775.977 I slot print_timing: id 0 | task 14967 | prompt eval time = 698.51 ms / 456 tokens ( 1.53 ms per token, 652.82 tokens per second) 12.31.775.985 I slot print_timing: id 0 | task 14967 | eval time = 19107.56 ms / 430 tokens ( 44.54 ms per token, 22.45 tokens per second) 12.31.775.985 I slot print_timing: id 0 | task 14967 | total time = 19806.07 ms / 886 tokens 12.31.775.986 I slot print_timing: id 0 | task 14967 | graphs reused = 14574 12.31.775.987 I slot print_timing: id 0 | task 14967 | graph reallocs = 0 / 0 (same size) / (changed size) 12.31.776.088 I slot release: id 0 | task 14967 | stop processing: n_tokens = 1558, truncated = 0 12.31.812.901 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.685 12.31.812.936 I slot launch_slot_: id 0 | task 15403 | processing task, is_child = 0 12.32.781.984 I slot print_timing: id 1 | task 14976 | n_gen = 431, tg = 22.51 t/s, tg_3s = 19.54 t/s 12.33.751.679 I slot print_timing: id 2 | task 15274 | n_gen = 159, tg = 22.52 t/s, tg_3s = 19.52 t/s 12.33.792.492 I slot print_timing: id 3 | task 15141 | n_gen = 292, tg = 22.21 t/s, tg_3s = 19.52 t/s 12.35.810.548 I slot print_timing: id 1 | task 14976 | n_gen = 506, tg = 22.82 t/s, tg_3s = 24.76 t/s 12.36.536.289 I slot print_timing: id 0 | task 15403 | n_gen = 100, tg = 24.80 t/s, tg_3s = 25.05 t/s 12.36.779.459 I slot print_timing: id 2 | task 15274 | n_gen = 234, tg = 23.20 t/s, tg_3s = 24.77 t/s 12.36.820.458 I slot print_timing: id 3 | task 15141 | n_gen = 367, tg = 22.69 t/s, tg_3s = 24.77 t/s 12.38.837.714 I slot print_timing: id 1 | task 14976 | n_gen = 581, tg = 23.05 t/s, tg_3s = 24.78 t/s 12.39.562.228 I slot print_timing: id 0 | task 15403 | n_gen = 175, tg = 24.79 t/s, tg_3s = 24.79 t/s 12.39.805.120 I slot print_timing: id 2 | task 15274 | n_gen = 309, tg = 23.57 t/s, tg_3s = 24.79 t/s 12.39.845.972 I slot print_timing: id 3 | task 15141 | n_gen = 442, tg = 23.02 t/s, tg_3s = 24.79 t/s 12.41.867.652 I slot print_timing: id 1 | task 14976 | n_gen = 656, tg = 23.23 t/s, tg_3s = 24.75 t/s 12.42.594.642 I slot print_timing: id 0 | task 15403 | n_gen = 250, tg = 24.77 t/s, tg_3s = 24.73 t/s 12.42.837.767 I slot print_timing: id 2 | task 15274 | n_gen = 384, tg = 23.79 t/s, tg_3s = 24.73 t/s 12.42.879.087 I slot print_timing: id 3 | task 15141 | n_gen = 517, tg = 23.26 t/s, tg_3s = 24.73 t/s 12.43.524.640 I slot print_timing: id 2 | task 15274 | prompt eval time = 764.54 ms / 502 tokens ( 1.52 ms per token, 656.61 tokens per second) 12.43.524.655 I slot print_timing: id 2 | task 15274 | eval time = 16788.14 ms / 401 tokens ( 41.97 ms per token, 23.83 tokens per second) 12.43.524.657 I slot print_timing: id 2 | task 15274 | total time = 17552.68 ms / 903 tokens 12.43.524.661 I slot print_timing: id 2 | task 15274 | graphs reused = 14845 12.43.524.662 I slot print_timing: id 2 | task 15274 | graph reallocs = 0 / 0 (same size) / (changed size) 12.43.524.772 I slot release: id 2 | task 15274 | stop processing: n_tokens = 1598, truncated = 0 12.43.567.853 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.668 12.43.567.889 I slot launch_slot_: id 2 | task 15679 | processing task, is_child = 0 12.44.896.803 I slot print_timing: id 1 | task 14976 | n_gen = 715, tg = 22.87 t/s, tg_3s = 19.48 t/s 12.45.623.388 I slot print_timing: id 0 | task 15403 | n_gen = 309, tg = 23.55 t/s, tg_3s = 19.48 t/s 12.45.907.355 I slot print_timing: id 3 | task 15141 | prompt eval time = 458.56 ms / 207 tokens ( 2.22 ms per token, 451.41 tokens per second) 12.45.907.362 I slot print_timing: id 3 | task 15141 | eval time = 25217.02 ms / 576 tokens ( 43.86 ms per token, 22.80 tokens per second) 12.45.907.364 I slot print_timing: id 3 | task 15141 | total time = 25675.59 ms / 783 tokens 12.45.907.365 I slot print_timing: id 3 | task 15141 | graphs reused = 14884 12.45.907.365 I slot print_timing: id 3 | task 15141 | graph reallocs = 0 / 0 (same size) / (changed size) 12.45.907.463 I slot release: id 3 | task 15141 | stop processing: n_tokens = 1706, truncated = 0 12.45.942.809 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.626 12.45.942.842 I slot launch_slot_: id 3 | task 15723 | processing task, is_child = 0 12.47.901.040 I slot print_timing: id 1 | task 14976 | n_gen = 779, tg = 22.73 t/s, tg_3s = 21.30 t/s 12.48.625.331 I slot print_timing: id 0 | task 15403 | n_gen = 373, tg = 23.13 t/s, tg_3s = 21.32 t/s 12.48.706.924 I slot print_timing: id 2 | task 15679 | n_gen = 100, tg = 22.42 t/s, tg_3s = 22.65 t/s 12.50.440.354 I slot print_timing: id 3 | task 15723 | n_gen = 100, tg = 24.77 t/s, tg_3s = 25.02 t/s 12.50.924.389 I slot print_timing: id 1 | task 14976 | n_gen = 854, tg = 22.90 t/s, tg_3s = 24.81 t/s 12.51.650.361 I slot print_timing: id 0 | task 15403 | n_gen = 448, tg = 23.40 t/s, tg_3s = 24.79 t/s 12.51.732.078 I slot print_timing: id 2 | task 15679 | n_gen = 175, tg = 23.39 t/s, tg_3s = 24.79 t/s 12.53.475.967 I slot print_timing: id 3 | task 15723 | n_gen = 175, tg = 24.74 t/s, tg_3s = 24.71 t/s 12.53.960.768 I slot print_timing: id 1 | task 14976 | n_gen = 929, tg = 23.04 t/s, tg_3s = 24.70 t/s 12.54.687.719 I slot print_timing: id 0 | task 15403 | n_gen = 523, tg = 23.57 t/s, tg_3s = 24.69 t/s 12.54.769.896 I slot print_timing: id 2 | task 15679 | n_gen = 250, tg = 23.76 t/s, tg_3s = 24.69 t/s 12.54.930.545 I slot print_timing: id 0 | task 15403 | prompt eval time = 730.83 ms / 487 tokens ( 1.50 ms per token, 666.37 tokens per second) 12.54.930.551 I slot print_timing: id 0 | task 15403 | eval time = 22386.77 ms / 529 tokens ( 42.40 ms per token, 23.59 tokens per second) 12.54.930.552 I slot print_timing: id 0 | task 15403 | total time = 23117.60 ms / 1016 tokens 12.54.930.553 I slot print_timing: id 0 | task 15403 | graphs reused = 15092 12.54.930.554 I slot print_timing: id 0 | task 15403 | graph reallocs = 0 / 0 (same size) / (changed size) 12.54.930.685 I slot release: id 0 | task 15403 | stop processing: n_tokens = 1688, truncated = 0 12.54.967.557 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.633 12.54.967.595 I slot launch_slot_: id 0 | task 15937 | processing task, is_child = 0 12.56.477.517 I slot print_timing: id 3 | task 15723 | n_gen = 234, tg = 23.22 t/s, tg_3s = 19.66 t/s 12.56.961.334 I slot print_timing: id 1 | task 14976 | n_gen = 988, tg = 22.80 t/s, tg_3s = 19.66 t/s 12.57.772.327 I slot print_timing: id 2 | task 15679 | n_gen = 309, tg = 22.85 t/s, tg_3s = 19.65 t/s 12.58.421.241 I slot print_timing: id 1 | task 14976 | prompt eval time = 767.26 ms / 503 tokens ( 1.53 ms per token, 655.58 tokens per second) 12.58.421.246 I slot print_timing: id 1 | task 14976 | eval time = 44744.35 ms / 1024 tokens ( 43.74 ms per token, 22.86 tokens per second) 12.58.421.246 I slot print_timing: id 1 | task 14976 | total time = 45511.61 ms / 1527 tokens 12.58.421.249 I slot print_timing: id 1 | task 14976 | graphs reused = 15160 12.58.421.250 I slot print_timing: id 1 | task 14976 | graph reallocs = 0 / 0 (same size) / (changed size) 12.58.421.368 I slot release: id 1 | task 14976 | stop processing: n_tokens = 2194, truncated = 0 12.58.464.523 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.487 12.58.472.814 I slot launch_slot_: id 1 | task 16009 | processing task, is_child = 0 12.59.511.196 I slot print_timing: id 3 | task 15723 | n_gen = 292, tg = 22.27 t/s, tg_3s = 19.12 t/s 13.00.367.193 I slot print_timing: id 0 | task 15937 | n_gen = 100, tg = 21.08 t/s, tg_3s = 21.29 t/s 13.00.812.302 I slot print_timing: id 2 | task 15679 | n_gen = 367, tg = 22.15 t/s, tg_3s = 19.08 t/s 13.02.546.584 I slot print_timing: id 3 | task 15723 | n_gen = 367, tg = 22.73 t/s, tg_3s = 24.71 t/s 13.03.231.341 I slot print_timing: id 1 | task 16009 | n_gen = 100, tg = 24.76 t/s, tg_3s = 25.01 t/s 13.03.392.617 I slot print_timing: id 0 | task 15937 | n_gen = 175, tg = 22.53 t/s, tg_3s = 24.79 t/s 13.03.838.385 I slot print_timing: id 2 | task 15679 | n_gen = 442, tg = 22.56 t/s, tg_3s = 24.78 t/s 13.05.576.565 I slot print_timing: id 3 | task 15723 | n_gen = 442, tg = 23.05 t/s, tg_3s = 24.75 t/s 13.06.260.505 I slot print_timing: id 1 | task 16009 | n_gen = 175, tg = 24.76 t/s, tg_3s = 24.76 t/s 13.06.421.260 I slot print_timing: id 0 | task 15937 | n_gen = 250, tg = 23.16 t/s, tg_3s = 24.76 t/s 13.06.866.635 I slot print_timing: id 2 | task 15679 | n_gen = 517, tg = 22.86 t/s, tg_3s = 24.77 t/s 13.08.606.993 I slot print_timing: id 3 | task 15723 | n_gen = 517, tg = 23.28 t/s, tg_3s = 24.75 t/s 13.09.293.796 I slot print_timing: id 1 | task 16009 | n_gen = 250, tg = 24.75 t/s, tg_3s = 24.73 t/s 13.09.455.263 I slot print_timing: id 0 | task 15937 | n_gen = 325, tg = 23.50 t/s, tg_3s = 24.72 t/s 13.09.901.555 I slot print_timing: id 2 | task 15679 | n_gen = 592, tg = 23.08 t/s, tg_3s = 24.71 t/s 13.11.641.948 I slot print_timing: id 3 | task 15723 | n_gen = 592, tg = 23.45 t/s, tg_3s = 24.71 t/s 13.12.330.891 I slot print_timing: id 1 | task 16009 | n_gen = 325, tg = 24.74 t/s, tg_3s = 24.69 t/s 13.12.492.573 I slot print_timing: id 0 | task 15937 | n_gen = 400, tg = 23.72 t/s, tg_3s = 24.69 t/s 13.12.939.396 I slot print_timing: id 2 | task 15679 | n_gen = 667, tg = 23.25 t/s, tg_3s = 24.69 t/s 13.13.668.727 I slot print_timing: id 1 | task 16009 | prompt eval time = 759.92 ms / 492 tokens ( 1.54 ms per token, 647.44 tokens per second) 13.13.668.735 I slot print_timing: id 1 | task 16009 | eval time = 14435.98 ms / 358 tokens ( 40.44 ms per token, 24.73 tokens per second) 13.13.668.736 I slot print_timing: id 1 | task 16009 | total time = 15195.90 ms / 850 tokens 13.13.668.736 I slot print_timing: id 1 | task 16009 | graphs reused = 15514 13.13.668.737 I slot print_timing: id 1 | task 16009 | graph reallocs = 0 / 0 (same size) / (changed size) 13.13.668.839 I slot release: id 1 | task 16009 | stop processing: n_tokens = 1522, truncated = 0 13.13.712.224 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.702 13.13.712.262 I slot launch_slot_: id 1 | task 16370 | processing task, is_child = 0 13.14.642.068 I slot print_timing: id 3 | task 15723 | n_gen = 649, tg = 22.98 t/s, tg_3s = 19.00 t/s 13.15.528.416 I slot print_timing: id 0 | task 15937 | n_gen = 458, tg = 23.01 t/s, tg_3s = 19.11 t/s 13.15.974.816 I slot print_timing: id 2 | task 15679 | n_gen = 725, tg = 22.85 t/s, tg_3s = 19.11 t/s 13.17.671.277 I slot print_timing: id 3 | task 15723 | n_gen = 724, tg = 23.15 t/s, tg_3s = 24.76 t/s 13.18.154.981 I slot print_timing: id 2 | task 15679 | prompt eval time = 724.10 ms / 456 tokens ( 1.59 ms per token, 629.75 tokens per second) 13.18.154.988 I slot print_timing: id 2 | task 15679 | eval time = 33862.98 ms / 779 tokens ( 43.53 ms per token, 22.97 tokens per second) 13.18.154.989 I slot print_timing: id 2 | task 15679 | total time = 34587.08 ms / 1235 tokens 13.18.154.990 I slot print_timing: id 2 | task 15679 | graphs reused = 15604 13.18.154.990 I slot print_timing: id 2 | task 15679 | graph reallocs = 0 / 0 (same size) / (changed size) 13.18.155.092 I slot release: id 2 | task 15679 | stop processing: n_tokens = 1930, truncated = 0 13.18.197.546 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.553 13.18.197.583 I slot launch_slot_: id 2 | task 16465 | processing task, is_child = 0 13.18.820.712 I slot print_timing: id 0 | task 15937 | n_gen = 525, tg = 22.63 t/s, tg_3s = 20.35 t/s 13.19.017.634 I slot print_timing: id 3 | task 15723 | prompt eval time = 500.90 ms / 254 tokens ( 1.97 ms per token, 507.09 tokens per second) 13.19.017.640 I slot print_timing: id 3 | task 15723 | eval time = 32573.88 ms / 742 tokens ( 43.96 ms per token, 22.75 tokens per second) 13.19.017.640 I slot print_timing: id 3 | task 15723 | total time = 33074.79 ms / 996 tokens 13.19.017.641 I slot print_timing: id 3 | task 15723 | graphs reused = 15606 13.19.017.641 I slot print_timing: id 3 | task 15723 | graph reallocs = 0 / 0 (same size) / (changed size) 13.19.017.711 I slot release: id 3 | task 15723 | stop processing: n_tokens = 1919, truncated = 0 13.19.051.244 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.557 13.19.051.267 I slot launch_slot_: id 3 | task 16472 | processing task, is_child = 0 13.19.446.099 I slot print_timing: id 1 | task 16370 | n_gen = 100, tg = 19.94 t/s, tg_3s = 20.14 t/s 13.21.825.810 I slot print_timing: id 0 | task 15937 | n_gen = 589, tg = 22.48 t/s, tg_3s = 21.30 t/s 13.22.472.200 I slot print_timing: id 1 | task 16370 | n_gen = 174, tg = 21.65 t/s, tg_3s = 24.45 t/s 13.23.276.673 I slot print_timing: id 2 | task 16465 | n_gen = 100, tg = 22.61 t/s, tg_3s = 22.84 t/s 13.23.315.734 I slot print_timing: id 0 | task 15937 | prompt eval time = 702.69 ms / 461 tokens ( 1.52 ms per token, 656.05 tokens per second) 13.23.315.738 I slot print_timing: id 0 | task 15937 | eval time = 27645.44 ms / 626 tokens ( 44.23 ms per token, 22.61 tokens per second) 13.23.315.738 I slot print_timing: id 0 | task 15937 | total time = 28348.13 ms / 1087 tokens 13.23.315.739 I slot print_timing: id 0 | task 15937 | graphs reused = 15699 13.23.315.740 I slot print_timing: id 0 | task 15937 | graph reallocs = 0 / 0 (same size) / (changed size) 13.23.315.843 I slot release: id 0 | task 15937 | stop processing: n_tokens = 1759, truncated = 0 13.23.352.386 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.607 13.23.352.417 I slot launch_slot_: id 0 | task 16570 | processing task, is_child = 0 13.24.164.504 I slot print_timing: id 3 | task 16472 | n_gen = 100, tg = 21.30 t/s, tg_3s = 21.51 t/s 13.25.489.048 I slot print_timing: id 1 | task 16370 | n_gen = 233, tg = 21.08 t/s, tg_3s = 19.56 t/s 13.26.292.672 I slot print_timing: id 2 | task 16465 | n_gen = 159, tg = 21.37 t/s, tg_3s = 19.56 t/s 13.27.178.904 I slot print_timing: id 3 | task 16472 | n_gen = 175, tg = 22.71 t/s, tg_3s = 24.88 t/s 13.28.062.803 I slot print_timing: id 0 | task 16570 | n_gen = 100, tg = 24.88 t/s, tg_3s = 25.13 t/s 13.28.506.211 I slot print_timing: id 1 | task 16370 | n_gen = 308, tg = 21.89 t/s, tg_3s = 24.86 t/s 13.29.313.633 I slot print_timing: id 2 | task 16465 | n_gen = 234, tg = 22.37 t/s, tg_3s = 24.83 t/s 13.30.200.384 I slot print_timing: id 3 | task 16472 | n_gen = 250, tg = 23.31 t/s, tg_3s = 24.82 t/s 13.31.088.418 I slot print_timing: id 0 | task 16570 | n_gen = 175, tg = 24.84 t/s, tg_3s = 24.79 t/s 13.31.531.953 I slot print_timing: id 1 | task 16370 | n_gen = 383, tg = 22.40 t/s, tg_3s = 24.79 t/s 13.32.338.145 I slot print_timing: id 2 | task 16465 | n_gen = 309, tg = 22.92 t/s, tg_3s = 24.80 t/s 13.33.226.935 I slot print_timing: id 3 | task 16472 | n_gen = 325, tg = 23.63 t/s, tg_3s = 24.78 t/s 13.34.111.991 I slot print_timing: id 0 | task 16570 | n_gen = 250, tg = 24.83 t/s, tg_3s = 24.81 t/s 13.34.556.288 I slot print_timing: id 1 | task 16370 | n_gen = 458, tg = 22.77 t/s, tg_3s = 24.80 t/s 13.35.364.329 I slot print_timing: id 2 | task 16465 | n_gen = 384, tg = 23.26 t/s, tg_3s = 24.78 t/s 13.36.252.468 I slot print_timing: id 3 | task 16472 | n_gen = 400, tg = 23.84 t/s, tg_3s = 24.79 t/s 13.37.141.799 I slot print_timing: id 0 | task 16570 | n_gen = 325, tg = 24.81 t/s, tg_3s = 24.75 t/s 13.37.586.619 I slot print_timing: id 1 | task 16370 | n_gen = 533, tg = 23.03 t/s, tg_3s = 24.75 t/s 13.38.396.755 I slot print_timing: id 2 | task 16465 | n_gen = 459, tg = 23.49 t/s, tg_3s = 24.73 t/s 13.39.288.981 I slot print_timing: id 3 | task 16472 | n_gen = 475, tg = 23.97 t/s, tg_3s = 24.70 t/s 13.40.176.986 I slot print_timing: id 0 | task 16570 | n_gen = 400, tg = 24.79 t/s, tg_3s = 24.71 t/s 13.40.622.174 I slot print_timing: id 1 | task 16370 | n_gen = 608, tg = 23.22 t/s, tg_3s = 24.71 t/s 13.41.436.871 I slot print_timing: id 2 | task 16465 | n_gen = 534, tg = 23.65 t/s, tg_3s = 24.67 t/s 13.42.326.385 I slot print_timing: id 3 | task 16472 | n_gen = 550, tg = 24.07 t/s, tg_3s = 24.69 t/s 13.43.213.389 I slot print_timing: id 0 | task 16570 | n_gen = 475, tg = 24.78 t/s, tg_3s = 24.70 t/s 13.43.658.623 I slot print_timing: id 1 | task 16370 | n_gen = 683, tg = 23.37 t/s, tg_3s = 24.70 t/s 13.43.740.134 I slot print_timing: id 2 | task 16465 | prompt eval time = 700.14 ms / 440 tokens ( 1.59 ms per token, 628.44 tokens per second) 13.43.740.137 I slot print_timing: id 2 | task 16465 | eval time = 24842.40 ms / 591 tokens ( 42.11 ms per token, 23.75 tokens per second) 13.43.740.138 I slot print_timing: id 2 | task 16465 | total time = 25542.54 ms / 1031 tokens 13.43.740.139 I slot print_timing: id 2 | task 16465 | graphs reused = 16184 13.43.740.140 I slot print_timing: id 2 | task 16465 | graph reallocs = 0 / 0 (same size) / (changed size) 13.43.740.242 I slot release: id 2 | task 16465 | stop processing: n_tokens = 1726, truncated = 0 13.43.783.375 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.619 13.43.783.411 I slot launch_slot_: id 2 | task 17061 | processing task, is_child = 0 13.45.361.381 I slot print_timing: id 3 | task 16472 | n_gen = 609, tg = 23.52 t/s, tg_3s = 19.44 t/s 13.45.684.189 I slot print_timing: id 3 | task 16472 | prompt eval time = 465.24 ms / 215 tokens ( 2.16 ms per token, 462.12 tokens per second) 13.45.684.194 I slot print_timing: id 3 | task 16472 | eval time = 26167.67 ms / 617 tokens ( 42.48 ms per token, 23.54 tokens per second) 13.45.684.196 I slot print_timing: id 3 | task 16472 | total time = 26632.91 ms / 832 tokens 13.45.684.196 I slot print_timing: id 3 | task 16472 | graphs reused = 16212 13.45.684.197 I slot print_timing: id 3 | task 16472 | graph reallocs = 0 / 0 (same size) / (changed size) 13.45.684.291 I slot release: id 3 | task 16472 | stop processing: n_tokens = 1755, truncated = 0 13.45.719.625 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.609 13.45.719.672 I slot launch_slot_: id 3 | task 17094 | processing task, is_child = 0 13.46.225.019 I slot print_timing: id 0 | task 16570 | n_gen = 524, tg = 23.62 t/s, tg_3s = 16.27 t/s 13.46.659.273 I slot print_timing: id 1 | task 16370 | n_gen = 732, tg = 22.72 t/s, tg_3s = 16.33 t/s 13.48.885.821 I slot print_timing: id 2 | task 17061 | n_gen = 100, tg = 22.66 t/s, tg_3s = 22.89 t/s 13.49.247.390 I slot print_timing: id 0 | task 16570 | n_gen = 599, tg = 23.76 t/s, tg_3s = 24.81 t/s 13.49.692.598 I slot print_timing: id 1 | task 16370 | n_gen = 807, tg = 22.89 t/s, tg_3s = 24.73 t/s 13.50.178.049 I slot print_timing: id 3 | task 17094 | n_gen = 100, tg = 24.79 t/s, tg_3s = 25.05 t/s 13.51.910.965 I slot print_timing: id 2 | task 17061 | n_gen = 175, tg = 23.53 t/s, tg_3s = 24.79 t/s 13.52.273.172 I slot print_timing: id 0 | task 16570 | n_gen = 674, tg = 23.87 t/s, tg_3s = 24.79 t/s 13.52.723.488 I slot print_timing: id 1 | task 16370 | n_gen = 882, tg = 23.04 t/s, tg_3s = 24.75 t/s 13.53.211.052 I slot print_timing: id 3 | task 17094 | n_gen = 175, tg = 24.77 t/s, tg_3s = 24.73 t/s 13.54.911.741 I slot print_timing: id 2 | task 17061 | n_gen = 249, tg = 23.86 t/s, tg_3s = 24.66 t/s 13.55.274.816 I slot print_timing: id 0 | task 16570 | n_gen = 748, tg = 23.95 t/s, tg_3s = 24.65 t/s 13.55.762.773 I slot print_timing: id 1 | task 16370 | n_gen = 957, tg = 23.16 t/s, tg_3s = 24.68 t/s 13.56.211.275 I slot print_timing: id 3 | task 17094 | n_gen = 249, tg = 24.74 t/s, tg_3s = 24.66 t/s 13.57.920.900 I slot print_timing: id 2 | task 17061 | n_gen = 323, tg = 24.02 t/s, tg_3s = 24.59 t/s 13.58.284.996 I slot print_timing: id 0 | task 16570 | n_gen = 822, tg = 24.00 t/s, tg_3s = 24.58 t/s 13.58.489.348 I slot print_timing: id 1 | task 16370 | prompt eval time = 769.63 ms / 502 tokens ( 1.53 ms per token, 652.26 tokens per second) 13.58.489.352 I slot print_timing: id 1 | task 16370 | eval time = 44007.45 ms / 1024 tokens ( 43.02 ms per token, 23.25 tokens per second) 13.58.489.353 I slot print_timing: id 1 | task 16370 | total time = 44777.08 ms / 1526 tokens 13.58.489.358 I slot print_timing: id 1 | task 16370 | graphs reused = 16514 13.58.489.359 I slot print_timing: id 1 | task 16370 | graph reallocs = 0 / 0 (same size) / (changed size) 13.58.489.468 I slot release: id 1 | task 16370 | stop processing: n_tokens = 2198, truncated = 0 13.58.532.962 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.486 13.58.539.355 I slot launch_slot_: id 1 | task 17402 | processing task, is_child = 0 13.59.221.159 I slot print_timing: id 3 | task 17094 | n_gen = 307, tg = 23.47 t/s, tg_3s = 19.27 t/s 14.00.956.660 I slot print_timing: id 2 | task 17061 | n_gen = 381, tg = 23.12 t/s, tg_3s = 19.11 t/s 14.01.318.793 I slot print_timing: id 0 | task 16570 | n_gen = 880, tg = 23.61 t/s, tg_3s = 19.12 t/s 14.02.251.686 I slot print_timing: id 3 | task 17094 | n_gen = 381, tg = 23.65 t/s, tg_3s = 24.42 t/s 14.03.303.707 I slot print_timing: id 1 | task 17402 | n_gen = 100, tg = 24.72 t/s, tg_3s = 24.97 t/s 14.03.992.149 I slot print_timing: id 2 | task 17061 | n_gen = 456, tg = 23.36 t/s, tg_3s = 24.71 t/s 14.04.275.527 I slot print_timing: id 3 | task 17094 | prompt eval time = 465.57 ms / 220 tokens ( 2.12 ms per token, 472.53 tokens per second) 14.04.275.531 I slot print_timing: id 3 | task 17094 | eval time = 18090.27 ms / 431 tokens ( 42.07 ms per token, 23.77 tokens per second) 14.04.275.531 I slot print_timing: id 3 | task 17094 | total time = 18555.84 ms / 651 tokens 14.04.275.532 I slot print_timing: id 3 | task 17094 | graphs reused = 16635 14.04.275.533 I slot print_timing: id 3 | task 17094 | graph reallocs = 0 / 0 (same size) / (changed size) 14.04.275.641 I slot release: id 3 | task 17094 | stop processing: n_tokens = 1574, truncated = 0 14.04.311.271 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.679 14.04.311.304 I slot launch_slot_: id 3 | task 17529 | processing task, is_child = 0 14.04.740.339 I slot print_timing: id 0 | task 16570 | n_gen = 955, tg = 23.46 t/s, tg_3s = 21.92 t/s 14.06.309.148 I slot print_timing: id 1 | task 17402 | n_gen = 164, tg = 23.25 t/s, tg_3s = 21.29 t/s 14.07.001.033 I slot print_timing: id 2 | task 17061 | n_gen = 520, tg = 23.08 t/s, tg_3s = 21.27 t/s 14.07.569.462 I slot print_timing: id 0 | task 16570 | prompt eval time = 731.03 ms / 487 tokens ( 1.50 ms per token, 666.19 tokens per second) 14.07.569.469 I slot print_timing: id 0 | task 16570 | eval time = 43486.01 ms / 1024 tokens ( 42.51 ms per token, 23.52 tokens per second) 14.07.569.470 I slot print_timing: id 0 | task 16570 | total time = 44217.04 ms / 1511 tokens 14.07.569.471 I slot print_timing: id 0 | task 16570 | graphs reused = 16702 14.07.569.472 I slot print_timing: id 0 | task 16570 | graph reallocs = 0 / 0 (same size) / (changed size) 14.07.569.576 I slot release: id 0 | task 16570 | stop processing: n_tokens = 2183, truncated = 0 14.07.606.709 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.489 14.07.608.980 I slot launch_slot_: id 0 | task 17601 | processing task, is_child = 0 14.09.310.034 I slot print_timing: id 1 | task 17402 | n_gen = 222, tg = 22.07 t/s, tg_3s = 19.33 t/s 14.09.472.800 I slot print_timing: id 3 | task 17529 | n_gen = 100, tg = 21.24 t/s, tg_3s = 21.45 t/s 14.10.037.337 I slot print_timing: id 2 | task 17061 | n_gen = 579, tg = 22.65 t/s, tg_3s = 19.43 t/s 14.11.369.304 I slot print_timing: id 2 | task 17061 | prompt eval time = 734.03 ms / 473 tokens ( 1.55 ms per token, 644.39 tokens per second) 14.11.369.310 I slot print_timing: id 2 | task 17061 | eval time = 26851.85 ms / 612 tokens ( 43.95 ms per token, 22.75 tokens per second) 14.11.369.311 I slot print_timing: id 2 | task 17061 | total time = 27585.88 ms / 1085 tokens 14.11.369.312 I slot print_timing: id 2 | task 17061 | graphs reused = 16777 14.11.369.313 I slot print_timing: id 2 | task 17061 | graph reallocs = 0 / 0 (same size) / (changed size) 14.11.369.420 I slot release: id 2 | task 17061 | stop processing: n_tokens = 1780, truncated = 0 14.11.412.244 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.600 14.11.412.277 I slot launch_slot_: id 2 | task 17680 | processing task, is_child = 0 14.12.336.190 I slot print_timing: id 1 | task 17402 | n_gen = 281, tg = 21.48 t/s, tg_3s = 19.50 t/s 14.12.499.131 I slot print_timing: id 3 | task 17529 | n_gen = 159, tg = 20.55 t/s, tg_3s = 19.50 t/s 14.12.982.211 I slot print_timing: id 0 | task 17601 | n_gen = 100, tg = 21.35 t/s, tg_3s = 21.57 t/s 14.15.360.691 I slot print_timing: id 1 | task 17402 | n_gen = 356, tg = 22.10 t/s, tg_3s = 24.80 t/s 14.15.522.793 I slot print_timing: id 3 | task 17529 | n_gen = 234, tg = 21.75 t/s, tg_3s = 24.80 t/s 14.16.003.696 I slot print_timing: id 0 | task 17601 | n_gen = 175, tg = 22.72 t/s, tg_3s = 24.82 t/s 14.16.125.467 I slot print_timing: id 2 | task 17680 | n_gen = 100, tg = 24.83 t/s, tg_3s = 25.08 t/s 14.18.383.078 I slot print_timing: id 1 | task 17402 | n_gen = 431, tg = 22.53 t/s, tg_3s = 24.81 t/s 14.18.545.427 I slot print_timing: id 3 | task 17529 | n_gen = 309, tg = 22.43 t/s, tg_3s = 24.81 t/s 14.19.027.324 I slot print_timing: id 0 | task 17601 | n_gen = 250, tg = 23.31 t/s, tg_3s = 24.80 t/s 14.19.149.475 I slot print_timing: id 2 | task 17680 | n_gen = 175, tg = 24.82 t/s, tg_3s = 24.80 t/s 14.21.410.557 I slot print_timing: id 1 | task 17402 | n_gen = 506, tg = 22.84 t/s, tg_3s = 24.77 t/s 14.21.572.928 I slot print_timing: id 3 | task 17529 | n_gen = 384, tg = 22.85 t/s, tg_3s = 24.77 t/s 14.22.055.154 I slot print_timing: id 0 | task 17601 | n_gen = 325, tg = 23.63 t/s, tg_3s = 24.77 t/s 14.22.176.720 I slot print_timing: id 2 | task 17680 | n_gen = 250, tg = 24.81 t/s, tg_3s = 24.78 t/s 14.23.022.530 I slot print_timing: id 1 | task 17402 | prompt eval time = 758.91 ms / 488 tokens ( 1.56 ms per token, 643.02 tokens per second) 14.23.022.537 I slot print_timing: id 1 | task 17402 | eval time = 23724.24 ms / 546 tokens ( 43.53 ms per token, 22.97 tokens per second) 14.23.022.538 I slot print_timing: id 1 | task 17402 | total time = 24483.16 ms / 1034 tokens 14.23.022.539 I slot print_timing: id 1 | task 17402 | graphs reused = 17045 14.23.022.540 I slot print_timing: id 1 | task 17402 | graph reallocs = 0 / 0 (same size) / (changed size) 14.23.022.648 I slot release: id 1 | task 17402 | stop processing: n_tokens = 1706, truncated = 0 14.23.066.575 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.626 14.23.066.616 I slot launch_slot_: id 1 | task 17954 | processing task, is_child = 0 14.24.578.509 I slot print_timing: id 3 | task 17529 | n_gen = 442, tg = 22.31 t/s, tg_3s = 19.30 t/s 14.25.062.327 I slot print_timing: id 0 | task 17601 | n_gen = 383, tg = 22.85 t/s, tg_3s = 19.29 t/s 14.25.184.856 I slot print_timing: id 2 | task 17680 | n_gen = 308, tg = 23.53 t/s, tg_3s = 19.28 t/s 14.27.612.249 I slot print_timing: id 3 | task 17529 | n_gen = 517, tg = 22.63 t/s, tg_3s = 24.72 t/s 14.27.812.630 I slot print_timing: id 1 | task 17954 | n_gen = 100, tg = 24.69 t/s, tg_3s = 24.94 t/s 14.28.095.850 I slot print_timing: id 0 | task 17601 | n_gen = 458, tg = 23.14 t/s, tg_3s = 24.72 t/s 14.28.217.815 I slot print_timing: id 2 | task 17680 | n_gen = 383, tg = 23.76 t/s, tg_3s = 24.73 t/s 14.30.626.432 I slot print_timing: id 3 | task 17529 | n_gen = 592, tg = 22.89 t/s, tg_3s = 24.88 t/s 14.30.826.110 I slot print_timing: id 1 | task 17954 | n_gen = 175, tg = 24.77 t/s, tg_3s = 24.89 t/s 14.31.106.303 I slot print_timing: id 0 | task 17601 | n_gen = 533, tg = 23.37 t/s, tg_3s = 24.91 t/s 14.31.227.299 I slot print_timing: id 2 | task 17680 | n_gen = 458, tg = 23.94 t/s, tg_3s = 24.92 t/s 14.32.998.990 I slot print_timing: id 2 | task 17680 | prompt eval time = 726.43 ms / 463 tokens ( 1.57 ms per token, 637.36 tokens per second) 14.32.998.997 I slot print_timing: id 2 | task 17680 | eval time = 20860.27 ms / 502 tokens ( 41.64 ms per token, 24.02 tokens per second) 14.32.998.998 I slot print_timing: id 2 | task 17680 | total time = 21586.70 ms / 965 tokens 14.32.998.999 I slot print_timing: id 2 | task 17680 | graphs reused = 17271 14.32.999.000 I slot print_timing: id 2 | task 17680 | graph reallocs = 0 / 0 (same size) / (changed size) 14.32.999.098 I slot release: id 2 | task 17680 | stop processing: n_tokens = 1660, truncated = 0 14.33.041.975 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.643 14.33.042.013 I slot launch_slot_: id 2 | task 18186 | processing task, is_child = 0 14.33.666.544 I slot print_timing: id 0 | task 17601 | prompt eval time = 736.75 ms / 494 tokens ( 1.49 ms per token, 670.51 tokens per second) 14.33.666.547 I slot print_timing: id 0 | task 17601 | eval time = 25320.81 ms / 582 tokens ( 43.58 ms per token, 22.95 tokens per second) 14.33.666.548 I slot print_timing: id 0 | task 17601 | total time = 26057.56 ms / 1076 tokens 14.33.666.548 I slot print_timing: id 0 | task 17601 | graphs reused = 17271 14.33.666.549 I slot print_timing: id 0 | task 17601 | graph reallocs = 0 / 0 (same size) / (changed size) 14.33.666.609 I slot release: id 0 | task 17601 | stop processing: n_tokens = 1748, truncated = 0 14.33.667.169 I slot print_timing: id 3 | task 17529 | n_gen = 653, tg = 22.59 t/s, tg_3s = 20.06 t/s 14.33.734.610 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.611 14.33.734.639 I slot launch_slot_: id 0 | task 18189 | processing task, is_child = 0 14.34.480.284 I slot print_timing: id 1 | task 17954 | n_gen = 234, tg = 21.82 t/s, tg_3s = 16.15 t/s 14.36.687.604 I slot print_timing: id 3 | task 17529 | n_gen = 710, tg = 22.24 t/s, tg_3s = 18.87 t/s 14.37.493.087 I slot print_timing: id 1 | task 17954 | n_gen = 308, tg = 22.42 t/s, tg_3s = 24.56 t/s 14.38.423.315 I slot print_timing: id 2 | task 18186 | n_gen = 100, tg = 21.11 t/s, tg_3s = 21.33 t/s 14.38.543.353 I slot print_timing: id 0 | task 18189 | n_gen = 100, tg = 24.78 t/s, tg_3s = 25.03 t/s 14.39.712.891 I slot print_timing: id 3 | task 17529 | n_gen = 785, tg = 22.46 t/s, tg_3s = 24.79 t/s 14.40.517.934 I slot print_timing: id 1 | task 17954 | n_gen = 383, tg = 22.85 t/s, tg_3s = 24.79 t/s 14.41.448.418 I slot print_timing: id 2 | task 18186 | n_gen = 175, tg = 22.56 t/s, tg_3s = 24.79 t/s 14.41.568.374 I slot print_timing: id 0 | task 18189 | n_gen = 175, tg = 24.79 t/s, tg_3s = 24.79 t/s 14.42.742.153 I slot print_timing: id 3 | task 17529 | n_gen = 860, tg = 22.65 t/s, tg_3s = 24.76 t/s 14.43.552.460 I slot print_timing: id 1 | task 17954 | n_gen = 458, tg = 23.14 t/s, tg_3s = 24.72 t/s 14.44.202.439 I slot print_timing: id 1 | task 17954 | prompt eval time = 735.89 ms / 471 tokens ( 1.56 ms per token, 640.04 tokens per second) 14.44.202.446 I slot print_timing: id 1 | task 17954 | eval time = 20399.93 ms / 474 tokens ( 43.13 ms per token, 23.19 tokens per second) 14.44.202.447 I slot print_timing: id 1 | task 17954 | total time = 21135.81 ms / 945 tokens 14.44.202.448 I slot print_timing: id 1 | task 17954 | graphs reused = 17508 14.44.202.449 I slot print_timing: id 1 | task 17954 | graph reallocs = 0 / 0 (same size) / (changed size) 14.44.202.561 I slot release: id 1 | task 17954 | stop processing: n_tokens = 1617, truncated = 0 14.44.246.524 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.660 14.44.246.564 I slot launch_slot_: id 1 | task 18433 | processing task, is_child = 0 14.44.892.769 I slot print_timing: id 0 | task 18189 | n_gen = 242, tg = 23.30 t/s, tg_3s = 20.15 t/s 14.44.893.028 I slot print_timing: id 2 | task 18186 | n_gen = 245, tg = 21.87 t/s, tg_3s = 20.32 t/s 14.45.780.277 I slot print_timing: id 3 | task 17529 | n_gen = 919, tg = 22.41 t/s, tg_3s = 19.42 t/s 14.47.925.639 I slot print_timing: id 0 | task 18189 | n_gen = 316, tg = 23.55 t/s, tg_3s = 24.40 t/s 14.47.926.674 I slot print_timing: id 2 | task 18186 | n_gen = 319, tg = 22.41 t/s, tg_3s = 24.39 t/s 14.48.819.377 I slot print_timing: id 3 | task 17529 | n_gen = 994, tg = 22.56 t/s, tg_3s = 24.68 t/s 14.48.980.189 I slot print_timing: id 1 | task 18433 | n_gen = 100, tg = 24.69 t/s, tg_3s = 24.94 t/s 14.50.034.833 I slot print_timing: id 3 | task 17529 | prompt eval time = 499.87 ms / 251 tokens ( 1.99 ms per token, 502.13 tokens per second) 14.50.034.841 I slot print_timing: id 3 | task 17529 | eval time = 45223.65 ms / 1024 tokens ( 44.21 ms per token, 22.62 tokens per second) 14.50.034.841 I slot print_timing: id 3 | task 17529 | total time = 45723.52 ms / 1275 tokens 14.50.034.842 I slot print_timing: id 3 | task 17529 | graphs reused = 17632 14.50.034.843 I slot print_timing: id 3 | task 17529 | graph reallocs = 0 / 0 (same size) / (changed size) 14.50.034.956 I slot release: id 3 | task 17529 | stop processing: n_tokens = 2198, truncated = 0 14.50.070.248 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.486 14.50.075.996 I slot launch_slot_: id 3 | task 18562 | processing task, is_child = 0 14.50.938.603 I slot print_timing: id 0 | task 18189 | n_gen = 381, tg = 23.18 t/s, tg_3s = 21.57 t/s 14.50.939.264 I slot print_timing: id 2 | task 18186 | n_gen = 384, tg = 22.26 t/s, tg_3s = 21.58 t/s 14.51.993.060 I slot print_timing: id 1 | task 18433 | n_gen = 165, tg = 23.36 t/s, tg_3s = 21.57 t/s 14.53.967.042 I slot print_timing: id 0 | task 18189 | n_gen = 456, tg = 23.43 t/s, tg_3s = 24.77 t/s 14.53.968.172 I slot print_timing: id 2 | task 18186 | n_gen = 459, tg = 22.64 t/s, tg_3s = 24.76 t/s 14.54.534.650 I slot print_timing: id 3 | task 18562 | n_gen = 100, tg = 24.81 t/s, tg_3s = 25.06 t/s 14.55.019.086 I slot print_timing: id 1 | task 18433 | n_gen = 240, tg = 23.79 t/s, tg_3s = 24.78 t/s 14.56.998.903 I slot print_timing: id 0 | task 18189 | n_gen = 531, tg = 23.61 t/s, tg_3s = 24.74 t/s 14.57.000.044 I slot print_timing: id 2 | task 18186 | n_gen = 534, tg = 22.91 t/s, tg_3s = 24.74 t/s 14.57.566.534 I slot print_timing: id 3 | task 18562 | n_gen = 175, tg = 24.78 t/s, tg_3s = 24.74 t/s 14.58.052.044 I slot print_timing: id 1 | task 18433 | n_gen = 315, tg = 24.00 t/s, tg_3s = 24.73 t/s 15.00.037.766 I slot print_timing: id 0 | task 18189 | n_gen = 606, tg = 23.74 t/s, tg_3s = 24.68 t/s 15.00.038.880 I slot print_timing: id 2 | task 18186 | n_gen = 609, tg = 23.11 t/s, tg_3s = 24.68 t/s 15.00.605.436 I slot print_timing: id 3 | task 18562 | n_gen = 250, tg = 24.75 t/s, tg_3s = 24.68 t/s 15.01.089.391 I slot print_timing: id 1 | task 18433 | n_gen = 390, tg = 24.13 t/s, tg_3s = 24.69 t/s 15.02.018.093 I slot print_timing: id 2 | task 18186 | prompt eval time = 692.31 ms / 442 tokens ( 1.57 ms per token, 638.45 tokens per second) 15.02.018.096 I slot print_timing: id 2 | task 18186 | eval time = 28283.76 ms / 658 tokens ( 43.05 ms per token, 23.23 tokens per second) 15.02.018.097 I slot print_timing: id 2 | task 18186 | total time = 28976.07 ms / 1100 tokens 15.02.018.098 I slot print_timing: id 2 | task 18186 | graphs reused = 17914 15.02.018.099 I slot print_timing: id 2 | task 18186 | graph reallocs = 0 / 0 (same size) / (changed size) 15.02.018.203 I slot release: id 2 | task 18186 | stop processing: n_tokens = 1795, truncated = 0 15.02.061.238 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.595 15.02.061.275 I slot launch_slot_: id 2 | task 18850 | processing task, is_child = 0 15.03.041.281 I slot print_timing: id 0 | task 18189 | n_gen = 665, tg = 23.30 t/s, tg_3s = 19.64 t/s 15.03.608.188 I slot print_timing: id 3 | task 18562 | n_gen = 309, tg = 23.58 t/s, tg_3s = 19.65 t/s 15.04.093.519 I slot print_timing: id 1 | task 18433 | n_gen = 449, tg = 23.43 t/s, tg_3s = 19.64 t/s 15.06.076.266 I slot print_timing: id 0 | task 18189 | n_gen = 740, tg = 23.44 t/s, tg_3s = 24.71 t/s 15.06.646.166 I slot print_timing: id 3 | task 18562 | n_gen = 384, tg = 23.79 t/s, tg_3s = 24.69 t/s 15.06.767.215 I slot print_timing: id 2 | task 18850 | n_gen = 100, tg = 24.73 t/s, tg_3s = 24.98 t/s 15.07.131.681 I slot print_timing: id 1 | task 18433 | n_gen = 524, tg = 23.60 t/s, tg_3s = 24.69 t/s 15.09.114.949 I slot print_timing: id 0 | task 18189 | n_gen = 815, tg = 23.55 t/s, tg_3s = 24.68 t/s 15.09.684.447 I slot print_timing: id 3 | task 18562 | n_gen = 459, tg = 23.93 t/s, tg_3s = 24.69 t/s 15.09.806.669 I slot print_timing: id 2 | task 18850 | n_gen = 175, tg = 24.70 t/s, tg_3s = 24.68 t/s 15.10.132.024 I slot print_timing: id 1 | task 18433 | n_gen = 598, tg = 23.73 t/s, tg_3s = 24.66 t/s 15.12.128.791 I slot print_timing: id 0 | task 18189 | n_gen = 889, tg = 23.63 t/s, tg_3s = 24.55 t/s 15.12.699.307 I slot print_timing: id 3 | task 18562 | n_gen = 533, tg = 24.01 t/s, tg_3s = 24.55 t/s 15.12.821.098 I slot print_timing: id 2 | task 18850 | n_gen = 249, tg = 24.66 t/s, tg_3s = 24.55 t/s 15.13.145.827 I slot print_timing: id 1 | task 18433 | n_gen = 672, tg = 23.82 t/s, tg_3s = 24.55 t/s 15.14.896.017 I slot print_timing: id 1 | task 18433 | prompt eval time = 724.71 ms / 457 tokens ( 1.59 ms per token, 630.60 tokens per second) 15.14.896.024 I slot print_timing: id 1 | task 18433 | eval time = 29924.74 ms / 715 tokens ( 41.91 ms per token, 23.86 tokens per second) 15.14.896.026 I slot print_timing: id 1 | task 18433 | total time = 30649.44 ms / 1172 tokens 15.14.896.027 I slot print_timing: id 1 | task 18433 | graphs reused = 18211 15.14.896.028 I slot print_timing: id 1 | task 18433 | graph reallocs = 0 / 0 (same size) / (changed size) 15.14.896.140 I slot release: id 1 | task 18433 | stop processing: n_tokens = 1844, truncated = 0 15.14.939.774 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.579 15.14.939.811 I slot launch_slot_: id 1 | task 19153 | processing task, is_child = 0 15.15.606.401 I slot print_timing: id 0 | task 18189 | n_gen = 959, tg = 23.33 t/s, tg_3s = 20.13 t/s 15.15.726.374 I slot print_timing: id 3 | task 18562 | n_gen = 591, tg = 23.43 t/s, tg_3s = 19.16 t/s 15.15.846.574 I slot print_timing: id 2 | task 18850 | n_gen = 307, tg = 23.39 t/s, tg_3s = 19.17 t/s 15.18.288.861 I slot print_timing: id 0 | task 18189 | prompt eval time = 814.01 ms / 519 tokens ( 1.57 ms per token, 637.58 tokens per second) 15.18.288.869 I slot print_timing: id 0 | task 18189 | eval time = 43740.20 ms / 1024 tokens ( 42.76 ms per token, 23.39 tokens per second) 15.18.288.871 I slot print_timing: id 0 | task 18189 | total time = 44554.21 ms / 1543 tokens 15.18.288.871 I slot print_timing: id 0 | task 18189 | graphs reused = 18274 15.18.288.872 I slot print_timing: id 0 | task 18189 | graph reallocs = 0 / 0 (same size) / (changed size) 15.18.288.972 I slot release: id 0 | task 18189 | stop processing: n_tokens = 2215, truncated = 0 15.18.325.874 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.482 15.18.331.885 I slot launch_slot_: id 0 | task 19221 | processing task, is_child = 0 15.18.997.327 I slot print_timing: id 2 | task 18850 | n_gen = 369, tg = 22.67 t/s, tg_3s = 19.68 t/s 15.18.997.630 I slot print_timing: id 3 | task 18562 | n_gen = 656, tg = 23.02 t/s, tg_3s = 19.87 t/s 15.20.355.711 I slot print_timing: id 1 | task 19153 | n_gen = 100, tg = 21.19 t/s, tg_3s = 21.41 t/s 15.22.010.049 I slot print_timing: id 2 | task 18850 | n_gen = 443, tg = 22.97 t/s, tg_3s = 24.56 t/s 15.22.010.634 I slot print_timing: id 3 | task 18562 | n_gen = 730, tg = 23.17 t/s, tg_3s = 24.56 t/s 15.23.060.953 I slot print_timing: id 0 | task 19221 | n_gen = 100, tg = 24.78 t/s, tg_3s = 25.03 t/s 15.23.384.721 I slot print_timing: id 1 | task 19153 | n_gen = 175, tg = 22.60 t/s, tg_3s = 24.76 t/s 15.23.667.769 I slot print_timing: id 2 | task 18850 | prompt eval time = 702.22 ms / 442 tokens ( 1.59 ms per token, 629.43 tokens per second) 15.23.667.775 I slot print_timing: id 2 | task 18850 | eval time = 20904.26 ms / 484 tokens ( 43.28 ms per token, 23.11 tokens per second) 15.23.667.776 I slot print_timing: id 2 | task 18850 | total time = 21606.49 ms / 926 tokens 15.23.667.777 I slot print_timing: id 2 | task 18850 | graphs reused = 18388 15.23.667.777 I slot print_timing: id 2 | task 18850 | graph reallocs = 0 / 0 (same size) / (changed size) 15.23.667.881 I slot release: id 2 | task 18850 | stop processing: n_tokens = 1621, truncated = 0 15.23.710.655 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.659 15.23.710.689 I slot launch_slot_: id 2 | task 19339 | processing task, is_child = 0 15.25.021.659 I slot print_timing: id 3 | task 18562 | n_gen = 789, tg = 22.86 t/s, tg_3s = 19.59 t/s 15.26.069.695 I slot print_timing: id 0 | task 19221 | n_gen = 159, tg = 22.56 t/s, tg_3s = 19.61 t/s 15.26.392.627 I slot print_timing: id 1 | task 19153 | n_gen = 234, tg = 21.76 t/s, tg_3s = 19.61 t/s 15.28.042.503 I slot print_timing: id 3 | task 18562 | n_gen = 864, tg = 23.01 t/s, tg_3s = 24.83 t/s 15.28.404.677 I slot print_timing: id 2 | task 19339 | n_gen = 100, tg = 24.78 t/s, tg_3s = 25.03 t/s 15.29.086.834 I slot print_timing: id 0 | task 19221 | n_gen = 234, tg = 23.25 t/s, tg_3s = 24.86 t/s 15.29.409.876 I slot print_timing: id 1 | task 19153 | n_gen = 309, tg = 22.44 t/s, tg_3s = 24.86 t/s 15.31.072.834 I slot print_timing: id 3 | task 18562 | n_gen = 939, tg = 23.14 t/s, tg_3s = 24.75 t/s 15.31.437.723 I slot print_timing: id 2 | task 19339 | n_gen = 175, tg = 24.76 t/s, tg_3s = 24.73 t/s 15.32.127.367 I slot print_timing: id 0 | task 19221 | n_gen = 309, tg = 23.58 t/s, tg_3s = 24.67 t/s 15.32.412.316 I slot print_timing: id 1 | task 19153 | n_gen = 383, tg = 22.84 t/s, tg_3s = 24.65 t/s 15.34.079.068 I slot print_timing: id 3 | task 18562 | n_gen = 1013, tg = 23.25 t/s, tg_3s = 24.62 t/s 15.34.441.963 I slot print_timing: id 2 | task 19339 | n_gen = 249, tg = 24.72 t/s, tg_3s = 24.63 t/s 15.34.523.405 I slot print_timing: id 3 | task 18562 | prompt eval time = 468.10 ms / 219 tokens ( 2.14 ms per token, 467.85 tokens per second) 15.34.523.412 I slot print_timing: id 3 | task 18562 | eval time = 43979.30 ms / 1024 tokens ( 42.99 ms per token, 23.26 tokens per second) 15.34.523.413 I slot print_timing: id 3 | task 18562 | total time = 44447.40 ms / 1243 tokens 15.34.523.414 I slot print_timing: id 3 | task 18562 | graphs reused = 18636 15.34.523.414 I slot print_timing: id 3 | task 18562 | graph reallocs = 0 / 0 (same size) / (changed size) 15.34.523.513 I slot release: id 3 | task 18562 | stop processing: n_tokens = 2166, truncated = 0 15.34.558.810 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.493 15.34.564.857 I slot launch_slot_: id 3 | task 19593 | processing task, is_child = 0 15.35.140.076 I slot print_timing: id 0 | task 19221 | n_gen = 372, tg = 23.08 t/s, tg_3s = 20.91 t/s 15.35.416.717 I slot print_timing: id 1 | task 19153 | n_gen = 446, tg = 22.55 t/s, tg_3s = 20.97 t/s 15.37.478.693 I slot print_timing: id 2 | task 19339 | n_gen = 313, tg = 23.87 t/s, tg_3s = 21.08 t/s 15.38.163.347 I slot print_timing: id 0 | task 19221 | n_gen = 447, tg = 23.35 t/s, tg_3s = 24.81 t/s 15.38.446.312 I slot print_timing: id 1 | task 19153 | n_gen = 521, tg = 22.85 t/s, tg_3s = 24.76 t/s 15.38.486.835 I slot print_timing: id 1 | task 19153 | prompt eval time = 744.77 ms / 484 tokens ( 1.54 ms per token, 649.86 tokens per second) 15.38.486.847 I slot print_timing: id 1 | task 19153 | eval time = 22802.24 ms / 522 tokens ( 43.77 ms per token, 22.85 tokens per second) 15.38.486.848 I slot print_timing: id 1 | task 19153 | total time = 23547.02 ms / 1006 tokens 15.38.486.848 I slot print_timing: id 1 | task 19153 | graphs reused = 18719 15.38.486.849 I slot print_timing: id 1 | task 19153 | graph reallocs = 0 / 0 (same size) / (changed size) 15.38.486.950 I slot release: id 1 | task 19153 | stop processing: n_tokens = 1678, truncated = 0 15.38.530.842 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.636 15.38.530.882 I slot launch_slot_: id 1 | task 19681 | processing task, is_child = 0 15.39.760.774 I slot print_timing: id 3 | task 19593 | n_gen = 100, tg = 21.24 t/s, tg_3s = 21.46 t/s 15.40.490.223 I slot print_timing: id 2 | task 19339 | n_gen = 371, tg = 23.01 t/s, tg_3s = 19.26 t/s 15.40.854.326 I slot print_timing: id 2 | task 19339 | prompt eval time = 699.51 ms / 438 tokens ( 1.60 ms per token, 626.15 tokens per second) 15.40.854.333 I slot print_timing: id 2 | task 19339 | eval time = 16444.12 ms / 380 tokens ( 43.39 ms per token, 23.05 tokens per second) 15.40.854.334 I slot print_timing: id 2 | task 19339 | total time = 17143.63 ms / 818 tokens 15.40.854.334 I slot print_timing: id 2 | task 19339 | graphs reused = 18757 15.40.854.335 I slot print_timing: id 2 | task 19339 | graph reallocs = 0 / 0 (same size) / (changed size) 15.40.854.430 I slot release: id 2 | task 19339 | stop processing: n_tokens = 1513, truncated = 0 15.40.897.270 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.706 15.40.897.306 I slot launch_slot_: id 2 | task 19724 | processing task, is_child = 0 15.41.579.494 I slot print_timing: id 0 | task 19221 | n_gen = 499, tg = 22.12 t/s, tg_3s = 15.22 t/s 15.42.787.843 I slot print_timing: id 3 | task 19593 | n_gen = 158, tg = 20.42 t/s, tg_3s = 19.16 t/s 15.43.958.228 I slot print_timing: id 1 | task 19681 | n_gen = 100, tg = 21.12 t/s, tg_3s = 21.34 t/s 15.44.602.820 I slot print_timing: id 0 | task 19221 | n_gen = 573, tg = 22.40 t/s, tg_3s = 24.48 t/s 15.45.652.642 I slot print_timing: id 2 | task 19724 | n_gen = 100, tg = 24.77 t/s, tg_3s = 25.02 t/s 15.45.814.482 I slot print_timing: id 3 | task 19593 | n_gen = 233, tg = 21.65 t/s, tg_3s = 24.78 t/s 15.46.984.468 I slot print_timing: id 1 | task 19681 | n_gen = 175, tg = 22.56 t/s, tg_3s = 24.78 t/s 15.47.627.695 I slot print_timing: id 0 | task 19221 | n_gen = 648, tg = 22.65 t/s, tg_3s = 24.79 t/s 15.48.679.876 I slot print_timing: id 2 | task 19724 | n_gen = 175, tg = 24.77 t/s, tg_3s = 24.78 t/s 15.48.841.780 I slot print_timing: id 3 | task 19593 | n_gen = 308, tg = 22.34 t/s, tg_3s = 24.77 t/s 15.50.010.529 I slot print_timing: id 1 | task 19681 | n_gen = 250, tg = 23.19 t/s, tg_3s = 24.78 t/s 15.50.535.970 I slot print_timing: id 0 | task 19221 | prompt eval time = 733.71 ms / 489 tokens ( 1.50 ms per token, 666.48 tokens per second) 15.50.535.977 I slot print_timing: id 0 | task 19221 | eval time = 31470.37 ms / 720 tokens ( 43.77 ms per token, 22.85 tokens per second) 15.50.535.977 I slot print_timing: id 0 | task 19221 | total time = 32204.07 ms / 1209 tokens 15.50.535.978 I slot print_timing: id 0 | task 19221 | graphs reused = 18975 15.50.535.979 I slot print_timing: id 0 | task 19221 | graph reallocs = 0 / 0 (same size) / (changed size) 15.50.536.090 I slot release: id 0 | task 19221 | stop processing: n_tokens = 1884, truncated = 0 15.50.573.080 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.567 15.50.573.120 I slot launch_slot_: id 0 | task 19948 | processing task, is_child = 0 15.51.683.518 I slot print_timing: id 2 | task 19724 | n_gen = 234, tg = 23.24 t/s, tg_3s = 19.64 t/s 15.51.849.797 I slot print_timing: id 3 | task 19593 | n_gen = 367, tg = 21.85 t/s, tg_3s = 19.61 t/s 15.53.022.293 I slot print_timing: id 1 | task 19681 | n_gen = 309, tg = 22.40 t/s, tg_3s = 19.59 t/s 15.54.719.554 I slot print_timing: id 2 | task 19724 | n_gen = 309, tg = 23.58 t/s, tg_3s = 24.70 t/s 15.54.881.739 I slot print_timing: id 3 | task 19593 | n_gen = 442, tg = 22.29 t/s, tg_3s = 24.74 t/s 15.55.284.020 I slot print_timing: id 0 | task 19948 | n_gen = 100, tg = 24.76 t/s, tg_3s = 25.01 t/s 15.56.054.573 I slot print_timing: id 1 | task 19681 | n_gen = 384, tg = 22.82 t/s, tg_3s = 24.73 t/s 15.57.752.915 I slot print_timing: id 2 | task 19724 | n_gen = 384, tg = 23.79 t/s, tg_3s = 24.73 t/s 15.57.915.190 I slot print_timing: id 3 | task 19593 | n_gen = 517, tg = 22.62 t/s, tg_3s = 24.72 t/s 15.58.318.054 I slot print_timing: id 0 | task 19948 | n_gen = 175, tg = 24.74 t/s, tg_3s = 24.72 t/s 15.59.085.872 I slot print_timing: id 1 | task 19681 | n_gen = 459, tg = 23.11 t/s, tg_3s = 24.74 t/s 16.00.786.505 I slot print_timing: id 2 | task 19724 | n_gen = 459, tg = 23.94 t/s, tg_3s = 24.72 t/s 16.00.948.448 I slot print_timing: id 3 | task 19593 | n_gen = 592, tg = 22.86 t/s, tg_3s = 24.73 t/s 16.01.351.141 I slot print_timing: id 0 | task 19948 | n_gen = 250, tg = 24.74 t/s, tg_3s = 24.73 t/s 16.02.120.078 I slot print_timing: id 1 | task 19681 | n_gen = 534, tg = 23.33 t/s, tg_3s = 24.72 t/s 16.03.169.562 I slot print_timing: id 2 | task 19724 | prompt eval time = 759.04 ms / 496 tokens ( 1.53 ms per token, 653.45 tokens per second) 16.03.169.573 I slot print_timing: id 2 | task 19724 | eval time = 21513.19 ms / 518 tokens ( 41.61 ms per token, 24.03 tokens per second) 16.03.169.574 I slot print_timing: id 2 | task 19724 | total time = 22272.24 ms / 1014 tokens 16.03.169.575 I slot print_timing: id 2 | task 19724 | graphs reused = 19268 16.03.169.575 I slot print_timing: id 2 | task 19724 | graph reallocs = 0 / 0 (same size) / (changed size) 16.03.169.683 I slot release: id 2 | task 19724 | stop processing: n_tokens = 1709, truncated = 0 16.03.212.569 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.625 16.03.212.607 I slot launch_slot_: id 2 | task 20246 | processing task, is_child = 0 16.03.966.676 I slot print_timing: id 3 | task 19593 | n_gen = 650, tg = 22.48 t/s, tg_3s = 19.22 t/s 16.04.361.297 I slot print_timing: id 0 | task 19948 | n_gen = 308, tg = 23.48 t/s, tg_3s = 19.27 t/s 16.05.130.249 I slot print_timing: id 1 | task 19681 | n_gen = 592, tg = 22.86 t/s, tg_3s = 19.27 t/s 16.06.987.600 I slot print_timing: id 3 | task 19593 | n_gen = 725, tg = 22.70 t/s, tg_3s = 24.83 t/s 16.07.388.828 I slot print_timing: id 0 | task 19948 | n_gen = 383, tg = 23.72 t/s, tg_3s = 24.77 t/s 16.07.911.185 I slot print_timing: id 0 | task 19948 | prompt eval time = 712.33 ms / 476 tokens ( 1.50 ms per token, 668.23 tokens per second) 16.07.911.189 I slot print_timing: id 0 | task 19948 | eval time = 16625.73 ms / 396 tokens ( 42.09 ms per token, 23.76 tokens per second) 16.07.911.190 I slot print_timing: id 0 | task 19948 | total time = 17338.06 ms / 872 tokens 16.07.911.191 I slot print_timing: id 0 | task 19948 | graphs reused = 19365 16.07.911.192 I slot print_timing: id 0 | task 19948 | graph reallocs = 0 / 0 (same size) / (changed size) 16.07.911.290 I slot release: id 0 | task 19948 | stop processing: n_tokens = 1547, truncated = 0 16.07.947.347 I slot print_timing: id 2 | task 20246 | n_gen = 100, tg = 24.87 t/s, tg_3s = 25.12 t/s 16.07.947.918 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.690 16.07.947.953 I slot launch_slot_: id 0 | task 20348 | processing task, is_child = 0 16.08.591.116 I slot print_timing: id 1 | task 19681 | n_gen = 663, tg = 22.58 t/s, tg_3s = 20.52 t/s 16.09.993.118 I slot print_timing: id 3 | task 19593 | n_gen = 784, tg = 22.44 t/s, tg_3s = 19.63 t/s 16.10.959.245 I slot print_timing: id 2 | task 20246 | n_gen = 159, tg = 22.59 t/s, tg_3s = 19.59 t/s 16.11.604.382 I slot print_timing: id 1 | task 19681 | n_gen = 737, tg = 22.76 t/s, tg_3s = 24.56 t/s 16.12.655.544 I slot print_timing: id 0 | task 20348 | n_gen = 100, tg = 24.77 t/s, tg_3s = 25.02 t/s 16.13.022.052 I slot print_timing: id 3 | task 19593 | n_gen = 859, tg = 22.63 t/s, tg_3s = 24.76 t/s 16.13.995.477 I slot print_timing: id 2 | task 20246 | n_gen = 234, tg = 23.23 t/s, tg_3s = 24.70 t/s 16.14.644.239 I slot print_timing: id 1 | task 19681 | n_gen = 812, tg = 22.93 t/s, tg_3s = 24.67 t/s 16.15.657.704 I slot print_timing: id 0 | task 20348 | n_gen = 174, tg = 24.72 t/s, tg_3s = 24.65 t/s 16.16.024.749 I slot print_timing: id 3 | task 19593 | n_gen = 933, tg = 22.77 t/s, tg_3s = 24.64 t/s 16.16.997.802 I slot print_timing: id 2 | task 20246 | n_gen = 308, tg = 23.56 t/s, tg_3s = 24.65 t/s 16.17.647.652 I slot print_timing: id 1 | task 19681 | n_gen = 886, tg = 23.06 t/s, tg_3s = 24.64 t/s 16.17.769.514 I slot print_timing: id 1 | task 19681 | prompt eval time = 740.68 ms / 478 tokens ( 1.55 ms per token, 645.35 tokens per second) 16.17.769.522 I slot print_timing: id 1 | task 19681 | eval time = 38497.94 ms / 889 tokens ( 43.35 ms per token, 23.07 tokens per second) 16.17.769.523 I slot print_timing: id 1 | task 19681 | total time = 39238.62 ms / 1367 tokens 16.17.769.523 I slot print_timing: id 1 | task 19681 | graphs reused = 19589 16.17.769.524 I slot print_timing: id 1 | task 19681 | graph reallocs = 0 / 0 (same size) / (changed size) 16.17.769.636 I slot release: id 1 | task 19681 | stop processing: n_tokens = 2039, truncated = 0 16.17.813.247 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.524 16.17.813.284 I slot launch_slot_: id 1 | task 20577 | processing task, is_child = 0 16.18.660.074 I slot print_timing: id 0 | task 20348 | n_gen = 231, tg = 23.00 t/s, tg_3s = 18.98 t/s 16.19.027.570 I slot print_timing: id 3 | task 19593 | n_gen = 990, tg = 22.51 t/s, tg_3s = 18.98 t/s 16.20.004.473 I slot print_timing: id 2 | task 20246 | n_gen = 365, tg = 22.70 t/s, tg_3s = 18.96 t/s 16.20.410.719 I slot print_timing: id 3 | task 19593 | prompt eval time = 535.16 ms / 290 tokens ( 1.85 ms per token, 541.90 tokens per second) 16.20.410.727 I slot print_timing: id 3 | task 19593 | eval time = 45310.69 ms / 1024 tokens ( 44.29 ms per token, 22.58 tokens per second) 16.20.410.728 I slot print_timing: id 3 | task 19593 | total time = 45845.85 ms / 1314 tokens 16.20.410.729 I slot print_timing: id 3 | task 19593 | graphs reused = 19633 16.20.410.729 I slot print_timing: id 3 | task 19593 | graph reallocs = 0 / 0 (same size) / (changed size) 16.20.410.838 I slot release: id 3 | task 19593 | stop processing: n_tokens = 2237, truncated = 0 16.20.446.316 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.477 16.20.454.228 I slot launch_slot_: id 3 | task 20626 | processing task, is_child = 0 16.21.674.197 I slot print_timing: id 0 | task 20348 | n_gen = 289, tg = 22.13 t/s, tg_3s = 19.24 t/s 16.23.006.750 I slot print_timing: id 2 | task 20246 | n_gen = 423, tg = 22.16 t/s, tg_3s = 19.32 t/s 16.23.247.713 I slot print_timing: id 1 | task 20577 | n_gen = 100, tg = 21.21 t/s, tg_3s = 21.42 t/s 16.24.695.323 I slot print_timing: id 0 | task 20348 | n_gen = 364, tg = 22.64 t/s, tg_3s = 24.83 t/s 16.25.179.981 I slot print_timing: id 3 | task 20626 | n_gen = 100, tg = 24.84 t/s, tg_3s = 25.09 t/s 16.26.026.542 I slot print_timing: id 2 | task 20246 | n_gen = 498, tg = 22.53 t/s, tg_3s = 24.84 t/s 16.26.268.329 I slot print_timing: id 1 | task 20577 | n_gen = 175, tg = 22.63 t/s, tg_3s = 24.83 t/s 16.27.723.306 I slot print_timing: id 0 | task 20348 | n_gen = 439, tg = 22.98 t/s, tg_3s = 24.77 t/s 16.28.210.099 I slot print_timing: id 3 | task 20626 | n_gen = 175, tg = 24.80 t/s, tg_3s = 24.75 t/s 16.29.058.358 I slot print_timing: id 2 | task 20246 | n_gen = 573, tg = 22.80 t/s, tg_3s = 24.74 t/s 16.29.300.838 I slot print_timing: id 1 | task 20577 | n_gen = 250, tg = 23.23 t/s, tg_3s = 24.73 t/s 16.30.762.654 I slot print_timing: id 0 | task 20348 | n_gen = 514, tg = 23.21 t/s, tg_3s = 24.68 t/s 16.31.210.264 I slot print_timing: id 3 | task 20626 | n_gen = 249, tg = 24.76 t/s, tg_3s = 24.67 t/s 16.32.060.940 I slot print_timing: id 2 | task 20246 | n_gen = 647, tg = 22.99 t/s, tg_3s = 24.65 t/s 16.32.302.426 I slot print_timing: id 1 | task 20577 | n_gen = 324, tg = 23.54 t/s, tg_3s = 24.65 t/s 16.33.799.997 I slot print_timing: id 0 | task 20348 | n_gen = 589, tg = 23.39 t/s, tg_3s = 24.69 t/s 16.34.247.926 I slot print_timing: id 3 | task 20626 | n_gen = 324, tg = 24.75 t/s, tg_3s = 24.69 t/s 16.35.098.010 I slot print_timing: id 2 | task 20246 | n_gen = 722, tg = 23.16 t/s, tg_3s = 24.69 t/s 16.35.341.123 I slot print_timing: id 1 | task 20577 | n_gen = 399, tg = 23.75 t/s, tg_3s = 24.68 t/s 16.36.837.305 I slot print_timing: id 0 | task 20348 | n_gen = 664, tg = 23.53 t/s, tg_3s = 24.69 t/s 16.37.283.654 I slot print_timing: id 3 | task 20626 | n_gen = 399, tg = 24.74 t/s, tg_3s = 24.71 t/s 16.38.050.639 I slot print_timing: id 1 | task 20577 | prompt eval time = 766.66 ms / 501 tokens ( 1.53 ms per token, 653.48 tokens per second) 16.38.050.646 I slot print_timing: id 1 | task 20577 | eval time = 19470.68 ms / 466 tokens ( 41.87 ms per token, 23.88 tokens per second) 16.38.050.647 I slot print_timing: id 1 | task 20577 | total time = 20237.34 ms / 967 tokens 16.38.050.648 I slot print_timing: id 1 | task 20577 | graphs reused = 20048 16.38.050.648 I slot print_timing: id 1 | task 20577 | graph reallocs = 0 / 0 (same size) / (changed size) 16.38.050.752 I slot release: id 1 | task 20577 | stop processing: n_tokens = 1639, truncated = 0 16.38.094.398 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.652 16.38.094.428 I slot launch_slot_: id 1 | task 21047 | processing task, is_child = 0 16.38.748.222 I slot print_timing: id 2 | task 20246 | n_gen = 797, tg = 22.89 t/s, tg_3s = 20.55 t/s 16.39.838.597 I slot print_timing: id 0 | task 20348 | n_gen = 722, tg = 23.12 t/s, tg_3s = 19.33 t/s 16.40.324.039 I slot print_timing: id 3 | task 20626 | n_gen = 458, tg = 23.89 t/s, tg_3s = 19.41 t/s 16.41.780.591 I slot print_timing: id 2 | task 20246 | n_gen = 871, tg = 23.01 t/s, tg_3s = 24.40 t/s 16.42.670.900 I slot print_timing: id 2 | task 20246 | prompt eval time = 753.76 ms / 486 tokens ( 1.55 ms per token, 644.77 tokens per second) 16.42.670.914 I slot print_timing: id 2 | task 20246 | eval time = 38704.52 ms / 893 tokens ( 43.39 ms per token, 23.05 tokens per second) 16.42.670.916 I slot print_timing: id 2 | task 20246 | total time = 39458.28 ms / 1379 tokens 16.42.670.920 I slot print_timing: id 2 | task 20246 | graphs reused = 20141 16.42.670.920 I slot print_timing: id 2 | task 20246 | graph reallocs = 0 / 0 (same size) / (changed size) 16.42.671.028 I slot release: id 2 | task 20246 | stop processing: n_tokens = 2074, truncated = 0 16.42.714.112 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.515 16.42.714.146 I slot launch_slot_: id 2 | task 21146 | processing task, is_child = 0 16.43.361.041 I slot print_timing: id 0 | task 20348 | n_gen = 794, tg = 22.85 t/s, tg_3s = 20.44 t/s 16.43.361.588 I slot print_timing: id 3 | task 20626 | n_gen = 518, tg = 23.32 t/s, tg_3s = 19.75 t/s 16.43.478.660 I slot print_timing: id 1 | task 21047 | n_gen = 100, tg = 21.28 t/s, tg_3s = 21.49 t/s 16.46.389.431 I slot print_timing: id 0 | task 20348 | n_gen = 868, tg = 22.98 t/s, tg_3s = 24.44 t/s 16.46.391.137 I slot print_timing: id 3 | task 20626 | n_gen = 592, tg = 23.46 t/s, tg_3s = 24.43 t/s 16.46.511.501 I slot print_timing: id 1 | task 21047 | n_gen = 175, tg = 22.64 t/s, tg_3s = 24.73 t/s 16.47.441.125 I slot print_timing: id 2 | task 21146 | n_gen = 100, tg = 24.73 t/s, tg_3s = 24.98 t/s 16.49.428.298 I slot print_timing: id 0 | task 20348 | n_gen = 943, tg = 23.11 t/s, tg_3s = 24.68 t/s 16.49.429.905 I slot print_timing: id 3 | task 20626 | n_gen = 667, tg = 23.59 t/s, tg_3s = 24.68 t/s 16.49.550.730 I slot print_timing: id 1 | task 21047 | n_gen = 250, tg = 23.22 t/s, tg_3s = 24.68 t/s 16.50.443.961 I slot print_timing: id 2 | task 21146 | n_gen = 174, tg = 24.69 t/s, tg_3s = 24.64 t/s 16.52.433.633 I slot print_timing: id 0 | task 20348 | n_gen = 1017, tg = 23.21 t/s, tg_3s = 24.62 t/s 16.52.435.309 I slot print_timing: id 3 | task 20626 | n_gen = 741, tg = 23.69 t/s, tg_3s = 24.62 t/s 16.52.555.518 I slot print_timing: id 1 | task 21047 | n_gen = 324, tg = 23.53 t/s, tg_3s = 24.63 t/s 16.52.716.946 I slot print_timing: id 0 | task 20348 | prompt eval time = 711.56 ms / 476 tokens ( 1.49 ms per token, 668.96 tokens per second) 16.52.716.950 I slot print_timing: id 0 | task 20348 | eval time = 44057.43 ms / 1024 tokens ( 43.07 ms per token, 23.22 tokens per second) 16.52.716.951 I slot print_timing: id 0 | task 20348 | total time = 44768.98 ms / 1500 tokens 16.52.716.952 I slot print_timing: id 0 | task 20348 | graphs reused = 20368 16.52.716.953 I slot print_timing: id 0 | task 20348 | graph reallocs = 0 / 0 (same size) / (changed size) 16.52.717.049 I slot release: id 0 | task 20348 | stop processing: n_tokens = 2175, truncated = 0 16.52.753.649 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.491 16.52.755.762 I slot launch_slot_: id 0 | task 21379 | processing task, is_child = 0 16.53.463.006 I slot print_timing: id 2 | task 21146 | n_gen = 233, tg = 23.14 t/s, tg_3s = 19.54 t/s 16.55.158.307 I slot print_timing: id 1 | task 21047 | prompt eval time = 731.85 ms / 466 tokens ( 1.57 ms per token, 636.75 tokens per second) 16.55.158.322 I slot print_timing: id 1 | task 21047 | eval time = 16332.02 ms / 373 tokens ( 43.90 ms per token, 22.78 tokens per second) 16.55.158.324 I slot print_timing: id 1 | task 21047 | total time = 17063.87 ms / 839 tokens 16.55.158.324 I slot print_timing: id 1 | task 21047 | graphs reused = 20410 16.55.158.325 I slot print_timing: id 1 | task 21047 | graph reallocs = 0 / 0 (same size) / (changed size) 16.55.158.437 I slot release: id 1 | task 21047 | stop processing: n_tokens = 1511, truncated = 0 16.55.201.701 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.707 16.55.201.734 I slot launch_slot_: id 1 | task 21425 | processing task, is_child = 0 16.55.862.546 I slot print_timing: id 3 | task 20626 | n_gen = 795, tg = 22.90 t/s, tg_3s = 15.76 t/s 16.56.499.384 I slot print_timing: id 2 | task 21146 | n_gen = 292, tg = 22.28 t/s, tg_3s = 19.43 t/s 16.58.112.909 I slot print_timing: id 0 | task 21379 | n_gen = 100, tg = 21.29 t/s, tg_3s = 21.50 t/s 16.58.882.627 I slot print_timing: id 3 | task 20626 | n_gen = 869, tg = 23.03 t/s, tg_3s = 24.50 t/s 16.59.286.746 I slot print_timing: id 3 | task 20626 | prompt eval time = 740.55 ms / 486 tokens ( 1.52 ms per token, 656.27 tokens per second) 16.59.286.752 I slot print_timing: id 3 | task 20626 | eval time = 38091.95 ms / 879 tokens ( 43.38 ms per token, 23.05 tokens per second) 16.59.286.753 I slot print_timing: id 3 | task 20626 | total time = 38832.51 ms / 1365 tokens 16.59.286.753 I slot print_timing: id 3 | task 20626 | graphs reused = 20492 16.59.286.754 I slot print_timing: id 3 | task 20626 | graph reallocs = 0 / 0 (same size) / (changed size) 16.59.286.853 I slot release: id 3 | task 20626 | stop processing: n_tokens = 2037, truncated = 0 16.59.322.081 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.524 16.59.322.117 I slot launch_slot_: id 3 | task 21512 | processing task, is_child = 0 17.00.187.562 I slot print_timing: id 2 | task 21146 | n_gen = 364, tg = 21.67 t/s, tg_3s = 19.52 t/s 17.00.742.271 I slot print_timing: id 1 | task 21425 | n_gen = 100, tg = 20.61 t/s, tg_3s = 20.82 t/s 17.01.148.417 I slot print_timing: id 0 | task 21379 | n_gen = 155, tg = 20.04 t/s, tg_3s = 18.12 t/s 17.03.206.578 I slot print_timing: id 2 | task 21146 | n_gen = 438, tg = 22.11 t/s, tg_3s = 24.51 t/s 17.03.770.196 I slot print_timing: id 1 | task 21425 | n_gen = 175, tg = 22.22 t/s, tg_3s = 24.77 t/s 17.04.172.654 I slot print_timing: id 0 | task 21379 | n_gen = 230, tg = 21.38 t/s, tg_3s = 24.80 t/s 17.04.255.167 I slot print_timing: id 3 | task 21512 | n_gen = 100, tg = 24.77 t/s, tg_3s = 25.02 t/s 17.06.235.660 I slot print_timing: id 2 | task 21146 | n_gen = 513, tg = 22.46 t/s, tg_3s = 24.76 t/s 17.06.800.427 I slot print_timing: id 1 | task 21425 | n_gen = 250, tg = 22.93 t/s, tg_3s = 24.75 t/s 17.07.203.879 I slot print_timing: id 0 | task 21379 | n_gen = 305, tg = 22.12 t/s, tg_3s = 24.74 t/s 17.07.286.545 I slot print_timing: id 3 | task 21512 | n_gen = 175, tg = 24.75 t/s, tg_3s = 24.74 t/s 17.09.265.015 I slot print_timing: id 2 | task 21146 | n_gen = 588, tg = 22.73 t/s, tg_3s = 24.76 t/s 17.09.831.593 I slot print_timing: id 1 | task 21425 | n_gen = 325, tg = 23.32 t/s, tg_3s = 24.74 t/s 17.10.235.113 I slot print_timing: id 0 | task 21379 | n_gen = 380, tg = 22.60 t/s, tg_3s = 24.74 t/s 17.10.317.308 I slot print_timing: id 3 | task 21512 | n_gen = 250, tg = 24.75 t/s, tg_3s = 24.75 t/s 17.12.296.564 I slot print_timing: id 2 | task 21146 | n_gen = 663, tg = 22.94 t/s, tg_3s = 24.74 t/s 17.12.861.847 I slot print_timing: id 1 | task 21425 | n_gen = 400, tg = 23.58 t/s, tg_3s = 24.75 t/s 17.13.265.383 I slot print_timing: id 0 | task 21379 | n_gen = 455, tg = 22.93 t/s, tg_3s = 24.75 t/s 17.13.347.892 I slot print_timing: id 3 | task 21512 | n_gen = 325, tg = 24.75 t/s, tg_3s = 24.75 t/s 17.15.328.440 I slot print_timing: id 2 | task 21146 | n_gen = 738, tg = 23.11 t/s, tg_3s = 24.74 t/s 17.15.895.075 I slot print_timing: id 1 | task 21425 | n_gen = 475, tg = 23.75 t/s, tg_3s = 24.73 t/s 17.16.301.288 I slot print_timing: id 0 | task 21379 | n_gen = 530, tg = 23.16 t/s, tg_3s = 24.70 t/s 17.16.384.559 I slot print_timing: id 3 | task 21512 | n_gen = 400, tg = 24.74 t/s, tg_3s = 24.70 t/s 17.18.334.939 I slot print_timing: id 2 | task 21146 | n_gen = 812, tg = 23.24 t/s, tg_3s = 24.61 t/s 17.18.904.441 I slot print_timing: id 1 | task 21425 | n_gen = 549, tg = 23.86 t/s, tg_3s = 24.59 t/s 17.19.309.762 I slot print_timing: id 0 | task 21379 | n_gen = 604, tg = 23.33 t/s, tg_3s = 24.60 t/s 17.19.392.964 I slot print_timing: id 3 | task 21512 | n_gen = 474, tg = 24.72 t/s, tg_3s = 24.60 t/s 17.21.341.178 I slot print_timing: id 2 | task 21146 | n_gen = 886, tg = 23.35 t/s, tg_3s = 24.62 t/s 17.21.912.182 I slot print_timing: id 1 | task 21425 | n_gen = 623, tg = 23.95 t/s, tg_3s = 24.60 t/s 17.22.318.255 I slot print_timing: id 0 | task 21379 | n_gen = 678, tg = 23.46 t/s, tg_3s = 24.60 t/s 17.22.401.127 I slot print_timing: id 3 | task 21512 | n_gen = 548, tg = 24.70 t/s, tg_3s = 24.60 t/s 17.24.005.231 I slot print_timing: id 1 | task 21425 | prompt eval time = 738.13 ms / 477 tokens ( 1.55 ms per token, 646.22 tokens per second) 17.24.005.238 I slot print_timing: id 1 | task 21425 | eval time = 28065.35 ms / 673 tokens ( 41.76 ms per token, 23.94 tokens per second) 17.24.005.240 I slot print_timing: id 1 | task 21425 | total time = 28803.48 ms / 1150 tokens 17.24.005.241 I slot print_timing: id 1 | task 21425 | graphs reused = 21073 17.24.005.242 I slot print_timing: id 1 | task 21425 | graph reallocs = 0 / 0 (same size) / (changed size) 17.24.005.393 I slot release: id 1 | task 21425 | stop processing: n_tokens = 1822, truncated = 0 17.24.061.502 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.586 17.24.061.552 I slot launch_slot_: id 1 | task 22102 | processing task, is_child = 0 17.24.762.303 I slot print_timing: id 2 | task 21146 | n_gen = 952, tg = 23.01 t/s, tg_3s = 19.29 t/s 17.25.333.855 I slot print_timing: id 0 | task 21379 | n_gen = 733, tg = 22.97 t/s, tg_3s = 18.24 t/s 17.25.417.030 I slot print_timing: id 3 | task 21512 | n_gen = 603, tg = 23.93 t/s, tg_3s = 18.24 t/s 17.26.025.861 I slot print_timing: id 0 | task 21379 | prompt eval time = 706.70 ms / 467 tokens ( 1.51 ms per token, 660.82 tokens per second) 17.26.025.866 I slot print_timing: id 0 | task 21379 | eval time = 32563.38 ms / 750 tokens ( 43.48 ms per token, 23.00 tokens per second) 17.26.025.867 I slot print_timing: id 0 | task 21379 | total time = 33270.09 ms / 1217 tokens 17.26.025.868 I slot print_timing: id 0 | task 21379 | graphs reused = 21101 17.26.025.869 I slot print_timing: id 0 | task 21379 | graph reallocs = 0 / 0 (same size) / (changed size) 17.26.025.974 I slot release: id 0 | task 21379 | stop processing: n_tokens = 1892, truncated = 0 17.26.063.247 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.564 17.26.063.289 I slot launch_slot_: id 0 | task 22135 | processing task, is_child = 0 17.27.772.631 I slot print_timing: id 2 | task 21146 | n_gen = 1009, tg = 22.74 t/s, tg_3s = 18.93 t/s 17.28.384.422 I slot print_timing: id 2 | task 21146 | prompt eval time = 723.79 ms / 458 tokens ( 1.58 ms per token, 632.78 tokens per second) 17.28.384.430 I slot print_timing: id 2 | task 21146 | eval time = 44946.48 ms / 1024 tokens ( 43.94 ms per token, 22.76 tokens per second) 17.28.384.432 I slot print_timing: id 2 | task 21146 | total time = 45670.26 ms / 1482 tokens 17.28.384.433 I slot print_timing: id 2 | task 21146 | graphs reused = 21140 17.28.384.434 I slot print_timing: id 2 | task 21146 | graph reallocs = 0 / 0 (same size) / (changed size) 17.28.384.539 I slot release: id 2 | task 21146 | stop processing: n_tokens = 2177, truncated = 0 17.28.427.696 I slot print_timing: id 3 | task 21512 | n_gen = 661, tg = 23.43 t/s, tg_3s = 19.26 t/s 17.28.427.707 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.491 17.28.434.154 I slot launch_slot_: id 2 | task 22178 | processing task, is_child = 0 17.30.147.308 I slot print_timing: id 1 | task 22102 | n_gen = 100, tg = 18.65 t/s, tg_3s = 18.84 t/s 17.31.432.993 I slot print_timing: id 0 | task 22135 | n_gen = 100, tg = 21.36 t/s, tg_3s = 21.58 t/s 17.31.434.543 I slot print_timing: id 3 | task 21512 | n_gen = 720, tg = 23.06 t/s, tg_3s = 19.62 t/s 17.32.035.731 I slot print_timing: id 3 | task 21512 | prompt eval time = 935.51 ms / 538 tokens ( 1.74 ms per token, 575.09 tokens per second) 17.32.035.739 I slot print_timing: id 3 | task 21512 | eval time = 31778.09 ms / 735 tokens ( 43.29 ms per token, 23.10 tokens per second) 17.32.035.742 I slot print_timing: id 3 | task 21512 | total time = 32713.60 ms / 1273 tokens 17.32.035.742 I slot print_timing: id 3 | task 21512 | graphs reused = 21211 17.32.035.743 I slot print_timing: id 3 | task 21512 | graph reallocs = 0 / 0 (same size) / (changed size) 17.32.035.852 I slot release: id 3 | task 21512 | stop processing: n_tokens = 1945, truncated = 0 17.32.071.051 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.549 17.32.071.084 I slot launch_slot_: id 3 | task 22254 | processing task, is_child = 0 17.33.179.709 I slot print_timing: id 1 | task 22102 | n_gen = 159, tg = 18.95 t/s, tg_3s = 19.46 t/s 17.33.785.216 I slot print_timing: id 2 | task 22178 | n_gen = 100, tg = 21.29 t/s, tg_3s = 21.50 t/s 17.34.470.362 I slot print_timing: id 0 | task 22135 | n_gen = 159, tg = 20.59 t/s, tg_3s = 19.42 t/s 17.36.203.006 I slot print_timing: id 1 | task 22102 | n_gen = 234, tg = 20.51 t/s, tg_3s = 24.81 t/s 17.36.809.617 I slot print_timing: id 2 | task 22178 | n_gen = 175, tg = 22.67 t/s, tg_3s = 24.80 t/s 17.36.810.179 I slot print_timing: id 3 | task 22254 | n_gen = 100, tg = 24.79 t/s, tg_3s = 25.04 t/s 17.37.456.463 I slot print_timing: id 2 | task 22178 | prompt eval time = 699.91 ms / 442 tokens ( 1.58 ms per token, 631.51 tokens per second) 17.37.456.469 I slot print_timing: id 2 | task 22178 | eval time = 8322.39 ms / 191 tokens ( 43.80 ms per token, 22.83 tokens per second) 17.37.456.470 I slot print_timing: id 2 | task 22178 | total time = 9022.30 ms / 633 tokens 17.37.456.471 I slot print_timing: id 2 | task 22178 | graphs reused = 21325 17.37.456.472 I slot print_timing: id 2 | task 22178 | graph reallocs = 0 / 0 (same size) / (changed size) 17.37.456.581 I slot release: id 2 | task 22178 | stop processing: n_tokens = 1328, truncated = 0 17.37.498.375 I slot print_timing: id 0 | task 22135 | n_gen = 234, tg = 21.78 t/s, tg_3s = 24.77 t/s 17.37.499.651 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.805 17.37.499.685 I slot launch_slot_: id 2 | task 22373 | processing task, is_child = 0 17.39.205.728 I slot print_timing: id 1 | task 22102 | n_gen = 293, tg = 20.33 t/s, tg_3s = 19.65 t/s 17.39.811.291 I slot print_timing: id 3 | task 22254 | n_gen = 159, tg = 22.59 t/s, tg_3s = 19.66 t/s 17.40.536.328 I slot print_timing: id 0 | task 22135 | n_gen = 294, tg = 21.33 t/s, tg_3s = 19.75 t/s 17.42.190.524 I slot print_timing: id 2 | task 22373 | n_gen = 100, tg = 24.82 t/s, tg_3s = 25.07 t/s 17.42.230.250 I slot print_timing: id 1 | task 22102 | n_gen = 368, tg = 21.10 t/s, tg_3s = 24.80 t/s 17.42.838.715 I slot print_timing: id 3 | task 22254 | n_gen = 234, tg = 23.25 t/s, tg_3s = 24.77 t/s 17.43.563.793 I slot print_timing: id 0 | task 22135 | n_gen = 369, tg = 21.95 t/s, tg_3s = 24.77 t/s 17.44.128.419 I slot print_timing: id 0 | task 22135 | prompt eval time = 735.15 ms / 492 tokens ( 1.49 ms per token, 669.25 tokens per second) 17.44.128.426 I slot print_timing: id 0 | task 22135 | eval time = 17329.98 ms / 383 tokens ( 45.37 ms per token, 22.04 tokens per second) 17.44.128.427 I slot print_timing: id 0 | task 22135 | total time = 18065.12 ms / 875 tokens 17.44.128.428 I slot print_timing: id 0 | task 22135 | graphs reused = 21470 17.44.128.429 I slot print_timing: id 0 | task 22135 | graph reallocs = 0 / 0 (same size) / (changed size) 17.44.128.532 I slot release: id 0 | task 22135 | stop processing: n_tokens = 1550, truncated = 0 17.44.556.641 I slot print_timing: id 1 | task 22102 | prompt eval time = 778.72 ms / 482 tokens ( 1.62 ms per token, 618.96 tokens per second) 17.44.556.647 I slot print_timing: id 1 | task 22102 | eval time = 19716.36 ms / 428 tokens ( 46.17 ms per token, 21.66 tokens per second) 17.44.556.648 I slot print_timing: id 1 | task 22102 | total time = 20495.08 ms / 910 tokens 17.44.556.649 I slot print_timing: id 1 | task 22102 | graphs reused = 21482 17.44.556.649 I slot print_timing: id 1 | task 22102 | graph reallocs = 0 / 0 (same size) / (changed size) 17.44.556.732 I slot release: id 1 | task 22102 | stop processing: n_tokens = 1582, truncated = 0 17.45.200.796 I slot print_timing: id 2 | task 22373 | n_gen = 187, tg = 26.58 t/s, tg_3s = 28.90 t/s 17.45.840.621 I slot print_timing: id 3 | task 22254 | n_gen = 331, tg = 25.34 t/s, tg_3s = 32.31 t/s 17.48.203.494 I slot print_timing: id 2 | task 22373 | n_gen = 309, tg = 30.80 t/s, tg_3s = 40.63 t/s 17.48.645.620 I slot print_timing: id 2 | task 22373 | prompt eval time = 702.24 ms / 443 tokens ( 1.59 ms per token, 630.84 tokens per second) 17.48.645.626 I slot print_timing: id 2 | task 22373 | eval time = 10443.69 ms / 327 tokens ( 32.04 ms per token, 31.22 tokens per second) 17.48.645.627 I slot print_timing: id 2 | task 22373 | total time = 11145.93 ms / 770 tokens 17.48.645.627 I slot print_timing: id 2 | task 22373 | graphs reused = 21646 17.48.645.628 I slot print_timing: id 2 | task 22373 | graph reallocs = 0 / 0 (same size) / (changed size) 17.48.645.704 I slot release: id 2 | task 22373 | stop processing: n_tokens = 1465, truncated = 0 17.48.845.053 I slot print_timing: id 3 | task 22254 | n_gen = 459, tg = 28.57 t/s, tg_3s = 42.60 t/s 17.48.873.081 I slot print_timing: id 3 | task 22254 | prompt eval time = 745.52 ms / 492 tokens ( 1.52 ms per token, 659.94 tokens per second) 17.48.873.084 I slot print_timing: id 3 | task 22254 | eval time = 16056.47 ms / 461 tokens ( 34.91 ms per token, 28.65 tokens per second) 17.48.873.085 I slot print_timing: id 3 | task 22254 | total time = 16801.99 ms / 953 tokens 17.48.873.086 I slot print_timing: id 3 | task 22254 | graphs reused = 21661 17.48.873.086 I slot print_timing: id 3 | task 22254 | graph reallocs = 0 / 0 (same size) / (changed size) 17.48.873.155 I slot release: id 3 | task 22254 | stop processing: n_tokens = 1647, truncated = 0 17.48.888.720 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1550, t_last = 341152727014 17.48.891.936 I slot launch_slot_: id 0 | task 22718 | processing task, is_child = 0 17.48.901.015 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1582, t_last = 341153155214 17.48.901.129 I slot launch_slot_: id 1 | task 22719 | processing task, is_child = 0 17.48.901.294 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1465, t_last = 341157244186 17.48.901.400 I slot launch_slot_: id 2 | task 22720 | processing task, is_child = 0 17.48.901.489 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1647, t_last = 341157471637 17.48.901.594 I slot launch_slot_: id 3 | task 22721 | processing task, is_child = 0 17.52.839.500 I slot print_timing: id 0 | task 22718 | prompt processing, n_tokens = 754, progress = 0.99, t = 3.94 s / 191.47 tokens per second 17.53.488.876 I slot print_timing: id 1 | task 22719 | prompt processing, n_tokens = 942, progress = 1.00, t = 3.94 s / 239.22 tokens per second 17.53.489.052 I slot print_timing: id 2 | task 22720 | prompt processing, n_tokens = 760, progress = 0.99, t = 3.94 s / 193.01 tokens per second 17.53.489.197 I slot print_timing: id 3 | task 22721 | prompt processing, n_tokens = 940, progress = 1.00, t = 3.94 s / 238.73 tokens per second 17.53.642.417 I slot print_timing: id 0 | task 22718 | prompt eval time = 4700.55 ms / 758 tokens ( 6.20 ms per token, 161.26 tokens per second) 17.53.642.420 I slot print_timing: id 0 | task 22718 | eval time = 40.27 ms / 2 tokens ( 40.27 ms per token, 24.83 tokens per second) 17.53.642.429 I slot print_timing: id 0 | task 22718 | total time = 4740.81 ms / 760 tokens 17.53.642.430 I slot print_timing: id 0 | task 22718 | graphs reused = 21663 17.53.642.430 I slot print_timing: id 0 | task 22718 | graph reallocs = 0 / 0 (same size) / (changed size) 17.53.642.481 I slot release: id 0 | task 22718 | stop processing: n_tokens = 759, truncated = 0 17.53.642.783 I slot print_timing: id 1 | task 22719 | prompt eval time = 4700.72 ms / 946 tokens ( 4.97 ms per token, 201.25 tokens per second) 17.53.642.784 I slot print_timing: id 1 | task 22719 | eval time = 40.33 ms / 2 tokens ( 40.33 ms per token, 24.79 tokens per second) 17.53.642.785 I slot print_timing: id 1 | task 22719 | total time = 4741.05 ms / 948 tokens 17.53.642.785 I slot print_timing: id 1 | task 22719 | graphs reused = 21663 17.53.642.786 I slot print_timing: id 1 | task 22719 | graph reallocs = 0 / 0 (same size) / (changed size) 17.53.642.833 I slot release: id 1 | task 22719 | stop processing: n_tokens = 947, truncated = 0 17.53.643.130 I slot print_timing: id 2 | task 22720 | prompt eval time = 4700.92 ms / 764 tokens ( 6.15 ms per token, 162.52 tokens per second) 17.53.643.133 I slot print_timing: id 2 | task 22720 | eval time = 40.36 ms / 2 tokens ( 40.36 ms per token, 24.78 tokens per second) 17.53.643.133 I slot print_timing: id 2 | task 22720 | total time = 4741.28 ms / 766 tokens 17.53.643.133 I slot print_timing: id 2 | task 22720 | graphs reused = 21663 17.53.643.133 I slot print_timing: id 2 | task 22720 | graph reallocs = 0 / 0 (same size) / (changed size) 17.53.643.168 I slot release: id 2 | task 22720 | stop processing: n_tokens = 765, truncated = 0 17.53.643.460 I slot print_timing: id 3 | task 22721 | prompt eval time = 4701.15 ms / 944 tokens ( 4.98 ms per token, 200.80 tokens per second) 17.53.643.462 I slot print_timing: id 3 | task 22721 | eval time = 40.35 ms / 2 tokens ( 40.35 ms per token, 24.78 tokens per second) 17.53.643.462 I slot print_timing: id 3 | task 22721 | total time = 4741.50 ms / 946 tokens 17.53.643.463 I slot print_timing: id 3 | task 22721 | graphs reused = 21663 17.53.643.463 I slot print_timing: id 3 | task 22721 | graph reallocs = 0 / 0 (same size) / (changed size) 17.53.643.505 I slot release: id 3 | task 22721 | stop processing: n_tokens = 945, truncated = 0 17.53.649.770 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 759, t_last = 341162240963 17.53.651.215 I slot launch_slot_: id 0 | task 22726 | processing task, is_child = 0 17.53.656.256 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 947, t_last = 341162241315 17.53.656.323 I slot launch_slot_: id 1 | task 22727 | processing task, is_child = 0 17.53.656.410 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 765, t_last = 341162241650 17.53.656.468 I slot launch_slot_: id 2 | task 22728 | processing task, is_child = 0 17.53.656.513 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 945, t_last = 341162241987 17.53.656.576 I slot launch_slot_: id 3 | task 22729 | processing task, is_child = 0 17.57.291.661 I slot print_timing: id 0 | task 22726 | prompt processing, n_tokens = 768, progress = 0.99, t = 3.64 s / 211.28 tokens per second 17.57.937.969 I slot print_timing: id 1 | task 22727 | prompt processing, n_tokens = 816, progress = 1.00, t = 3.64 s / 224.48 tokens per second 17.57.938.128 I slot print_timing: id 2 | task 22728 | prompt processing, n_tokens = 772, progress = 0.99, t = 3.63 s / 212.38 tokens per second 17.57.938.274 I slot print_timing: id 3 | task 22729 | prompt processing, n_tokens = 821, progress = 1.00, t = 3.63 s / 225.87 tokens per second 17.58.091.567 I slot print_timing: id 0 | task 22726 | prompt eval time = 4394.30 ms / 772 tokens ( 5.69 ms per token, 175.68 tokens per second) 17.58.091.569 I slot print_timing: id 0 | task 22726 | eval time = 40.68 ms / 2 tokens ( 40.68 ms per token, 24.58 tokens per second) 17.58.091.570 I slot print_timing: id 0 | task 22726 | total time = 4434.98 ms / 774 tokens 17.58.091.570 I slot print_timing: id 0 | task 22726 | graphs reused = 21664 17.58.091.571 I slot print_timing: id 0 | task 22726 | graph reallocs = 0 / 0 (same size) / (changed size) 17.58.091.619 I slot release: id 0 | task 22726 | stop processing: n_tokens = 773, truncated = 0 17.58.091.892 I slot print_timing: id 1 | task 22727 | prompt eval time = 4394.53 ms / 820 tokens ( 5.36 ms per token, 186.60 tokens per second) 17.58.091.896 I slot print_timing: id 1 | task 22727 | eval time = 40.72 ms / 2 tokens ( 40.72 ms per token, 24.56 tokens per second) 17.58.091.896 I slot print_timing: id 1 | task 22727 | total time = 4435.25 ms / 822 tokens 17.58.091.896 I slot print_timing: id 1 | task 22727 | graphs reused = 21664 17.58.091.897 I slot print_timing: id 1 | task 22727 | graph reallocs = 0 / 0 (same size) / (changed size) 17.58.091.933 I slot release: id 1 | task 22727 | stop processing: n_tokens = 821, truncated = 0 17.58.092.205 I slot print_timing: id 2 | task 22728 | prompt eval time = 4394.74 ms / 776 tokens ( 5.66 ms per token, 176.57 tokens per second) 17.58.092.210 I slot print_timing: id 2 | task 22728 | eval time = 40.76 ms / 2 tokens ( 40.76 ms per token, 24.54 tokens per second) 17.58.092.210 I slot print_timing: id 2 | task 22728 | total time = 4435.50 ms / 778 tokens 17.58.092.211 I slot print_timing: id 2 | task 22728 | graphs reused = 21664 17.58.092.211 I slot print_timing: id 2 | task 22728 | graph reallocs = 0 / 0 (same size) / (changed size) 17.58.092.243 I slot release: id 2 | task 22728 | stop processing: n_tokens = 777, truncated = 0 17.58.092.530 I slot print_timing: id 3 | task 22729 | prompt eval time = 4395.08 ms / 825 tokens ( 5.33 ms per token, 187.71 tokens per second) 17.58.092.533 I slot print_timing: id 3 | task 22729 | eval time = 40.69 ms / 2 tokens ( 40.69 ms per token, 24.58 tokens per second) 17.58.092.533 I slot print_timing: id 3 | task 22729 | total time = 4435.77 ms / 827 tokens 17.58.092.533 I slot print_timing: id 3 | task 22729 | graphs reused = 21664 17.58.092.533 I slot print_timing: id 3 | task 22729 | graph reallocs = 0 / 0 (same size) / (changed size) 17.58.092.566 I slot release: id 3 | task 22729 | stop processing: n_tokens = 826, truncated = 0 17.58.099.790 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 341166690101 17.58.101.408 I slot launch_slot_: id 0 | task 22734 | processing task, is_child = 0 17.58.105.775 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.850 17.58.105.794 I slot launch_slot_: id 1 | task 22735 | processing task, is_child = 0 17.58.105.875 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 777, t_last = 341166690725 17.58.105.935 I slot launch_slot_: id 2 | task 22736 | processing task, is_child = 0 17.58.105.981 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 341166691048 17.58.106.041 I slot launch_slot_: id 3 | task 22737 | processing task, is_child = 0 18.02.546.771 I slot print_timing: id 0 | task 22734 | prompt processing, n_tokens = 927, progress = 1.00, t = 4.44 s / 208.76 tokens per second 18.02.546.944 I slot print_timing: id 2 | task 22736 | prompt processing, n_tokens = 852, progress = 1.00, t = 4.44 s / 191.88 tokens per second 18.02.547.091 I slot print_timing: id 3 | task 22737 | prompt processing, n_tokens = 845, progress = 1.00, t = 4.44 s / 190.31 tokens per second 18.02.661.247 I slot print_timing: id 1 | task 22735 | prompt eval time = 4440.66 ms / 493 tokens ( 9.01 ms per token, 111.02 tokens per second) 18.02.661.249 I slot print_timing: id 1 | task 22735 | eval time = 114.49 ms / 2 tokens ( 114.49 ms per token, 8.73 tokens per second) 18.02.661.250 I slot print_timing: id 1 | task 22735 | total time = 4555.15 ms / 495 tokens 18.02.661.251 I slot print_timing: id 1 | task 22735 | graphs reused = 21664 18.02.661.251 I slot print_timing: id 1 | task 22735 | graph reallocs = 0 / 0 (same size) / (changed size) 18.02.661.296 I slot release: id 1 | task 22735 | stop processing: n_tokens = 798, truncated = 0 18.02.701.092 I slot print_timing: id 0 | task 22734 | prompt eval time = 4554.91 ms / 931 tokens ( 4.89 ms per token, 204.39 tokens per second) 18.02.701.094 I slot print_timing: id 0 | task 22734 | eval time = 40.13 ms / 2 tokens ( 40.13 ms per token, 24.92 tokens per second) 18.02.701.095 I slot print_timing: id 0 | task 22734 | total time = 4595.04 ms / 933 tokens 18.02.701.095 I slot print_timing: id 0 | task 22734 | graphs reused = 21664 18.02.701.096 I slot print_timing: id 0 | task 22734 | graph reallocs = 0 / 0 (same size) / (changed size) 18.02.701.146 I slot release: id 0 | task 22734 | stop processing: n_tokens = 932, truncated = 0 18.02.701.425 I slot print_timing: id 2 | task 22736 | prompt eval time = 4555.37 ms / 856 tokens ( 5.32 ms per token, 187.91 tokens per second) 18.02.701.428 I slot print_timing: id 2 | task 22736 | eval time = 39.82 ms / 2 tokens ( 39.82 ms per token, 25.11 tokens per second) 18.02.701.428 I slot print_timing: id 2 | task 22736 | total time = 4595.20 ms / 858 tokens 18.02.701.428 I slot print_timing: id 2 | task 22736 | graphs reused = 21664 18.02.701.429 I slot print_timing: id 2 | task 22736 | graph reallocs = 0 / 0 (same size) / (changed size) 18.02.701.470 I slot release: id 2 | task 22736 | stop processing: n_tokens = 857, truncated = 0 18.02.701.772 I slot print_timing: id 3 | task 22737 | prompt eval time = 4555.65 ms / 849 tokens ( 5.37 ms per token, 186.36 tokens per second) 18.02.701.774 I slot print_timing: id 3 | task 22737 | eval time = 39.82 ms / 2 tokens ( 39.82 ms per token, 25.11 tokens per second) 18.02.701.774 I slot print_timing: id 3 | task 22737 | total time = 4595.48 ms / 851 tokens 18.02.701.775 I slot print_timing: id 3 | task 22737 | graphs reused = 21664 18.02.701.775 I slot print_timing: id 3 | task 22737 | graph reallocs = 0 / 0 (same size) / (changed size) 18.02.701.811 I slot release: id 3 | task 22737 | stop processing: n_tokens = 850, truncated = 0 18.02.701.816 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 798, t_last = 341171259778 18.02.703.555 I slot launch_slot_: id 1 | task 22742 | processing task, is_child = 0 18.02.708.545 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 341171299628 18.02.708.622 I slot launch_slot_: id 0 | task 22743 | processing task, is_child = 0 18.02.708.705 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 857, t_last = 341171299952 18.02.708.765 I slot launch_slot_: id 2 | task 22744 | processing task, is_child = 0 18.02.708.806 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 850, t_last = 341171300293 18.02.708.865 I slot launch_slot_: id 3 | task 22745 | processing task, is_child = 0 18.07.937.756 I slot print_timing: id 0 | task 22743 | prompt processing, n_tokens = 985, progress = 1.00, t = 5.23 s / 188.38 tokens per second 18.08.228.592 I slot print_timing: id 1 | task 22742 | prompt processing, n_tokens = 950, progress = 1.00, t = 5.23 s / 181.69 tokens per second 18.08.228.755 I slot print_timing: id 2 | task 22744 | prompt processing, n_tokens = 887, progress = 1.00, t = 5.23 s / 169.64 tokens per second 18.08.228.901 I slot print_timing: id 3 | task 22745 | prompt processing, n_tokens = 1226, progress = 0.70, t = 5.23 s / 234.48 tokens per second 18.09.004.280 I slot print_timing: id 3 | task 22745 | prompt processing, n_tokens = 1738, progress = 1.00, t = 6.29 s / 276.12 tokens per second 18.09.073.649 I slot print_timing: id 0 | task 22743 | prompt eval time = 6294.85 ms / 989 tokens ( 6.36 ms per token, 157.11 tokens per second) 18.09.073.651 I slot print_timing: id 0 | task 22743 | eval time = 69.93 ms / 2 tokens ( 69.93 ms per token, 14.30 tokens per second) 18.09.073.652 I slot print_timing: id 0 | task 22743 | total time = 6364.78 ms / 991 tokens 18.09.073.652 I slot print_timing: id 0 | task 22743 | graphs reused = 21665 18.09.073.652 I slot print_timing: id 0 | task 22743 | graph reallocs = 0 / 0 (same size) / (changed size) 18.09.073.707 I slot release: id 0 | task 22743 | stop processing: n_tokens = 990, truncated = 0 18.09.073.972 I slot print_timing: id 1 | task 22742 | prompt eval time = 6295.06 ms / 954 tokens ( 6.60 ms per token, 151.55 tokens per second) 18.09.073.974 I slot print_timing: id 1 | task 22742 | eval time = 69.97 ms / 2 tokens ( 69.97 ms per token, 14.29 tokens per second) 18.09.073.974 I slot print_timing: id 1 | task 22742 | total time = 6365.03 ms / 956 tokens 18.09.073.975 I slot print_timing: id 1 | task 22742 | graphs reused = 21665 18.09.073.975 I slot print_timing: id 1 | task 22742 | graph reallocs = 0 / 0 (same size) / (changed size) 18.09.074.010 I slot release: id 1 | task 22742 | stop processing: n_tokens = 955, truncated = 0 18.09.074.281 I slot print_timing: id 2 | task 22744 | prompt eval time = 6295.27 ms / 891 tokens ( 7.07 ms per token, 141.53 tokens per second) 18.09.074.284 I slot print_timing: id 2 | task 22744 | eval time = 70.01 ms / 2 tokens ( 70.01 ms per token, 14.28 tokens per second) 18.09.074.284 I slot print_timing: id 2 | task 22744 | total time = 6365.28 ms / 893 tokens 18.09.074.284 I slot print_timing: id 2 | task 22744 | graphs reused = 21665 18.09.074.285 I slot print_timing: id 2 | task 22744 | graph reallocs = 0 / 0 (same size) / (changed size) 18.09.074.331 I slot release: id 2 | task 22744 | stop processing: n_tokens = 892, truncated = 0 18.09.090.672 I slot print_timing: id 3 | task 22745 | prompt eval time = 6365.82 ms / 1742 tokens ( 3.65 ms per token, 273.65 tokens per second) 18.09.090.676 I slot print_timing: id 3 | task 22745 | eval time = 15.79 ms / 2 tokens ( 15.79 ms per token, 63.34 tokens per second) 18.09.090.676 I slot print_timing: id 3 | task 22745 | total time = 6381.60 ms / 1744 tokens 18.09.090.677 I slot print_timing: id 3 | task 22745 | graphs reused = 21665 18.09.090.677 I slot print_timing: id 3 | task 22745 | graph reallocs = 0 / 0 (same size) / (changed size) 18.09.090.781 I slot release: id 3 | task 22745 | stop processing: n_tokens = 1743, truncated = 0 18.09.090.788 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.828 (> 0.100 thold), f_keep = 0.843 18.09.090.815 I slot launch_slot_: id 2 | task 22751 | processing task, is_child = 0 18.09.097.741 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 990, t_last = 341177672189 18.09.097.828 I slot launch_slot_: id 0 | task 22752 | processing task, is_child = 0 18.09.097.953 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 955, t_last = 341177672492 18.09.098.025 I slot launch_slot_: id 1 | task 22753 | processing task, is_child = 0 18.09.098.099 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1743, t_last = 341177689263 18.09.098.187 I slot launch_slot_: id 3 | task 22754 | processing task, is_child = 0 18.12.372.665 I slot print_timing: id 0 | task 22752 | prompt processing, n_tokens = 858, progress = 1.00, t = 3.27 s / 262.03 tokens per second 18.13.018.186 I slot print_timing: id 1 | task 22753 | prompt processing, n_tokens = 723, progress = 0.99, t = 3.27 s / 220.80 tokens per second 18.13.018.322 I slot print_timing: id 2 | task 22751 | prompt processing, n_tokens = 529, progress = 1.00, t = 3.27 s / 161.56 tokens per second 18.13.018.473 I slot print_timing: id 3 | task 22754 | prompt processing, n_tokens = 696, progress = 0.99, t = 3.27 s / 212.57 tokens per second 18.13.171.461 I slot print_timing: id 0 | task 22752 | prompt eval time = 4032.84 ms / 862 tokens ( 4.68 ms per token, 213.75 tokens per second) 18.13.171.463 I slot print_timing: id 0 | task 22752 | eval time = 40.43 ms / 2 tokens ( 40.43 ms per token, 24.74 tokens per second) 18.13.171.464 I slot print_timing: id 0 | task 22752 | total time = 4073.27 ms / 864 tokens 18.13.171.464 I slot print_timing: id 0 | task 22752 | graphs reused = 21667 18.13.171.465 I slot print_timing: id 0 | task 22752 | graph reallocs = 0 / 0 (same size) / (changed size) 18.13.171.512 I slot release: id 0 | task 22752 | stop processing: n_tokens = 863, truncated = 0 18.13.171.794 I slot print_timing: id 1 | task 22753 | prompt eval time = 4033.06 ms / 727 tokens ( 5.55 ms per token, 180.26 tokens per second) 18.13.171.798 I slot print_timing: id 1 | task 22753 | eval time = 40.47 ms / 2 tokens ( 40.47 ms per token, 24.71 tokens per second) 18.13.171.798 I slot print_timing: id 1 | task 22753 | total time = 4073.53 ms / 729 tokens 18.13.171.799 I slot print_timing: id 1 | task 22753 | graphs reused = 21667 18.13.171.799 I slot print_timing: id 1 | task 22753 | graph reallocs = 0 / 0 (same size) / (changed size) 18.13.171.842 I slot release: id 1 | task 22753 | stop processing: n_tokens = 728, truncated = 0 18.13.172.112 I slot print_timing: id 2 | task 22751 | prompt eval time = 4033.36 ms / 533 tokens ( 7.57 ms per token, 132.15 tokens per second) 18.13.172.114 I slot print_timing: id 2 | task 22751 | eval time = 40.42 ms / 2 tokens ( 40.42 ms per token, 24.74 tokens per second) 18.13.172.114 I slot print_timing: id 2 | task 22751 | total time = 4073.78 ms / 535 tokens 18.13.172.114 I slot print_timing: id 2 | task 22751 | graphs reused = 21667 18.13.172.115 I slot print_timing: id 2 | task 22751 | graph reallocs = 0 / 0 (same size) / (changed size) 18.13.172.162 I slot release: id 2 | task 22751 | stop processing: n_tokens = 909, truncated = 0 18.13.172.442 I slot print_timing: id 3 | task 22754 | prompt eval time = 4033.71 ms / 700 tokens ( 5.76 ms per token, 173.54 tokens per second) 18.13.172.448 I slot print_timing: id 3 | task 22754 | eval time = 40.32 ms / 2 tokens ( 40.32 ms per token, 24.80 tokens per second) 18.13.172.448 I slot print_timing: id 3 | task 22754 | total time = 4074.03 ms / 702 tokens 18.13.172.449 I slot print_timing: id 3 | task 22754 | graphs reused = 21667 18.13.172.449 I slot print_timing: id 3 | task 22754 | graph reallocs = 0 / 0 (same size) / (changed size) 18.13.172.484 I slot release: id 3 | task 22754 | stop processing: n_tokens = 701, truncated = 0 18.13.178.778 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 341181769994 18.13.180.443 I slot launch_slot_: id 0 | task 22759 | processing task, is_child = 0 18.13.184.823 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.848 18.13.184.842 I slot launch_slot_: id 1 | task 22762 | processing task, is_child = 0 18.13.184.922 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.874 (> 0.100 thold), f_keep = 0.880 18.13.184.937 I slot launch_slot_: id 3 | task 22760 | processing task, is_child = 0 18.13.184.981 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 909, t_last = 341181770644 18.13.185.500 I slot launch_slot_: id 2 | task 22761 | processing task, is_child = 0 18.16.466.583 I slot print_timing: id 0 | task 22759 | prompt processing, n_tokens = 824, progress = 1.00, t = 3.28 s / 251.18 tokens per second 18.16.466.745 I slot print_timing: id 3 | task 22760 | prompt processing, n_tokens = 518, progress = 0.99, t = 3.28 s / 157.92 tokens per second 18.16.562.757 I slot print_timing: id 1 | task 22762 | prompt eval time = 3280.74 ms / 493 tokens ( 6.65 ms per token, 150.27 tokens per second) 18.16.562.760 I slot print_timing: id 1 | task 22762 | eval time = 96.46 ms / 2 tokens ( 96.46 ms per token, 10.37 tokens per second) 18.16.562.760 I slot print_timing: id 1 | task 22762 | total time = 3377.20 ms / 495 tokens 18.16.562.761 I slot print_timing: id 1 | task 22762 | graphs reused = 21667 18.16.562.761 I slot print_timing: id 1 | task 22762 | graph reallocs = 0 / 0 (same size) / (changed size) 18.16.562.805 I slot release: id 1 | task 22762 | stop processing: n_tokens = 705, truncated = 0 18.16.563.076 I slot print_timing: id 2 | task 22761 | prompt eval time = 3280.89 ms / 497 tokens ( 6.60 ms per token, 151.48 tokens per second) 18.16.563.078 I slot print_timing: id 2 | task 22761 | eval time = 96.50 ms / 2 tokens ( 96.50 ms per token, 10.36 tokens per second) 18.16.563.079 I slot print_timing: id 2 | task 22761 | total time = 3377.40 ms / 499 tokens 18.16.563.079 I slot print_timing: id 2 | task 22761 | graphs reused = 21667 18.16.563.079 I slot print_timing: id 2 | task 22761 | graph reallocs = 0 / 0 (same size) / (changed size) 18.16.563.114 I slot release: id 2 | task 22761 | stop processing: n_tokens = 709, truncated = 0 18.16.593.466 I slot print_timing: id 0 | task 22759 | prompt eval time = 3377.00 ms / 828 tokens ( 4.08 ms per token, 245.19 tokens per second) 18.16.593.471 I slot print_timing: id 0 | task 22759 | eval time = 30.96 ms / 2 tokens ( 30.96 ms per token, 32.30 tokens per second) 18.16.593.472 I slot print_timing: id 0 | task 22759 | total time = 3407.96 ms / 830 tokens 18.16.593.472 I slot print_timing: id 0 | task 22759 | graphs reused = 21667 18.16.593.472 I slot print_timing: id 0 | task 22759 | graph reallocs = 0 / 0 (same size) / (changed size) 18.16.593.508 I slot release: id 0 | task 22759 | stop processing: n_tokens = 829, truncated = 0 18.16.593.779 I slot print_timing: id 3 | task 22760 | prompt eval time = 3377.68 ms / 522 tokens ( 6.47 ms per token, 154.54 tokens per second) 18.16.593.781 I slot print_timing: id 3 | task 22760 | eval time = 30.33 ms / 2 tokens ( 30.33 ms per token, 32.97 tokens per second) 18.16.593.782 I slot print_timing: id 3 | task 22760 | total time = 3408.02 ms / 524 tokens 18.16.593.782 I slot print_timing: id 3 | task 22760 | graphs reused = 21667 18.16.593.783 I slot print_timing: id 3 | task 22760 | graph reallocs = 0 / 0 (same size) / (changed size) 18.16.593.813 I slot release: id 3 | task 22760 | stop processing: n_tokens = 707, truncated = 0 18.16.593.817 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 705, t_last = 341185161288 18.16.594.564 I slot launch_slot_: id 1 | task 22767 | processing task, is_child = 0 18.16.599.582 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 709, t_last = 341185161596 18.16.599.644 I slot launch_slot_: id 2 | task 22768 | processing task, is_child = 0 18.16.599.734 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 829, t_last = 341185191990 18.16.599.790 I slot launch_slot_: id 0 | task 22769 | processing task, is_child = 0 18.16.599.828 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 341185192295 18.16.599.899 I slot launch_slot_: id 3 | task 22770 | processing task, is_child = 0 18.20.932.913 I slot print_timing: id 0 | task 22769 | prompt processing, n_tokens = 922, progress = 1.00, t = 4.33 s / 212.79 tokens per second 18.21.583.229 I slot print_timing: id 1 | task 22767 | prompt processing, n_tokens = 913, progress = 1.00, t = 4.33 s / 210.71 tokens per second 18.21.583.393 I slot print_timing: id 2 | task 22768 | prompt processing, n_tokens = 958, progress = 1.00, t = 4.33 s / 221.10 tokens per second 18.21.583.553 I slot print_timing: id 3 | task 22770 | prompt processing, n_tokens = 932, progress = 1.00, t = 4.33 s / 215.10 tokens per second 18.21.737.154 I slot print_timing: id 0 | task 22769 | prompt eval time = 5096.50 ms / 926 tokens ( 5.50 ms per token, 181.69 tokens per second) 18.21.737.160 I slot print_timing: id 0 | task 22769 | eval time = 40.75 ms / 2 tokens ( 40.75 ms per token, 24.54 tokens per second) 18.21.737.160 I slot print_timing: id 0 | task 22769 | total time = 5137.25 ms / 928 tokens 18.21.737.161 I slot print_timing: id 0 | task 22769 | graphs reused = 21669 18.21.737.161 I slot print_timing: id 0 | task 22769 | graph reallocs = 0 / 0 (same size) / (changed size) 18.21.737.214 I slot release: id 0 | task 22769 | stop processing: n_tokens = 927, truncated = 0 18.21.737.489 I slot print_timing: id 1 | task 22767 | prompt eval time = 5096.76 ms / 917 tokens ( 5.56 ms per token, 179.92 tokens per second) 18.21.737.491 I slot print_timing: id 1 | task 22767 | eval time = 40.76 ms / 2 tokens ( 40.76 ms per token, 24.53 tokens per second) 18.21.737.492 I slot print_timing: id 1 | task 22767 | total time = 5137.52 ms / 919 tokens 18.21.737.492 I slot print_timing: id 1 | task 22767 | graphs reused = 21669 18.21.737.492 I slot print_timing: id 1 | task 22767 | graph reallocs = 0 / 0 (same size) / (changed size) 18.21.737.539 I slot release: id 1 | task 22767 | stop processing: n_tokens = 918, truncated = 0 18.21.737.833 I slot print_timing: id 2 | task 22768 | prompt eval time = 5097.14 ms / 962 tokens ( 5.30 ms per token, 188.73 tokens per second) 18.21.737.835 I slot print_timing: id 2 | task 22768 | eval time = 40.68 ms / 2 tokens ( 40.68 ms per token, 24.58 tokens per second) 18.21.737.835 I slot print_timing: id 2 | task 22768 | total time = 5137.81 ms / 964 tokens 18.21.737.835 I slot print_timing: id 2 | task 22768 | graphs reused = 21669 18.21.737.836 I slot print_timing: id 2 | task 22768 | graph reallocs = 0 / 0 (same size) / (changed size) 18.21.737.870 I slot release: id 2 | task 22768 | stop processing: n_tokens = 963, truncated = 0 18.21.738.185 I slot print_timing: id 3 | task 22770 | prompt eval time = 5097.69 ms / 936 tokens ( 5.45 ms per token, 183.61 tokens per second) 18.21.738.188 I slot print_timing: id 3 | task 22770 | eval time = 40.43 ms / 2 tokens ( 40.43 ms per token, 24.74 tokens per second) 18.21.738.189 I slot print_timing: id 3 | task 22770 | total time = 5138.11 ms / 938 tokens 18.21.738.189 I slot print_timing: id 3 | task 22770 | graphs reused = 21669 18.21.738.190 I slot print_timing: id 3 | task 22770 | graph reallocs = 0 / 0 (same size) / (changed size) 18.21.738.226 I slot release: id 3 | task 22770 | stop processing: n_tokens = 937, truncated = 0 18.21.744.722 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.889 18.21.744.749 I slot launch_slot_: id 0 | task 22775 | processing task, is_child = 0 18.21.750.460 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 918, t_last = 341190336021 18.21.750.535 I slot launch_slot_: id 1 | task 22776 | processing task, is_child = 0 18.21.750.628 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 963, t_last = 341190336352 18.21.750.691 I slot launch_slot_: id 2 | task 22777 | processing task, is_child = 0 18.21.750.738 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 937, t_last = 341190336709 18.21.750.799 I slot launch_slot_: id 3 | task 22778 | processing task, is_child = 0 18.26.345.040 I slot print_timing: id 1 | task 22776 | prompt processing, n_tokens = 817, progress = 1.00, t = 4.59 s / 177.85 tokens per second 18.26.345.209 I slot print_timing: id 2 | task 22777 | prompt processing, n_tokens = 882, progress = 1.00, t = 4.59 s / 192.00 tokens per second 18.26.345.361 I slot print_timing: id 3 | task 22778 | prompt processing, n_tokens = 996, progress = 1.00, t = 4.59 s / 216.82 tokens per second 18.26.453.891 I slot print_timing: id 0 | task 22775 | prompt eval time = 4594.22 ms / 514 tokens ( 8.94 ms per token, 111.88 tokens per second) 18.26.453.897 I slot print_timing: id 0 | task 22775 | eval time = 108.86 ms / 2 tokens ( 108.86 ms per token, 9.19 tokens per second) 18.26.453.897 I slot print_timing: id 0 | task 22775 | total time = 4703.08 ms / 516 tokens 18.26.453.898 I slot print_timing: id 0 | task 22775 | graphs reused = 21669 18.26.453.898 I slot print_timing: id 0 | task 22775 | graph reallocs = 0 / 0 (same size) / (changed size) 18.26.453.950 I slot release: id 0 | task 22775 | stop processing: n_tokens = 925, truncated = 0 18.26.487.271 I slot print_timing: id 1 | task 22776 | prompt eval time = 4703.30 ms / 821 tokens ( 5.73 ms per token, 174.56 tokens per second) 18.26.487.274 I slot print_timing: id 1 | task 22776 | eval time = 33.02 ms / 2 tokens ( 33.02 ms per token, 30.29 tokens per second) 18.26.487.274 I slot print_timing: id 1 | task 22776 | total time = 4736.32 ms / 823 tokens 18.26.487.275 I slot print_timing: id 1 | task 22776 | graphs reused = 21669 18.26.487.275 I slot print_timing: id 1 | task 22776 | graph reallocs = 0 / 0 (same size) / (changed size) 18.26.487.316 I slot release: id 1 | task 22776 | stop processing: n_tokens = 822, truncated = 0 18.26.487.585 I slot print_timing: id 2 | task 22777 | prompt eval time = 4703.52 ms / 886 tokens ( 5.31 ms per token, 188.37 tokens per second) 18.26.487.587 I slot print_timing: id 2 | task 22777 | eval time = 33.05 ms / 2 tokens ( 33.05 ms per token, 30.26 tokens per second) 18.26.487.587 I slot print_timing: id 2 | task 22777 | total time = 4736.57 ms / 888 tokens 18.26.487.587 I slot print_timing: id 2 | task 22777 | graphs reused = 21669 18.26.487.588 I slot print_timing: id 2 | task 22777 | graph reallocs = 0 / 0 (same size) / (changed size) 18.26.487.627 I slot release: id 2 | task 22777 | stop processing: n_tokens = 887, truncated = 0 18.26.487.909 I slot print_timing: id 3 | task 22778 | prompt eval time = 4703.76 ms / 1000 tokens ( 4.70 ms per token, 212.60 tokens per second) 18.26.487.911 I slot print_timing: id 3 | task 22778 | eval time = 33.06 ms / 2 tokens ( 33.06 ms per token, 30.25 tokens per second) 18.26.487.912 I slot print_timing: id 3 | task 22778 | total time = 4736.82 ms / 1002 tokens 18.26.487.912 I slot print_timing: id 3 | task 22778 | graphs reused = 21669 18.26.487.912 I slot print_timing: id 3 | task 22778 | graph reallocs = 0 / 0 (same size) / (changed size) 18.26.487.965 I slot release: id 3 | task 22778 | stop processing: n_tokens = 1001, truncated = 0 18.26.487.971 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.799 (> 0.100 thold), f_keep = 0.892 18.26.487.997 I slot launch_slot_: id 2 | task 22783 | processing task, is_child = 0 18.26.493.551 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.891 (> 0.100 thold), f_keep = 0.790 18.26.493.580 I slot launch_slot_: id 3 | task 22784 | processing task, is_child = 0 18.26.493.673 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 925, t_last = 341195052432 18.26.494.464 I slot launch_slot_: id 0 | task 22785 | processing task, is_child = 0 18.26.494.518 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 822, t_last = 341195085798 18.26.494.575 I slot launch_slot_: id 1 | task 22786 | processing task, is_child = 0 18.29.927.224 I slot print_timing: id 1 | task 22786 | prompt processing, n_tokens = 957, progress = 1.00, t = 3.43 s / 278.85 tokens per second 18.29.927.401 I slot print_timing: id 2 | task 22783 | prompt processing, n_tokens = 616, progress = 1.00, t = 3.43 s / 179.49 tokens per second 18.30.021.488 I slot print_timing: id 0 | task 22785 | prompt eval time = 3432.34 ms / 388 tokens ( 8.85 ms per token, 113.04 tokens per second) 18.30.021.491 I slot print_timing: id 0 | task 22785 | eval time = 94.56 ms / 2 tokens ( 94.56 ms per token, 10.58 tokens per second) 18.30.021.491 I slot print_timing: id 0 | task 22785 | total time = 3526.90 ms / 390 tokens 18.30.021.492 I slot print_timing: id 0 | task 22785 | graphs reused = 21669 18.30.021.492 I slot print_timing: id 0 | task 22785 | graph reallocs = 0 / 0 (same size) / (changed size) 18.30.021.545 I slot release: id 0 | task 22785 | stop processing: n_tokens = 873, truncated = 0 18.30.022.593 I slot print_timing: id 3 | task 22784 | prompt eval time = 3432.38 ms / 404 tokens ( 8.50 ms per token, 117.70 tokens per second) 18.30.022.595 I slot print_timing: id 3 | task 22784 | eval time = 95.38 ms / 2 tokens ( 95.38 ms per token, 10.48 tokens per second) 18.30.022.595 I slot print_timing: id 3 | task 22784 | total time = 3527.76 ms / 406 tokens 18.30.022.595 I slot print_timing: id 3 | task 22784 | graphs reused = 21669 18.30.022.596 I slot print_timing: id 3 | task 22784 | graph reallocs = 0 / 0 (same size) / (changed size) 18.30.022.644 I slot release: id 3 | task 22784 | stop processing: n_tokens = 889, truncated = 0 18.30.047.794 I slot print_timing: id 1 | task 22786 | prompt eval time = 3527.17 ms / 961 tokens ( 3.67 ms per token, 272.46 tokens per second) 18.30.047.797 I slot print_timing: id 1 | task 22786 | eval time = 25.93 ms / 2 tokens ( 25.93 ms per token, 38.57 tokens per second) 18.30.047.798 I slot print_timing: id 1 | task 22786 | total time = 3553.10 ms / 963 tokens 18.30.047.798 I slot print_timing: id 1 | task 22786 | graphs reused = 21669 18.30.047.799 I slot print_timing: id 1 | task 22786 | graph reallocs = 0 / 0 (same size) / (changed size) 18.30.047.845 I slot release: id 1 | task 22786 | stop processing: n_tokens = 962, truncated = 0 18.30.048.133 I slot print_timing: id 2 | task 22783 | prompt eval time = 3527.53 ms / 620 tokens ( 5.69 ms per token, 175.76 tokens per second) 18.30.048.135 I slot print_timing: id 2 | task 22783 | eval time = 25.85 ms / 2 tokens ( 25.85 ms per token, 38.68 tokens per second) 18.30.048.136 I slot print_timing: id 2 | task 22783 | total time = 3553.38 ms / 622 tokens 18.30.048.136 I slot print_timing: id 2 | task 22783 | graphs reused = 21669 18.30.048.137 I slot print_timing: id 2 | task 22783 | graph reallocs = 0 / 0 (same size) / (changed size) 18.30.048.180 I slot release: id 2 | task 22783 | stop processing: n_tokens = 991, truncated = 0 18.30.048.184 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 341198620028 18.30.048.973 I slot launch_slot_: id 0 | task 22791 | processing task, is_child = 0 18.30.054.200 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 889, t_last = 341198621126 18.30.054.274 I slot launch_slot_: id 3 | task 22792 | processing task, is_child = 0 18.30.054.368 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 341198646327 18.30.054.435 I slot launch_slot_: id 1 | task 22793 | processing task, is_child = 0 18.30.054.481 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 341198646662 18.30.054.541 I slot launch_slot_: id 2 | task 22794 | processing task, is_child = 0 18.34.694.178 I slot print_timing: id 0 | task 22791 | prompt processing, n_tokens = 865, progress = 1.00, t = 4.64 s / 186.44 tokens per second 18.35.345.471 I slot print_timing: id 1 | task 22793 | prompt processing, n_tokens = 899, progress = 1.00, t = 4.64 s / 193.77 tokens per second 18.35.345.657 I slot print_timing: id 2 | task 22794 | prompt processing, n_tokens = 1276, progress = 1.00, t = 4.64 s / 275.03 tokens per second 18.35.345.864 I slot print_timing: id 3 | task 22792 | prompt processing, n_tokens = 906, progress = 1.00, t = 4.64 s / 195.28 tokens per second 18.35.500.288 I slot print_timing: id 0 | task 22791 | prompt eval time = 5404.73 ms / 869 tokens ( 6.22 ms per token, 160.79 tokens per second) 18.35.500.291 I slot print_timing: id 0 | task 22791 | eval time = 41.01 ms / 2 tokens ( 41.01 ms per token, 24.39 tokens per second) 18.35.500.291 I slot print_timing: id 0 | task 22791 | total time = 5445.74 ms / 871 tokens 18.35.500.292 I slot print_timing: id 0 | task 22791 | graphs reused = 21671 18.35.500.292 I slot print_timing: id 0 | task 22791 | graph reallocs = 0 / 0 (same size) / (changed size) 18.35.500.343 I slot release: id 0 | task 22791 | stop processing: n_tokens = 870, truncated = 0 18.35.500.632 I slot print_timing: id 1 | task 22793 | prompt eval time = 5405.04 ms / 903 tokens ( 5.99 ms per token, 167.07 tokens per second) 18.35.500.634 I slot print_timing: id 1 | task 22793 | eval time = 40.97 ms / 2 tokens ( 40.97 ms per token, 24.41 tokens per second) 18.35.500.635 I slot print_timing: id 1 | task 22793 | total time = 5446.01 ms / 905 tokens 18.35.500.635 I slot print_timing: id 1 | task 22793 | graphs reused = 21671 18.35.500.635 I slot print_timing: id 1 | task 22793 | graph reallocs = 0 / 0 (same size) / (changed size) 18.35.500.674 I slot release: id 1 | task 22793 | stop processing: n_tokens = 904, truncated = 0 18.35.500.963 I slot print_timing: id 2 | task 22794 | prompt eval time = 5405.38 ms / 1280 tokens ( 4.22 ms per token, 236.80 tokens per second) 18.35.500.966 I slot print_timing: id 2 | task 22794 | eval time = 40.91 ms / 2 tokens ( 40.91 ms per token, 24.45 tokens per second) 18.35.500.966 I slot print_timing: id 2 | task 22794 | total time = 5446.28 ms / 1282 tokens 18.35.500.967 I slot print_timing: id 2 | task 22794 | graphs reused = 21671 18.35.500.967 I slot print_timing: id 2 | task 22794 | graph reallocs = 0 / 0 (same size) / (changed size) 18.35.501.022 I slot release: id 2 | task 22794 | stop processing: n_tokens = 1281, truncated = 0 18.35.501.313 I slot print_timing: id 3 | task 22792 | prompt eval time = 5405.80 ms / 910 tokens ( 5.94 ms per token, 168.34 tokens per second) 18.35.501.316 I slot print_timing: id 3 | task 22792 | eval time = 40.76 ms / 2 tokens ( 40.76 ms per token, 24.54 tokens per second) 18.35.501.317 I slot print_timing: id 3 | task 22792 | total time = 5446.56 ms / 912 tokens 18.35.501.317 I slot print_timing: id 3 | task 22792 | graphs reused = 21671 18.35.501.317 I slot print_timing: id 3 | task 22792 | graph reallocs = 0 / 0 (same size) / (changed size) 18.35.501.353 I slot release: id 3 | task 22792 | stop processing: n_tokens = 911, truncated = 0 18.35.508.736 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 870, t_last = 341204098825 18.35.510.472 I slot launch_slot_: id 0 | task 22799 | processing task, is_child = 0 18.35.516.056 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.877 18.35.516.075 I slot launch_slot_: id 2 | task 22800 | processing task, is_child = 0 18.35.516.165 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 341204099156 18.35.517.037 I slot launch_slot_: id 1 | task 22801 | processing task, is_child = 0 18.35.517.089 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 911, t_last = 341204099835 18.35.517.152 I slot launch_slot_: id 3 | task 22802 | processing task, is_child = 0 18.39.689.695 I slot print_timing: id 0 | task 22799 | prompt processing, n_tokens = 763, progress = 0.99, t = 4.17 s / 182.88 tokens per second 18.39.689.859 I slot print_timing: id 1 | task 22801 | prompt processing, n_tokens = 519, progress = 1.00, t = 4.17 s / 124.40 tokens per second 18.39.690.052 I slot print_timing: id 3 | task 22802 | prompt processing, n_tokens = 1199, progress = 1.00, t = 4.17 s / 287.39 tokens per second 18.39.802.718 I slot print_timing: id 2 | task 22800 | prompt eval time = 4172.39 ms / 476 tokens ( 8.77 ms per token, 114.08 tokens per second) 18.39.802.721 I slot print_timing: id 2 | task 22800 | eval time = 113.04 ms / 2 tokens ( 113.04 ms per token, 8.85 tokens per second) 18.39.802.721 I slot print_timing: id 2 | task 22800 | total time = 4285.43 ms / 478 tokens 18.39.802.722 I slot print_timing: id 2 | task 22800 | graphs reused = 21671 18.39.802.722 I slot print_timing: id 2 | task 22800 | graph reallocs = 0 / 0 (same size) / (changed size) 18.39.802.787 I slot release: id 2 | task 22800 | stop processing: n_tokens = 1241, truncated = 0 18.39.842.852 I slot print_timing: id 0 | task 22799 | prompt eval time = 4284.91 ms / 767 tokens ( 5.59 ms per token, 179.00 tokens per second) 18.39.842.858 I slot print_timing: id 0 | task 22799 | eval time = 40.78 ms / 2 tokens ( 40.78 ms per token, 24.52 tokens per second) 18.39.842.858 I slot print_timing: id 0 | task 22799 | total time = 4325.69 ms / 769 tokens 18.39.842.859 I slot print_timing: id 0 | task 22799 | graphs reused = 21671 18.39.842.859 I slot print_timing: id 0 | task 22799 | graph reallocs = 0 / 0 (same size) / (changed size) 18.39.842.907 I slot release: id 0 | task 22799 | stop processing: n_tokens = 768, truncated = 0 18.39.843.193 I slot print_timing: id 1 | task 22801 | prompt eval time = 4285.22 ms / 523 tokens ( 8.19 ms per token, 122.05 tokens per second) 18.39.843.200 I slot print_timing: id 1 | task 22801 | eval time = 40.75 ms / 2 tokens ( 40.75 ms per token, 24.54 tokens per second) 18.39.843.200 I slot print_timing: id 1 | task 22801 | total time = 4325.97 ms / 525 tokens 18.39.843.201 I slot print_timing: id 1 | task 22801 | graphs reused = 21671 18.39.843.201 I slot print_timing: id 1 | task 22801 | graph reallocs = 0 / 0 (same size) / (changed size) 18.39.843.258 I slot release: id 1 | task 22801 | stop processing: n_tokens = 1288, truncated = 0 18.39.843.540 I slot print_timing: id 3 | task 22802 | prompt eval time = 4285.74 ms / 1203 tokens ( 3.56 ms per token, 280.70 tokens per second) 18.39.843.543 I slot print_timing: id 3 | task 22802 | eval time = 40.40 ms / 2 tokens ( 40.40 ms per token, 24.75 tokens per second) 18.39.843.543 I slot print_timing: id 3 | task 22802 | total time = 4326.14 ms / 1205 tokens 18.39.843.544 I slot print_timing: id 3 | task 22802 | graphs reused = 21671 18.39.843.544 I slot print_timing: id 3 | task 22802 | graph reallocs = 0 / 0 (same size) / (changed size) 18.39.843.585 I slot release: id 3 | task 22802 | stop processing: n_tokens = 1204, truncated = 0 18.39.843.589 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.872 (> 0.100 thold), f_keep = 0.889 18.39.843.619 I slot launch_slot_: id 0 | task 22807 | processing task, is_child = 0 18.39.850.229 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1241, t_last = 341208401269 18.39.850.311 I slot launch_slot_: id 2 | task 22808 | processing task, is_child = 0 18.39.850.420 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1288, t_last = 341208441741 18.39.850.495 I slot launch_slot_: id 1 | task 22809 | processing task, is_child = 0 18.39.850.548 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1204, t_last = 341208442067 18.39.850.619 I slot launch_slot_: id 3 | task 22810 | processing task, is_child = 0 18.43.475.353 I slot print_timing: id 0 | task 22807 | prompt processing, n_tokens = 528, progress = 0.99, t = 3.62 s / 145.67 tokens per second 18.44.121.976 I slot print_timing: id 1 | task 22809 | prompt processing, n_tokens = 840, progress = 1.00, t = 3.62 s / 231.75 tokens per second 18.44.122.138 I slot print_timing: id 2 | task 22808 | prompt processing, n_tokens = 766, progress = 0.99, t = 3.62 s / 211.34 tokens per second 18.44.122.266 I slot print_timing: id 3 | task 22810 | prompt processing, n_tokens = 870, progress = 1.00, t = 3.62 s / 240.04 tokens per second 18.44.275.653 I slot print_timing: id 0 | task 22807 | prompt eval time = 4384.55 ms / 532 tokens ( 8.24 ms per token, 121.34 tokens per second) 18.44.275.658 I slot print_timing: id 0 | task 22807 | eval time = 40.48 ms / 2 tokens ( 40.48 ms per token, 24.71 tokens per second) 18.44.275.659 I slot print_timing: id 0 | task 22807 | total time = 4425.03 ms / 534 tokens 18.44.275.659 I slot print_timing: id 0 | task 22807 | graphs reused = 21672 18.44.275.660 I slot print_timing: id 0 | task 22807 | graph reallocs = 0 / 0 (same size) / (changed size) 18.44.275.711 I slot release: id 0 | task 22807 | stop processing: n_tokens = 784, truncated = 0 18.44.275.995 I slot print_timing: id 1 | task 22809 | prompt eval time = 4384.75 ms / 844 tokens ( 5.20 ms per token, 192.49 tokens per second) 18.44.275.998 I slot print_timing: id 1 | task 22809 | eval time = 40.52 ms / 2 tokens ( 40.52 ms per token, 24.68 tokens per second) 18.44.275.998 I slot print_timing: id 1 | task 22809 | total time = 4425.27 ms / 846 tokens 18.44.275.999 I slot print_timing: id 1 | task 22809 | graphs reused = 21672 18.44.275.999 I slot print_timing: id 1 | task 22809 | graph reallocs = 0 / 0 (same size) / (changed size) 18.44.276.045 I slot release: id 1 | task 22809 | stop processing: n_tokens = 845, truncated = 0 18.44.276.331 I slot print_timing: id 2 | task 22808 | prompt eval time = 4384.95 ms / 770 tokens ( 5.69 ms per token, 175.60 tokens per second) 18.44.276.333 I slot print_timing: id 2 | task 22808 | eval time = 40.56 ms / 2 tokens ( 40.56 ms per token, 24.66 tokens per second) 18.44.276.334 I slot print_timing: id 2 | task 22808 | total time = 4425.51 ms / 772 tokens 18.44.276.334 I slot print_timing: id 2 | task 22808 | graphs reused = 21672 18.44.276.334 I slot print_timing: id 2 | task 22808 | graph reallocs = 0 / 0 (same size) / (changed size) 18.44.276.371 I slot release: id 2 | task 22808 | stop processing: n_tokens = 771, truncated = 0 18.44.276.662 I slot print_timing: id 3 | task 22810 | prompt eval time = 4385.30 ms / 874 tokens ( 5.02 ms per token, 199.30 tokens per second) 18.44.276.666 I slot print_timing: id 3 | task 22810 | eval time = 40.45 ms / 2 tokens ( 40.45 ms per token, 24.72 tokens per second) 18.44.276.667 I slot print_timing: id 3 | task 22810 | total time = 4425.75 ms / 876 tokens 18.44.276.667 I slot print_timing: id 3 | task 22810 | graphs reused = 21672 18.44.276.667 I slot print_timing: id 3 | task 22810 | graph reallocs = 0 / 0 (same size) / (changed size) 18.44.276.713 I slot release: id 3 | task 22810 | stop processing: n_tokens = 875, truncated = 0 18.44.283.526 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.811 (> 0.100 thold), f_keep = 0.860 18.44.283.551 I slot launch_slot_: id 2 | task 22815 | processing task, is_child = 0 18.44.288.357 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 784, t_last = 341212874193 18.44.288.425 I slot launch_slot_: id 0 | task 22816 | processing task, is_child = 0 18.44.288.521 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 845, t_last = 341212874527 18.44.288.599 I slot launch_slot_: id 1 | task 22817 | processing task, is_child = 0 18.44.288.643 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 875, t_last = 341212875195 18.44.288.709 I slot launch_slot_: id 3 | task 22818 | processing task, is_child = 0 18.47.536.930 I slot print_timing: id 0 | task 22816 | prompt processing, n_tokens = 746, progress = 0.99, t = 3.25 s / 229.67 tokens per second 18.48.181.824 I slot print_timing: id 1 | task 22817 | prompt processing, n_tokens = 775, progress = 0.99, t = 3.25 s / 238.60 tokens per second 18.48.181.972 I slot print_timing: id 2 | task 22815 | prompt processing, n_tokens = 560, progress = 1.00, t = 3.25 s / 172.41 tokens per second 18.48.182.104 I slot print_timing: id 3 | task 22818 | prompt processing, n_tokens = 752, progress = 0.99, t = 3.25 s / 231.53 tokens per second 18.48.335.296 I slot print_timing: id 0 | task 22816 | prompt eval time = 4006.09 ms / 750 tokens ( 5.34 ms per token, 187.21 tokens per second) 18.48.335.298 I slot print_timing: id 0 | task 22816 | eval time = 40.48 ms / 2 tokens ( 40.48 ms per token, 24.70 tokens per second) 18.48.335.299 I slot print_timing: id 0 | task 22816 | total time = 4046.58 ms / 752 tokens 18.48.335.299 I slot print_timing: id 0 | task 22816 | graphs reused = 21673 18.48.335.300 I slot print_timing: id 0 | task 22816 | graph reallocs = 0 / 0 (same size) / (changed size) 18.48.335.347 I slot release: id 0 | task 22816 | stop processing: n_tokens = 751, truncated = 0 18.48.335.627 I slot print_timing: id 1 | task 22817 | prompt eval time = 4006.33 ms / 779 tokens ( 5.14 ms per token, 194.44 tokens per second) 18.48.335.629 I slot print_timing: id 1 | task 22817 | eval time = 40.53 ms / 2 tokens ( 40.53 ms per token, 24.68 tokens per second) 18.48.335.629 I slot print_timing: id 1 | task 22817 | total time = 4046.85 ms / 781 tokens 18.48.335.630 I slot print_timing: id 1 | task 22817 | graphs reused = 21673 18.48.335.630 I slot print_timing: id 1 | task 22817 | graph reallocs = 0 / 0 (same size) / (changed size) 18.48.335.671 I slot release: id 1 | task 22817 | stop processing: n_tokens = 780, truncated = 0 18.48.335.944 I slot print_timing: id 2 | task 22815 | prompt eval time = 4006.56 ms / 564 tokens ( 7.10 ms per token, 140.77 tokens per second) 18.48.335.947 I slot print_timing: id 2 | task 22815 | eval time = 40.55 ms / 2 tokens ( 40.55 ms per token, 24.66 tokens per second) 18.48.335.948 I slot print_timing: id 2 | task 22815 | total time = 4047.12 ms / 566 tokens 18.48.335.948 I slot print_timing: id 2 | task 22815 | graphs reused = 21673 18.48.335.948 I slot print_timing: id 2 | task 22815 | graph reallocs = 0 / 0 (same size) / (changed size) 18.48.335.980 I slot release: id 2 | task 22815 | stop processing: n_tokens = 819, truncated = 0 18.48.336.268 I slot print_timing: id 3 | task 22818 | prompt eval time = 4006.81 ms / 756 tokens ( 5.30 ms per token, 188.68 tokens per second) 18.48.336.275 I slot print_timing: id 3 | task 22818 | eval time = 40.55 ms / 2 tokens ( 40.55 ms per token, 24.66 tokens per second) 18.48.336.276 I slot print_timing: id 3 | task 22818 | total time = 4047.36 ms / 758 tokens 18.48.336.276 I slot print_timing: id 3 | task 22818 | graphs reused = 21673 18.48.336.276 I slot print_timing: id 3 | task 22818 | graph reallocs = 0 / 0 (same size) / (changed size) 18.48.336.309 I slot release: id 3 | task 22818 | stop processing: n_tokens = 757, truncated = 0 18.48.342.962 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 341216933829 18.48.344.281 I slot launch_slot_: id 0 | task 22823 | processing task, is_child = 0 18.48.348.604 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 341216934153 18.48.348.664 I slot launch_slot_: id 1 | task 22824 | processing task, is_child = 0 18.48.348.744 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 819, t_last = 341216934462 18.48.348.800 I slot launch_slot_: id 2 | task 22825 | processing task, is_child = 0 18.48.348.840 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 757, t_last = 341216934791 18.48.348.894 I slot launch_slot_: id 3 | task 22826 | processing task, is_child = 0 18.52.340.201 I slot print_timing: id 0 | task 22823 | prompt processing, n_tokens = 877, progress = 1.00, t = 3.99 s / 219.73 tokens per second 18.52.989.208 I slot print_timing: id 1 | task 22824 | prompt processing, n_tokens = 881, progress = 1.00, t = 3.99 s / 220.73 tokens per second 18.52.989.379 I slot print_timing: id 2 | task 22825 | prompt processing, n_tokens = 893, progress = 1.00, t = 3.99 s / 223.74 tokens per second 18.52.989.528 I slot print_timing: id 3 | task 22826 | prompt processing, n_tokens = 899, progress = 1.00, t = 3.99 s / 225.25 tokens per second 18.53.142.974 I slot print_timing: id 0 | task 22823 | prompt eval time = 4753.62 ms / 881 tokens ( 5.40 ms per token, 185.33 tokens per second) 18.53.142.976 I slot print_timing: id 0 | task 22823 | eval time = 40.45 ms / 2 tokens ( 40.45 ms per token, 24.72 tokens per second) 18.53.142.977 I slot print_timing: id 0 | task 22823 | total time = 4794.07 ms / 883 tokens 18.53.142.977 I slot print_timing: id 0 | task 22823 | graphs reused = 21675 18.53.142.978 I slot print_timing: id 0 | task 22823 | graph reallocs = 0 / 0 (same size) / (changed size) 18.53.143.039 I slot release: id 0 | task 22823 | stop processing: n_tokens = 882, truncated = 0 18.53.143.322 I slot print_timing: id 1 | task 22824 | prompt eval time = 4753.85 ms / 885 tokens ( 5.37 ms per token, 186.16 tokens per second) 18.53.143.324 I slot print_timing: id 1 | task 22824 | eval time = 40.52 ms / 2 tokens ( 40.52 ms per token, 24.68 tokens per second) 18.53.143.325 I slot print_timing: id 1 | task 22824 | total time = 4794.37 ms / 887 tokens 18.53.143.325 I slot print_timing: id 1 | task 22824 | graphs reused = 21675 18.53.143.325 I slot print_timing: id 1 | task 22824 | graph reallocs = 0 / 0 (same size) / (changed size) 18.53.143.362 I slot release: id 1 | task 22824 | stop processing: n_tokens = 886, truncated = 0 18.53.143.628 I slot print_timing: id 2 | task 22825 | prompt eval time = 4754.09 ms / 897 tokens ( 5.30 ms per token, 188.68 tokens per second) 18.53.143.630 I slot print_timing: id 2 | task 22825 | eval time = 40.53 ms / 2 tokens ( 40.53 ms per token, 24.67 tokens per second) 18.53.143.631 I slot print_timing: id 2 | task 22825 | total time = 4794.62 ms / 899 tokens 18.53.143.631 I slot print_timing: id 2 | task 22825 | graphs reused = 21675 18.53.143.631 I slot print_timing: id 2 | task 22825 | graph reallocs = 0 / 0 (same size) / (changed size) 18.53.143.664 I slot release: id 2 | task 22825 | stop processing: n_tokens = 898, truncated = 0 18.53.143.980 I slot print_timing: id 3 | task 22826 | prompt eval time = 4754.36 ms / 903 tokens ( 5.27 ms per token, 189.93 tokens per second) 18.53.143.982 I slot print_timing: id 3 | task 22826 | eval time = 40.56 ms / 2 tokens ( 40.56 ms per token, 24.65 tokens per second) 18.53.143.982 I slot print_timing: id 3 | task 22826 | total time = 4794.93 ms / 905 tokens 18.53.143.983 I slot print_timing: id 3 | task 22826 | graphs reused = 21675 18.53.143.983 I slot print_timing: id 3 | task 22826 | graph reallocs = 0 / 0 (same size) / (changed size) 18.53.144.023 I slot release: id 3 | task 22826 | stop processing: n_tokens = 904, truncated = 0 18.53.150.606 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.912 18.53.150.637 I slot launch_slot_: id 0 | task 22831 | processing task, is_child = 0 18.53.155.797 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 886, t_last = 341221741844 18.53.155.884 I slot launch_slot_: id 1 | task 22832 | processing task, is_child = 0 18.53.155.973 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 898, t_last = 341221742146 18.53.156.034 I slot launch_slot_: id 2 | task 22833 | processing task, is_child = 0 18.53.156.084 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 341221742505 18.53.156.156 I slot launch_slot_: id 3 | task 22834 | processing task, is_child = 0 18.56.631.258 I slot print_timing: id 0 | task 22831 | prompt processing, n_tokens = 529, progress = 1.00, t = 3.48 s / 152.23 tokens per second 18.57.278.704 I slot print_timing: id 1 | task 22832 | prompt processing, n_tokens = 773, progress = 0.99, t = 3.47 s / 222.45 tokens per second 18.57.278.843 I slot print_timing: id 2 | task 22833 | prompt processing, n_tokens = 773, progress = 0.99, t = 3.47 s / 222.45 tokens per second 18.57.278.969 I slot print_timing: id 3 | task 22834 | prompt processing, n_tokens = 941, progress = 1.00, t = 3.47 s / 270.80 tokens per second 18.57.432.213 I slot print_timing: id 0 | task 22831 | prompt eval time = 4235.84 ms / 533 tokens ( 7.95 ms per token, 125.83 tokens per second) 18.57.432.218 I slot print_timing: id 0 | task 22831 | eval time = 40.21 ms / 2 tokens ( 40.21 ms per token, 24.87 tokens per second) 18.57.432.219 I slot print_timing: id 0 | task 22831 | total time = 4276.05 ms / 535 tokens 18.57.432.219 I slot print_timing: id 0 | task 22831 | graphs reused = 21677 18.57.432.220 I slot print_timing: id 0 | task 22831 | graph reallocs = 0 / 0 (same size) / (changed size) 18.57.432.271 I slot release: id 0 | task 22831 | stop processing: n_tokens = 899, truncated = 0 18.57.432.544 I slot print_timing: id 1 | task 22832 | prompt eval time = 4236.02 ms / 777 tokens ( 5.45 ms per token, 183.43 tokens per second) 18.57.432.546 I slot print_timing: id 1 | task 22832 | eval time = 40.27 ms / 2 tokens ( 40.27 ms per token, 24.83 tokens per second) 18.57.432.547 I slot print_timing: id 1 | task 22832 | total time = 4276.29 ms / 779 tokens 18.57.432.547 I slot print_timing: id 1 | task 22832 | graphs reused = 21677 18.57.432.547 I slot print_timing: id 1 | task 22832 | graph reallocs = 0 / 0 (same size) / (changed size) 18.57.432.586 I slot release: id 1 | task 22832 | stop processing: n_tokens = 778, truncated = 0 18.57.432.872 I slot print_timing: id 2 | task 22833 | prompt eval time = 4236.23 ms / 777 tokens ( 5.45 ms per token, 183.42 tokens per second) 18.57.432.874 I slot print_timing: id 2 | task 22833 | eval time = 40.31 ms / 2 tokens ( 40.31 ms per token, 24.81 tokens per second) 18.57.432.876 I slot print_timing: id 2 | task 22833 | total time = 4276.55 ms / 779 tokens 18.57.432.876 I slot print_timing: id 2 | task 22833 | graphs reused = 21677 18.57.432.876 I slot print_timing: id 2 | task 22833 | graph reallocs = 0 / 0 (same size) / (changed size) 18.57.432.911 I slot release: id 2 | task 22833 | stop processing: n_tokens = 778, truncated = 0 18.57.433.186 I slot print_timing: id 3 | task 22834 | prompt eval time = 4236.56 ms / 945 tokens ( 4.48 ms per token, 223.06 tokens per second) 18.57.433.187 I slot print_timing: id 3 | task 22834 | eval time = 40.23 ms / 2 tokens ( 40.23 ms per token, 24.86 tokens per second) 18.57.433.188 I slot print_timing: id 3 | task 22834 | total time = 4276.80 ms / 947 tokens 18.57.433.188 I slot print_timing: id 3 | task 22834 | graphs reused = 21677 18.57.433.188 I slot print_timing: id 3 | task 22834 | graph reallocs = 0 / 0 (same size) / (changed size) 18.57.433.229 I slot release: id 3 | task 22834 | stop processing: n_tokens = 946, truncated = 0 18.57.440.323 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 341226030754 18.57.442.229 I slot launch_slot_: id 0 | task 22839 | processing task, is_child = 0 18.57.446.795 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.871 18.57.446.814 I slot launch_slot_: id 3 | task 22841 | processing task, is_child = 0 18.57.446.894 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 341226031068 18.57.447.652 I slot launch_slot_: id 1 | task 22840 | processing task, is_child = 0 18.57.447.696 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 341226031393 18.57.447.754 I slot launch_slot_: id 2 | task 22842 | processing task, is_child = 0 19.01.459.907 I slot print_timing: id 0 | task 22839 | prompt processing, n_tokens = 876, progress = 1.00, t = 4.01 s / 218.37 tokens per second 19.01.460.062 I slot print_timing: id 2 | task 22842 | prompt processing, n_tokens = 908, progress = 1.00, t = 4.01 s / 226.36 tokens per second 19.01.561.610 I slot print_timing: id 1 | task 22840 | prompt eval time = 4011.80 ms / 500 tokens ( 8.02 ms per token, 124.63 tokens per second) 19.01.561.612 I slot print_timing: id 1 | task 22840 | eval time = 101.99 ms / 2 tokens ( 101.99 ms per token, 9.80 tokens per second) 19.01.561.613 I slot print_timing: id 1 | task 22840 | total time = 4113.79 ms / 502 tokens 19.01.561.613 I slot print_timing: id 1 | task 22840 | graphs reused = 21677 19.01.561.614 I slot print_timing: id 1 | task 22840 | graph reallocs = 0 / 0 (same size) / (changed size) 19.01.561.667 I slot release: id 1 | task 22840 | stop processing: n_tokens = 930, truncated = 0 19.01.562.300 I slot print_timing: id 3 | task 22841 | prompt eval time = 4011.91 ms / 494 tokens ( 8.12 ms per token, 123.13 tokens per second) 19.01.562.302 I slot print_timing: id 3 | task 22841 | eval time = 102.40 ms / 2 tokens ( 102.40 ms per token, 9.77 tokens per second) 19.01.562.302 I slot print_timing: id 3 | task 22841 | total time = 4114.31 ms / 496 tokens 19.01.562.303 I slot print_timing: id 3 | task 22841 | graphs reused = 21677 19.01.562.303 I slot print_timing: id 3 | task 22841 | graph reallocs = 0 / 0 (same size) / (changed size) 19.01.562.354 I slot release: id 3 | task 22841 | stop processing: n_tokens = 924, truncated = 0 19.01.592.305 I slot print_timing: id 0 | task 22839 | prompt eval time = 4113.57 ms / 880 tokens ( 4.67 ms per token, 213.93 tokens per second) 19.01.592.307 I slot print_timing: id 0 | task 22839 | eval time = 30.97 ms / 2 tokens ( 30.97 ms per token, 32.29 tokens per second) 19.01.592.308 I slot print_timing: id 0 | task 22839 | total time = 4144.54 ms / 882 tokens 19.01.592.308 I slot print_timing: id 0 | task 22839 | graphs reused = 21677 19.01.592.309 I slot print_timing: id 0 | task 22839 | graph reallocs = 0 / 0 (same size) / (changed size) 19.01.592.372 I slot release: id 0 | task 22839 | stop processing: n_tokens = 881, truncated = 0 19.01.592.756 I slot print_timing: id 2 | task 22842 | prompt eval time = 4114.06 ms / 912 tokens ( 4.51 ms per token, 221.68 tokens per second) 19.01.592.759 I slot print_timing: id 2 | task 22842 | eval time = 30.76 ms / 2 tokens ( 30.76 ms per token, 32.51 tokens per second) 19.01.592.760 I slot print_timing: id 2 | task 22842 | total time = 4144.82 ms / 914 tokens 19.01.592.760 I slot print_timing: id 2 | task 22842 | graphs reused = 21677 19.01.592.761 I slot print_timing: id 2 | task 22842 | graph reallocs = 0 / 0 (same size) / (changed size) 19.01.592.813 I slot release: id 2 | task 22842 | stop processing: n_tokens = 913, truncated = 0 19.01.592.819 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.891 (> 0.100 thold), f_keep = 0.894 19.01.592.849 I slot launch_slot_: id 0 | task 22847 | processing task, is_child = 0 19.01.598.215 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.863 19.01.598.244 I slot launch_slot_: id 2 | task 22848 | processing task, is_child = 0 19.01.635.325 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 930, t_last = 341230160150 19.01.635.433 I slot launch_slot_: id 1 | task 22850 | processing task, is_child = 0 19.01.635.498 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 924, t_last = 341230160836 19.02.256.635 I slot launch_slot_: id 3 | task 22851 | processing task, is_child = 0 19.05.298.733 I slot print_timing: id 2 | task 22848 | prompt eval time = 2940.40 ms / 486 tokens ( 6.05 ms per token, 165.28 tokens per second) 19.05.298.735 I slot print_timing: id 2 | task 22848 | eval time = 759.85 ms / 2 tokens ( 759.85 ms per token, 1.32 tokens per second) 19.05.298.736 I slot print_timing: id 2 | task 22848 | total time = 3700.25 ms / 488 tokens 19.05.298.736 I slot print_timing: id 2 | task 22848 | graphs reused = 21677 19.05.298.737 I slot print_timing: id 2 | task 22848 | graph reallocs = 0 / 0 (same size) / (changed size) 19.05.298.788 I slot release: id 2 | task 22848 | stop processing: n_tokens = 883, truncated = 0 19.05.299.094 I slot print_timing: id 1 | task 22850 | prompt processing, n_tokens = 1168, progress = 1.00, t = 3.04 s / 384.02 tokens per second 19.05.366.619 I slot print_timing: id 0 | task 22847 | prompt eval time = 3700.09 ms / 520 tokens ( 7.12 ms per token, 140.54 tokens per second) 19.05.366.621 I slot print_timing: id 0 | task 22847 | eval time = 68.15 ms / 2 tokens ( 68.15 ms per token, 14.67 tokens per second) 19.05.366.622 I slot print_timing: id 0 | task 22847 | total time = 3768.24 ms / 522 tokens 19.05.366.622 I slot print_timing: id 0 | task 22847 | graphs reused = 21677 19.05.366.623 I slot print_timing: id 0 | task 22847 | graph reallocs = 0 / 0 (same size) / (changed size) 19.05.366.684 I slot release: id 0 | task 22847 | stop processing: n_tokens = 885, truncated = 0 19.05.367.408 I slot print_timing: id 3 | task 22851 | prompt eval time = 3042.18 ms / 474 tokens ( 6.42 ms per token, 155.81 tokens per second) 19.05.367.415 I slot print_timing: id 3 | task 22851 | eval time = 68.32 ms / 2 tokens ( 68.32 ms per token, 14.64 tokens per second) 19.05.367.416 I slot print_timing: id 3 | task 22851 | total time = 3110.50 ms / 476 tokens 19.05.367.416 I slot print_timing: id 3 | task 22851 | graphs reused = 21677 19.05.367.417 I slot print_timing: id 3 | task 22851 | graph reallocs = 0 / 0 (same size) / (changed size) 19.05.367.463 I slot release: id 3 | task 22851 | stop processing: n_tokens = 871, truncated = 0 19.05.367.468 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 341233897270 19.05.368.474 I slot launch_slot_: id 2 | task 22855 | processing task, is_child = 0 19.06.330.183 I slot print_timing: id 1 | task 22850 | prompt eval time = 3110.36 ms / 1172 tokens ( 2.65 ms per token, 376.80 tokens per second) 19.06.330.185 I slot print_timing: id 1 | task 22850 | eval time = 963.12 ms / 2 tokens ( 963.12 ms per token, 1.04 tokens per second) 19.06.330.185 I slot print_timing: id 1 | task 22850 | total time = 4073.49 ms / 1174 tokens 19.06.330.186 I slot print_timing: id 1 | task 22850 | graphs reused = 21677 19.06.330.186 I slot print_timing: id 1 | task 22850 | graph reallocs = 0 / 0 (same size) / (changed size) 19.06.330.251 I slot release: id 1 | task 22850 | stop processing: n_tokens = 1173, truncated = 0 19.06.330.258 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.835 (> 0.100 thold), f_keep = 0.883 19.06.330.288 I slot launch_slot_: id 1 | task 22857 | processing task, is_child = 0 19.06.330.403 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 885, t_last = 341233965166 19.06.330.479 I slot launch_slot_: id 0 | task 22858 | processing task, is_child = 0 19.08.280.919 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 341233965945 19.08.281.025 I slot launch_slot_: id 3 | task 22860 | processing task, is_child = 0 19.11.295.895 I slot print_timing: id 0 | task 22858 | prompt processing, n_tokens = 2076, progress = 0.80, t = 4.97 s / 418.10 tokens per second 19.11.851.044 I slot print_timing: id 1 | task 22857 | prompt processing, n_tokens = 68, progress = 0.58, t = 3.01 s / 22.56 tokens per second 19.11.851.090 I slot print_timing: id 2 | task 22855 | prompt processing, n_tokens = 1175, progress = 1.00, t = 5.92 s / 198.36 tokens per second 19.14.108.333 I slot print_timing: id 0 | task 22858 | prompt processing, n_tokens = 2588, progress = 1.00, t = 7.78 s / 332.76 tokens per second 19.14.108.690 I slot print_timing: id 1 | task 22857 | prompt processing, n_tokens = 580, progress = 1.00, t = 5.83 s / 99.54 tokens per second 19.14.108.900 I slot print_timing: id 3 | task 22860 | prompt processing, n_tokens = 1983, progress = 0.79, t = 5.16 s / 384.00 tokens per second 19.14.865.837 I slot print_timing: id 2 | task 22855 | prompt eval time = 8736.10 ms / 1179 tokens ( 7.41 ms per token, 134.96 tokens per second) 19.14.865.844 I slot print_timing: id 2 | task 22855 | eval time = 757.52 ms / 2 tokens ( 757.52 ms per token, 1.32 tokens per second) 19.14.865.844 I slot print_timing: id 2 | task 22855 | total time = 9493.62 ms / 1181 tokens 19.14.865.845 I slot print_timing: id 2 | task 22855 | graphs reused = 21677 19.14.865.845 I slot print_timing: id 2 | task 22855 | graph reallocs = 0 / 0 (same size) / (changed size) 19.14.865.926 I slot release: id 2 | task 22855 | stop processing: n_tokens = 1180, truncated = 0 19.14.865.942 I slot print_timing: id 3 | task 22860 | prompt processing, n_tokens = 2495, progress = 1.00, t = 5.92 s / 421.38 tokens per second 19.14.927.400 I slot print_timing: id 0 | task 22858 | prompt eval time = 8534.71 ms / 2592 tokens ( 3.29 ms per token, 303.70 tokens per second) 19.14.927.406 I slot print_timing: id 0 | task 22858 | eval time = 62.15 ms / 2 tokens ( 62.15 ms per token, 16.09 tokens per second) 19.14.927.406 I slot print_timing: id 0 | task 22858 | total time = 8596.86 ms / 2594 tokens 19.14.927.406 I slot print_timing: id 0 | task 22858 | graphs reused = 21677 19.14.927.407 I slot print_timing: id 0 | task 22858 | graph reallocs = 0 / 0 (same size) / (changed size) 19.14.927.531 I slot release: id 0 | task 22858 | stop processing: n_tokens = 2593, truncated = 0 19.14.927.832 I slot print_timing: id 1 | task 22857 | prompt eval time = 6584.52 ms / 584 tokens ( 11.27 ms per token, 88.69 tokens per second) 19.14.927.834 I slot print_timing: id 1 | task 22857 | eval time = 62.27 ms / 2 tokens ( 62.27 ms per token, 16.06 tokens per second) 19.14.927.834 I slot print_timing: id 1 | task 22857 | total time = 6646.79 ms / 586 tokens 19.14.927.835 I slot print_timing: id 1 | task 22857 | graphs reused = 21677 19.14.927.835 I slot print_timing: id 1 | task 22857 | graph reallocs = 0 / 0 (same size) / (changed size) 19.14.927.891 I slot release: id 1 | task 22857 | stop processing: n_tokens = 1241, truncated = 0 19.14.928.302 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.846 (> 0.100 thold), f_keep = 0.896 19.14.928.334 I slot launch_slot_: id 0 | task 22865 | processing task, is_child = 0 19.15.246.375 I slot print_timing: id 3 | task 22860 | prompt eval time = 5984.38 ms / 2499 tokens ( 2.39 ms per token, 417.59 tokens per second) 19.15.246.378 I slot print_timing: id 3 | task 22860 | eval time = 318.07 ms / 2 tokens ( 318.07 ms per token, 3.14 tokens per second) 19.15.246.378 I slot print_timing: id 3 | task 22860 | total time = 6302.45 ms / 2501 tokens 19.15.246.378 I slot print_timing: id 3 | task 22860 | graphs reused = 21677 19.15.246.379 I slot print_timing: id 3 | task 22860 | graph reallocs = 0 / 0 (same size) / (changed size) 19.15.246.500 I slot release: id 3 | task 22860 | stop processing: n_tokens = 2500, truncated = 0 19.15.246.506 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1180, t_last = 341243464408 19.15.246.597 I slot launch_slot_: id 2 | task 22867 | processing task, is_child = 0 19.15.251.754 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.930 19.15.251.780 I slot launch_slot_: id 3 | task 22868 | processing task, is_child = 0 19.15.251.845 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1241, t_last = 341243526373 19.15.251.924 I slot launch_slot_: id 1 | task 22869 | processing task, is_child = 0 19.20.554.383 I slot print_timing: id 1 | task 22869 | prompt processing, n_tokens = 1807, progress = 1.00, t = 5.30 s / 340.81 tokens per second 19.20.554.653 I slot print_timing: id 2 | task 22867 | prompt processing, n_tokens = 1243, progress = 0.71, t = 5.30 s / 234.44 tokens per second 19.21.993.969 I slot print_timing: id 0 | task 22865 | prompt eval time = 5621.10 ms / 670 tokens ( 8.39 ms per token, 119.19 tokens per second) 19.21.993.972 I slot print_timing: id 0 | task 22865 | eval time = 1439.59 ms / 2 tokens ( 1439.59 ms per token, 0.69 tokens per second) 19.21.993.973 I slot print_timing: id 0 | task 22865 | total time = 7060.69 ms / 672 tokens 19.21.993.973 I slot print_timing: id 0 | task 22865 | graphs reused = 21677 19.21.993.974 I slot print_timing: id 0 | task 22865 | graph reallocs = 0 / 0 (same size) / (changed size) 19.21.994.105 I slot release: id 0 | task 22865 | stop processing: n_tokens = 2747, truncated = 0 19.21.994.418 I slot print_timing: id 2 | task 22867 | prompt processing, n_tokens = 1755, progress = 1.00, t = 6.74 s / 260.32 tokens per second 19.21.994.692 I slot print_timing: id 3 | task 22868 | prompt processing, n_tokens = 655, progress = 1.00, t = 3.80 s / 172.37 tokens per second 19.22.076.423 I slot print_timing: id 1 | task 22869 | prompt eval time = 6742.44 ms / 1811 tokens ( 3.72 ms per token, 268.60 tokens per second) 19.22.076.428 I slot print_timing: id 1 | task 22869 | eval time = 82.01 ms / 2 tokens ( 82.01 ms per token, 12.19 tokens per second) 19.22.076.428 I slot print_timing: id 1 | task 22869 | total time = 6824.45 ms / 1813 tokens 19.22.076.429 I slot print_timing: id 1 | task 22869 | graphs reused = 21677 19.22.076.429 I slot print_timing: id 1 | task 22869 | graph reallocs = 0 / 0 (same size) / (changed size) 19.22.076.524 I slot release: id 1 | task 22869 | stop processing: n_tokens = 1812, truncated = 0 19.22.077.365 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.728 (> 0.100 thold), f_keep = 0.806 19.22.077.401 I slot launch_slot_: id 1 | task 22874 | processing task, is_child = 0 19.22.083.308 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2747, t_last = 341250592588 19.22.083.452 I slot launch_slot_: id 0 | task 22875 | processing task, is_child = 0 19.24.177.291 I slot print_timing: id 2 | task 22867 | prompt eval time = 6824.85 ms / 1759 tokens ( 3.88 ms per token, 257.73 tokens per second) 19.24.177.295 I slot print_timing: id 2 | task 22867 | eval time = 2100.37 ms / 2 tokens ( 2100.37 ms per token, 0.48 tokens per second) 19.24.177.296 I slot print_timing: id 2 | task 22867 | total time = 8925.22 ms / 1761 tokens 19.24.177.296 I slot print_timing: id 2 | task 22867 | graphs reused = 21677 19.24.177.297 I slot print_timing: id 2 | task 22867 | graph reallocs = 0 / 0 (same size) / (changed size) 19.24.177.394 I slot release: id 2 | task 22867 | stop processing: n_tokens = 1760, truncated = 0 19.24.177.702 I slot print_timing: id 3 | task 22868 | prompt eval time = 3883.60 ms / 659 tokens ( 5.89 ms per token, 169.69 tokens per second) 19.24.177.705 I slot print_timing: id 3 | task 22868 | eval time = 2100.35 ms / 2 tokens ( 2100.35 ms per token, 0.48 tokens per second) 19.24.177.705 I slot print_timing: id 3 | task 22868 | total time = 5983.95 ms / 661 tokens 19.24.177.705 I slot print_timing: id 3 | task 22868 | graphs reused = 21677 19.24.177.706 I slot print_timing: id 3 | task 22868 | graph reallocs = 0 / 0 (same size) / (changed size) 19.24.177.838 I slot release: id 3 | task 22868 | stop processing: n_tokens = 2643, truncated = 0 19.24.845.015 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.836 (> 0.100 thold), f_keep = 0.830 19.24.845.058 I slot launch_slot_: id 2 | task 22878 | processing task, is_child = 0 19.25.507.364 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2643, t_last = 341252776321 19.25.507.519 I slot launch_slot_: id 3 | task 22879 | processing task, is_child = 0 19.28.818.173 I slot print_timing: id 0 | task 22875 | prompt eval time = 5982.41 ms / 1829 tokens ( 3.27 ms per token, 305.73 tokens per second) 19.28.818.175 I slot print_timing: id 0 | task 22875 | eval time = 752.30 ms / 2 tokens ( 752.30 ms per token, 1.33 tokens per second) 19.28.818.176 I slot print_timing: id 0 | task 22875 | total time = 6734.71 ms / 1831 tokens 19.28.818.176 I slot print_timing: id 0 | task 22875 | graphs reused = 21677 19.28.818.177 I slot print_timing: id 0 | task 22875 | graph reallocs = 0 / 0 (same size) / (changed size) 19.28.818.277 I slot release: id 0 | task 22875 | stop processing: n_tokens = 1830, truncated = 0 19.28.818.569 I slot print_timing: id 1 | task 22874 | prompt eval time = 5982.52 ms / 710 tokens ( 8.43 ms per token, 118.68 tokens per second) 19.28.818.572 I slot print_timing: id 1 | task 22874 | eval time = 752.40 ms / 2 tokens ( 752.40 ms per token, 1.33 tokens per second) 19.28.818.572 I slot print_timing: id 1 | task 22874 | total time = 6734.93 ms / 712 tokens 19.28.818.572 I slot print_timing: id 1 | task 22874 | graphs reused = 21677 19.28.818.573 I slot print_timing: id 1 | task 22874 | graph reallocs = 0 / 0 (same size) / (changed size) 19.28.818.659 I slot release: id 1 | task 22874 | stop processing: n_tokens = 2006, truncated = 0 19.28.819.085 I slot print_timing: id 3 | task 22879 | prompt processing, n_tokens = 1904, progress = 1.00, t = 3.31 s / 575.29 tokens per second 19.28.872.154 I slot print_timing: id 2 | task 22878 | prompt eval time = 3311.01 ms / 504 tokens ( 6.57 ms per token, 152.22 tokens per second) 19.28.872.156 I slot print_timing: id 2 | task 22878 | eval time = 53.08 ms / 2 tokens ( 53.08 ms per token, 18.84 tokens per second) 19.28.872.157 I slot print_timing: id 2 | task 22878 | total time = 3364.09 ms / 506 tokens 19.28.872.157 I slot print_timing: id 2 | task 22878 | graphs reused = 21677 19.28.872.158 I slot print_timing: id 2 | task 22878 | graph reallocs = 0 / 0 (same size) / (changed size) 19.28.872.247 I slot release: id 2 | task 22878 | stop processing: n_tokens = 1748, truncated = 0 19.28.872.655 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1830, t_last = 341257416760 19.28.876.055 I slot launch_slot_: id 0 | task 22883 | processing task, is_child = 0 19.28.882.599 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2006, t_last = 341257417142 19.28.882.711 I slot launch_slot_: id 1 | task 22884 | processing task, is_child = 0 19.28.882.784 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1748, t_last = 341257470729 19.28.882.874 I slot launch_slot_: id 2 | task 22885 | processing task, is_child = 0 19.30.044.491 I slot print_timing: id 3 | task 22879 | prompt eval time = 3364.39 ms / 1908 tokens ( 1.76 ms per token, 567.12 tokens per second) 19.30.044.493 I slot print_timing: id 3 | task 22879 | eval time = 1171.83 ms / 2 tokens ( 1171.83 ms per token, 0.85 tokens per second) 19.30.044.493 I slot print_timing: id 3 | task 22879 | total time = 4536.23 ms / 1910 tokens 19.30.044.494 I slot print_timing: id 3 | task 22879 | graphs reused = 21677 19.30.044.494 I slot print_timing: id 3 | task 22879 | graph reallocs = 0 / 0 (same size) / (changed size) 19.30.044.609 I slot release: id 3 | task 22879 | stop processing: n_tokens = 1909, truncated = 0 19.32.011.582 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1909, t_last = 341258643092 19.32.058.479 I slot launch_slot_: id 3 | task 22888 | processing task, is_child = 0 19.32.058.494 I slot print_timing: id 0 | task 22883 | prompt processing, n_tokens = 729, progress = 0.99, t = 3.13 s / 233.00 tokens per second 19.32.058.679 I slot print_timing: id 1 | task 22884 | prompt processing, n_tokens = 707, progress = 0.99, t = 3.13 s / 225.98 tokens per second 19.32.058.825 I slot print_timing: id 2 | task 22885 | prompt processing, n_tokens = 740, progress = 0.99, t = 3.13 s / 236.54 tokens per second 19.33.184.006 I slot print_timing: id 0 | task 22883 | prompt eval time = 3617.11 ms / 733 tokens ( 4.93 ms per token, 202.65 tokens per second) 19.33.184.009 I slot print_timing: id 0 | task 22883 | eval time = 684.01 ms / 2 tokens ( 684.01 ms per token, 1.46 tokens per second) 19.33.184.009 I slot print_timing: id 0 | task 22883 | total time = 4301.12 ms / 735 tokens 19.33.184.010 I slot print_timing: id 0 | task 22883 | graphs reused = 21678 19.33.184.010 I slot print_timing: id 0 | task 22883 | graph reallocs = 0 / 0 (same size) / (changed size) 19.33.184.054 I slot release: id 0 | task 22883 | stop processing: n_tokens = 734, truncated = 0 19.33.184.340 I slot print_timing: id 1 | task 22884 | prompt eval time = 3617.27 ms / 711 tokens ( 5.09 ms per token, 196.56 tokens per second) 19.33.184.347 I slot print_timing: id 1 | task 22884 | eval time = 684.06 ms / 2 tokens ( 684.06 ms per token, 1.46 tokens per second) 19.33.184.348 I slot print_timing: id 1 | task 22884 | total time = 4301.34 ms / 713 tokens 19.33.184.349 I slot print_timing: id 1 | task 22884 | graphs reused = 21678 19.33.184.349 I slot print_timing: id 1 | task 22884 | graph reallocs = 0 / 0 (same size) / (changed size) 19.33.184.384 I slot release: id 1 | task 22884 | stop processing: n_tokens = 712, truncated = 0 19.33.184.674 I slot print_timing: id 2 | task 22885 | prompt eval time = 3617.54 ms / 744 tokens ( 4.86 ms per token, 205.66 tokens per second) 19.33.184.677 I slot print_timing: id 2 | task 22885 | eval time = 684.00 ms / 2 tokens ( 684.00 ms per token, 1.46 tokens per second) 19.33.184.678 I slot print_timing: id 2 | task 22885 | total time = 4301.54 ms / 746 tokens 19.33.184.678 I slot print_timing: id 2 | task 22885 | graphs reused = 21678 19.33.184.678 I slot print_timing: id 2 | task 22885 | graph reallocs = 0 / 0 (same size) / (changed size) 19.33.184.723 I slot release: id 2 | task 22885 | stop processing: n_tokens = 745, truncated = 0 19.33.221.512 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.864 (> 0.100 thold), f_keep = 0.854 19.33.221.538 I slot launch_slot_: id 0 | task 22892 | processing task, is_child = 0 19.33.224.525 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 712, t_last = 341261782866 19.33.224.593 I slot launch_slot_: id 1 | task 22893 | processing task, is_child = 0 19.33.224.636 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 745, t_last = 341261783205 19.33.224.693 I slot launch_slot_: id 2 | task 22894 | processing task, is_child = 0 19.35.079.655 I slot print_timing: id 3 | task 22888 | prompt eval time = 1162.52 ms / 710 tokens ( 1.64 ms per token, 610.74 tokens per second) 19.35.079.658 I slot print_timing: id 3 | task 22888 | eval time = 1858.14 ms / 2 tokens ( 1858.14 ms per token, 0.54 tokens per second) 19.35.079.659 I slot print_timing: id 3 | task 22888 | total time = 3020.66 ms / 712 tokens 19.35.079.659 I slot print_timing: id 3 | task 22888 | graphs reused = 21678 19.35.079.660 I slot print_timing: id 3 | task 22888 | graph reallocs = 0 / 0 (same size) / (changed size) 19.35.079.711 I slot release: id 3 | task 22888 | stop processing: n_tokens = 711, truncated = 0 19.36.455.247 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 341263678193 19.36.457.321 I slot launch_slot_: id 3 | task 22897 | processing task, is_child = 0 19.36.457.342 I slot print_timing: id 1 | task 22893 | prompt processing, n_tokens = 1036, progress = 1.00, t = 3.23 s / 320.73 tokens per second 19.36.457.555 I slot print_timing: id 2 | task 22894 | prompt processing, n_tokens = 785, progress = 0.99, t = 3.23 s / 243.03 tokens per second 19.36.966.832 I slot print_timing: id 0 | task 22892 | prompt eval time = 3230.54 ms / 509 tokens ( 6.35 ms per token, 157.56 tokens per second) 19.36.966.837 I slot print_timing: id 0 | task 22892 | eval time = 511.59 ms / 2 tokens ( 511.59 ms per token, 1.95 tokens per second) 19.36.966.837 I slot print_timing: id 0 | task 22892 | total time = 3742.13 ms / 511 tokens 19.36.966.838 I slot print_timing: id 0 | task 22892 | graphs reused = 21678 19.36.966.838 I slot print_timing: id 0 | task 22892 | graph reallocs = 0 / 0 (same size) / (changed size) 19.36.966.883 I slot release: id 0 | task 22892 | stop processing: n_tokens = 727, truncated = 0 19.37.647.848 I slot print_timing: id 1 | task 22893 | prompt eval time = 3742.36 ms / 1040 tokens ( 3.60 ms per token, 277.90 tokens per second) 19.37.647.851 I slot print_timing: id 1 | task 22893 | eval time = 680.65 ms / 2 tokens ( 680.65 ms per token, 1.47 tokens per second) 19.37.647.852 I slot print_timing: id 1 | task 22893 | total time = 4423.01 ms / 1042 tokens 19.37.647.852 I slot print_timing: id 1 | task 22893 | graphs reused = 21678 19.37.647.853 I slot print_timing: id 1 | task 22893 | graph reallocs = 0 / 0 (same size) / (changed size) 19.37.647.911 I slot release: id 1 | task 22893 | stop processing: n_tokens = 1041, truncated = 0 19.37.648.208 I slot print_timing: id 2 | task 22894 | prompt eval time = 3742.59 ms / 789 tokens ( 4.74 ms per token, 210.82 tokens per second) 19.37.648.211 I slot print_timing: id 2 | task 22894 | eval time = 680.73 ms / 2 tokens ( 680.73 ms per token, 1.47 tokens per second) 19.37.648.211 I slot print_timing: id 2 | task 22894 | total time = 4423.32 ms / 791 tokens 19.37.648.212 I slot print_timing: id 2 | task 22894 | graphs reused = 21678 19.37.648.212 I slot print_timing: id 2 | task 22894 | graph reallocs = 0 / 0 (same size) / (changed size) 19.37.648.254 I slot release: id 2 | task 22894 | stop processing: n_tokens = 790, truncated = 0 19.37.648.259 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 341265565365 19.37.650.270 I slot launch_slot_: id 0 | task 22900 | processing task, is_child = 0 19.37.654.036 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1041, t_last = 341266246393 19.37.654.129 I slot launch_slot_: id 1 | task 22901 | processing task, is_child = 0 19.37.654.173 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 341266246736 19.37.654.234 I slot launch_slot_: id 2 | task 22902 | processing task, is_child = 0 19.41.125.832 I slot print_timing: id 3 | task 22897 | prompt eval time = 2629.70 ms / 784 tokens ( 3.35 ms per token, 298.13 tokens per second) 19.41.125.834 I slot print_timing: id 3 | task 22897 | eval time = 2038.40 ms / 2 tokens ( 2038.40 ms per token, 0.49 tokens per second) 19.41.125.835 I slot print_timing: id 3 | task 22897 | total time = 4668.10 ms / 786 tokens 19.41.125.835 I slot print_timing: id 3 | task 22897 | graphs reused = 21678 19.41.125.836 I slot print_timing: id 3 | task 22897 | graph reallocs = 0 / 0 (same size) / (changed size) 19.41.125.884 I slot release: id 3 | task 22897 | stop processing: n_tokens = 785, truncated = 0 19.41.125.896 I slot print_timing: id 0 | task 22900 | prompt processing, n_tokens = 772, progress = 0.99, t = 3.47 s / 222.39 tokens per second 19.41.126.038 I slot print_timing: id 1 | task 22901 | prompt processing, n_tokens = 821, progress = 1.00, t = 3.47 s / 236.51 tokens per second 19.41.126.171 I slot print_timing: id 2 | task 22902 | prompt processing, n_tokens = 827, progress = 1.00, t = 3.47 s / 238.25 tokens per second 19.41.214.925 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 785, t_last = 341269724366 19.41.216.876 I slot launch_slot_: id 3 | task 22906 | processing task, is_child = 0 19.41.757.041 I slot print_timing: id 0 | task 22900 | prompt eval time = 3559.94 ms / 776 tokens ( 4.59 ms per token, 217.98 tokens per second) 19.41.757.046 I slot print_timing: id 0 | task 22900 | eval time = 542.86 ms / 2 tokens ( 542.86 ms per token, 1.84 tokens per second) 19.41.757.047 I slot print_timing: id 0 | task 22900 | total time = 4102.80 ms / 778 tokens 19.41.757.047 I slot print_timing: id 0 | task 22900 | graphs reused = 21678 19.41.757.048 I slot print_timing: id 0 | task 22900 | graph reallocs = 0 / 0 (same size) / (changed size) 19.41.757.092 I slot release: id 0 | task 22900 | stop processing: n_tokens = 777, truncated = 0 19.41.757.364 I slot print_timing: id 1 | task 22901 | prompt eval time = 3560.24 ms / 825 tokens ( 4.32 ms per token, 231.73 tokens per second) 19.41.757.366 I slot print_timing: id 1 | task 22901 | eval time = 542.83 ms / 2 tokens ( 542.83 ms per token, 1.84 tokens per second) 19.41.757.367 I slot print_timing: id 1 | task 22901 | total time = 4103.06 ms / 827 tokens 19.41.757.368 I slot print_timing: id 1 | task 22901 | graphs reused = 21678 19.41.757.368 I slot print_timing: id 1 | task 22901 | graph reallocs = 0 / 0 (same size) / (changed size) 19.41.757.412 I slot release: id 1 | task 22901 | stop processing: n_tokens = 826, truncated = 0 19.41.757.714 I slot print_timing: id 2 | task 22902 | prompt eval time = 3560.55 ms / 831 tokens ( 4.28 ms per token, 233.39 tokens per second) 19.41.757.716 I slot print_timing: id 2 | task 22902 | eval time = 542.79 ms / 2 tokens ( 542.79 ms per token, 1.84 tokens per second) 19.41.757.717 I slot print_timing: id 2 | task 22902 | total time = 4103.35 ms / 833 tokens 19.41.757.717 I slot print_timing: id 2 | task 22902 | graphs reused = 21678 19.41.757.718 I slot print_timing: id 2 | task 22902 | graph reallocs = 0 / 0 (same size) / (changed size) 19.41.757.757 I slot release: id 2 | task 22902 | stop processing: n_tokens = 832, truncated = 0 19.42.442.002 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.891 19.42.442.029 I slot launch_slot_: id 1 | task 22910 | processing task, is_child = 0 19.42.447.231 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 777, t_last = 341270355574 19.42.447.326 I slot launch_slot_: id 0 | task 22911 | processing task, is_child = 0 19.42.447.376 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.825 (> 0.100 thold), f_keep = 0.885 19.42.447.396 I slot launch_slot_: id 2 | task 22912 | processing task, is_child = 0 19.43.126.646 I slot print_timing: id 3 | task 22906 | prompt eval time = 1225.11 ms / 885 tokens ( 1.38 ms per token, 722.39 tokens per second) 19.43.126.649 I slot print_timing: id 3 | task 22906 | eval time = 684.65 ms / 2 tokens ( 684.65 ms per token, 1.46 tokens per second) 19.43.126.649 I slot print_timing: id 3 | task 22906 | total time = 1909.76 ms / 887 tokens 19.43.126.650 I slot print_timing: id 3 | task 22906 | graphs reused = 21678 19.43.126.650 I slot print_timing: id 3 | task 22906 | graph reallocs = 0 / 0 (same size) / (changed size) 19.43.126.699 I slot release: id 3 | task 22906 | stop processing: n_tokens = 886, truncated = 0 19.45.102.966 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 886, t_last = 341271725181 19.45.149.262 I slot launch_slot_: id 3 | task 22915 | processing task, is_child = 0 19.46.355.567 I slot print_timing: id 0 | task 22911 | prompt eval time = 3223.25 ms / 677 tokens ( 4.76 ms per token, 210.04 tokens per second) 19.46.355.569 I slot print_timing: id 0 | task 22911 | eval time = 684.91 ms / 2 tokens ( 684.91 ms per token, 1.46 tokens per second) 19.46.355.569 I slot print_timing: id 0 | task 22911 | total time = 3908.16 ms / 679 tokens 19.46.355.570 I slot print_timing: id 0 | task 22911 | graphs reused = 21679 19.46.355.570 I slot print_timing: id 0 | task 22911 | graph reallocs = 0 / 0 (same size) / (changed size) 19.46.355.610 I slot release: id 0 | task 22911 | stop processing: n_tokens = 678, truncated = 0 19.46.355.910 I slot print_timing: id 1 | task 22910 | prompt eval time = 3223.53 ms / 539 tokens ( 5.98 ms per token, 167.21 tokens per second) 19.46.355.911 I slot print_timing: id 1 | task 22910 | eval time = 684.89 ms / 2 tokens ( 684.89 ms per token, 1.46 tokens per second) 19.46.355.912 I slot print_timing: id 1 | task 22910 | total time = 3908.42 ms / 541 tokens 19.46.355.912 I slot print_timing: id 1 | task 22910 | graphs reused = 21679 19.46.355.912 I slot print_timing: id 1 | task 22910 | graph reallocs = 0 / 0 (same size) / (changed size) 19.46.355.957 I slot release: id 1 | task 22910 | stop processing: n_tokens = 849, truncated = 0 19.46.356.245 I slot print_timing: id 2 | task 22912 | prompt eval time = 3223.77 ms / 577 tokens ( 5.59 ms per token, 178.98 tokens per second) 19.46.356.248 I slot print_timing: id 2 | task 22912 | eval time = 684.87 ms / 2 tokens ( 684.87 ms per token, 1.46 tokens per second) 19.46.356.248 I slot print_timing: id 2 | task 22912 | total time = 3908.64 ms / 579 tokens 19.46.356.248 I slot print_timing: id 2 | task 22912 | graphs reused = 21679 19.46.356.249 I slot print_timing: id 2 | task 22912 | graph reallocs = 0 / 0 (same size) / (changed size) 19.46.356.305 I slot release: id 2 | task 22912 | stop processing: n_tokens = 893, truncated = 0 19.46.393.037 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 341274954092 19.46.394.485 I slot launch_slot_: id 0 | task 22919 | processing task, is_child = 0 19.46.398.041 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 849, t_last = 341274954439 19.46.398.119 I slot launch_slot_: id 1 | task 22921 | processing task, is_child = 0 19.46.398.169 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 893, t_last = 341274954789 19.46.398.232 I slot launch_slot_: id 2 | task 22920 | processing task, is_child = 0 19.47.741.228 I slot print_timing: id 3 | task 22915 | prompt eval time = 1243.35 ms / 792 tokens ( 1.57 ms per token, 636.99 tokens per second) 19.47.741.231 I slot print_timing: id 3 | task 22915 | eval time = 1348.19 ms / 2 tokens ( 1348.19 ms per token, 0.74 tokens per second) 19.47.741.231 I slot print_timing: id 3 | task 22915 | total time = 2591.54 ms / 794 tokens 19.47.741.232 I slot print_timing: id 3 | task 22915 | graphs reused = 21679 19.47.741.232 I slot print_timing: id 3 | task 22915 | graph reallocs = 0 / 0 (same size) / (changed size) 19.47.741.283 I slot release: id 3 | task 22915 | stop processing: n_tokens = 793, truncated = 0 19.49.721.149 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 793, t_last = 341276339765 19.49.767.288 I slot launch_slot_: id 3 | task 22924 | processing task, is_child = 0 19.49.767.304 I slot print_timing: id 0 | task 22919 | prompt processing, n_tokens = 809, progress = 1.00, t = 3.32 s / 243.46 tokens per second 19.49.767.451 I slot print_timing: id 1 | task 22921 | prompt processing, n_tokens = 736, progress = 0.99, t = 3.32 s / 221.50 tokens per second 19.49.767.592 I slot print_timing: id 2 | task 22920 | prompt processing, n_tokens = 715, progress = 0.99, t = 3.32 s / 215.18 tokens per second 19.50.882.374 I slot print_timing: id 0 | task 22919 | prompt eval time = 3800.11 ms / 813 tokens ( 4.67 ms per token, 213.94 tokens per second) 19.50.882.376 I slot print_timing: id 0 | task 22919 | eval time = 684.01 ms / 2 tokens ( 684.01 ms per token, 1.46 tokens per second) 19.50.882.377 I slot print_timing: id 0 | task 22919 | total time = 4484.12 ms / 815 tokens 19.50.882.377 I slot print_timing: id 0 | task 22919 | graphs reused = 21679 19.50.882.378 I slot print_timing: id 0 | task 22919 | graph reallocs = 0 / 0 (same size) / (changed size) 19.50.882.444 I slot release: id 0 | task 22919 | stop processing: n_tokens = 814, truncated = 0 19.50.882.722 I slot print_timing: id 1 | task 22921 | prompt eval time = 3800.34 ms / 740 tokens ( 5.14 ms per token, 194.72 tokens per second) 19.50.882.725 I slot print_timing: id 1 | task 22921 | eval time = 684.09 ms / 2 tokens ( 684.09 ms per token, 1.46 tokens per second) 19.50.882.725 I slot print_timing: id 1 | task 22921 | total time = 4484.43 ms / 742 tokens 19.50.882.725 I slot print_timing: id 1 | task 22921 | graphs reused = 21679 19.50.882.726 I slot print_timing: id 1 | task 22921 | graph reallocs = 0 / 0 (same size) / (changed size) 19.50.882.771 I slot release: id 1 | task 22921 | stop processing: n_tokens = 741, truncated = 0 19.50.883.046 I slot print_timing: id 2 | task 22920 | prompt eval time = 3800.57 ms / 719 tokens ( 5.29 ms per token, 189.18 tokens per second) 19.50.883.048 I slot print_timing: id 2 | task 22920 | eval time = 684.13 ms / 2 tokens ( 684.13 ms per token, 1.46 tokens per second) 19.50.883.049 I slot print_timing: id 2 | task 22920 | total time = 4484.70 ms / 721 tokens 19.50.883.049 I slot print_timing: id 2 | task 22920 | graphs reused = 21679 19.50.883.050 I slot print_timing: id 2 | task 22920 | graph reallocs = 0 / 0 (same size) / (changed size) 19.50.883.098 I slot release: id 2 | task 22920 | stop processing: n_tokens = 720, truncated = 0 19.50.919.711 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 814, t_last = 341279480926 19.50.921.487 I slot launch_slot_: id 0 | task 22928 | processing task, is_child = 0 19.50.924.417 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 341279481254 19.50.924.485 I slot launch_slot_: id 1 | task 22929 | processing task, is_child = 0 19.50.924.529 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 341279481580 19.50.924.589 I slot launch_slot_: id 2 | task 22930 | processing task, is_child = 0 19.51.890.610 I slot print_timing: id 3 | task 22924 | prompt eval time = 1151.98 ms / 694 tokens ( 1.66 ms per token, 602.44 tokens per second) 19.51.890.612 I slot print_timing: id 3 | task 22924 | eval time = 970.90 ms / 2 tokens ( 970.90 ms per token, 1.03 tokens per second) 19.51.890.613 I slot print_timing: id 3 | task 22924 | total time = 2122.88 ms / 696 tokens 19.51.890.613 I slot print_timing: id 3 | task 22924 | graphs reused = 21679 19.51.890.613 I slot print_timing: id 3 | task 22924 | graph reallocs = 0 / 0 (same size) / (changed size) 19.51.890.659 I slot release: id 3 | task 22924 | stop processing: n_tokens = 695, truncated = 0 19.53.859.699 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.881 19.53.859.737 I slot launch_slot_: id 3 | task 22933 | processing task, is_child = 0 19.54.703.271 I slot print_timing: id 0 | task 22928 | prompt eval time = 3093.11 ms / 693 tokens ( 4.46 ms per token, 224.05 tokens per second) 19.54.703.274 I slot print_timing: id 0 | task 22928 | eval time = 685.57 ms / 2 tokens ( 685.57 ms per token, 1.46 tokens per second) 19.54.703.274 I slot print_timing: id 0 | task 22928 | total time = 3778.67 ms / 695 tokens 19.54.703.275 I slot print_timing: id 0 | task 22928 | graphs reused = 21680 19.54.703.275 I slot print_timing: id 0 | task 22928 | graph reallocs = 0 / 0 (same size) / (changed size) 19.54.703.316 I slot release: id 0 | task 22928 | stop processing: n_tokens = 694, truncated = 0 19.54.703.594 I slot print_timing: id 1 | task 22929 | prompt eval time = 3093.31 ms / 718 tokens ( 4.31 ms per token, 232.11 tokens per second) 19.54.703.596 I slot print_timing: id 1 | task 22929 | eval time = 685.62 ms / 2 tokens ( 685.62 ms per token, 1.46 tokens per second) 19.54.703.596 I slot print_timing: id 1 | task 22929 | total time = 3778.93 ms / 720 tokens 19.54.703.596 I slot print_timing: id 1 | task 22929 | graphs reused = 21680 19.54.703.597 I slot print_timing: id 1 | task 22929 | graph reallocs = 0 / 0 (same size) / (changed size) 19.54.703.635 I slot release: id 1 | task 22929 | stop processing: n_tokens = 719, truncated = 0 19.54.703.930 I slot print_timing: id 2 | task 22930 | prompt eval time = 3093.55 ms / 694 tokens ( 4.46 ms per token, 224.34 tokens per second) 19.54.703.932 I slot print_timing: id 2 | task 22930 | eval time = 685.67 ms / 2 tokens ( 685.67 ms per token, 1.46 tokens per second) 19.54.703.933 I slot print_timing: id 2 | task 22930 | total time = 3779.22 ms / 696 tokens 19.54.703.933 I slot print_timing: id 2 | task 22930 | graphs reused = 21680 19.54.703.933 I slot print_timing: id 2 | task 22930 | graph reallocs = 0 / 0 (same size) / (changed size) 19.54.703.958 I slot release: id 2 | task 22930 | stop processing: n_tokens = 695, truncated = 0 19.54.740.803 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.885 19.54.740.847 I slot launch_slot_: id 0 | task 22937 | processing task, is_child = 0 19.54.743.773 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.851 19.54.743.793 I slot launch_slot_: id 1 | task 22938 | processing task, is_child = 0 19.54.743.835 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.881 19.54.743.850 I slot launch_slot_: id 2 | task 22939 | processing task, is_child = 0 19.56.832.127 I slot print_timing: id 3 | task 22933 | prompt eval time = 835.04 ms / 518 tokens ( 1.61 ms per token, 620.33 tokens per second) 19.56.832.130 I slot print_timing: id 3 | task 22933 | eval time = 2091.32 ms / 2 tokens ( 2091.32 ms per token, 0.48 tokens per second) 19.56.832.131 I slot print_timing: id 3 | task 22933 | total time = 2926.36 ms / 520 tokens 19.56.832.131 I slot print_timing: id 3 | task 22933 | graphs reused = 21680 19.56.832.132 I slot print_timing: id 3 | task 22933 | graph reallocs = 0 / 0 (same size) / (changed size) 19.56.832.176 I slot release: id 3 | task 22933 | stop processing: n_tokens = 697, truncated = 0 19.56.920.977 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.878 19.56.921.015 I slot launch_slot_: id 3 | task 22942 | processing task, is_child = 0 19.56.973.491 I slot print_timing: id 0 | task 22937 | prompt eval time = 2176.54 ms / 513 tokens ( 4.24 ms per token, 235.70 tokens per second) 19.56.973.495 I slot print_timing: id 0 | task 22937 | eval time = 53.10 ms / 2 tokens ( 53.10 ms per token, 18.83 tokens per second) 19.56.973.496 I slot print_timing: id 0 | task 22937 | total time = 2229.63 ms / 515 tokens 19.56.973.497 I slot print_timing: id 0 | task 22937 | graphs reused = 21680 19.56.973.497 I slot print_timing: id 0 | task 22937 | graph reallocs = 0 / 0 (same size) / (changed size) 19.56.973.537 I slot release: id 0 | task 22937 | stop processing: n_tokens = 691, truncated = 0 19.56.973.808 I slot print_timing: id 1 | task 22938 | prompt eval time = 2176.70 ms / 499 tokens ( 4.36 ms per token, 229.25 tokens per second) 19.56.973.815 I slot print_timing: id 1 | task 22938 | eval time = 53.13 ms / 2 tokens ( 53.13 ms per token, 18.82 tokens per second) 19.56.973.816 I slot print_timing: id 1 | task 22938 | total time = 2229.84 ms / 501 tokens 19.56.973.816 I slot print_timing: id 1 | task 22938 | graphs reused = 21680 19.56.973.816 I slot print_timing: id 1 | task 22938 | graph reallocs = 0 / 0 (same size) / (changed size) 19.56.973.846 I slot release: id 1 | task 22938 | stop processing: n_tokens = 702, truncated = 0 19.56.974.124 I slot print_timing: id 2 | task 22939 | prompt eval time = 2176.89 ms / 510 tokens ( 4.27 ms per token, 234.28 tokens per second) 19.56.974.127 I slot print_timing: id 2 | task 22939 | eval time = 53.16 ms / 2 tokens ( 53.16 ms per token, 18.81 tokens per second) 19.56.974.127 I slot print_timing: id 2 | task 22939 | total time = 2230.05 ms / 512 tokens 19.56.974.127 I slot print_timing: id 2 | task 22939 | graphs reused = 21680 19.56.974.128 I slot print_timing: id 2 | task 22939 | graph reallocs = 0 / 0 (same size) / (changed size) 19.56.974.163 I slot release: id 2 | task 22939 | stop processing: n_tokens = 689, truncated = 0 19.56.981.248 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.837 (> 0.100 thold), f_keep = 0.886 19.56.981.283 I slot launch_slot_: id 0 | task 22945 | processing task, is_child = 0 19.57.622.839 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.872 19.57.622.883 I slot launch_slot_: id 1 | task 22946 | processing task, is_child = 0 19.57.622.927 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 689, t_last = 341285572645 19.57.622.992 I slot launch_slot_: id 2 | task 22947 | processing task, is_child = 0 20.00.579.285 I slot print_timing: id 3 | task 22942 | prompt eval time = 2270.63 ms / 518 tokens ( 4.38 ms per token, 228.13 tokens per second) 20.00.579.288 I slot print_timing: id 3 | task 22942 | eval time = 1387.63 ms / 2 tokens ( 1387.63 ms per token, 0.72 tokens per second) 20.00.579.288 I slot print_timing: id 3 | task 22942 | total time = 3658.26 ms / 520 tokens 20.00.579.289 I slot print_timing: id 3 | task 22942 | graphs reused = 21680 20.00.579.289 I slot print_timing: id 3 | task 22942 | graph reallocs = 0 / 0 (same size) / (changed size) 20.00.579.330 I slot release: id 3 | task 22942 | stop processing: n_tokens = 699, truncated = 0 20.00.667.596 I slot print_timing: id 1 | task 22946 | prompt eval time = 2955.88 ms / 489 tokens ( 6.04 ms per token, 165.43 tokens per second) 20.00.667.598 I slot print_timing: id 1 | task 22946 | eval time = 88.59 ms / 2 tokens ( 88.59 ms per token, 11.29 tokens per second) 20.00.667.599 I slot print_timing: id 1 | task 22946 | total time = 3044.47 ms / 491 tokens 20.00.667.599 I slot print_timing: id 1 | task 22946 | graphs reused = 21680 20.00.667.599 I slot print_timing: id 1 | task 22946 | graph reallocs = 0 / 0 (same size) / (changed size) 20.00.667.641 I slot release: id 1 | task 22946 | stop processing: n_tokens = 692, truncated = 0 20.00.668.014 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 699, t_last = 341289177812 20.00.669.686 I slot launch_slot_: id 3 | task 22951 | processing task, is_child = 0 20.01.181.461 I slot print_timing: id 0 | task 22945 | prompt eval time = 3044.34 ms / 554 tokens ( 5.50 ms per token, 181.98 tokens per second) 20.01.181.464 I slot print_timing: id 0 | task 22945 | eval time = 514.12 ms / 2 tokens ( 514.12 ms per token, 1.95 tokens per second) 20.01.181.464 I slot print_timing: id 0 | task 22945 | total time = 3558.46 ms / 556 tokens 20.01.181.465 I slot print_timing: id 0 | task 22945 | graphs reused = 21680 20.01.181.465 I slot print_timing: id 0 | task 22945 | graph reallocs = 0 / 0 (same size) / (changed size) 20.01.181.505 I slot release: id 0 | task 22945 | stop processing: n_tokens = 732, truncated = 0 20.01.181.784 I slot print_timing: id 2 | task 22947 | prompt eval time = 3044.70 ms / 874 tokens ( 3.48 ms per token, 287.06 tokens per second) 20.01.181.787 I slot print_timing: id 2 | task 22947 | eval time = 513.77 ms / 2 tokens ( 513.77 ms per token, 1.95 tokens per second) 20.01.181.787 I slot print_timing: id 2 | task 22947 | total time = 3558.47 ms / 876 tokens 20.01.181.787 I slot print_timing: id 2 | task 22947 | graphs reused = 21680 20.01.181.788 I slot print_timing: id 2 | task 22947 | graph reallocs = 0 / 0 (same size) / (changed size) 20.01.181.836 I slot release: id 2 | task 22947 | stop processing: n_tokens = 875, truncated = 0 20.01.181.839 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 692, t_last = 341289266123 20.01.181.923 I slot launch_slot_: id 1 | task 22953 | processing task, is_child = 0 20.02.061.338 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 341289779987 20.02.061.448 I slot launch_slot_: id 0 | task 22955 | processing task, is_child = 0 20.02.061.496 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 875, t_last = 341289780318 20.02.061.564 I slot launch_slot_: id 2 | task 22956 | processing task, is_child = 0 20.05.232.371 I slot print_timing: id 0 | task 22955 | prompt processing, n_tokens = 580, progress = 0.53, t = 3.17 s / 182.94 tokens per second 20.05.232.420 I slot print_timing: id 1 | task 22953 | prompt processing, n_tokens = 1101, progress = 1.00, t = 4.05 s / 272.14 tokens per second 20.06.624.644 I slot print_timing: id 3 | task 22951 | prompt eval time = 4561.36 ms / 861 tokens ( 5.30 ms per token, 188.76 tokens per second) 20.06.624.647 I slot print_timing: id 3 | task 22951 | eval time = 1392.29 ms / 2 tokens ( 1392.29 ms per token, 0.72 tokens per second) 20.06.624.647 I slot print_timing: id 3 | task 22951 | total time = 5953.65 ms / 863 tokens 20.06.624.648 I slot print_timing: id 3 | task 22951 | graphs reused = 21680 20.06.624.648 I slot print_timing: id 3 | task 22951 | graph reallocs = 0 / 0 (same size) / (changed size) 20.06.624.701 I slot release: id 3 | task 22951 | stop processing: n_tokens = 862, truncated = 0 20.06.624.714 I slot print_timing: id 0 | task 22955 | prompt processing, n_tokens = 1092, progress = 1.00, t = 4.56 s / 239.34 tokens per second 20.06.624.929 I slot print_timing: id 2 | task 22956 | prompt processing, n_tokens = 1094, progress = 1.00, t = 3.92 s / 279.22 tokens per second 20.06.713.004 I slot print_timing: id 1 | task 22953 | prompt eval time = 5438.07 ms / 1105 tokens ( 4.92 ms per token, 203.20 tokens per second) 20.06.713.007 I slot print_timing: id 1 | task 22953 | eval time = 88.61 ms / 2 tokens ( 88.61 ms per token, 11.29 tokens per second) 20.06.713.007 I slot print_timing: id 1 | task 22953 | total time = 5526.68 ms / 1107 tokens 20.06.713.007 I slot print_timing: id 1 | task 22953 | graphs reused = 21680 20.06.713.008 I slot print_timing: id 1 | task 22953 | graph reallocs = 0 / 0 (same size) / (changed size) 20.06.713.066 I slot release: id 1 | task 22953 | stop processing: n_tokens = 1106, truncated = 0 20.06.713.446 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.892 20.06.713.488 I slot launch_slot_: id 1 | task 22960 | processing task, is_child = 0 20.07.388.256 I slot print_timing: id 0 | task 22955 | prompt eval time = 4651.17 ms / 1096 tokens ( 4.24 ms per token, 235.64 tokens per second) 20.07.388.258 I slot print_timing: id 0 | task 22955 | eval time = 675.51 ms / 2 tokens ( 675.51 ms per token, 1.48 tokens per second) 20.07.388.259 I slot print_timing: id 0 | task 22955 | total time = 5326.68 ms / 1098 tokens 20.07.388.259 I slot print_timing: id 0 | task 22955 | graphs reused = 21680 20.07.388.260 I slot print_timing: id 0 | task 22955 | graph reallocs = 0 / 0 (same size) / (changed size) 20.07.388.313 I slot release: id 0 | task 22955 | stop processing: n_tokens = 1097, truncated = 0 20.07.388.575 I slot print_timing: id 2 | task 22956 | prompt eval time = 4007.41 ms / 1098 tokens ( 3.65 ms per token, 273.99 tokens per second) 20.07.388.578 I slot print_timing: id 2 | task 22956 | eval time = 675.13 ms / 2 tokens ( 675.13 ms per token, 1.48 tokens per second) 20.07.388.578 I slot print_timing: id 2 | task 22956 | total time = 4682.54 ms / 1100 tokens 20.07.388.579 I slot print_timing: id 2 | task 22956 | graphs reused = 21680 20.07.388.579 I slot print_timing: id 2 | task 22956 | graph reallocs = 0 / 0 (same size) / (changed size) 20.07.388.622 I slot release: id 2 | task 22956 | stop processing: n_tokens = 1099, truncated = 0 20.07.388.627 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.897 20.07.388.652 I slot launch_slot_: id 2 | task 22962 | processing task, is_child = 0 20.08.094.774 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.898 20.08.094.806 I slot launch_slot_: id 0 | task 22964 | processing task, is_child = 0 20.08.094.865 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 862, t_last = 341295223183 20.08.095.919 I slot launch_slot_: id 3 | task 22965 | processing task, is_child = 0 20.09.461.441 I slot print_timing: id 1 | task 22960 | prompt eval time = 1379.39 ms / 497 tokens ( 2.78 ms per token, 360.30 tokens per second) 20.09.461.445 I slot print_timing: id 1 | task 22960 | eval time = 1366.67 ms / 2 tokens ( 1366.67 ms per token, 0.73 tokens per second) 20.09.461.445 I slot print_timing: id 1 | task 22960 | total time = 2746.06 ms / 499 tokens 20.09.461.446 I slot print_timing: id 1 | task 22960 | graphs reused = 21680 20.09.461.446 I slot print_timing: id 1 | task 22960 | graph reallocs = 0 / 0 (same size) / (changed size) 20.09.461.499 I slot release: id 1 | task 22960 | stop processing: n_tokens = 1087, truncated = 0 20.09.550.375 I slot print_timing: id 2 | task 22962 | prompt eval time = 2069.44 ms / 512 tokens ( 4.04 ms per token, 247.41 tokens per second) 20.09.550.379 I slot print_timing: id 2 | task 22962 | eval time = 88.56 ms / 2 tokens ( 88.56 ms per token, 11.29 tokens per second) 20.09.550.379 I slot print_timing: id 2 | task 22962 | total time = 2158.01 ms / 514 tokens 20.09.550.380 I slot print_timing: id 2 | task 22962 | graphs reused = 21680 20.09.550.380 I slot print_timing: id 2 | task 22962 | graph reallocs = 0 / 0 (same size) / (changed size) 20.09.550.433 I slot release: id 2 | task 22962 | stop processing: n_tokens = 1095, truncated = 0 20.09.550.813 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.907 20.09.550.848 I slot launch_slot_: id 1 | task 22968 | processing task, is_child = 0 20.10.230.347 I slot print_timing: id 0 | task 22964 | prompt eval time = 1454.20 ms / 506 tokens ( 2.87 ms per token, 347.96 tokens per second) 20.10.230.350 I slot print_timing: id 0 | task 22964 | eval time = 680.21 ms / 2 tokens ( 680.21 ms per token, 1.47 tokens per second) 20.10.230.350 I slot print_timing: id 0 | task 22964 | total time = 2134.41 ms / 508 tokens 20.10.230.351 I slot print_timing: id 0 | task 22964 | graphs reused = 21680 20.10.230.351 I slot print_timing: id 0 | task 22964 | graph reallocs = 0 / 0 (same size) / (changed size) 20.10.230.410 I slot release: id 0 | task 22964 | stop processing: n_tokens = 1087, truncated = 0 20.10.230.700 I slot print_timing: id 3 | task 22965 | prompt eval time = 1454.49 ms / 515 tokens ( 2.82 ms per token, 354.08 tokens per second) 20.10.230.706 I slot print_timing: id 3 | task 22965 | eval time = 679.89 ms / 2 tokens ( 679.89 ms per token, 1.47 tokens per second) 20.10.230.706 I slot print_timing: id 3 | task 22965 | total time = 2134.38 ms / 517 tokens 20.10.230.706 I slot print_timing: id 3 | task 22965 | graphs reused = 21680 20.10.230.707 I slot print_timing: id 3 | task 22965 | graph reallocs = 0 / 0 (same size) / (changed size) 20.10.230.752 I slot release: id 3 | task 22965 | stop processing: n_tokens = 1096, truncated = 0 20.10.230.759 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.894 (> 0.100 thold), f_keep = 0.907 20.10.230.794 I slot launch_slot_: id 0 | task 22970 | processing task, is_child = 0 20.10.321.537 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.900 20.10.321.560 I slot launch_slot_: id 2 | task 22972 | processing task, is_child = 0 20.10.321.623 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.900 20.10.321.639 I slot launch_slot_: id 3 | task 22973 | processing task, is_child = 0 20.12.326.713 I slot print_timing: id 1 | task 22968 | prompt eval time = 769.60 ms / 506 tokens ( 1.52 ms per token, 657.48 tokens per second) 20.12.326.718 I slot print_timing: id 1 | task 22968 | eval time = 2005.18 ms / 2 tokens ( 2005.18 ms per token, 0.50 tokens per second) 20.12.326.719 I slot print_timing: id 1 | task 22968 | total time = 2774.78 ms / 508 tokens 20.12.326.719 I slot print_timing: id 1 | task 22968 | graphs reused = 21680 20.12.326.720 I slot print_timing: id 1 | task 22968 | graph reallocs = 0 / 0 (same size) / (changed size) 20.12.326.777 I slot release: id 1 | task 22968 | stop processing: n_tokens = 1096, truncated = 0 20.12.423.560 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.900 20.12.423.609 I slot launch_slot_: id 1 | task 22976 | processing task, is_child = 0 20.13.107.606 I slot print_timing: id 0 | task 22970 | prompt eval time = 2189.12 ms / 523 tokens ( 4.19 ms per token, 238.91 tokens per second) 20.13.107.608 I slot print_timing: id 0 | task 22970 | eval time = 684.68 ms / 2 tokens ( 684.68 ms per token, 1.46 tokens per second) 20.13.107.610 I slot print_timing: id 0 | task 22970 | total time = 2873.81 ms / 525 tokens 20.13.107.610 I slot print_timing: id 0 | task 22970 | graphs reused = 21680 20.13.107.611 I slot print_timing: id 0 | task 22970 | graph reallocs = 0 / 0 (same size) / (changed size) 20.13.107.667 I slot release: id 0 | task 22970 | stop processing: n_tokens = 1104, truncated = 0 20.13.107.942 I slot print_timing: id 2 | task 22972 | prompt eval time = 2101.51 ms / 514 tokens ( 4.09 ms per token, 244.59 tokens per second) 20.13.107.948 I slot print_timing: id 2 | task 22972 | eval time = 684.75 ms / 2 tokens ( 684.75 ms per token, 1.46 tokens per second) 20.13.107.948 I slot print_timing: id 2 | task 22972 | total time = 2786.26 ms / 516 tokens 20.13.107.948 I slot print_timing: id 2 | task 22972 | graphs reused = 21680 20.13.107.949 I slot print_timing: id 2 | task 22972 | graph reallocs = 0 / 0 (same size) / (changed size) 20.13.107.987 I slot release: id 2 | task 22972 | stop processing: n_tokens = 1097, truncated = 0 20.13.108.258 I slot print_timing: id 3 | task 22973 | prompt eval time = 2101.75 ms / 508 tokens ( 4.14 ms per token, 241.70 tokens per second) 20.13.108.260 I slot print_timing: id 3 | task 22973 | eval time = 684.70 ms / 2 tokens ( 684.70 ms per token, 1.46 tokens per second) 20.13.108.261 I slot print_timing: id 3 | task 22973 | total time = 2786.45 ms / 510 tokens 20.13.108.261 I slot print_timing: id 3 | task 22973 | graphs reused = 21680 20.13.108.261 I slot print_timing: id 3 | task 22973 | graph reallocs = 0 / 0 (same size) / (changed size) 20.13.108.314 I slot release: id 3 | task 22973 | stop processing: n_tokens = 1089, truncated = 0 20.13.145.272 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.893 20.13.145.302 I slot launch_slot_: id 0 | task 22979 | processing task, is_child = 0 20.13.149.713 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.899 20.13.149.735 I slot launch_slot_: id 2 | task 22980 | processing task, is_child = 0 20.13.149.791 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.905 20.13.149.806 I slot launch_slot_: id 3 | task 22981 | processing task, is_child = 0 20.15.122.394 I slot print_timing: id 1 | task 22976 | prompt eval time = 721.65 ms / 500 tokens ( 1.44 ms per token, 692.85 tokens per second) 20.15.122.397 I slot print_timing: id 1 | task 22976 | eval time = 1977.12 ms / 2 tokens ( 1977.12 ms per token, 0.51 tokens per second) 20.15.122.398 I slot print_timing: id 1 | task 22976 | total time = 2698.77 ms / 502 tokens 20.15.122.398 I slot print_timing: id 1 | task 22976 | graphs reused = 21680 20.15.122.398 I slot print_timing: id 1 | task 22976 | graph reallocs = 0 / 0 (same size) / (changed size) 20.15.122.453 I slot release: id 1 | task 22976 | stop processing: n_tokens = 1090, truncated = 0 20.15.218.895 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1090, t_last = 341303720935 20.15.221.591 I slot launch_slot_: id 1 | task 22984 | processing task, is_child = 0 20.15.865.995 I slot print_timing: id 0 | task 22979 | prompt eval time = 2068.47 ms / 504 tokens ( 4.10 ms per token, 243.66 tokens per second) 20.15.865.998 I slot print_timing: id 0 | task 22979 | eval time = 647.71 ms / 2 tokens ( 647.71 ms per token, 1.54 tokens per second) 20.15.865.998 I slot print_timing: id 0 | task 22979 | total time = 2716.18 ms / 506 tokens 20.15.865.999 I slot print_timing: id 0 | task 22979 | graphs reused = 21680 20.15.865.999 I slot print_timing: id 0 | task 22979 | graph reallocs = 0 / 0 (same size) / (changed size) 20.15.866.052 I slot release: id 0 | task 22979 | stop processing: n_tokens = 1092, truncated = 0 20.15.866.325 I slot print_timing: id 2 | task 22980 | prompt eval time = 2068.61 ms / 511 tokens ( 4.05 ms per token, 247.03 tokens per second) 20.15.866.328 I slot print_timing: id 2 | task 22980 | eval time = 647.77 ms / 2 tokens ( 647.77 ms per token, 1.54 tokens per second) 20.15.866.328 I slot print_timing: id 2 | task 22980 | total time = 2716.38 ms / 513 tokens 20.15.866.329 I slot print_timing: id 2 | task 22980 | graphs reused = 21680 20.15.866.329 I slot print_timing: id 2 | task 22980 | graph reallocs = 0 / 0 (same size) / (changed size) 20.15.866.370 I slot release: id 2 | task 22980 | stop processing: n_tokens = 1094, truncated = 0 20.15.866.649 I slot print_timing: id 3 | task 22981 | prompt eval time = 2068.83 ms / 512 tokens ( 4.04 ms per token, 247.48 tokens per second) 20.15.866.651 I slot print_timing: id 3 | task 22981 | eval time = 647.76 ms / 2 tokens ( 647.76 ms per token, 1.54 tokens per second) 20.15.866.652 I slot print_timing: id 3 | task 22981 | total time = 2716.59 ms / 514 tokens 20.15.866.652 I slot print_timing: id 3 | task 22981 | graphs reused = 21680 20.15.866.652 I slot print_timing: id 3 | task 22981 | graph reallocs = 0 / 0 (same size) / (changed size) 20.15.866.694 I slot release: id 3 | task 22981 | stop processing: n_tokens = 1093, truncated = 0 20.16.550.853 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1092, t_last = 341304464534 20.16.554.045 I slot launch_slot_: id 0 | task 22988 | processing task, is_child = 0 20.16.559.248 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1094, t_last = 341304464853 20.16.559.329 I slot launch_slot_: id 2 | task 22989 | processing task, is_child = 0 20.16.559.385 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1093, t_last = 341304465176 20.16.559.462 I slot launch_slot_: id 3 | task 22990 | processing task, is_child = 0 20.18.736.117 I slot print_timing: id 1 | task 22984 | prompt eval time = 1329.24 ms / 983 tokens ( 1.35 ms per token, 739.52 tokens per second) 20.18.736.119 I slot print_timing: id 1 | task 22984 | eval time = 2185.26 ms / 2 tokens ( 2185.26 ms per token, 0.46 tokens per second) 20.18.736.120 I slot print_timing: id 1 | task 22984 | total time = 3514.51 ms / 985 tokens 20.18.736.120 I slot print_timing: id 1 | task 22984 | graphs reused = 21680 20.18.736.121 I slot print_timing: id 1 | task 22984 | graph reallocs = 0 / 0 (same size) / (changed size) 20.18.736.179 I slot release: id 1 | task 22984 | stop processing: n_tokens = 984, truncated = 0 20.20.027.113 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.886 20.20.027.157 I slot launch_slot_: id 1 | task 22993 | processing task, is_child = 0 20.20.027.166 I slot print_timing: id 0 | task 22988 | prompt processing, n_tokens = 992, progress = 1.00, t = 3.47 s / 286.07 tokens per second 20.20.677.049 I slot print_timing: id 2 | task 22989 | prompt processing, n_tokens = 1033, progress = 1.00, t = 3.47 s / 297.90 tokens per second 20.20.677.231 I slot print_timing: id 3 | task 22990 | prompt processing, n_tokens = 1062, progress = 1.00, t = 3.47 s / 306.27 tokens per second 20.21.536.519 I slot print_timing: id 0 | task 22988 | prompt eval time = 4279.04 ms / 996 tokens ( 4.30 ms per token, 232.76 tokens per second) 20.21.536.525 I slot print_timing: id 0 | task 22988 | eval time = 698.00 ms / 2 tokens ( 698.00 ms per token, 1.43 tokens per second) 20.21.536.526 I slot print_timing: id 0 | task 22988 | total time = 4977.05 ms / 998 tokens 20.21.536.526 I slot print_timing: id 0 | task 22988 | graphs reused = 21680 20.21.536.526 I slot print_timing: id 0 | task 22988 | graph reallocs = 0 / 0 (same size) / (changed size) 20.21.536.590 I slot release: id 0 | task 22988 | stop processing: n_tokens = 997, truncated = 0 20.21.536.882 I slot print_timing: id 2 | task 22989 | prompt eval time = 4279.25 ms / 1037 tokens ( 4.13 ms per token, 242.33 tokens per second) 20.21.536.884 I slot print_timing: id 2 | task 22989 | eval time = 698.08 ms / 2 tokens ( 698.08 ms per token, 1.43 tokens per second) 20.21.536.885 I slot print_timing: id 2 | task 22989 | total time = 4977.33 ms / 1039 tokens 20.21.536.885 I slot print_timing: id 2 | task 22989 | graphs reused = 21680 20.21.536.885 I slot print_timing: id 2 | task 22989 | graph reallocs = 0 / 0 (same size) / (changed size) 20.21.536.936 I slot release: id 2 | task 22989 | stop processing: n_tokens = 1038, truncated = 0 20.21.537.238 I slot print_timing: id 3 | task 22990 | prompt eval time = 4279.50 ms / 1066 tokens ( 4.01 ms per token, 249.09 tokens per second) 20.21.537.243 I slot print_timing: id 3 | task 22990 | eval time = 698.12 ms / 2 tokens ( 698.12 ms per token, 1.43 tokens per second) 20.21.537.243 I slot print_timing: id 3 | task 22990 | total time = 4977.62 ms / 1068 tokens 20.21.537.243 I slot print_timing: id 3 | task 22990 | graphs reused = 21680 20.21.537.244 I slot print_timing: id 3 | task 22990 | graph reallocs = 0 / 0 (same size) / (changed size) 20.21.537.298 I slot release: id 3 | task 22990 | stop processing: n_tokens = 1067, truncated = 0 20.21.574.063 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.875 20.21.574.095 I slot launch_slot_: id 0 | task 22997 | processing task, is_child = 0 20.21.578.276 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1038, t_last = 341310135420 20.21.578.362 I slot launch_slot_: id 2 | task 22998 | processing task, is_child = 0 20.21.578.415 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1067, t_last = 341310135780 20.21.578.483 I slot launch_slot_: id 3 | task 22999 | processing task, is_child = 0 20.22.426.832 I slot print_timing: id 1 | task 22993 | prompt eval time = 897.10 ms / 527 tokens ( 1.70 ms per token, 587.45 tokens per second) 20.22.426.834 I slot print_timing: id 1 | task 22993 | eval time = 852.77 ms / 2 tokens ( 852.77 ms per token, 1.17 tokens per second) 20.22.426.835 I slot print_timing: id 1 | task 22993 | total time = 1749.87 ms / 529 tokens 20.22.426.836 I slot print_timing: id 1 | task 22993 | graphs reused = 21680 20.22.426.836 I slot print_timing: id 1 | task 22993 | graph reallocs = 0 / 0 (same size) / (changed size) 20.22.426.901 I slot release: id 1 | task 22993 | stop processing: n_tokens = 995, truncated = 0 20.23.716.647 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 995, t_last = 341311025384 20.24.363.800 I slot launch_slot_: id 1 | task 23002 | processing task, is_child = 0 20.25.490.209 I slot print_timing: id 0 | task 22997 | prompt eval time = 3221.05 ms / 527 tokens ( 6.11 ms per token, 163.61 tokens per second) 20.25.490.210 I slot print_timing: id 0 | task 22997 | eval time = 690.66 ms / 2 tokens ( 690.66 ms per token, 1.45 tokens per second) 20.25.490.211 I slot print_timing: id 0 | task 22997 | total time = 3911.72 ms / 529 tokens 20.25.490.211 I slot print_timing: id 0 | task 22997 | graphs reused = 21680 20.25.490.212 I slot print_timing: id 0 | task 22997 | graph reallocs = 0 / 0 (same size) / (changed size) 20.25.490.270 I slot release: id 0 | task 22997 | stop processing: n_tokens = 1008, truncated = 0 20.25.490.547 I slot print_timing: id 2 | task 22998 | prompt eval time = 3221.25 ms / 731 tokens ( 4.41 ms per token, 226.93 tokens per second) 20.25.490.551 I slot print_timing: id 2 | task 22998 | eval time = 690.72 ms / 2 tokens ( 690.72 ms per token, 1.45 tokens per second) 20.25.490.552 I slot print_timing: id 2 | task 22998 | total time = 3911.97 ms / 733 tokens 20.25.490.552 I slot print_timing: id 2 | task 22998 | graphs reused = 21680 20.25.490.552 I slot print_timing: id 2 | task 22998 | graph reallocs = 0 / 0 (same size) / (changed size) 20.25.490.596 I slot release: id 2 | task 22998 | stop processing: n_tokens = 732, truncated = 0 20.25.490.880 I slot print_timing: id 3 | task 22999 | prompt eval time = 3221.46 ms / 774 tokens ( 4.16 ms per token, 240.26 tokens per second) 20.25.490.882 I slot print_timing: id 3 | task 22999 | eval time = 690.76 ms / 2 tokens ( 690.76 ms per token, 1.45 tokens per second) 20.25.490.883 I slot print_timing: id 3 | task 22999 | total time = 3912.22 ms / 776 tokens 20.25.490.883 I slot print_timing: id 3 | task 22999 | graphs reused = 21680 20.25.490.883 I slot print_timing: id 3 | task 22999 | graph reallocs = 0 / 0 (same size) / (changed size) 20.25.490.921 I slot release: id 3 | task 22999 | stop processing: n_tokens = 775, truncated = 0 20.25.527.616 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.862 20.25.527.644 I slot launch_slot_: id 2 | task 23006 | processing task, is_child = 0 20.25.531.225 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.814 20.25.531.245 I slot launch_slot_: id 3 | task 23007 | processing task, is_child = 0 20.25.531.296 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1008, t_last = 341314088753 20.25.532.078 I slot launch_slot_: id 0 | task 23008 | processing task, is_child = 0 20.27.530.194 I slot print_timing: id 1 | task 23002 | prompt eval time = 1163.63 ms / 706 tokens ( 1.65 ms per token, 606.72 tokens per second) 20.27.530.196 I slot print_timing: id 1 | task 23002 | eval time = 2002.57 ms / 2 tokens ( 2002.57 ms per token, 0.50 tokens per second) 20.27.530.197 I slot print_timing: id 1 | task 23002 | total time = 3166.21 ms / 708 tokens 20.27.530.197 I slot print_timing: id 1 | task 23002 | graphs reused = 21680 20.27.530.198 I slot print_timing: id 1 | task 23002 | graph reallocs = 0 / 0 (same size) / (changed size) 20.27.530.244 I slot release: id 1 | task 23002 | stop processing: n_tokens = 707, truncated = 0 20.27.626.912 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.893 20.27.626.955 I slot launch_slot_: id 1 | task 23011 | processing task, is_child = 0 20.27.695.385 I slot print_timing: id 0 | task 23008 | prompt eval time = 2094.21 ms / 463 tokens ( 4.52 ms per token, 221.09 tokens per second) 20.27.695.391 I slot print_timing: id 0 | task 23008 | eval time = 69.08 ms / 2 tokens ( 69.08 ms per token, 14.48 tokens per second) 20.27.695.391 I slot print_timing: id 0 | task 23008 | total time = 2163.29 ms / 465 tokens 20.27.695.392 I slot print_timing: id 0 | task 23008 | graphs reused = 21680 20.27.695.392 I slot print_timing: id 0 | task 23008 | graph reallocs = 0 / 0 (same size) / (changed size) 20.27.695.434 I slot release: id 0 | task 23008 | stop processing: n_tokens = 722, truncated = 0 20.27.695.713 I slot print_timing: id 2 | task 23006 | prompt eval time = 2094.39 ms / 508 tokens ( 4.12 ms per token, 242.55 tokens per second) 20.27.695.715 I slot print_timing: id 2 | task 23006 | eval time = 69.13 ms / 2 tokens ( 69.13 ms per token, 14.47 tokens per second) 20.27.695.715 I slot print_timing: id 2 | task 23006 | total time = 2163.51 ms / 510 tokens 20.27.695.715 I slot print_timing: id 2 | task 23006 | graphs reused = 21680 20.27.695.716 I slot print_timing: id 2 | task 23006 | graph reallocs = 0 / 0 (same size) / (changed size) 20.27.695.753 I slot release: id 2 | task 23006 | stop processing: n_tokens = 724, truncated = 0 20.27.696.038 I slot print_timing: id 3 | task 23007 | prompt eval time = 2094.59 ms / 457 tokens ( 4.58 ms per token, 218.18 tokens per second) 20.27.696.041 I slot print_timing: id 3 | task 23007 | eval time = 69.13 ms / 2 tokens ( 69.13 ms per token, 14.47 tokens per second) 20.27.696.041 I slot print_timing: id 3 | task 23007 | total time = 2163.72 ms / 459 tokens 20.27.696.041 I slot print_timing: id 3 | task 23007 | graphs reused = 21680 20.27.696.041 I slot print_timing: id 3 | task 23007 | graph reallocs = 0 / 0 (same size) / (changed size) 20.27.696.067 I slot release: id 3 | task 23007 | stop processing: n_tokens = 716, truncated = 0 20.28.377.294 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.874 20.28.377.321 I slot launch_slot_: id 0 | task 23015 | processing task, is_child = 0 20.28.379.775 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 724, t_last = 341316294235 20.28.379.843 I slot launch_slot_: id 2 | task 23016 | processing task, is_child = 0 20.28.379.886 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.881 20.28.379.901 I slot launch_slot_: id 3 | task 23017 | processing task, is_child = 0 20.30.313.677 I slot print_timing: id 1 | task 23011 | prompt eval time = 750.33 ms / 519 tokens ( 1.45 ms per token, 691.70 tokens per second) 20.30.313.679 I slot print_timing: id 1 | task 23011 | eval time = 1936.38 ms / 2 tokens ( 1936.38 ms per token, 0.52 tokens per second) 20.30.313.680 I slot print_timing: id 1 | task 23011 | total time = 2686.71 ms / 521 tokens 20.30.313.680 I slot print_timing: id 1 | task 23011 | graphs reused = 21680 20.30.313.681 I slot print_timing: id 1 | task 23011 | graph reallocs = 0 / 0 (same size) / (changed size) 20.30.313.727 I slot release: id 1 | task 23011 | stop processing: n_tokens = 710, truncated = 0 20.31.052.131 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 341318912209 20.31.054.612 I slot launch_slot_: id 1 | task 23020 | processing task, is_child = 0 20.31.685.745 I slot print_timing: id 0 | task 23015 | prompt eval time = 2671.90 ms / 465 tokens ( 5.75 ms per token, 174.03 tokens per second) 20.31.685.748 I slot print_timing: id 0 | task 23015 | eval time = 633.94 ms / 2 tokens ( 633.94 ms per token, 1.58 tokens per second) 20.31.685.749 I slot print_timing: id 0 | task 23015 | total time = 3305.84 ms / 467 tokens 20.31.685.749 I slot print_timing: id 0 | task 23015 | graphs reused = 21680 20.31.685.749 I slot print_timing: id 0 | task 23015 | graph reallocs = 0 / 0 (same size) / (changed size) 20.31.685.800 I slot release: id 0 | task 23015 | stop processing: n_tokens = 724, truncated = 0 20.31.686.414 I slot print_timing: id 3 | task 23017 | prompt eval time = 2672.05 ms / 473 tokens ( 5.65 ms per token, 177.02 tokens per second) 20.31.686.416 I slot print_timing: id 3 | task 23017 | eval time = 634.29 ms / 2 tokens ( 634.29 ms per token, 1.58 tokens per second) 20.31.686.416 I slot print_timing: id 3 | task 23017 | total time = 3306.33 ms / 475 tokens 20.31.686.417 I slot print_timing: id 3 | task 23017 | graphs reused = 21680 20.31.686.417 I slot print_timing: id 3 | task 23017 | graph reallocs = 0 / 0 (same size) / (changed size) 20.31.686.453 I slot release: id 3 | task 23017 | stop processing: n_tokens = 732, truncated = 0 20.32.346.016 I slot print_timing: id 2 | task 23016 | prompt eval time = 3306.06 ms / 944 tokens ( 3.50 ms per token, 285.54 tokens per second) 20.32.346.018 I slot print_timing: id 2 | task 23016 | eval time = 659.93 ms / 2 tokens ( 659.93 ms per token, 1.52 tokens per second) 20.32.346.019 I slot print_timing: id 2 | task 23016 | total time = 3965.99 ms / 946 tokens 20.32.346.019 I slot print_timing: id 2 | task 23016 | graphs reused = 21680 20.32.346.019 I slot print_timing: id 2 | task 23016 | graph reallocs = 0 / 0 (same size) / (changed size) 20.32.346.073 I slot release: id 2 | task 23016 | stop processing: n_tokens = 945, truncated = 0 20.32.346.079 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.806 (> 0.100 thold), f_keep = 0.852 20.32.346.105 I slot launch_slot_: id 2 | task 23023 | processing task, is_child = 0 20.32.350.101 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 724, t_last = 341320284282 20.32.350.181 I slot launch_slot_: id 0 | task 23024 | processing task, is_child = 0 20.33.168.330 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 341320284935 20.33.168.425 I slot launch_slot_: id 3 | task 23026 | processing task, is_child = 0 20.35.273.609 I slot print_timing: id 1 | task 23020 | prompt eval time = 2113.70 ms / 930 tokens ( 2.27 ms per token, 439.99 tokens per second) 20.35.273.615 I slot print_timing: id 1 | task 23020 | eval time = 2105.28 ms / 2 tokens ( 2105.28 ms per token, 0.47 tokens per second) 20.35.273.615 I slot print_timing: id 1 | task 23020 | total time = 4218.97 ms / 932 tokens 20.35.273.616 I slot print_timing: id 1 | task 23020 | graphs reused = 21680 20.35.273.616 I slot print_timing: id 1 | task 23020 | graph reallocs = 0 / 0 (same size) / (changed size) 20.35.273.669 I slot release: id 1 | task 23020 | stop processing: n_tokens = 931, truncated = 0 20.36.014.328 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 341323872151 20.36.017.446 I slot launch_slot_: id 1 | task 23029 | processing task, is_child = 0 20.36.885.745 I slot print_timing: id 0 | task 23024 | prompt eval time = 3663.67 ms / 914 tokens ( 4.01 ms per token, 249.48 tokens per second) 20.36.885.747 I slot print_timing: id 0 | task 23024 | eval time = 871.81 ms / 2 tokens ( 871.81 ms per token, 1.15 tokens per second) 20.36.885.747 I slot print_timing: id 0 | task 23024 | total time = 4535.48 ms / 916 tokens 20.36.885.748 I slot print_timing: id 0 | task 23024 | graphs reused = 21680 20.36.885.748 I slot print_timing: id 0 | task 23024 | graph reallocs = 0 / 0 (same size) / (changed size) 20.36.885.805 I slot release: id 0 | task 23024 | stop processing: n_tokens = 915, truncated = 0 20.36.886.110 I slot print_timing: id 2 | task 23023 | prompt eval time = 3663.85 ms / 571 tokens ( 6.42 ms per token, 155.85 tokens per second) 20.36.886.113 I slot print_timing: id 2 | task 23023 | eval time = 871.78 ms / 2 tokens ( 871.78 ms per token, 1.15 tokens per second) 20.36.886.113 I slot print_timing: id 2 | task 23023 | total time = 4535.63 ms / 573 tokens 20.36.886.114 I slot print_timing: id 2 | task 23023 | graphs reused = 21680 20.36.886.114 I slot print_timing: id 2 | task 23023 | graph reallocs = 0 / 0 (same size) / (changed size) 20.36.886.166 I slot release: id 2 | task 23023 | stop processing: n_tokens = 1000, truncated = 0 20.37.550.390 I slot print_timing: id 3 | task 23026 | prompt eval time = 3717.94 ms / 1051 tokens ( 3.54 ms per token, 282.68 tokens per second) 20.37.550.392 I slot print_timing: id 3 | task 23026 | eval time = 663.93 ms / 2 tokens ( 663.93 ms per token, 1.51 tokens per second) 20.37.550.392 I slot print_timing: id 3 | task 23026 | total time = 4381.87 ms / 1053 tokens 20.37.550.393 I slot print_timing: id 3 | task 23026 | graphs reused = 21680 20.37.550.393 I slot print_timing: id 3 | task 23026 | graph reallocs = 0 / 0 (same size) / (changed size) 20.37.550.452 I slot release: id 3 | task 23026 | stop processing: n_tokens = 1052, truncated = 0 20.37.550.458 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 915, t_last = 341325484287 20.37.553.262 I slot launch_slot_: id 0 | task 23032 | processing task, is_child = 0 20.37.557.332 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1000, t_last = 341325484648 20.37.557.416 I slot launch_slot_: id 2 | task 23033 | processing task, is_child = 0 20.37.557.471 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1052, t_last = 341326148934 20.37.557.544 I slot launch_slot_: id 3 | task 23034 | processing task, is_child = 0 20.43.097.207 I slot print_timing: id 1 | task 23029 | prompt eval time = 4290.48 ms / 1054 tokens ( 4.07 ms per token, 245.66 tokens per second) 20.43.097.209 I slot print_timing: id 1 | task 23029 | eval time = 2789.26 ms / 2 tokens ( 2789.26 ms per token, 0.36 tokens per second) 20.43.097.210 I slot print_timing: id 1 | task 23029 | total time = 7079.74 ms / 1056 tokens 20.43.097.211 I slot print_timing: id 1 | task 23029 | graphs reused = 21680 20.43.097.211 I slot print_timing: id 1 | task 23029 | graph reallocs = 0 / 0 (same size) / (changed size) 20.43.097.274 I slot release: id 1 | task 23029 | stop processing: n_tokens = 1055, truncated = 0 20.43.097.288 I slot print_timing: id 0 | task 23032 | prompt processing, n_tokens = 2067, progress = 1.00, t = 5.54 s / 373.15 tokens per second 20.43.097.606 I slot print_timing: id 2 | task 23033 | prompt processing, n_tokens = 1569, progress = 0.75, t = 5.54 s / 283.26 tokens per second 20.45.295.838 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1055, t_last = 341331695757 20.45.299.220 I slot launch_slot_: id 1 | task 23038 | processing task, is_child = 0 20.45.299.342 I slot print_timing: id 2 | task 23033 | prompt processing, n_tokens = 2081, progress = 1.00, t = 7.74 s / 268.94 tokens per second 20.45.299.672 I slot print_timing: id 3 | task 23034 | prompt processing, n_tokens = 1533, progress = 0.75, t = 4.99 s / 307.37 tokens per second 20.47.993.564 I slot print_timing: id 0 | task 23032 | prompt eval time = 7738.28 ms / 2071 tokens ( 3.74 ms per token, 267.63 tokens per second) 20.47.993.567 I slot print_timing: id 0 | task 23032 | eval time = 2697.73 ms / 2 tokens ( 2697.73 ms per token, 0.37 tokens per second) 20.47.993.567 I slot print_timing: id 0 | task 23032 | total time = 10436.01 ms / 2073 tokens 20.47.993.568 I slot print_timing: id 0 | task 23032 | graphs reused = 21680 20.47.993.568 I slot print_timing: id 0 | task 23032 | graph reallocs = 0 / 0 (same size) / (changed size) 20.47.993.691 I slot release: id 0 | task 23032 | stop processing: n_tokens = 2072, truncated = 0 20.47.994.071 I slot print_timing: id 3 | task 23034 | prompt processing, n_tokens = 2045, progress = 1.00, t = 7.69 s / 266.09 tokens per second 20.48.711.590 I slot print_timing: id 2 | task 23033 | prompt eval time = 10436.20 ms / 2085 tokens ( 5.01 ms per token, 199.79 tokens per second) 20.48.711.595 I slot print_timing: id 2 | task 23033 | eval time = 717.58 ms / 2 tokens ( 717.58 ms per token, 1.39 tokens per second) 20.48.711.597 I slot print_timing: id 2 | task 23033 | total time = 11153.77 ms / 2087 tokens 20.48.711.597 I slot print_timing: id 2 | task 23033 | graphs reused = 21680 20.48.711.597 I slot print_timing: id 2 | task 23033 | graph reallocs = 0 / 0 (same size) / (changed size) 20.48.711.708 I slot release: id 2 | task 23033 | stop processing: n_tokens = 2086, truncated = 0 20.48.712.099 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.842 (> 0.100 thold), f_keep = 0.856 20.48.712.145 I slot launch_slot_: id 0 | task 23041 | processing task, is_child = 0 20.48.716.655 I slot print_timing: id 1 | task 23038 | prompt processing, n_tokens = 2022, progress = 1.00, t = 3.41 s / 592.60 tokens per second 20.48.975.869 I slot print_timing: id 3 | task 23034 | prompt eval time = 8404.08 ms / 2049 tokens ( 4.10 ms per token, 243.81 tokens per second) 20.48.975.871 I slot print_timing: id 3 | task 23034 | eval time = 263.77 ms / 2 tokens ( 263.77 ms per token, 3.79 tokens per second) 20.48.975.872 I slot print_timing: id 3 | task 23034 | total time = 8667.85 ms / 2051 tokens 20.48.975.872 I slot print_timing: id 3 | task 23034 | graphs reused = 21680 20.48.975.872 I slot print_timing: id 3 | task 23034 | graph reallocs = 0 / 0 (same size) / (changed size) 20.48.975.981 I slot release: id 3 | task 23034 | stop processing: n_tokens = 2050, truncated = 0 20.48.975.990 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.838 (> 0.100 thold), f_keep = 0.850 20.48.976.026 I slot launch_slot_: id 2 | task 23043 | processing task, is_child = 0 20.48.981.500 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.865 20.48.981.527 I slot launch_slot_: id 3 | task 23044 | processing task, is_child = 0 20.50.502.593 I slot print_timing: id 1 | task 23038 | prompt eval time = 3676.30 ms / 2026 tokens ( 1.81 ms per token, 551.10 tokens per second) 20.50.502.595 I slot print_timing: id 1 | task 23038 | eval time = 1527.04 ms / 2 tokens ( 1527.04 ms per token, 0.65 tokens per second) 20.50.502.596 I slot print_timing: id 1 | task 23038 | total time = 5203.35 ms / 2028 tokens 20.50.502.597 I slot print_timing: id 1 | task 23038 | graphs reused = 21680 20.50.502.597 I slot print_timing: id 1 | task 23038 | graph reallocs = 0 / 0 (same size) / (changed size) 20.50.502.712 I slot release: id 1 | task 23038 | stop processing: n_tokens = 2027, truncated = 0 20.51.263.115 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.834 (> 0.100 thold), f_keep = 0.875 20.51.263.153 I slot launch_slot_: id 1 | task 23047 | processing task, is_child = 0 20.51.584.942 I slot print_timing: id 0 | task 23041 | prompt eval time = 2546.15 ms / 551 tokens ( 4.62 ms per token, 216.40 tokens per second) 20.51.584.944 I slot print_timing: id 0 | task 23041 | eval time = 322.22 ms / 2 tokens ( 322.22 ms per token, 3.10 tokens per second) 20.51.584.945 I slot print_timing: id 0 | task 23041 | total time = 2868.38 ms / 553 tokens 20.51.584.946 I slot print_timing: id 0 | task 23041 | graphs reused = 21680 20.51.584.946 I slot print_timing: id 0 | task 23041 | graph reallocs = 0 / 0 (same size) / (changed size) 20.51.585.056 I slot release: id 0 | task 23041 | stop processing: n_tokens = 2107, truncated = 0 20.51.585.669 I slot print_timing: id 3 | task 23044 | prompt eval time = 2281.45 ms / 514 tokens ( 4.44 ms per token, 225.30 tokens per second) 20.51.585.671 I slot print_timing: id 3 | task 23044 | eval time = 322.56 ms / 2 tokens ( 322.56 ms per token, 3.10 tokens per second) 20.51.585.672 I slot print_timing: id 3 | task 23044 | total time = 2604.01 ms / 516 tokens 20.51.585.672 I slot print_timing: id 3 | task 23044 | graphs reused = 21680 20.51.585.672 I slot print_timing: id 3 | task 23044 | graph reallocs = 0 / 0 (same size) / (changed size) 20.51.585.770 I slot release: id 3 | task 23044 | stop processing: n_tokens = 2048, truncated = 0 20.52.267.986 I slot print_timing: id 2 | task 23043 | prompt eval time = 2603.80 ms / 547 tokens ( 4.76 ms per token, 210.08 tokens per second) 20.52.267.989 I slot print_timing: id 2 | task 23043 | eval time = 682.61 ms / 2 tokens ( 682.61 ms per token, 1.46 tokens per second) 20.52.267.994 I slot print_timing: id 2 | task 23043 | total time = 3286.41 ms / 549 tokens 20.52.267.995 I slot print_timing: id 2 | task 23043 | graphs reused = 21680 20.52.267.995 I slot print_timing: id 2 | task 23043 | graph reallocs = 0 / 0 (same size) / (changed size) 20.52.268.107 I slot release: id 2 | task 23043 | stop processing: n_tokens = 2117, truncated = 0 20.52.268.118 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.842 20.52.268.150 I slot launch_slot_: id 0 | task 23050 | processing task, is_child = 0 20.52.277.152 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.805 (> 0.100 thold), f_keep = 0.838 20.52.277.183 I slot launch_slot_: id 2 | task 23051 | processing task, is_child = 0 20.52.277.280 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.866 20.52.277.298 I slot launch_slot_: id 3 | task 23052 | processing task, is_child = 0 20.54.514.983 I slot print_timing: id 1 | task 23047 | prompt eval time = 2471.61 ms / 616 tokens ( 4.01 ms per token, 249.23 tokens per second) 20.54.514.989 I slot print_timing: id 1 | task 23047 | eval time = 780.22 ms / 2 tokens ( 780.22 ms per token, 1.28 tokens per second) 20.54.514.989 I slot print_timing: id 1 | task 23047 | total time = 3251.82 ms / 618 tokens 20.54.514.990 I slot print_timing: id 1 | task 23047 | graphs reused = 21680 20.54.514.990 I slot print_timing: id 1 | task 23047 | graph reallocs = 0 / 0 (same size) / (changed size) 20.54.515.106 I slot release: id 1 | task 23047 | stop processing: n_tokens = 2127, truncated = 0 20.54.580.238 I slot print_timing: id 0 | task 23050 | prompt eval time = 2237.41 ms / 365 tokens ( 6.13 ms per token, 163.14 tokens per second) 20.54.580.243 I slot print_timing: id 0 | task 23050 | eval time = 65.52 ms / 2 tokens ( 65.52 ms per token, 15.26 tokens per second) 20.54.580.244 I slot print_timing: id 0 | task 23050 | total time = 2302.93 ms / 367 tokens 20.54.580.244 I slot print_timing: id 0 | task 23050 | graphs reused = 21680 20.54.580.245 I slot print_timing: id 0 | task 23050 | graph reallocs = 0 / 0 (same size) / (changed size) 20.54.580.350 I slot release: id 0 | task 23050 | stop processing: n_tokens = 1956, truncated = 0 20.54.581.093 I slot print_timing: id 3 | task 23052 | prompt eval time = 2237.67 ms / 467 tokens ( 4.79 ms per token, 208.70 tokens per second) 20.54.581.099 I slot print_timing: id 3 | task 23052 | eval time = 65.57 ms / 2 tokens ( 65.57 ms per token, 15.25 tokens per second) 20.54.581.100 I slot print_timing: id 3 | task 23052 | total time = 2303.23 ms / 469 tokens 20.54.581.101 I slot print_timing: id 3 | task 23052 | graphs reused = 21680 20.54.581.101 I slot print_timing: id 3 | task 23052 | graph reallocs = 0 / 0 (same size) / (changed size) 20.54.581.189 I slot release: id 3 | task 23052 | stop processing: n_tokens = 2001, truncated = 0 20.54.581.198 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.906 20.54.581.225 I slot launch_slot_: id 0 | task 23056 | processing task, is_child = 0 20.54.589.399 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.848 (> 0.100 thold), f_keep = 0.834 20.54.589.430 I slot launch_slot_: id 1 | task 23057 | processing task, is_child = 0 20.54.589.530 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.865 (> 0.100 thold), f_keep = 0.887 20.54.589.546 I slot launch_slot_: id 3 | task 23058 | processing task, is_child = 0 20.55.978.107 I slot print_timing: id 2 | task 23051 | prompt eval time = 2303.00 ms / 604 tokens ( 3.81 ms per token, 262.27 tokens per second) 20.55.978.111 I slot print_timing: id 2 | task 23051 | eval time = 1397.34 ms / 2 tokens ( 1397.34 ms per token, 0.72 tokens per second) 20.55.978.112 I slot print_timing: id 2 | task 23051 | total time = 3700.34 ms / 606 tokens 20.55.978.112 I slot print_timing: id 2 | task 23051 | graphs reused = 21680 20.55.978.112 I slot print_timing: id 2 | task 23051 | graph reallocs = 0 / 0 (same size) / (changed size) 20.55.978.242 I slot release: id 2 | task 23051 | stop processing: n_tokens = 2205, truncated = 0 20.56.704.912 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.804 20.56.704.949 I slot launch_slot_: id 2 | task 23061 | processing task, is_child = 0 20.57.204.845 I slot print_timing: id 0 | task 23056 | prompt eval time = 2114.98 ms / 407 tokens ( 5.20 ms per token, 192.44 tokens per second) 20.57.204.847 I slot print_timing: id 0 | task 23056 | eval time = 500.31 ms / 2 tokens ( 500.31 ms per token, 2.00 tokens per second) 20.57.204.847 I slot print_timing: id 0 | task 23056 | total time = 2615.29 ms / 409 tokens 20.57.204.848 I slot print_timing: id 0 | task 23056 | graphs reused = 21680 20.57.204.848 I slot print_timing: id 0 | task 23056 | graph reallocs = 0 / 0 (same size) / (changed size) 20.57.204.965 I slot release: id 0 | task 23056 | stop processing: n_tokens = 1998, truncated = 0 20.57.205.252 I slot print_timing: id 1 | task 23057 | prompt eval time = 2115.21 ms / 481 tokens ( 4.40 ms per token, 227.40 tokens per second) 20.57.205.255 I slot print_timing: id 1 | task 23057 | eval time = 500.35 ms / 2 tokens ( 500.35 ms per token, 2.00 tokens per second) 20.57.205.255 I slot print_timing: id 1 | task 23057 | total time = 2615.55 ms / 483 tokens 20.57.205.255 I slot print_timing: id 1 | task 23057 | graphs reused = 21680 20.57.205.256 I slot print_timing: id 1 | task 23057 | graph reallocs = 0 / 0 (same size) / (changed size) 20.57.205.343 I slot release: id 1 | task 23057 | stop processing: n_tokens = 2092, truncated = 0 20.57.256.874 I slot print_timing: id 3 | task 23058 | prompt eval time = 2615.82 ms / 518 tokens ( 5.05 ms per token, 198.03 tokens per second) 20.57.256.877 I slot print_timing: id 3 | task 23058 | eval time = 51.22 ms / 2 tokens ( 51.22 ms per token, 19.53 tokens per second) 20.57.256.879 I slot print_timing: id 3 | task 23058 | total time = 2667.03 ms / 520 tokens 20.57.256.879 I slot print_timing: id 3 | task 23058 | graphs reused = 21680 20.57.256.879 I slot print_timing: id 3 | task 23058 | graph reallocs = 0 / 0 (same size) / (changed size) 20.57.256.982 I slot release: id 3 | task 23058 | stop processing: n_tokens = 2052, truncated = 0 20.57.256.991 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.887 20.57.257.018 I slot launch_slot_: id 0 | task 23064 | processing task, is_child = 0 20.57.265.306 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.842 (> 0.100 thold), f_keep = 0.848 20.57.265.332 I slot launch_slot_: id 1 | task 23065 | processing task, is_child = 0 20.57.265.421 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.864 20.57.265.435 I slot launch_slot_: id 3 | task 23066 | processing task, is_child = 0 20.58.935.075 I slot print_timing: id 2 | task 23061 | prompt eval time = 551.64 ms / 270 tokens ( 2.04 ms per token, 489.45 tokens per second) 20.58.935.079 I slot print_timing: id 2 | task 23061 | eval time = 1678.47 ms / 2 tokens ( 1678.47 ms per token, 0.60 tokens per second) 20.58.935.079 I slot print_timing: id 2 | task 23061 | total time = 2230.12 ms / 272 tokens 20.58.935.079 I slot print_timing: id 2 | task 23061 | graphs reused = 21680 20.58.935.080 I slot print_timing: id 2 | task 23061 | graph reallocs = 0 / 0 (same size) / (changed size) 20.58.935.192 I slot release: id 2 | task 23061 | stop processing: n_tokens = 1959, truncated = 0 20.59.665.655 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.905 20.59.665.683 I slot launch_slot_: id 2 | task 23069 | processing task, is_child = 0 21.00.166.961 I slot print_timing: id 0 | task 23064 | prompt eval time = 2399.92 ms / 464 tokens ( 5.17 ms per token, 193.34 tokens per second) 21.00.166.965 I slot print_timing: id 0 | task 23064 | eval time = 501.59 ms / 2 tokens ( 501.59 ms per token, 1.99 tokens per second) 21.00.166.966 I slot print_timing: id 0 | task 23064 | total time = 2901.51 ms / 466 tokens 21.00.166.966 I slot print_timing: id 0 | task 23064 | graphs reused = 21680 21.00.166.967 I slot print_timing: id 0 | task 23064 | graph reallocs = 0 / 0 (same size) / (changed size) 21.00.167.076 I slot release: id 0 | task 23064 | stop processing: n_tokens = 2055, truncated = 0 21.00.167.376 I slot print_timing: id 1 | task 23065 | prompt eval time = 2400.07 ms / 496 tokens ( 4.84 ms per token, 206.66 tokens per second) 21.00.167.379 I slot print_timing: id 1 | task 23065 | eval time = 501.73 ms / 2 tokens ( 501.73 ms per token, 1.99 tokens per second) 21.00.167.379 I slot print_timing: id 1 | task 23065 | total time = 2901.80 ms / 498 tokens 21.00.167.379 I slot print_timing: id 1 | task 23065 | graphs reused = 21680 21.00.167.380 I slot print_timing: id 1 | task 23065 | graph reallocs = 0 / 0 (same size) / (changed size) 21.00.167.476 I slot release: id 1 | task 23065 | stop processing: n_tokens = 2107, truncated = 0 21.00.218.756 I slot print_timing: id 3 | task 23066 | prompt eval time = 2902.08 ms / 620 tokens ( 4.68 ms per token, 213.64 tokens per second) 21.00.218.758 I slot print_timing: id 3 | task 23066 | eval time = 50.97 ms / 2 tokens ( 50.97 ms per token, 19.62 tokens per second) 21.00.218.759 I slot print_timing: id 3 | task 23066 | total time = 2953.05 ms / 622 tokens 21.00.218.759 I slot print_timing: id 3 | task 23066 | graphs reused = 21680 21.00.218.760 I slot print_timing: id 3 | task 23066 | graph reallocs = 0 / 0 (same size) / (changed size) 21.00.218.871 I slot release: id 3 | task 23066 | stop processing: n_tokens = 2156, truncated = 0 21.00.218.880 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.863 21.00.218.904 I slot launch_slot_: id 0 | task 23072 | processing task, is_child = 0 21.00.227.335 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.820 (> 0.100 thold), f_keep = 0.842 21.00.227.356 I slot launch_slot_: id 1 | task 23073 | processing task, is_child = 0 21.00.227.451 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.822 21.00.227.467 I slot launch_slot_: id 3 | task 23074 | processing task, is_child = 0 21.01.500.935 I slot print_timing: id 2 | task 23069 | prompt eval time = 552.81 ms / 270 tokens ( 2.05 ms per token, 488.42 tokens per second) 21.01.500.941 I slot print_timing: id 2 | task 23069 | eval time = 1282.44 ms / 2 tokens ( 1282.44 ms per token, 0.78 tokens per second) 21.01.500.942 I slot print_timing: id 2 | task 23069 | total time = 1835.24 ms / 272 tokens 21.01.500.942 I slot print_timing: id 2 | task 23069 | graphs reused = 21680 21.01.500.943 I slot print_timing: id 2 | task 23069 | graph reallocs = 0 / 0 (same size) / (changed size) 21.01.501.050 I slot release: id 2 | task 23069 | stop processing: n_tokens = 1959, truncated = 0 21.02.260.150 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.906 21.02.260.180 I slot launch_slot_: id 2 | task 23077 | processing task, is_child = 0 21.02.808.629 I slot print_timing: id 0 | task 23072 | prompt eval time = 2032.29 ms / 429 tokens ( 4.74 ms per token, 211.09 tokens per second) 21.02.808.634 I slot print_timing: id 0 | task 23072 | eval time = 548.86 ms / 2 tokens ( 548.86 ms per token, 1.82 tokens per second) 21.02.808.634 I slot print_timing: id 0 | task 23072 | total time = 2581.15 ms / 431 tokens 21.02.808.635 I slot print_timing: id 0 | task 23072 | graphs reused = 21680 21.02.808.635 I slot print_timing: id 0 | task 23072 | graph reallocs = 0 / 0 (same size) / (changed size) 21.02.808.748 I slot release: id 0 | task 23072 | stop processing: n_tokens = 2020, truncated = 0 21.02.809.459 I slot print_timing: id 3 | task 23074 | prompt eval time = 2032.46 ms / 338 tokens ( 6.01 ms per token, 166.30 tokens per second) 21.02.809.462 I slot print_timing: id 3 | task 23074 | eval time = 549.31 ms / 2 tokens ( 549.31 ms per token, 1.82 tokens per second) 21.02.809.462 I slot print_timing: id 3 | task 23074 | total time = 2581.77 ms / 340 tokens 21.02.809.463 I slot print_timing: id 3 | task 23074 | graphs reused = 21680 21.02.809.463 I slot print_timing: id 3 | task 23074 | graph reallocs = 0 / 0 (same size) / (changed size) 21.02.809.559 I slot release: id 3 | task 23074 | stop processing: n_tokens = 1978, truncated = 0 21.02.863.420 I slot print_timing: id 1 | task 23073 | prompt eval time = 2581.54 ms / 553 tokens ( 4.67 ms per token, 214.21 tokens per second) 21.02.863.422 I slot print_timing: id 1 | task 23073 | eval time = 54.27 ms / 2 tokens ( 54.27 ms per token, 18.43 tokens per second) 21.02.863.423 I slot print_timing: id 1 | task 23073 | total time = 2635.81 ms / 555 tokens 21.02.863.423 I slot print_timing: id 1 | task 23073 | graphs reused = 21680 21.02.863.424 I slot print_timing: id 1 | task 23073 | graph reallocs = 0 / 0 (same size) / (changed size) 21.02.863.528 I slot release: id 1 | task 23073 | stop processing: n_tokens = 2164, truncated = 0 21.02.863.843 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.820 21.02.863.873 I slot launch_slot_: id 1 | task 23080 | processing task, is_child = 0 21.02.871.411 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.878 21.02.871.442 I slot launch_slot_: id 0 | task 23081 | processing task, is_child = 0 21.02.871.531 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.896 21.02.871.545 I slot launch_slot_: id 3 | task 23082 | processing task, is_child = 0 21.04.426.053 I slot print_timing: id 2 | task 23077 | prompt eval time = 603.32 ms / 316 tokens ( 1.91 ms per token, 523.77 tokens per second) 21.04.426.055 I slot print_timing: id 2 | task 23077 | eval time = 1562.21 ms / 2 tokens ( 1562.21 ms per token, 0.64 tokens per second) 21.04.426.055 I slot print_timing: id 2 | task 23077 | total time = 2165.53 ms / 318 tokens 21.04.426.056 I slot print_timing: id 2 | task 23077 | graphs reused = 21680 21.04.426.056 I slot print_timing: id 2 | task 23077 | graph reallocs = 0 / 0 (same size) / (changed size) 21.04.426.171 I slot release: id 2 | task 23077 | stop processing: n_tokens = 2005, truncated = 0 21.04.523.883 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2005, t_last = 341353024654 21.04.528.217 I slot launch_slot_: id 2 | task 23085 | processing task, is_child = 0 21.05.754.513 I slot print_timing: id 0 | task 23081 | prompt eval time = 1651.54 ms / 301 tokens ( 5.49 ms per token, 182.25 tokens per second) 21.05.754.519 I slot print_timing: id 0 | task 23081 | eval time = 1231.41 ms / 2 tokens ( 1231.41 ms per token, 0.81 tokens per second) 21.05.754.520 I slot print_timing: id 0 | task 23081 | total time = 2882.96 ms / 303 tokens 21.05.754.520 I slot print_timing: id 0 | task 23081 | graphs reused = 21680 21.05.754.520 I slot print_timing: id 0 | task 23081 | graph reallocs = 0 / 0 (same size) / (changed size) 21.05.754.630 I slot release: id 0 | task 23081 | stop processing: n_tokens = 1892, truncated = 0 21.05.754.942 I slot print_timing: id 1 | task 23080 | prompt eval time = 1651.80 ms / 330 tokens ( 5.01 ms per token, 199.78 tokens per second) 21.05.754.944 I slot print_timing: id 1 | task 23080 | eval time = 1231.45 ms / 2 tokens ( 1231.45 ms per token, 0.81 tokens per second) 21.05.754.944 I slot print_timing: id 1 | task 23080 | total time = 2883.25 ms / 332 tokens 21.05.754.945 I slot print_timing: id 1 | task 23080 | graphs reused = 21680 21.05.754.945 I slot print_timing: id 1 | task 23080 | graph reallocs = 0 / 0 (same size) / (changed size) 21.05.755.033 I slot release: id 1 | task 23080 | stop processing: n_tokens = 1978, truncated = 0 21.05.755.337 I slot print_timing: id 3 | task 23082 | prompt eval time = 1652.06 ms / 297 tokens ( 5.56 ms per token, 179.78 tokens per second) 21.05.755.340 I slot print_timing: id 3 | task 23082 | eval time = 1231.46 ms / 2 tokens ( 1231.46 ms per token, 0.81 tokens per second) 21.05.755.340 I slot print_timing: id 3 | task 23082 | total time = 2883.52 ms / 299 tokens 21.05.755.340 I slot print_timing: id 3 | task 23082 | graphs reused = 21680 21.05.755.341 I slot print_timing: id 3 | task 23082 | graph reallocs = 0 / 0 (same size) / (changed size) 21.05.755.421 I slot release: id 3 | task 23082 | stop processing: n_tokens = 1937, truncated = 0 21.06.447.832 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1892, t_last = 341354353113 21.06.453.250 I slot launch_slot_: id 0 | task 23089 | processing task, is_child = 0 21.06.460.307 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1978, t_last = 341354353516 21.06.460.423 I slot launch_slot_: id 1 | task 23090 | processing task, is_child = 0 21.06.460.511 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1937, t_last = 341354353903 21.06.460.624 I slot launch_slot_: id 3 | task 23091 | processing task, is_child = 0 21.09.249.536 I slot print_timing: id 2 | task 23085 | prompt eval time = 1919.60 ms / 1430 tokens ( 1.34 ms per token, 744.95 tokens per second) 21.09.249.539 I slot print_timing: id 2 | task 23085 | eval time = 2801.71 ms / 2 tokens ( 2801.71 ms per token, 0.36 tokens per second) 21.09.249.539 I slot print_timing: id 2 | task 23085 | total time = 4721.30 ms / 1432 tokens 21.09.249.540 I slot print_timing: id 2 | task 23085 | graphs reused = 21680 21.09.249.540 I slot print_timing: id 2 | task 23085 | graph reallocs = 0 / 0 (same size) / (changed size) 21.09.249.626 I slot release: id 2 | task 23085 | stop processing: n_tokens = 1431, truncated = 0 21.10.554.724 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1431, t_last = 341357848109 21.11.206.178 I slot launch_slot_: id 2 | task 23094 | processing task, is_child = 0 21.11.206.193 I slot print_timing: id 0 | task 23089 | prompt processing, n_tokens = 977, progress = 1.00, t = 4.09 s / 238.64 tokens per second 21.11.206.375 I slot print_timing: id 1 | task 23090 | prompt processing, n_tokens = 1494, progress = 1.00, t = 4.09 s / 364.93 tokens per second 21.11.206.719 I slot print_timing: id 3 | task 23091 | prompt processing, n_tokens = 1111, progress = 0.68, t = 4.09 s / 271.38 tokens per second 21.12.723.088 I slot print_timing: id 3 | task 23091 | prompt processing, n_tokens = 1623, progress = 1.00, t = 6.26 s / 259.20 tokens per second 21.13.455.059 I slot print_timing: id 0 | task 23089 | prompt eval time = 6262.11 ms / 981 tokens ( 6.38 ms per token, 156.66 tokens per second) 21.13.455.064 I slot print_timing: id 0 | task 23089 | eval time = 732.32 ms / 2 tokens ( 732.32 ms per token, 1.37 tokens per second) 21.13.455.064 I slot print_timing: id 0 | task 23089 | total time = 6994.43 ms / 983 tokens 21.13.455.065 I slot print_timing: id 0 | task 23089 | graphs reused = 21680 21.13.455.065 I slot print_timing: id 0 | task 23089 | graph reallocs = 0 / 0 (same size) / (changed size) 21.13.455.126 I slot release: id 0 | task 23089 | stop processing: n_tokens = 982, truncated = 0 21.13.455.401 I slot print_timing: id 1 | task 23090 | prompt eval time = 6262.28 ms / 1498 tokens ( 4.18 ms per token, 239.21 tokens per second) 21.13.455.408 I slot print_timing: id 1 | task 23090 | eval time = 732.37 ms / 2 tokens ( 732.37 ms per token, 1.37 tokens per second) 21.13.455.409 I slot print_timing: id 1 | task 23090 | total time = 6994.64 ms / 1500 tokens 21.13.455.409 I slot print_timing: id 1 | task 23090 | graphs reused = 21680 21.13.455.409 I slot print_timing: id 1 | task 23090 | graph reallocs = 0 / 0 (same size) / (changed size) 21.13.455.489 I slot release: id 1 | task 23090 | stop processing: n_tokens = 1499, truncated = 0 21.13.506.341 I slot print_timing: id 3 | task 23091 | prompt eval time = 6994.92 ms / 1627 tokens ( 4.30 ms per token, 232.60 tokens per second) 21.13.506.344 I slot print_timing: id 3 | task 23091 | eval time = 50.53 ms / 2 tokens ( 50.53 ms per token, 19.79 tokens per second) 21.13.506.344 I slot print_timing: id 3 | task 23091 | total time = 7045.45 ms / 1629 tokens 21.13.506.345 I slot print_timing: id 3 | task 23091 | graphs reused = 21680 21.13.506.345 I slot print_timing: id 3 | task 23091 | graph reallocs = 0 / 0 (same size) / (changed size) 21.13.506.426 I slot release: id 3 | task 23091 | stop processing: n_tokens = 1628, truncated = 0 21.13.506.434 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.878 21.13.506.457 I slot launch_slot_: id 0 | task 23098 | processing task, is_child = 0 21.13.512.114 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1499, t_last = 341362053972 21.13.512.213 I slot launch_slot_: id 1 | task 23099 | processing task, is_child = 0 21.13.512.282 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1628, t_last = 341362104910 21.13.512.371 I slot launch_slot_: id 3 | task 23100 | processing task, is_child = 0 21.15.449.879 I slot print_timing: id 2 | task 23094 | prompt eval time = 2299.45 ms / 969 tokens ( 2.37 ms per token, 421.41 tokens per second) 21.15.449.882 I slot print_timing: id 2 | task 23094 | eval time = 1943.83 ms / 2 tokens ( 1943.83 ms per token, 0.51 tokens per second) 21.15.449.883 I slot print_timing: id 2 | task 23094 | total time = 4243.27 ms / 971 tokens 21.15.449.883 I slot print_timing: id 2 | task 23094 | graphs reused = 21680 21.15.449.884 I slot print_timing: id 2 | task 23094 | graph reallocs = 0 / 0 (same size) / (changed size) 21.15.449.945 I slot release: id 2 | task 23094 | stop processing: n_tokens = 970, truncated = 0 21.16.799.110 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.888 21.16.799.151 I slot launch_slot_: id 2 | task 23103 | processing task, is_child = 0 21.16.799.166 I slot print_timing: id 1 | task 23099 | prompt processing, n_tokens = 939, progress = 1.00, t = 3.29 s / 285.73 tokens per second 21.16.799.468 I slot print_timing: id 3 | task 23100 | prompt processing, n_tokens = 960, progress = 1.00, t = 3.29 s / 292.13 tokens per second 21.17.540.161 I slot print_timing: id 0 | task 23098 | prompt eval time = 3286.73 ms / 493 tokens ( 6.67 ms per token, 150.00 tokens per second) 21.17.540.167 I slot print_timing: id 0 | task 23098 | eval time = 741.05 ms / 2 tokens ( 741.05 ms per token, 1.35 tokens per second) 21.17.540.167 I slot print_timing: id 0 | task 23098 | total time = 4027.78 ms / 495 tokens 21.17.540.168 I slot print_timing: id 0 | task 23098 | graphs reused = 21680 21.17.540.168 I slot print_timing: id 0 | task 23098 | graph reallocs = 0 / 0 (same size) / (changed size) 21.17.540.228 I slot release: id 0 | task 23098 | stop processing: n_tokens = 959, truncated = 0 21.17.607.783 I slot print_timing: id 1 | task 23099 | prompt eval time = 4028.02 ms / 943 tokens ( 4.27 ms per token, 234.11 tokens per second) 21.17.607.788 I slot print_timing: id 1 | task 23099 | eval time = 67.26 ms / 2 tokens ( 67.26 ms per token, 14.87 tokens per second) 21.17.607.788 I slot print_timing: id 1 | task 23099 | total time = 4095.28 ms / 945 tokens 21.17.607.788 I slot print_timing: id 1 | task 23099 | graphs reused = 21680 21.17.607.789 I slot print_timing: id 1 | task 23099 | graph reallocs = 0 / 0 (same size) / (changed size) 21.17.607.842 I slot release: id 1 | task 23099 | stop processing: n_tokens = 944, truncated = 0 21.17.608.403 I slot print_timing: id 3 | task 23100 | prompt eval time = 4028.22 ms / 964 tokens ( 4.18 ms per token, 239.31 tokens per second) 21.17.608.405 I slot print_timing: id 3 | task 23100 | eval time = 67.59 ms / 2 tokens ( 67.59 ms per token, 14.80 tokens per second) 21.17.608.406 I slot print_timing: id 3 | task 23100 | total time = 4095.81 ms / 966 tokens 21.17.608.406 I slot print_timing: id 3 | task 23100 | graphs reused = 21680 21.17.608.407 I slot print_timing: id 3 | task 23100 | graph reallocs = 0 / 0 (same size) / (changed size) 21.17.608.453 I slot release: id 3 | task 23100 | stop processing: n_tokens = 965, truncated = 0 21.17.608.458 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.898 21.17.608.483 I slot launch_slot_: id 0 | task 23106 | processing task, is_child = 0 21.18.257.466 I slot print_timing: id 2 | task 23103 | prompt eval time = 808.80 ms / 500 tokens ( 1.62 ms per token, 618.20 tokens per second) 21.18.257.469 I slot print_timing: id 2 | task 23103 | eval time = 649.33 ms / 2 tokens ( 649.33 ms per token, 1.54 tokens per second) 21.18.257.469 I slot print_timing: id 2 | task 23103 | total time = 1458.12 ms / 502 tokens 21.18.257.470 I slot print_timing: id 2 | task 23103 | graphs reused = 21680 21.18.257.470 I slot print_timing: id 2 | task 23103 | graph reallocs = 0 / 0 (same size) / (changed size) 21.18.257.526 I slot release: id 2 | task 23103 | stop processing: n_tokens = 954, truncated = 0 21.18.257.534 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 944, t_last = 341366206324 21.18.257.643 I slot launch_slot_: id 1 | task 23108 | processing task, is_child = 0 21.18.260.707 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 965, t_last = 341366206935 21.18.260.798 I slot launch_slot_: id 3 | task 23109 | processing task, is_child = 0 21.20.245.398 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 341366856009 21.20.245.518 I slot launch_slot_: id 2 | task 23111 | processing task, is_child = 0 21.23.228.498 I slot print_timing: id 0 | task 23106 | prompt eval time = 2632.90 ms / 492 tokens ( 5.35 ms per token, 186.87 tokens per second) 21.23.228.502 I slot print_timing: id 0 | task 23106 | eval time = 2983.10 ms / 2 tokens ( 2983.10 ms per token, 0.34 tokens per second) 21.23.228.503 I slot print_timing: id 0 | task 23106 | total time = 5616.00 ms / 494 tokens 21.23.228.503 I slot print_timing: id 0 | task 23106 | graphs reused = 21680 21.23.228.504 I slot print_timing: id 0 | task 23106 | graph reallocs = 0 / 0 (same size) / (changed size) 21.23.228.568 I slot release: id 0 | task 23106 | stop processing: n_tokens = 958, truncated = 0 21.23.228.582 I slot print_timing: id 1 | task 23108 | prompt processing, n_tokens = 785, progress = 0.99, t = 4.97 s / 158.04 tokens per second 21.23.228.767 I slot print_timing: id 3 | task 23109 | prompt processing, n_tokens = 1580, progress = 0.97, t = 4.97 s / 318.09 tokens per second 21.24.174.584 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 958, t_last = 341371827050 21.24.177.425 I slot launch_slot_: id 0 | task 23114 | processing task, is_child = 0 21.24.177.528 I slot print_timing: id 2 | task 23111 | prompt processing, n_tokens = 1574, progress = 1.00, t = 3.93 s / 400.64 tokens per second 21.24.177.806 I slot print_timing: id 3 | task 23109 | prompt processing, n_tokens = 1619, progress = 1.00, t = 5.91 s / 273.80 tokens per second 21.25.771.206 I slot print_timing: id 1 | task 23108 | prompt eval time = 5913.55 ms / 789 tokens ( 7.49 ms per token, 133.42 tokens per second) 21.25.771.211 I slot print_timing: id 1 | task 23108 | eval time = 1596.63 ms / 2 tokens ( 1596.63 ms per token, 0.63 tokens per second) 21.25.771.211 I slot print_timing: id 1 | task 23108 | total time = 7510.18 ms / 791 tokens 21.25.771.212 I slot print_timing: id 1 | task 23108 | graphs reused = 21680 21.25.771.212 I slot print_timing: id 1 | task 23108 | graph reallocs = 0 / 0 (same size) / (changed size) 21.25.771.259 I slot release: id 1 | task 23108 | stop processing: n_tokens = 790, truncated = 0 21.26.455.293 I slot print_timing: id 2 | task 23111 | prompt eval time = 5525.98 ms / 1578 tokens ( 3.50 ms per token, 285.56 tokens per second) 21.26.455.295 I slot print_timing: id 2 | task 23111 | eval time = 683.72 ms / 2 tokens ( 683.72 ms per token, 1.46 tokens per second) 21.26.455.296 I slot print_timing: id 2 | task 23111 | total time = 6209.71 ms / 1580 tokens 21.26.455.296 I slot print_timing: id 2 | task 23111 | graphs reused = 21680 21.26.455.297 I slot print_timing: id 2 | task 23111 | graph reallocs = 0 / 0 (same size) / (changed size) 21.26.455.388 I slot release: id 2 | task 23111 | stop processing: n_tokens = 1579, truncated = 0 21.26.455.680 I slot print_timing: id 3 | task 23109 | prompt eval time = 7510.87 ms / 1623 tokens ( 4.63 ms per token, 216.09 tokens per second) 21.26.455.682 I slot print_timing: id 3 | task 23109 | eval time = 683.72 ms / 2 tokens ( 683.72 ms per token, 1.46 tokens per second) 21.26.455.682 I slot print_timing: id 3 | task 23109 | total time = 8194.59 ms / 1625 tokens 21.26.455.683 I slot print_timing: id 3 | task 23109 | graphs reused = 21680 21.26.455.683 I slot print_timing: id 3 | task 23109 | graph reallocs = 0 / 0 (same size) / (changed size) 21.26.455.757 I slot release: id 3 | task 23109 | stop processing: n_tokens = 1624, truncated = 0 21.26.455.764 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.857 (> 0.100 thold), f_keep = 0.886 21.26.455.791 I slot launch_slot_: id 2 | task 23117 | processing task, is_child = 0 21.26.696.378 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.812 (> 0.100 thold), f_keep = 0.861 21.26.696.409 I slot launch_slot_: id 3 | task 23119 | processing task, is_child = 0 21.26.696.469 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 341374369741 21.26.696.538 I slot launch_slot_: id 1 | task 23120 | processing task, is_child = 0 21.28.103.185 I slot print_timing: id 0 | task 23114 | prompt eval time = 2518.93 ms / 1610 tokens ( 1.56 ms per token, 639.16 tokens per second) 21.28.103.190 I slot print_timing: id 0 | task 23114 | eval time = 1406.81 ms / 2 tokens ( 1406.81 ms per token, 0.71 tokens per second) 21.28.103.191 I slot print_timing: id 0 | task 23114 | total time = 3925.74 ms / 1612 tokens 21.28.103.191 I slot print_timing: id 0 | task 23114 | graphs reused = 21680 21.28.103.191 I slot print_timing: id 0 | task 23114 | graph reallocs = 0 / 0 (same size) / (changed size) 21.28.103.282 I slot release: id 0 | task 23114 | stop processing: n_tokens = 1611, truncated = 0 21.29.491.391 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1611, t_last = 341376701765 21.29.495.789 I slot launch_slot_: id 0 | task 23123 | processing task, is_child = 0 21.30.074.700 I slot print_timing: id 2 | task 23117 | prompt eval time = 3028.91 ms / 571 tokens ( 5.30 ms per token, 188.52 tokens per second) 21.30.074.702 I slot print_timing: id 2 | task 23117 | eval time = 583.31 ms / 2 tokens ( 583.31 ms per token, 1.71 tokens per second) 21.30.074.702 I slot print_timing: id 2 | task 23117 | total time = 3612.22 ms / 573 tokens 21.30.074.703 I slot print_timing: id 2 | task 23117 | graphs reused = 21680 21.30.074.703 I slot print_timing: id 2 | task 23117 | graph reallocs = 0 / 0 (same size) / (changed size) 21.30.074.799 I slot release: id 2 | task 23117 | stop processing: n_tokens = 1634, truncated = 0 21.30.750.735 I slot print_timing: id 1 | task 23120 | prompt eval time = 3377.88 ms / 826 tokens ( 4.09 ms per token, 244.53 tokens per second) 21.30.750.740 I slot print_timing: id 1 | task 23120 | eval time = 676.31 ms / 2 tokens ( 676.31 ms per token, 1.48 tokens per second) 21.30.750.740 I slot print_timing: id 1 | task 23120 | total time = 4054.19 ms / 828 tokens 21.30.750.741 I slot print_timing: id 1 | task 23120 | graphs reused = 21680 21.30.750.741 I slot print_timing: id 1 | task 23120 | graph reallocs = 0 / 0 (same size) / (changed size) 21.30.750.791 I slot release: id 1 | task 23120 | stop processing: n_tokens = 827, truncated = 0 21.30.751.100 I slot print_timing: id 3 | task 23119 | prompt eval time = 3378.47 ms / 616 tokens ( 5.48 ms per token, 182.33 tokens per second) 21.30.751.102 I slot print_timing: id 3 | task 23119 | eval time = 675.98 ms / 2 tokens ( 675.98 ms per token, 1.48 tokens per second) 21.30.751.103 I slot print_timing: id 3 | task 23119 | total time = 4054.46 ms / 618 tokens 21.30.751.103 I slot print_timing: id 3 | task 23119 | graphs reused = 21680 21.30.751.103 I slot print_timing: id 3 | task 23119 | graph reallocs = 0 / 0 (same size) / (changed size) 21.30.751.195 I slot release: id 3 | task 23119 | stop processing: n_tokens = 1724, truncated = 0 21.30.751.201 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1634, t_last = 341378673282 21.30.755.376 I slot launch_slot_: id 2 | task 23126 | processing task, is_child = 0 21.30.760.558 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 827, t_last = 341379349273 21.30.760.632 I slot launch_slot_: id 1 | task 23127 | processing task, is_child = 0 21.30.760.704 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1724, t_last = 341379349678 21.30.760.793 I slot launch_slot_: id 3 | task 23128 | processing task, is_child = 0 21.34.402.529 I slot print_timing: id 0 | task 23123 | prompt eval time = 2871.69 ms / 854 tokens ( 3.36 ms per token, 297.39 tokens per second) 21.34.402.532 I slot print_timing: id 0 | task 23123 | eval time = 2035.03 ms / 2 tokens ( 2035.03 ms per token, 0.49 tokens per second) 21.34.402.532 I slot print_timing: id 0 | task 23123 | total time = 4906.72 ms / 856 tokens 21.34.402.533 I slot print_timing: id 0 | task 23123 | graphs reused = 21681 21.34.402.533 I slot print_timing: id 0 | task 23123 | graph reallocs = 0 / 0 (same size) / (changed size) 21.34.402.582 I slot release: id 0 | task 23123 | stop processing: n_tokens = 855, truncated = 0 21.34.402.595 I slot print_timing: id 1 | task 23127 | prompt processing, n_tokens = 843, progress = 1.00, t = 3.64 s / 231.51 tokens per second 21.34.402.738 I slot print_timing: id 2 | task 23126 | prompt processing, n_tokens = 824, progress = 1.00, t = 3.64 s / 226.30 tokens per second 21.34.402.897 I slot print_timing: id 3 | task 23128 | prompt processing, n_tokens = 863, progress = 1.00, t = 3.64 s / 237.01 tokens per second 21.34.491.454 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 341383001064 21.34.494.186 I slot launch_slot_: id 0 | task 23132 | processing task, is_child = 0 21.34.904.614 I slot print_timing: id 1 | task 23127 | prompt eval time = 3729.68 ms / 847 tokens ( 4.40 ms per token, 227.10 tokens per second) 21.34.904.618 I slot print_timing: id 1 | task 23127 | eval time = 413.98 ms / 2 tokens ( 413.98 ms per token, 2.42 tokens per second) 21.34.904.619 I slot print_timing: id 1 | task 23127 | total time = 4143.66 ms / 849 tokens 21.34.904.619 I slot print_timing: id 1 | task 23127 | graphs reused = 21681 21.34.904.620 I slot print_timing: id 1 | task 23127 | graph reallocs = 0 / 0 (same size) / (changed size) 21.34.904.666 I slot release: id 1 | task 23127 | stop processing: n_tokens = 848, truncated = 0 21.34.904.959 I slot print_timing: id 2 | task 23126 | prompt eval time = 3729.99 ms / 828 tokens ( 4.50 ms per token, 221.98 tokens per second) 21.34.904.961 I slot print_timing: id 2 | task 23126 | eval time = 413.95 ms / 2 tokens ( 413.95 ms per token, 2.42 tokens per second) 21.34.904.961 I slot print_timing: id 2 | task 23126 | total time = 4143.94 ms / 830 tokens 21.34.904.962 I slot print_timing: id 2 | task 23126 | graphs reused = 21681 21.34.904.962 I slot print_timing: id 2 | task 23126 | graph reallocs = 0 / 0 (same size) / (changed size) 21.34.905.002 I slot release: id 2 | task 23126 | stop processing: n_tokens = 829, truncated = 0 21.34.905.306 I slot print_timing: id 3 | task 23128 | prompt eval time = 3730.33 ms / 867 tokens ( 4.30 ms per token, 232.42 tokens per second) 21.34.905.308 I slot print_timing: id 3 | task 23128 | eval time = 413.86 ms / 2 tokens ( 413.86 ms per token, 2.42 tokens per second) 21.34.905.310 I slot print_timing: id 3 | task 23128 | total time = 4144.19 ms / 869 tokens 21.34.905.310 I slot print_timing: id 3 | task 23128 | graphs reused = 21681 21.34.905.310 I slot print_timing: id 3 | task 23128 | graph reallocs = 0 / 0 (same size) / (changed size) 21.34.905.346 I slot release: id 3 | task 23128 | stop processing: n_tokens = 868, truncated = 0 21.35.588.691 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 848, t_last = 341383503148 21.35.591.340 I slot launch_slot_: id 1 | task 23136 | processing task, is_child = 0 21.35.594.931 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 829, t_last = 341383503484 21.35.595.000 I slot launch_slot_: id 2 | task 23137 | processing task, is_child = 0 21.35.595.050 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 868, t_last = 341383503828 21.35.595.119 I slot launch_slot_: id 3 | task 23138 | processing task, is_child = 0 21.36.628.405 I slot print_timing: id 0 | task 23132 | prompt eval time = 1094.49 ms / 759 tokens ( 1.44 ms per token, 693.47 tokens per second) 21.36.628.410 I slot print_timing: id 0 | task 23132 | eval time = 1039.71 ms / 2 tokens ( 1039.71 ms per token, 0.96 tokens per second) 21.36.628.410 I slot print_timing: id 0 | task 23132 | total time = 2134.21 ms / 761 tokens 21.36.628.411 I slot print_timing: id 0 | task 23132 | graphs reused = 21681 21.36.628.411 I slot print_timing: id 0 | task 23132 | graph reallocs = 0 / 0 (same size) / (changed size) 21.36.628.456 I slot release: id 0 | task 23132 | stop processing: n_tokens = 760, truncated = 0 21.38.599.459 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 760, t_last = 341385226938 21.38.645.657 I slot launch_slot_: id 0 | task 23141 | processing task, is_child = 0 21.38.645.720 I slot print_timing: id 1 | task 23136 | prompt processing, n_tokens = 724, progress = 0.99, t = 3.00 s / 240.99 tokens per second 21.38.645.859 I slot print_timing: id 2 | task 23137 | prompt processing, n_tokens = 696, progress = 0.99, t = 3.00 s / 231.67 tokens per second 21.38.645.982 I slot print_timing: id 3 | task 23138 | prompt processing, n_tokens = 678, progress = 0.99, t = 3.00 s / 225.68 tokens per second 21.39.724.341 I slot print_timing: id 1 | task 23136 | prompt eval time = 3453.70 ms / 728 tokens ( 4.74 ms per token, 210.79 tokens per second) 21.39.724.346 I slot print_timing: id 1 | task 23136 | eval time = 675.51 ms / 2 tokens ( 675.51 ms per token, 1.48 tokens per second) 21.39.724.346 I slot print_timing: id 1 | task 23136 | total time = 4129.21 ms / 730 tokens 21.39.724.347 I slot print_timing: id 1 | task 23136 | graphs reused = 21682 21.39.724.347 I slot print_timing: id 1 | task 23136 | graph reallocs = 0 / 0 (same size) / (changed size) 21.39.724.397 I slot release: id 1 | task 23136 | stop processing: n_tokens = 729, truncated = 0 21.39.724.686 I slot print_timing: id 2 | task 23137 | prompt eval time = 3453.93 ms / 700 tokens ( 4.93 ms per token, 202.67 tokens per second) 21.39.724.688 I slot print_timing: id 2 | task 23137 | eval time = 675.57 ms / 2 tokens ( 675.57 ms per token, 1.48 tokens per second) 21.39.724.688 I slot print_timing: id 2 | task 23137 | total time = 4129.50 ms / 702 tokens 21.39.724.689 I slot print_timing: id 2 | task 23137 | graphs reused = 21682 21.39.724.689 I slot print_timing: id 2 | task 23137 | graph reallocs = 0 / 0 (same size) / (changed size) 21.39.724.725 I slot release: id 2 | task 23137 | stop processing: n_tokens = 701, truncated = 0 21.39.725.016 I slot print_timing: id 3 | task 23138 | prompt eval time = 3454.27 ms / 682 tokens ( 5.06 ms per token, 197.44 tokens per second) 21.39.725.018 I slot print_timing: id 3 | task 23138 | eval time = 675.51 ms / 2 tokens ( 675.51 ms per token, 1.48 tokens per second) 21.39.725.019 I slot print_timing: id 3 | task 23138 | total time = 4129.78 ms / 684 tokens 21.39.725.019 I slot print_timing: id 3 | task 23138 | graphs reused = 21682 21.39.725.019 I slot print_timing: id 3 | task 23138 | graph reallocs = 0 / 0 (same size) / (changed size) 21.39.725.044 I slot release: id 3 | task 23138 | stop processing: n_tokens = 683, truncated = 0 21.39.777.534 I slot print_timing: id 0 | task 23141 | prompt eval time = 1116.01 ms / 665 tokens ( 1.68 ms per token, 595.87 tokens per second) 21.39.777.535 I slot print_timing: id 0 | task 23141 | eval time = 15.85 ms / 2 tokens ( 15.85 ms per token, 63.08 tokens per second) 21.39.777.536 I slot print_timing: id 0 | task 23141 | total time = 1131.87 ms / 667 tokens 21.39.777.536 I slot print_timing: id 0 | task 23141 | graphs reused = 21682 21.39.777.537 I slot print_timing: id 0 | task 23141 | graph reallocs = 0 / 0 (same size) / (changed size) 21.39.777.571 I slot release: id 0 | task 23141 | stop processing: n_tokens = 666, truncated = 0 21.42.651.783 I srv operator(): operator(): cleaning up before exit...