/Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/d5a53342a2f5/LFM2.5-24B-A2B-UD-Q5_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 0.00.050.916 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.050.973 I srv llama_server: initializing ... 0.00.050.978 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.051.060 I srv init_listene: The UI is disabled 0.00.051.061 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.051.096 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) 0.00.052.763 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/d5a53342a2f5/LFM2.5-24B-A2B-UD-Q5_K_XL.gguf' 0.01.193.461 I cmn init: llama threadpool init, n_threads = 8 0.01.277.704 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.01.280.821 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.280.834 I srv llama_server: model loaded 0.01.280.836 I srv llama_server: listening on http://127.0.0.1:8091 0.31.230.132 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.230.158 I slot launch_slot_: id 0 | task 1 | processing task, is_child = 0 0.31.230.159 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.230.169 I slot launch_slot_: id 1 | task 2 | processing task, is_child = 0 0.31.230.169 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.230.179 I slot launch_slot_: id 2 | task 3 | processing task, is_child = 0 0.31.230.180 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.230.189 I slot launch_slot_: id 3 | task 0 | processing task, is_child = 0 0.32.655.211 I slot print_timing: id 0 | task 1 | prompt eval time = 1376.69 ms / 131 tokens ( 10.51 ms per token, 95.16 tokens per second) 0.32.655.216 I slot print_timing: id 0 | task 1 | eval time = 48.31 ms / 2 tokens ( 48.31 ms per token, 20.70 tokens per second) 0.32.655.217 I slot print_timing: id 0 | task 1 | total time = 1425.01 ms / 133 tokens 0.32.655.217 I slot print_timing: id 0 | task 1 | graphs reused = 1 0.32.655.217 I slot print_timing: id 0 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.655.239 I slot release: id 0 | task 1 | stop processing: n_tokens = 132, truncated = 0 0.32.655.601 I slot print_timing: id 1 | task 2 | prompt eval time = 1377.14 ms / 112 tokens ( 12.30 ms per token, 81.33 tokens per second) 0.32.655.604 I slot print_timing: id 1 | task 2 | eval time = 48.26 ms / 2 tokens ( 48.26 ms per token, 20.72 tokens per second) 0.32.655.605 I slot print_timing: id 1 | task 2 | total time = 1425.40 ms / 114 tokens 0.32.655.605 I slot print_timing: id 1 | task 2 | graphs reused = 1 0.32.655.605 I slot print_timing: id 1 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.655.622 I slot release: id 1 | task 2 | stop processing: n_tokens = 113, truncated = 0 0.32.655.892 I slot print_timing: id 2 | task 3 | prompt eval time = 1377.52 ms / 117 tokens ( 11.77 ms per token, 84.94 tokens per second) 0.32.655.894 I slot print_timing: id 2 | task 3 | eval time = 48.16 ms / 2 tokens ( 48.16 ms per token, 20.76 tokens per second) 0.32.655.895 I slot print_timing: id 2 | task 3 | total time = 1425.68 ms / 119 tokens 0.32.655.895 I slot print_timing: id 2 | task 3 | graphs reused = 1 0.32.655.895 I slot print_timing: id 2 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.655.906 I slot release: id 2 | task 3 | stop processing: n_tokens = 118, truncated = 0 0.32.656.332 I slot print_timing: id 3 | task 0 | prompt eval time = 1378.09 ms / 123 tokens ( 11.20 ms per token, 89.25 tokens per second) 0.32.656.333 I slot print_timing: id 3 | task 0 | eval time = 48.03 ms / 2 tokens ( 48.03 ms per token, 20.82 tokens per second) 0.32.656.333 I slot print_timing: id 3 | task 0 | total time = 1426.12 ms / 125 tokens 0.32.656.334 I slot print_timing: id 3 | task 0 | graphs reused = 1 0.32.656.334 I slot print_timing: id 3 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.656.342 I slot release: id 3 | task 0 | stop processing: n_tokens = 124, truncated = 0 0.32.662.850 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.227 0.32.663.094 I slot launch_slot_: id 0 | task 7 | processing task, is_child = 0 0.32.664.172 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 0.32.664.205 I slot launch_slot_: id 2 | task 8 | processing task, is_child = 0 0.32.664.236 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.257 0.32.664.263 I slot launch_slot_: id 1 | task 9 | processing task, is_child = 0 0.32.664.280 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.234 0.32.664.307 I slot launch_slot_: id 3 | task 10 | processing task, is_child = 0 0.33.970.115 I slot print_timing: id 0 | task 7 | prompt eval time = 1258.91 ms / 110 tokens ( 11.44 ms per token, 87.38 tokens per second) 0.33.970.117 I slot print_timing: id 0 | task 7 | eval time = 46.88 ms / 2 tokens ( 46.88 ms per token, 21.33 tokens per second) 0.33.970.118 I slot print_timing: id 0 | task 7 | total time = 1305.80 ms / 112 tokens 0.33.970.118 I slot print_timing: id 0 | task 7 | graphs reused = 1 0.33.970.119 I slot print_timing: id 0 | task 7 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.970.139 I slot release: id 0 | task 7 | stop processing: n_tokens = 111, truncated = 0 0.33.970.436 I slot print_timing: id 1 | task 9 | prompt eval time = 1259.19 ms / 199 tokens ( 6.33 ms per token, 158.04 tokens per second) 0.33.970.438 I slot print_timing: id 1 | task 9 | eval time = 46.92 ms / 2 tokens ( 46.92 ms per token, 21.31 tokens per second) 0.33.970.438 I slot print_timing: id 1 | task 9 | total time = 1306.11 ms / 201 tokens 0.33.970.439 I slot print_timing: id 1 | task 9 | graphs reused = 1 0.33.970.439 I slot print_timing: id 1 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.970.455 I slot release: id 1 | task 9 | stop processing: n_tokens = 200, truncated = 0 0.33.970.746 I slot print_timing: id 2 | task 8 | prompt eval time = 1259.58 ms / 161 tokens ( 7.82 ms per token, 127.82 tokens per second) 0.33.970.750 I slot print_timing: id 2 | task 8 | eval time = 46.83 ms / 2 tokens ( 46.83 ms per token, 21.35 tokens per second) 0.33.970.750 I slot print_timing: id 2 | task 8 | total time = 1306.41 ms / 163 tokens 0.33.970.750 I slot print_timing: id 2 | task 8 | graphs reused = 1 0.33.970.751 I slot print_timing: id 2 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.970.766 I slot release: id 2 | task 8 | stop processing: n_tokens = 162, truncated = 0 0.33.971.055 I slot print_timing: id 3 | task 10 | prompt eval time = 1259.88 ms / 161 tokens ( 7.83 ms per token, 127.79 tokens per second) 0.33.971.057 I slot print_timing: id 3 | task 10 | eval time = 46.82 ms / 2 tokens ( 46.82 ms per token, 21.36 tokens per second) 0.33.971.057 I slot print_timing: id 3 | task 10 | total time = 1306.71 ms / 163 tokens 0.33.971.057 I slot print_timing: id 3 | task 10 | graphs reused = 1 0.33.971.058 I slot print_timing: id 3 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.971.074 I slot release: id 3 | task 10 | stop processing: n_tokens = 162, truncated = 0 0.33.975.555 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.261 0.33.975.973 I slot launch_slot_: id 0 | task 14 | processing task, is_child = 0 0.33.977.020 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.145 0.33.977.054 I slot launch_slot_: id 1 | task 15 | processing task, is_child = 0 0.33.977.088 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.185 0.33.977.117 I slot launch_slot_: id 2 | task 16 | processing task, is_child = 0 0.33.977.139 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.179 0.33.977.168 I slot launch_slot_: id 3 | task 17 | processing task, is_child = 0 0.35.253.401 I slot print_timing: id 0 | task 14 | prompt eval time = 1229.31 ms / 116 tokens ( 10.60 ms per token, 94.36 tokens per second) 0.35.253.406 I slot print_timing: id 0 | task 14 | eval time = 46.91 ms / 2 tokens ( 46.91 ms per token, 21.32 tokens per second) 0.35.253.406 I slot print_timing: id 0 | task 14 | total time = 1276.22 ms / 118 tokens 0.35.253.407 I slot print_timing: id 0 | task 14 | graphs reused = 1 0.35.253.407 I slot print_timing: id 0 | task 14 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.253.430 I slot release: id 0 | task 14 | stop processing: n_tokens = 117, truncated = 0 0.35.253.714 I slot print_timing: id 1 | task 15 | prompt eval time = 1229.59 ms / 127 tokens ( 9.68 ms per token, 103.29 tokens per second) 0.35.253.716 I slot print_timing: id 1 | task 15 | eval time = 46.94 ms / 2 tokens ( 46.94 ms per token, 21.30 tokens per second) 0.35.253.716 I slot print_timing: id 1 | task 15 | total time = 1276.53 ms / 129 tokens 0.35.253.717 I slot print_timing: id 1 | task 15 | graphs reused = 1 0.35.253.717 I slot print_timing: id 1 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.253.731 I slot release: id 1 | task 15 | stop processing: n_tokens = 128, truncated = 0 0.35.254.020 I slot print_timing: id 2 | task 16 | prompt eval time = 1229.85 ms / 119 tokens ( 10.33 ms per token, 96.76 tokens per second) 0.35.254.022 I slot print_timing: id 2 | task 16 | eval time = 46.97 ms / 2 tokens ( 46.97 ms per token, 21.29 tokens per second) 0.35.254.022 I slot print_timing: id 2 | task 16 | total time = 1276.82 ms / 121 tokens 0.35.254.023 I slot print_timing: id 2 | task 16 | graphs reused = 1 0.35.254.023 I slot print_timing: id 2 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.254.036 I slot release: id 2 | task 16 | stop processing: n_tokens = 120, truncated = 0 0.35.254.340 I slot print_timing: id 3 | task 17 | prompt eval time = 1230.14 ms / 151 tokens ( 8.15 ms per token, 122.75 tokens per second) 0.35.254.349 I slot print_timing: id 3 | task 17 | eval time = 46.99 ms / 2 tokens ( 46.99 ms per token, 21.28 tokens per second) 0.35.254.349 I slot print_timing: id 3 | task 17 | total time = 1277.13 ms / 153 tokens 0.35.254.349 I slot print_timing: id 3 | task 17 | graphs reused = 1 0.35.254.350 I slot print_timing: id 3 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.254.362 I slot release: id 3 | task 17 | stop processing: n_tokens = 152, truncated = 0 0.35.258.381 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.248 0.35.258.767 I slot launch_slot_: id 0 | task 22 | processing task, is_child = 0 0.35.259.811 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.227 0.35.259.842 I slot launch_slot_: id 1 | task 21 | processing task, is_child = 0 0.35.259.874 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.242 0.35.259.902 I slot launch_slot_: id 2 | task 23 | processing task, is_child = 0 0.35.259.919 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.191 0.35.259.947 I slot launch_slot_: id 3 | task 24 | processing task, is_child = 0 0.36.676.524 I slot print_timing: id 0 | task 22 | prompt eval time = 1369.80 ms / 184 tokens ( 7.44 ms per token, 134.33 tokens per second) 0.36.676.526 I slot print_timing: id 0 | task 22 | eval time = 46.77 ms / 2 tokens ( 46.77 ms per token, 21.38 tokens per second) 0.36.676.526 I slot print_timing: id 0 | task 22 | total time = 1416.57 ms / 186 tokens 0.36.676.527 I slot print_timing: id 0 | task 22 | graphs reused = 1 0.36.676.527 I slot print_timing: id 0 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.676.568 I slot release: id 0 | task 22 | stop processing: n_tokens = 185, truncated = 0 0.36.676.845 I slot print_timing: id 1 | task 21 | prompt eval time = 1370.14 ms / 135 tokens ( 10.15 ms per token, 98.53 tokens per second) 0.36.676.848 I slot print_timing: id 1 | task 21 | eval time = 46.74 ms / 2 tokens ( 46.74 ms per token, 21.40 tokens per second) 0.36.676.848 I slot print_timing: id 1 | task 21 | total time = 1416.88 ms / 137 tokens 0.36.676.848 I slot print_timing: id 1 | task 21 | graphs reused = 1 0.36.676.849 I slot print_timing: id 1 | task 21 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.676.863 I slot release: id 1 | task 21 | stop processing: n_tokens = 136, truncated = 0 0.36.677.238 I slot print_timing: id 2 | task 23 | prompt eval time = 1370.51 ms / 143 tokens ( 9.58 ms per token, 104.34 tokens per second) 0.36.677.240 I slot print_timing: id 2 | task 23 | eval time = 46.76 ms / 2 tokens ( 46.76 ms per token, 21.39 tokens per second) 0.36.677.240 I slot print_timing: id 2 | task 23 | total time = 1417.26 ms / 145 tokens 0.36.677.241 I slot print_timing: id 2 | task 23 | graphs reused = 1 0.36.677.241 I slot print_timing: id 2 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.677.263 I slot release: id 2 | task 23 | stop processing: n_tokens = 144, truncated = 0 0.36.677.575 I slot print_timing: id 3 | task 24 | prompt eval time = 1370.87 ms / 120 tokens ( 11.42 ms per token, 87.54 tokens per second) 0.36.677.578 I slot print_timing: id 3 | task 24 | eval time = 46.72 ms / 2 tokens ( 46.72 ms per token, 21.40 tokens per second) 0.36.677.578 I slot print_timing: id 3 | task 24 | total time = 1417.59 ms / 122 tokens 0.36.677.578 I slot print_timing: id 3 | task 24 | graphs reused = 1 0.36.677.579 I slot print_timing: id 3 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.677.594 I slot release: id 3 | task 24 | stop processing: n_tokens = 121, truncated = 0 0.36.681.571 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.157 0.36.682.202 I slot launch_slot_: id 0 | task 29 | processing task, is_child = 0 0.36.683.254 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.213 0.36.683.287 I slot launch_slot_: id 1 | task 30 | processing task, is_child = 0 0.36.683.320 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.201 0.36.683.348 I slot launch_slot_: id 2 | task 28 | processing task, is_child = 0 0.36.683.366 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.240 0.36.683.503 I slot launch_slot_: id 3 | task 31 | processing task, is_child = 0 0.38.113.059 I slot print_timing: id 0 | task 29 | prompt eval time = 1382.66 ms / 131 tokens ( 10.55 ms per token, 94.75 tokens per second) 0.38.113.061 I slot print_timing: id 0 | task 29 | eval time = 46.89 ms / 2 tokens ( 46.89 ms per token, 21.33 tokens per second) 0.38.113.062 I slot print_timing: id 0 | task 29 | total time = 1429.55 ms / 133 tokens 0.38.113.062 I slot print_timing: id 0 | task 29 | graphs reused = 1 0.38.113.063 I slot print_timing: id 0 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.113.087 I slot release: id 0 | task 29 | stop processing: n_tokens = 132, truncated = 0 0.38.113.375 I slot print_timing: id 1 | task 30 | prompt eval time = 1382.94 ms / 179 tokens ( 7.73 ms per token, 129.43 tokens per second) 0.38.113.380 I slot print_timing: id 1 | task 30 | eval time = 46.92 ms / 2 tokens ( 46.92 ms per token, 21.31 tokens per second) 0.38.113.381 I slot print_timing: id 1 | task 30 | total time = 1429.86 ms / 181 tokens 0.38.113.381 I slot print_timing: id 1 | task 30 | graphs reused = 1 0.38.113.381 I slot print_timing: id 1 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.113.401 I slot release: id 1 | task 30 | stop processing: n_tokens = 180, truncated = 0 0.38.113.689 I slot print_timing: id 2 | task 28 | prompt eval time = 1383.23 ms / 141 tokens ( 9.81 ms per token, 101.94 tokens per second) 0.38.113.691 I slot print_timing: id 2 | task 28 | eval time = 46.93 ms / 2 tokens ( 46.93 ms per token, 21.31 tokens per second) 0.38.113.691 I slot print_timing: id 2 | task 28 | total time = 1430.16 ms / 143 tokens 0.38.113.691 I slot print_timing: id 2 | task 28 | graphs reused = 1 0.38.113.692 I slot print_timing: id 2 | task 28 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.113.710 I slot release: id 2 | task 28 | stop processing: n_tokens = 142, truncated = 0 0.38.113.988 I slot print_timing: id 3 | task 31 | prompt eval time = 1383.54 ms / 125 tokens ( 11.07 ms per token, 90.35 tokens per second) 0.38.113.991 I slot print_timing: id 3 | task 31 | eval time = 46.91 ms / 2 tokens ( 46.91 ms per token, 21.32 tokens per second) 0.38.113.991 I slot print_timing: id 3 | task 31 | total time = 1430.45 ms / 127 tokens 0.38.113.991 I slot print_timing: id 3 | task 31 | graphs reused = 1 0.38.113.992 I slot print_timing: id 3 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.114.006 I slot release: id 3 | task 31 | stop processing: n_tokens = 126, truncated = 0 0.38.118.866 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.220 0.38.119.300 I slot launch_slot_: id 0 | task 35 | processing task, is_child = 0 0.38.120.491 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.167 0.38.120.526 I slot launch_slot_: id 1 | task 36 | processing task, is_child = 0 0.38.120.559 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.204 0.38.120.588 I slot launch_slot_: id 2 | task 37 | processing task, is_child = 0 0.38.120.605 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.238 0.38.120.633 I slot launch_slot_: id 3 | task 38 | processing task, is_child = 0 0.39.222.697 I slot print_timing: id 0 | task 35 | prompt eval time = 1055.44 ms / 143 tokens ( 7.38 ms per token, 135.49 tokens per second) 0.39.222.699 I slot print_timing: id 0 | task 35 | eval time = 46.61 ms / 2 tokens ( 46.61 ms per token, 21.45 tokens per second) 0.39.222.700 I slot print_timing: id 0 | task 35 | total time = 1102.06 ms / 145 tokens 0.39.222.700 I slot print_timing: id 0 | task 35 | graphs reused = 1 0.39.222.701 I slot print_timing: id 0 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.222.722 I slot release: id 0 | task 35 | stop processing: n_tokens = 144, truncated = 0 0.39.223.011 I slot print_timing: id 1 | task 36 | prompt eval time = 1055.72 ms / 145 tokens ( 7.28 ms per token, 137.35 tokens per second) 0.39.223.013 I slot print_timing: id 1 | task 36 | eval time = 46.64 ms / 2 tokens ( 46.64 ms per token, 21.44 tokens per second) 0.39.223.013 I slot print_timing: id 1 | task 36 | total time = 1102.36 ms / 147 tokens 0.39.223.013 I slot print_timing: id 1 | task 36 | graphs reused = 1 0.39.223.014 I slot print_timing: id 1 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.223.030 I slot release: id 1 | task 36 | stop processing: n_tokens = 146, truncated = 0 0.39.223.312 I slot print_timing: id 2 | task 37 | prompt eval time = 1055.98 ms / 113 tokens ( 9.34 ms per token, 107.01 tokens per second) 0.39.223.317 I slot print_timing: id 2 | task 37 | eval time = 46.67 ms / 2 tokens ( 46.67 ms per token, 21.43 tokens per second) 0.39.223.317 I slot print_timing: id 2 | task 37 | total time = 1102.64 ms / 115 tokens 0.39.223.318 I slot print_timing: id 2 | task 37 | graphs reused = 1 0.39.223.318 I slot print_timing: id 2 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.223.329 I slot release: id 2 | task 37 | stop processing: n_tokens = 114, truncated = 0 0.39.223.623 I slot print_timing: id 3 | task 38 | prompt eval time = 1056.29 ms / 122 tokens ( 8.66 ms per token, 115.50 tokens per second) 0.39.223.625 I slot print_timing: id 3 | task 38 | eval time = 46.66 ms / 2 tokens ( 46.66 ms per token, 21.43 tokens per second) 0.39.223.626 I slot print_timing: id 3 | task 38 | total time = 1102.95 ms / 124 tokens 0.39.223.626 I slot print_timing: id 3 | task 38 | graphs reused = 1 0.39.223.626 I slot print_timing: id 3 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.223.638 I slot release: id 3 | task 38 | stop processing: n_tokens = 123, truncated = 0 0.39.227.274 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.244 0.39.227.643 I slot launch_slot_: id 3 | task 42 | processing task, is_child = 0 0.39.228.566 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.201 0.39.228.599 I slot launch_slot_: id 0 | task 43 | processing task, is_child = 0 0.39.228.632 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.199 0.39.228.660 I slot launch_slot_: id 1 | task 44 | processing task, is_child = 0 0.39.228.680 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.254 0.39.228.707 I slot launch_slot_: id 2 | task 45 | processing task, is_child = 0 0.40.418.429 I slot print_timing: id 0 | task 43 | prompt eval time = 1142.94 ms / 146 tokens ( 7.83 ms per token, 127.74 tokens per second) 0.40.418.432 I slot print_timing: id 0 | task 43 | eval time = 46.78 ms / 2 tokens ( 46.78 ms per token, 21.38 tokens per second) 0.40.418.433 I slot print_timing: id 0 | task 43 | total time = 1189.71 ms / 148 tokens 0.40.418.433 I slot print_timing: id 0 | task 43 | graphs reused = 1 0.40.418.434 I slot print_timing: id 0 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.418.456 I slot release: id 0 | task 43 | stop processing: n_tokens = 147, truncated = 0 0.40.418.730 I slot print_timing: id 1 | task 44 | prompt eval time = 1143.22 ms / 123 tokens ( 9.29 ms per token, 107.59 tokens per second) 0.40.418.732 I slot print_timing: id 1 | task 44 | eval time = 46.79 ms / 2 tokens ( 46.79 ms per token, 21.37 tokens per second) 0.40.418.733 I slot print_timing: id 1 | task 44 | total time = 1190.00 ms / 125 tokens 0.40.418.733 I slot print_timing: id 1 | task 44 | graphs reused = 1 0.40.418.733 I slot print_timing: id 1 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.418.745 I slot release: id 1 | task 44 | stop processing: n_tokens = 124, truncated = 0 0.40.419.021 I slot print_timing: id 2 | task 45 | prompt eval time = 1143.48 ms / 110 tokens ( 10.40 ms per token, 96.20 tokens per second) 0.40.419.022 I slot print_timing: id 2 | task 45 | eval time = 46.80 ms / 2 tokens ( 46.80 ms per token, 21.37 tokens per second) 0.40.419.023 I slot print_timing: id 2 | task 45 | total time = 1190.28 ms / 112 tokens 0.40.419.023 I slot print_timing: id 2 | task 45 | graphs reused = 1 0.40.419.023 I slot print_timing: id 2 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.419.035 I slot release: id 2 | task 45 | stop processing: n_tokens = 111, truncated = 0 0.40.419.325 I slot print_timing: id 3 | task 42 | prompt eval time = 1143.84 ms / 115 tokens ( 9.95 ms per token, 100.54 tokens per second) 0.40.419.328 I slot print_timing: id 3 | task 42 | eval time = 46.74 ms / 2 tokens ( 46.74 ms per token, 21.40 tokens per second) 0.40.419.328 I slot print_timing: id 3 | task 42 | total time = 1190.58 ms / 117 tokens 0.40.419.328 I slot print_timing: id 3 | task 42 | graphs reused = 1 0.40.419.329 I slot print_timing: id 3 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.419.337 I slot release: id 3 | task 42 | stop processing: n_tokens = 116, truncated = 0 0.40.424.107 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.197 0.40.424.523 I slot launch_slot_: id 0 | task 49 | processing task, is_child = 0 0.40.425.336 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.234 0.40.425.366 I slot launch_slot_: id 1 | task 50 | processing task, is_child = 0 0.40.425.398 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.284 0.40.425.425 I slot launch_slot_: id 3 | task 51 | processing task, is_child = 0 0.40.425.443 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.261 0.40.425.470 I slot launch_slot_: id 2 | task 52 | processing task, is_child = 0 0.41.675.501 I slot print_timing: id 0 | task 49 | prompt eval time = 1203.08 ms / 103 tokens ( 11.68 ms per token, 85.61 tokens per second) 0.41.675.506 I slot print_timing: id 0 | task 49 | eval time = 46.94 ms / 2 tokens ( 46.94 ms per token, 21.30 tokens per second) 0.41.675.507 I slot print_timing: id 0 | task 49 | total time = 1250.02 ms / 105 tokens 0.41.675.507 I slot print_timing: id 0 | task 49 | graphs reused = 1 0.41.675.508 I slot print_timing: id 0 | task 49 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.675.529 I slot release: id 0 | task 49 | stop processing: n_tokens = 104, truncated = 0 0.41.675.800 I slot print_timing: id 1 | task 50 | prompt eval time = 1203.36 ms / 137 tokens ( 8.78 ms per token, 113.85 tokens per second) 0.41.675.804 I slot print_timing: id 1 | task 50 | eval time = 46.96 ms / 2 tokens ( 46.96 ms per token, 21.30 tokens per second) 0.41.675.804 I slot print_timing: id 1 | task 50 | total time = 1250.31 ms / 139 tokens 0.41.675.804 I slot print_timing: id 1 | task 50 | graphs reused = 1 0.41.675.805 I slot print_timing: id 1 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.675.822 I slot release: id 1 | task 50 | stop processing: n_tokens = 138, truncated = 0 0.41.676.109 I slot print_timing: id 2 | task 52 | prompt eval time = 1203.66 ms / 114 tokens ( 10.56 ms per token, 94.71 tokens per second) 0.41.676.112 I slot print_timing: id 2 | task 52 | eval time = 46.95 ms / 2 tokens ( 46.95 ms per token, 21.30 tokens per second) 0.41.676.112 I slot print_timing: id 2 | task 52 | total time = 1250.61 ms / 116 tokens 0.41.676.112 I slot print_timing: id 2 | task 52 | graphs reused = 1 0.41.676.113 I slot print_timing: id 2 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.676.126 I slot release: id 2 | task 52 | stop processing: n_tokens = 115, truncated = 0 0.41.676.441 I slot print_timing: id 3 | task 51 | prompt eval time = 1204.02 ms / 131 tokens ( 9.19 ms per token, 108.80 tokens per second) 0.41.676.444 I slot print_timing: id 3 | task 51 | eval time = 46.91 ms / 2 tokens ( 46.91 ms per token, 21.32 tokens per second) 0.41.676.444 I slot print_timing: id 3 | task 51 | total time = 1250.93 ms / 133 tokens 0.41.676.444 I slot print_timing: id 3 | task 51 | graphs reused = 1 0.41.676.445 I slot print_timing: id 3 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.676.459 I slot release: id 3 | task 51 | stop processing: n_tokens = 132, truncated = 0 0.41.681.284 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.279 0.41.681.662 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.41.682.766 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.210 0.41.682.938 I slot launch_slot_: id 1 | task 57 | processing task, is_child = 0 0.41.682.970 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.252 0.41.682.998 I slot launch_slot_: id 2 | task 58 | processing task, is_child = 0 0.41.683.014 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.220 0.41.683.045 I slot launch_slot_: id 3 | task 59 | processing task, is_child = 0 0.43.045.625 I slot print_timing: id 0 | task 56 | prompt eval time = 1315.78 ms / 132 tokens ( 9.97 ms per token, 100.32 tokens per second) 0.43.045.628 I slot print_timing: id 0 | task 56 | eval time = 46.80 ms / 2 tokens ( 46.80 ms per token, 21.37 tokens per second) 0.43.045.628 I slot print_timing: id 0 | task 56 | total time = 1362.57 ms / 134 tokens 0.43.045.629 I slot print_timing: id 0 | task 56 | graphs reused = 1 0.43.045.629 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.045.651 I slot release: id 0 | task 56 | stop processing: n_tokens = 133, truncated = 0 0.43.045.934 I slot print_timing: id 1 | task 57 | prompt eval time = 1316.05 ms / 186 tokens ( 7.08 ms per token, 141.33 tokens per second) 0.43.045.936 I slot print_timing: id 1 | task 57 | eval time = 46.82 ms / 2 tokens ( 46.82 ms per token, 21.36 tokens per second) 0.43.045.936 I slot print_timing: id 1 | task 57 | total time = 1362.87 ms / 188 tokens 0.43.045.936 I slot print_timing: id 1 | task 57 | graphs reused = 1 0.43.045.937 I slot print_timing: id 1 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.045.961 I slot release: id 1 | task 57 | stop processing: n_tokens = 187, truncated = 0 0.43.046.252 I slot print_timing: id 2 | task 58 | prompt eval time = 1316.33 ms / 168 tokens ( 7.84 ms per token, 127.63 tokens per second) 0.43.046.254 I slot print_timing: id 2 | task 58 | eval time = 46.85 ms / 2 tokens ( 46.85 ms per token, 21.35 tokens per second) 0.43.046.254 I slot print_timing: id 2 | task 58 | total time = 1363.18 ms / 170 tokens 0.43.046.255 I slot print_timing: id 2 | task 58 | graphs reused = 1 0.43.046.255 I slot print_timing: id 2 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.046.267 I slot release: id 2 | task 58 | stop processing: n_tokens = 169, truncated = 0 0.43.046.576 I slot print_timing: id 3 | task 59 | prompt eval time = 1316.66 ms / 178 tokens ( 7.40 ms per token, 135.19 tokens per second) 0.43.046.578 I slot print_timing: id 3 | task 59 | eval time = 46.83 ms / 2 tokens ( 46.83 ms per token, 21.35 tokens per second) 0.43.046.579 I slot print_timing: id 3 | task 59 | total time = 1363.49 ms / 180 tokens 0.43.046.579 I slot print_timing: id 3 | task 59 | graphs reused = 1 0.43.046.579 I slot print_timing: id 3 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.046.593 I slot release: id 3 | task 59 | stop processing: n_tokens = 179, truncated = 0 0.43.050.701 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.218 0.43.051.237 I slot launch_slot_: id 0 | task 63 | processing task, is_child = 0 0.43.052.301 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.155 0.43.052.342 I slot launch_slot_: id 1 | task 65 | processing task, is_child = 0 0.43.052.377 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.172 0.43.052.409 I slot launch_slot_: id 2 | task 64 | processing task, is_child = 0 0.43.052.428 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.162 0.43.052.461 I slot launch_slot_: id 3 | task 66 | processing task, is_child = 0 0.44.382.986 I slot print_timing: id 0 | task 63 | prompt eval time = 1283.65 ms / 141 tokens ( 9.10 ms per token, 109.84 tokens per second) 0.44.382.989 I slot print_timing: id 0 | task 63 | eval time = 46.87 ms / 2 tokens ( 46.87 ms per token, 21.34 tokens per second) 0.44.382.989 I slot print_timing: id 0 | task 63 | total time = 1330.52 ms / 143 tokens 0.44.382.990 I slot print_timing: id 0 | task 63 | graphs reused = 1 0.44.382.990 I slot print_timing: id 0 | task 63 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.383.012 I slot release: id 0 | task 63 | stop processing: n_tokens = 142, truncated = 0 0.44.383.275 I slot print_timing: id 1 | task 65 | prompt eval time = 1283.94 ms / 150 tokens ( 8.56 ms per token, 116.83 tokens per second) 0.44.383.277 I slot print_timing: id 1 | task 65 | eval time = 46.86 ms / 2 tokens ( 46.86 ms per token, 21.34 tokens per second) 0.44.383.278 I slot print_timing: id 1 | task 65 | total time = 1330.80 ms / 152 tokens 0.44.383.278 I slot print_timing: id 1 | task 65 | graphs reused = 1 0.44.383.278 I slot print_timing: id 1 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.383.294 I slot release: id 1 | task 65 | stop processing: n_tokens = 151, truncated = 0 0.44.383.571 I slot print_timing: id 2 | task 64 | prompt eval time = 1284.21 ms / 168 tokens ( 7.64 ms per token, 130.82 tokens per second) 0.44.383.573 I slot print_timing: id 2 | task 64 | eval time = 46.87 ms / 2 tokens ( 46.87 ms per token, 21.34 tokens per second) 0.44.383.573 I slot print_timing: id 2 | task 64 | total time = 1331.08 ms / 170 tokens 0.44.383.573 I slot print_timing: id 2 | task 64 | graphs reused = 1 0.44.383.574 I slot print_timing: id 2 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.383.594 I slot release: id 2 | task 64 | stop processing: n_tokens = 169, truncated = 0 0.44.383.886 I slot print_timing: id 3 | task 66 | prompt eval time = 1284.52 ms / 124 tokens ( 10.36 ms per token, 96.53 tokens per second) 0.44.383.887 I slot print_timing: id 3 | task 66 | eval time = 46.86 ms / 2 tokens ( 46.86 ms per token, 21.34 tokens per second) 0.44.383.887 I slot print_timing: id 3 | task 66 | total time = 1331.38 ms / 126 tokens 0.44.383.888 I slot print_timing: id 3 | task 66 | graphs reused = 1 0.44.383.888 I slot print_timing: id 3 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.383.898 I slot release: id 3 | task 66 | stop processing: n_tokens = 125, truncated = 0 0.44.387.646 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.240 0.44.387.989 I slot launch_slot_: id 3 | task 70 | processing task, is_child = 0 0.44.389.128 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.204 0.44.389.160 I slot launch_slot_: id 0 | task 71 | processing task, is_child = 0 0.44.389.194 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.192 0.44.389.345 I slot launch_slot_: id 1 | task 72 | processing task, is_child = 0 0.44.389.364 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.172 0.44.389.394 I slot launch_slot_: id 2 | task 73 | processing task, is_child = 0 0.45.631.263 I slot print_timing: id 0 | task 71 | prompt eval time = 1194.96 ms / 131 tokens ( 9.12 ms per token, 109.63 tokens per second) 0.45.631.265 I slot print_timing: id 0 | task 71 | eval time = 46.90 ms / 2 tokens ( 46.90 ms per token, 21.32 tokens per second) 0.45.631.265 I slot print_timing: id 0 | task 71 | total time = 1241.86 ms / 133 tokens 0.45.631.266 I slot print_timing: id 0 | task 71 | graphs reused = 1 0.45.631.266 I slot print_timing: id 0 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.631.289 I slot release: id 0 | task 71 | stop processing: n_tokens = 132, truncated = 0 0.45.631.582 I slot print_timing: id 1 | task 72 | prompt eval time = 1195.24 ms / 111 tokens ( 10.77 ms per token, 92.87 tokens per second) 0.45.631.587 I slot print_timing: id 1 | task 72 | eval time = 46.94 ms / 2 tokens ( 46.94 ms per token, 21.31 tokens per second) 0.45.631.588 I slot print_timing: id 1 | task 72 | total time = 1242.17 ms / 113 tokens 0.45.631.588 I slot print_timing: id 1 | task 72 | graphs reused = 1 0.45.631.588 I slot print_timing: id 1 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.631.601 I slot release: id 1 | task 72 | stop processing: n_tokens = 112, truncated = 0 0.45.631.894 I slot print_timing: id 2 | task 73 | prompt eval time = 1195.52 ms / 160 tokens ( 7.47 ms per token, 133.83 tokens per second) 0.45.631.896 I slot print_timing: id 2 | task 73 | eval time = 46.95 ms / 2 tokens ( 46.95 ms per token, 21.30 tokens per second) 0.45.631.896 I slot print_timing: id 2 | task 73 | total time = 1242.47 ms / 162 tokens 0.45.631.896 I slot print_timing: id 2 | task 73 | graphs reused = 1 0.45.631.897 I slot print_timing: id 2 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.631.914 I slot release: id 2 | task 73 | stop processing: n_tokens = 161, truncated = 0 0.45.632.214 I slot print_timing: id 3 | task 70 | prompt eval time = 1195.84 ms / 164 tokens ( 7.29 ms per token, 137.14 tokens per second) 0.45.632.215 I slot print_timing: id 3 | task 70 | eval time = 46.94 ms / 2 tokens ( 46.94 ms per token, 21.30 tokens per second) 0.45.632.216 I slot print_timing: id 3 | task 70 | total time = 1242.78 ms / 166 tokens 0.45.632.216 I slot print_timing: id 3 | task 70 | graphs reused = 1 0.45.632.216 I slot print_timing: id 3 | task 70 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.632.230 I slot release: id 3 | task 70 | stop processing: n_tokens = 165, truncated = 0 0.45.636.276 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.220 0.45.636.680 I slot launch_slot_: id 0 | task 77 | processing task, is_child = 0 0.45.637.721 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.270 (> 0.100 thold), f_keep = 0.186 0.45.637.755 I slot launch_slot_: id 2 | task 78 | processing task, is_child = 0 0.45.637.789 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.259 0.45.637.817 I slot launch_slot_: id 1 | task 79 | processing task, is_child = 0 0.45.637.836 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.182 0.45.637.866 I slot launch_slot_: id 3 | task 80 | processing task, is_child = 0 0.46.906.068 I slot print_timing: id 0 | task 77 | prompt eval time = 1221.32 ms / 166 tokens ( 7.36 ms per token, 135.92 tokens per second) 0.46.906.070 I slot print_timing: id 0 | task 77 | eval time = 46.88 ms / 2 tokens ( 46.88 ms per token, 21.33 tokens per second) 0.46.906.070 I slot print_timing: id 0 | task 77 | total time = 1268.19 ms / 168 tokens 0.46.906.071 I slot print_timing: id 0 | task 77 | graphs reused = 1 0.46.906.071 I slot print_timing: id 0 | task 77 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.906.093 I slot release: id 0 | task 77 | stop processing: n_tokens = 167, truncated = 0 0.46.906.367 I slot print_timing: id 1 | task 79 | prompt eval time = 1221.58 ms / 112 tokens ( 10.91 ms per token, 91.68 tokens per second) 0.46.906.369 I slot print_timing: id 1 | task 79 | eval time = 46.90 ms / 2 tokens ( 46.90 ms per token, 21.32 tokens per second) 0.46.906.370 I slot print_timing: id 1 | task 79 | total time = 1268.48 ms / 114 tokens 0.46.906.370 I slot print_timing: id 1 | task 79 | graphs reused = 1 0.46.906.370 I slot print_timing: id 1 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.906.382 I slot release: id 1 | task 79 | stop processing: n_tokens = 113, truncated = 0 0.46.906.661 I slot print_timing: id 2 | task 78 | prompt eval time = 1221.88 ms / 111 tokens ( 11.01 ms per token, 90.84 tokens per second) 0.46.906.664 I slot print_timing: id 2 | task 78 | eval time = 46.89 ms / 2 tokens ( 46.89 ms per token, 21.33 tokens per second) 0.46.906.664 I slot print_timing: id 2 | task 78 | total time = 1268.77 ms / 113 tokens 0.46.906.664 I slot print_timing: id 2 | task 78 | graphs reused = 1 0.46.906.665 I slot print_timing: id 2 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.906.677 I slot release: id 2 | task 78 | stop processing: n_tokens = 112, truncated = 0 0.46.906.971 I slot print_timing: id 3 | task 80 | prompt eval time = 1222.18 ms / 166 tokens ( 7.36 ms per token, 135.82 tokens per second) 0.46.906.974 I slot print_timing: id 3 | task 80 | eval time = 46.88 ms / 2 tokens ( 46.88 ms per token, 21.33 tokens per second) 0.46.906.975 I slot print_timing: id 3 | task 80 | total time = 1269.06 ms / 168 tokens 0.46.906.975 I slot print_timing: id 3 | task 80 | graphs reused = 1 0.46.906.975 I slot print_timing: id 3 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.906.993 I slot release: id 3 | task 80 | stop processing: n_tokens = 167, truncated = 0 0.46.911.282 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.174 0.46.911.799 I slot launch_slot_: id 0 | task 84 | processing task, is_child = 0 0.46.912.730 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.257 0.46.912.770 I slot launch_slot_: id 1 | task 85 | processing task, is_child = 0 0.46.912.824 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.259 0.46.912.856 I slot launch_slot_: id 2 | task 86 | processing task, is_child = 0 0.46.912.878 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.174 0.46.913.042 I slot launch_slot_: id 3 | task 87 | processing task, is_child = 0 0.48.035.974 I slot print_timing: id 0 | task 84 | prompt eval time = 1076.00 ms / 133 tokens ( 8.09 ms per token, 123.61 tokens per second) 0.48.035.976 I slot print_timing: id 0 | task 84 | eval time = 46.92 ms / 2 tokens ( 46.92 ms per token, 21.31 tokens per second) 0.48.035.976 I slot print_timing: id 0 | task 84 | total time = 1122.92 ms / 135 tokens 0.48.035.977 I slot print_timing: id 0 | task 84 | graphs reused = 1 0.48.035.977 I slot print_timing: id 0 | task 84 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.035.997 I slot release: id 0 | task 84 | stop processing: n_tokens = 134, truncated = 0 0.48.036.260 I slot print_timing: id 1 | task 85 | prompt eval time = 1076.25 ms / 145 tokens ( 7.42 ms per token, 134.73 tokens per second) 0.48.036.265 I slot print_timing: id 1 | task 85 | eval time = 46.94 ms / 2 tokens ( 46.94 ms per token, 21.30 tokens per second) 0.48.036.266 I slot print_timing: id 1 | task 85 | total time = 1123.19 ms / 147 tokens 0.48.036.266 I slot print_timing: id 1 | task 85 | graphs reused = 1 0.48.036.266 I slot print_timing: id 1 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.036.282 I slot release: id 1 | task 85 | stop processing: n_tokens = 146, truncated = 0 0.48.036.567 I slot print_timing: id 2 | task 86 | prompt eval time = 1076.52 ms / 122 tokens ( 8.82 ms per token, 113.33 tokens per second) 0.48.036.569 I slot print_timing: id 2 | task 86 | eval time = 46.97 ms / 2 tokens ( 46.97 ms per token, 21.29 tokens per second) 0.48.036.570 I slot print_timing: id 2 | task 86 | total time = 1123.49 ms / 124 tokens 0.48.036.570 I slot print_timing: id 2 | task 86 | graphs reused = 1 0.48.036.570 I slot print_timing: id 2 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.036.581 I slot release: id 2 | task 86 | stop processing: n_tokens = 123, truncated = 0 0.48.036.885 I slot print_timing: id 3 | task 87 | prompt eval time = 1076.92 ms / 127 tokens ( 8.48 ms per token, 117.93 tokens per second) 0.48.036.888 I slot print_timing: id 3 | task 87 | eval time = 46.88 ms / 2 tokens ( 46.88 ms per token, 21.33 tokens per second) 0.48.036.889 I slot print_timing: id 3 | task 87 | total time = 1123.80 ms / 129 tokens 0.48.036.889 I slot print_timing: id 3 | task 87 | graphs reused = 1 0.48.036.889 I slot print_timing: id 3 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.036.901 I slot release: id 3 | task 87 | stop processing: n_tokens = 128, truncated = 0 0.48.041.715 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.205 (> 0.100 thold), f_keep = 0.234 0.48.042.089 I slot launch_slot_: id 3 | task 91 | processing task, is_child = 0 0.48.043.174 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 0.48.043.208 I slot launch_slot_: id 0 | task 92 | processing task, is_child = 0 0.48.043.241 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.199 0.48.043.417 I slot launch_slot_: id 1 | task 93 | processing task, is_child = 0 0.48.043.435 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.236 0.48.043.571 I slot launch_slot_: id 2 | task 94 | processing task, is_child = 0 0.49.194.390 I slot print_timing: id 0 | task 92 | prompt eval time = 1104.06 ms / 126 tokens ( 8.76 ms per token, 114.12 tokens per second) 0.49.194.392 I slot print_timing: id 0 | task 92 | eval time = 46.76 ms / 2 tokens ( 46.76 ms per token, 21.39 tokens per second) 0.49.194.392 I slot print_timing: id 0 | task 92 | total time = 1150.81 ms / 128 tokens 0.49.194.393 I slot print_timing: id 0 | task 92 | graphs reused = 1 0.49.194.393 I slot print_timing: id 0 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.194.411 I slot release: id 0 | task 92 | stop processing: n_tokens = 127, truncated = 0 0.49.194.673 I slot print_timing: id 1 | task 93 | prompt eval time = 1104.31 ms / 140 tokens ( 7.89 ms per token, 126.78 tokens per second) 0.49.194.674 I slot print_timing: id 1 | task 93 | eval time = 46.77 ms / 2 tokens ( 46.77 ms per token, 21.38 tokens per second) 0.49.194.675 I slot print_timing: id 1 | task 93 | total time = 1151.08 ms / 142 tokens 0.49.194.675 I slot print_timing: id 1 | task 93 | graphs reused = 1 0.49.194.675 I slot print_timing: id 1 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.194.690 I slot release: id 1 | task 93 | stop processing: n_tokens = 141, truncated = 0 0.49.195.070 I slot print_timing: id 2 | task 94 | prompt eval time = 1104.67 ms / 133 tokens ( 8.31 ms per token, 120.40 tokens per second) 0.49.195.072 I slot print_timing: id 2 | task 94 | eval time = 46.81 ms / 2 tokens ( 46.81 ms per token, 21.36 tokens per second) 0.49.195.072 I slot print_timing: id 2 | task 94 | total time = 1151.47 ms / 135 tokens 0.49.195.073 I slot print_timing: id 2 | task 94 | graphs reused = 1 0.49.195.073 I slot print_timing: id 2 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.195.083 I slot release: id 2 | task 94 | stop processing: n_tokens = 134, truncated = 0 0.49.195.378 I slot print_timing: id 3 | task 91 | prompt eval time = 1104.98 ms / 146 tokens ( 7.57 ms per token, 132.13 tokens per second) 0.49.195.380 I slot print_timing: id 3 | task 91 | eval time = 46.79 ms / 2 tokens ( 46.79 ms per token, 21.37 tokens per second) 0.49.195.380 I slot print_timing: id 3 | task 91 | total time = 1151.77 ms / 148 tokens 0.49.195.381 I slot print_timing: id 3 | task 91 | graphs reused = 1 0.49.195.381 I slot print_timing: id 3 | task 91 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.195.396 I slot release: id 3 | task 91 | stop processing: n_tokens = 147, truncated = 0 0.49.199.209 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 0.49.199.662 I slot launch_slot_: id 0 | task 98 | processing task, is_child = 0 0.49.200.782 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.224 0.49.200.818 I slot launch_slot_: id 2 | task 99 | processing task, is_child = 0 0.49.200.852 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.204 0.49.200.882 I slot launch_slot_: id 3 | task 100 | processing task, is_child = 0 0.49.200.901 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.213 0.49.200.930 I slot launch_slot_: id 1 | task 101 | processing task, is_child = 0 0.50.476.792 I slot print_timing: id 0 | task 98 | prompt eval time = 1229.19 ms / 123 tokens ( 9.99 ms per token, 100.07 tokens per second) 0.50.476.794 I slot print_timing: id 0 | task 98 | eval time = 46.65 ms / 2 tokens ( 46.65 ms per token, 21.44 tokens per second) 0.50.476.794 I slot print_timing: id 0 | task 98 | total time = 1275.85 ms / 125 tokens 0.50.476.795 I slot print_timing: id 0 | task 98 | graphs reused = 1 0.50.476.795 I slot print_timing: id 0 | task 98 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.476.814 I slot release: id 0 | task 98 | stop processing: n_tokens = 124, truncated = 0 0.50.477.101 I slot print_timing: id 1 | task 101 | prompt eval time = 1229.47 ms / 171 tokens ( 7.19 ms per token, 139.08 tokens per second) 0.50.477.103 I slot print_timing: id 1 | task 101 | eval time = 46.68 ms / 2 tokens ( 46.68 ms per token, 21.42 tokens per second) 0.50.477.104 I slot print_timing: id 1 | task 101 | total time = 1276.15 ms / 173 tokens 0.50.477.104 I slot print_timing: id 1 | task 101 | graphs reused = 1 0.50.477.105 I slot print_timing: id 1 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.477.123 I slot release: id 1 | task 101 | stop processing: n_tokens = 172, truncated = 0 0.50.477.407 I slot print_timing: id 2 | task 99 | prompt eval time = 1229.72 ms / 120 tokens ( 10.25 ms per token, 97.58 tokens per second) 0.50.477.409 I slot print_timing: id 2 | task 99 | eval time = 46.72 ms / 2 tokens ( 46.72 ms per token, 21.40 tokens per second) 0.50.477.409 I slot print_timing: id 2 | task 99 | total time = 1276.45 ms / 122 tokens 0.50.477.409 I slot print_timing: id 2 | task 99 | graphs reused = 1 0.50.477.409 I slot print_timing: id 2 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.477.422 I slot release: id 2 | task 99 | stop processing: n_tokens = 121, truncated = 0 0.50.477.712 I slot print_timing: id 3 | task 100 | prompt eval time = 1230.01 ms / 110 tokens ( 11.18 ms per token, 89.43 tokens per second) 0.50.477.714 I slot print_timing: id 3 | task 100 | eval time = 46.73 ms / 2 tokens ( 46.73 ms per token, 21.40 tokens per second) 0.50.477.715 I slot print_timing: id 3 | task 100 | total time = 1276.74 ms / 112 tokens 0.50.477.715 I slot print_timing: id 3 | task 100 | graphs reused = 1 0.50.477.715 I slot print_timing: id 3 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.477.728 I slot release: id 3 | task 100 | stop processing: n_tokens = 111, truncated = 0 0.50.481.794 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.256 (> 0.100 thold), f_keep = 0.248 0.50.482.227 I slot launch_slot_: id 2 | task 105 | processing task, is_child = 0 0.50.483.211 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.270 0.50.483.245 I slot launch_slot_: id 3 | task 106 | processing task, is_child = 0 0.50.483.280 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 0.50.483.309 I slot launch_slot_: id 0 | task 107 | processing task, is_child = 0 0.50.483.329 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.169 0.50.483.359 I slot launch_slot_: id 1 | task 108 | processing task, is_child = 0 0.51.965.599 I slot print_timing: id 0 | task 107 | prompt eval time = 1435.46 ms / 232 tokens ( 6.19 ms per token, 161.62 tokens per second) 0.51.965.603 I slot print_timing: id 0 | task 107 | eval time = 46.77 ms / 2 tokens ( 46.77 ms per token, 21.38 tokens per second) 0.51.965.603 I slot print_timing: id 0 | task 107 | total time = 1482.23 ms / 234 tokens 0.51.965.604 I slot print_timing: id 0 | task 107 | graphs reused = 1 0.51.965.604 I slot print_timing: id 0 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.965.632 I slot release: id 0 | task 107 | stop processing: n_tokens = 233, truncated = 0 0.51.965.913 I slot print_timing: id 1 | task 108 | prompt eval time = 1435.74 ms / 176 tokens ( 8.16 ms per token, 122.59 tokens per second) 0.51.965.915 I slot print_timing: id 1 | task 108 | eval time = 46.80 ms / 2 tokens ( 46.80 ms per token, 21.37 tokens per second) 0.51.965.916 I slot print_timing: id 1 | task 108 | total time = 1482.54 ms / 178 tokens 0.51.965.916 I slot print_timing: id 1 | task 108 | graphs reused = 1 0.51.965.916 I slot print_timing: id 1 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.965.935 I slot release: id 1 | task 108 | stop processing: n_tokens = 177, truncated = 0 0.51.966.209 I slot print_timing: id 2 | task 105 | prompt eval time = 1436.00 ms / 117 tokens ( 12.27 ms per token, 81.48 tokens per second) 0.51.966.211 I slot print_timing: id 2 | task 105 | eval time = 46.81 ms / 2 tokens ( 46.81 ms per token, 21.36 tokens per second) 0.51.966.211 I slot print_timing: id 2 | task 105 | total time = 1482.82 ms / 119 tokens 0.51.966.211 I slot print_timing: id 2 | task 105 | graphs reused = 1 0.51.966.212 I slot print_timing: id 2 | task 105 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.966.226 I slot release: id 2 | task 105 | stop processing: n_tokens = 118, truncated = 0 0.51.966.521 I slot print_timing: id 3 | task 106 | prompt eval time = 1436.30 ms / 138 tokens ( 10.41 ms per token, 96.08 tokens per second) 0.51.966.523 I slot print_timing: id 3 | task 106 | eval time = 46.82 ms / 2 tokens ( 46.82 ms per token, 21.36 tokens per second) 0.51.966.523 I slot print_timing: id 3 | task 106 | total time = 1483.12 ms / 140 tokens 0.51.966.523 I slot print_timing: id 3 | task 106 | graphs reused = 1 0.51.966.524 I slot print_timing: id 3 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.966.543 I slot release: id 3 | task 106 | stop processing: n_tokens = 139, truncated = 0 0.51.971.077 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.263 0.51.971.511 I slot launch_slot_: id 2 | task 113 | processing task, is_child = 0 0.51.972.883 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 0.51.973.040 I slot launch_slot_: id 3 | task 112 | processing task, is_child = 0 0.51.973.078 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.124 0.51.973.110 I slot launch_slot_: id 0 | task 114 | processing task, is_child = 0 0.51.973.130 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.164 0.51.973.160 I slot launch_slot_: id 1 | task 115 | processing task, is_child = 0 0.53.640.942 I slot print_timing: id 0 | task 114 | prompt eval time = 1620.87 ms / 158 tokens ( 10.26 ms per token, 97.48 tokens per second) 0.53.640.948 I slot print_timing: id 0 | task 114 | eval time = 46.91 ms / 2 tokens ( 46.91 ms per token, 21.32 tokens per second) 0.53.640.949 I slot print_timing: id 0 | task 114 | total time = 1667.77 ms / 160 tokens 0.53.640.949 I slot print_timing: id 0 | task 114 | graphs reused = 1 0.53.640.949 I slot print_timing: id 0 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.640.977 I slot release: id 0 | task 114 | stop processing: n_tokens = 159, truncated = 0 0.53.641.293 I slot print_timing: id 1 | task 115 | prompt eval time = 1621.15 ms / 227 tokens ( 7.14 ms per token, 140.02 tokens per second) 0.53.641.297 I slot print_timing: id 1 | task 115 | eval time = 46.96 ms / 2 tokens ( 46.96 ms per token, 21.29 tokens per second) 0.53.641.298 I slot print_timing: id 1 | task 115 | total time = 1668.11 ms / 229 tokens 0.53.641.298 I slot print_timing: id 1 | task 115 | graphs reused = 1 0.53.641.298 I slot print_timing: id 1 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.641.319 I slot release: id 1 | task 115 | stop processing: n_tokens = 228, truncated = 0 0.53.641.700 I slot print_timing: id 2 | task 113 | prompt eval time = 1621.51 ms / 156 tokens ( 10.39 ms per token, 96.21 tokens per second) 0.53.641.704 I slot print_timing: id 2 | task 113 | eval time = 47.00 ms / 2 tokens ( 47.00 ms per token, 21.28 tokens per second) 0.53.641.705 I slot print_timing: id 2 | task 113 | total time = 1668.50 ms / 158 tokens 0.53.641.705 I slot print_timing: id 2 | task 113 | graphs reused = 1 0.53.641.706 I slot print_timing: id 2 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.641.726 I slot release: id 2 | task 113 | stop processing: n_tokens = 157, truncated = 0 0.53.642.103 I slot print_timing: id 3 | task 112 | prompt eval time = 1621.86 ms / 143 tokens ( 11.34 ms per token, 88.17 tokens per second) 0.53.642.105 I slot print_timing: id 3 | task 112 | eval time = 47.04 ms / 2 tokens ( 47.04 ms per token, 21.26 tokens per second) 0.53.642.106 I slot print_timing: id 3 | task 112 | total time = 1668.90 ms / 145 tokens 0.53.642.106 I slot print_timing: id 3 | task 112 | graphs reused = 1 0.53.642.106 I slot print_timing: id 3 | task 112 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.642.124 I slot release: id 3 | task 112 | stop processing: n_tokens = 144, truncated = 0 0.53.646.190 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 0.53.646.641 I slot launch_slot_: id 3 | task 119 | processing task, is_child = 0 0.53.648.031 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.256 (> 0.100 thold), f_keep = 0.191 0.53.648.067 I slot launch_slot_: id 2 | task 120 | processing task, is_child = 0 0.53.648.104 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.182 0.53.648.136 I slot launch_slot_: id 0 | task 121 | processing task, is_child = 0 0.53.648.157 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.153 (> 0.100 thold), f_keep = 0.127 0.53.648.305 I slot launch_slot_: id 1 | task 122 | processing task, is_child = 0 0.55.082.430 I slot print_timing: id 0 | task 121 | prompt eval time = 1387.13 ms / 143 tokens ( 9.70 ms per token, 103.09 tokens per second) 0.55.082.432 I slot print_timing: id 0 | task 121 | eval time = 46.98 ms / 2 tokens ( 46.98 ms per token, 21.29 tokens per second) 0.55.082.433 I slot print_timing: id 0 | task 121 | total time = 1434.12 ms / 145 tokens 0.55.082.433 I slot print_timing: id 0 | task 121 | graphs reused = 1 0.55.082.434 I slot print_timing: id 0 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.082.456 I slot release: id 0 | task 121 | stop processing: n_tokens = 144, truncated = 0 0.55.082.735 I slot print_timing: id 1 | task 122 | prompt eval time = 1387.41 ms / 189 tokens ( 7.34 ms per token, 136.23 tokens per second) 0.55.082.737 I slot print_timing: id 1 | task 122 | eval time = 47.00 ms / 2 tokens ( 47.00 ms per token, 21.27 tokens per second) 0.55.082.738 I slot print_timing: id 1 | task 122 | total time = 1434.41 ms / 191 tokens 0.55.082.738 I slot print_timing: id 1 | task 122 | graphs reused = 1 0.55.082.738 I slot print_timing: id 1 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.082.762 I slot release: id 1 | task 122 | stop processing: n_tokens = 190, truncated = 0 0.55.083.053 I slot print_timing: id 2 | task 120 | prompt eval time = 1387.71 ms / 117 tokens ( 11.86 ms per token, 84.31 tokens per second) 0.55.083.055 I slot print_timing: id 2 | task 120 | eval time = 47.01 ms / 2 tokens ( 47.01 ms per token, 21.27 tokens per second) 0.55.083.055 I slot print_timing: id 2 | task 120 | total time = 1434.72 ms / 119 tokens 0.55.083.055 I slot print_timing: id 2 | task 120 | graphs reused = 1 0.55.083.056 I slot print_timing: id 2 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.083.067 I slot release: id 2 | task 120 | stop processing: n_tokens = 118, truncated = 0 0.55.083.363 I slot print_timing: id 3 | task 119 | prompt eval time = 1388.04 ms / 107 tokens ( 12.97 ms per token, 77.09 tokens per second) 0.55.083.366 I slot print_timing: id 3 | task 119 | eval time = 46.98 ms / 2 tokens ( 46.98 ms per token, 21.29 tokens per second) 0.55.083.366 I slot print_timing: id 3 | task 119 | total time = 1435.02 ms / 109 tokens 0.55.083.367 I slot print_timing: id 3 | task 119 | graphs reused = 1 0.55.083.367 I slot print_timing: id 3 | task 119 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.083.378 I slot release: id 3 | task 119 | stop processing: n_tokens = 108, truncated = 0 0.55.087.469 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.201 0.55.087.989 I slot launch_slot_: id 0 | task 126 | processing task, is_child = 0 0.55.088.853 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.254 0.55.088.884 I slot launch_slot_: id 2 | task 127 | processing task, is_child = 0 0.55.088.919 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 0.55.088.948 I slot launch_slot_: id 3 | task 128 | processing task, is_child = 0 0.55.088.967 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.153 0.55.088.998 I slot launch_slot_: id 1 | task 129 | processing task, is_child = 0 0.56.387.013 I slot print_timing: id 0 | task 126 | prompt eval time = 1251.18 ms / 173 tokens ( 7.23 ms per token, 138.27 tokens per second) 0.56.387.015 I slot print_timing: id 0 | task 126 | eval time = 46.83 ms / 2 tokens ( 46.83 ms per token, 21.35 tokens per second) 0.56.387.015 I slot print_timing: id 0 | task 126 | total time = 1298.01 ms / 175 tokens 0.56.387.015 I slot print_timing: id 0 | task 126 | graphs reused = 1 0.56.387.016 I slot print_timing: id 0 | task 126 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.387.039 I slot release: id 0 | task 126 | stop processing: n_tokens = 174, truncated = 0 0.56.387.322 I slot print_timing: id 1 | task 129 | prompt eval time = 1251.44 ms / 138 tokens ( 9.07 ms per token, 110.27 tokens per second) 0.56.387.324 I slot print_timing: id 1 | task 129 | eval time = 46.87 ms / 2 tokens ( 46.87 ms per token, 21.34 tokens per second) 0.56.387.325 I slot print_timing: id 1 | task 129 | total time = 1298.30 ms / 140 tokens 0.56.387.325 I slot print_timing: id 1 | task 129 | graphs reused = 1 0.56.387.325 I slot print_timing: id 1 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.387.342 I slot release: id 1 | task 129 | stop processing: n_tokens = 139, truncated = 0 0.56.387.613 I slot print_timing: id 2 | task 127 | prompt eval time = 1251.69 ms / 110 tokens ( 11.38 ms per token, 87.88 tokens per second) 0.56.387.615 I slot print_timing: id 2 | task 127 | eval time = 46.89 ms / 2 tokens ( 46.89 ms per token, 21.33 tokens per second) 0.56.387.615 I slot print_timing: id 2 | task 127 | total time = 1298.58 ms / 112 tokens 0.56.387.615 I slot print_timing: id 2 | task 127 | graphs reused = 1 0.56.387.616 I slot print_timing: id 2 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.387.633 I slot release: id 2 | task 127 | stop processing: n_tokens = 111, truncated = 0 0.56.387.928 I slot print_timing: id 3 | task 128 | prompt eval time = 1252.01 ms / 123 tokens ( 10.18 ms per token, 98.24 tokens per second) 0.56.387.930 I slot print_timing: id 3 | task 128 | eval time = 46.87 ms / 2 tokens ( 46.87 ms per token, 21.33 tokens per second) 0.56.387.931 I slot print_timing: id 3 | task 128 | total time = 1298.88 ms / 125 tokens 0.56.387.931 I slot print_timing: id 3 | task 128 | graphs reused = 1 0.56.387.931 I slot print_timing: id 3 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.387.944 I slot release: id 3 | task 128 | stop processing: n_tokens = 124, truncated = 0 0.56.391.628 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.270 0.56.391.983 I slot launch_slot_: id 2 | task 133 | processing task, is_child = 0 0.56.393.155 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.167 0.56.393.192 I slot launch_slot_: id 0 | task 134 | processing task, is_child = 0 0.56.393.225 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.209 0.56.393.268 I slot launch_slot_: id 1 | task 135 | processing task, is_child = 0 0.56.393.285 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.234 0.56.393.316 I slot launch_slot_: id 3 | task 136 | processing task, is_child = 0 0.57.691.502 I slot print_timing: id 0 | task 134 | prompt eval time = 1251.31 ms / 161 tokens ( 7.77 ms per token, 128.67 tokens per second) 0.57.691.504 I slot print_timing: id 0 | task 134 | eval time = 46.87 ms / 2 tokens ( 46.87 ms per token, 21.34 tokens per second) 0.57.691.504 I slot print_timing: id 0 | task 134 | total time = 1298.18 ms / 163 tokens 0.57.691.505 I slot print_timing: id 0 | task 134 | graphs reused = 1 0.57.691.505 I slot print_timing: id 0 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.691.532 I slot release: id 0 | task 134 | stop processing: n_tokens = 162, truncated = 0 0.57.691.827 I slot print_timing: id 1 | task 135 | prompt eval time = 1251.58 ms / 134 tokens ( 9.34 ms per token, 107.06 tokens per second) 0.57.691.830 I slot print_timing: id 1 | task 135 | eval time = 46.91 ms / 2 tokens ( 46.91 ms per token, 21.32 tokens per second) 0.57.691.830 I slot print_timing: id 1 | task 135 | total time = 1298.49 ms / 136 tokens 0.57.691.831 I slot print_timing: id 1 | task 135 | graphs reused = 1 0.57.691.831 I slot print_timing: id 1 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.691.848 I slot release: id 1 | task 135 | stop processing: n_tokens = 135, truncated = 0 0.57.692.437 I slot print_timing: id 3 | task 136 | prompt eval time = 1252.29 ms / 136 tokens ( 9.21 ms per token, 108.60 tokens per second) 0.57.692.441 I slot print_timing: id 3 | task 136 | eval time = 46.79 ms / 2 tokens ( 46.79 ms per token, 21.37 tokens per second) 0.57.692.442 I slot print_timing: id 3 | task 136 | total time = 1299.08 ms / 138 tokens 0.57.692.442 I slot print_timing: id 3 | task 136 | graphs reused = 1 0.57.692.442 I slot print_timing: id 3 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.692.454 I slot release: id 3 | task 136 | stop processing: n_tokens = 137, truncated = 0 0.57.710.618 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.179 0.57.711.041 I slot launch_slot_: id 0 | task 141 | processing task, is_child = 0 0.57.711.775 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.215 0.57.711.827 I slot launch_slot_: id 1 | task 142 | processing task, is_child = 0 0.57.711.848 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.212 0.57.711.882 I slot launch_slot_: id 3 | task 143 | processing task, is_child = 0 0.58.880.692 I slot print_timing: id 0 | task 141 | prompt eval time = 1122.00 ms / 131 tokens ( 8.56 ms per token, 116.76 tokens per second) 0.58.880.694 I slot print_timing: id 0 | task 141 | eval time = 46.80 ms / 2 tokens ( 46.80 ms per token, 21.37 tokens per second) 0.58.880.694 I slot print_timing: id 0 | task 141 | total time = 1168.80 ms / 133 tokens 0.58.880.695 I slot print_timing: id 0 | task 141 | graphs reused = 1 0.58.880.695 I slot print_timing: id 0 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.880.714 I slot release: id 0 | task 141 | stop processing: n_tokens = 132, truncated = 0 0.58.880.984 I slot print_timing: id 1 | task 142 | prompt eval time = 1122.25 ms / 181 tokens ( 6.20 ms per token, 161.28 tokens per second) 0.58.880.986 I slot print_timing: id 1 | task 142 | eval time = 46.82 ms / 2 tokens ( 46.82 ms per token, 21.36 tokens per second) 0.58.880.987 I slot print_timing: id 1 | task 142 | total time = 1169.07 ms / 183 tokens 0.58.880.987 I slot print_timing: id 1 | task 142 | graphs reused = 1 0.58.880.987 I slot print_timing: id 1 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.881.006 I slot release: id 1 | task 142 | stop processing: n_tokens = 182, truncated = 0 0.58.881.609 I slot print_timing: id 3 | task 143 | prompt eval time = 1122.81 ms / 175 tokens ( 6.42 ms per token, 155.86 tokens per second) 0.58.881.610 I slot print_timing: id 3 | task 143 | eval time = 46.87 ms / 2 tokens ( 46.87 ms per token, 21.34 tokens per second) 0.58.881.611 I slot print_timing: id 3 | task 143 | total time = 1169.68 ms / 177 tokens 0.58.881.611 I slot print_timing: id 3 | task 143 | graphs reused = 1 0.58.881.611 I slot print_timing: id 3 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.881.627 I slot release: id 3 | task 143 | stop processing: n_tokens = 176, truncated = 0 0.58.899.625 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.170 (> 0.100 thold), f_keep = 0.220 0.58.900.051 I slot launch_slot_: id 0 | task 148 | processing task, is_child = 0 0.58.900.858 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.159 0.58.901.025 I slot launch_slot_: id 1 | task 149 | processing task, is_child = 0 0.58.901.047 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.165 0.58.901.084 I slot launch_slot_: id 3 | task 150 | processing task, is_child = 0 1.00.002.871 I slot print_timing: id 0 | task 148 | prompt eval time = 1054.76 ms / 171 tokens ( 6.17 ms per token, 162.12 tokens per second) 1.00.002.876 I slot print_timing: id 0 | task 148 | eval time = 47.02 ms / 2 tokens ( 47.02 ms per token, 21.27 tokens per second) 1.00.002.876 I slot print_timing: id 0 | task 148 | total time = 1101.78 ms / 173 tokens 1.00.002.877 I slot print_timing: id 0 | task 148 | graphs reused = 1 1.00.002.877 I slot print_timing: id 0 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.002.899 I slot release: id 0 | task 148 | stop processing: n_tokens = 172, truncated = 0 1.00.003.164 I slot print_timing: id 1 | task 149 | prompt eval time = 1055.02 ms / 123 tokens ( 8.58 ms per token, 116.59 tokens per second) 1.00.003.166 I slot print_timing: id 1 | task 149 | eval time = 47.04 ms / 2 tokens ( 47.04 ms per token, 21.26 tokens per second) 1.00.003.166 I slot print_timing: id 1 | task 149 | total time = 1102.06 ms / 125 tokens 1.00.003.166 I slot print_timing: id 1 | task 149 | graphs reused = 1 1.00.003.167 I slot print_timing: id 1 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.003.179 I slot release: id 1 | task 149 | stop processing: n_tokens = 124, truncated = 0 1.00.003.753 I slot print_timing: id 3 | task 150 | prompt eval time = 1055.70 ms / 115 tokens ( 9.18 ms per token, 108.93 tokens per second) 1.00.003.754 I slot print_timing: id 3 | task 150 | eval time = 46.93 ms / 2 tokens ( 46.93 ms per token, 21.31 tokens per second) 1.00.003.755 I slot print_timing: id 3 | task 150 | total time = 1102.64 ms / 117 tokens 1.00.003.755 I slot print_timing: id 3 | task 150 | graphs reused = 1 1.00.003.755 I slot print_timing: id 3 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.003.766 I slot release: id 3 | task 150 | stop processing: n_tokens = 116, truncated = 0 1.00.021.741 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.169 1.00.022.210 I slot launch_slot_: id 0 | task 155 | processing task, is_child = 0 1.00.022.754 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.242 1.00.022.941 I slot launch_slot_: id 1 | task 156 | processing task, is_child = 0 1.00.022.962 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.225 (> 0.100 thold), f_keep = 0.250 1.00.023.112 I slot launch_slot_: id 3 | task 157 | processing task, is_child = 0 1.00.971.619 I slot print_timing: id 0 | task 155 | prompt eval time = 901.60 ms / 125 tokens ( 7.21 ms per token, 138.64 tokens per second) 1.00.971.624 I slot print_timing: id 0 | task 155 | eval time = 46.90 ms / 2 tokens ( 46.90 ms per token, 21.32 tokens per second) 1.00.971.625 I slot print_timing: id 0 | task 155 | total time = 948.50 ms / 127 tokens 1.00.971.625 I slot print_timing: id 0 | task 155 | graphs reused = 1 1.00.971.626 I slot print_timing: id 0 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.971.645 I slot release: id 0 | task 155 | stop processing: n_tokens = 126, truncated = 0 1.00.972.003 I slot print_timing: id 1 | task 156 | prompt eval time = 901.93 ms / 116 tokens ( 7.78 ms per token, 128.61 tokens per second) 1.00.972.006 I slot print_timing: id 1 | task 156 | eval time = 46.93 ms / 2 tokens ( 46.93 ms per token, 21.31 tokens per second) 1.00.972.006 I slot print_timing: id 1 | task 156 | total time = 948.87 ms / 118 tokens 1.00.972.007 I slot print_timing: id 1 | task 156 | graphs reused = 1 1.00.972.007 I slot print_timing: id 1 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.972.018 I slot release: id 1 | task 156 | stop processing: n_tokens = 117, truncated = 0 1.00.972.703 I slot print_timing: id 3 | task 157 | prompt eval time = 902.72 ms / 129 tokens ( 7.00 ms per token, 142.90 tokens per second) 1.00.972.705 I slot print_timing: id 3 | task 157 | eval time = 46.83 ms / 2 tokens ( 46.83 ms per token, 21.35 tokens per second) 1.00.972.706 I slot print_timing: id 3 | task 157 | total time = 949.55 ms / 131 tokens 1.00.972.706 I slot print_timing: id 3 | task 157 | graphs reused = 1 1.00.972.706 I slot print_timing: id 3 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.972.720 I slot release: id 3 | task 157 | stop processing: n_tokens = 130, truncated = 0 1.00.990.780 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.223 (> 0.100 thold), f_keep = 0.230 1.00.991.098 I slot launch_slot_: id 0 | task 162 | processing task, is_child = 0 1.00.991.667 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 1.00.991.706 I slot launch_slot_: id 1 | task 163 | processing task, is_child = 0 1.00.991.727 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.223 1.00.991.772 I slot launch_slot_: id 3 | task 164 | processing task, is_child = 0 1.01.909.733 I slot print_timing: id 0 | task 162 | prompt eval time = 870.84 ms / 130 tokens ( 6.70 ms per token, 149.28 tokens per second) 1.01.909.735 I slot print_timing: id 0 | task 162 | eval time = 47.12 ms / 2 tokens ( 47.12 ms per token, 21.22 tokens per second) 1.01.909.736 I slot print_timing: id 0 | task 162 | total time = 917.96 ms / 132 tokens 1.01.909.737 I slot print_timing: id 0 | task 162 | graphs reused = 1 1.01.909.737 I slot print_timing: id 0 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.909.756 I slot release: id 0 | task 162 | stop processing: n_tokens = 131, truncated = 0 1.01.910.045 I slot print_timing: id 1 | task 163 | prompt eval time = 871.10 ms / 130 tokens ( 6.70 ms per token, 149.24 tokens per second) 1.01.910.047 I slot print_timing: id 1 | task 163 | eval time = 47.15 ms / 2 tokens ( 47.15 ms per token, 21.21 tokens per second) 1.01.910.047 I slot print_timing: id 1 | task 163 | total time = 918.25 ms / 132 tokens 1.01.910.047 I slot print_timing: id 1 | task 163 | graphs reused = 1 1.01.910.048 I slot print_timing: id 1 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.910.061 I slot release: id 1 | task 163 | stop processing: n_tokens = 131, truncated = 0 1.01.910.370 I slot print_timing: id 2 | task 133 | prompt eval time = 1251.88 ms / 122 tokens ( 10.26 ms per token, 97.45 tokens per second) 1.01.910.373 I slot print_timing: id 2 | task 133 | eval time = 4265.14 ms / 18 tokens ( 250.89 ms per token, 3.99 tokens per second) 1.01.910.373 I slot print_timing: id 2 | task 133 | total time = 5517.02 ms / 140 tokens 1.01.910.373 I slot print_timing: id 2 | task 133 | graphs reused = 1 1.01.910.373 I slot print_timing: id 2 | task 133 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.910.384 I slot release: id 2 | task 133 | stop processing: n_tokens = 139, truncated = 0 1.01.910.688 I slot print_timing: id 3 | task 164 | prompt eval time = 871.68 ms / 143 tokens ( 6.10 ms per token, 164.05 tokens per second) 1.01.910.693 I slot print_timing: id 3 | task 164 | eval time = 47.20 ms / 2 tokens ( 47.20 ms per token, 21.18 tokens per second) 1.01.910.693 I slot print_timing: id 3 | task 164 | total time = 918.88 ms / 145 tokens 1.01.910.693 I slot print_timing: id 3 | task 164 | graphs reused = 1 1.01.910.694 I slot print_timing: id 3 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.910.706 I slot release: id 3 | task 164 | stop processing: n_tokens = 144, truncated = 0 1.01.915.602 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.225 (> 0.100 thold), f_keep = 0.221 1.01.916.044 I slot launch_slot_: id 0 | task 168 | processing task, is_child = 0 1.01.917.090 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.286 (> 0.100 thold), f_keep = 0.216 1.01.917.129 I slot launch_slot_: id 2 | task 169 | processing task, is_child = 0 1.01.917.163 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.221 1.01.917.202 I slot launch_slot_: id 1 | task 170 | processing task, is_child = 0 1.01.917.222 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.201 1.01.917.253 I slot launch_slot_: id 3 | task 171 | processing task, is_child = 0 1.03.132.607 I slot print_timing: id 0 | task 168 | prompt eval time = 1168.10 ms / 129 tokens ( 9.06 ms per token, 110.44 tokens per second) 1.03.132.609 I slot print_timing: id 0 | task 168 | eval time = 47.24 ms / 2 tokens ( 47.24 ms per token, 21.17 tokens per second) 1.03.132.609 I slot print_timing: id 0 | task 168 | total time = 1215.35 ms / 131 tokens 1.03.132.610 I slot print_timing: id 0 | task 168 | graphs reused = 1 1.03.132.610 I slot print_timing: id 0 | task 168 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.132.628 I slot release: id 0 | task 168 | stop processing: n_tokens = 130, truncated = 0 1.03.132.898 I slot print_timing: id 1 | task 170 | prompt eval time = 1168.37 ms / 124 tokens ( 9.42 ms per token, 106.13 tokens per second) 1.03.132.900 I slot print_timing: id 1 | task 170 | eval time = 47.26 ms / 2 tokens ( 47.26 ms per token, 21.16 tokens per second) 1.03.132.900 I slot print_timing: id 1 | task 170 | total time = 1215.63 ms / 126 tokens 1.03.132.900 I slot print_timing: id 1 | task 170 | graphs reused = 1 1.03.132.901 I slot print_timing: id 1 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.132.916 I slot release: id 1 | task 170 | stop processing: n_tokens = 125, truncated = 0 1.03.133.205 I slot print_timing: id 2 | task 169 | prompt eval time = 1168.65 ms / 105 tokens ( 11.13 ms per token, 89.85 tokens per second) 1.03.133.207 I slot print_timing: id 2 | task 169 | eval time = 47.27 ms / 2 tokens ( 47.27 ms per token, 21.15 tokens per second) 1.03.133.208 I slot print_timing: id 2 | task 169 | total time = 1215.92 ms / 107 tokens 1.03.133.208 I slot print_timing: id 2 | task 169 | graphs reused = 1 1.03.133.209 I slot print_timing: id 2 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.133.221 I slot release: id 2 | task 169 | stop processing: n_tokens = 106, truncated = 0 1.03.133.547 I slot print_timing: id 3 | task 171 | prompt eval time = 1169.15 ms / 161 tokens ( 7.26 ms per token, 137.71 tokens per second) 1.03.133.548 I slot print_timing: id 3 | task 171 | eval time = 47.10 ms / 2 tokens ( 47.10 ms per token, 21.23 tokens per second) 1.03.133.549 I slot print_timing: id 3 | task 171 | total time = 1216.25 ms / 163 tokens 1.03.133.549 I slot print_timing: id 3 | task 171 | graphs reused = 1 1.03.133.549 I slot print_timing: id 3 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.133.567 I slot release: id 3 | task 171 | stop processing: n_tokens = 162, truncated = 0 1.03.138.073 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.223 1.03.138.682 I slot launch_slot_: id 0 | task 177 | processing task, is_child = 0 1.03.139.604 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.232 1.03.139.637 I slot launch_slot_: id 1 | task 176 | processing task, is_child = 0 1.03.139.671 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.283 1.03.139.700 I slot launch_slot_: id 2 | task 175 | processing task, is_child = 0 1.03.139.720 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.179 1.03.139.750 I slot launch_slot_: id 3 | task 178 | processing task, is_child = 0 1.04.463.056 I slot print_timing: id 0 | task 177 | prompt eval time = 1276.46 ms / 143 tokens ( 8.93 ms per token, 112.03 tokens per second) 1.04.463.058 I slot print_timing: id 0 | task 177 | eval time = 46.84 ms / 2 tokens ( 46.84 ms per token, 21.35 tokens per second) 1.04.463.059 I slot print_timing: id 0 | task 177 | total time = 1323.30 ms / 145 tokens 1.04.463.059 I slot print_timing: id 0 | task 177 | graphs reused = 1 1.04.463.060 I slot print_timing: id 0 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.463.081 I slot release: id 0 | task 177 | stop processing: n_tokens = 144, truncated = 0 1.04.463.362 I slot print_timing: id 1 | task 176 | prompt eval time = 1276.75 ms / 155 tokens ( 8.24 ms per token, 121.40 tokens per second) 1.04.463.364 I slot print_timing: id 1 | task 176 | eval time = 46.84 ms / 2 tokens ( 46.84 ms per token, 21.35 tokens per second) 1.04.463.365 I slot print_timing: id 1 | task 176 | total time = 1323.60 ms / 157 tokens 1.04.463.365 I slot print_timing: id 1 | task 176 | graphs reused = 1 1.04.463.365 I slot print_timing: id 1 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.463.388 I slot release: id 1 | task 176 | stop processing: n_tokens = 156, truncated = 0 1.04.463.660 I slot print_timing: id 2 | task 175 | prompt eval time = 1277.01 ms / 113 tokens ( 11.30 ms per token, 88.49 tokens per second) 1.04.463.661 I slot print_timing: id 2 | task 175 | eval time = 46.87 ms / 2 tokens ( 46.87 ms per token, 21.33 tokens per second) 1.04.463.662 I slot print_timing: id 2 | task 175 | total time = 1323.88 ms / 115 tokens 1.04.463.662 I slot print_timing: id 2 | task 175 | graphs reused = 1 1.04.463.662 I slot print_timing: id 2 | task 175 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.463.674 I slot release: id 2 | task 175 | stop processing: n_tokens = 114, truncated = 0 1.04.463.953 I slot print_timing: id 3 | task 178 | prompt eval time = 1277.30 ms / 169 tokens ( 7.56 ms per token, 132.31 tokens per second) 1.04.463.955 I slot print_timing: id 3 | task 178 | eval time = 46.87 ms / 2 tokens ( 46.87 ms per token, 21.34 tokens per second) 1.04.463.955 I slot print_timing: id 3 | task 178 | total time = 1324.17 ms / 171 tokens 1.04.463.956 I slot print_timing: id 3 | task 178 | graphs reused = 1 1.04.463.956 I slot print_timing: id 3 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.463.970 I slot release: id 3 | task 178 | stop processing: n_tokens = 170, truncated = 0 1.04.467.927 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.263 1.04.468.102 I slot launch_slot_: id 2 | task 184 | processing task, is_child = 0 1.04.469.259 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.201 1.04.469.294 I slot launch_slot_: id 0 | task 182 | processing task, is_child = 0 1.04.469.330 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.186 1.04.469.361 I slot launch_slot_: id 1 | task 183 | processing task, is_child = 0 1.04.469.380 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.171 1.04.469.411 I slot launch_slot_: id 3 | task 185 | processing task, is_child = 0 1.05.689.823 I slot print_timing: id 0 | task 182 | prompt eval time = 1173.66 ms / 111 tokens ( 10.57 ms per token, 94.58 tokens per second) 1.05.689.825 I slot print_timing: id 0 | task 182 | eval time = 46.74 ms / 2 tokens ( 46.74 ms per token, 21.40 tokens per second) 1.05.689.825 I slot print_timing: id 0 | task 182 | total time = 1220.40 ms / 113 tokens 1.05.689.826 I slot print_timing: id 0 | task 182 | graphs reused = 1 1.05.689.826 I slot print_timing: id 0 | task 182 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.689.844 I slot release: id 0 | task 182 | stop processing: n_tokens = 112, truncated = 0 1.05.690.116 I slot print_timing: id 1 | task 183 | prompt eval time = 1173.92 ms / 150 tokens ( 7.83 ms per token, 127.78 tokens per second) 1.05.690.118 I slot print_timing: id 1 | task 183 | eval time = 46.76 ms / 2 tokens ( 46.76 ms per token, 21.38 tokens per second) 1.05.690.119 I slot print_timing: id 1 | task 183 | total time = 1220.69 ms / 152 tokens 1.05.690.119 I slot print_timing: id 1 | task 183 | graphs reused = 1 1.05.690.119 I slot print_timing: id 1 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.690.136 I slot release: id 1 | task 183 | stop processing: n_tokens = 151, truncated = 0 1.05.690.408 I slot print_timing: id 2 | task 184 | prompt eval time = 1174.18 ms / 113 tokens ( 10.39 ms per token, 96.24 tokens per second) 1.05.690.410 I slot print_timing: id 2 | task 184 | eval time = 46.78 ms / 2 tokens ( 46.78 ms per token, 21.37 tokens per second) 1.05.690.410 I slot print_timing: id 2 | task 184 | total time = 1220.97 ms / 115 tokens 1.05.690.411 I slot print_timing: id 2 | task 184 | graphs reused = 1 1.05.690.411 I slot print_timing: id 2 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.690.421 I slot release: id 2 | task 184 | stop processing: n_tokens = 114, truncated = 0 1.05.690.704 I slot print_timing: id 3 | task 185 | prompt eval time = 1174.46 ms / 138 tokens ( 8.51 ms per token, 117.50 tokens per second) 1.05.690.708 I slot print_timing: id 3 | task 185 | eval time = 46.79 ms / 2 tokens ( 46.79 ms per token, 21.37 tokens per second) 1.05.690.708 I slot print_timing: id 3 | task 185 | total time = 1221.25 ms / 140 tokens 1.05.690.709 I slot print_timing: id 3 | task 185 | graphs reused = 1 1.05.690.709 I slot print_timing: id 3 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.690.725 I slot release: id 3 | task 185 | stop processing: n_tokens = 139, truncated = 0 1.05.694.879 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 1.05.695.160 I slot launch_slot_: id 0 | task 189 | processing task, is_child = 0 1.05.696.270 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.263 (> 0.100 thold), f_keep = 0.263 1.05.696.306 I slot launch_slot_: id 2 | task 190 | processing task, is_child = 0 1.05.696.342 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 1.05.696.512 I slot launch_slot_: id 1 | task 191 | processing task, is_child = 0 1.05.696.532 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.209 1.05.696.563 I slot launch_slot_: id 3 | task 192 | processing task, is_child = 0 1.06.940.228 I slot print_timing: id 0 | task 189 | prompt eval time = 1196.59 ms / 153 tokens ( 7.82 ms per token, 127.86 tokens per second) 1.06.940.230 I slot print_timing: id 0 | task 189 | eval time = 47.07 ms / 2 tokens ( 47.07 ms per token, 21.24 tokens per second) 1.06.940.231 I slot print_timing: id 0 | task 189 | total time = 1243.66 ms / 155 tokens 1.06.940.231 I slot print_timing: id 0 | task 189 | graphs reused = 1 1.06.940.232 I slot print_timing: id 0 | task 189 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.940.253 I slot release: id 0 | task 189 | stop processing: n_tokens = 154, truncated = 0 1.06.940.518 I slot print_timing: id 1 | task 191 | prompt eval time = 1196.84 ms / 131 tokens ( 9.14 ms per token, 109.45 tokens per second) 1.06.940.520 I slot print_timing: id 1 | task 191 | eval time = 47.10 ms / 2 tokens ( 47.10 ms per token, 21.23 tokens per second) 1.06.940.521 I slot print_timing: id 1 | task 191 | total time = 1243.94 ms / 133 tokens 1.06.940.521 I slot print_timing: id 1 | task 191 | graphs reused = 1 1.06.940.521 I slot print_timing: id 1 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.940.534 I slot release: id 1 | task 191 | stop processing: n_tokens = 132, truncated = 0 1.06.940.813 I slot print_timing: id 2 | task 190 | prompt eval time = 1197.16 ms / 114 tokens ( 10.50 ms per token, 95.23 tokens per second) 1.06.940.814 I slot print_timing: id 2 | task 190 | eval time = 47.06 ms / 2 tokens ( 47.06 ms per token, 21.25 tokens per second) 1.06.940.815 I slot print_timing: id 2 | task 190 | total time = 1244.22 ms / 116 tokens 1.06.940.816 I slot print_timing: id 2 | task 190 | graphs reused = 1 1.06.940.816 I slot print_timing: id 2 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.940.825 I slot release: id 2 | task 190 | stop processing: n_tokens = 115, truncated = 0 1.06.941.102 I slot print_timing: id 3 | task 192 | prompt eval time = 1197.44 ms / 126 tokens ( 9.50 ms per token, 105.22 tokens per second) 1.06.941.110 I slot print_timing: id 3 | task 192 | eval time = 47.07 ms / 2 tokens ( 47.07 ms per token, 21.25 tokens per second) 1.06.941.110 I slot print_timing: id 3 | task 192 | total time = 1244.50 ms / 128 tokens 1.06.941.111 I slot print_timing: id 3 | task 192 | graphs reused = 1 1.06.941.111 I slot print_timing: id 3 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.941.120 I slot release: id 3 | task 192 | stop processing: n_tokens = 127, truncated = 0 1.06.945.446 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 1.06.945.859 I slot launch_slot_: id 0 | task 196 | processing task, is_child = 0 1.06.946.777 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.261 1.06.946.813 I slot launch_slot_: id 2 | task 197 | processing task, is_child = 0 1.06.946.848 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.227 1.06.946.880 I slot launch_slot_: id 1 | task 198 | processing task, is_child = 0 1.06.946.899 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.228 1.06.946.932 I slot launch_slot_: id 3 | task 199 | processing task, is_child = 0 1.08.345.326 I slot print_timing: id 0 | task 196 | prompt eval time = 1351.30 ms / 157 tokens ( 8.61 ms per token, 116.18 tokens per second) 1.08.345.328 I slot print_timing: id 0 | task 196 | eval time = 47.09 ms / 2 tokens ( 47.09 ms per token, 21.24 tokens per second) 1.08.345.329 I slot print_timing: id 0 | task 196 | total time = 1398.39 ms / 159 tokens 1.08.345.329 I slot print_timing: id 0 | task 196 | graphs reused = 1 1.08.345.330 I slot print_timing: id 0 | task 196 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.345.349 I slot release: id 0 | task 196 | stop processing: n_tokens = 158, truncated = 0 1.08.345.612 I slot print_timing: id 1 | task 198 | prompt eval time = 1351.55 ms / 130 tokens ( 10.40 ms per token, 96.19 tokens per second) 1.08.345.614 I slot print_timing: id 1 | task 198 | eval time = 47.11 ms / 2 tokens ( 47.11 ms per token, 21.23 tokens per second) 1.08.345.614 I slot print_timing: id 1 | task 198 | total time = 1398.66 ms / 132 tokens 1.08.345.615 I slot print_timing: id 1 | task 198 | graphs reused = 1 1.08.345.615 I slot print_timing: id 1 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.345.627 I slot release: id 1 | task 198 | stop processing: n_tokens = 131, truncated = 0 1.08.345.916 I slot print_timing: id 2 | task 197 | prompt eval time = 1351.84 ms / 119 tokens ( 11.36 ms per token, 88.03 tokens per second) 1.08.345.919 I slot print_timing: id 2 | task 197 | eval time = 47.11 ms / 2 tokens ( 47.11 ms per token, 21.23 tokens per second) 1.08.345.919 I slot print_timing: id 2 | task 197 | total time = 1398.95 ms / 121 tokens 1.08.345.920 I slot print_timing: id 2 | task 197 | graphs reused = 1 1.08.345.920 I slot print_timing: id 2 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.345.932 I slot release: id 2 | task 197 | stop processing: n_tokens = 120, truncated = 0 1.08.346.260 I slot print_timing: id 3 | task 199 | prompt eval time = 1352.18 ms / 170 tokens ( 7.95 ms per token, 125.72 tokens per second) 1.08.346.265 I slot print_timing: id 3 | task 199 | eval time = 47.11 ms / 2 tokens ( 47.11 ms per token, 21.23 tokens per second) 1.08.346.265 I slot print_timing: id 3 | task 199 | total time = 1399.28 ms / 172 tokens 1.08.346.266 I slot print_timing: id 3 | task 199 | graphs reused = 1 1.08.346.266 I slot print_timing: id 3 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.346.280 I slot release: id 3 | task 199 | stop processing: n_tokens = 171, truncated = 0 1.08.350.498 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 1.08.350.985 I slot launch_slot_: id 0 | task 203 | processing task, is_child = 0 1.08.352.150 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.221 1.08.352.187 I slot launch_slot_: id 1 | task 204 | processing task, is_child = 0 1.08.352.223 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.159 (> 0.100 thold), f_keep = 0.242 1.08.352.256 I slot launch_slot_: id 2 | task 205 | processing task, is_child = 0 1.08.352.277 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.170 1.08.352.441 I slot launch_slot_: id 3 | task 206 | processing task, is_child = 0 1.09.794.532 I slot print_timing: id 0 | task 203 | prompt eval time = 1394.97 ms / 110 tokens ( 12.68 ms per token, 78.85 tokens per second) 1.09.794.534 I slot print_timing: id 0 | task 203 | eval time = 47.11 ms / 2 tokens ( 47.11 ms per token, 21.23 tokens per second) 1.09.794.534 I slot print_timing: id 0 | task 203 | total time = 1442.08 ms / 112 tokens 1.09.794.535 I slot print_timing: id 0 | task 203 | graphs reused = 1 1.09.794.535 I slot print_timing: id 0 | task 203 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.794.554 I slot release: id 0 | task 203 | stop processing: n_tokens = 111, truncated = 0 1.09.794.844 I slot print_timing: id 1 | task 204 | prompt eval time = 1395.26 ms / 155 tokens ( 9.00 ms per token, 111.09 tokens per second) 1.09.794.847 I slot print_timing: id 1 | task 204 | eval time = 47.12 ms / 2 tokens ( 47.12 ms per token, 21.22 tokens per second) 1.09.794.847 I slot print_timing: id 1 | task 204 | total time = 1442.38 ms / 157 tokens 1.09.794.847 I slot print_timing: id 1 | task 204 | graphs reused = 1 1.09.794.848 I slot print_timing: id 1 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.794.866 I slot release: id 1 | task 204 | stop processing: n_tokens = 156, truncated = 0 1.09.795.165 I slot print_timing: id 2 | task 205 | prompt eval time = 1395.54 ms / 182 tokens ( 7.67 ms per token, 130.42 tokens per second) 1.09.795.169 I slot print_timing: id 2 | task 205 | eval time = 47.15 ms / 2 tokens ( 47.15 ms per token, 21.21 tokens per second) 1.09.795.169 I slot print_timing: id 2 | task 205 | total time = 1442.69 ms / 184 tokens 1.09.795.170 I slot print_timing: id 2 | task 205 | graphs reused = 1 1.09.795.170 I slot print_timing: id 2 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.795.198 I slot release: id 2 | task 205 | stop processing: n_tokens = 183, truncated = 0 1.09.795.489 I slot print_timing: id 3 | task 206 | prompt eval time = 1395.83 ms / 135 tokens ( 10.34 ms per token, 96.72 tokens per second) 1.09.795.491 I slot print_timing: id 3 | task 206 | eval time = 47.18 ms / 2 tokens ( 47.18 ms per token, 21.20 tokens per second) 1.09.795.491 I slot print_timing: id 3 | task 206 | total time = 1443.01 ms / 137 tokens 1.09.795.492 I slot print_timing: id 3 | task 206 | graphs reused = 1 1.09.795.492 I slot print_timing: id 3 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.795.511 I slot release: id 3 | task 206 | stop processing: n_tokens = 136, truncated = 0 1.09.800.802 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.261 1.09.801.036 I slot launch_slot_: id 0 | task 210 | processing task, is_child = 0 1.09.802.300 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.186 1.09.802.478 I slot launch_slot_: id 1 | task 211 | processing task, is_child = 0 1.09.802.516 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.158 1.09.802.549 I slot launch_slot_: id 2 | task 212 | processing task, is_child = 0 1.09.802.568 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.213 1.09.802.600 I slot launch_slot_: id 3 | task 213 | processing task, is_child = 0 1.11.137.943 I slot print_timing: id 0 | task 210 | prompt eval time = 1288.19 ms / 136 tokens ( 9.47 ms per token, 105.57 tokens per second) 1.11.137.945 I slot print_timing: id 0 | task 210 | eval time = 47.15 ms / 2 tokens ( 47.15 ms per token, 21.21 tokens per second) 1.11.137.946 I slot print_timing: id 0 | task 210 | total time = 1335.34 ms / 138 tokens 1.11.137.946 I slot print_timing: id 0 | task 210 | graphs reused = 1 1.11.137.946 I slot print_timing: id 0 | task 210 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.137.968 I slot release: id 0 | task 210 | stop processing: n_tokens = 137, truncated = 0 1.11.138.252 I slot print_timing: id 1 | task 211 | prompt eval time = 1288.47 ms / 117 tokens ( 11.01 ms per token, 90.81 tokens per second) 1.11.138.254 I slot print_timing: id 1 | task 211 | eval time = 47.17 ms / 2 tokens ( 47.17 ms per token, 21.20 tokens per second) 1.11.138.254 I slot print_timing: id 1 | task 211 | total time = 1335.64 ms / 119 tokens 1.11.138.254 I slot print_timing: id 1 | task 211 | graphs reused = 1 1.11.138.255 I slot print_timing: id 1 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.138.271 I slot release: id 1 | task 211 | stop processing: n_tokens = 118, truncated = 0 1.11.138.544 I slot print_timing: id 2 | task 212 | prompt eval time = 1288.73 ms / 160 tokens ( 8.05 ms per token, 124.15 tokens per second) 1.11.138.546 I slot print_timing: id 2 | task 212 | eval time = 47.19 ms / 2 tokens ( 47.19 ms per token, 21.19 tokens per second) 1.11.138.546 I slot print_timing: id 2 | task 212 | total time = 1335.92 ms / 162 tokens 1.11.138.547 I slot print_timing: id 2 | task 212 | graphs reused = 1 1.11.138.547 I slot print_timing: id 2 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.138.560 I slot release: id 2 | task 212 | stop processing: n_tokens = 161, truncated = 0 1.11.138.944 I slot print_timing: id 3 | task 213 | prompt eval time = 1289.10 ms / 134 tokens ( 9.62 ms per token, 103.95 tokens per second) 1.11.138.947 I slot print_timing: id 3 | task 213 | eval time = 47.20 ms / 2 tokens ( 47.20 ms per token, 21.19 tokens per second) 1.11.138.947 I slot print_timing: id 3 | task 213 | total time = 1336.30 ms / 136 tokens 1.11.138.947 I slot print_timing: id 3 | task 213 | graphs reused = 1 1.11.138.948 I slot print_timing: id 3 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.138.963 I slot release: id 3 | task 213 | stop processing: n_tokens = 135, truncated = 0 1.11.143.238 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.254 1.11.143.618 I slot launch_slot_: id 1 | task 217 | processing task, is_child = 0 1.11.144.826 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.212 1.11.144.870 I slot launch_slot_: id 0 | task 218 | processing task, is_child = 0 1.11.144.906 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.180 1.11.145.049 I slot launch_slot_: id 2 | task 219 | processing task, is_child = 0 1.11.145.068 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.215 1.11.145.103 I slot launch_slot_: id 3 | task 220 | processing task, is_child = 0 1.12.439.316 I slot print_timing: id 1 | task 217 | prompt eval time = 1247.32 ms / 124 tokens ( 10.06 ms per token, 99.41 tokens per second) 1.12.439.320 I slot print_timing: id 1 | task 217 | eval time = 46.88 ms / 2 tokens ( 46.88 ms per token, 21.33 tokens per second) 1.12.439.321 I slot print_timing: id 1 | task 217 | total time = 1294.19 ms / 126 tokens 1.12.439.321 I slot print_timing: id 1 | task 217 | graphs reused = 1 1.12.439.321 I slot print_timing: id 1 | task 217 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.439.339 I slot release: id 1 | task 217 | stop processing: n_tokens = 125, truncated = 0 1.12.439.631 I slot print_timing: id 2 | task 219 | prompt eval time = 1247.62 ms / 118 tokens ( 10.57 ms per token, 94.58 tokens per second) 1.12.439.633 I slot print_timing: id 2 | task 219 | eval time = 46.89 ms / 2 tokens ( 46.89 ms per token, 21.33 tokens per second) 1.12.439.634 I slot print_timing: id 2 | task 219 | total time = 1294.50 ms / 120 tokens 1.12.439.634 I slot print_timing: id 2 | task 219 | graphs reused = 1 1.12.439.634 I slot print_timing: id 2 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.439.653 I slot release: id 2 | task 219 | stop processing: n_tokens = 119, truncated = 0 1.12.439.946 I slot print_timing: id 3 | task 220 | prompt eval time = 1247.93 ms / 156 tokens ( 8.00 ms per token, 125.01 tokens per second) 1.12.439.948 I slot print_timing: id 3 | task 220 | eval time = 46.87 ms / 2 tokens ( 46.87 ms per token, 21.34 tokens per second) 1.12.439.948 I slot print_timing: id 3 | task 220 | total time = 1294.81 ms / 158 tokens 1.12.439.948 I slot print_timing: id 3 | task 220 | graphs reused = 1 1.12.439.948 I slot print_timing: id 3 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.439.971 I slot release: id 3 | task 220 | stop processing: n_tokens = 157, truncated = 0 1.12.458.410 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.232 1.12.458.808 I slot launch_slot_: id 1 | task 225 | processing task, is_child = 0 1.12.459.401 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.244 1.12.459.451 I slot launch_slot_: id 2 | task 226 | processing task, is_child = 0 1.12.459.473 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.185 1.12.459.516 I slot launch_slot_: id 3 | task 227 | processing task, is_child = 0 1.13.424.758 I slot print_timing: id 1 | task 225 | prompt eval time = 917.82 ms / 149 tokens ( 6.16 ms per token, 162.34 tokens per second) 1.13.424.760 I slot print_timing: id 1 | task 225 | eval time = 47.41 ms / 2 tokens ( 47.41 ms per token, 21.09 tokens per second) 1.13.424.761 I slot print_timing: id 1 | task 225 | total time = 965.23 ms / 151 tokens 1.13.424.762 I slot print_timing: id 1 | task 225 | graphs reused = 1 1.13.424.762 I slot print_timing: id 1 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.424.783 I slot release: id 1 | task 225 | stop processing: n_tokens = 150, truncated = 0 1.13.425.050 I slot print_timing: id 2 | task 226 | prompt eval time = 918.18 ms / 162 tokens ( 5.67 ms per token, 176.44 tokens per second) 1.13.425.052 I slot print_timing: id 2 | task 226 | eval time = 47.33 ms / 2 tokens ( 47.33 ms per token, 21.13 tokens per second) 1.13.425.052 I slot print_timing: id 2 | task 226 | total time = 965.51 ms / 164 tokens 1.13.425.053 I slot print_timing: id 2 | task 226 | graphs reused = 1 1.13.425.053 I slot print_timing: id 2 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.425.068 I slot release: id 2 | task 226 | stop processing: n_tokens = 163, truncated = 0 1.13.425.338 I slot print_timing: id 3 | task 227 | prompt eval time = 918.68 ms / 154 tokens ( 5.97 ms per token, 167.63 tokens per second) 1.13.425.340 I slot print_timing: id 3 | task 227 | eval time = 47.10 ms / 2 tokens ( 47.10 ms per token, 21.23 tokens per second) 1.13.425.344 I slot print_timing: id 3 | task 227 | total time = 965.78 ms / 156 tokens 1.13.425.344 I slot print_timing: id 3 | task 227 | graphs reused = 1 1.13.425.344 I slot print_timing: id 3 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.425.362 I slot release: id 3 | task 227 | stop processing: n_tokens = 155, truncated = 0 1.13.443.684 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.193 1.13.444.155 I slot launch_slot_: id 1 | task 232 | processing task, is_child = 0 1.13.445.081 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.178 1.13.445.126 I slot launch_slot_: id 2 | task 233 | processing task, is_child = 0 1.13.445.148 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.187 1.13.445.186 I slot launch_slot_: id 3 | task 234 | processing task, is_child = 0 1.14.275.408 I slot print_timing: id 0 | task 218 | prompt eval time = 1247.05 ms / 151 tokens ( 8.26 ms per token, 121.09 tokens per second) 1.14.275.410 I slot print_timing: id 0 | task 218 | eval time = 1883.24 ms / 8 tokens ( 269.03 ms per token, 3.72 tokens per second) 1.14.275.415 I slot print_timing: id 0 | task 218 | total time = 3130.30 ms / 159 tokens 1.14.275.416 I slot print_timing: id 0 | task 218 | graphs reused = 1 1.14.275.416 I slot print_timing: id 0 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.275.439 I slot release: id 0 | task 218 | stop processing: n_tokens = 158, truncated = 0 1.14.378.117 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.184 1.14.378.892 I slot launch_slot_: id 0 | task 237 | processing task, is_child = 0 1.14.759.042 I slot print_timing: id 1 | task 232 | prompt eval time = 932.15 ms / 156 tokens ( 5.98 ms per token, 167.36 tokens per second) 1.14.759.043 I slot print_timing: id 1 | task 232 | eval time = 381.70 ms / 2 tokens ( 381.70 ms per token, 2.62 tokens per second) 1.14.759.044 I slot print_timing: id 1 | task 232 | total time = 1313.84 ms / 158 tokens 1.14.759.044 I slot print_timing: id 1 | task 232 | graphs reused = 1 1.14.759.045 I slot print_timing: id 1 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.759.068 I slot release: id 1 | task 232 | stop processing: n_tokens = 157, truncated = 0 1.14.759.354 I slot print_timing: id 2 | task 233 | prompt eval time = 932.41 ms / 115 tokens ( 8.11 ms per token, 123.34 tokens per second) 1.14.759.356 I slot print_timing: id 2 | task 233 | eval time = 381.74 ms / 2 tokens ( 381.74 ms per token, 2.62 tokens per second) 1.14.759.356 I slot print_timing: id 2 | task 233 | total time = 1314.14 ms / 117 tokens 1.14.759.357 I slot print_timing: id 2 | task 233 | graphs reused = 1 1.14.759.357 I slot print_timing: id 2 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.759.375 I slot release: id 2 | task 233 | stop processing: n_tokens = 116, truncated = 0 1.14.759.757 I slot print_timing: id 3 | task 234 | prompt eval time = 932.88 ms / 108 tokens ( 8.64 ms per token, 115.77 tokens per second) 1.14.759.759 I slot print_timing: id 3 | task 234 | eval time = 381.65 ms / 2 tokens ( 381.65 ms per token, 2.62 tokens per second) 1.14.759.759 I slot print_timing: id 3 | task 234 | total time = 1314.53 ms / 110 tokens 1.14.759.759 I slot print_timing: id 3 | task 234 | graphs reused = 1 1.14.759.760 I slot print_timing: id 3 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.759.780 I slot release: id 3 | task 234 | stop processing: n_tokens = 109, truncated = 0 1.14.802.090 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.185 1.14.802.547 I slot launch_slot_: id 1 | task 240 | processing task, is_child = 0 1.14.802.944 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.250 1.14.803.117 I slot launch_slot_: id 2 | task 241 | processing task, is_child = 0 1.14.803.139 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.266 1.14.803.285 I slot launch_slot_: id 3 | task 242 | processing task, is_child = 0 1.15.543.325 I slot print_timing: id 0 | task 237 | prompt eval time = 423.19 ms / 186 tokens ( 2.28 ms per token, 439.52 tokens per second) 1.15.543.327 I slot print_timing: id 0 | task 237 | eval time = 741.23 ms / 2 tokens ( 741.23 ms per token, 1.35 tokens per second) 1.15.543.327 I slot print_timing: id 0 | task 237 | total time = 1164.42 ms / 188 tokens 1.15.543.328 I slot print_timing: id 0 | task 237 | graphs reused = 1 1.15.543.328 I slot print_timing: id 0 | task 237 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.543.354 I slot release: id 0 | task 237 | stop processing: n_tokens = 187, truncated = 0 1.15.646.138 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.155 1.15.646.966 I slot launch_slot_: id 0 | task 245 | processing task, is_child = 0 1.15.974.837 I slot print_timing: id 1 | task 240 | prompt eval time = 842.12 ms / 122 tokens ( 6.90 ms per token, 144.87 tokens per second) 1.15.974.842 I slot print_timing: id 1 | task 240 | eval time = 329.42 ms / 2 tokens ( 329.42 ms per token, 3.04 tokens per second) 1.15.974.843 I slot print_timing: id 1 | task 240 | total time = 1171.54 ms / 124 tokens 1.15.974.843 I slot print_timing: id 1 | task 240 | graphs reused = 1 1.15.974.843 I slot print_timing: id 1 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.974.861 I slot release: id 1 | task 240 | stop processing: n_tokens = 123, truncated = 0 1.15.975.151 I slot print_timing: id 2 | task 241 | prompt eval time = 842.40 ms / 113 tokens ( 7.45 ms per token, 134.14 tokens per second) 1.15.975.153 I slot print_timing: id 2 | task 241 | eval time = 329.44 ms / 2 tokens ( 329.44 ms per token, 3.04 tokens per second) 1.15.975.153 I slot print_timing: id 2 | task 241 | total time = 1171.84 ms / 115 tokens 1.15.975.154 I slot print_timing: id 2 | task 241 | graphs reused = 1 1.15.975.154 I slot print_timing: id 2 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.975.165 I slot release: id 2 | task 241 | stop processing: n_tokens = 114, truncated = 0 1.15.975.470 I slot print_timing: id 3 | task 242 | prompt eval time = 842.81 ms / 103 tokens ( 8.18 ms per token, 122.21 tokens per second) 1.15.975.473 I slot print_timing: id 3 | task 242 | eval time = 329.33 ms / 2 tokens ( 329.33 ms per token, 3.04 tokens per second) 1.15.975.479 I slot print_timing: id 3 | task 242 | total time = 1172.15 ms / 105 tokens 1.15.975.479 I slot print_timing: id 3 | task 242 | graphs reused = 1 1.15.975.479 I slot print_timing: id 3 | task 242 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.975.494 I slot release: id 3 | task 242 | stop processing: n_tokens = 104, truncated = 0 1.16.017.133 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.236 1.16.017.326 I slot launch_slot_: id 1 | task 248 | processing task, is_child = 0 1.16.017.804 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.254 1.16.017.842 I slot launch_slot_: id 2 | task 249 | processing task, is_child = 0 1.16.017.863 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.288 1.16.017.899 I slot launch_slot_: id 3 | task 250 | processing task, is_child = 0 1.16.876.929 I slot print_timing: id 0 | task 245 | prompt eval time = 370.15 ms / 128 tokens ( 2.89 ms per token, 345.80 tokens per second) 1.16.876.931 I slot print_timing: id 0 | task 245 | eval time = 859.79 ms / 2 tokens ( 859.79 ms per token, 1.16 tokens per second) 1.16.876.932 I slot print_timing: id 0 | task 245 | total time = 1229.95 ms / 130 tokens 1.16.876.932 I slot print_timing: id 0 | task 245 | graphs reused = 1 1.16.876.933 I slot print_timing: id 0 | task 245 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.876.954 I slot release: id 0 | task 245 | stop processing: n_tokens = 129, truncated = 0 1.16.979.622 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.225 1.16.980.541 I slot launch_slot_: id 0 | task 253 | processing task, is_child = 0 1.17.320.102 I slot print_timing: id 1 | task 248 | prompt eval time = 961.11 ms / 163 tokens ( 5.90 ms per token, 169.60 tokens per second) 1.17.320.107 I slot print_timing: id 1 | task 248 | eval time = 341.09 ms / 2 tokens ( 341.09 ms per token, 2.93 tokens per second) 1.17.320.108 I slot print_timing: id 1 | task 248 | total time = 1302.20 ms / 165 tokens 1.17.320.108 I slot print_timing: id 1 | task 248 | graphs reused = 1 1.17.320.109 I slot print_timing: id 1 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.320.128 I slot release: id 1 | task 248 | stop processing: n_tokens = 164, truncated = 0 1.17.320.435 I slot print_timing: id 2 | task 249 | prompt eval time = 961.37 ms / 127 tokens ( 7.57 ms per token, 132.10 tokens per second) 1.17.320.437 I slot print_timing: id 2 | task 249 | eval time = 341.13 ms / 2 tokens ( 341.13 ms per token, 2.93 tokens per second) 1.17.320.437 I slot print_timing: id 2 | task 249 | total time = 1302.50 ms / 129 tokens 1.17.320.437 I slot print_timing: id 2 | task 249 | graphs reused = 1 1.17.320.437 I slot print_timing: id 2 | task 249 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.320.449 I slot release: id 2 | task 249 | stop processing: n_tokens = 128, truncated = 0 1.17.320.738 I slot print_timing: id 3 | task 250 | prompt eval time = 961.67 ms / 139 tokens ( 6.92 ms per token, 144.54 tokens per second) 1.17.320.745 I slot print_timing: id 3 | task 250 | eval time = 341.12 ms / 2 tokens ( 341.12 ms per token, 2.93 tokens per second) 1.17.320.745 I slot print_timing: id 3 | task 250 | total time = 1302.79 ms / 141 tokens 1.17.320.745 I slot print_timing: id 3 | task 250 | graphs reused = 1 1.17.320.746 I slot print_timing: id 3 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.320.767 I slot release: id 3 | task 250 | stop processing: n_tokens = 140, truncated = 0 1.17.362.648 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 1.17.363.115 I slot launch_slot_: id 1 | task 256 | processing task, is_child = 0 1.17.363.853 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.227 1.17.363.894 I slot launch_slot_: id 2 | task 257 | processing task, is_child = 0 1.17.363.916 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.207 1.17.364.112 I slot launch_slot_: id 3 | task 258 | processing task, is_child = 0 1.18.251.163 I slot print_timing: id 0 | task 253 | prompt eval time = 382.10 ms / 136 tokens ( 2.81 ms per token, 355.93 tokens per second) 1.18.251.165 I slot print_timing: id 0 | task 253 | eval time = 888.51 ms / 2 tokens ( 888.51 ms per token, 1.13 tokens per second) 1.18.251.165 I slot print_timing: id 0 | task 253 | total time = 1270.61 ms / 138 tokens 1.18.251.166 I slot print_timing: id 0 | task 253 | graphs reused = 1 1.18.251.166 I slot print_timing: id 0 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.251.187 I slot release: id 0 | task 253 | stop processing: n_tokens = 137, truncated = 0 1.18.353.779 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.212 1.18.354.434 I slot launch_slot_: id 0 | task 261 | processing task, is_child = 0 1.18.724.537 I slot print_timing: id 1 | task 256 | prompt eval time = 988.97 ms / 121 tokens ( 8.17 ms per token, 122.35 tokens per second) 1.18.724.539 I slot print_timing: id 1 | task 256 | eval time = 371.44 ms / 2 tokens ( 371.44 ms per token, 2.69 tokens per second) 1.18.724.540 I slot print_timing: id 1 | task 256 | total time = 1360.41 ms / 123 tokens 1.18.724.540 I slot print_timing: id 1 | task 256 | graphs reused = 1 1.18.724.541 I slot print_timing: id 1 | task 256 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.724.559 I slot release: id 1 | task 256 | stop processing: n_tokens = 122, truncated = 0 1.18.724.834 I slot print_timing: id 2 | task 257 | prompt eval time = 989.24 ms / 142 tokens ( 6.97 ms per token, 143.55 tokens per second) 1.18.724.838 I slot print_timing: id 2 | task 257 | eval time = 371.46 ms / 2 tokens ( 371.46 ms per token, 2.69 tokens per second) 1.18.724.838 I slot print_timing: id 2 | task 257 | total time = 1360.70 ms / 144 tokens 1.18.724.838 I slot print_timing: id 2 | task 257 | graphs reused = 1 1.18.724.839 I slot print_timing: id 2 | task 257 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.724.853 I slot release: id 2 | task 257 | stop processing: n_tokens = 143, truncated = 0 1.18.725.166 I slot print_timing: id 3 | task 258 | prompt eval time = 989.63 ms / 159 tokens ( 6.22 ms per token, 160.67 tokens per second) 1.18.725.168 I slot print_timing: id 3 | task 258 | eval time = 371.39 ms / 2 tokens ( 371.39 ms per token, 2.69 tokens per second) 1.18.725.169 I slot print_timing: id 3 | task 258 | total time = 1361.02 ms / 161 tokens 1.18.725.169 I slot print_timing: id 3 | task 258 | graphs reused = 1 1.18.725.169 I slot print_timing: id 3 | task 258 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.725.182 I slot release: id 3 | task 258 | stop processing: n_tokens = 160, truncated = 0 1.18.767.105 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.238 1.18.767.300 I slot launch_slot_: id 1 | task 264 | processing task, is_child = 0 1.18.768.117 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.203 1.18.768.162 I slot launch_slot_: id 2 | task 265 | processing task, is_child = 0 1.18.768.184 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.181 1.18.768.230 I slot launch_slot_: id 3 | task 266 | processing task, is_child = 0 1.19.754.909 I slot print_timing: id 0 | task 261 | prompt eval time = 412.66 ms / 170 tokens ( 2.43 ms per token, 411.96 tokens per second) 1.19.754.915 I slot print_timing: id 0 | task 261 | eval time = 987.80 ms / 2 tokens ( 987.80 ms per token, 1.01 tokens per second) 1.19.754.916 I slot print_timing: id 0 | task 261 | total time = 1400.46 ms / 172 tokens 1.19.754.916 I slot print_timing: id 0 | task 261 | graphs reused = 1 1.19.754.916 I slot print_timing: id 0 | task 261 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.754.941 I slot release: id 0 | task 261 | stop processing: n_tokens = 171, truncated = 0 1.19.857.647 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.170 1.19.858.416 I slot launch_slot_: id 0 | task 269 | processing task, is_child = 0 1.20.169.811 I slot print_timing: id 1 | task 264 | prompt eval time = 1088.73 ms / 158 tokens ( 6.89 ms per token, 145.12 tokens per second) 1.20.169.816 I slot print_timing: id 1 | task 264 | eval time = 312.84 ms / 2 tokens ( 312.84 ms per token, 3.20 tokens per second) 1.20.169.817 I slot print_timing: id 1 | task 264 | total time = 1401.58 ms / 160 tokens 1.20.169.817 I slot print_timing: id 1 | task 264 | graphs reused = 1 1.20.169.818 I slot print_timing: id 1 | task 264 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.169.841 I slot release: id 1 | task 264 | stop processing: n_tokens = 159, truncated = 0 1.20.170.099 I slot print_timing: id 2 | task 265 | prompt eval time = 1088.98 ms / 120 tokens ( 9.07 ms per token, 110.20 tokens per second) 1.20.170.103 I slot print_timing: id 2 | task 265 | eval time = 312.87 ms / 2 tokens ( 312.87 ms per token, 3.20 tokens per second) 1.20.170.104 I slot print_timing: id 2 | task 265 | total time = 1401.84 ms / 122 tokens 1.20.170.104 I slot print_timing: id 2 | task 265 | graphs reused = 1 1.20.170.104 I slot print_timing: id 2 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.170.116 I slot release: id 2 | task 265 | stop processing: n_tokens = 121, truncated = 0 1.20.170.402 I slot print_timing: id 3 | task 266 | prompt eval time = 1089.38 ms / 184 tokens ( 5.92 ms per token, 168.90 tokens per second) 1.20.170.404 I slot print_timing: id 3 | task 266 | eval time = 312.76 ms / 2 tokens ( 312.76 ms per token, 3.20 tokens per second) 1.20.170.405 I slot print_timing: id 3 | task 266 | total time = 1402.13 ms / 186 tokens 1.20.170.405 I slot print_timing: id 3 | task 266 | graphs reused = 1 1.20.170.405 I slot print_timing: id 3 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.170.426 I slot release: id 3 | task 266 | stop processing: n_tokens = 185, truncated = 0 1.20.212.290 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.182 1.20.212.827 I slot launch_slot_: id 1 | task 272 | processing task, is_child = 0 1.20.213.668 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.240 1.20.213.704 I slot launch_slot_: id 2 | task 273 | processing task, is_child = 0 1.20.213.732 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.157 1.20.213.773 I slot launch_slot_: id 3 | task 274 | processing task, is_child = 0 1.21.004.811 I slot print_timing: id 0 | task 269 | prompt eval time = 353.87 ms / 103 tokens ( 3.44 ms per token, 291.07 tokens per second) 1.21.004.813 I slot print_timing: id 0 | task 269 | eval time = 792.52 ms / 2 tokens ( 792.52 ms per token, 1.26 tokens per second) 1.21.004.814 I slot print_timing: id 0 | task 269 | total time = 1146.38 ms / 105 tokens 1.21.004.815 I slot print_timing: id 0 | task 269 | graphs reused = 1 1.21.004.815 I slot print_timing: id 0 | task 269 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.004.832 I slot release: id 0 | task 269 | stop processing: n_tokens = 104, truncated = 0 1.21.144.401 I slot print_timing: id 1 | task 272 | prompt eval time = 892.86 ms / 134 tokens ( 6.66 ms per token, 150.08 tokens per second) 1.21.144.406 I slot print_timing: id 1 | task 272 | eval time = 37.76 ms / 2 tokens ( 37.76 ms per token, 26.48 tokens per second) 1.21.144.406 I slot print_timing: id 1 | task 272 | total time = 930.62 ms / 136 tokens 1.21.144.406 I slot print_timing: id 1 | task 272 | graphs reused = 1 1.21.144.407 I slot print_timing: id 1 | task 272 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.144.425 I slot release: id 1 | task 272 | stop processing: n_tokens = 135, truncated = 0 1.21.144.711 I slot print_timing: id 2 | task 273 | prompt eval time = 893.14 ms / 145 tokens ( 6.16 ms per token, 162.35 tokens per second) 1.21.144.714 I slot print_timing: id 2 | task 273 | eval time = 37.77 ms / 2 tokens ( 37.77 ms per token, 26.47 tokens per second) 1.21.144.714 I slot print_timing: id 2 | task 273 | total time = 930.92 ms / 147 tokens 1.21.144.714 I slot print_timing: id 2 | task 273 | graphs reused = 1 1.21.144.715 I slot print_timing: id 2 | task 273 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.144.729 I slot release: id 2 | task 273 | stop processing: n_tokens = 146, truncated = 0 1.21.145.025 I slot print_timing: id 3 | task 274 | prompt eval time = 893.58 ms / 125 tokens ( 7.15 ms per token, 139.89 tokens per second) 1.21.145.027 I slot print_timing: id 3 | task 274 | eval time = 37.64 ms / 2 tokens ( 37.64 ms per token, 26.57 tokens per second) 1.21.145.028 I slot print_timing: id 3 | task 274 | total time = 931.22 ms / 127 tokens 1.21.145.028 I slot print_timing: id 3 | task 274 | graphs reused = 1 1.21.145.028 I slot print_timing: id 3 | task 274 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.145.036 I slot release: id 3 | task 274 | stop processing: n_tokens = 126, truncated = 0 1.21.158.275 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 104, t_last = 342441840530 1.21.158.527 I slot launch_slot_: id 0 | task 278 | processing task, is_child = 0 1.21.159.553 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 135, t_last = 342441980123 1.21.159.589 I slot launch_slot_: id 1 | task 280 | processing task, is_child = 0 1.21.159.629 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 146, t_last = 342441980427 1.21.159.660 I slot launch_slot_: id 2 | task 279 | processing task, is_child = 0 1.21.159.679 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 126, t_last = 342441980734 1.21.159.708 I slot launch_slot_: id 3 | task 281 | processing task, is_child = 0 1.24.166.394 I slot print_timing: id 0 | task 278 | prompt processing, n_tokens = 617, progress = 0.54, t = 3.01 s / 205.21 tokens per second 1.24.250.806 I slot print_timing: id 1 | task 280 | prompt processing, n_tokens = 643, progress = 0.55, t = 3.01 s / 213.86 tokens per second 1.24.250.850 I slot print_timing: id 2 | task 279 | prompt processing, n_tokens = 632, progress = 0.55, t = 3.01 s / 210.20 tokens per second 1.24.250.896 I slot print_timing: id 3 | task 281 | prompt processing, n_tokens = 156, progress = 0.14, t = 3.01 s / 51.89 tokens per second 1.26.888.195 I slot print_timing: id 0 | task 278 | prompt processing, n_tokens = 1129, progress = 1.00, t = 5.73 s / 197.09 tokens per second 1.27.129.510 I slot print_timing: id 1 | task 280 | prompt processing, n_tokens = 1155, progress = 1.00, t = 5.73 s / 201.63 tokens per second 1.27.129.715 I slot print_timing: id 2 | task 279 | prompt processing, n_tokens = 1144, progress = 1.00, t = 5.73 s / 199.71 tokens per second 1.27.129.907 I slot print_timing: id 3 | task 281 | prompt processing, n_tokens = 637, progress = 0.55, t = 5.73 s / 111.20 tokens per second 1.27.949.177 I slot print_timing: id 3 | task 281 | prompt processing, n_tokens = 1149, progress = 1.00, t = 6.79 s / 169.26 tokens per second 1.32.680.368 I slot print_timing: id 0 | task 278 | n_gen = 100, tg = 20.92 t/s, tg_3s = 21.13 t/s 1.32.681.082 I slot print_timing: id 1 | task 280 | n_gen = 100, tg = 20.92 t/s, tg_3s = 21.13 t/s 1.32.681.716 I slot print_timing: id 2 | task 279 | n_gen = 100, tg = 20.92 t/s, tg_3s = 21.13 t/s 1.32.730.400 I slot print_timing: id 3 | task 281 | n_gen = 100, tg = 21.06 t/s, tg_3s = 21.28 t/s 1.35.698.121 I slot print_timing: id 0 | task 278 | n_gen = 163, tg = 20.90 t/s, tg_3s = 20.88 t/s 1.35.698.839 I slot print_timing: id 1 | task 280 | n_gen = 163, tg = 20.90 t/s, tg_3s = 20.88 t/s 1.35.699.555 I slot print_timing: id 2 | task 279 | n_gen = 163, tg = 20.90 t/s, tg_3s = 20.88 t/s 1.35.747.905 I slot print_timing: id 3 | task 281 | n_gen = 163, tg = 20.99 t/s, tg_3s = 20.88 t/s 1.38.706.961 I slot print_timing: id 0 | task 278 | n_gen = 226, tg = 20.91 t/s, tg_3s = 20.94 t/s 1.38.707.698 I slot print_timing: id 1 | task 280 | n_gen = 226, tg = 20.91 t/s, tg_3s = 20.94 t/s 1.38.708.456 I slot print_timing: id 2 | task 279 | n_gen = 226, tg = 20.91 t/s, tg_3s = 20.94 t/s 1.38.756.789 I slot print_timing: id 3 | task 281 | n_gen = 226, tg = 20.98 t/s, tg_3s = 20.94 t/s 1.41.725.147 I slot print_timing: id 0 | task 278 | n_gen = 289, tg = 20.91 t/s, tg_3s = 20.87 t/s 1.41.725.830 I slot print_timing: id 1 | task 280 | n_gen = 289, tg = 20.90 t/s, tg_3s = 20.87 t/s 1.41.726.476 I slot print_timing: id 2 | task 279 | n_gen = 289, tg = 20.90 t/s, tg_3s = 20.87 t/s 1.41.774.843 I slot print_timing: id 3 | task 281 | n_gen = 289, tg = 20.95 t/s, tg_3s = 20.87 t/s 1.44.745.995 I slot print_timing: id 0 | task 278 | n_gen = 352, tg = 20.90 t/s, tg_3s = 20.86 t/s 1.44.746.574 I slot print_timing: id 1 | task 280 | n_gen = 352, tg = 20.90 t/s, tg_3s = 20.86 t/s 1.44.747.241 I slot print_timing: id 2 | task 279 | n_gen = 352, tg = 20.90 t/s, tg_3s = 20.86 t/s 1.44.795.982 I slot print_timing: id 3 | task 281 | n_gen = 352, tg = 20.94 t/s, tg_3s = 20.85 t/s 1.47.773.382 I slot print_timing: id 0 | task 278 | n_gen = 415, tg = 20.88 t/s, tg_3s = 20.81 t/s 1.47.774.114 I slot print_timing: id 1 | task 280 | n_gen = 415, tg = 20.88 t/s, tg_3s = 20.81 t/s 1.47.774.788 I slot print_timing: id 2 | task 279 | n_gen = 415, tg = 20.88 t/s, tg_3s = 20.81 t/s 1.47.823.505 I slot print_timing: id 3 | task 281 | n_gen = 415, tg = 20.92 t/s, tg_3s = 20.81 t/s 1.50.466.576 I slot print_timing: id 0 | task 278 | prompt eval time = 6788.87 ms / 1133 tokens ( 5.99 ms per token, 166.89 tokens per second) 1.50.466.584 I slot print_timing: id 0 | task 278 | eval time = 22517.99 ms / 471 tokens ( 47.91 ms per token, 20.87 tokens per second) 1.50.466.585 I slot print_timing: id 0 | task 278 | total time = 29306.86 ms / 1604 tokens 1.50.466.586 I slot print_timing: id 0 | task 278 | graphs reused = 469 1.50.466.587 I slot print_timing: id 0 | task 278 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.466.703 I slot release: id 0 | task 278 | stop processing: n_tokens = 1603, truncated = 0 1.50.509.814 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.666 1.50.509.870 I slot launch_slot_: id 0 | task 756 | processing task, is_child = 0 1.51.473.115 I slot print_timing: id 1 | task 280 | n_gen = 474, tg = 20.11 t/s, tg_3s = 15.95 t/s 1.51.473.412 I slot print_timing: id 2 | task 279 | n_gen = 474, tg = 20.11 t/s, tg_3s = 15.95 t/s 1.51.473.706 I slot print_timing: id 3 | task 281 | n_gen = 473, tg = 20.13 t/s, tg_3s = 15.89 t/s 1.54.498.146 I slot print_timing: id 1 | task 280 | n_gen = 537, tg = 20.19 t/s, tg_3s = 20.83 t/s 1.54.498.830 I slot print_timing: id 2 | task 279 | n_gen = 537, tg = 20.19 t/s, tg_3s = 20.82 t/s 1.54.499.492 I slot print_timing: id 3 | task 281 | n_gen = 536, tg = 20.21 t/s, tg_3s = 20.82 t/s 1.56.275.913 I slot print_timing: id 0 | task 756 | n_gen = 100, tg = 20.96 t/s, tg_3s = 21.17 t/s 1.57.525.908 I slot print_timing: id 1 | task 280 | n_gen = 600, tg = 20.25 t/s, tg_3s = 20.81 t/s 1.57.526.615 I slot print_timing: id 2 | task 279 | n_gen = 600, tg = 20.25 t/s, tg_3s = 20.81 t/s 1.57.527.274 I slot print_timing: id 3 | task 281 | n_gen = 599, tg = 20.27 t/s, tg_3s = 20.81 t/s 1.59.308.443 I slot print_timing: id 0 | task 756 | n_gen = 163, tg = 20.89 t/s, tg_3s = 20.77 t/s 2.00.560.506 I slot print_timing: id 1 | task 280 | n_gen = 663, tg = 20.30 t/s, tg_3s = 20.76 t/s 2.00.561.127 I slot print_timing: id 2 | task 279 | n_gen = 663, tg = 20.30 t/s, tg_3s = 20.76 t/s 2.00.561.818 I slot print_timing: id 3 | task 281 | n_gen = 662, tg = 20.32 t/s, tg_3s = 20.76 t/s 2.00.848.076 I slot print_timing: id 2 | task 279 | prompt eval time = 6789.42 ms / 1148 tokens ( 5.91 ms per token, 169.09 tokens per second) 2.00.848.081 I slot print_timing: id 2 | task 279 | eval time = 32898.90 ms / 669 tokens ( 49.25 ms per token, 20.30 tokens per second) 2.00.848.082 I slot print_timing: id 2 | task 279 | total time = 39688.32 ms / 1817 tokens 2.00.848.083 I slot print_timing: id 2 | task 279 | graphs reused = 662 2.00.848.083 I slot print_timing: id 2 | task 279 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.848.200 I slot release: id 2 | task 279 | stop processing: n_tokens = 1816, truncated = 0 2.00.897.091 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.588 2.00.897.133 I slot launch_slot_: id 2 | task 955 | processing task, is_child = 0 2.02.328.222 I slot print_timing: id 0 | task 756 | n_gen = 206, tg = 19.02 t/s, tg_3s = 14.24 t/s 2.03.587.164 I slot print_timing: id 1 | task 280 | n_gen = 707, tg = 19.81 t/s, tg_3s = 14.54 t/s 2.03.587.710 I slot print_timing: id 3 | task 281 | n_gen = 706, tg = 19.83 t/s, tg_3s = 14.54 t/s 2.04.660.315 I slot print_timing: id 3 | task 281 | prompt eval time = 6870.59 ms / 1153 tokens ( 5.96 ms per token, 167.82 tokens per second) 2.04.660.321 I slot print_timing: id 3 | task 281 | eval time = 36629.94 ms / 729 tokens ( 50.32 ms per token, 19.87 tokens per second) 2.04.660.321 I slot print_timing: id 3 | task 281 | total time = 43500.54 ms / 1882 tokens 2.04.660.322 I slot print_timing: id 3 | task 281 | graphs reused = 718 2.04.660.322 I slot print_timing: id 3 | task 281 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.660.406 I slot release: id 3 | task 281 | stop processing: n_tokens = 1881, truncated = 0 2.04.699.249 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.568 2.04.699.272 I slot launch_slot_: id 3 | task 1017 | processing task, is_child = 0 2.05.675.717 I slot print_timing: id 0 | task 756 | n_gen = 259, tg = 18.27 t/s, tg_3s = 15.83 t/s 2.06.594.273 I slot print_timing: id 1 | task 280 | n_gen = 752, tg = 19.43 t/s, tg_3s = 14.96 t/s 2.07.555.068 I slot print_timing: id 2 | task 955 | n_gen = 100, tg = 17.83 t/s, tg_3s = 18.01 t/s 2.08.704.165 I slot print_timing: id 0 | task 756 | n_gen = 322, tg = 18.71 t/s, tg_3s = 20.80 t/s 2.09.614.775 I slot print_timing: id 1 | task 280 | n_gen = 815, tg = 19.54 t/s, tg_3s = 20.86 t/s 2.10.477.062 I slot print_timing: id 3 | task 1017 | n_gen = 100, tg = 20.98 t/s, tg_3s = 21.19 t/s 2.10.572.671 I slot print_timing: id 2 | task 955 | n_gen = 163, tg = 18.90 t/s, tg_3s = 20.88 t/s 2.11.720.329 I slot print_timing: id 0 | task 756 | n_gen = 385, tg = 19.04 t/s, tg_3s = 20.89 t/s 2.12.628.003 I slot print_timing: id 1 | task 280 | n_gen = 878, tg = 19.63 t/s, tg_3s = 20.91 t/s 2.13.492.475 I slot print_timing: id 3 | task 1017 | n_gen = 163, tg = 20.95 t/s, tg_3s = 20.89 t/s 2.13.587.729 I slot print_timing: id 2 | task 955 | n_gen = 226, tg = 19.42 t/s, tg_3s = 20.90 t/s 2.14.737.359 I slot print_timing: id 0 | task 756 | n_gen = 448, tg = 19.28 t/s, tg_3s = 20.88 t/s 2.15.642.596 I slot print_timing: id 1 | task 280 | n_gen = 941, tg = 19.71 t/s, tg_3s = 20.90 t/s 2.16.508.998 I slot print_timing: id 3 | task 1017 | n_gen = 226, tg = 20.93 t/s, tg_3s = 20.88 t/s 2.16.605.256 I slot print_timing: id 2 | task 955 | n_gen = 289, tg = 19.72 t/s, tg_3s = 20.88 t/s 2.17.759.855 I slot print_timing: id 0 | task 756 | n_gen = 511, tg = 19.46 t/s, tg_3s = 20.84 t/s 2.18.676.386 I slot print_timing: id 1 | task 280 | n_gen = 1004, tg = 19.77 t/s, tg_3s = 20.77 t/s 2.19.544.373 I slot print_timing: id 3 | task 1017 | n_gen = 289, tg = 20.89 t/s, tg_3s = 20.76 t/s 2.19.639.379 I slot print_timing: id 1 | task 280 | prompt eval time = 6789.15 ms / 1159 tokens ( 5.86 ms per token, 170.71 tokens per second) 2.19.639.384 I slot print_timing: id 1 | task 280 | eval time = 51690.49 ms / 1024 tokens ( 50.53 ms per token, 19.79 tokens per second) 2.19.639.384 I slot print_timing: id 1 | task 280 | total time = 58479.64 ms / 2183 tokens 2.19.639.385 I slot print_timing: id 1 | task 280 | graphs reused = 1006 2.19.639.386 I slot print_timing: id 1 | task 280 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.639.508 I slot release: id 1 | task 280 | stop processing: n_tokens = 2182, truncated = 0 2.19.640.170 I slot print_timing: id 2 | task 955 | n_gen = 352, tg = 19.90 t/s, tg_3s = 20.76 t/s 2.19.688.810 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.489 2.19.695.655 I slot launch_slot_: id 1 | task 1312 | processing task, is_child = 0 2.20.804.132 I slot print_timing: id 0 | task 756 | n_gen = 559, tg = 19.08 t/s, tg_3s = 15.77 t/s 2.22.577.807 I slot print_timing: id 3 | task 1017 | n_gen = 337, tg = 19.98 t/s, tg_3s = 15.82 t/s 2.22.672.948 I slot print_timing: id 2 | task 955 | n_gen = 400, tg = 19.30 t/s, tg_3s = 15.83 t/s 2.23.768.523 I slot print_timing: id 0 | task 756 | prompt eval time = 1042.10 ms / 554 tokens ( 1.88 ms per token, 531.62 tokens per second) 2.23.768.526 I slot print_timing: id 0 | task 756 | eval time = 32216.55 ms / 621 tokens ( 51.96 ms per token, 19.24 tokens per second) 2.23.768.528 I slot print_timing: id 0 | task 756 | total time = 33258.64 ms / 1175 tokens 2.23.768.529 I slot print_timing: id 0 | task 756 | graphs reused = 1073 2.23.768.529 I slot print_timing: id 0 | task 756 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.768.623 I slot release: id 0 | task 756 | stop processing: n_tokens = 1791, truncated = 0 2.23.809.487 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.596 2.23.809.521 I slot launch_slot_: id 0 | task 1384 | processing task, is_child = 0 2.25.610.882 I slot print_timing: id 3 | task 1017 | n_gen = 384, tg = 19.29 t/s, tg_3s = 15.50 t/s 2.25.706.255 I slot print_timing: id 2 | task 955 | n_gen = 447, tg = 18.81 t/s, tg_3s = 15.49 t/s 2.26.041.919 I slot print_timing: id 1 | task 1312 | n_gen = 100, tg = 17.94 t/s, tg_3s = 18.12 t/s 2.28.626.244 I slot print_timing: id 3 | task 1017 | n_gen = 447, tg = 19.50 t/s, tg_3s = 20.89 t/s 2.28.720.897 I slot print_timing: id 2 | task 955 | n_gen = 510, tg = 19.05 t/s, tg_3s = 20.90 t/s 2.29.053.602 I slot print_timing: id 1 | task 1312 | n_gen = 163, tg = 18.99 t/s, tg_3s = 20.92 t/s 2.29.482.694 I slot print_timing: id 0 | task 1384 | n_gen = 100, tg = 20.98 t/s, tg_3s = 21.19 t/s 2.30.587.928 I slot print_timing: id 3 | task 1017 | prompt eval time = 1058.74 ms / 544 tokens ( 1.95 ms per token, 513.82 tokens per second) 2.30.587.933 I slot print_timing: id 3 | task 1017 | eval time = 24829.89 ms / 488 tokens ( 50.99 ms per token, 19.61 tokens per second) 2.30.587.934 I slot print_timing: id 3 | task 1017 | total time = 25888.64 ms / 1032 tokens 2.30.587.935 I slot print_timing: id 3 | task 1017 | graphs reused = 1195 2.30.587.936 I slot print_timing: id 3 | task 1017 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.588.064 I slot release: id 3 | task 1017 | stop processing: n_tokens = 1668, truncated = 0 2.30.629.132 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.640 2.30.629.165 I slot launch_slot_: id 3 | task 1511 | processing task, is_child = 0 2.31.750.083 I slot print_timing: id 2 | task 955 | n_gen = 554, tg = 18.59 t/s, tg_3s = 14.53 t/s 2.32.076.281 I slot print_timing: id 1 | task 1312 | n_gen = 207, tg = 17.83 t/s, tg_3s = 14.56 t/s 2.32.509.153 I slot print_timing: id 0 | task 1384 | n_gen = 144, tg = 18.46 t/s, tg_3s = 14.54 t/s 2.34.776.113 I slot print_timing: id 2 | task 955 | n_gen = 617, tg = 18.80 t/s, tg_3s = 20.82 t/s 2.35.111.382 I slot print_timing: id 1 | task 1312 | n_gen = 270, tg = 18.44 t/s, tg_3s = 20.76 t/s 2.35.544.280 I slot print_timing: id 0 | task 1384 | n_gen = 207, tg = 19.11 t/s, tg_3s = 20.76 t/s 2.36.458.100 I slot print_timing: id 3 | task 1511 | n_gen = 100, tg = 20.82 t/s, tg_3s = 21.03 t/s 2.37.792.158 I slot print_timing: id 2 | task 955 | n_gen = 680, tg = 18.97 t/s, tg_3s = 20.89 t/s 2.38.125.364 I slot print_timing: id 1 | task 1312 | n_gen = 333, tg = 18.86 t/s, tg_3s = 20.90 t/s 2.38.173.624 I slot print_timing: id 2 | task 955 | prompt eval time = 1104.61 ms / 548 tokens ( 2.02 ms per token, 496.10 tokens per second) 2.38.173.629 I slot print_timing: id 2 | task 955 | eval time = 36171.88 ms / 688 tokens ( 52.65 ms per token, 18.99 tokens per second) 2.38.173.631 I slot print_timing: id 2 | task 955 | total time = 37276.49 ms / 1236 tokens 2.38.173.632 I slot print_timing: id 2 | task 955 | graphs reused = 1328 2.38.173.633 I slot print_timing: id 2 | task 955 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.173.753 I slot release: id 2 | task 955 | stop processing: n_tokens = 1867, truncated = 0 2.38.222.444 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.572 2.38.222.491 I slot launch_slot_: id 2 | task 1651 | processing task, is_child = 0 2.38.956.905 I slot print_timing: id 0 | task 1384 | n_gen = 264, tg = 18.53 t/s, tg_3s = 16.70 t/s 2.39.465.969 I slot print_timing: id 3 | task 1511 | n_gen = 148, tg = 18.94 t/s, tg_3s = 15.96 t/s 2.41.088.730 I slot print_timing: id 0 | task 1384 | prompt eval time = 953.78 ms / 531 tokens ( 1.80 ms per token, 556.73 tokens per second) 2.41.088.738 I slot print_timing: id 0 | task 1384 | eval time = 16325.42 ms / 308 tokens ( 53.18 ms per token, 18.81 tokens per second) 2.41.088.739 I slot print_timing: id 0 | task 1384 | total time = 17279.20 ms / 839 tokens 2.41.088.740 I slot print_timing: id 0 | task 1384 | graphs reused = 1370 2.41.088.741 I slot print_timing: id 0 | task 1384 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.088.862 I slot release: id 0 | task 1384 | stop processing: n_tokens = 1493, truncated = 0 2.41.130.654 I slot print_timing: id 1 | task 1312 | n_gen = 381, tg = 18.44 t/s, tg_3s = 15.97 t/s 2.41.131.723 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.715 2.41.131.773 I slot launch_slot_: id 0 | task 1698 | processing task, is_child = 0 2.42.502.436 I slot print_timing: id 3 | task 1511 | n_gen = 198, tg = 18.24 t/s, tg_3s = 16.47 t/s 2.44.157.292 I slot print_timing: id 1 | task 1312 | n_gen = 431, tg = 18.19 t/s, tg_3s = 16.52 t/s 2.44.396.867 I slot print_timing: id 2 | task 1651 | n_gen = 100, tg = 18.50 t/s, tg_3s = 18.69 t/s 2.45.539.559 I slot print_timing: id 3 | task 1511 | n_gen = 262, tg = 18.86 t/s, tg_3s = 21.07 t/s 2.46.586.986 I slot print_timing: id 0 | task 1698 | n_gen = 100, tg = 21.10 t/s, tg_3s = 21.31 t/s 2.47.160.808 I slot print_timing: id 1 | task 1312 | n_gen = 494, tg = 18.51 t/s, tg_3s = 20.98 t/s 2.47.399.166 I slot print_timing: id 2 | task 1651 | n_gen = 163, tg = 19.39 t/s, tg_3s = 20.98 t/s 2.48.549.315 I slot print_timing: id 3 | task 1511 | n_gen = 325, tg = 19.23 t/s, tg_3s = 20.93 t/s 2.49.596.646 I slot print_timing: id 0 | task 1698 | n_gen = 163, tg = 21.03 t/s, tg_3s = 20.93 t/s 2.50.170.477 I slot print_timing: id 1 | task 1312 | n_gen = 557, tg = 18.75 t/s, tg_3s = 20.93 t/s 2.50.410.225 I slot print_timing: id 2 | task 1651 | n_gen = 226, tg = 19.80 t/s, tg_3s = 20.92 t/s 2.51.557.986 I slot print_timing: id 3 | task 1511 | n_gen = 388, tg = 19.49 t/s, tg_3s = 20.94 t/s 2.52.610.908 I slot print_timing: id 0 | task 1698 | n_gen = 226, tg = 21.00 t/s, tg_3s = 20.90 t/s 2.53.188.165 I slot print_timing: id 1 | task 1312 | n_gen = 620, tg = 18.95 t/s, tg_3s = 20.88 t/s 2.53.428.285 I slot print_timing: id 2 | task 1651 | n_gen = 289, tg = 20.02 t/s, tg_3s = 20.87 t/s 2.54.580.706 I slot print_timing: id 3 | task 1511 | n_gen = 451, tg = 19.67 t/s, tg_3s = 20.84 t/s 2.55.632.509 I slot print_timing: id 0 | task 1698 | n_gen = 289, tg = 20.96 t/s, tg_3s = 20.85 t/s 2.56.209.197 I slot print_timing: id 1 | task 1312 | n_gen = 683, tg = 19.11 t/s, tg_3s = 20.85 t/s 2.56.449.201 I slot print_timing: id 2 | task 1651 | n_gen = 352, tg = 20.17 t/s, tg_3s = 20.85 t/s 2.57.599.370 I slot print_timing: id 3 | task 1511 | n_gen = 514, tg = 19.81 t/s, tg_3s = 20.87 t/s 2.58.652.150 I slot print_timing: id 0 | task 1698 | n_gen = 352, tg = 20.95 t/s, tg_3s = 20.86 t/s 2.59.232.228 I slot print_timing: id 1 | task 1312 | n_gen = 746, tg = 19.25 t/s, tg_3s = 20.84 t/s 2.59.473.915 I slot print_timing: id 2 | task 1651 | n_gen = 415, tg = 20.27 t/s, tg_3s = 20.83 t/s 2.59.857.782 I slot print_timing: id 0 | task 1698 | prompt eval time = 763.21 ms / 475 tokens ( 1.61 ms per token, 622.38 tokens per second) 2.59.857.788 I slot print_timing: id 0 | task 1698 | eval time = 17962.79 ms / 377 tokens ( 47.77 ms per token, 20.93 tokens per second) 2.59.857.789 I slot print_timing: id 0 | task 1698 | total time = 18726.00 ms / 852 tokens 2.59.857.789 I slot print_timing: id 0 | task 1698 | graphs reused = 1745 2.59.857.790 I slot print_timing: id 0 | task 1698 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.857.914 I slot release: id 0 | task 1698 | stop processing: n_tokens = 1521, truncated = 0 2.59.901.488 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.702 2.59.901.525 I slot launch_slot_: id 0 | task 2078 | processing task, is_child = 0 3.00.664.752 I slot print_timing: id 3 | task 1511 | n_gen = 564, tg = 19.44 t/s, tg_3s = 16.31 t/s 3.02.250.736 I slot print_timing: id 1 | task 1312 | n_gen = 796, tg = 19.05 t/s, tg_3s = 16.56 t/s 3.02.483.568 I slot print_timing: id 2 | task 1651 | n_gen = 465, tg = 19.80 t/s, tg_3s = 16.61 t/s 3.03.690.309 I slot print_timing: id 3 | task 1511 | n_gen = 628, tg = 19.60 t/s, tg_3s = 21.15 t/s 3.05.268.504 I slot print_timing: id 1 | task 1312 | n_gen = 859, tg = 19.18 t/s, tg_3s = 20.88 t/s 3.05.363.215 I slot print_timing: id 0 | task 2078 | n_gen = 100, tg = 21.07 t/s, tg_3s = 21.28 t/s 3.05.508.054 I slot print_timing: id 2 | task 1651 | n_gen = 528, tg = 19.92 t/s, tg_3s = 20.83 t/s 3.06.705.611 I slot print_timing: id 3 | task 1511 | n_gen = 691, tg = 19.71 t/s, tg_3s = 20.89 t/s 3.08.296.187 I slot print_timing: id 1 | task 1312 | n_gen = 922, tg = 19.28 t/s, tg_3s = 20.81 t/s 3.08.391.889 I slot print_timing: id 0 | task 2078 | n_gen = 163, tg = 20.96 t/s, tg_3s = 20.80 t/s 3.08.538.802 I slot print_timing: id 2 | task 1651 | n_gen = 591, tg = 20.00 t/s, tg_3s = 20.79 t/s 3.09.741.242 I slot print_timing: id 3 | task 1511 | n_gen = 754, tg = 19.80 t/s, tg_3s = 20.75 t/s 3.09.981.858 I slot print_timing: id 3 | task 1511 | prompt eval time = 1073.43 ms / 546 tokens ( 1.97 ms per token, 508.65 tokens per second) 3.09.981.864 I slot print_timing: id 3 | task 1511 | eval time = 38279.26 ms / 759 tokens ( 50.50 ms per token, 19.80 tokens per second) 3.09.981.865 I slot print_timing: id 3 | task 1511 | total time = 39352.68 ms / 1305 tokens 3.09.981.866 I slot print_timing: id 3 | task 1511 | graphs reused = 1939 3.09.981.867 I slot print_timing: id 3 | task 1511 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.982.015 I slot release: id 3 | task 1511 | stop processing: n_tokens = 1969, truncated = 0 3.10.023.365 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.542 3.10.023.401 I slot launch_slot_: id 3 | task 2277 | processing task, is_child = 0 3.11.325.209 I slot print_timing: id 1 | task 1312 | n_gen = 972, tg = 19.11 t/s, tg_3s = 16.51 t/s 3.11.417.935 I slot print_timing: id 0 | task 2078 | n_gen = 213, tg = 19.71 t/s, tg_3s = 16.52 t/s 3.11.559.297 I slot print_timing: id 2 | task 1651 | n_gen = 641, tg = 19.68 t/s, tg_3s = 16.55 t/s 3.13.766.438 I slot print_timing: id 1 | task 1312 | prompt eval time = 827.29 ms / 512 tokens ( 1.62 ms per token, 618.89 tokens per second) 3.13.766.446 I slot print_timing: id 1 | task 1312 | eval time = 53243.47 ms / 1024 tokens ( 52.05 ms per token, 19.21 tokens per second) 3.13.766.447 I slot print_timing: id 1 | task 1312 | total time = 54070.77 ms / 1536 tokens 3.13.766.448 I slot print_timing: id 1 | task 1312 | graphs reused = 2002 3.13.766.449 I slot print_timing: id 1 | task 1312 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.766.610 I slot release: id 1 | task 1312 | stop processing: n_tokens = 2178, truncated = 0 3.13.816.661 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.490 3.13.823.430 I slot launch_slot_: id 1 | task 2345 | processing task, is_child = 0 3.14.674.430 I slot print_timing: id 0 | task 2078 | n_gen = 266, tg = 18.91 t/s, tg_3s = 16.28 t/s 3.14.674.733 I slot print_timing: id 2 | task 1651 | n_gen = 691, tg = 19.37 t/s, tg_3s = 16.05 t/s 3.16.232.348 I slot print_timing: id 3 | task 2277 | n_gen = 100, tg = 18.11 t/s, tg_3s = 18.29 t/s 3.17.714.181 I slot print_timing: id 0 | task 2078 | n_gen = 329, tg = 19.24 t/s, tg_3s = 20.73 t/s 3.17.715.510 I slot print_timing: id 2 | task 1651 | n_gen = 754, tg = 19.47 t/s, tg_3s = 20.72 t/s 3.19.244.315 I slot print_timing: id 3 | task 2277 | n_gen = 163, tg = 19.10 t/s, tg_3s = 20.92 t/s 3.19.482.376 I slot print_timing: id 1 | task 2345 | n_gen = 100, tg = 20.98 t/s, tg_3s = 21.19 t/s 3.20.723.484 I slot print_timing: id 0 | task 2078 | n_gen = 392, tg = 19.49 t/s, tg_3s = 20.94 t/s 3.20.724.707 I slot print_timing: id 2 | task 1651 | n_gen = 817, tg = 19.58 t/s, tg_3s = 20.94 t/s 3.22.255.496 I slot print_timing: id 3 | task 2277 | n_gen = 226, tg = 19.58 t/s, tg_3s = 20.92 t/s 3.22.494.919 I slot print_timing: id 1 | task 2345 | n_gen = 163, tg = 20.95 t/s, tg_3s = 20.91 t/s 3.23.738.686 I slot print_timing: id 0 | task 2078 | n_gen = 455, tg = 19.68 t/s, tg_3s = 20.89 t/s 3.23.739.956 I slot print_timing: id 2 | task 1651 | n_gen = 880, tg = 19.67 t/s, tg_3s = 20.89 t/s 3.25.280.064 I slot print_timing: id 3 | task 2277 | n_gen = 289, tg = 19.84 t/s, tg_3s = 20.83 t/s 3.25.520.581 I slot print_timing: id 1 | task 2345 | n_gen = 226, tg = 20.92 t/s, tg_3s = 20.82 t/s 3.26.771.839 I slot print_timing: id 0 | task 2078 | n_gen = 518, tg = 19.80 t/s, tg_3s = 20.77 t/s 3.26.773.272 I slot print_timing: id 2 | task 1651 | n_gen = 943, tg = 19.74 t/s, tg_3s = 20.77 t/s 3.28.312.228 I slot print_timing: id 3 | task 2277 | n_gen = 352, tg = 20.00 t/s, tg_3s = 20.78 t/s 3.28.552.665 I slot print_timing: id 1 | task 2345 | n_gen = 289, tg = 20.89 t/s, tg_3s = 20.78 t/s 3.29.802.794 I slot print_timing: id 0 | task 2078 | n_gen = 581, tg = 19.90 t/s, tg_3s = 20.79 t/s 3.29.804.133 I slot print_timing: id 2 | task 1651 | n_gen = 1006, tg = 19.80 t/s, tg_3s = 20.79 t/s 3.30.670.484 I slot print_timing: id 2 | task 1651 | prompt eval time = 823.24 ms / 504 tokens ( 1.63 ms per token, 612.21 tokens per second) 3.30.670.492 I slot print_timing: id 2 | task 1651 | eval time = 51624.74 ms / 1024 tokens ( 50.46 ms per token, 19.82 tokens per second) 3.30.670.493 I slot print_timing: id 2 | task 1651 | total time = 52447.98 ms / 1528 tokens 3.30.670.494 I slot print_timing: id 2 | task 1651 | graphs reused = 2332 3.30.670.495 I slot print_timing: id 2 | task 1651 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.670.635 I slot release: id 2 | task 1651 | stop processing: n_tokens = 2191, truncated = 0 3.30.719.840 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.487 3.30.726.132 I slot launch_slot_: id 2 | task 2682 | processing task, is_child = 0 3.31.607.331 I slot print_timing: id 1 | task 2345 | n_gen = 336, tg = 19.89 t/s, tg_3s = 15.39 t/s 3.31.607.583 I slot print_timing: id 3 | task 2277 | n_gen = 404, tg = 19.33 t/s, tg_3s = 15.78 t/s 3.32.833.030 I slot print_timing: id 0 | task 2078 | n_gen = 627, tg = 19.46 t/s, tg_3s = 15.18 t/s 3.34.131.426 I slot print_timing: id 3 | task 2277 | prompt eval time = 740.97 ms / 442 tokens ( 1.68 ms per token, 596.51 tokens per second) 3.34.131.432 I slot print_timing: id 3 | task 2277 | eval time = 23367.04 ms / 456 tokens ( 51.36 ms per token, 19.47 tokens per second) 3.34.131.433 I slot print_timing: id 3 | task 2277 | total time = 24108.01 ms / 898 tokens 3.34.131.434 I slot print_timing: id 3 | task 2277 | graphs reused = 2381 3.34.131.435 I slot print_timing: id 3 | task 2277 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.131.566 I slot release: id 3 | task 2277 | stop processing: n_tokens = 1592, truncated = 0 3.34.172.635 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.671 3.34.172.672 I slot launch_slot_: id 3 | task 2738 | processing task, is_child = 0 3.34.826.182 I slot print_timing: id 1 | task 2345 | n_gen = 390, tg = 19.39 t/s, tg_3s = 16.78 t/s 3.35.847.534 I slot print_timing: id 0 | task 2078 | n_gen = 677, tg = 19.21 t/s, tg_3s = 16.59 t/s 3.37.048.896 I slot print_timing: id 2 | task 2682 | n_gen = 100, tg = 18.49 t/s, tg_3s = 18.68 t/s 3.37.867.087 I slot print_timing: id 1 | task 2345 | n_gen = 453, tg = 19.56 t/s, tg_3s = 20.72 t/s 3.38.873.764 I slot print_timing: id 0 | task 2078 | n_gen = 740, tg = 19.34 t/s, tg_3s = 20.82 t/s 3.39.646.638 I slot print_timing: id 3 | task 2738 | n_gen = 100, tg = 20.89 t/s, tg_3s = 21.10 t/s 3.40.079.715 I slot print_timing: id 2 | task 2682 | n_gen = 163, tg = 19.32 t/s, tg_3s = 20.79 t/s 3.40.894.764 I slot print_timing: id 1 | task 2345 | n_gen = 516, tg = 19.71 t/s, tg_3s = 20.81 t/s 3.41.898.572 I slot print_timing: id 0 | task 2078 | n_gen = 803, tg = 19.45 t/s, tg_3s = 20.83 t/s 3.42.669.347 I slot print_timing: id 3 | task 2738 | n_gen = 163, tg = 20.87 t/s, tg_3s = 20.84 t/s 3.43.099.311 I slot print_timing: id 2 | task 2682 | n_gen = 226, tg = 19.73 t/s, tg_3s = 20.86 t/s 3.43.913.358 I slot print_timing: id 1 | task 2345 | n_gen = 579, tg = 19.83 t/s, tg_3s = 20.87 t/s 3.44.922.202 I slot print_timing: id 0 | task 2078 | n_gen = 866, tg = 19.54 t/s, tg_3s = 20.84 t/s 3.45.691.749 I slot print_timing: id 3 | task 2738 | n_gen = 226, tg = 20.87 t/s, tg_3s = 20.84 t/s 3.46.121.714 I slot print_timing: id 2 | task 2682 | n_gen = 289, tg = 19.96 t/s, tg_3s = 20.84 t/s 3.46.938.612 I slot print_timing: id 1 | task 2345 | n_gen = 642, tg = 19.92 t/s, tg_3s = 20.82 t/s 3.47.946.967 I slot print_timing: id 0 | task 2078 | n_gen = 929, tg = 19.63 t/s, tg_3s = 20.83 t/s 3.48.717.609 I slot print_timing: id 3 | task 2738 | n_gen = 289, tg = 20.86 t/s, tg_3s = 20.82 t/s 3.48.957.044 I slot print_timing: id 1 | task 2345 | prompt eval time = 939.99 ms / 523 tokens ( 1.80 ms per token, 556.39 tokens per second) 3.48.957.052 I slot print_timing: id 1 | task 2345 | eval time = 34193.61 ms / 684 tokens ( 50.06 ms per token, 19.97 tokens per second) 3.48.957.053 I slot print_timing: id 1 | task 2345 | total time = 35133.60 ms / 1207 tokens 3.48.957.054 I slot print_timing: id 1 | task 2345 | graphs reused = 2672 3.48.957.055 I slot print_timing: id 1 | task 2345 | graph reallocs = 0 / 0 (same size) / (changed size) 3.48.957.220 I slot release: id 1 | task 2345 | stop processing: n_tokens = 1849, truncated = 0 3.49.007.140 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.578 3.49.007.193 I slot launch_slot_: id 1 | task 3035 | processing task, is_child = 0 3.49.840.256 I slot print_timing: id 2 | task 2682 | n_gen = 351, tg = 19.29 t/s, tg_3s = 16.67 t/s 3.50.957.793 I slot print_timing: id 0 | task 2078 | n_gen = 976, tg = 19.39 t/s, tg_3s = 15.61 t/s 3.51.760.047 I slot print_timing: id 3 | task 2738 | n_gen = 337, tg = 19.94 t/s, tg_3s = 15.78 t/s 3.52.868.963 I slot print_timing: id 2 | task 2682 | n_gen = 414, tg = 19.51 t/s, tg_3s = 20.80 t/s 3.53.251.413 I slot print_timing: id 0 | task 2078 | prompt eval time = 762.37 ms / 473 tokens ( 1.61 ms per token, 620.43 tokens per second) 3.53.251.421 I slot print_timing: id 0 | task 2078 | eval time = 52587.51 ms / 1024 tokens ( 51.41 ms per token, 19.45 tokens per second) 3.53.251.422 I slot print_timing: id 0 | task 2078 | total time = 53349.88 ms / 1497 tokens 3.53.251.423 I slot print_timing: id 0 | task 2078 | graphs reused = 2741 3.53.251.423 I slot print_timing: id 0 | task 2078 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.251.539 I slot release: id 0 | task 2078 | stop processing: n_tokens = 2166, truncated = 0 3.53.293.938 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.493 3.53.299.707 I slot launch_slot_: id 0 | task 3110 | processing task, is_child = 0 3.54.802.786 I slot print_timing: id 3 | task 2738 | n_gen = 387, tg = 19.40 t/s, tg_3s = 16.43 t/s 3.55.267.496 I slot print_timing: id 1 | task 3035 | n_gen = 100, tg = 18.54 t/s, tg_3s = 18.73 t/s 3.55.873.195 I slot print_timing: id 2 | task 2682 | n_gen = 464, tg = 19.15 t/s, tg_3s = 16.64 t/s 3.57.835.961 I slot print_timing: id 3 | task 2738 | n_gen = 451, tg = 19.63 t/s, tg_3s = 21.10 t/s 3.58.310.950 I slot print_timing: id 1 | task 3035 | n_gen = 164, tg = 19.45 t/s, tg_3s = 21.03 t/s 3.58.312.215 I slot print_timing: id 3 | task 2738 | prompt eval time = 735.48 ms / 433 tokens ( 1.70 ms per token, 588.73 tokens per second) 3.58.312.223 I slot print_timing: id 3 | task 2738 | eval time = 23404.06 ms / 461 tokens ( 50.88 ms per token, 19.65 tokens per second) 3.58.312.224 I slot print_timing: id 3 | task 2738 | total time = 24139.54 ms / 894 tokens 3.58.312.224 I slot print_timing: id 3 | task 2738 | graphs reused = 2831 3.58.312.225 I slot print_timing: id 3 | task 2738 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.312.345 I slot release: id 3 | task 2738 | stop processing: n_tokens = 1588, truncated = 0 3.58.353.186 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.673 3.58.353.231 I slot launch_slot_: id 3 | task 3204 | processing task, is_child = 0 3.59.006.067 I slot print_timing: id 2 | task 2682 | n_gen = 517, tg = 18.89 t/s, tg_3s = 16.92 t/s 3.59.366.946 I slot print_timing: id 0 | task 3110 | n_gen = 100, tg = 18.65 t/s, tg_3s = 18.84 t/s 4.01.321.919 I slot print_timing: id 1 | task 3035 | n_gen = 215, tg = 18.78 t/s, tg_3s = 16.94 t/s 4.02.031.484 I slot print_timing: id 2 | task 2682 | n_gen = 581, tg = 19.12 t/s, tg_3s = 21.15 t/s 4.02.413.259 I slot print_timing: id 0 | task 3110 | n_gen = 165, tg = 19.63 t/s, tg_3s = 21.34 t/s 4.03.754.309 I slot print_timing: id 3 | task 3204 | n_gen = 100, tg = 21.21 t/s, tg_3s = 21.43 t/s 4.04.330.612 I slot print_timing: id 1 | task 3035 | n_gen = 278, tg = 19.23 t/s, tg_3s = 20.94 t/s 4.05.050.817 I slot print_timing: id 2 | task 2682 | n_gen = 644, tg = 19.28 t/s, tg_3s = 20.87 t/s 4.05.433.134 I slot print_timing: id 0 | task 3110 | n_gen = 228, tg = 19.96 t/s, tg_3s = 20.86 t/s 4.06.777.890 I slot print_timing: id 3 | task 3204 | n_gen = 163, tg = 21.06 t/s, tg_3s = 20.84 t/s 4.07.354.421 I slot print_timing: id 1 | task 3035 | n_gen = 341, tg = 19.51 t/s, tg_3s = 20.83 t/s 4.07.545.360 I slot print_timing: id 0 | task 3110 | prompt eval time = 759.96 ms / 472 tokens ( 1.61 ms per token, 621.08 tokens per second) 4.07.545.364 I slot print_timing: id 0 | task 3110 | eval time = 13485.68 ms / 272 tokens ( 49.76 ms per token, 20.10 tokens per second) 4.07.545.365 I slot print_timing: id 0 | task 3110 | total time = 14245.64 ms / 744 tokens 4.07.545.366 I slot print_timing: id 0 | task 3110 | graphs reused = 3007 4.07.545.367 I slot print_timing: id 0 | task 3110 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.545.477 I slot release: id 0 | task 3110 | stop processing: n_tokens = 1413, truncated = 0 4.07.587.889 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.756 4.07.587.927 I slot launch_slot_: id 0 | task 3386 | processing task, is_child = 0 4.08.272.231 I slot print_timing: id 2 | task 2682 | n_gen = 698, tg = 19.06 t/s, tg_3s = 16.76 t/s 4.09.796.374 I slot print_timing: id 3 | task 3204 | n_gen = 213, tg = 19.80 t/s, tg_3s = 16.56 t/s 4.10.355.935 I slot print_timing: id 1 | task 3035 | n_gen = 391, tg = 19.09 t/s, tg_3s = 16.66 t/s 4.11.288.601 I slot print_timing: id 2 | task 2682 | n_gen = 762, tg = 19.22 t/s, tg_3s = 21.22 t/s 4.12.817.424 I slot print_timing: id 3 | task 3204 | n_gen = 277, tg = 20.10 t/s, tg_3s = 21.18 t/s 4.13.006.878 I slot print_timing: id 0 | task 3386 | n_gen = 100, tg = 21.26 t/s, tg_3s = 21.48 t/s 4.13.391.414 I slot print_timing: id 1 | task 3035 | n_gen = 455, tg = 19.35 t/s, tg_3s = 21.08 t/s 4.14.303.092 I slot print_timing: id 2 | task 2682 | n_gen = 825, tg = 19.34 t/s, tg_3s = 20.90 t/s 4.15.839.381 I slot print_timing: id 3 | task 3204 | n_gen = 340, tg = 20.24 t/s, tg_3s = 20.85 t/s 4.16.032.073 I slot print_timing: id 0 | task 3386 | n_gen = 163, tg = 21.09 t/s, tg_3s = 20.83 t/s 4.16.416.082 I slot print_timing: id 1 | task 3035 | n_gen = 518, tg = 19.52 t/s, tg_3s = 20.83 t/s 4.17.328.005 I slot print_timing: id 2 | task 2682 | n_gen = 888, tg = 19.44 t/s, tg_3s = 20.83 t/s 4.18.046.595 I slot print_timing: id 1 | task 3035 | prompt eval time = 921.80 ms / 520 tokens ( 1.77 ms per token, 564.11 tokens per second) 4.18.046.603 I slot print_timing: id 1 | task 3035 | eval time = 28117.59 ms / 552 tokens ( 51.03 ms per token, 19.60 tokens per second) 4.18.046.604 I slot print_timing: id 1 | task 3035 | total time = 29039.39 ms / 1072 tokens 4.18.046.605 I slot print_timing: id 1 | task 3035 | graphs reused = 3210 4.18.046.606 I slot print_timing: id 1 | task 3035 | graph reallocs = 0 / 0 (same size) / (changed size) 4.18.046.716 I slot release: id 1 | task 3035 | stop processing: n_tokens = 1721, truncated = 0 4.18.095.615 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.621 4.18.095.658 I slot launch_slot_: id 1 | task 3594 | processing task, is_child = 0 4.18.893.030 I slot print_timing: id 3 | task 3204 | n_gen = 389, tg = 19.59 t/s, tg_3s = 16.05 t/s 4.19.033.411 I slot print_timing: id 0 | task 3386 | n_gen = 211, tg = 19.66 t/s, tg_3s = 15.99 t/s 4.20.360.801 I slot print_timing: id 2 | task 2682 | n_gen = 937, tg = 19.23 t/s, tg_3s = 16.16 t/s 4.21.902.144 I slot print_timing: id 3 | task 3204 | n_gen = 452, tg = 19.77 t/s, tg_3s = 20.94 t/s 4.22.044.414 I slot print_timing: id 0 | task 3386 | n_gen = 274, tg = 19.94 t/s, tg_3s = 20.92 t/s 4.22.238.320 I slot print_timing: id 2 | task 2682 | prompt eval time = 969.80 ms / 527 tokens ( 1.84 ms per token, 543.41 tokens per second) 4.22.238.327 I slot print_timing: id 2 | task 2682 | eval time = 50542.38 ms / 976 tokens ( 51.84 ms per token, 19.29 tokens per second) 4.22.238.329 I slot print_timing: id 2 | task 2682 | total time = 51512.17 ms / 1503 tokens 4.22.238.330 I slot print_timing: id 2 | task 2682 | graphs reused = 3279 4.22.238.331 I slot print_timing: id 2 | task 2682 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.238.451 I slot release: id 2 | task 2682 | stop processing: n_tokens = 2166, truncated = 0 4.22.287.115 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.493 4.22.293.293 I slot launch_slot_: id 2 | task 3668 | processing task, is_child = 0 4.24.340.402 I slot print_timing: id 1 | task 3594 | n_gen = 100, tg = 18.17 t/s, tg_3s = 18.36 t/s 4.24.918.942 I slot print_timing: id 3 | task 3204 | n_gen = 500, tg = 19.32 t/s, tg_3s = 15.91 t/s 4.25.061.468 I slot print_timing: id 0 | task 3386 | n_gen = 322, tg = 19.21 t/s, tg_3s = 15.91 t/s 4.27.223.886 I slot print_timing: id 0 | task 3386 | prompt eval time = 763.32 ms / 475 tokens ( 1.61 ms per token, 622.28 tokens per second) 4.27.223.894 I slot print_timing: id 0 | task 3386 | eval time = 18872.63 ms / 367 tokens ( 51.56 ms per token, 19.39 tokens per second) 4.27.223.895 I slot print_timing: id 0 | task 3386 | total time = 19635.95 ms / 842 tokens 4.27.223.896 I slot print_timing: id 0 | task 3386 | graphs reused = 3364 4.27.223.896 I slot print_timing: id 0 | task 3386 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.224.015 I slot release: id 0 | task 3386 | stop processing: n_tokens = 1511, truncated = 0 4.27.267.056 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.707 4.27.267.099 I slot launch_slot_: id 0 | task 3758 | processing task, is_child = 0 4.27.940.997 I slot print_timing: id 1 | task 3594 | n_gen = 162, tg = 17.79 t/s, tg_3s = 17.22 t/s 4.27.941.587 I slot print_timing: id 3 | task 3204 | n_gen = 550, tg = 19.03 t/s, tg_3s = 16.54 t/s 4.28.488.907 I slot print_timing: id 2 | task 3668 | n_gen = 100, tg = 18.42 t/s, tg_3s = 18.60 t/s 4.30.942.131 I slot print_timing: id 3 | task 3204 | n_gen = 613, tg = 19.21 t/s, tg_3s = 21.00 t/s 4.30.988.654 I slot print_timing: id 1 | task 3594 | n_gen = 226, tg = 18.60 t/s, tg_3s = 21.00 t/s 4.31.512.376 I slot print_timing: id 2 | task 3668 | n_gen = 164, tg = 19.41 t/s, tg_3s = 21.17 t/s 4.32.227.697 I slot print_timing: id 3 | task 3204 | prompt eval time = 734.02 ms / 433 tokens ( 1.70 ms per token, 589.90 tokens per second) 4.32.227.705 I slot print_timing: id 3 | task 3204 | eval time = 33140.43 ms / 640 tokens ( 51.86 ms per token, 19.28 tokens per second) 4.32.227.708 I slot print_timing: id 3 | task 3204 | total time = 33874.45 ms / 1073 tokens 4.32.227.708 I slot print_timing: id 3 | task 3204 | graphs reused = 3453 4.32.227.709 I slot print_timing: id 3 | task 3204 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.227.831 I slot release: id 3 | task 3204 | stop processing: n_tokens = 1767, truncated = 0 4.32.268.634 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.604 4.32.268.682 I slot launch_slot_: id 3 | task 3851 | processing task, is_child = 0 4.33.334.058 I slot print_timing: id 0 | task 3758 | n_gen = 100, tg = 18.63 t/s, tg_3s = 18.82 t/s 4.34.035.108 I slot print_timing: id 1 | task 3594 | n_gen = 277, tg = 18.23 t/s, tg_3s = 16.74 t/s 4.34.514.053 I slot print_timing: id 2 | task 3668 | n_gen = 214, tg = 18.68 t/s, tg_3s = 16.66 t/s 4.36.376.395 I slot print_timing: id 0 | task 3758 | n_gen = 164, tg = 19.51 t/s, tg_3s = 21.04 t/s 4.37.045.096 I slot print_timing: id 1 | task 3594 | n_gen = 340, tg = 18.68 t/s, tg_3s = 20.93 t/s 4.37.523.227 I slot print_timing: id 2 | task 3668 | n_gen = 277, tg = 19.15 t/s, tg_3s = 20.94 t/s 4.37.715.588 I slot print_timing: id 3 | task 3851 | n_gen = 100, tg = 21.03 t/s, tg_3s = 21.25 t/s 4.39.392.863 I slot print_timing: id 0 | task 3758 | n_gen = 227, tg = 19.87 t/s, tg_3s = 20.89 t/s 4.40.066.971 I slot print_timing: id 1 | task 3594 | n_gen = 403, tg = 18.99 t/s, tg_3s = 20.85 t/s 4.40.547.724 I slot print_timing: id 2 | task 3668 | n_gen = 340, tg = 19.44 t/s, tg_3s = 20.83 t/s 4.40.740.405 I slot print_timing: id 3 | task 3851 | n_gen = 163, tg = 20.95 t/s, tg_3s = 20.83 t/s 4.41.603.238 I slot print_timing: id 1 | task 3594 | prompt eval time = 796.84 ms / 484 tokens ( 1.65 ms per token, 607.40 tokens per second) 4.41.603.245 I slot print_timing: id 1 | task 3594 | eval time = 22710.73 ms / 435 tokens ( 52.33 ms per token, 19.11 tokens per second) 4.41.603.246 I slot print_timing: id 1 | task 3594 | total time = 23507.57 ms / 919 tokens 4.41.603.247 I slot print_timing: id 1 | task 3594 | graphs reused = 3631 4.41.603.248 I slot print_timing: id 1 | task 3594 | graph reallocs = 0 / 0 (same size) / (changed size) 4.41.603.383 I slot release: id 1 | task 3594 | stop processing: n_tokens = 1572, truncated = 0 4.41.652.416 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.679 4.41.652.456 I slot launch_slot_: id 1 | task 4035 | processing task, is_child = 0 4.42.441.829 I slot print_timing: id 0 | task 3758 | n_gen = 276, tg = 19.07 t/s, tg_3s = 16.07 t/s 4.43.561.041 I slot print_timing: id 2 | task 3668 | n_gen = 389, tg = 18.98 t/s, tg_3s = 16.26 t/s 4.43.747.512 I slot print_timing: id 3 | task 3851 | n_gen = 212, tg = 19.65 t/s, tg_3s = 16.29 t/s 4.45.472.494 I slot print_timing: id 0 | task 3758 | n_gen = 340, tg = 19.42 t/s, tg_3s = 21.12 t/s 4.46.573.686 I slot print_timing: id 2 | task 3668 | n_gen = 452, tg = 19.22 t/s, tg_3s = 20.91 t/s 4.46.765.638 I slot print_timing: id 3 | task 3851 | n_gen = 275, tg = 19.92 t/s, tg_3s = 20.87 t/s 4.47.146.794 I slot print_timing: id 1 | task 4035 | n_gen = 100, tg = 21.04 t/s, tg_3s = 21.26 t/s 4.48.486.888 I slot print_timing: id 0 | task 3758 | n_gen = 403, tg = 19.64 t/s, tg_3s = 20.90 t/s 4.49.586.732 I slot print_timing: id 2 | task 3668 | n_gen = 515, tg = 19.42 t/s, tg_3s = 20.91 t/s 4.49.778.537 I slot print_timing: id 3 | task 3851 | n_gen = 338, tg = 20.10 t/s, tg_3s = 20.91 t/s 4.50.159.833 I slot print_timing: id 1 | task 4035 | n_gen = 163, tg = 20.99 t/s, tg_3s = 20.91 t/s 4.50.879.220 I slot print_timing: id 3 | task 3851 | prompt eval time = 740.46 ms / 442 tokens ( 1.68 ms per token, 596.93 tokens per second) 4.50.879.228 I slot print_timing: id 3 | task 3851 | eval time = 17870.07 ms / 361 tokens ( 49.64 ms per token, 20.15 tokens per second) 4.50.879.229 I slot print_timing: id 3 | task 3851 | total time = 18610.53 ms / 803 tokens 4.50.879.229 I slot print_timing: id 3 | task 3851 | graphs reused = 3807 4.50.879.230 I slot print_timing: id 3 | task 3851 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.879.340 I slot release: id 3 | task 3851 | stop processing: n_tokens = 1497, truncated = 0 4.50.919.858 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.713 4.50.919.893 I slot launch_slot_: id 3 | task 4216 | processing task, is_child = 0 4.51.617.487 I slot print_timing: id 0 | task 3758 | n_gen = 455, tg = 19.24 t/s, tg_3s = 16.61 t/s 4.52.633.542 I slot print_timing: id 2 | task 3668 | n_gen = 565, tg = 19.11 t/s, tg_3s = 16.41 t/s 4.53.193.217 I slot print_timing: id 1 | task 4035 | n_gen = 213, tg = 19.72 t/s, tg_3s = 16.48 t/s 4.54.655.252 I slot print_timing: id 0 | task 3758 | n_gen = 519, tg = 19.45 t/s, tg_3s = 21.07 t/s 4.55.665.920 I slot print_timing: id 2 | task 3668 | n_gen = 629, tg = 19.29 t/s, tg_3s = 21.11 t/s 4.56.238.200 I slot print_timing: id 1 | task 4035 | n_gen = 277, tg = 20.01 t/s, tg_3s = 21.02 t/s 4.56.382.807 I slot print_timing: id 3 | task 4216 | n_gen = 100, tg = 21.14 t/s, tg_3s = 21.35 t/s 4.57.672.703 I slot print_timing: id 0 | task 3758 | n_gen = 582, tg = 19.59 t/s, tg_3s = 20.88 t/s 4.58.434.888 I slot print_timing: id 1 | task 4035 | prompt eval time = 789.70 ms / 476 tokens ( 1.66 ms per token, 602.76 tokens per second) 4.58.434.895 I slot print_timing: id 1 | task 4035 | eval time = 15992.73 ms / 323 tokens ( 49.67 ms per token, 20.13 tokens per second) 4.58.434.896 I slot print_timing: id 1 | task 4035 | total time = 16782.42 ms / 799 tokens 4.58.434.897 I slot print_timing: id 1 | task 4035 | graphs reused = 3947 4.58.434.898 I slot print_timing: id 1 | task 4035 | graph reallocs = 0 / 0 (same size) / (changed size) 4.58.435.021 I slot release: id 1 | task 4035 | stop processing: n_tokens = 1452, truncated = 0 4.58.484.639 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.736 4.58.484.674 I slot launch_slot_: id 1 | task 4362 | processing task, is_child = 0 4.59.329.763 I slot print_timing: id 2 | task 3668 | n_gen = 690, tg = 19.02 t/s, tg_3s = 16.65 t/s 4.59.419.243 I slot print_timing: id 3 | task 4216 | n_gen = 147, tg = 18.91 t/s, tg_3s = 15.48 t/s 5.00.701.270 I slot print_timing: id 0 | task 3758 | n_gen = 629, tg = 19.22 t/s, tg_3s = 15.52 t/s 5.02.334.831 I slot print_timing: id 2 | task 3668 | n_gen = 752, tg = 19.15 t/s, tg_3s = 20.63 t/s 5.02.431.120 I slot print_timing: id 3 | task 4216 | n_gen = 210, tg = 19.48 t/s, tg_3s = 20.92 t/s 5.03.726.389 I slot print_timing: id 0 | task 3758 | n_gen = 692, tg = 19.35 t/s, tg_3s = 20.83 t/s 5.04.158.017 I slot print_timing: id 1 | task 4362 | n_gen = 100, tg = 20.89 t/s, tg_3s = 21.10 t/s 5.05.359.326 I slot print_timing: id 2 | task 3668 | n_gen = 815, tg = 19.27 t/s, tg_3s = 20.83 t/s 5.05.456.133 I slot print_timing: id 3 | task 4216 | n_gen = 273, tg = 19.77 t/s, tg_3s = 20.83 t/s 5.06.750.023 I slot print_timing: id 0 | task 3758 | n_gen = 755, tg = 19.47 t/s, tg_3s = 20.84 t/s 5.07.180.849 I slot print_timing: id 1 | task 4362 | n_gen = 163, tg = 20.87 t/s, tg_3s = 20.84 t/s 5.08.383.325 I slot print_timing: id 2 | task 3668 | n_gen = 878, tg = 19.37 t/s, tg_3s = 20.83 t/s 5.08.480.259 I slot print_timing: id 3 | task 4216 | n_gen = 336, tg = 19.96 t/s, tg_3s = 20.83 t/s 5.09.776.949 I slot print_timing: id 0 | task 3758 | n_gen = 818, tg = 19.57 t/s, tg_3s = 20.81 t/s 5.10.209.934 I slot print_timing: id 1 | task 4362 | n_gen = 226, tg = 20.85 t/s, tg_3s = 20.80 t/s 5.11.409.482 I slot print_timing: id 2 | task 3668 | n_gen = 941, tg = 19.46 t/s, tg_3s = 20.82 t/s 5.11.506.441 I slot print_timing: id 3 | task 4216 | n_gen = 399, tg = 20.09 t/s, tg_3s = 20.82 t/s 5.12.176.892 I slot print_timing: id 0 | task 3758 | prompt eval time = 752.95 ms / 463 tokens ( 1.63 ms per token, 614.91 tokens per second) 5.12.176.899 I slot print_timing: id 0 | task 3758 | eval time = 44156.83 ms / 868 tokens ( 50.93 ms per token, 19.63 tokens per second) 5.12.176.900 I slot print_timing: id 0 | task 3758 | total time = 44909.78 ms / 1331 tokens 5.12.176.901 I slot print_timing: id 0 | task 3758 | graphs reused = 4211 5.12.176.902 I slot print_timing: id 0 | task 3758 | graph reallocs = 0 / 0 (same size) / (changed size) 5.12.177.015 I slot release: id 0 | task 3758 | stop processing: n_tokens = 2000, truncated = 0 5.12.219.636 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.534 5.12.219.679 I slot launch_slot_: id 0 | task 4633 | processing task, is_child = 0 5.13.240.682 I slot print_timing: id 1 | task 4362 | n_gen = 274, tg = 19.75 t/s, tg_3s = 15.84 t/s 5.14.455.070 I slot print_timing: id 2 | task 3668 | n_gen = 990, tg = 19.26 t/s, tg_3s = 16.09 t/s 5.14.548.788 I slot print_timing: id 3 | task 4216 | n_gen = 448, tg = 19.56 t/s, tg_3s = 16.11 t/s 5.16.040.624 I slot print_timing: id 2 | task 3668 | prompt eval time = 820.28 ms / 505 tokens ( 1.62 ms per token, 615.64 tokens per second) 5.16.040.630 I slot print_timing: id 2 | task 3668 | eval time = 52927.04 ms / 1024 tokens ( 51.74 ms per token, 19.33 tokens per second) 5.16.040.630 I slot print_timing: id 2 | task 3668 | total time = 53747.32 ms / 1529 tokens 5.16.040.630 I slot print_timing: id 2 | task 3668 | graphs reused = 4274 5.16.040.631 I slot print_timing: id 2 | task 3668 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.040.706 I slot release: id 2 | task 3668 | stop processing: n_tokens = 2203, truncated = 0 5.16.086.205 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.485 5.16.092.953 I slot launch_slot_: id 2 | task 4701 | processing task, is_child = 0 5.16.818.692 I slot print_timing: id 1 | task 4362 | n_gen = 336, tg = 19.25 t/s, tg_3s = 17.33 t/s 5.17.558.463 I slot print_timing: id 3 | task 4216 | n_gen = 497, tg = 19.18 t/s, tg_3s = 16.28 t/s 5.18.457.090 I slot print_timing: id 0 | task 4633 | n_gen = 100, tg = 18.48 t/s, tg_3s = 18.66 t/s 5.19.840.685 I slot print_timing: id 1 | task 4362 | n_gen = 399, tg = 19.49 t/s, tg_3s = 20.85 t/s 5.20.604.618 I slot print_timing: id 3 | task 4216 | n_gen = 561, tg = 19.37 t/s, tg_3s = 21.01 t/s 5.21.462.930 I slot print_timing: id 0 | task 4633 | n_gen = 163, tg = 19.37 t/s, tg_3s = 20.96 t/s 5.21.608.660 I slot print_timing: id 2 | task 4701 | n_gen = 100, tg = 21.06 t/s, tg_3s = 21.27 t/s 5.22.857.515 I slot print_timing: id 1 | task 4362 | n_gen = 462, tg = 19.67 t/s, tg_3s = 20.88 t/s 5.23.631.333 I slot print_timing: id 3 | task 4216 | n_gen = 624, tg = 19.51 t/s, tg_3s = 20.81 t/s 5.24.494.519 I slot print_timing: id 0 | task 4633 | n_gen = 226, tg = 19.74 t/s, tg_3s = 20.78 t/s 5.24.640.530 I slot print_timing: id 2 | task 4701 | n_gen = 163, tg = 20.95 t/s, tg_3s = 20.78 t/s 5.25.893.878 I slot print_timing: id 1 | task 4362 | n_gen = 525, tg = 19.79 t/s, tg_3s = 20.75 t/s 5.26.665.213 I slot print_timing: id 3 | task 4216 | n_gen = 687, tg = 19.62 t/s, tg_3s = 20.77 t/s 5.27.525.736 I slot print_timing: id 0 | task 4633 | n_gen = 289, tg = 19.96 t/s, tg_3s = 20.78 t/s 5.27.670.943 I slot print_timing: id 2 | task 4701 | n_gen = 226, tg = 20.90 t/s, tg_3s = 20.79 t/s 5.28.922.108 I slot print_timing: id 1 | task 4362 | n_gen = 588, tg = 19.90 t/s, tg_3s = 20.80 t/s 5.29.693.992 I slot print_timing: id 3 | task 4216 | n_gen = 750, tg = 19.71 t/s, tg_3s = 20.80 t/s 5.30.559.586 I slot print_timing: id 0 | task 4633 | n_gen = 352, tg = 20.10 t/s, tg_3s = 20.77 t/s 5.30.705.296 I slot print_timing: id 2 | task 4701 | n_gen = 289, tg = 20.87 t/s, tg_3s = 20.76 t/s 5.31.954.372 I slot print_timing: id 1 | task 4362 | n_gen = 651, tg = 19.98 t/s, tg_3s = 20.78 t/s 5.32.727.726 I slot print_timing: id 3 | task 4216 | n_gen = 813, tg = 19.79 t/s, tg_3s = 20.77 t/s 5.33.593.059 I slot print_timing: id 0 | task 4633 | n_gen = 415, tg = 20.20 t/s, tg_3s = 20.77 t/s 5.33.740.073 I slot print_timing: id 2 | task 4701 | n_gen = 352, tg = 20.85 t/s, tg_3s = 20.76 t/s 5.34.992.450 I slot print_timing: id 1 | task 4362 | n_gen = 714, tg = 20.04 t/s, tg_3s = 20.74 t/s 5.35.763.676 I slot print_timing: id 3 | task 4216 | n_gen = 876, tg = 19.86 t/s, tg_3s = 20.75 t/s 5.35.911.199 I slot print_timing: id 2 | task 4701 | prompt eval time = 814.35 ms / 494 tokens ( 1.65 ms per token, 606.62 tokens per second) 5.35.911.205 I slot print_timing: id 2 | task 4701 | eval time = 19003.89 ms / 397 tokens ( 47.99 ms per token, 20.84 tokens per second) 5.35.911.206 I slot print_timing: id 2 | task 4701 | total time = 19818.23 ms / 891 tokens 5.35.911.207 I slot print_timing: id 2 | task 4701 | graphs reused = 4667 5.35.911.208 I slot print_timing: id 2 | task 4701 | graph reallocs = 0 / 0 (same size) / (changed size) 5.35.911.345 I slot release: id 2 | task 4701 | stop processing: n_tokens = 1533, truncated = 0 5.35.960.664 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.697 5.35.960.706 I slot launch_slot_: id 2 | task 5101 | processing task, is_child = 0 5.36.680.896 I slot print_timing: id 0 | task 4633 | n_gen = 465, tg = 19.68 t/s, tg_3s = 16.19 t/s 5.38.022.267 I slot print_timing: id 1 | task 4362 | n_gen = 762, tg = 19.71 t/s, tg_3s = 15.84 t/s 5.38.795.064 I slot print_timing: id 3 | task 4216 | n_gen = 924, tg = 19.60 t/s, tg_3s = 15.83 t/s 5.39.707.369 I slot print_timing: id 0 | task 4633 | n_gen = 527, tg = 19.77 t/s, tg_3s = 20.49 t/s 5.41.056.458 I slot print_timing: id 1 | task 4362 | n_gen = 825, tg = 19.79 t/s, tg_3s = 20.76 t/s 5.41.540.098 I slot print_timing: id 2 | task 5101 | n_gen = 100, tg = 20.75 t/s, tg_3s = 20.96 t/s 5.41.830.862 I slot print_timing: id 3 | task 4216 | n_gen = 987, tg = 19.67 t/s, tg_3s = 20.75 t/s 5.42.745.813 I slot print_timing: id 0 | task 4633 | n_gen = 590, tg = 19.87 t/s, tg_3s = 20.73 t/s 5.43.615.321 I slot print_timing: id 3 | task 4216 | prompt eval time = 779.99 ms / 478 tokens ( 1.63 ms per token, 612.83 tokens per second) 5.43.615.329 I slot print_timing: id 3 | task 4216 | eval time = 51915.42 ms / 1024 tokens ( 50.75 ms per token, 19.71 tokens per second) 5.43.615.332 I slot print_timing: id 3 | task 4216 | total time = 52695.42 ms / 1502 tokens 5.43.615.333 I slot print_timing: id 3 | task 4216 | graphs reused = 4808 5.43.615.334 I slot print_timing: id 3 | task 4216 | graph reallocs = 0 / 0 (same size) / (changed size) 5.43.615.473 I slot release: id 3 | task 4216 | stop processing: n_tokens = 2196, truncated = 0 5.43.656.514 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 5.43.662.724 I slot launch_slot_: id 3 | task 5247 | processing task, is_child = 0 5.44.325.038 I slot print_timing: id 1 | task 4362 | n_gen = 880, tg = 19.57 t/s, tg_3s = 16.83 t/s 5.44.548.186 I slot print_timing: id 2 | task 5101 | n_gen = 149, tg = 19.03 t/s, tg_3s = 16.29 t/s 5.45.748.094 I slot print_timing: id 0 | task 4633 | n_gen = 639, tg = 19.54 t/s, tg_3s = 16.32 t/s 5.47.339.659 I slot print_timing: id 1 | task 4362 | n_gen = 942, tg = 19.64 t/s, tg_3s = 20.57 t/s 5.47.579.871 I slot print_timing: id 2 | task 5101 | n_gen = 212, tg = 19.52 t/s, tg_3s = 20.78 t/s 5.48.780.820 I slot print_timing: id 0 | task 4633 | n_gen = 702, tg = 19.65 t/s, tg_3s = 20.77 t/s 5.49.167.995 I slot print_timing: id 3 | task 5247 | n_gen = 100, tg = 20.80 t/s, tg_3s = 21.01 t/s 5.50.371.714 I slot print_timing: id 1 | task 4362 | n_gen = 1005, tg = 19.70 t/s, tg_3s = 20.78 t/s 5.50.613.031 I slot print_timing: id 2 | task 5101 | n_gen = 275, tg = 19.79 t/s, tg_3s = 20.77 t/s 5.51.283.381 I slot print_timing: id 1 | task 4362 | prompt eval time = 933.99 ms / 522 tokens ( 1.79 ms per token, 558.89 tokens per second) 5.51.283.390 I slot print_timing: id 1 | task 4362 | eval time = 51864.70 ms / 1024 tokens ( 50.70 ms per token, 19.72 tokens per second) 5.51.283.391 I slot print_timing: id 1 | task 4362 | total time = 52798.70 ms / 1546 tokens 5.51.283.392 I slot print_timing: id 1 | task 4362 | graphs reused = 4950 5.51.283.393 I slot print_timing: id 1 | task 4362 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.283.537 I slot release: id 1 | task 4362 | stop processing: n_tokens = 2199, truncated = 0 5.51.333.176 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.486 5.51.339.976 I slot launch_slot_: id 1 | task 5394 | processing task, is_child = 0 5.52.061.009 I slot print_timing: id 0 | task 4633 | n_gen = 756, tg = 19.38 t/s, tg_3s = 16.46 t/s 5.52.197.532 I slot print_timing: id 3 | task 5247 | n_gen = 148, tg = 18.87 t/s, tg_3s = 15.84 t/s 5.53.640.211 I slot print_timing: id 2 | task 5101 | n_gen = 324, tg = 19.15 t/s, tg_3s = 16.19 t/s 5.55.090.847 I slot print_timing: id 0 | task 4633 | n_gen = 819, tg = 19.48 t/s, tg_3s = 20.79 t/s 5.55.237.728 I slot print_timing: id 3 | task 5247 | n_gen = 212, tg = 19.48 t/s, tg_3s = 21.05 t/s 5.56.684.053 I slot print_timing: id 2 | task 5101 | n_gen = 387, tg = 19.38 t/s, tg_3s = 20.70 t/s 5.56.875.775 I slot print_timing: id 1 | task 5394 | n_gen = 100, tg = 20.95 t/s, tg_3s = 21.16 t/s 5.58.125.558 I slot print_timing: id 0 | task 4633 | n_gen = 882, tg = 19.57 t/s, tg_3s = 20.76 t/s 5.58.270.681 I slot print_timing: id 3 | task 5247 | n_gen = 275, tg = 19.76 t/s, tg_3s = 20.77 t/s 5.59.277.507 I slot print_timing: id 2 | task 5101 | prompt eval time = 809.15 ms / 488 tokens ( 1.66 ms per token, 603.10 tokens per second) 5.59.277.516 I slot print_timing: id 2 | task 5101 | eval time = 22507.64 ms / 441 tokens ( 51.15 ms per token, 19.55 tokens per second) 5.59.277.517 I slot print_timing: id 2 | task 5101 | total time = 23316.79 ms / 929 tokens 5.59.277.517 I slot print_timing: id 2 | task 5101 | graphs reused = 5097 5.59.277.518 I slot print_timing: id 2 | task 5101 | graph reallocs = 0 / 0 (same size) / (changed size) 5.59.277.627 I slot release: id 2 | task 5101 | stop processing: n_tokens = 1571, truncated = 0 5.59.326.485 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.680 5.59.326.525 I slot launch_slot_: id 2 | task 5547 | processing task, is_child = 0 6.00.065.316 I slot print_timing: id 1 | task 5394 | n_gen = 152, tg = 19.08 t/s, tg_3s = 16.30 t/s 6.01.133.144 I slot print_timing: id 0 | task 4633 | n_gen = 930, tg = 19.34 t/s, tg_3s = 15.96 t/s 6.01.273.991 I slot print_timing: id 3 | task 5247 | n_gen = 323, tg = 19.09 t/s, tg_3s = 15.98 t/s 6.03.071.971 I slot print_timing: id 1 | task 5394 | n_gen = 215, tg = 19.59 t/s, tg_3s = 20.95 t/s 6.04.180.782 I slot print_timing: id 0 | task 4633 | n_gen = 994, tg = 19.44 t/s, tg_3s = 21.00 t/s 6.04.279.809 I slot print_timing: id 3 | task 5247 | n_gen = 386, tg = 19.37 t/s, tg_3s = 20.96 t/s 6.04.857.323 I slot print_timing: id 2 | task 5547 | n_gen = 100, tg = 21.05 t/s, tg_3s = 21.26 t/s 6.05.291.686 I slot print_timing: id 3 | task 5247 | prompt eval time = 744.61 ms / 448 tokens ( 1.66 ms per token, 601.66 tokens per second) 6.05.291.691 I slot print_timing: id 3 | task 5247 | eval time = 20884.34 ms / 407 tokens ( 51.44 ms per token, 19.44 tokens per second) 6.05.291.694 I slot print_timing: id 3 | task 5247 | total time = 21628.94 ms / 855 tokens 6.05.291.694 I slot print_timing: id 3 | task 5247 | graphs reused = 5204 6.05.291.695 I slot print_timing: id 3 | task 5247 | graph reallocs = 0 / 0 (same size) / (changed size) 6.05.291.826 I slot release: id 3 | task 5247 | stop processing: n_tokens = 1549, truncated = 0 6.05.333.009 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.689 6.05.333.040 I slot launch_slot_: id 3 | task 5659 | processing task, is_child = 0 6.06.105.230 I slot print_timing: id 1 | task 5394 | n_gen = 264, tg = 18.85 t/s, tg_3s = 16.15 t/s 6.06.293.258 I slot print_timing: id 0 | task 4633 | prompt eval time = 878.93 ms / 519 tokens ( 1.69 ms per token, 590.49 tokens per second) 6.06.293.263 I slot print_timing: id 0 | task 4633 | eval time = 53194.65 ms / 1024 tokens ( 52.00 ms per token, 19.23 tokens per second) 6.06.293.264 I slot print_timing: id 0 | task 4633 | total time = 54073.57 ms / 1543 tokens 6.06.293.264 I slot print_timing: id 0 | task 4633 | graphs reused = 5207 6.06.293.265 I slot print_timing: id 0 | task 4633 | graph reallocs = 0 / 0 (same size) / (changed size) 6.06.293.324 I slot release: id 0 | task 4633 | stop processing: n_tokens = 2212, truncated = 0 6.06.332.839 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.483 6.06.337.674 I slot launch_slot_: id 0 | task 5667 | processing task, is_child = 0 6.07.885.006 I slot print_timing: id 2 | task 5547 | n_gen = 136, tg = 17.46 t/s, tg_3s = 11.89 t/s 6.09.123.917 I slot print_timing: id 1 | task 5394 | n_gen = 314, tg = 18.44 t/s, tg_3s = 16.56 t/s 6.10.894.974 I slot print_timing: id 2 | task 5547 | n_gen = 199, tg = 18.43 t/s, tg_3s = 20.93 t/s 6.11.469.742 I slot print_timing: id 3 | task 5659 | n_gen = 100, tg = 18.46 t/s, tg_3s = 18.64 t/s 6.11.802.985 I slot print_timing: id 0 | task 5667 | n_gen = 100, tg = 21.01 t/s, tg_3s = 21.23 t/s 6.12.138.985 I slot print_timing: id 1 | task 5394 | n_gen = 377, tg = 18.81 t/s, tg_3s = 20.90 t/s 6.13.911.929 I slot print_timing: id 2 | task 5547 | n_gen = 262, tg = 18.97 t/s, tg_3s = 20.88 t/s 6.14.487.416 I slot print_timing: id 3 | task 5659 | n_gen = 163, tg = 19.33 t/s, tg_3s = 20.88 t/s 6.14.822.015 I slot print_timing: id 0 | task 5667 | n_gen = 163, tg = 20.96 t/s, tg_3s = 20.87 t/s 6.15.157.411 I slot print_timing: id 1 | task 5394 | n_gen = 440, tg = 19.08 t/s, tg_3s = 20.87 t/s 6.16.937.007 I slot print_timing: id 2 | task 5547 | n_gen = 325, tg = 19.30 t/s, tg_3s = 20.83 t/s 6.17.514.519 I slot print_timing: id 3 | task 5659 | n_gen = 226, tg = 19.72 t/s, tg_3s = 20.81 t/s 6.17.849.897 I slot print_timing: id 0 | task 5667 | n_gen = 226, tg = 20.91 t/s, tg_3s = 20.81 t/s 6.18.187.250 I slot print_timing: id 1 | task 5394 | n_gen = 503, tg = 19.28 t/s, tg_3s = 20.79 t/s 6.19.959.363 I slot print_timing: id 2 | task 5547 | n_gen = 388, tg = 19.54 t/s, tg_3s = 20.84 t/s 6.20.532.188 I slot print_timing: id 3 | task 5659 | n_gen = 289, tg = 19.96 t/s, tg_3s = 20.88 t/s 6.20.866.114 I slot print_timing: id 0 | task 5667 | n_gen = 289, tg = 20.91 t/s, tg_3s = 20.89 t/s 6.21.200.225 I slot print_timing: id 1 | task 5394 | n_gen = 566, tg = 19.45 t/s, tg_3s = 20.91 t/s 6.22.105.545 I slot print_timing: id 2 | task 5547 | prompt eval time = 826.97 ms / 510 tokens ( 1.62 ms per token, 616.71 tokens per second) 6.22.105.555 I slot print_timing: id 2 | task 5547 | eval time = 21952.04 ms / 433 tokens ( 50.81 ms per token, 19.68 tokens per second) 6.22.105.556 I slot print_timing: id 2 | task 5547 | total time = 22779.00 ms / 943 tokens 6.22.105.557 I slot print_timing: id 2 | task 5547 | graphs reused = 5520 6.22.105.558 I slot print_timing: id 2 | task 5547 | graph reallocs = 0 / 0 (same size) / (changed size) 6.22.105.722 I slot release: id 2 | task 5547 | stop processing: n_tokens = 1585, truncated = 0 6.22.154.972 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.674 6.22.155.008 I slot launch_slot_: id 2 | task 5985 | processing task, is_child = 0 6.23.541.334 I slot print_timing: id 3 | task 5659 | n_gen = 337, tg = 19.27 t/s, tg_3s = 15.95 t/s 6.23.819.793 I slot print_timing: id 1 | task 5394 | prompt eval time = 809.41 ms / 488 tokens ( 1.66 ms per token, 602.91 tokens per second) 6.23.819.798 I slot print_timing: id 1 | task 5394 | eval time = 31670.39 ms / 606 tokens ( 52.35 ms per token, 19.10 tokens per second) 6.23.819.798 I slot print_timing: id 1 | task 5394 | total time = 32479.80 ms / 1094 tokens 6.23.819.799 I slot print_timing: id 1 | task 5394 | graphs reused = 5537 6.23.819.799 I slot print_timing: id 1 | task 5394 | graph reallocs = 0 / 0 (same size) / (changed size) 6.23.819.862 I slot release: id 1 | task 5394 | stop processing: n_tokens = 1753, truncated = 0 6.23.865.658 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.609 6.23.865.683 I slot launch_slot_: id 1 | task 6007 | processing task, is_child = 0 6.24.011.536 I slot print_timing: id 0 | task 5667 | n_gen = 338, tg = 19.92 t/s, tg_3s = 15.58 t/s 6.26.564.831 I slot print_timing: id 3 | task 5659 | n_gen = 384, tg = 18.72 t/s, tg_3s = 15.54 t/s 6.27.033.861 I slot print_timing: id 0 | task 5667 | n_gen = 387, tg = 19.36 t/s, tg_3s = 16.21 t/s 6.28.469.752 I slot print_timing: id 2 | task 5985 | n_gen = 100, tg = 18.04 t/s, tg_3s = 18.22 t/s 6.29.521.856 I slot print_timing: id 1 | task 6007 | n_gen = 100, tg = 21.15 t/s, tg_3s = 21.36 t/s 6.29.570.962 I slot print_timing: id 3 | task 5659 | n_gen = 447, tg = 19.01 t/s, tg_3s = 20.96 t/s 6.30.047.432 I slot print_timing: id 0 | task 5667 | n_gen = 450, tg = 19.56 t/s, tg_3s = 20.91 t/s 6.30.573.517 I slot print_timing: id 3 | task 5659 | prompt eval time = 772.71 ms / 471 tokens ( 1.64 ms per token, 609.54 tokens per second) 6.30.573.525 I slot print_timing: id 3 | task 5659 | eval time = 24467.76 ms / 468 tokens ( 52.39 ms per token, 19.09 tokens per second) 6.30.573.525 I slot print_timing: id 3 | task 5659 | total time = 25240.47 ms / 939 tokens 6.30.573.526 I slot print_timing: id 3 | task 5659 | graphs reused = 5656 6.30.573.527 I slot print_timing: id 3 | task 5659 | graph reallocs = 0 / 0 (same size) / (changed size) 6.30.573.642 I slot release: id 3 | task 5659 | stop processing: n_tokens = 1633, truncated = 0 6.30.614.574 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.654 6.30.614.612 I slot launch_slot_: id 3 | task 6133 | processing task, is_child = 0 6.31.489.672 I slot print_timing: id 2 | task 5985 | n_gen = 149, tg = 17.39 t/s, tg_3s = 16.23 t/s 6.32.559.730 I slot print_timing: id 1 | task 6007 | n_gen = 150, tg = 19.30 t/s, tg_3s = 16.46 t/s 6.33.086.802 I slot print_timing: id 0 | task 5667 | n_gen = 500, tg = 19.20 t/s, tg_3s = 16.45 t/s 6.34.526.461 I slot print_timing: id 2 | task 5985 | n_gen = 213, tg = 18.36 t/s, tg_3s = 21.07 t/s 6.35.579.180 I slot print_timing: id 1 | task 6007 | n_gen = 213, tg = 19.74 t/s, tg_3s = 20.86 t/s 6.36.106.050 I slot print_timing: id 0 | task 5667 | n_gen = 563, tg = 19.37 t/s, tg_3s = 20.87 t/s 6.36.107.965 I slot print_timing: id 3 | task 6133 | n_gen = 100, tg = 21.01 t/s, tg_3s = 21.22 t/s 6.37.543.446 I slot print_timing: id 2 | task 5985 | n_gen = 276, tg = 18.88 t/s, tg_3s = 20.88 t/s 6.38.593.578 I slot print_timing: id 1 | task 6007 | n_gen = 276, tg = 20.00 t/s, tg_3s = 20.90 t/s 6.39.117.470 I slot print_timing: id 0 | task 5667 | n_gen = 626, tg = 19.52 t/s, tg_3s = 20.92 t/s 6.39.119.328 I slot print_timing: id 3 | task 6133 | n_gen = 163, tg = 20.97 t/s, tg_3s = 20.92 t/s 6.40.551.733 I slot print_timing: id 2 | task 5985 | n_gen = 339, tg = 19.24 t/s, tg_3s = 20.94 t/s 6.41.605.783 I slot print_timing: id 1 | task 6007 | n_gen = 339, tg = 20.16 t/s, tg_3s = 20.91 t/s 6.42.132.631 I slot print_timing: id 0 | task 5667 | n_gen = 689, tg = 19.63 t/s, tg_3s = 20.89 t/s 6.42.134.558 I slot print_timing: id 3 | task 6133 | n_gen = 226, tg = 20.95 t/s, tg_3s = 20.89 t/s 6.43.573.633 I slot print_timing: id 2 | task 5985 | n_gen = 402, tg = 19.47 t/s, tg_3s = 20.85 t/s 6.44.626.159 I slot print_timing: id 1 | task 6007 | n_gen = 402, tg = 20.27 t/s, tg_3s = 20.86 t/s 6.45.149.520 I slot print_timing: id 0 | task 5667 | n_gen = 752, tg = 19.73 t/s, tg_3s = 20.88 t/s 6.45.151.481 I slot print_timing: id 3 | task 6133 | n_gen = 289, tg = 20.94 t/s, tg_3s = 20.88 t/s 6.46.589.858 I slot print_timing: id 2 | task 5985 | n_gen = 465, tg = 19.65 t/s, tg_3s = 20.89 t/s 6.47.641.285 I slot print_timing: id 1 | task 6007 | n_gen = 465, tg = 20.35 t/s, tg_3s = 20.89 t/s 6.47.737.641 I slot print_timing: id 2 | task 5985 | prompt eval time = 826.25 ms / 512 tokens ( 1.61 ms per token, 619.66 tokens per second) 6.47.737.649 I slot print_timing: id 2 | task 5985 | eval time = 24756.37 ms / 489 tokens ( 50.73 ms per token, 19.71 tokens per second) 6.47.737.650 I slot print_timing: id 2 | task 5985 | total time = 25582.62 ms / 1001 tokens 6.47.737.651 I slot print_timing: id 2 | task 5985 | graphs reused = 5996 6.47.737.651 I slot print_timing: id 2 | task 5985 | graph reallocs = 0 / 0 (same size) / (changed size) 6.47.737.769 I slot release: id 2 | task 5985 | stop processing: n_tokens = 1643, truncated = 0 6.47.786.258 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.650 6.47.786.299 I slot launch_slot_: id 2 | task 6479 | processing task, is_child = 0 6.48.526.626 I slot print_timing: id 0 | task 5667 | n_gen = 808, tg = 19.48 t/s, tg_3s = 16.58 t/s 6.48.527.161 I slot print_timing: id 3 | task 6133 | n_gen = 345, tg = 20.08 t/s, tg_3s = 16.59 t/s 6.50.666.667 I slot print_timing: id 1 | task 6007 | n_gen = 514, tg = 19.86 t/s, tg_3s = 16.20 t/s 6.51.535.192 I slot print_timing: id 0 | task 5667 | n_gen = 871, tg = 19.58 t/s, tg_3s = 20.94 t/s 6.51.537.148 I slot print_timing: id 3 | task 6133 | n_gen = 408, tg = 20.21 t/s, tg_3s = 20.93 t/s 6.53.310.232 I slot print_timing: id 2 | task 6479 | n_gen = 100, tg = 21.09 t/s, tg_3s = 21.30 t/s 6.53.696.790 I slot print_timing: id 1 | task 6007 | n_gen = 577, tg = 19.96 t/s, tg_3s = 20.79 t/s 6.54.560.902 I slot print_timing: id 0 | task 5667 | n_gen = 934, tg = 19.65 t/s, tg_3s = 20.82 t/s 6.54.562.660 I slot print_timing: id 3 | task 6133 | n_gen = 471, tg = 20.29 t/s, tg_3s = 20.82 t/s 6.56.336.953 I slot print_timing: id 2 | task 6479 | n_gen = 163, tg = 20.98 t/s, tg_3s = 20.81 t/s 6.56.720.663 I slot print_timing: id 1 | task 6007 | n_gen = 640, tg = 20.04 t/s, tg_3s = 20.83 t/s 6.57.586.164 I slot print_timing: id 0 | task 5667 | n_gen = 997, tg = 19.72 t/s, tg_3s = 20.82 t/s 6.57.588.092 I slot print_timing: id 3 | task 6133 | n_gen = 534, tg = 20.35 t/s, tg_3s = 20.82 t/s 6.58.886.365 I slot print_timing: id 0 | task 5667 | prompt eval time = 754.10 ms / 464 tokens ( 1.63 ms per token, 615.30 tokens per second) 6.58.886.372 I slot print_timing: id 0 | task 5667 | eval time = 51794.58 ms / 1024 tokens ( 50.63 ms per token, 19.75 tokens per second) 6.58.886.373 I slot print_timing: id 0 | task 5667 | total time = 52548.68 ms / 1488 tokens 6.58.886.374 I slot print_timing: id 0 | task 5667 | graphs reused = 6209 6.58.886.374 I slot print_timing: id 0 | task 5667 | graph reallocs = 0 / 0 (same size) / (changed size) 6.58.886.495 I slot release: id 0 | task 5667 | stop processing: n_tokens = 2160, truncated = 0 6.58.929.056 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.494 6.58.931.386 I slot launch_slot_: id 0 | task 6698 | processing task, is_child = 0 6.59.642.902 I slot print_timing: id 2 | task 6479 | n_gen = 218, tg = 19.68 t/s, tg_3s = 16.64 t/s 6.59.722.240 I slot print_timing: id 1 | task 6007 | n_gen = 688, tg = 19.70 t/s, tg_3s = 15.99 t/s 7.00.609.957 I slot print_timing: id 3 | task 6133 | n_gen = 583, tg = 19.92 t/s, tg_3s = 16.22 t/s 7.02.643.749 I slot print_timing: id 2 | task 6479 | n_gen = 281, tg = 19.96 t/s, tg_3s = 20.99 t/s 7.02.739.049 I slot print_timing: id 1 | task 6007 | n_gen = 752, tg = 19.82 t/s, tg_3s = 21.21 t/s 7.03.655.964 I slot print_timing: id 3 | task 6133 | n_gen = 647, tg = 20.02 t/s, tg_3s = 21.01 t/s 7.04.424.445 I slot print_timing: id 0 | task 6698 | n_gen = 100, tg = 21.05 t/s, tg_3s = 21.27 t/s 7.05.673.948 I slot print_timing: id 2 | task 6479 | n_gen = 344, tg = 20.11 t/s, tg_3s = 20.79 t/s 7.05.768.799 I slot print_timing: id 1 | task 6007 | n_gen = 815, tg = 19.89 t/s, tg_3s = 20.79 t/s 7.06.681.058 I slot print_timing: id 3 | task 6133 | n_gen = 710, tg = 20.09 t/s, tg_3s = 20.83 t/s 7.07.445.732 I slot print_timing: id 0 | task 6698 | n_gen = 163, tg = 20.97 t/s, tg_3s = 20.85 t/s 7.07.734.326 I slot print_timing: id 3 | task 6133 | prompt eval time = 781.10 ms / 478 tokens ( 1.63 ms per token, 611.96 tokens per second) 7.07.734.331 I slot print_timing: id 3 | task 6133 | eval time = 36338.60 ms / 732 tokens ( 49.71 ms per token, 20.12 tokens per second) 7.07.734.332 I slot print_timing: id 3 | task 6133 | total time = 37119.71 ms / 1210 tokens 7.07.734.333 I slot print_timing: id 3 | task 6133 | graphs reused = 6377 7.07.734.333 I slot print_timing: id 3 | task 6133 | graph reallocs = 0 / 0 (same size) / (changed size) 7.07.734.447 I slot release: id 3 | task 6133 | stop processing: n_tokens = 1904, truncated = 0 7.07.775.023 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.561 7.07.775.073 I slot launch_slot_: id 3 | task 6870 | processing task, is_child = 0 7.08.701.259 I slot print_timing: id 2 | task 6479 | n_gen = 393, tg = 19.52 t/s, tg_3s = 16.19 t/s 7.08.794.414 I slot print_timing: id 1 | task 6007 | n_gen = 864, tg = 19.63 t/s, tg_3s = 16.20 t/s 7.10.475.070 I slot print_timing: id 0 | task 6698 | n_gen = 213, tg = 19.72 t/s, tg_3s = 16.51 t/s 7.11.454.332 I slot print_timing: id 2 | task 6479 | prompt eval time = 828.74 ms / 516 tokens ( 1.61 ms per token, 622.63 tokens per second) 7.11.454.337 I slot print_timing: id 2 | task 6479 | eval time = 22839.28 ms / 452 tokens ( 50.64 ms per token, 19.75 tokens per second) 7.11.454.337 I slot print_timing: id 2 | task 6479 | total time = 23668.03 ms / 968 tokens 7.11.454.338 I slot print_timing: id 2 | task 6479 | graphs reused = 6437 7.11.454.338 I slot print_timing: id 2 | task 6479 | graph reallocs = 0 / 0 (same size) / (changed size) 7.11.454.401 I slot release: id 2 | task 6479 | stop processing: n_tokens = 1610, truncated = 0 7.11.500.479 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.663 7.11.500.509 I slot launch_slot_: id 2 | task 6936 | processing task, is_child = 0 7.12.226.637 I slot print_timing: id 1 | task 6007 | n_gen = 923, tg = 19.46 t/s, tg_3s = 17.19 t/s 7.13.512.020 I slot print_timing: id 0 | task 6698 | n_gen = 262, tg = 18.93 t/s, tg_3s = 16.13 t/s 7.13.898.281 I slot print_timing: id 1 | task 6007 | prompt eval time = 975.46 ms / 529 tokens ( 1.84 ms per token, 542.31 tokens per second) 7.13.898.289 I slot print_timing: id 1 | task 6007 | eval time = 49057.13 ms / 957 tokens ( 51.31 ms per token, 19.49 tokens per second) 7.13.898.290 I slot print_timing: id 1 | task 6007 | total time = 50032.59 ms / 1486 tokens 7.13.898.291 I slot print_timing: id 1 | task 6007 | graphs reused = 6469 7.13.898.292 I slot print_timing: id 1 | task 6007 | graph reallocs = 0 / 0 (same size) / (changed size) 7.13.898.430 I slot release: id 1 | task 6007 | stop processing: n_tokens = 2145, truncated = 0 7.13.947.847 I slot print_timing: id 3 | task 6870 | n_gen = 100, tg = 18.37 t/s, tg_3s = 18.56 t/s 7.13.947.858 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.498 7.13.954.651 I slot launch_slot_: id 1 | task 6973 | processing task, is_child = 0 7.16.555.427 I slot print_timing: id 0 | task 6698 | n_gen = 312, tg = 18.48 t/s, tg_3s = 16.43 t/s 7.16.982.925 I slot print_timing: id 3 | task 6870 | n_gen = 150, tg = 17.69 t/s, tg_3s = 16.47 t/s 7.17.697.747 I slot print_timing: id 2 | task 6936 | n_gen = 100, tg = 18.39 t/s, tg_3s = 18.58 t/s 7.19.411.212 I slot print_timing: id 1 | task 6973 | n_gen = 100, tg = 21.22 t/s, tg_3s = 21.43 t/s 7.19.600.106 I slot print_timing: id 0 | task 6698 | n_gen = 376, tg = 18.86 t/s, tg_3s = 21.02 t/s 7.20.028.490 I slot print_timing: id 3 | task 6870 | n_gen = 214, tg = 18.57 t/s, tg_3s = 21.01 t/s 7.20.740.283 I slot print_timing: id 2 | task 6936 | n_gen = 164, tg = 19.35 t/s, tg_3s = 21.04 t/s 7.22.458.852 I slot print_timing: id 1 | task 6973 | n_gen = 164, tg = 21.13 t/s, tg_3s = 21.00 t/s 7.22.602.248 I slot print_timing: id 0 | task 6698 | n_gen = 439, tg = 19.14 t/s, tg_3s = 20.98 t/s 7.23.036.947 I slot print_timing: id 3 | task 6870 | n_gen = 277, tg = 19.06 t/s, tg_3s = 20.94 t/s 7.23.756.044 I slot print_timing: id 2 | task 6936 | n_gen = 227, tg = 19.75 t/s, tg_3s = 20.89 t/s 7.25.481.638 I slot print_timing: id 1 | task 6973 | n_gen = 227, tg = 21.05 t/s, tg_3s = 20.84 t/s 7.25.624.889 I slot print_timing: id 0 | task 6698 | n_gen = 502, tg = 19.34 t/s, tg_3s = 20.84 t/s 7.26.058.789 I slot print_timing: id 3 | task 6870 | n_gen = 340, tg = 19.37 t/s, tg_3s = 20.85 t/s 7.26.776.387 I slot print_timing: id 2 | task 6936 | n_gen = 290, tg = 19.98 t/s, tg_3s = 20.86 t/s 7.28.260.700 I slot print_timing: id 1 | task 6973 | prompt eval time = 790.59 ms / 475 tokens ( 1.66 ms per token, 600.82 tokens per second) 7.28.260.709 I slot print_timing: id 1 | task 6973 | eval time = 13515.44 ms / 285 tokens ( 47.59 ms per token, 21.01 tokens per second) 7.28.260.710 I slot print_timing: id 1 | task 6973 | total time = 14306.03 ms / 760 tokens 7.28.260.711 I slot print_timing: id 1 | task 6973 | graphs reused = 6751 7.28.260.711 I slot print_timing: id 1 | task 6973 | graph reallocs = 0 / 0 (same size) / (changed size) 7.28.260.849 I slot release: id 1 | task 6973 | stop processing: n_tokens = 1432, truncated = 0 7.28.310.693 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.746 7.28.310.735 I slot launch_slot_: id 1 | task 7261 | processing task, is_child = 0 7.29.006.905 I slot print_timing: id 0 | task 6698 | n_gen = 559, tg = 19.05 t/s, tg_3s = 16.85 t/s 7.29.097.071 I slot print_timing: id 3 | task 6870 | n_gen = 389, tg = 18.89 t/s, tg_3s = 16.13 t/s 7.29.796.652 I slot print_timing: id 2 | task 6936 | n_gen = 339, tg = 19.33 t/s, tg_3s = 16.22 t/s 7.32.019.191 I slot print_timing: id 0 | task 6698 | n_gen = 622, tg = 19.23 t/s, tg_3s = 20.91 t/s 7.32.120.124 I slot print_timing: id 3 | task 6870 | n_gen = 453, tg = 19.18 t/s, tg_3s = 21.17 t/s 7.32.842.339 I slot print_timing: id 2 | task 6936 | n_gen = 403, tg = 19.58 t/s, tg_3s = 21.01 t/s 7.33.804.240 I slot print_timing: id 1 | task 7261 | n_gen = 100, tg = 21.03 t/s, tg_3s = 21.24 t/s 7.35.048.044 I slot print_timing: id 0 | task 6698 | n_gen = 685, tg = 19.36 t/s, tg_3s = 20.80 t/s 7.35.145.559 I slot print_timing: id 3 | task 6870 | n_gen = 516, tg = 19.37 t/s, tg_3s = 20.82 t/s 7.35.864.306 I slot print_timing: id 2 | task 6936 | n_gen = 466, tg = 19.75 t/s, tg_3s = 20.85 t/s 7.36.824.753 I slot print_timing: id 1 | task 7261 | n_gen = 163, tg = 20.96 t/s, tg_3s = 20.86 t/s 7.38.071.550 I slot print_timing: id 0 | task 6698 | n_gen = 748, tg = 19.48 t/s, tg_3s = 20.84 t/s 7.38.169.222 I slot print_timing: id 3 | task 6870 | n_gen = 579, tg = 19.52 t/s, tg_3s = 20.84 t/s 7.38.889.501 I slot print_timing: id 2 | task 6936 | n_gen = 529, tg = 19.87 t/s, tg_3s = 20.83 t/s 7.39.804.986 I slot print_timing: id 3 | task 6870 | prompt eval time = 783.85 ms / 485 tokens ( 1.62 ms per token, 618.74 tokens per second) 7.39.804.994 I slot print_timing: id 3 | task 6870 | eval time = 31246.05 ms / 613 tokens ( 51.06 ms per token, 19.59 tokens per second) 7.39.804.996 I slot print_timing: id 3 | task 6870 | total time = 32029.90 ms / 1098 tokens 7.39.804.996 I slot print_timing: id 3 | task 6870 | graphs reused = 6973 7.39.804.997 I slot print_timing: id 3 | task 6870 | graph reallocs = 0 / 0 (same size) / (changed size) 7.39.805.135 I slot release: id 3 | task 6870 | stop processing: n_tokens = 1792, truncated = 0 7.39.845.861 I slot print_timing: id 1 | task 7261 | n_gen = 226, tg = 20.93 t/s, tg_3s = 20.85 t/s 7.39.846.467 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.596 7.39.846.500 I slot launch_slot_: id 3 | task 7489 | processing task, is_child = 0 7.41.114.596 I slot print_timing: id 0 | task 6698 | n_gen = 798, tg = 19.25 t/s, tg_3s = 16.43 t/s 7.41.933.378 I slot print_timing: id 2 | task 6936 | n_gen = 579, tg = 19.51 t/s, tg_3s = 16.43 t/s 7.42.846.594 I slot print_timing: id 1 | task 7261 | n_gen = 275, tg = 19.93 t/s, tg_3s = 16.33 t/s 7.44.139.942 I slot print_timing: id 0 | task 6698 | n_gen = 861, tg = 19.36 t/s, tg_3s = 20.82 t/s 7.44.957.525 I slot print_timing: id 2 | task 6936 | n_gen = 642, tg = 19.64 t/s, tg_3s = 20.83 t/s 7.45.345.298 I slot print_timing: id 3 | task 7489 | n_gen = 100, tg = 20.83 t/s, tg_3s = 21.04 t/s 7.45.873.196 I slot print_timing: id 1 | task 7261 | n_gen = 338, tg = 20.09 t/s, tg_3s = 20.82 t/s 7.47.174.691 I slot print_timing: id 0 | task 6698 | n_gen = 924, tg = 19.45 t/s, tg_3s = 20.76 t/s 7.47.995.351 I slot print_timing: id 2 | task 6936 | n_gen = 705, tg = 19.73 t/s, tg_3s = 20.74 t/s 7.48.382.579 I slot print_timing: id 3 | task 7489 | n_gen = 163, tg = 20.80 t/s, tg_3s = 20.74 t/s 7.48.911.640 I slot print_timing: id 1 | task 7261 | n_gen = 401, tg = 20.19 t/s, tg_3s = 20.73 t/s 7.50.213.060 I slot print_timing: id 0 | task 6698 | n_gen = 987, tg = 19.53 t/s, tg_3s = 20.73 t/s 7.50.647.746 I slot print_timing: id 2 | task 6936 | prompt eval time = 814.44 ms / 496 tokens ( 1.64 ms per token, 609.01 tokens per second) 7.50.647.751 I slot print_timing: id 2 | task 6936 | eval time = 38332.78 ms / 760 tokens ( 50.50 ms per token, 19.80 tokens per second) 7.50.647.752 I slot print_timing: id 2 | task 6936 | total time = 39147.23 ms / 1256 tokens 7.50.647.753 I slot print_timing: id 2 | task 6936 | graphs reused = 7180 7.50.647.754 I slot print_timing: id 2 | task 6936 | graph reallocs = 0 / 0 (same size) / (changed size) 7.50.647.884 I slot release: id 2 | task 6936 | stop processing: n_tokens = 1898, truncated = 0 7.50.697.082 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.563 7.50.697.117 I slot launch_slot_: id 2 | task 7702 | processing task, is_child = 0 7.51.431.515 I slot print_timing: id 3 | task 7489 | n_gen = 212, tg = 19.47 t/s, tg_3s = 16.07 t/s 7.51.940.628 I slot print_timing: id 1 | task 7261 | n_gen = 449, tg = 19.61 t/s, tg_3s = 15.85 t/s 7.52.688.289 I slot print_timing: id 0 | task 6698 | prompt eval time = 790.58 ms / 498 tokens ( 1.59 ms per token, 629.92 tokens per second) 7.52.688.295 I slot print_timing: id 0 | task 6698 | eval time = 52966.31 ms / 1024 tokens ( 51.78 ms per token, 19.31 tokens per second) 7.52.688.295 I slot print_timing: id 0 | task 6698 | total time = 53756.89 ms / 1522 tokens 7.52.688.295 I slot print_timing: id 0 | task 6698 | graphs reused = 7204 7.52.688.296 I slot print_timing: id 0 | task 6698 | graph reallocs = 0 / 0 (same size) / (changed size) 7.52.688.355 I slot release: id 0 | task 6698 | stop processing: n_tokens = 2194, truncated = 0 7.52.727.356 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 7.52.731.699 I slot launch_slot_: id 0 | task 7731 | processing task, is_child = 0 7.53.704.324 I slot print_timing: id 1 | task 7261 | prompt eval time = 785.78 ms / 469 tokens ( 1.68 ms per token, 596.86 tokens per second) 7.53.704.326 I slot print_timing: id 1 | task 7261 | eval time = 24607.80 ms / 472 tokens ( 52.25 ms per token, 19.14 tokens per second) 7.53.704.327 I slot print_timing: id 1 | task 7261 | total time = 25393.58 ms / 941 tokens 7.53.704.327 I slot print_timing: id 1 | task 7261 | graphs reused = 7208 7.53.704.328 I slot print_timing: id 1 | task 7261 | graph reallocs = 0 / 0 (same size) / (changed size) 7.53.704.391 I slot release: id 1 | task 7261 | stop processing: n_tokens = 1613, truncated = 0 7.53.750.546 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.662 7.53.750.568 I slot launch_slot_: id 1 | task 7739 | processing task, is_child = 0 7.54.474.994 I slot print_timing: id 3 | task 7489 | n_gen = 247, tg = 17.72 t/s, tg_3s = 11.50 t/s 7.55.707.655 I slot print_timing: id 3 | task 7489 | prompt eval time = 746.73 ms / 448 tokens ( 1.67 ms per token, 599.95 tokens per second) 7.55.707.664 I slot print_timing: id 3 | task 7489 | eval time = 15114.42 ms / 272 tokens ( 55.77 ms per token, 17.93 tokens per second) 7.55.707.665 I slot print_timing: id 3 | task 7489 | total time = 15861.15 ms / 720 tokens 7.55.707.666 I slot print_timing: id 3 | task 7489 | graphs reused = 7231 7.55.707.666 I slot print_timing: id 3 | task 7489 | graph reallocs = 0 / 0 (same size) / (changed size) 7.55.707.784 I slot release: id 3 | task 7489 | stop processing: n_tokens = 1414, truncated = 0 7.55.748.344 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.755 7.55.748.380 I slot launch_slot_: id 3 | task 7767 | processing task, is_child = 0 7.58.263.772 I slot print_timing: id 2 | task 7702 | n_gen = 100, tg = 14.68 t/s, tg_3s = 14.83 t/s 7.59.596.770 I slot print_timing: id 0 | task 7731 | n_gen = 100, tg = 16.28 t/s, tg_3s = 16.45 t/s 7.59.935.799 I slot print_timing: id 1 | task 7739 | n_gen = 100, tg = 18.43 t/s, tg_3s = 18.61 t/s 8.01.226.386 I slot print_timing: id 3 | task 7767 | n_gen = 100, tg = 20.99 t/s, tg_3s = 21.20 t/s 8.01.273.784 I slot print_timing: id 2 | task 7702 | n_gen = 163, tg = 16.61 t/s, tg_3s = 20.93 t/s 8.02.611.814 I slot print_timing: id 0 | task 7731 | n_gen = 163, tg = 17.81 t/s, tg_3s = 20.90 t/s 8.02.946.646 I slot print_timing: id 1 | task 7739 | n_gen = 163, tg = 19.32 t/s, tg_3s = 20.92 t/s 8.04.240.005 I slot print_timing: id 3 | task 7767 | n_gen = 163, tg = 20.96 t/s, tg_3s = 20.91 t/s 8.04.286.850 I slot print_timing: id 2 | task 7702 | n_gen = 226, tg = 17.62 t/s, tg_3s = 20.91 t/s 8.05.621.879 I slot print_timing: id 0 | task 7731 | n_gen = 226, tg = 18.59 t/s, tg_3s = 20.93 t/s 8.05.958.887 I slot print_timing: id 1 | task 7739 | n_gen = 226, tg = 19.74 t/s, tg_3s = 20.91 t/s 8.07.256.639 I slot print_timing: id 3 | task 7767 | n_gen = 226, tg = 20.94 t/s, tg_3s = 20.88 t/s 8.07.304.038 I slot print_timing: id 2 | task 7702 | n_gen = 289, tg = 18.25 t/s, tg_3s = 20.88 t/s 8.08.643.988 I slot print_timing: id 0 | task 7731 | n_gen = 289, tg = 19.04 t/s, tg_3s = 20.85 t/s 8.08.979.939 I slot print_timing: id 1 | task 7739 | n_gen = 289, tg = 19.98 t/s, tg_3s = 20.85 t/s 8.10.281.029 I slot print_timing: id 3 | task 7767 | n_gen = 289, tg = 20.91 t/s, tg_3s = 20.83 t/s 8.10.328.518 I slot print_timing: id 2 | task 7702 | n_gen = 352, tg = 18.66 t/s, tg_3s = 20.83 t/s 8.11.668.982 I slot print_timing: id 0 | task 7731 | n_gen = 352, tg = 19.34 t/s, tg_3s = 20.83 t/s 8.12.009.020 I slot print_timing: id 1 | task 7739 | n_gen = 352, tg = 20.12 t/s, tg_3s = 20.80 t/s 8.12.298.444 I slot print_timing: id 2 | task 7702 | prompt eval time = 822.93 ms / 508 tokens ( 1.62 ms per token, 617.30 tokens per second) 8.12.298.453 I slot print_timing: id 2 | task 7702 | eval time = 20778.38 ms / 393 tokens ( 53.01 ms per token, 18.87 tokens per second) 8.12.298.454 I slot print_timing: id 2 | task 7702 | total time = 21601.32 ms / 901 tokens 8.12.298.455 I slot print_timing: id 2 | task 7702 | graphs reused = 7558 8.12.298.456 I slot print_timing: id 2 | task 7702 | graph reallocs = 0 / 0 (same size) / (changed size) 8.12.298.595 I slot release: id 2 | task 7702 | stop processing: n_tokens = 1543, truncated = 0 8.12.347.785 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.692 8.12.347.823 I slot launch_slot_: id 2 | task 8101 | processing task, is_child = 0 8.13.296.961 I slot print_timing: id 3 | task 7767 | n_gen = 337, tg = 20.01 t/s, tg_3s = 15.92 t/s 8.14.710.942 I slot print_timing: id 0 | task 7731 | n_gen = 401, tg = 18.87 t/s, tg_3s = 16.11 t/s 8.15.048.320 I slot print_timing: id 1 | task 7739 | n_gen = 401, tg = 19.53 t/s, tg_3s = 16.12 t/s 8.16.334.866 I slot print_timing: id 3 | task 7767 | n_gen = 401, tg = 20.18 t/s, tg_3s = 21.07 t/s 8.17.714.055 I slot print_timing: id 0 | task 7731 | n_gen = 464, tg = 19.13 t/s, tg_3s = 20.98 t/s 8.17.859.024 I slot print_timing: id 2 | task 8101 | n_gen = 100, tg = 21.05 t/s, tg_3s = 21.26 t/s 8.18.049.202 I slot print_timing: id 1 | task 7739 | n_gen = 464, tg = 19.71 t/s, tg_3s = 20.99 t/s 8.19.290.000 I slot print_timing: id 3 | task 7767 | prompt eval time = 761.16 ms / 454 tokens ( 1.68 ms per token, 596.46 tokens per second) 8.19.290.008 I slot print_timing: id 3 | task 7767 | eval time = 22780.45 ms / 463 tokens ( 49.31 ms per token, 20.28 tokens per second) 8.19.290.009 I slot print_timing: id 3 | task 7767 | total time = 23541.61 ms / 917 tokens 8.19.290.009 I slot print_timing: id 3 | task 7767 | graphs reused = 7685 8.19.290.010 I slot print_timing: id 3 | task 7767 | graph reallocs = 0 / 0 (same size) / (changed size) 8.19.290.133 I slot release: id 3 | task 7767 | stop processing: n_tokens = 1611, truncated = 0 8.19.331.002 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.663 8.19.331.048 I slot launch_slot_: id 3 | task 8234 | processing task, is_child = 0 8.20.744.524 I slot print_timing: id 0 | task 7731 | n_gen = 514, tg = 18.84 t/s, tg_3s = 16.50 t/s 8.20.884.934 I slot print_timing: id 2 | task 8101 | n_gen = 150, tg = 19.28 t/s, tg_3s = 16.52 t/s 8.21.073.497 I slot print_timing: id 1 | task 7739 | n_gen = 514, tg = 19.35 t/s, tg_3s = 16.53 t/s 8.22.659.419 I slot print_timing: id 0 | task 7731 | prompt eval time = 785.01 ms / 493 tokens ( 1.59 ms per token, 628.02 tokens per second) 8.22.659.426 I slot print_timing: id 0 | task 7731 | eval time = 29142.70 ms / 554 tokens ( 52.70 ms per token, 18.98 tokens per second) 8.22.659.428 I slot print_timing: id 0 | task 7731 | total time = 29927.71 ms / 1047 tokens 8.22.659.428 I slot print_timing: id 0 | task 7731 | graphs reused = 7738 8.22.659.429 I slot print_timing: id 0 | task 7731 | graph reallocs = 0 / 0 (same size) / (changed size) 8.22.659.543 I slot release: id 0 | task 7731 | stop processing: n_tokens = 1719, truncated = 0 8.22.702.798 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.621 8.22.702.840 I slot launch_slot_: id 0 | task 8292 | processing task, is_child = 0 8.23.926.080 I slot print_timing: id 2 | task 8101 | n_gen = 200, tg = 18.48 t/s, tg_3s = 16.44 t/s 8.24.113.293 I slot print_timing: id 1 | task 7739 | n_gen = 564, tg = 19.05 t/s, tg_3s = 16.45 t/s 8.25.416.276 I slot print_timing: id 3 | task 8234 | n_gen = 100, tg = 18.59 t/s, tg_3s = 18.78 t/s 8.26.954.101 I slot print_timing: id 2 | task 8101 | n_gen = 265, tg = 19.13 t/s, tg_3s = 21.47 t/s 8.27.152.692 I slot print_timing: id 1 | task 7739 | n_gen = 629, tg = 19.27 t/s, tg_3s = 21.39 t/s 8.28.111.439 I slot print_timing: id 0 | task 8292 | n_gen = 100, tg = 21.27 t/s, tg_3s = 21.49 t/s 8.28.448.852 I slot print_timing: id 3 | task 8234 | n_gen = 164, tg = 19.50 t/s, tg_3s = 21.10 t/s 8.29.983.333 I slot print_timing: id 2 | task 8101 | n_gen = 328, tg = 19.43 t/s, tg_3s = 20.80 t/s 8.30.174.443 I slot print_timing: id 1 | task 7739 | n_gen = 692, tg = 19.40 t/s, tg_3s = 20.85 t/s 8.31.135.034 I slot print_timing: id 0 | task 8292 | n_gen = 163, tg = 21.10 t/s, tg_3s = 20.84 t/s 8.31.472.975 I slot print_timing: id 3 | task 8234 | n_gen = 227, tg = 19.86 t/s, tg_3s = 20.83 t/s 8.32.997.544 I slot print_timing: id 2 | task 8101 | n_gen = 391, tg = 19.66 t/s, tg_3s = 20.90 t/s 8.33.188.547 I slot print_timing: id 1 | task 7739 | n_gen = 755, tg = 19.52 t/s, tg_3s = 20.90 t/s 8.34.141.745 I slot print_timing: id 0 | task 8292 | n_gen = 226, tg = 21.06 t/s, tg_3s = 20.95 t/s 8.34.479.476 I slot print_timing: id 3 | task 8234 | n_gen = 290, tg = 20.09 t/s, tg_3s = 20.95 t/s 8.36.013.442 I slot print_timing: id 2 | task 8101 | n_gen = 454, tg = 19.82 t/s, tg_3s = 20.89 t/s 8.36.205.464 I slot print_timing: id 1 | task 7739 | n_gen = 818, tg = 19.62 t/s, tg_3s = 20.88 t/s 8.37.164.954 I slot print_timing: id 0 | task 8292 | n_gen = 289, tg = 21.01 t/s, tg_3s = 20.84 t/s 8.37.502.751 I slot print_timing: id 3 | task 8234 | n_gen = 353, tg = 20.22 t/s, tg_3s = 20.84 t/s 8.39.033.573 I slot print_timing: id 2 | task 8101 | n_gen = 517, tg = 19.94 t/s, tg_3s = 20.86 t/s 8.39.224.113 I slot print_timing: id 1 | task 7739 | n_gen = 881, tg = 19.70 t/s, tg_3s = 20.87 t/s 8.40.190.578 I slot print_timing: id 0 | task 8292 | n_gen = 352, tg = 20.98 t/s, tg_3s = 20.82 t/s 8.40.530.832 I slot print_timing: id 3 | task 8234 | n_gen = 416, tg = 20.30 t/s, tg_3s = 20.81 t/s 8.42.072.255 I slot print_timing: id 2 | task 8101 | n_gen = 580, tg = 20.02 t/s, tg_3s = 20.73 t/s 8.42.264.808 I slot print_timing: id 1 | task 7739 | n_gen = 944, tg = 19.77 t/s, tg_3s = 20.72 t/s 8.43.227.226 I slot print_timing: id 0 | task 8292 | n_gen = 415, tg = 20.94 t/s, tg_3s = 20.75 t/s 8.43.566.355 I slot print_timing: id 3 | task 8234 | n_gen = 479, tg = 20.36 t/s, tg_3s = 20.75 t/s 8.45.104.814 I slot print_timing: id 2 | task 8101 | n_gen = 643, tg = 20.09 t/s, tg_3s = 20.77 t/s 8.45.296.278 I slot print_timing: id 1 | task 7739 | n_gen = 1007, tg = 19.83 t/s, tg_3s = 20.78 t/s 8.46.110.797 I slot print_timing: id 0 | task 8292 | prompt eval time = 755.16 ms / 466 tokens ( 1.62 ms per token, 617.09 tokens per second) 8.46.110.807 I slot print_timing: id 0 | task 8292 | eval time = 22652.79 ms / 475 tokens ( 47.79 ms per token, 20.92 tokens per second) 8.46.110.808 I slot print_timing: id 0 | task 8292 | total time = 23407.95 ms / 941 tokens 8.46.110.809 I slot print_timing: id 0 | task 8292 | graphs reused = 8210 8.46.110.810 I slot print_timing: id 0 | task 8292 | graph reallocs = 0 / 0 (same size) / (changed size) 8.46.110.921 I slot release: id 0 | task 8292 | stop processing: n_tokens = 1613, truncated = 0 8.46.111.608 I slot print_timing: id 1 | task 7739 | prompt eval time = 812.93 ms / 493 tokens ( 1.65 ms per token, 606.45 tokens per second) 8.46.111.617 I slot print_timing: id 1 | task 7739 | eval time = 51548.11 ms / 1024 tokens ( 50.39 ms per token, 19.85 tokens per second) 8.46.111.618 I slot print_timing: id 1 | task 7739 | total time = 52361.04 ms / 1517 tokens 8.46.111.618 I slot print_timing: id 1 | task 7739 | graphs reused = 8210 8.46.111.619 I slot print_timing: id 1 | task 7739 | graph reallocs = 0 / 0 (same size) / (changed size) 8.46.111.727 I slot release: id 1 | task 7739 | stop processing: n_tokens = 2189, truncated = 0 8.46.143.780 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.662 8.46.143.809 I slot launch_slot_: id 0 | task 8770 | processing task, is_child = 0 8.46.149.923 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.488 8.46.150.128 I slot launch_slot_: id 1 | task 8771 | processing task, is_child = 0 8.47.632.050 I slot print_timing: id 2 | task 8101 | prompt eval time = 808.10 ms / 487 tokens ( 1.66 ms per token, 602.65 tokens per second) 8.47.632.052 I slot print_timing: id 2 | task 8101 | eval time = 34476.12 ms / 666 tokens ( 51.84 ms per token, 19.29 tokens per second) 8.47.632.053 I slot print_timing: id 2 | task 8101 | total time = 35284.22 ms / 1153 tokens 8.47.632.053 I slot print_timing: id 2 | task 8101 | graphs reused = 8211 8.47.632.054 I slot print_timing: id 2 | task 8101 | graph reallocs = 0 / 0 (same size) / (changed size) 8.47.632.117 I slot release: id 2 | task 8101 | stop processing: n_tokens = 1795, truncated = 0 8.47.632.372 I slot print_timing: id 3 | task 8234 | n_gen = 534, tg = 19.35 t/s, tg_3s = 13.53 t/s 8.47.721.566 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.595 8.47.721.606 I slot launch_slot_: id 2 | task 8774 | processing task, is_child = 0 8.50.642.935 I slot print_timing: id 3 | task 8234 | n_gen = 581, tg = 18.98 t/s, tg_3s = 15.61 t/s 8.53.180.434 I slot print_timing: id 0 | task 8770 | n_gen = 100, tg = 18.13 t/s, tg_3s = 18.32 t/s 8.53.181.164 I slot print_timing: id 1 | task 8771 | n_gen = 100, tg = 18.13 t/s, tg_3s = 18.32 t/s 8.53.277.271 I slot print_timing: id 2 | task 8774 | n_gen = 100, tg = 20.90 t/s, tg_3s = 21.12 t/s 8.53.664.045 I slot print_timing: id 3 | task 8234 | n_gen = 644, tg = 19.15 t/s, tg_3s = 20.85 t/s 8.56.198.640 I slot print_timing: id 0 | task 8770 | n_gen = 163, tg = 19.11 t/s, tg_3s = 20.87 t/s 8.56.199.309 I slot print_timing: id 1 | task 8771 | n_gen = 163, tg = 19.11 t/s, tg_3s = 20.87 t/s 8.56.296.213 I slot print_timing: id 2 | task 8774 | n_gen = 163, tg = 20.89 t/s, tg_3s = 20.87 t/s 8.56.681.813 I slot print_timing: id 3 | task 8234 | n_gen = 707, tg = 19.29 t/s, tg_3s = 20.88 t/s 8.59.226.211 I slot print_timing: id 0 | task 8770 | n_gen = 226, tg = 19.56 t/s, tg_3s = 20.81 t/s 8.59.226.914 I slot print_timing: id 1 | task 8771 | n_gen = 226, tg = 19.56 t/s, tg_3s = 20.81 t/s 8.59.323.760 I slot print_timing: id 2 | task 8774 | n_gen = 226, tg = 20.87 t/s, tg_3s = 20.81 t/s 8.59.706.751 I slot print_timing: id 3 | task 8234 | n_gen = 770, tg = 19.41 t/s, tg_3s = 20.83 t/s 9.01.667.387 I slot print_timing: id 3 | task 8234 | prompt eval time = 760.90 ms / 456 tokens ( 1.67 ms per token, 599.29 tokens per second) 9.01.667.392 I slot print_timing: id 3 | task 8234 | eval time = 41575.43 ms / 811 tokens ( 51.33 ms per token, 19.48 tokens per second) 9.01.667.393 I slot print_timing: id 3 | task 8234 | total time = 42336.33 ms / 1267 tokens 9.01.667.394 I slot print_timing: id 3 | task 8234 | graphs reused = 8483 9.01.667.395 I slot print_timing: id 3 | task 8234 | graph reallocs = 0 / 0 (same size) / (changed size) 9.01.667.524 I slot release: id 3 | task 8234 | stop processing: n_tokens = 1961, truncated = 0 9.01.708.350 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.545 9.01.708.389 I slot launch_slot_: id 3 | task 9052 | processing task, is_child = 0 9.02.366.386 I slot print_timing: id 0 | task 8770 | n_gen = 279, tg = 18.98 t/s, tg_3s = 16.88 t/s 9.02.366.681 I slot print_timing: id 1 | task 8771 | n_gen = 279, tg = 18.98 t/s, tg_3s = 16.88 t/s 9.02.366.954 I slot print_timing: id 2 | task 8774 | n_gen = 277, tg = 19.96 t/s, tg_3s = 16.76 t/s 9.04.757.730 I slot print_timing: id 0 | task 8770 | prompt eval time = 1570.80 ms / 461 tokens ( 3.41 ms per token, 293.48 tokens per second) 9.04.757.737 I slot print_timing: id 0 | task 8770 | eval time = 17036.79 ms / 329 tokens ( 51.94 ms per token, 19.25 tokens per second) 9.04.757.738 I slot print_timing: id 0 | task 8770 | total time = 18607.59 ms / 790 tokens 9.04.757.739 I slot print_timing: id 0 | task 8770 | graphs reused = 8531 9.04.757.740 I slot print_timing: id 0 | task 8770 | graph reallocs = 0 / 0 (same size) / (changed size) 9.04.757.857 I slot release: id 0 | task 8770 | stop processing: n_tokens = 1462, truncated = 0 9.04.800.981 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.731 9.04.801.016 I slot launch_slot_: id 0 | task 9105 | processing task, is_child = 0 9.05.522.351 I slot print_timing: id 1 | task 8771 | n_gen = 331, tg = 18.54 t/s, tg_3s = 16.48 t/s 9.05.522.626 I slot print_timing: id 2 | task 8774 | n_gen = 329, tg = 19.32 t/s, tg_3s = 16.48 t/s 9.07.816.922 I slot print_timing: id 3 | task 9052 | n_gen = 100, tg = 18.44 t/s, tg_3s = 18.63 t/s 9.08.536.776 I slot print_timing: id 1 | task 8771 | n_gen = 394, tg = 18.88 t/s, tg_3s = 20.90 t/s 9.08.537.441 I slot print_timing: id 2 | task 8774 | n_gen = 392, tg = 19.55 t/s, tg_3s = 20.90 t/s 9.10.310.081 I slot print_timing: id 0 | task 9105 | n_gen = 100, tg = 21.03 t/s, tg_3s = 21.24 t/s 9.10.839.757 I slot print_timing: id 3 | task 9052 | n_gen = 163, tg = 19.31 t/s, tg_3s = 20.84 t/s 9.11.555.309 I slot print_timing: id 1 | task 8771 | n_gen = 457, tg = 19.13 t/s, tg_3s = 20.87 t/s 9.11.556.023 I slot print_timing: id 2 | task 8774 | n_gen = 455, tg = 19.73 t/s, tg_3s = 20.87 t/s 9.13.326.925 I slot print_timing: id 0 | task 9105 | n_gen = 163, tg = 20.97 t/s, tg_3s = 20.88 t/s 9.13.855.820 I slot print_timing: id 3 | task 9052 | n_gen = 226, tg = 19.72 t/s, tg_3s = 20.89 t/s 9.14.572.949 I slot print_timing: id 1 | task 8771 | n_gen = 520, tg = 19.33 t/s, tg_3s = 20.88 t/s 9.14.573.628 I slot print_timing: id 2 | task 8774 | n_gen = 518, tg = 19.86 t/s, tg_3s = 20.88 t/s 9.15.387.794 I slot print_timing: id 1 | task 8771 | prompt eval time = 1570.94 ms / 494 tokens ( 3.18 ms per token, 314.46 tokens per second) 9.15.387.802 I slot print_timing: id 1 | task 8771 | eval time = 27666.46 ms / 537 tokens ( 51.62 ms per token, 19.37 tokens per second) 9.15.387.803 I slot print_timing: id 1 | task 8771 | total time = 29237.40 ms / 1031 tokens 9.15.387.804 I slot print_timing: id 1 | task 8771 | graphs reused = 8735 9.15.387.805 I slot print_timing: id 1 | task 8771 | graph reallocs = 0 / 0 (same size) / (changed size) 9.15.387.942 I slot release: id 1 | task 8771 | stop processing: n_tokens = 1703, truncated = 0 9.15.437.560 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.627 9.15.437.606 I slot launch_slot_: id 1 | task 9314 | processing task, is_child = 0 9.16.328.102 I slot print_timing: id 0 | task 9105 | n_gen = 211, tg = 19.58 t/s, tg_3s = 15.99 t/s 9.16.328.625 I slot print_timing: id 2 | task 8774 | prompt eval time = 819.71 ms / 506 tokens ( 1.62 ms per token, 617.30 tokens per second) 9.16.328.632 I slot print_timing: id 2 | task 8774 | eval time = 27787.31 ms / 540 tokens ( 51.55 ms per token, 19.40 tokens per second) 9.16.328.633 I slot print_timing: id 2 | task 8774 | total time = 28607.01 ms / 1046 tokens 9.16.328.633 I slot print_timing: id 2 | task 8774 | graphs reused = 8736 9.16.328.634 I slot print_timing: id 2 | task 8774 | graph reallocs = 0 / 0 (same size) / (changed size) 9.16.328.691 I slot release: id 2 | task 8774 | stop processing: n_tokens = 1688, truncated = 0 9.16.374.624 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.633 9.16.374.645 I slot launch_slot_: id 2 | task 9320 | processing task, is_child = 0 9.17.378.709 I slot print_timing: id 3 | task 9052 | n_gen = 266, tg = 17.75 t/s, tg_3s = 11.35 t/s 9.19.369.043 I slot print_timing: id 0 | task 9105 | n_gen = 255, tg = 18.45 t/s, tg_3s = 14.47 t/s 9.19.658.253 I slot print_timing: id 3 | task 9052 | prompt eval time = 739.99 ms / 440 tokens ( 1.68 ms per token, 594.61 tokens per second) 9.19.658.260 I slot print_timing: id 3 | task 9052 | eval time = 17209.87 ms / 313 tokens ( 55.16 ms per token, 18.13 tokens per second) 9.19.658.261 I slot print_timing: id 3 | task 9052 | total time = 17949.85 ms / 753 tokens 9.19.658.262 I slot print_timing: id 3 | task 9052 | graphs reused = 8781 9.19.658.263 I slot print_timing: id 3 | task 9052 | graph reallocs = 0 / 0 (same size) / (changed size) 9.19.658.388 I slot release: id 3 | task 9052 | stop processing: n_tokens = 1447, truncated = 0 9.19.699.421 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.738 9.19.699.456 I slot launch_slot_: id 3 | task 9371 | processing task, is_child = 0 9.22.412.637 I slot print_timing: id 0 | task 9105 | n_gen = 305, tg = 18.08 t/s, tg_3s = 16.43 t/s 9.22.557.032 I slot print_timing: id 1 | task 9314 | n_gen = 100, tg = 15.66 t/s, tg_3s = 15.81 t/s 9.22.844.124 I slot print_timing: id 2 | task 9320 | n_gen = 100, tg = 18.41 t/s, tg_3s = 18.59 t/s 9.25.182.567 I slot print_timing: id 3 | task 9371 | n_gen = 100, tg = 21.02 t/s, tg_3s = 21.23 t/s 9.25.418.899 I slot print_timing: id 0 | task 9105 | n_gen = 368, tg = 18.52 t/s, tg_3s = 20.96 t/s 9.25.562.697 I slot print_timing: id 1 | task 9314 | n_gen = 163, tg = 17.37 t/s, tg_3s = 20.96 t/s 9.25.849.990 I slot print_timing: id 2 | task 9320 | n_gen = 163, tg = 19.32 t/s, tg_3s = 20.96 t/s 9.28.194.715 I slot print_timing: id 3 | task 9371 | n_gen = 163, tg = 20.98 t/s, tg_3s = 20.92 t/s 9.28.431.121 I slot print_timing: id 0 | task 9105 | n_gen = 431, tg = 18.84 t/s, tg_3s = 20.91 t/s 9.28.575.247 I slot print_timing: id 1 | task 9314 | n_gen = 226, tg = 18.23 t/s, tg_3s = 20.91 t/s 9.28.863.154 I slot print_timing: id 2 | task 9320 | n_gen = 226, tg = 19.74 t/s, tg_3s = 20.91 t/s 9.31.206.847 I slot print_timing: id 3 | task 9371 | n_gen = 226, tg = 20.96 t/s, tg_3s = 20.92 t/s 9.31.445.134 I slot print_timing: id 0 | task 9105 | n_gen = 494, tg = 19.08 t/s, tg_3s = 20.90 t/s 9.31.589.041 I slot print_timing: id 1 | task 9314 | n_gen = 289, tg = 18.76 t/s, tg_3s = 20.90 t/s 9.31.876.541 I slot print_timing: id 2 | task 9320 | n_gen = 289, tg = 19.99 t/s, tg_3s = 20.91 t/s 9.34.223.553 I slot print_timing: id 3 | task 9371 | n_gen = 289, tg = 20.94 t/s, tg_3s = 20.88 t/s 9.34.460.318 I slot print_timing: id 0 | task 9105 | n_gen = 557, tg = 19.27 t/s, tg_3s = 20.89 t/s 9.34.605.171 I slot print_timing: id 1 | task 9314 | n_gen = 352, tg = 19.11 t/s, tg_3s = 20.89 t/s 9.34.892.626 I slot print_timing: id 2 | task 9320 | n_gen = 352, tg = 20.14 t/s, tg_3s = 20.89 t/s 9.37.243.899 I slot print_timing: id 3 | task 9371 | n_gen = 352, tg = 20.93 t/s, tg_3s = 20.86 t/s 9.37.479.487 I slot print_timing: id 0 | task 9105 | n_gen = 620, tg = 19.42 t/s, tg_3s = 20.87 t/s 9.37.624.321 I slot print_timing: id 1 | task 9314 | n_gen = 415, tg = 19.35 t/s, tg_3s = 20.87 t/s 9.37.913.366 I slot print_timing: id 2 | task 9320 | n_gen = 415, tg = 20.25 t/s, tg_3s = 20.86 t/s 9.40.273.300 I slot print_timing: id 3 | task 9371 | n_gen = 415, tg = 20.91 t/s, tg_3s = 20.80 t/s 9.40.512.883 I slot print_timing: id 0 | task 9105 | n_gen = 683, tg = 19.54 t/s, tg_3s = 20.77 t/s 9.40.658.687 I slot print_timing: id 1 | task 9314 | n_gen = 478, tg = 19.53 t/s, tg_3s = 20.76 t/s 9.40.949.653 I slot print_timing: id 2 | task 9320 | n_gen = 478, tg = 20.31 t/s, tg_3s = 20.75 t/s 9.43.312.343 I slot print_timing: id 3 | task 9371 | n_gen = 478, tg = 20.88 t/s, tg_3s = 20.73 t/s 9.43.550.868 I slot print_timing: id 0 | task 9105 | n_gen = 746, tg = 19.63 t/s, tg_3s = 20.74 t/s 9.43.695.851 I slot print_timing: id 1 | task 9314 | n_gen = 541, tg = 19.66 t/s, tg_3s = 20.74 t/s 9.43.985.018 I slot print_timing: id 2 | task 9320 | n_gen = 541, tg = 20.36 t/s, tg_3s = 20.76 t/s 9.46.316.859 I slot print_timing: id 3 | task 9371 | n_gen = 536, tg = 20.70 t/s, tg_3s = 19.30 t/s 9.46.568.541 I slot print_timing: id 0 | task 9105 | n_gen = 804, tg = 19.60 t/s, tg_3s = 19.22 t/s 9.46.721.208 I slot print_timing: id 1 | task 9314 | n_gen = 599, tg = 19.61 t/s, tg_3s = 19.17 t/s 9.47.023.947 I slot print_timing: id 2 | task 9320 | n_gen = 599, tg = 20.23 t/s, tg_3s = 19.09 t/s 9.48.492.574 I slot print_timing: id 3 | task 9371 | prompt eval time = 772.75 ms / 468 tokens ( 1.65 ms per token, 605.63 tokens per second) 9.48.492.583 I slot print_timing: id 3 | task 9371 | eval time = 28020.35 ms / 580 tokens ( 48.39 ms per token, 20.66 tokens per second) 9.48.492.584 I slot print_timing: id 3 | task 9371 | total time = 28793.11 ms / 1048 tokens 9.48.492.585 I slot print_timing: id 3 | task 9371 | graphs reused = 9357 9.48.492.586 I slot print_timing: id 3 | task 9371 | graph reallocs = 0 / 0 (same size) / (changed size) 9.48.492.702 I slot release: id 3 | task 9371 | stop processing: n_tokens = 1742, truncated = 0 9.48.534.075 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.613 9.48.534.111 I slot launch_slot_: id 3 | task 9954 | processing task, is_child = 0 9.49.591.560 I slot print_timing: id 0 | task 9105 | n_gen = 852, tg = 19.35 t/s, tg_3s = 15.88 t/s 9.49.745.216 I slot print_timing: id 1 | task 9314 | n_gen = 647, tg = 19.28 t/s, tg_3s = 15.87 t/s 9.50.034.796 I slot print_timing: id 2 | task 9320 | n_gen = 647, tg = 19.84 t/s, tg_3s = 15.94 t/s 9.52.625.690 I slot print_timing: id 0 | task 9105 | n_gen = 915, tg = 19.44 t/s, tg_3s = 20.76 t/s 9.52.769.721 I slot print_timing: id 1 | task 9314 | n_gen = 710, tg = 19.41 t/s, tg_3s = 20.83 t/s 9.53.058.186 I slot print_timing: id 2 | task 9320 | n_gen = 710, tg = 19.92 t/s, tg_3s = 20.84 t/s 9.54.065.820 I slot print_timing: id 3 | task 9954 | n_gen = 100, tg = 20.83 t/s, tg_3s = 21.04 t/s 9.55.651.924 I slot print_timing: id 0 | task 9105 | n_gen = 978, tg = 19.52 t/s, tg_3s = 20.82 t/s 9.55.796.699 I slot print_timing: id 1 | task 9314 | n_gen = 773, tg = 19.51 t/s, tg_3s = 20.81 t/s 9.56.087.401 I slot print_timing: id 2 | task 9320 | n_gen = 773, tg = 19.99 t/s, tg_3s = 20.80 t/s 9.57.101.174 I slot print_timing: id 3 | task 9954 | n_gen = 163, tg = 20.80 t/s, tg_3s = 20.76 t/s 9.57.870.696 I slot print_timing: id 0 | task 9105 | prompt eval time = 800.45 ms / 511 tokens ( 1.57 ms per token, 638.39 tokens per second) 9.57.870.704 I slot print_timing: id 0 | task 9105 | eval time = 52269.22 ms / 1024 tokens ( 51.09 ms per token, 19.57 tokens per second) 9.57.870.705 I slot print_timing: id 0 | task 9105 | total time = 53069.67 ms / 1535 tokens 9.57.870.706 I slot print_timing: id 0 | task 9105 | graphs reused = 9533 9.57.870.707 I slot print_timing: id 0 | task 9105 | graph reallocs = 0 / 0 (same size) / (changed size) 9.57.870.822 I slot release: id 0 | task 9105 | stop processing: n_tokens = 2207, truncated = 0 9.57.913.628 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.484 9.57.920.286 I slot launch_slot_: id 0 | task 10136 | processing task, is_child = 0 9.58.842.156 I slot print_timing: id 1 | task 9314 | n_gen = 823, tg = 19.29 t/s, tg_3s = 16.42 t/s 9.59.122.882 I slot print_timing: id 2 | task 9320 | n_gen = 823, tg = 19.73 t/s, tg_3s = 16.47 t/s 10.00.123.556 I slot print_timing: id 3 | task 9954 | n_gen = 213, tg = 19.61 t/s, tg_3s = 16.54 t/s 10.01.850.621 I slot print_timing: id 1 | task 9314 | n_gen = 886, tg = 19.40 t/s, tg_3s = 20.94 t/s 10.02.139.187 I slot print_timing: id 2 | task 9320 | n_gen = 886, tg = 19.81 t/s, tg_3s = 20.89 t/s 10.03.147.685 I slot print_timing: id 3 | task 9954 | n_gen = 276, tg = 19.88 t/s, tg_3s = 20.83 t/s 10.03.386.988 I slot print_timing: id 0 | task 10136 | n_gen = 100, tg = 20.91 t/s, tg_3s = 21.12 t/s 10.04.882.495 I slot print_timing: id 1 | task 9314 | n_gen = 949, tg = 19.49 t/s, tg_3s = 20.78 t/s 10.05.172.173 I slot print_timing: id 2 | task 9320 | n_gen = 949, tg = 19.87 t/s, tg_3s = 20.77 t/s 10.06.181.358 I slot print_timing: id 3 | task 9954 | n_gen = 339, tg = 20.04 t/s, tg_3s = 20.77 t/s 10.06.420.259 I slot print_timing: id 0 | task 10136 | n_gen = 163, tg = 20.86 t/s, tg_3s = 20.77 t/s 10.07.916.125 I slot print_timing: id 1 | task 9314 | n_gen = 1012, tg = 19.56 t/s, tg_3s = 20.77 t/s 10.08.206.623 I slot print_timing: id 2 | task 9320 | n_gen = 1012, tg = 19.92 t/s, tg_3s = 20.76 t/s 10.08.496.448 I slot print_timing: id 1 | task 9314 | prompt eval time = 796.30 ms / 483 tokens ( 1.65 ms per token, 606.56 tokens per second) 10.08.496.456 I slot print_timing: id 1 | task 9314 | eval time = 52262.53 ms / 1024 tokens ( 51.09 ms per token, 19.57 tokens per second) 10.08.496.457 I slot print_timing: id 1 | task 9314 | total time = 53058.83 ms / 1507 tokens 10.08.496.458 I slot print_timing: id 1 | task 9314 | graphs reused = 9737 10.08.496.458 I slot print_timing: id 1 | task 9314 | graph reallocs = 0 / 0 (same size) / (changed size) 10.08.496.597 I slot release: id 1 | task 9314 | stop processing: n_tokens = 2179, truncated = 0 10.08.546.261 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.490 10.08.553.032 I slot launch_slot_: id 1 | task 10345 | processing task, is_child = 0 10.09.254.082 I slot print_timing: id 3 | task 9954 | n_gen = 389, tg = 19.46 t/s, tg_3s = 16.27 t/s 10.09.437.299 I slot print_timing: id 0 | task 10136 | n_gen = 211, tg = 19.47 t/s, tg_3s = 15.91 t/s 10.09.484.562 I slot print_timing: id 2 | task 9320 | prompt eval time = 1091.58 ms / 560 tokens ( 1.95 ms per token, 513.02 tokens per second) 10.09.484.566 I slot print_timing: id 2 | task 9320 | eval time = 52018.33 ms / 1024 tokens ( 50.85 ms per token, 19.67 tokens per second) 10.09.484.566 I slot print_timing: id 2 | task 9320 | total time = 53109.91 ms / 1584 tokens 10.09.484.567 I slot print_timing: id 2 | task 9320 | graphs reused = 9739 10.09.484.567 I slot print_timing: id 2 | task 9320 | graph reallocs = 0 / 0 (same size) / (changed size) 10.09.484.635 I slot release: id 2 | task 9320 | stop processing: n_tokens = 2226, truncated = 0 10.09.530.243 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.480 10.09.534.792 I slot launch_slot_: id 2 | task 10352 | processing task, is_child = 0 10.12.261.668 I slot print_timing: id 3 | task 9954 | n_gen = 437, tg = 19.00 t/s, tg_3s = 15.96 t/s 10.12.451.019 I slot print_timing: id 0 | task 10136 | n_gen = 260, tg = 18.77 t/s, tg_3s = 16.26 t/s 10.14.748.407 I slot print_timing: id 1 | task 10345 | n_gen = 100, tg = 18.31 t/s, tg_3s = 18.50 t/s 10.15.036.031 I slot print_timing: id 2 | task 10352 | n_gen = 100, tg = 21.02 t/s, tg_3s = 21.23 t/s 10.15.275.601 I slot print_timing: id 3 | task 9954 | n_gen = 500, tg = 19.22 t/s, tg_3s = 20.90 t/s 10.15.464.986 I slot print_timing: id 0 | task 10136 | n_gen = 323, tg = 19.15 t/s, tg_3s = 20.90 t/s 10.17.426.303 I slot print_timing: id 0 | task 10136 | prompt eval time = 732.88 ms / 451 tokens ( 1.63 ms per token, 615.38 tokens per second) 10.17.426.310 I slot print_timing: id 0 | task 10136 | eval time = 18773.12 ms / 364 tokens ( 51.72 ms per token, 19.34 tokens per second) 10.17.426.312 I slot print_timing: id 0 | task 10136 | total time = 19506.00 ms / 815 tokens 10.17.426.312 I slot print_timing: id 0 | task 10136 | graphs reused = 9887 10.17.426.313 I slot print_timing: id 0 | task 10136 | graph reallocs = 0 / 0 (same size) / (changed size) 10.17.426.422 I slot release: id 0 | task 10136 | stop processing: n_tokens = 1487, truncated = 0 10.17.468.894 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.718 10.17.468.928 I slot launch_slot_: id 0 | task 10505 | processing task, is_child = 0 10.18.151.023 I slot print_timing: id 1 | task 10345 | n_gen = 158, tg = 17.82 t/s, tg_3s = 17.05 t/s 10.18.151.286 I slot print_timing: id 2 | task 10352 | n_gen = 152, tg = 19.30 t/s, tg_3s = 16.69 t/s 10.18.278.851 I slot print_timing: id 3 | task 9954 | n_gen = 549, tg = 18.92 t/s, tg_3s = 16.32 t/s 10.21.161.766 I slot print_timing: id 1 | task 10345 | n_gen = 222, tg = 18.70 t/s, tg_3s = 21.26 t/s 10.21.162.053 I slot print_timing: id 2 | task 10352 | n_gen = 216, tg = 19.84 t/s, tg_3s = 21.26 t/s 10.21.303.490 I slot print_timing: id 3 | task 9954 | n_gen = 614, tg = 19.16 t/s, tg_3s = 21.49 t/s 10.22.892.696 I slot print_timing: id 0 | task 10505 | n_gen = 100, tg = 21.23 t/s, tg_3s = 21.45 t/s 10.24.192.190 I slot print_timing: id 1 | task 10345 | n_gen = 285, tg = 19.13 t/s, tg_3s = 20.79 t/s 10.24.192.929 I slot print_timing: id 2 | task 10352 | n_gen = 279, tg = 20.05 t/s, tg_3s = 20.79 t/s 10.24.337.553 I slot print_timing: id 3 | task 9954 | n_gen = 677, tg = 19.30 t/s, tg_3s = 20.76 t/s 10.25.915.104 I slot print_timing: id 0 | task 10505 | n_gen = 163, tg = 21.08 t/s, tg_3s = 20.84 t/s 10.27.206.052 I slot print_timing: id 1 | task 10345 | n_gen = 348, tg = 19.43 t/s, tg_3s = 20.90 t/s 10.27.206.713 I slot print_timing: id 2 | task 10352 | n_gen = 342, tg = 20.20 t/s, tg_3s = 20.90 t/s 10.27.350.588 I slot print_timing: id 3 | task 9954 | n_gen = 740, tg = 19.43 t/s, tg_3s = 20.91 t/s 10.28.929.202 I slot print_timing: id 0 | task 10505 | n_gen = 226, tg = 21.03 t/s, tg_3s = 20.90 t/s 10.30.223.027 I slot print_timing: id 1 | task 10345 | n_gen = 411, tg = 19.64 t/s, tg_3s = 20.88 t/s 10.30.223.761 I slot print_timing: id 2 | task 10352 | n_gen = 405, tg = 20.30 t/s, tg_3s = 20.88 t/s 10.30.368.327 I slot print_timing: id 3 | task 9954 | n_gen = 803, tg = 19.53 t/s, tg_3s = 20.88 t/s 10.31.949.146 I slot print_timing: id 0 | task 10505 | n_gen = 289, tg = 20.99 t/s, tg_3s = 20.86 t/s 10.32.669.878 I slot print_timing: id 2 | task 10352 | prompt eval time = 791.99 ms / 479 tokens ( 1.65 ms per token, 604.80 tokens per second) 10.32.669.885 I slot print_timing: id 2 | task 10352 | eval time = 22343.08 ms / 456 tokens ( 49.11 ms per token, 20.36 tokens per second) 10.32.669.889 I slot print_timing: id 2 | task 10352 | total time = 23135.07 ms / 935 tokens 10.32.669.890 I slot print_timing: id 2 | task 10352 | graphs reused = 10189 10.32.669.891 I slot print_timing: id 2 | task 10352 | graph reallocs = 0 / 0 (same size) / (changed size) 10.32.670.037 I slot release: id 2 | task 10352 | stop processing: n_tokens = 1621, truncated = 0 10.32.719.160 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.659 10.32.719.202 I slot launch_slot_: id 2 | task 10812 | processing task, is_child = 0 10.33.423.925 I slot print_timing: id 1 | task 10345 | n_gen = 464, tg = 19.23 t/s, tg_3s = 16.56 t/s 10.33.424.193 I slot print_timing: id 3 | task 9954 | n_gen = 853, tg = 19.31 t/s, tg_3s = 16.36 t/s 10.34.960.917 I slot print_timing: id 0 | task 10505 | n_gen = 338, tg = 20.14 t/s, tg_3s = 16.27 t/s 10.36.439.608 I slot print_timing: id 1 | task 10345 | n_gen = 527, tg = 19.41 t/s, tg_3s = 20.89 t/s 10.36.440.967 I slot print_timing: id 3 | task 9954 | n_gen = 916, tg = 19.41 t/s, tg_3s = 20.88 t/s 10.37.979.338 I slot print_timing: id 0 | task 10505 | n_gen = 401, tg = 20.25 t/s, tg_3s = 20.87 t/s 10.38.221.984 I slot print_timing: id 2 | task 10812 | n_gen = 100, tg = 21.02 t/s, tg_3s = 21.23 t/s 10.39.473.189 I slot print_timing: id 1 | task 10345 | n_gen = 590, tg = 19.55 t/s, tg_3s = 20.77 t/s 10.39.474.462 I slot print_timing: id 3 | task 9954 | n_gen = 979, tg = 19.50 t/s, tg_3s = 20.77 t/s 10.41.017.092 I slot print_timing: id 0 | task 10505 | n_gen = 464, tg = 20.32 t/s, tg_3s = 20.74 t/s 10.41.258.760 I slot print_timing: id 2 | task 10812 | n_gen = 163, tg = 20.91 t/s, tg_3s = 20.75 t/s 10.41.645.238 I slot print_timing: id 3 | task 9954 | prompt eval time = 778.21 ms / 471 tokens ( 1.65 ms per token, 605.24 tokens per second) 10.41.645.243 I slot print_timing: id 3 | task 9954 | eval time = 52332.91 ms / 1024 tokens ( 51.16 ms per token, 19.55 tokens per second) 10.41.645.244 I slot print_timing: id 3 | task 9954 | total time = 53111.11 ms / 1495 tokens 10.41.645.245 I slot print_timing: id 3 | task 9954 | graphs reused = 10357 10.41.645.246 I slot print_timing: id 3 | task 9954 | graph reallocs = 0 / 0 (same size) / (changed size) 10.41.645.392 I slot release: id 3 | task 9954 | stop processing: n_tokens = 2189, truncated = 0 10.41.686.482 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.488 10.41.693.105 I slot launch_slot_: id 3 | task 10986 | processing task, is_child = 0 10.42.513.146 I slot print_timing: id 1 | task 10345 | n_gen = 639, tg = 19.23 t/s, tg_3s = 16.12 t/s 10.44.019.299 I slot print_timing: id 0 | task 10505 | n_gen = 513, tg = 19.85 t/s, tg_3s = 16.32 t/s 10.44.261.284 I slot print_timing: id 2 | task 10812 | n_gen = 212, tg = 19.63 t/s, tg_3s = 16.32 t/s 10.45.552.592 I slot print_timing: id 1 | task 10345 | n_gen = 703, tg = 19.39 t/s, tg_3s = 21.06 t/s 10.47.031.218 I slot print_timing: id 0 | task 10505 | n_gen = 576, tg = 19.96 t/s, tg_3s = 20.92 t/s 10.47.176.633 I slot print_timing: id 3 | task 10986 | n_gen = 100, tg = 21.01 t/s, tg_3s = 21.23 t/s 10.47.271.763 I slot print_timing: id 2 | task 10812 | n_gen = 275, tg = 19.91 t/s, tg_3s = 20.93 t/s 10.47.748.321 I slot print_timing: id 1 | task 10345 | prompt eval time = 789.87 ms / 474 tokens ( 1.67 ms per token, 600.10 tokens per second) 10.47.748.333 I slot print_timing: id 1 | task 10345 | eval time = 38405.40 ms / 749 tokens ( 51.34 ms per token, 19.48 tokens per second) 10.47.748.334 I slot print_timing: id 1 | task 10345 | total time = 39195.27 ms / 1223 tokens 10.47.748.335 I slot print_timing: id 1 | task 10345 | graphs reused = 10466 10.47.748.336 I slot print_timing: id 1 | task 10345 | graph reallocs = 0 / 0 (same size) / (changed size) 10.47.748.466 I slot release: id 1 | task 10345 | stop processing: n_tokens = 1895, truncated = 0 10.47.798.127 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.564 10.47.798.178 I slot launch_slot_: id 1 | task 11101 | processing task, is_child = 0 10.50.050.244 I slot print_timing: id 0 | task 10505 | n_gen = 625, tg = 19.61 t/s, tg_3s = 16.23 t/s 10.50.196.578 I slot print_timing: id 3 | task 10986 | n_gen = 149, tg = 19.14 t/s, tg_3s = 16.23 t/s 10.50.291.832 I slot print_timing: id 2 | task 10812 | n_gen = 324, tg = 19.25 t/s, tg_3s = 16.22 t/s 10.52.212.898 I slot print_timing: id 2 | task 10812 | prompt eval time = 793.14 ms / 478 tokens ( 1.66 ms per token, 602.67 tokens per second) 10.52.212.903 I slot print_timing: id 2 | task 10812 | eval time = 18700.54 ms / 364 tokens ( 51.52 ms per token, 19.41 tokens per second) 10.52.212.904 I slot print_timing: id 2 | task 10812 | total time = 19493.68 ms / 842 tokens 10.52.212.905 I slot print_timing: id 2 | task 10812 | graphs reused = 10540 10.52.212.906 I slot print_timing: id 2 | task 10812 | graph reallocs = 0 / 0 (same size) / (changed size) 10.52.213.037 I slot release: id 2 | task 10812 | stop processing: n_tokens = 1528, truncated = 0 10.52.261.985 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.699 10.52.262.025 I slot launch_slot_: id 2 | task 11181 | processing task, is_child = 0 10.53.070.700 I slot print_timing: id 0 | task 10505 | n_gen = 674, tg = 19.32 t/s, tg_3s = 16.22 t/s 10.53.211.331 I slot print_timing: id 3 | task 10986 | n_gen = 198, tg = 18.33 t/s, tg_3s = 16.25 t/s 10.53.959.669 I slot print_timing: id 1 | task 11101 | n_gen = 100, tg = 18.44 t/s, tg_3s = 18.63 t/s 10.56.075.557 I slot print_timing: id 0 | task 10505 | n_gen = 737, tg = 19.45 t/s, tg_3s = 20.97 t/s 10.56.220.833 I slot print_timing: id 3 | task 10986 | n_gen = 261, tg = 18.90 t/s, tg_3s = 20.93 t/s 10.56.984.885 I slot print_timing: id 1 | task 11101 | n_gen = 163, tg = 19.30 t/s, tg_3s = 20.82 t/s 10.57.752.320 I slot print_timing: id 2 | task 11181 | n_gen = 100, tg = 20.93 t/s, tg_3s = 21.15 t/s 10.59.093.654 I slot print_timing: id 0 | task 10505 | n_gen = 800, tg = 19.55 t/s, tg_3s = 20.87 t/s 10.59.240.161 I slot print_timing: id 3 | task 10986 | n_gen = 324, tg = 19.26 t/s, tg_3s = 20.87 t/s 11.00.005.453 I slot print_timing: id 1 | task 11101 | n_gen = 226, tg = 19.71 t/s, tg_3s = 20.86 t/s 11.00.774.418 I slot print_timing: id 2 | task 11181 | n_gen = 163, tg = 20.90 t/s, tg_3s = 20.85 t/s 11.02.118.125 I slot print_timing: id 0 | task 10505 | n_gen = 863, tg = 19.64 t/s, tg_3s = 20.83 t/s 11.02.264.386 I slot print_timing: id 3 | task 10986 | n_gen = 387, tg = 19.50 t/s, tg_3s = 20.83 t/s 11.03.029.921 I slot print_timing: id 1 | task 11101 | n_gen = 289, tg = 19.95 t/s, tg_3s = 20.83 t/s 11.03.797.822 I slot print_timing: id 2 | task 11181 | n_gen = 226, tg = 20.88 t/s, tg_3s = 20.84 t/s 11.05.143.910 I slot print_timing: id 0 | task 10505 | n_gen = 926, tg = 19.72 t/s, tg_3s = 20.82 t/s 11.05.291.191 I slot print_timing: id 3 | task 10986 | n_gen = 450, tg = 19.67 t/s, tg_3s = 20.81 t/s 11.06.061.290 I slot print_timing: id 1 | task 11101 | n_gen = 352, tg = 20.09 t/s, tg_3s = 20.78 t/s 11.06.833.111 I slot print_timing: id 2 | task 11181 | n_gen = 289, tg = 20.85 t/s, tg_3s = 20.76 t/s 11.08.177.321 I slot print_timing: id 0 | task 10505 | n_gen = 989, tg = 19.78 t/s, tg_3s = 20.77 t/s 11.08.324.328 I slot print_timing: id 3 | task 10986 | n_gen = 513, tg = 19.80 t/s, tg_3s = 20.77 t/s 11.09.095.640 I slot print_timing: id 1 | task 11101 | n_gen = 415, tg = 20.19 t/s, tg_3s = 20.76 t/s 11.09.865.994 I slot print_timing: id 0 | task 10505 | prompt eval time = 761.39 ms / 471 tokens ( 1.62 ms per token, 618.61 tokens per second) 11.09.866.002 I slot print_timing: id 0 | task 10505 | eval time = 51635.67 ms / 1024 tokens ( 50.47 ms per token, 19.81 tokens per second) 11.09.866.003 I slot print_timing: id 0 | task 10505 | total time = 52397.06 ms / 1495 tokens 11.09.866.004 I slot print_timing: id 0 | task 10505 | graphs reused = 10889 11.09.866.005 I slot print_timing: id 0 | task 10505 | graph reallocs = 0 / 0 (same size) / (changed size) 11.09.866.113 I slot release: id 0 | task 10505 | stop processing: n_tokens = 2167, truncated = 0 11.09.867.512 I slot print_timing: id 2 | task 11181 | n_gen = 352, tg = 20.84 t/s, tg_3s = 20.76 t/s 11.09.909.081 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.881 (> 0.100 thold), f_keep = 0.493 11.09.914.962 I slot launch_slot_: id 0 | task 11536 | processing task, is_child = 0 11.11.346.500 I slot print_timing: id 3 | task 10986 | n_gen = 558, tg = 19.29 t/s, tg_3s = 14.89 t/s 11.11.393.289 I slot print_timing: id 3 | task 10986 | prompt eval time = 772.41 ms / 469 tokens ( 1.65 ms per token, 607.19 tokens per second) 11.11.393.296 I slot print_timing: id 3 | task 10986 | eval time = 28927.76 ms / 559 tokens ( 51.84 ms per token, 19.29 tokens per second) 11.11.393.296 I slot print_timing: id 3 | task 10986 | total time = 29700.18 ms / 1028 tokens 11.11.393.297 I slot print_timing: id 3 | task 10986 | graphs reused = 10899 11.11.393.297 I slot print_timing: id 3 | task 10986 | graph reallocs = 0 / 0 (same size) / (changed size) 11.11.393.366 I slot release: id 3 | task 10986 | stop processing: n_tokens = 1722, truncated = 0 11.11.431.940 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.620 11.11.431.966 I slot launch_slot_: id 3 | task 11551 | processing task, is_child = 0 11.12.170.143 I slot print_timing: id 1 | task 11101 | n_gen = 448, tg = 18.96 t/s, tg_3s = 10.73 t/s 11.12.870.974 I slot print_timing: id 2 | task 11181 | n_gen = 384, tg = 19.30 t/s, tg_3s = 10.65 t/s 11.14.978.564 I slot print_timing: id 2 | task 11181 | prompt eval time = 761.34 ms / 453 tokens ( 1.68 ms per token, 595.00 tokens per second) 11.14.978.580 I slot print_timing: id 2 | task 11181 | eval time = 21955.19 ms / 429 tokens ( 51.30 ms per token, 19.49 tokens per second) 11.14.978.581 I slot print_timing: id 2 | task 11181 | total time = 22716.53 ms / 882 tokens 11.14.978.582 I slot print_timing: id 2 | task 11181 | graphs reused = 10958 11.14.978.583 I slot print_timing: id 2 | task 11181 | graph reallocs = 0 / 0 (same size) / (changed size) 11.14.978.720 I slot release: id 2 | task 11181 | stop processing: n_tokens = 1568, truncated = 0 11.15.027.959 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.681 11.15.028.000 I slot launch_slot_: id 2 | task 11615 | processing task, is_child = 0 11.15.690.449 I slot print_timing: id 1 | task 11101 | n_gen = 510, tg = 18.78 t/s, tg_3s = 17.61 t/s 11.16.865.501 I slot print_timing: id 0 | task 11536 | n_gen = 100, tg = 16.67 t/s, tg_3s = 16.84 t/s 11.17.487.764 I slot print_timing: id 3 | task 11551 | n_gen = 100, tg = 18.62 t/s, tg_3s = 18.81 t/s 11.17.534.230 I slot print_timing: id 1 | task 11101 | prompt eval time = 793.03 ms / 479 tokens ( 1.66 ms per token, 604.01 tokens per second) 11.17.534.237 I slot print_timing: id 1 | task 11101 | eval time = 28943.01 ms / 548 tokens ( 52.91 ms per token, 18.90 tokens per second) 11.17.534.238 I slot print_timing: id 1 | task 11101 | total time = 29736.04 ms / 1027 tokens 11.17.534.238 I slot print_timing: id 1 | task 11101 | graphs reused = 10994 11.17.534.239 I slot print_timing: id 1 | task 11101 | graph reallocs = 0 / 0 (same size) / (changed size) 11.17.534.351 I slot release: id 1 | task 11101 | stop processing: n_tokens = 1699, truncated = 0 11.17.583.252 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.629 11.17.583.298 I slot launch_slot_: id 1 | task 11656 | processing task, is_child = 0 11.19.866.817 I slot print_timing: id 0 | task 11536 | n_gen = 148, tg = 16.44 t/s, tg_3s = 15.99 t/s 11.20.488.031 I slot print_timing: id 3 | task 11551 | n_gen = 148, tg = 17.67 t/s, tg_3s = 16.00 t/s 11.21.201.536 I slot print_timing: id 2 | task 11615 | n_gen = 100, tg = 18.26 t/s, tg_3s = 18.44 t/s 11.22.868.486 I slot print_timing: id 0 | task 11536 | n_gen = 211, tg = 17.58 t/s, tg_3s = 20.99 t/s 11.23.108.367 I slot print_timing: id 1 | task 11656 | n_gen = 100, tg = 20.93 t/s, tg_3s = 21.14 t/s 11.23.492.194 I slot print_timing: id 3 | task 11551 | n_gen = 211, tg = 18.55 t/s, tg_3s = 20.97 t/s 11.24.207.502 I slot print_timing: id 2 | task 11615 | n_gen = 163, tg = 19.22 t/s, tg_3s = 20.96 t/s 11.25.885.966 I slot print_timing: id 0 | task 11536 | n_gen = 274, tg = 18.25 t/s, tg_3s = 20.88 t/s 11.26.126.036 I slot print_timing: id 1 | task 11656 | n_gen = 163, tg = 20.91 t/s, tg_3s = 20.88 t/s 11.26.510.222 I slot print_timing: id 3 | task 11551 | n_gen = 274, tg = 19.04 t/s, tg_3s = 20.87 t/s 11.27.226.967 I slot print_timing: id 2 | task 11615 | n_gen = 226, tg = 19.65 t/s, tg_3s = 20.86 t/s 11.28.905.578 I slot print_timing: id 0 | task 11536 | n_gen = 337, tg = 18.69 t/s, tg_3s = 20.86 t/s 11.29.146.080 I slot print_timing: id 1 | task 11656 | n_gen = 226, tg = 20.90 t/s, tg_3s = 20.86 t/s 11.29.531.789 I slot print_timing: id 3 | task 11551 | n_gen = 337, tg = 19.35 t/s, tg_3s = 20.85 t/s 11.30.252.120 I slot print_timing: id 2 | task 11615 | n_gen = 289, tg = 19.90 t/s, tg_3s = 20.83 t/s 11.30.589.869 I slot print_timing: id 3 | task 11551 | prompt eval time = 738.82 ms / 440 tokens ( 1.68 ms per token, 595.55 tokens per second) 11.30.589.876 I slot print_timing: id 3 | task 11551 | eval time = 18419.08 ms / 359 tokens ( 51.45 ms per token, 19.44 tokens per second) 11.30.589.877 I slot print_timing: id 3 | task 11551 | total time = 19157.89 ms / 799 tokens 11.30.589.878 I slot print_timing: id 3 | task 11551 | graphs reused = 11247 11.30.589.879 I slot print_timing: id 3 | task 11551 | graph reallocs = 0 / 0 (same size) / (changed size) 11.30.590.018 I slot release: id 3 | task 11551 | stop processing: n_tokens = 1493, truncated = 0 11.30.631.271 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.715 11.30.631.310 I slot launch_slot_: id 3 | task 11915 | processing task, is_child = 0 11.31.935.139 I slot print_timing: id 0 | task 11536 | n_gen = 387, tg = 18.37 t/s, tg_3s = 16.50 t/s 11.32.170.997 I slot print_timing: id 1 | task 11656 | n_gen = 276, tg = 19.94 t/s, tg_3s = 16.53 t/s 11.33.280.227 I slot print_timing: id 2 | task 11615 | n_gen = 339, tg = 19.31 t/s, tg_3s = 16.51 t/s 11.34.428.196 I slot print_timing: id 2 | task 11615 | prompt eval time = 750.49 ms / 437 tokens ( 1.72 ms per token, 582.29 tokens per second) 11.34.428.201 I slot print_timing: id 2 | task 11615 | eval time = 18649.69 ms / 363 tokens ( 51.52 ms per token, 19.41 tokens per second) 11.34.428.202 I slot print_timing: id 2 | task 11615 | total time = 19400.18 ms / 800 tokens 11.34.428.203 I slot print_timing: id 2 | task 11615 | graphs reused = 11310 11.34.428.204 I slot print_timing: id 2 | task 11615 | graph reallocs = 0 / 0 (same size) / (changed size) 11.34.428.330 I slot release: id 2 | task 11615 | stop processing: n_tokens = 1486, truncated = 0 11.34.477.251 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.719 11.34.477.292 I slot launch_slot_: id 2 | task 11983 | processing task, is_child = 0 11.35.169.404 I slot print_timing: id 0 | task 11536 | n_gen = 441, tg = 18.15 t/s, tg_3s = 16.70 t/s 11.35.257.822 I slot print_timing: id 1 | task 11656 | n_gen = 326, tg = 19.25 t/s, tg_3s = 16.20 t/s 11.35.536.764 I slot print_timing: id 0 | task 11536 | prompt eval time = 1011.38 ms / 539 tokens ( 1.88 ms per token, 532.93 tokens per second) 11.35.536.766 I slot print_timing: id 0 | task 11536 | eval time = 24610.41 ms / 448 tokens ( 55.06 ms per token, 18.16 tokens per second) 11.35.536.766 I slot print_timing: id 0 | task 11536 | total time = 25621.79 ms / 987 tokens 11.35.536.767 I slot print_timing: id 0 | task 11536 | graphs reused = 11315 11.35.536.767 I slot print_timing: id 0 | task 11536 | graph reallocs = 0 / 0 (same size) / (changed size) 11.35.536.831 I slot release: id 0 | task 11536 | stop processing: n_tokens = 1659, truncated = 0 11.35.575.952 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.644 11.35.575.977 I slot launch_slot_: id 0 | task 11993 | processing task, is_child = 0 11.37.391.274 I slot print_timing: id 3 | task 11915 | n_gen = 100, tg = 16.46 t/s, tg_3s = 16.63 t/s 11.38.298.036 I slot print_timing: id 1 | task 11656 | n_gen = 377, tg = 18.88 t/s, tg_3s = 16.78 t/s 11.40.410.439 I slot print_timing: id 3 | task 11915 | n_gen = 163, tg = 17.93 t/s, tg_3s = 20.87 t/s 11.40.602.011 I slot print_timing: id 2 | task 11983 | n_gen = 100, tg = 18.53 t/s, tg_3s = 18.71 t/s 11.41.032.624 I slot print_timing: id 0 | task 11993 | n_gen = 100, tg = 20.94 t/s, tg_3s = 21.15 t/s 11.41.321.573 I slot print_timing: id 1 | task 11656 | n_gen = 440, tg = 19.13 t/s, tg_3s = 20.84 t/s 11.43.436.360 I slot print_timing: id 3 | task 11915 | n_gen = 226, tg = 18.66 t/s, tg_3s = 20.82 t/s 11.43.628.210 I slot print_timing: id 2 | task 11983 | n_gen = 163, tg = 19.35 t/s, tg_3s = 20.82 t/s 11.44.059.690 I slot print_timing: id 0 | task 11993 | n_gen = 163, tg = 20.89 t/s, tg_3s = 20.81 t/s 11.44.346.367 I slot print_timing: id 1 | task 11656 | n_gen = 503, tg = 19.33 t/s, tg_3s = 20.83 t/s 11.46.449.710 I slot print_timing: id 3 | task 11915 | n_gen = 289, tg = 19.11 t/s, tg_3s = 20.91 t/s 11.46.640.808 I slot print_timing: id 2 | task 11983 | n_gen = 226, tg = 19.77 t/s, tg_3s = 20.91 t/s 11.47.070.306 I slot print_timing: id 0 | task 11993 | n_gen = 226, tg = 20.90 t/s, tg_3s = 20.93 t/s 11.47.358.606 I slot print_timing: id 1 | task 11656 | n_gen = 566, tg = 19.50 t/s, tg_3s = 20.91 t/s 11.49.468.043 I slot print_timing: id 3 | task 11915 | n_gen = 352, tg = 19.40 t/s, tg_3s = 20.87 t/s 11.49.659.224 I slot print_timing: id 2 | task 11983 | n_gen = 289, tg = 20.00 t/s, tg_3s = 20.87 t/s 11.50.089.175 I slot print_timing: id 0 | task 11993 | n_gen = 289, tg = 20.89 t/s, tg_3s = 20.87 t/s 11.50.378.201 I slot print_timing: id 1 | task 11656 | n_gen = 629, tg = 19.63 t/s, tg_3s = 20.86 t/s 11.52.496.391 I slot print_timing: id 3 | task 11915 | n_gen = 415, tg = 19.60 t/s, tg_3s = 20.80 t/s 11.52.687.134 I slot print_timing: id 2 | task 11983 | n_gen = 352, tg = 20.14 t/s, tg_3s = 20.81 t/s 11.53.115.691 I slot print_timing: id 0 | task 11993 | n_gen = 352, tg = 20.88 t/s, tg_3s = 20.82 t/s 11.53.402.921 I slot print_timing: id 1 | task 11656 | n_gen = 692, tg = 19.73 t/s, tg_3s = 20.83 t/s 11.55.514.934 I slot print_timing: id 3 | task 11915 | n_gen = 478, tg = 19.76 t/s, tg_3s = 20.87 t/s 11.55.707.324 I slot print_timing: id 2 | task 11983 | n_gen = 415, tg = 20.25 t/s, tg_3s = 20.86 t/s 11.56.140.362 I slot print_timing: id 0 | task 11993 | n_gen = 415, tg = 20.87 t/s, tg_3s = 20.83 t/s 11.56.429.896 I slot print_timing: id 1 | task 11656 | n_gen = 755, tg = 19.82 t/s, tg_3s = 20.81 t/s 11.57.969.594 I slot print_timing: id 1 | task 11656 | prompt eval time = 795.72 ms / 483 tokens ( 1.65 ms per token, 607.00 tokens per second) 11.57.969.599 I slot print_timing: id 1 | task 11656 | eval time = 39590.57 ms / 787 tokens ( 50.37 ms per token, 19.85 tokens per second) 11.57.969.600 I slot print_timing: id 1 | task 11656 | total time = 40386.29 ms / 1270 tokens 11.57.969.601 I slot print_timing: id 1 | task 11656 | graphs reused = 11765 11.57.969.602 I slot print_timing: id 1 | task 11656 | graph reallocs = 0 / 0 (same size) / (changed size) 11.57.969.719 I slot release: id 1 | task 11656 | stop processing: n_tokens = 1942, truncated = 0 11.58.019.139 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.550 11.58.019.176 I slot launch_slot_: id 1 | task 12449 | processing task, is_child = 0 11.58.726.220 I slot print_timing: id 2 | task 11983 | n_gen = 464, tg = 19.73 t/s, tg_3s = 16.23 t/s 11.58.726.510 I slot print_timing: id 3 | task 11915 | n_gen = 531, tg = 19.38 t/s, tg_3s = 16.50 t/s 11.59.142.083 I slot print_timing: id 0 | task 11993 | n_gen = 463, tg = 20.23 t/s, tg_3s = 15.99 t/s 12.01.757.483 I slot print_timing: id 2 | task 11983 | n_gen = 527, tg = 19.85 t/s, tg_3s = 20.78 t/s 12.01.758.077 I slot print_timing: id 3 | task 11915 | n_gen = 594, tg = 19.52 t/s, tg_3s = 20.78 t/s 12.02.189.940 I slot print_timing: id 0 | task 11993 | n_gen = 527, tg = 20.32 t/s, tg_3s = 21.00 t/s 12.02.432.155 I slot print_timing: id 3 | task 11915 | prompt eval time = 745.49 ms / 447 tokens ( 1.67 ms per token, 599.61 tokens per second) 12.02.432.162 I slot print_timing: id 3 | task 11915 | eval time = 31055.35 ms / 608 tokens ( 51.16 ms per token, 19.55 tokens per second) 12.02.432.163 I slot print_timing: id 3 | task 11915 | total time = 31800.84 ms / 1055 tokens 12.02.432.165 I slot print_timing: id 3 | task 11915 | graphs reused = 11840 12.02.432.166 I slot print_timing: id 3 | task 11915 | graph reallocs = 0 / 0 (same size) / (changed size) 12.02.432.300 I slot release: id 3 | task 11915 | stop processing: n_tokens = 1749, truncated = 0 12.02.473.663 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.611 12.02.473.697 I slot launch_slot_: id 3 | task 12529 | processing task, is_child = 0 12.04.176.284 I slot print_timing: id 1 | task 12449 | n_gen = 100, tg = 18.47 t/s, tg_3s = 18.65 t/s 12.04.805.181 I slot print_timing: id 2 | task 11983 | n_gen = 577, tg = 19.49 t/s, tg_3s = 16.41 t/s 12.05.234.843 I slot print_timing: id 0 | task 11993 | n_gen = 577, tg = 19.91 t/s, tg_3s = 16.42 t/s 12.07.199.674 I slot print_timing: id 1 | task 12449 | n_gen = 163, tg = 19.32 t/s, tg_3s = 20.84 t/s 12.07.820.598 I slot print_timing: id 2 | task 11983 | n_gen = 640, tg = 19.62 t/s, tg_3s = 20.89 t/s 12.07.964.199 I slot print_timing: id 3 | task 12529 | n_gen = 100, tg = 20.97 t/s, tg_3s = 21.19 t/s 12.08.250.249 I slot print_timing: id 0 | task 11993 | n_gen = 640, tg = 20.00 t/s, tg_3s = 20.89 t/s 12.09.203.571 I slot print_timing: id 0 | task 11993 | prompt eval time = 728.26 ms / 445 tokens ( 1.64 ms per token, 611.05 tokens per second) 12.09.203.576 I slot print_timing: id 0 | task 11993 | eval time = 32899.33 ms / 660 tokens ( 49.92 ms per token, 20.03 tokens per second) 12.09.203.577 I slot print_timing: id 0 | task 11993 | total time = 33627.59 ms / 1105 tokens 12.09.203.577 I slot print_timing: id 0 | task 11993 | graphs reused = 11963 12.09.203.578 I slot print_timing: id 0 | task 11993 | graph reallocs = 0 / 0 (same size) / (changed size) 12.09.203.695 I slot release: id 0 | task 11993 | stop processing: n_tokens = 1800, truncated = 0 12.09.245.712 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.593 12.09.245.752 I slot launch_slot_: id 0 | task 12658 | processing task, is_child = 0 12.10.245.782 I slot print_timing: id 1 | task 12449 | n_gen = 213, tg = 18.55 t/s, tg_3s = 16.41 t/s 12.10.849.887 I slot print_timing: id 2 | task 11983 | n_gen = 690, tg = 19.36 t/s, tg_3s = 16.51 t/s 12.10.989.708 I slot print_timing: id 3 | task 12529 | n_gen = 150, tg = 19.24 t/s, tg_3s = 16.53 t/s 12.13.263.447 I slot print_timing: id 1 | task 12449 | n_gen = 278, tg = 19.17 t/s, tg_3s = 21.54 t/s 12.13.869.848 I slot print_timing: id 2 | task 11983 | n_gen = 755, tg = 19.53 t/s, tg_3s = 21.52 t/s 12.14.009.306 I slot print_timing: id 3 | task 12529 | n_gen = 215, tg = 19.88 t/s, tg_3s = 21.53 t/s 12.14.622.184 I slot print_timing: id 0 | task 12658 | n_gen = 100, tg = 21.47 t/s, tg_3s = 21.69 t/s 12.16.295.798 I slot print_timing: id 1 | task 12449 | n_gen = 342, tg = 19.51 t/s, tg_3s = 21.11 t/s 12.16.871.288 I slot print_timing: id 2 | task 11983 | n_gen = 818, tg = 19.63 t/s, tg_3s = 20.99 t/s 12.16.967.545 I slot print_timing: id 2 | task 11983 | prompt eval time = 780.83 ms / 462 tokens ( 1.69 ms per token, 591.68 tokens per second) 12.16.967.552 I slot print_timing: id 2 | task 11983 | eval time = 41709.41 ms / 820 tokens ( 50.93 ms per token, 19.64 tokens per second) 12.16.967.554 I slot print_timing: id 2 | task 11983 | total time = 42490.24 ms / 1282 tokens 12.16.967.555 I slot print_timing: id 2 | task 11983 | graphs reused = 12111 12.16.967.556 I slot print_timing: id 2 | task 11983 | graph reallocs = 0 / 0 (same size) / (changed size) 12.16.967.674 I slot release: id 2 | task 11983 | stop processing: n_tokens = 1968, truncated = 0 12.17.016.567 I slot print_timing: id 3 | task 12529 | n_gen = 278, tg = 20.11 t/s, tg_3s = 20.95 t/s 12.17.016.579 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.543 12.17.016.618 I slot launch_slot_: id 2 | task 12810 | processing task, is_child = 0 12.17.715.324 I slot print_timing: id 0 | task 12658 | n_gen = 151, tg = 19.47 t/s, tg_3s = 16.49 t/s 12.19.332.697 I slot print_timing: id 1 | task 12449 | n_gen = 391, tg = 19.01 t/s, tg_3s = 16.13 t/s 12.20.051.073 I slot print_timing: id 3 | task 12529 | n_gen = 327, tg = 19.40 t/s, tg_3s = 16.15 t/s 12.20.719.501 I slot print_timing: id 0 | task 12658 | n_gen = 213, tg = 19.80 t/s, tg_3s = 20.64 t/s 12.21.770.895 I slot print_timing: id 1 | task 12449 | prompt eval time = 796.07 ms / 482 tokens ( 1.65 ms per token, 605.47 tokens per second) 12.21.770.904 I slot print_timing: id 1 | task 12449 | eval time = 22955.64 ms / 442 tokens ( 52.05 ms per token, 19.21 tokens per second) 12.21.770.905 I slot print_timing: id 1 | task 12449 | total time = 23751.71 ms / 924 tokens 12.21.770.914 I slot print_timing: id 1 | task 12449 | graphs reused = 12192 12.21.770.915 I slot print_timing: id 1 | task 12449 | graph reallocs = 0 / 0 (same size) / (changed size) 12.21.771.054 I slot release: id 1 | task 12449 | stop processing: n_tokens = 1596, truncated = 0 12.21.820.221 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.669 12.21.820.263 I slot launch_slot_: id 1 | task 12897 | processing task, is_child = 0 12.23.082.901 I slot print_timing: id 3 | task 12529 | n_gen = 376, tg = 18.90 t/s, tg_3s = 16.16 t/s 12.23.222.293 I slot print_timing: id 2 | task 12810 | n_gen = 100, tg = 18.27 t/s, tg_3s = 18.45 t/s 12.23.734.792 I slot print_timing: id 0 | task 12658 | n_gen = 262, tg = 19.02 t/s, tg_3s = 16.25 t/s 12.26.083.070 I slot print_timing: id 3 | task 12529 | n_gen = 439, tg = 19.18 t/s, tg_3s = 21.00 t/s 12.26.225.349 I slot print_timing: id 2 | task 12810 | n_gen = 163, tg = 19.24 t/s, tg_3s = 20.98 t/s 12.26.749.883 I slot print_timing: id 0 | task 12658 | n_gen = 325, tg = 19.36 t/s, tg_3s = 20.89 t/s 12.27.324.784 I slot print_timing: id 1 | task 12897 | n_gen = 100, tg = 21.02 t/s, tg_3s = 21.24 t/s 12.29.092.780 I slot print_timing: id 3 | task 12529 | n_gen = 502, tg = 19.38 t/s, tg_3s = 20.93 t/s 12.29.234.879 I slot print_timing: id 2 | task 12810 | n_gen = 226, tg = 19.68 t/s, tg_3s = 20.93 t/s 12.29.760.407 I slot print_timing: id 0 | task 12658 | n_gen = 388, tg = 19.60 t/s, tg_3s = 20.93 t/s 12.30.335.786 I slot print_timing: id 1 | task 12897 | n_gen = 163, tg = 20.99 t/s, tg_3s = 20.92 t/s 12.32.110.275 I slot print_timing: id 3 | task 12529 | n_gen = 565, tg = 19.54 t/s, tg_3s = 20.88 t/s 12.32.253.360 I slot print_timing: id 2 | task 12810 | n_gen = 289, tg = 19.93 t/s, tg_3s = 20.87 t/s 12.32.780.066 I slot print_timing: id 0 | task 12658 | n_gen = 451, tg = 19.76 t/s, tg_3s = 20.86 t/s 12.33.359.662 I slot print_timing: id 1 | task 12897 | n_gen = 226, tg = 20.94 t/s, tg_3s = 20.83 t/s 12.35.144.201 I slot print_timing: id 3 | task 12529 | n_gen = 628, tg = 19.66 t/s, tg_3s = 20.77 t/s 12.35.287.247 I slot print_timing: id 2 | task 12810 | n_gen = 352, tg = 20.08 t/s, tg_3s = 20.77 t/s 12.35.814.518 I slot print_timing: id 0 | task 12658 | n_gen = 514, tg = 19.88 t/s, tg_3s = 20.76 t/s 12.36.391.007 I slot print_timing: id 1 | task 12897 | n_gen = 289, tg = 20.91 t/s, tg_3s = 20.78 t/s 12.37.779.532 I slot print_timing: id 0 | task 12658 | prompt eval time = 766.31 ms / 482 tokens ( 1.59 ms per token, 628.99 tokens per second) 12.37.779.539 I slot print_timing: id 0 | task 12658 | eval time = 27767.46 ms / 555 tokens ( 50.12 ms per token, 19.95 tokens per second) 12.37.779.540 I slot print_timing: id 0 | task 12658 | total time = 28533.77 ms / 1037 tokens 12.37.779.541 I slot print_timing: id 0 | task 12658 | graphs reused = 12506 12.37.779.542 I slot print_timing: id 0 | task 12658 | graph reallocs = 0 / 0 (same size) / (changed size) 12.37.779.659 I slot release: id 0 | task 12658 | stop processing: n_tokens = 1732, truncated = 0 12.37.822.168 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.617 12.37.822.213 I slot launch_slot_: id 0 | task 13218 | processing task, is_child = 0 12.38.474.357 I slot print_timing: id 2 | task 12810 | n_gen = 406, tg = 19.59 t/s, tg_3s = 16.94 t/s 12.38.474.635 I slot print_timing: id 3 | task 12529 | n_gen = 685, tg = 19.42 t/s, tg_3s = 17.11 t/s 12.38.926.365 I slot print_timing: id 3 | task 12529 | prompt eval time = 770.56 ms / 463 tokens ( 1.66 ms per token, 600.86 tokens per second) 12.38.926.371 I slot print_timing: id 3 | task 12529 | eval time = 35682.10 ms / 694 tokens ( 51.49 ms per token, 19.42 tokens per second) 12.38.926.371 I slot print_timing: id 3 | task 12529 | total time = 36452.65 ms / 1157 tokens 12.38.926.372 I slot print_timing: id 3 | task 12529 | graphs reused = 12514 12.38.926.372 I slot print_timing: id 3 | task 12529 | graph reallocs = 0 / 0 (same size) / (changed size) 12.38.926.432 I slot release: id 3 | task 12529 | stop processing: n_tokens = 1851, truncated = 0 12.38.964.646 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.577 12.38.964.670 I slot launch_slot_: id 3 | task 13230 | processing task, is_child = 0 12.39.621.298 I slot print_timing: id 1 | task 12897 | n_gen = 331, tg = 19.41 t/s, tg_3s = 13.00 t/s 12.41.518.391 I slot print_timing: id 2 | task 12810 | n_gen = 457, tg = 19.23 t/s, tg_3s = 16.75 t/s 12.42.653.343 I slot print_timing: id 1 | task 12897 | n_gen = 395, tg = 19.66 t/s, tg_3s = 21.11 t/s 12.43.847.721 I slot print_timing: id 0 | task 13218 | n_gen = 100, tg = 18.70 t/s, tg_3s = 18.89 t/s 12.44.039.398 I slot print_timing: id 1 | task 12897 | prompt eval time = 795.76 ms / 479 tokens ( 1.66 ms per token, 601.94 tokens per second) 12.44.039.403 I slot print_timing: id 1 | task 12897 | eval time = 21423.36 ms / 424 tokens ( 50.65 ms per token, 19.74 tokens per second) 12.44.039.404 I slot print_timing: id 1 | task 12897 | total time = 22219.12 ms / 903 tokens 12.44.039.405 I slot print_timing: id 1 | task 12897 | graphs reused = 12605 12.44.039.406 I slot print_timing: id 1 | task 12897 | graph reallocs = 0 / 0 (same size) / (changed size) 12.44.039.545 I slot release: id 1 | task 12897 | stop processing: n_tokens = 1575, truncated = 0 12.44.089.205 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.678 12.44.089.251 I slot launch_slot_: id 1 | task 13326 | processing task, is_child = 0 12.44.814.121 I slot print_timing: id 2 | task 12810 | n_gen = 512, tg = 18.92 t/s, tg_3s = 16.69 t/s 12.45.091.322 I slot print_timing: id 3 | task 13230 | n_gen = 100, tg = 18.37 t/s, tg_3s = 18.56 t/s 12.46.868.194 I slot print_timing: id 0 | task 13218 | n_gen = 149, tg = 17.80 t/s, tg_3s = 16.22 t/s 12.47.826.673 I slot print_timing: id 2 | task 12810 | n_gen = 575, tg = 19.12 t/s, tg_3s = 20.91 t/s 12.48.113.821 I slot print_timing: id 3 | task 13230 | n_gen = 164, tg = 19.38 t/s, tg_3s = 21.17 t/s 12.49.593.959 I slot print_timing: id 1 | task 13326 | n_gen = 100, tg = 21.10 t/s, tg_3s = 21.32 t/s 12.49.881.968 I slot print_timing: id 0 | task 13218 | n_gen = 212, tg = 18.62 t/s, tg_3s = 20.90 t/s 12.50.843.598 I slot print_timing: id 2 | task 12810 | n_gen = 638, tg = 19.28 t/s, tg_3s = 20.88 t/s 12.51.130.919 I slot print_timing: id 3 | task 13230 | n_gen = 227, tg = 19.78 t/s, tg_3s = 20.88 t/s 12.52.613.811 I slot print_timing: id 1 | task 13326 | n_gen = 163, tg = 21.01 t/s, tg_3s = 20.86 t/s 12.52.899.726 I slot print_timing: id 0 | task 13218 | n_gen = 275, tg = 19.10 t/s, tg_3s = 20.88 t/s 12.53.860.121 I slot print_timing: id 2 | task 12810 | n_gen = 701, tg = 19.41 t/s, tg_3s = 20.88 t/s 12.54.148.608 I slot print_timing: id 3 | task 13230 | n_gen = 290, tg = 20.01 t/s, tg_3s = 20.88 t/s 12.55.634.414 I slot print_timing: id 1 | task 13326 | n_gen = 226, tg = 20.97 t/s, tg_3s = 20.86 t/s 12.55.921.608 I slot print_timing: id 0 | task 13218 | n_gen = 338, tg = 19.40 t/s, tg_3s = 20.85 t/s 12.56.880.634 I slot print_timing: id 2 | task 12810 | n_gen = 764, tg = 19.53 t/s, tg_3s = 20.86 t/s 12.57.168.360 I slot print_timing: id 3 | task 13230 | n_gen = 353, tg = 20.15 t/s, tg_3s = 20.86 t/s 12.58.648.419 I slot print_timing: id 1 | task 13326 | n_gen = 289, tg = 20.95 t/s, tg_3s = 20.90 t/s 12.58.933.929 I slot print_timing: id 0 | task 13218 | n_gen = 401, tg = 19.63 t/s, tg_3s = 20.91 t/s 12.59.892.465 I slot print_timing: id 2 | task 12810 | n_gen = 827, tg = 19.63 t/s, tg_3s = 20.92 t/s 13.00.180.252 I slot print_timing: id 3 | task 13230 | n_gen = 416, tg = 20.27 t/s, tg_3s = 20.92 t/s 13.01.669.402 I slot print_timing: id 1 | task 13326 | n_gen = 352, tg = 20.93 t/s, tg_3s = 20.85 t/s 13.01.958.270 I slot print_timing: id 0 | task 13218 | n_gen = 464, tg = 19.78 t/s, tg_3s = 20.83 t/s 13.02.920.012 I slot print_timing: id 2 | task 12810 | n_gen = 890, tg = 19.70 t/s, tg_3s = 20.81 t/s 13.03.211.315 I slot print_timing: id 3 | task 13230 | n_gen = 479, tg = 20.33 t/s, tg_3s = 20.78 t/s 13.04.707.307 I slot print_timing: id 1 | task 13326 | n_gen = 415, tg = 20.90 t/s, tg_3s = 20.74 t/s 13.04.996.179 I slot print_timing: id 0 | task 13218 | n_gen = 527, tg = 19.89 t/s, tg_3s = 20.74 t/s 13.05.961.438 I slot print_timing: id 2 | task 12810 | n_gen = 953, tg = 19.77 t/s, tg_3s = 20.71 t/s 13.06.251.005 I slot print_timing: id 3 | task 13230 | n_gen = 542, tg = 20.38 t/s, tg_3s = 20.73 t/s 13.07.745.002 I slot print_timing: id 1 | task 13326 | n_gen = 478, tg = 20.88 t/s, tg_3s = 20.74 t/s 13.08.034.180 I slot print_timing: id 0 | task 13218 | n_gen = 590, tg = 19.98 t/s, tg_3s = 20.74 t/s 13.08.132.077 I slot print_timing: id 2 | task 12810 | prompt eval time = 787.06 ms / 471 tokens ( 1.67 ms per token, 598.43 tokens per second) 13.08.132.086 I slot print_timing: id 2 | task 12810 | eval time = 50328.39 ms / 998 tokens ( 50.48 ms per token, 19.81 tokens per second) 13.08.132.087 I slot print_timing: id 2 | task 12810 | total time = 51115.45 ms / 1469 tokens 13.08.132.088 I slot print_timing: id 2 | task 12810 | graphs reused = 13087 13.08.132.089 I slot print_timing: id 2 | task 12810 | graph reallocs = 0 / 0 (same size) / (changed size) 13.08.132.224 I slot release: id 2 | task 12810 | stop processing: n_tokens = 2155, truncated = 0 13.08.181.556 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.496 13.08.187.919 I slot launch_slot_: id 2 | task 13815 | processing task, is_child = 0 13.09.260.818 I slot print_timing: id 3 | task 13230 | n_gen = 588, tg = 19.86 t/s, tg_3s = 15.28 t/s 13.10.759.074 I slot print_timing: id 1 | task 13326 | n_gen = 525, tg = 20.27 t/s, tg_3s = 15.59 t/s 13.11.046.472 I slot print_timing: id 0 | task 13218 | n_gen = 637, tg = 19.57 t/s, tg_3s = 15.60 t/s 13.12.300.780 I slot print_timing: id 3 | task 13230 | n_gen = 652, tg = 19.97 t/s, tg_3s = 21.05 t/s 13.13.793.923 I slot print_timing: id 1 | task 13326 | n_gen = 588, tg = 20.32 t/s, tg_3s = 20.76 t/s 13.13.842.736 I slot print_timing: id 2 | task 13815 | n_gen = 100, tg = 20.96 t/s, tg_3s = 21.17 t/s 13.14.083.050 I slot print_timing: id 0 | task 13218 | n_gen = 700, tg = 19.67 t/s, tg_3s = 20.75 t/s 13.15.335.962 I slot print_timing: id 3 | task 13230 | n_gen = 715, tg = 20.04 t/s, tg_3s = 20.76 t/s 13.16.822.206 I slot print_timing: id 1 | task 13326 | n_gen = 651, tg = 20.36 t/s, tg_3s = 20.80 t/s 13.16.870.916 I slot print_timing: id 2 | task 13815 | n_gen = 163, tg = 20.90 t/s, tg_3s = 20.80 t/s 13.17.111.403 I slot print_timing: id 0 | task 13218 | n_gen = 763, tg = 19.76 t/s, tg_3s = 20.80 t/s 13.18.362.653 I slot print_timing: id 3 | task 13230 | n_gen = 778, tg = 20.10 t/s, tg_3s = 20.81 t/s 13.19.852.359 I slot print_timing: id 1 | task 13326 | n_gen = 714, tg = 20.40 t/s, tg_3s = 20.79 t/s 13.19.901.042 I slot print_timing: id 2 | task 13815 | n_gen = 226, tg = 20.87 t/s, tg_3s = 20.79 t/s 13.20.140.281 I slot print_timing: id 0 | task 13218 | n_gen = 826, tg = 19.84 t/s, tg_3s = 20.80 t/s 13.21.397.026 I slot print_timing: id 3 | task 13230 | n_gen = 841, tg = 20.15 t/s, tg_3s = 20.76 t/s 13.22.892.391 I slot print_timing: id 1 | task 13326 | n_gen = 777, tg = 20.43 t/s, tg_3s = 20.72 t/s 13.22.941.285 I slot print_timing: id 2 | task 13815 | n_gen = 289, tg = 20.84 t/s, tg_3s = 20.72 t/s 13.23.181.355 I slot print_timing: id 0 | task 13218 | n_gen = 889, tg = 19.90 t/s, tg_3s = 20.72 t/s 13.24.441.195 I slot print_timing: id 3 | task 13230 | n_gen = 904, tg = 20.18 t/s, tg_3s = 20.70 t/s 13.25.937.286 I slot print_timing: id 1 | task 13326 | n_gen = 840, tg = 20.45 t/s, tg_3s = 20.69 t/s 13.25.986.474 I slot print_timing: id 2 | task 13815 | n_gen = 352, tg = 20.81 t/s, tg_3s = 20.69 t/s 13.26.227.396 I slot print_timing: id 0 | task 13218 | n_gen = 952, tg = 19.95 t/s, tg_3s = 20.68 t/s 13.27.483.582 I slot print_timing: id 3 | task 13230 | n_gen = 967, tg = 20.22 t/s, tg_3s = 20.71 t/s 13.28.975.996 I slot print_timing: id 1 | task 13326 | n_gen = 903, tg = 20.47 t/s, tg_3s = 20.73 t/s 13.29.024.562 I slot print_timing: id 2 | task 13815 | n_gen = 415, tg = 20.80 t/s, tg_3s = 20.74 t/s 13.29.263.299 I slot print_timing: id 0 | task 13218 | n_gen = 1015, tg = 20.00 t/s, tg_3s = 20.75 t/s 13.29.697.656 I slot print_timing: id 0 | task 13218 | prompt eval time = 730.67 ms / 446 tokens ( 1.64 ms per token, 610.40 tokens per second) 13.29.697.664 I slot print_timing: id 0 | task 13218 | eval time = 51144.76 ms / 1024 tokens ( 49.99 ms per token, 20.00 tokens per second) 13.29.697.665 I slot print_timing: id 0 | task 13218 | total time = 51875.43 ms / 1470 tokens 13.29.697.666 I slot print_timing: id 0 | task 13218 | graphs reused = 13512 13.29.697.666 I slot print_timing: id 0 | task 13218 | graph reallocs = 0 / 0 (same size) / (changed size) 13.29.697.776 I slot release: id 0 | task 13218 | stop processing: n_tokens = 2165, truncated = 0 13.29.741.150 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.493 13.29.748.124 I slot launch_slot_: id 0 | task 14248 | processing task, is_child = 0 13.30.501.481 I slot print_timing: id 3 | task 13230 | n_gen = 1016, tg = 19.98 t/s, tg_3s = 16.24 t/s 13.30.890.401 I slot print_timing: id 3 | task 13230 | prompt eval time = 738.62 ms / 443 tokens ( 1.67 ms per token, 599.76 tokens per second) 13.30.890.406 I slot print_timing: id 3 | task 13230 | eval time = 51187.10 ms / 1024 tokens ( 50.04 ms per token, 19.99 tokens per second) 13.30.890.409 I slot print_timing: id 3 | task 13230 | total time = 51925.72 ms / 1467 tokens 13.30.890.412 I slot print_timing: id 3 | task 13230 | graphs reused = 13520 13.30.890.413 I slot print_timing: id 3 | task 13230 | graph reallocs = 0 / 0 (same size) / (changed size) 13.30.890.528 I slot release: id 3 | task 13230 | stop processing: n_tokens = 2161, truncated = 0 13.30.931.730 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.494 13.30.938.620 I slot launch_slot_: id 3 | task 14260 | processing task, is_child = 0 13.32.013.948 I slot print_timing: id 1 | task 13326 | n_gen = 939, tg = 19.91 t/s, tg_3s = 11.85 t/s 13.32.061.205 I slot print_timing: id 2 | task 13815 | n_gen = 451, tg = 19.61 t/s, tg_3s = 11.86 t/s 13.35.053.286 I slot print_timing: id 1 | task 13326 | n_gen = 1002, tg = 19.96 t/s, tg_3s = 20.73 t/s 13.35.101.863 I slot print_timing: id 2 | task 13815 | n_gen = 514, tg = 19.74 t/s, tg_3s = 20.72 t/s 13.35.917.175 I slot print_timing: id 0 | task 14248 | n_gen = 100, tg = 18.28 t/s, tg_3s = 18.46 t/s 13.36.109.862 I slot print_timing: id 1 | task 13326 | prompt eval time = 813.86 ms / 494 tokens ( 1.65 ms per token, 606.98 tokens per second) 13.36.109.868 I slot print_timing: id 1 | task 13326 | eval time = 51206.74 ms / 1024 tokens ( 50.06 ms per token, 19.98 tokens per second) 13.36.109.869 I slot print_timing: id 1 | task 13326 | total time = 52020.60 ms / 1518 tokens 13.36.109.870 I slot print_timing: id 1 | task 13326 | graphs reused = 13611 13.36.109.871 I slot print_timing: id 1 | task 13326 | graph reallocs = 0 / 0 (same size) / (changed size) 13.36.109.984 I slot release: id 1 | task 13326 | stop processing: n_tokens = 2190, truncated = 0 13.36.158.897 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.488 13.36.166.671 I slot launch_slot_: id 1 | task 14356 | processing task, is_child = 0 13.37.147.003 I slot print_timing: id 3 | task 14260 | n_gen = 100, tg = 18.13 t/s, tg_3s = 18.31 t/s 13.38.148.706 I slot print_timing: id 2 | task 13815 | n_gen = 563, tg = 19.36 t/s, tg_3s = 16.08 t/s 13.38.958.723 I slot print_timing: id 0 | task 14248 | n_gen = 149, tg = 17.50 t/s, tg_3s = 16.11 t/s 13.40.157.569 I slot print_timing: id 3 | task 14260 | n_gen = 163, tg = 19.12 t/s, tg_3s = 20.93 t/s 13.41.159.519 I slot print_timing: id 2 | task 13815 | n_gen = 626, tg = 19.51 t/s, tg_3s = 20.92 t/s 13.41.685.364 I slot print_timing: id 1 | task 14356 | n_gen = 100, tg = 20.95 t/s, tg_3s = 21.16 t/s 13.41.972.241 I slot print_timing: id 0 | task 14248 | n_gen = 212, tg = 18.39 t/s, tg_3s = 20.91 t/s 13.43.173.419 I slot print_timing: id 3 | task 14260 | n_gen = 226, tg = 19.59 t/s, tg_3s = 20.89 t/s 13.44.179.039 I slot print_timing: id 2 | task 13815 | n_gen = 689, tg = 19.62 t/s, tg_3s = 20.86 t/s 13.44.707.051 I slot print_timing: id 1 | task 14356 | n_gen = 163, tg = 20.91 t/s, tg_3s = 20.85 t/s 13.44.994.651 I slot print_timing: id 0 | task 14248 | n_gen = 275, tg = 18.90 t/s, tg_3s = 20.84 t/s 13.46.193.614 I slot print_timing: id 3 | task 14260 | n_gen = 289, tg = 19.85 t/s, tg_3s = 20.86 t/s 13.47.202.107 I slot print_timing: id 2 | task 13815 | n_gen = 752, tg = 19.72 t/s, tg_3s = 20.84 t/s 13.47.728.167 I slot print_timing: id 1 | task 14356 | n_gen = 226, tg = 20.89 t/s, tg_3s = 20.85 t/s 13.48.015.032 I slot print_timing: id 0 | task 14248 | n_gen = 338, tg = 19.24 t/s, tg_3s = 20.86 t/s 13.49.211.095 I slot print_timing: id 3 | task 14260 | n_gen = 352, tg = 20.03 t/s, tg_3s = 20.88 t/s 13.50.220.300 I slot print_timing: id 2 | task 13815 | n_gen = 815, tg = 19.80 t/s, tg_3s = 20.87 t/s 13.50.750.300 I slot print_timing: id 1 | task 14356 | n_gen = 289, tg = 20.88 t/s, tg_3s = 20.85 t/s 13.51.038.685 I slot print_timing: id 0 | task 14248 | n_gen = 401, tg = 19.48 t/s, tg_3s = 20.84 t/s 13.52.248.242 I slot print_timing: id 3 | task 14260 | n_gen = 415, tg = 20.13 t/s, tg_3s = 20.74 t/s 13.53.260.768 I slot print_timing: id 2 | task 13815 | n_gen = 878, tg = 19.87 t/s, tg_3s = 20.72 t/s 13.53.792.736 I slot print_timing: id 1 | task 14356 | n_gen = 352, tg = 20.85 t/s, tg_3s = 20.71 t/s 13.54.080.748 I slot print_timing: id 0 | task 14248 | n_gen = 464, tg = 19.64 t/s, tg_3s = 20.71 t/s 13.55.285.024 I slot print_timing: id 3 | task 14260 | n_gen = 478, tg = 20.21 t/s, tg_3s = 20.75 t/s 13.55.524.198 I slot print_timing: id 3 | task 14260 | prompt eval time = 747.60 ms / 449 tokens ( 1.67 ms per token, 600.59 tokens per second) 13.55.524.209 I slot print_timing: id 3 | task 14260 | eval time = 23837.97 ms / 483 tokens ( 49.46 ms per token, 20.22 tokens per second) 13.55.524.211 I slot print_timing: id 3 | task 14260 | total time = 24585.56 ms / 932 tokens 13.55.524.212 I slot print_timing: id 3 | task 14260 | graphs reused = 13995 13.55.524.213 I slot print_timing: id 3 | task 14260 | graph reallocs = 0 / 0 (same size) / (changed size) 13.55.524.329 I slot release: id 3 | task 14260 | stop processing: n_tokens = 1626, truncated = 0 13.55.565.510 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.657 13.55.565.545 I slot launch_slot_: id 3 | task 14747 | processing task, is_child = 0 13.56.268.234 I slot print_timing: id 2 | task 13815 | n_gen = 927, tg = 19.64 t/s, tg_3s = 16.29 t/s 13.56.820.639 I slot print_timing: id 1 | task 14356 | n_gen = 401, tg = 20.14 t/s, tg_3s = 16.18 t/s 13.57.121.584 I slot print_timing: id 0 | task 14248 | n_gen = 513, tg = 19.23 t/s, tg_3s = 16.11 t/s 13.59.293.161 I slot print_timing: id 2 | task 13815 | n_gen = 989, tg = 19.69 t/s, tg_3s = 20.50 t/s 13.59.340.349 I slot print_timing: id 0 | task 14248 | prompt eval time = 752.54 ms / 462 tokens ( 1.63 ms per token, 613.92 tokens per second) 13.59.340.354 I slot print_timing: id 0 | task 14248 | eval time = 28839.67 ms / 559 tokens ( 51.68 ms per token, 19.35 tokens per second) 13.59.340.355 I slot print_timing: id 0 | task 14248 | total time = 29592.21 ms / 1021 tokens 13.59.340.356 I slot print_timing: id 0 | task 14248 | graphs reused = 14056 13.59.340.357 I slot print_timing: id 0 | task 14248 | graph reallocs = 0 / 0 (same size) / (changed size) 13.59.340.467 I slot release: id 0 | task 14248 | stop processing: n_tokens = 1716, truncated = 0 13.59.383.697 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.622 13.59.383.734 I slot launch_slot_: id 0 | task 14813 | processing task, is_child = 0 14.00.054.951 I slot print_timing: id 1 | task 14356 | n_gen = 455, tg = 19.66 t/s, tg_3s = 16.70 t/s 14.01.614.951 I slot print_timing: id 2 | task 13815 | prompt eval time = 931.37 ms / 522 tokens ( 1.78 ms per token, 560.46 tokens per second) 14.01.614.967 I slot print_timing: id 2 | task 13815 | eval time = 52495.64 ms / 1024 tokens ( 51.32 ms per token, 19.49 tokens per second) 14.01.614.967 I slot print_timing: id 2 | task 13815 | total time = 53427.01 ms / 1546 tokens 14.01.614.968 I slot print_timing: id 2 | task 13815 | graphs reused = 14087 14.01.614.969 I slot print_timing: id 2 | task 13815 | graph reallocs = 0 / 0 (same size) / (changed size) 14.01.615.111 I slot release: id 2 | task 13815 | stop processing: n_tokens = 2232, truncated = 0 14.01.664.322 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.478 14.01.671.227 I slot launch_slot_: id 2 | task 14848 | processing task, is_child = 0 14.02.454.792 I slot print_timing: id 3 | task 14747 | n_gen = 100, tg = 16.22 t/s, tg_3s = 16.38 t/s 14.03.060.418 I slot print_timing: id 1 | task 14356 | n_gen = 503, tg = 19.23 t/s, tg_3s = 15.97 t/s 14.05.479.495 I slot print_timing: id 0 | task 14813 | n_gen = 100, tg = 18.52 t/s, tg_3s = 18.71 t/s 14.05.480.372 I slot print_timing: id 3 | task 14747 | n_gen = 165, tg = 17.96 t/s, tg_3s = 21.48 t/s 14.06.083.939 I slot print_timing: id 1 | task 14356 | n_gen = 568, tg = 19.47 t/s, tg_3s = 21.50 t/s 14.07.069.266 I slot print_timing: id 2 | task 14848 | n_gen = 100, tg = 21.45 t/s, tg_3s = 21.67 t/s 14.08.503.714 I slot print_timing: id 0 | task 14813 | n_gen = 164, tg = 19.48 t/s, tg_3s = 21.16 t/s 14.08.505.559 I slot print_timing: id 3 | task 14747 | n_gen = 229, tg = 18.76 t/s, tg_3s = 21.16 t/s 14.09.125.659 I slot print_timing: id 1 | task 14356 | n_gen = 632, tg = 19.62 t/s, tg_3s = 21.04 t/s 14.10.086.627 I slot print_timing: id 2 | task 14848 | n_gen = 163, tg = 21.23 t/s, tg_3s = 20.88 t/s 14.11.523.917 I slot print_timing: id 0 | task 14813 | n_gen = 227, tg = 19.84 t/s, tg_3s = 20.86 t/s 14.11.525.791 I slot print_timing: id 3 | task 14747 | n_gen = 292, tg = 19.18 t/s, tg_3s = 20.86 t/s 14.12.147.815 I slot print_timing: id 1 | task 14356 | n_gen = 695, tg = 19.72 t/s, tg_3s = 20.85 t/s 14.13.106.529 I slot print_timing: id 2 | task 14848 | n_gen = 226, tg = 21.12 t/s, tg_3s = 20.86 t/s 14.14.540.385 I slot print_timing: id 0 | task 14813 | n_gen = 290, tg = 20.06 t/s, tg_3s = 20.89 t/s 14.14.542.038 I slot print_timing: id 3 | task 14747 | n_gen = 355, tg = 19.46 t/s, tg_3s = 20.89 t/s 14.15.160.561 I slot print_timing: id 1 | task 14356 | n_gen = 758, tg = 19.82 t/s, tg_3s = 20.91 t/s 14.15.446.534 I slot print_timing: id 1 | task 14356 | prompt eval time = 792.25 ms / 477 tokens ( 1.66 ms per token, 602.08 tokens per second) 14.15.446.539 I slot print_timing: id 1 | task 14356 | eval time = 38487.60 ms / 764 tokens ( 50.44 ms per token, 19.82 tokens per second) 14.15.446.540 I slot print_timing: id 1 | task 14356 | total time = 39279.85 ms / 1241 tokens 14.15.446.541 I slot print_timing: id 1 | task 14356 | graphs reused = 14359 14.15.446.542 I slot print_timing: id 1 | task 14356 | graph reallocs = 0 / 0 (same size) / (changed size) 14.15.446.655 I slot release: id 1 | task 14356 | stop processing: n_tokens = 1913, truncated = 0 14.15.495.760 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.558 14.15.495.803 I slot launch_slot_: id 1 | task 15126 | processing task, is_child = 0 14.16.216.192 I slot print_timing: id 2 | task 14848 | n_gen = 277, tg = 20.06 t/s, tg_3s = 16.40 t/s 14.17.580.174 I slot print_timing: id 0 | task 14813 | n_gen = 339, tg = 19.37 t/s, tg_3s = 16.12 t/s 14.17.582.070 I slot print_timing: id 3 | task 14747 | n_gen = 404, tg = 18.98 t/s, tg_3s = 16.12 t/s 14.19.252.205 I slot print_timing: id 2 | task 14848 | n_gen = 340, tg = 20.18 t/s, tg_3s = 20.75 t/s 14.20.590.917 I slot print_timing: id 0 | task 14813 | n_gen = 402, tg = 19.60 t/s, tg_3s = 20.93 t/s 14.20.592.696 I slot print_timing: id 3 | task 14747 | n_gen = 467, tg = 19.22 t/s, tg_3s = 20.93 t/s 14.21.022.502 I slot print_timing: id 1 | task 15126 | n_gen = 100, tg = 20.99 t/s, tg_3s = 21.20 t/s 14.22.271.288 I slot print_timing: id 2 | task 14848 | n_gen = 403, tg = 20.29 t/s, tg_3s = 20.87 t/s 14.23.611.813 I slot print_timing: id 0 | task 14813 | n_gen = 465, tg = 19.76 t/s, tg_3s = 20.85 t/s 14.23.613.743 I slot print_timing: id 3 | task 14747 | n_gen = 530, tg = 19.40 t/s, tg_3s = 20.85 t/s 14.24.043.203 I slot print_timing: id 1 | task 15126 | n_gen = 163, tg = 20.94 t/s, tg_3s = 20.86 t/s 14.24.811.370 I slot print_timing: id 0 | task 14813 | prompt eval time = 750.31 ms / 454 tokens ( 1.65 ms per token, 605.08 tokens per second) 14.24.811.377 I slot print_timing: id 0 | task 14813 | eval time = 24677.32 ms / 490 tokens ( 50.46 ms per token, 19.82 tokens per second) 14.24.811.378 I slot print_timing: id 0 | task 14813 | total time = 25427.63 ms / 944 tokens 14.24.811.379 I slot print_timing: id 0 | task 14813 | graphs reused = 14536 14.24.811.379 I slot print_timing: id 0 | task 14813 | graph reallocs = 0 / 0 (same size) / (changed size) 14.24.811.489 I slot release: id 0 | task 14813 | stop processing: n_tokens = 1639, truncated = 0 14.24.854.753 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.652 14.24.854.790 I slot launch_slot_: id 0 | task 15308 | processing task, is_child = 0 14.25.530.959 I slot print_timing: id 2 | task 14848 | n_gen = 458, tg = 19.80 t/s, tg_3s = 16.87 t/s 14.26.638.117 I slot print_timing: id 3 | task 14747 | n_gen = 580, tg = 19.12 t/s, tg_3s = 16.53 t/s 14.27.057.191 I slot print_timing: id 1 | task 15126 | n_gen = 213, tg = 19.72 t/s, tg_3s = 16.59 t/s 14.28.552.616 I slot print_timing: id 2 | task 14848 | n_gen = 521, tg = 19.92 t/s, tg_3s = 20.85 t/s 14.29.270.853 I slot print_timing: id 2 | task 14848 | prompt eval time = 783.25 ms / 467 tokens ( 1.68 ms per token, 596.23 tokens per second) 14.29.270.861 I slot print_timing: id 2 | task 14848 | eval time = 26816.36 ms / 536 tokens ( 50.12 ms per token, 19.95 tokens per second) 14.29.270.862 I slot print_timing: id 2 | task 14848 | total time = 27599.61 ms / 1003 tokens 14.29.270.862 I slot print_timing: id 2 | task 14848 | graphs reused = 14612 14.29.270.863 I slot print_timing: id 2 | task 14848 | graph reallocs = 0 / 0 (same size) / (changed size) 14.29.270.988 I slot release: id 2 | task 14848 | stop processing: n_tokens = 1695, truncated = 0 14.29.319.674 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.630 14.29.319.716 I slot launch_slot_: id 2 | task 15389 | processing task, is_child = 0 14.29.992.346 I slot print_timing: id 3 | task 14747 | n_gen = 637, tg = 18.90 t/s, tg_3s = 16.99 t/s 14.30.079.968 I slot print_timing: id 1 | task 15126 | n_gen = 262, tg = 18.95 t/s, tg_3s = 16.21 t/s 14.30.966.822 I slot print_timing: id 0 | task 15308 | n_gen = 100, tg = 18.48 t/s, tg_3s = 18.67 t/s 14.33.036.088 I slot print_timing: id 3 | task 14747 | n_gen = 700, tg = 19.05 t/s, tg_3s = 20.70 t/s 14.33.082.676 I slot print_timing: id 1 | task 15126 | n_gen = 325, tg = 19.31 t/s, tg_3s = 20.98 t/s 14.33.989.809 I slot print_timing: id 0 | task 15308 | n_gen = 163, tg = 19.33 t/s, tg_3s = 20.84 t/s 14.34.806.120 I slot print_timing: id 2 | task 15389 | n_gen = 100, tg = 20.95 t/s, tg_3s = 21.16 t/s 14.36.050.336 I slot print_timing: id 3 | task 14747 | n_gen = 763, tg = 19.19 t/s, tg_3s = 20.90 t/s 14.36.096.345 I slot print_timing: id 1 | task 15126 | n_gen = 388, tg = 19.55 t/s, tg_3s = 20.90 t/s 14.37.004.793 I slot print_timing: id 0 | task 15308 | n_gen = 226, tg = 19.75 t/s, tg_3s = 20.90 t/s 14.37.818.430 I slot print_timing: id 2 | task 15389 | n_gen = 163, tg = 20.94 t/s, tg_3s = 20.91 t/s 14.39.067.061 I slot print_timing: id 3 | task 14747 | n_gen = 826, tg = 19.31 t/s, tg_3s = 20.88 t/s 14.39.113.732 I slot print_timing: id 1 | task 15126 | n_gen = 451, tg = 19.73 t/s, tg_3s = 20.88 t/s 14.40.024.518 I slot print_timing: id 0 | task 15308 | n_gen = 289, tg = 19.98 t/s, tg_3s = 20.86 t/s 14.40.840.577 I slot print_timing: id 2 | task 15389 | n_gen = 226, tg = 20.91 t/s, tg_3s = 20.85 t/s 14.42.090.299 I slot print_timing: id 3 | task 14747 | n_gen = 889, tg = 19.41 t/s, tg_3s = 20.84 t/s 14.42.137.010 I slot print_timing: id 1 | task 15126 | n_gen = 514, tg = 19.86 t/s, tg_3s = 20.84 t/s 14.43.046.773 I slot print_timing: id 0 | task 15308 | n_gen = 352, tg = 20.13 t/s, tg_3s = 20.85 t/s 14.43.863.050 I slot print_timing: id 2 | task 15389 | n_gen = 289, tg = 20.90 t/s, tg_3s = 20.84 t/s 14.44.294.354 I slot print_timing: id 1 | task 15126 | prompt eval time = 809.50 ms / 489 tokens ( 1.66 ms per token, 604.08 tokens per second) 14.44.294.359 I slot print_timing: id 1 | task 15126 | eval time = 27989.04 ms / 559 tokens ( 50.16 ms per token, 19.94 tokens per second) 14.44.294.360 I slot print_timing: id 1 | task 15126 | total time = 28798.54 ms / 1048 tokens 14.44.294.361 I slot print_timing: id 1 | task 15126 | graphs reused = 14907 14.44.294.362 I slot print_timing: id 1 | task 15126 | graph reallocs = 0 / 0 (same size) / (changed size) 14.44.294.497 I slot release: id 1 | task 15126 | stop processing: n_tokens = 1720, truncated = 0 14.44.343.902 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.621 14.44.343.942 I slot launch_slot_: id 1 | task 15690 | processing task, is_child = 0 14.45.155.327 I slot print_timing: id 3 | task 14747 | n_gen = 938, tg = 19.20 t/s, tg_3s = 15.99 t/s 14.46.091.259 I slot print_timing: id 0 | task 15308 | n_gen = 401, tg = 19.53 t/s, tg_3s = 16.09 t/s 14.46.185.328 I slot print_timing: id 3 | task 14747 | prompt eval time = 784.63 ms / 484 tokens ( 1.62 ms per token, 616.85 tokens per second) 14.46.185.333 I slot print_timing: id 3 | task 14747 | eval time = 49835.14 ms / 960 tokens ( 51.97 ms per token, 19.24 tokens per second) 14.46.185.335 I slot print_timing: id 3 | task 14747 | total time = 50619.77 ms / 1444 tokens 14.46.185.335 I slot print_timing: id 3 | task 14747 | graphs reused = 14928 14.46.185.336 I slot print_timing: id 3 | task 14747 | graph reallocs = 0 / 0 (same size) / (changed size) 14.46.185.404 I slot release: id 3 | task 14747 | stop processing: n_tokens = 2138, truncated = 0 14.46.223.576 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.500 14.46.227.889 I slot launch_slot_: id 3 | task 15716 | processing task, is_child = 0 14.46.909.091 I slot print_timing: id 2 | task 15389 | n_gen = 325, tg = 19.25 t/s, tg_3s = 11.82 t/s 14.49.134.006 I slot print_timing: id 0 | task 15308 | n_gen = 452, tg = 19.17 t/s, tg_3s = 16.76 t/s 14.49.953.360 I slot print_timing: id 2 | task 15389 | n_gen = 389, tg = 19.52 t/s, tg_3s = 21.02 t/s 14.50.193.084 I slot print_timing: id 2 | task 15389 | prompt eval time = 760.56 ms / 452 tokens ( 1.68 ms per token, 594.30 tokens per second) 14.50.193.089 I slot print_timing: id 2 | task 15389 | eval time = 20112.80 ms / 394 tokens ( 51.18 ms per token, 19.54 tokens per second) 14.50.193.090 I slot print_timing: id 2 | task 15389 | total time = 20873.36 ms / 846 tokens 14.50.193.090 I slot print_timing: id 2 | task 15389 | graphs reused = 14995 14.50.193.091 I slot print_timing: id 2 | task 15389 | graph reallocs = 0 / 0 (same size) / (changed size) 14.50.193.209 I slot release: id 2 | task 15389 | stop processing: n_tokens = 1538, truncated = 0 14.50.241.710 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.694 14.50.241.755 I slot launch_slot_: id 2 | task 15788 | processing task, is_child = 0 14.51.144.450 I slot print_timing: id 1 | task 15690 | n_gen = 100, tg = 16.53 t/s, tg_3s = 16.70 t/s 14.52.151.858 I slot print_timing: id 0 | task 15308 | n_gen = 501, tg = 18.84 t/s, tg_3s = 16.24 t/s 14.52.344.902 I slot print_timing: id 3 | task 15716 | n_gen = 100, tg = 18.49 t/s, tg_3s = 18.68 t/s 14.54.161.969 I slot print_timing: id 1 | task 15690 | n_gen = 163, tg = 17.99 t/s, tg_3s = 20.88 t/s 14.55.163.129 I slot print_timing: id 0 | task 15308 | n_gen = 564, tg = 19.05 t/s, tg_3s = 20.92 t/s 14.55.355.819 I slot print_timing: id 3 | task 15716 | n_gen = 163, tg = 19.37 t/s, tg_3s = 20.92 t/s 14.55.736.645 I slot print_timing: id 2 | task 15788 | n_gen = 100, tg = 20.91 t/s, tg_3s = 21.12 t/s 14.57.171.449 I slot print_timing: id 1 | task 15690 | n_gen = 226, tg = 18.72 t/s, tg_3s = 20.93 t/s 14.58.178.292 I slot print_timing: id 0 | task 15308 | n_gen = 627, tg = 19.22 t/s, tg_3s = 20.89 t/s 14.58.373.301 I slot print_timing: id 3 | task 15716 | n_gen = 226, tg = 19.77 t/s, tg_3s = 20.88 t/s 14.58.760.101 I slot print_timing: id 2 | task 15788 | n_gen = 163, tg = 20.88 t/s, tg_3s = 20.84 t/s 15.00.198.684 I slot print_timing: id 0 | task 15308 | prompt eval time = 755.04 ms / 466 tokens ( 1.62 ms per token, 617.18 tokens per second) 15.00.198.689 I slot print_timing: id 0 | task 15308 | eval time = 34588.84 ms / 669 tokens ( 51.78 ms per token, 19.31 tokens per second) 15.00.198.690 I slot print_timing: id 0 | task 15308 | total time = 35343.89 ms / 1135 tokens 15.00.198.691 I slot print_timing: id 0 | task 15308 | graphs reused = 15185 15.00.198.692 I slot print_timing: id 0 | task 15308 | graph reallocs = 0 / 0 (same size) / (changed size) 15.00.198.809 I slot release: id 0 | task 15308 | stop processing: n_tokens = 1830, truncated = 0 15.00.199.488 I slot print_timing: id 1 | task 15690 | n_gen = 289, tg = 19.14 t/s, tg_3s = 20.81 t/s 15.00.242.013 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.584 15.00.242.052 I slot launch_slot_: id 0 | task 15984 | processing task, is_child = 0 15.01.391.920 I slot print_timing: id 3 | task 15716 | n_gen = 276, tg = 19.10 t/s, tg_3s = 16.56 t/s 15.01.763.908 I slot print_timing: id 2 | task 15788 | n_gen = 213, tg = 19.70 t/s, tg_3s = 16.65 t/s 15.03.211.440 I slot print_timing: id 1 | task 15690 | n_gen = 340, tg = 18.77 t/s, tg_3s = 16.93 t/s 15.04.411.293 I slot print_timing: id 3 | task 15716 | n_gen = 340, tg = 19.46 t/s, tg_3s = 21.20 t/s 15.04.792.975 I slot print_timing: id 2 | task 15788 | n_gen = 277, tg = 20.01 t/s, tg_3s = 21.13 t/s 15.05.652.946 I slot print_timing: id 0 | task 15984 | n_gen = 100, tg = 21.14 t/s, tg_3s = 21.36 t/s 15.06.228.072 I slot print_timing: id 1 | task 15690 | n_gen = 403, tg = 19.08 t/s, tg_3s = 20.88 t/s 15.07.428.966 I slot print_timing: id 3 | task 15716 | n_gen = 403, tg = 19.67 t/s, tg_3s = 20.88 t/s 15.07.810.565 I slot print_timing: id 2 | task 15788 | n_gen = 340, tg = 20.17 t/s, tg_3s = 20.88 t/s 15.08.672.680 I slot print_timing: id 0 | task 15984 | n_gen = 163, tg = 21.03 t/s, tg_3s = 20.86 t/s 15.09.246.899 I slot print_timing: id 1 | task 15690 | n_gen = 466, tg = 19.30 t/s, tg_3s = 20.87 t/s 15.10.299.490 I slot print_timing: id 2 | task 15788 | prompt eval time = 760.61 ms / 449 tokens ( 1.69 ms per token, 590.32 tokens per second) 15.10.299.495 I slot print_timing: id 2 | task 15788 | eval time = 19297.12 ms / 392 tokens ( 49.35 ms per token, 20.26 tokens per second) 15.10.299.498 I slot print_timing: id 2 | task 15788 | total time = 20057.72 ms / 841 tokens 15.10.299.499 I slot print_timing: id 2 | task 15788 | graphs reused = 15380 15.10.299.499 I slot print_timing: id 2 | task 15788 | graph reallocs = 0 / 0 (same size) / (changed size) 15.10.299.614 I slot release: id 2 | task 15788 | stop processing: n_tokens = 1533, truncated = 0 15.10.348.507 I slot print_timing: id 3 | task 15716 | prompt eval time = 762.49 ms / 457 tokens ( 1.67 ms per token, 599.35 tokens per second) 15.10.348.515 I slot print_timing: id 3 | task 15716 | eval time = 23358.12 ms / 464 tokens ( 50.45 ms per token, 19.82 tokens per second) 15.10.348.516 I slot print_timing: id 3 | task 15716 | total time = 24120.61 ms / 921 tokens 15.10.348.517 I slot print_timing: id 3 | task 15716 | graphs reused = 15380 15.10.348.518 I slot print_timing: id 3 | task 15716 | graph reallocs = 0 / 0 (same size) / (changed size) 15.10.348.627 I slot release: id 3 | task 15716 | stop processing: n_tokens = 1615, truncated = 0 15.10.348.639 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.697 15.10.348.672 I slot launch_slot_: id 2 | task 16184 | processing task, is_child = 0 15.11.078.543 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.661 15.11.078.570 I slot launch_slot_: id 3 | task 16186 | processing task, is_child = 0 15.11.815.169 I slot print_timing: id 0 | task 15984 | n_gen = 200, tg = 18.35 t/s, tg_3s = 11.77 t/s 15.12.269.513 I slot print_timing: id 1 | task 15690 | n_gen = 500, tg = 18.40 t/s, tg_3s = 11.25 t/s 15.14.838.258 I slot print_timing: id 0 | task 15984 | n_gen = 263, tg = 18.89 t/s, tg_3s = 20.84 t/s 15.15.317.136 I slot print_timing: id 1 | task 15690 | n_gen = 564, tg = 18.67 t/s, tg_3s = 21.00 t/s 15.16.562.575 I slot print_timing: id 2 | task 16184 | n_gen = 100, tg = 20.86 t/s, tg_3s = 21.07 t/s 15.16.611.384 I slot print_timing: id 3 | task 16186 | n_gen = 100, tg = 21.00 t/s, tg_3s = 21.21 t/s 15.17.855.853 I slot print_timing: id 0 | task 15984 | n_gen = 326, tg = 19.25 t/s, tg_3s = 20.88 t/s 15.18.338.094 I slot print_timing: id 1 | task 15690 | n_gen = 627, tg = 18.86 t/s, tg_3s = 20.85 t/s 15.19.586.453 I slot print_timing: id 2 | task 16184 | n_gen = 163, tg = 20.85 t/s, tg_3s = 20.83 t/s 15.19.635.154 I slot print_timing: id 3 | task 16186 | n_gen = 163, tg = 20.94 t/s, tg_3s = 20.83 t/s 15.20.879.856 I slot print_timing: id 0 | task 15984 | n_gen = 389, tg = 19.49 t/s, tg_3s = 20.83 t/s 15.21.363.286 I slot print_timing: id 1 | task 15690 | n_gen = 690, tg = 19.03 t/s, tg_3s = 20.83 t/s 15.22.617.848 I slot print_timing: id 2 | task 16184 | n_gen = 226, tg = 20.83 t/s, tg_3s = 20.78 t/s 15.22.666.742 I slot print_timing: id 3 | task 16186 | n_gen = 226, tg = 20.89 t/s, tg_3s = 20.78 t/s 15.23.912.473 I slot print_timing: id 0 | task 15984 | n_gen = 452, tg = 19.66 t/s, tg_3s = 20.77 t/s 15.24.392.786 I slot print_timing: id 1 | task 15690 | n_gen = 753, tg = 19.17 t/s, tg_3s = 20.80 t/s 15.25.643.461 I slot print_timing: id 2 | task 16184 | n_gen = 289, tg = 20.83 t/s, tg_3s = 20.82 t/s 15.25.692.006 I slot print_timing: id 3 | task 16186 | n_gen = 289, tg = 20.88 t/s, tg_3s = 20.82 t/s 15.26.940.756 I slot print_timing: id 0 | task 15984 | n_gen = 515, tg = 19.79 t/s, tg_3s = 20.80 t/s 15.27.422.528 I slot print_timing: id 1 | task 15690 | n_gen = 816, tg = 19.28 t/s, tg_3s = 20.79 t/s 15.28.669.572 I slot print_timing: id 2 | task 16184 | n_gen = 352, tg = 20.83 t/s, tg_3s = 20.82 t/s 15.28.718.160 I slot print_timing: id 3 | task 16186 | n_gen = 352, tg = 20.87 t/s, tg_3s = 20.82 t/s 15.29.964.641 I slot print_timing: id 0 | task 15984 | n_gen = 578, tg = 19.90 t/s, tg_3s = 20.83 t/s 15.30.251.999 I slot print_timing: id 0 | task 15984 | prompt eval time = 728.52 ms / 443 tokens ( 1.64 ms per token, 608.08 tokens per second) 15.30.252.006 I slot print_timing: id 0 | task 15984 | eval time = 29281.41 ms / 584 tokens ( 50.23 ms per token, 19.91 tokens per second) 15.30.252.007 I slot print_timing: id 0 | task 15984 | total time = 30009.93 ms / 1027 tokens 15.30.252.008 I slot print_timing: id 0 | task 15984 | graphs reused = 15761 15.30.252.009 I slot print_timing: id 0 | task 15984 | graph reallocs = 0 / 0 (same size) / (changed size) 15.30.252.121 I slot release: id 0 | task 15984 | stop processing: n_tokens = 1722, truncated = 0 15.30.294.810 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.620 15.30.294.856 I slot launch_slot_: id 0 | task 16573 | processing task, is_child = 0 15.30.970.842 I slot print_timing: id 1 | task 15690 | n_gen = 877, tg = 19.12 t/s, tg_3s = 17.19 t/s 15.31.705.354 I slot print_timing: id 2 | task 16184 | n_gen = 402, tg = 20.16 t/s, tg_3s = 16.47 t/s 15.31.752.605 I slot print_timing: id 3 | task 16186 | n_gen = 402, tg = 20.20 t/s, tg_3s = 16.48 t/s 15.33.998.935 I slot print_timing: id 1 | task 15690 | n_gen = 941, tg = 19.24 t/s, tg_3s = 21.14 t/s 15.34.745.435 I slot print_timing: id 2 | task 16184 | n_gen = 467, tg = 20.32 t/s, tg_3s = 21.38 t/s 15.34.792.309 I slot print_timing: id 3 | task 16186 | n_gen = 467, tg = 20.35 t/s, tg_3s = 21.38 t/s 15.35.680.365 I slot print_timing: id 0 | task 16573 | n_gen = 100, tg = 21.38 t/s, tg_3s = 21.60 t/s 15.37.039.828 I slot print_timing: id 1 | task 15690 | n_gen = 1006, tg = 19.37 t/s, tg_3s = 21.38 t/s 15.37.761.708 I slot print_timing: id 2 | task 16184 | n_gen = 531, tg = 20.43 t/s, tg_3s = 21.22 t/s 15.37.810.641 I slot print_timing: id 3 | task 16186 | n_gen = 531, tg = 20.45 t/s, tg_3s = 21.20 t/s 15.37.905.639 I slot print_timing: id 1 | task 15690 | prompt eval time = 810.89 ms / 489 tokens ( 1.66 ms per token, 603.04 tokens per second) 15.37.905.644 I slot print_timing: id 1 | task 15690 | eval time = 52750.80 ms / 1024 tokens ( 51.56 ms per token, 19.39 tokens per second) 15.37.905.645 I slot print_timing: id 1 | task 15690 | total time = 53561.69 ms / 1513 tokens 15.37.905.646 I slot print_timing: id 1 | task 15690 | graphs reused = 15906 15.37.905.647 I slot print_timing: id 1 | task 15690 | graph reallocs = 0 / 0 (same size) / (changed size) 15.37.905.786 I slot release: id 1 | task 15690 | stop processing: n_tokens = 2185, truncated = 0 15.37.955.153 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.489 15.37.961.941 I slot launch_slot_: id 1 | task 16723 | processing task, is_child = 0 15.38.750.771 I slot print_timing: id 0 | task 16573 | n_gen = 150, tg = 19.35 t/s, tg_3s = 16.28 t/s 15.40.804.480 I slot print_timing: id 2 | task 16184 | n_gen = 580, tg = 19.97 t/s, tg_3s = 16.10 t/s 15.40.853.150 I slot print_timing: id 3 | task 16186 | n_gen = 580, tg = 20.00 t/s, tg_3s = 16.11 t/s 15.41.763.622 I slot print_timing: id 0 | task 16573 | n_gen = 213, tg = 19.79 t/s, tg_3s = 20.91 t/s 15.43.486.459 I slot print_timing: id 1 | task 16723 | n_gen = 100, tg = 20.91 t/s, tg_3s = 21.12 t/s 15.43.822.153 I slot print_timing: id 2 | task 16184 | n_gen = 643, tg = 20.06 t/s, tg_3s = 20.88 t/s 15.43.870.833 I slot print_timing: id 3 | task 16186 | n_gen = 643, tg = 20.08 t/s, tg_3s = 20.88 t/s 15.44.780.330 I slot print_timing: id 0 | task 16573 | n_gen = 276, tg = 20.03 t/s, tg_3s = 20.88 t/s 15.46.513.891 I slot print_timing: id 1 | task 16723 | n_gen = 163, tg = 20.87 t/s, tg_3s = 20.81 t/s 15.46.853.352 I slot print_timing: id 2 | task 16184 | n_gen = 706, tg = 20.12 t/s, tg_3s = 20.78 t/s 15.46.902.415 I slot print_timing: id 3 | task 16186 | n_gen = 706, tg = 20.14 t/s, tg_3s = 20.78 t/s 15.47.812.649 I slot print_timing: id 0 | task 16573 | n_gen = 339, tg = 20.16 t/s, tg_3s = 20.78 t/s 15.49.547.883 I slot print_timing: id 1 | task 16723 | n_gen = 226, tg = 20.84 t/s, tg_3s = 20.76 t/s 15.49.885.316 I slot print_timing: id 2 | task 16184 | n_gen = 769, tg = 20.17 t/s, tg_3s = 20.78 t/s 15.49.933.987 I slot print_timing: id 3 | task 16186 | n_gen = 769, tg = 20.19 t/s, tg_3s = 20.78 t/s 15.50.844.399 I slot print_timing: id 0 | task 16573 | n_gen = 402, tg = 20.26 t/s, tg_3s = 20.78 t/s 15.52.581.472 I slot print_timing: id 1 | task 16723 | n_gen = 289, tg = 20.82 t/s, tg_3s = 20.77 t/s 15.52.919.190 I slot print_timing: id 2 | task 16184 | n_gen = 832, tg = 20.22 t/s, tg_3s = 20.77 t/s 15.52.967.702 I slot print_timing: id 3 | task 16186 | n_gen = 832, tg = 20.23 t/s, tg_3s = 20.77 t/s 15.53.884.117 I slot print_timing: id 0 | task 16573 | n_gen = 465, tg = 20.32 t/s, tg_3s = 20.73 t/s 15.55.284.300 I slot print_timing: id 3 | task 16186 | prompt eval time = 818.84 ms / 463 tokens ( 1.77 ms per token, 565.43 tokens per second) 15.55.284.307 I slot print_timing: id 3 | task 16186 | eval time = 43386.69 ms / 880 tokens ( 49.36 ms per token, 20.26 tokens per second) 15.55.284.308 I slot print_timing: id 3 | task 16186 | total time = 44205.53 ms / 1343 tokens 15.55.284.309 I slot print_timing: id 3 | task 16186 | graphs reused = 16247 15.55.284.310 I slot print_timing: id 3 | task 16186 | graph reallocs = 0 / 0 (same size) / (changed size) 15.55.284.424 I slot release: id 3 | task 16186 | stop processing: n_tokens = 2037, truncated = 0 15.55.325.530 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.524 15.55.325.577 I slot launch_slot_: id 3 | task 17071 | processing task, is_child = 0 15.56.013.995 I slot print_timing: id 1 | task 16723 | n_gen = 347, tg = 20.04 t/s, tg_3s = 16.90 t/s 15.56.014.304 I slot print_timing: id 2 | task 16184 | n_gen = 883, tg = 19.96 t/s, tg_3s = 16.48 t/s 15.56.891.467 I slot print_timing: id 0 | task 16573 | n_gen = 514, tg = 19.85 t/s, tg_3s = 16.29 t/s 15.58.942.387 I slot print_timing: id 1 | task 16723 | prompt eval time = 789.12 ms / 474 tokens ( 1.66 ms per token, 600.67 tokens per second) 15.58.942.391 I slot print_timing: id 1 | task 16723 | eval time = 20191.31 ms / 408 tokens ( 49.61 ms per token, 20.16 tokens per second) 15.58.942.393 I slot print_timing: id 1 | task 16723 | total time = 20980.43 ms / 882 tokens 15.58.942.393 I slot print_timing: id 1 | task 16723 | graphs reused = 16306 15.58.942.394 I slot print_timing: id 1 | task 16723 | graph reallocs = 0 / 0 (same size) / (changed size) 15.58.942.521 I slot release: id 1 | task 16723 | stop processing: n_tokens = 1554, truncated = 0 15.58.992.493 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.687 15.58.992.533 I slot launch_slot_: id 1 | task 17135 | processing task, is_child = 0 15.59.681.364 I slot print_timing: id 2 | task 16184 | n_gen = 946, tg = 19.74 t/s, tg_3s = 17.18 t/s 15.59.911.242 I slot print_timing: id 0 | task 16573 | n_gen = 563, tg = 19.47 t/s, tg_3s = 16.23 t/s 16.01.454.202 I slot print_timing: id 3 | task 17071 | n_gen = 100, tg = 18.48 t/s, tg_3s = 18.66 t/s 16.02.706.033 I slot print_timing: id 2 | task 16184 | n_gen = 1009, tg = 19.81 t/s, tg_3s = 20.83 t/s 16.02.943.595 I slot print_timing: id 0 | task 16573 | n_gen = 627, tg = 19.63 t/s, tg_3s = 21.11 t/s 16.03.422.027 I slot print_timing: id 2 | task 16184 | prompt eval time = 1461.50 ms / 511 tokens ( 2.86 ms per token, 349.64 tokens per second) 16.03.422.034 I slot print_timing: id 2 | task 16184 | eval time = 51606.26 ms / 1024 tokens ( 50.45 ms per token, 19.82 tokens per second) 16.03.422.035 I slot print_timing: id 2 | task 16184 | total time = 53067.76 ms / 1535 tokens 16.03.422.035 I slot print_timing: id 2 | task 16184 | graphs reused = 16382 16.03.422.036 I slot print_timing: id 2 | task 16184 | graph reallocs = 0 / 0 (same size) / (changed size) 16.03.422.140 I slot release: id 2 | task 16184 | stop processing: n_tokens = 2227, truncated = 0 16.03.470.400 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.480 16.03.481.608 I slot launch_slot_: id 2 | task 17216 | processing task, is_child = 0 16.04.485.289 I slot print_timing: id 3 | task 17071 | n_gen = 148, tg = 17.52 t/s, tg_3s = 15.84 t/s 16.04.716.227 I slot print_timing: id 0 | task 16573 | prompt eval time = 755.09 ms / 463 tokens ( 1.63 ms per token, 613.18 tokens per second) 16.04.716.229 I slot print_timing: id 0 | task 16573 | eval time = 33666.28 ms / 649 tokens ( 51.95 ms per token, 19.25 tokens per second) 16.04.716.230 I slot print_timing: id 0 | task 16573 | total time = 34421.36 ms / 1112 tokens 16.04.716.230 I slot print_timing: id 0 | task 16573 | graphs reused = 16390 16.04.716.230 I slot print_timing: id 0 | task 16573 | graph reallocs = 0 / 0 (same size) / (changed size) 16.04.716.291 I slot release: id 0 | task 16573 | stop processing: n_tokens = 1807, truncated = 0 16.04.755.578 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.591 16.04.755.605 I slot launch_slot_: id 0 | task 17229 | processing task, is_child = 0 16.05.803.803 I slot print_timing: id 1 | task 17135 | n_gen = 100, tg = 16.41 t/s, tg_3s = 16.57 t/s 16.07.502.569 I slot print_timing: id 3 | task 17071 | n_gen = 199, tg = 17.36 t/s, tg_3s = 16.90 t/s 16.08.843.529 I slot print_timing: id 1 | task 17135 | n_gen = 164, tg = 17.96 t/s, tg_3s = 21.05 t/s 16.09.608.042 I slot print_timing: id 2 | task 17216 | n_gen = 100, tg = 18.64 t/s, tg_3s = 18.83 t/s 16.10.179.867 I slot print_timing: id 0 | task 17229 | n_gen = 100, tg = 21.05 t/s, tg_3s = 21.27 t/s 16.10.516.459 I slot print_timing: id 3 | task 17071 | n_gen = 262, tg = 18.10 t/s, tg_3s = 20.90 t/s 16.11.854.699 I slot print_timing: id 1 | task 17135 | n_gen = 227, tg = 18.70 t/s, tg_3s = 20.92 t/s 16.12.622.650 I slot print_timing: id 2 | task 17216 | n_gen = 163, tg = 19.46 t/s, tg_3s = 20.90 t/s 16.13.197.016 I slot print_timing: id 0 | task 17229 | n_gen = 163, tg = 20.99 t/s, tg_3s = 20.88 t/s 16.13.534.551 I slot print_timing: id 3 | task 17071 | n_gen = 325, tg = 18.58 t/s, tg_3s = 20.87 t/s 16.14.542.249 I slot print_timing: id 3 | task 17071 | prompt eval time = 770.78 ms / 465 tokens ( 1.66 ms per token, 603.28 tokens per second) 16.14.542.254 I slot print_timing: id 3 | task 17071 | eval time = 18445.87 ms / 346 tokens ( 53.47 ms per token, 18.70 tokens per second) 16.14.542.256 I slot print_timing: id 3 | task 17071 | total time = 19216.65 ms / 811 tokens 16.14.542.257 I slot print_timing: id 3 | task 17071 | graphs reused = 16580 16.14.542.258 I slot print_timing: id 3 | task 17071 | graph reallocs = 0 / 0 (same size) / (changed size) 16.14.542.393 I slot release: id 3 | task 17071 | stop processing: n_tokens = 1505, truncated = 0 16.14.583.268 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.891 (> 0.100 thold), f_keep = 0.710 16.14.583.304 I slot launch_slot_: id 3 | task 17423 | processing task, is_child = 0 16.15.309.299 I slot print_timing: id 1 | task 17135 | n_gen = 285, tg = 18.28 t/s, tg_3s = 16.79 t/s 16.15.623.582 I slot print_timing: id 2 | task 17216 | n_gen = 211, tg = 18.54 t/s, tg_3s = 15.99 t/s 16.16.228.101 I slot print_timing: id 0 | task 17229 | n_gen = 212, tg = 19.63 t/s, tg_3s = 16.17 t/s 16.18.327.175 I slot print_timing: id 1 | task 17135 | n_gen = 348, tg = 18.70 t/s, tg_3s = 20.88 t/s 16.18.519.046 I slot print_timing: id 1 | task 17135 | prompt eval time = 777.54 ms / 456 tokens ( 1.71 ms per token, 586.47 tokens per second) 16.18.519.053 I slot print_timing: id 1 | task 17135 | eval time = 18748.97 ms / 352 tokens ( 53.42 ms per token, 18.72 tokens per second) 16.18.519.055 I slot print_timing: id 1 | task 17135 | total time = 19526.50 ms / 808 tokens 16.18.519.055 I slot print_timing: id 1 | task 17135 | graphs reused = 16645 16.18.519.056 I slot print_timing: id 1 | task 17135 | graph reallocs = 0 / 0 (same size) / (changed size) 16.18.519.167 I slot release: id 1 | task 17135 | stop processing: n_tokens = 1480, truncated = 0 16.18.567.835 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.722 16.18.567.873 I slot launch_slot_: id 1 | task 17493 | processing task, is_child = 0 16.19.288.516 I slot print_timing: id 0 | task 17229 | n_gen = 262, tg = 18.90 t/s, tg_3s = 16.34 t/s 16.19.288.828 I slot print_timing: id 2 | task 17216 | n_gen = 274, tg = 18.21 t/s, tg_3s = 17.19 t/s 16.20.813.893 I slot print_timing: id 3 | task 17423 | n_gen = 100, tg = 18.25 t/s, tg_3s = 18.44 t/s 16.22.297.120 I slot print_timing: id 0 | task 17229 | n_gen = 324, tg = 19.20 t/s, tg_3s = 20.61 t/s 16.22.298.427 I slot print_timing: id 2 | task 17216 | n_gen = 336, tg = 18.61 t/s, tg_3s = 20.60 t/s 16.23.060.606 I slot print_timing: id 0 | task 17229 | prompt eval time = 721.85 ms / 435 tokens ( 1.66 ms per token, 602.62 tokens per second) 16.23.060.611 I slot print_timing: id 0 | task 17229 | eval time = 17583.14 ms / 340 tokens ( 51.87 ms per token, 19.28 tokens per second) 16.23.060.611 I slot print_timing: id 0 | task 17229 | total time = 18304.99 ms / 775 tokens 16.23.060.612 I slot print_timing: id 0 | task 17229 | graphs reused = 16721 16.23.060.613 I slot print_timing: id 0 | task 17229 | graph reallocs = 0 / 0 (same size) / (changed size) 16.23.060.731 I slot release: id 0 | task 17229 | stop processing: n_tokens = 1470, truncated = 0 16.23.103.380 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.727 16.23.103.416 I slot launch_slot_: id 0 | task 17574 | processing task, is_child = 0 16.23.853.863 I slot print_timing: id 3 | task 17423 | n_gen = 150, tg = 17.61 t/s, tg_3s = 16.45 t/s 16.24.736.468 I slot print_timing: id 1 | task 17493 | n_gen = 100, tg = 18.47 t/s, tg_3s = 18.66 t/s 16.25.340.482 I slot print_timing: id 2 | task 17216 | n_gen = 387, tg = 18.34 t/s, tg_3s = 16.77 t/s 16.26.865.766 I slot print_timing: id 3 | task 17423 | n_gen = 214, tg = 18.56 t/s, tg_3s = 21.25 t/s 16.27.771.114 I slot print_timing: id 1 | task 17493 | n_gen = 164, tg = 19.42 t/s, tg_3s = 21.09 t/s 16.28.347.222 I slot print_timing: id 2 | task 17216 | n_gen = 450, tg = 18.67 t/s, tg_3s = 20.95 t/s 16.28.537.643 I slot print_timing: id 0 | task 17574 | n_gen = 100, tg = 21.13 t/s, tg_3s = 21.35 t/s 16.29.878.411 I slot print_timing: id 3 | task 17423 | n_gen = 277, tg = 19.05 t/s, tg_3s = 20.91 t/s 16.30.784.581 I slot print_timing: id 1 | task 17493 | n_gen = 227, tg = 19.81 t/s, tg_3s = 20.91 t/s 16.31.357.086 I slot print_timing: id 2 | task 17216 | n_gen = 513, tg = 18.92 t/s, tg_3s = 20.93 t/s 16.31.546.522 I slot print_timing: id 0 | task 17574 | n_gen = 163, tg = 21.06 t/s, tg_3s = 20.94 t/s 16.32.885.572 I slot print_timing: id 3 | task 17423 | n_gen = 340, tg = 19.38 t/s, tg_3s = 20.95 t/s 16.33.795.753 I slot print_timing: id 1 | task 17493 | n_gen = 290, tg = 20.04 t/s, tg_3s = 20.92 t/s 16.34.371.983 I slot print_timing: id 2 | task 17216 | n_gen = 576, tg = 19.12 t/s, tg_3s = 20.90 t/s 16.34.562.359 I slot print_timing: id 0 | task 17574 | n_gen = 226, tg = 21.01 t/s, tg_3s = 20.89 t/s 16.35.908.693 I slot print_timing: id 3 | task 17423 | n_gen = 403, tg = 19.59 t/s, tg_3s = 20.84 t/s 16.36.826.091 I slot print_timing: id 1 | task 17493 | n_gen = 353, tg = 20.17 t/s, tg_3s = 20.79 t/s 16.37.404.253 I slot print_timing: id 2 | task 17216 | n_gen = 639, tg = 19.27 t/s, tg_3s = 20.78 t/s 16.37.594.208 I slot print_timing: id 0 | task 17574 | n_gen = 289, tg = 20.96 t/s, tg_3s = 20.78 t/s 16.38.938.784 I slot print_timing: id 3 | task 17423 | n_gen = 466, tg = 19.75 t/s, tg_3s = 20.79 t/s 16.39.847.748 I slot print_timing: id 1 | task 17493 | n_gen = 416, tg = 20.27 t/s, tg_3s = 20.85 t/s 16.40.425.587 I slot print_timing: id 2 | task 17216 | n_gen = 702, tg = 19.40 t/s, tg_3s = 20.85 t/s 16.40.616.578 I slot print_timing: id 0 | task 17574 | n_gen = 352, tg = 20.94 t/s, tg_3s = 20.84 t/s 16.41.963.748 I slot print_timing: id 3 | task 17423 | n_gen = 529, tg = 19.87 t/s, tg_3s = 20.83 t/s 16.42.877.225 I slot print_timing: id 1 | task 17493 | n_gen = 479, tg = 20.34 t/s, tg_3s = 20.80 t/s 16.43.454.199 I slot print_timing: id 2 | task 17216 | n_gen = 765, tg = 19.51 t/s, tg_3s = 20.80 t/s 16.43.645.538 I slot print_timing: id 0 | task 17574 | n_gen = 415, tg = 20.92 t/s, tg_3s = 20.80 t/s 16.44.990.592 I slot print_timing: id 3 | task 17423 | n_gen = 592, tg = 19.97 t/s, tg_3s = 20.81 t/s 16.45.901.841 I slot print_timing: id 1 | task 17493 | n_gen = 542, tg = 20.40 t/s, tg_3s = 20.83 t/s 16.46.478.621 I slot print_timing: id 2 | task 17216 | n_gen = 828, tg = 19.61 t/s, tg_3s = 20.83 t/s 16.46.669.220 I slot print_timing: id 0 | task 17574 | n_gen = 478, tg = 20.91 t/s, tg_3s = 20.84 t/s 16.48.017.351 I slot print_timing: id 3 | task 17423 | n_gen = 655, tg = 20.04 t/s, tg_3s = 20.81 t/s 16.48.933.729 I slot print_timing: id 1 | task 17493 | n_gen = 605, tg = 20.44 t/s, tg_3s = 20.78 t/s 16.49.512.033 I slot print_timing: id 2 | task 17216 | n_gen = 891, tg = 19.68 t/s, tg_3s = 20.77 t/s 16.49.703.341 I slot print_timing: id 0 | task 17574 | n_gen = 541, tg = 20.89 t/s, tg_3s = 20.76 t/s 16.51.055.603 I slot print_timing: id 3 | task 17423 | n_gen = 718, tg = 20.10 t/s, tg_3s = 20.74 t/s 16.51.681.835 I slot print_timing: id 3 | task 17423 | prompt eval time = 807.13 ms / 503 tokens ( 1.60 ms per token, 623.20 tokens per second) 16.51.681.844 I slot print_timing: id 3 | task 17423 | eval time = 36291.39 ms / 731 tokens ( 49.71 ms per token, 20.11 tokens per second) 16.51.681.845 I slot print_timing: id 3 | task 17423 | total time = 37098.52 ms / 1234 tokens 16.51.681.846 I slot print_timing: id 3 | task 17423 | graphs reused = 17299 16.51.681.847 I slot print_timing: id 3 | task 17423 | graph reallocs = 0 / 0 (same size) / (changed size) 16.51.681.974 I slot release: id 3 | task 17423 | stop processing: n_tokens = 1928, truncated = 0 16.51.722.719 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.554 16.51.722.756 I slot launch_slot_: id 3 | task 18159 | processing task, is_child = 0 16.52.424.547 I slot print_timing: id 1 | task 17493 | n_gen = 664, tg = 20.06 t/s, tg_3s = 16.90 t/s 16.52.554.504 I slot print_timing: id 2 | task 17216 | n_gen = 940, tg = 19.46 t/s, tg_3s = 16.11 t/s 16.52.741.850 I slot print_timing: id 0 | task 17574 | n_gen = 590, tg = 20.39 t/s, tg_3s = 16.13 t/s 16.53.209.750 I slot print_timing: id 0 | task 17574 | prompt eval time = 749.67 ms / 456 tokens ( 1.64 ms per token, 608.27 tokens per second) 16.53.209.755 I slot print_timing: id 0 | task 17574 | eval time = 29356.66 ms / 600 tokens ( 49.01 ms per token, 20.40 tokens per second) 16.53.209.756 I slot print_timing: id 0 | task 17574 | total time = 30106.33 ms / 1056 tokens 16.53.209.756 I slot print_timing: id 0 | task 17574 | graphs reused = 17313 16.53.209.757 I slot print_timing: id 0 | task 17574 | graph reallocs = 0 / 0 (same size) / (changed size) 16.53.209.823 I slot release: id 0 | task 17574 | stop processing: n_tokens = 1751, truncated = 0 16.53.249.572 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.610 16.53.249.598 I slot launch_slot_: id 0 | task 18178 | processing task, is_child = 0 16.55.459.867 I slot print_timing: id 1 | task 17493 | n_gen = 714, tg = 19.76 t/s, tg_3s = 16.47 t/s 16.55.557.077 I slot print_timing: id 2 | task 17216 | n_gen = 990, tg = 19.29 t/s, tg_3s = 16.65 t/s 16.57.195.845 I slot print_timing: id 2 | task 17216 | prompt eval time = 815.78 ms / 501 tokens ( 1.63 ms per token, 614.13 tokens per second) 16.57.195.851 I slot print_timing: id 2 | task 17216 | eval time = 52898.44 ms / 1024 tokens ( 51.71 ms per token, 19.34 tokens per second) 16.57.195.852 I slot print_timing: id 2 | task 17216 | total time = 53714.22 ms / 1525 tokens 16.57.195.853 I slot print_timing: id 2 | task 17216 | graphs reused = 17380 16.57.195.854 I slot print_timing: id 2 | task 17216 | graph reallocs = 0 / 0 (same size) / (changed size) 16.57.195.979 I slot release: id 2 | task 17216 | stop processing: n_tokens = 2194, truncated = 0 16.57.244.742 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.487 16.57.256.841 I slot launch_slot_: id 2 | task 18249 | processing task, is_child = 0 16.58.486.493 I slot print_timing: id 1 | task 17493 | n_gen = 762, tg = 19.46 t/s, tg_3s = 15.86 t/s 16.58.579.781 I slot print_timing: id 3 | task 18159 | n_gen = 100, tg = 16.30 t/s, tg_3s = 16.47 t/s 16.59.438.667 I slot print_timing: id 0 | task 18178 | n_gen = 100, tg = 18.11 t/s, tg_3s = 18.30 t/s 17.01.500.970 I slot print_timing: id 1 | task 17493 | n_gen = 825, tg = 19.56 t/s, tg_3s = 20.90 t/s 17.01.598.648 I slot print_timing: id 3 | task 18159 | n_gen = 163, tg = 17.82 t/s, tg_3s = 20.87 t/s 17.02.463.436 I slot print_timing: id 0 | task 18178 | n_gen = 163, tg = 19.08 t/s, tg_3s = 20.83 t/s 17.02.801.680 I slot print_timing: id 2 | task 18249 | n_gen = 100, tg = 20.91 t/s, tg_3s = 21.12 t/s 17.04.333.780 I slot print_timing: id 1 | task 17493 | prompt eval time = 809.84 ms / 487 tokens ( 1.66 ms per token, 601.35 tokens per second) 17.04.333.788 I slot print_timing: id 1 | task 17493 | eval time = 44956.05 ms / 884 tokens ( 50.91 ms per token, 19.64 tokens per second) 17.04.333.790 I slot print_timing: id 1 | task 17493 | total time = 45765.90 ms / 1371 tokens 17.04.333.791 I slot print_timing: id 1 | task 17493 | graphs reused = 17510 17.04.333.792 I slot print_timing: id 1 | task 17493 | graph reallocs = 0 / 0 (same size) / (changed size) 17.04.333.939 I slot release: id 1 | task 17493 | stop processing: n_tokens = 2043, truncated = 0 17.04.383.014 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.523 17.04.383.053 I slot launch_slot_: id 1 | task 18384 | processing task, is_child = 0 17.05.116.713 I slot print_timing: id 3 | task 18159 | n_gen = 222, tg = 17.53 t/s, tg_3s = 16.77 t/s 17.05.485.843 I slot print_timing: id 0 | task 18178 | n_gen = 211, tg = 18.24 t/s, tg_3s = 15.88 t/s 17.05.812.410 I slot print_timing: id 2 | task 18249 | n_gen = 148, tg = 18.98 t/s, tg_3s = 15.94 t/s 17.08.123.595 I slot print_timing: id 3 | task 18159 | n_gen = 285, tg = 18.19 t/s, tg_3s = 20.95 t/s 17.08.502.237 I slot print_timing: id 0 | task 18178 | n_gen = 275, tg = 18.86 t/s, tg_3s = 21.22 t/s 17.08.837.241 I slot print_timing: id 2 | task 18249 | n_gen = 212, tg = 19.59 t/s, tg_3s = 21.16 t/s 17.09.885.542 I slot print_timing: id 1 | task 18384 | n_gen = 100, tg = 21.15 t/s, tg_3s = 21.37 t/s 17.11.135.236 I slot print_timing: id 3 | task 18159 | n_gen = 348, tg = 18.63 t/s, tg_3s = 20.92 t/s 17.11.515.713 I slot print_timing: id 0 | task 18178 | n_gen = 338, tg = 19.21 t/s, tg_3s = 20.91 t/s 17.11.854.705 I slot print_timing: id 2 | task 18249 | n_gen = 275, tg = 19.87 t/s, tg_3s = 20.88 t/s 17.12.907.294 I slot print_timing: id 1 | task 18384 | n_gen = 163, tg = 21.03 t/s, tg_3s = 20.85 t/s 17.14.152.067 I slot print_timing: id 3 | task 18159 | n_gen = 411, tg = 18.94 t/s, tg_3s = 20.88 t/s 17.14.533.870 I slot print_timing: id 0 | task 18178 | n_gen = 401, tg = 19.45 t/s, tg_3s = 20.87 t/s 17.14.869.776 I slot print_timing: id 2 | task 18249 | n_gen = 338, tg = 20.06 t/s, tg_3s = 20.90 t/s 17.15.921.496 I slot print_timing: id 1 | task 18384 | n_gen = 226, tg = 21.00 t/s, tg_3s = 20.90 t/s 17.16.160.357 I slot print_timing: id 0 | task 18178 | prompt eval time = 723.83 ms / 438 tokens ( 1.65 ms per token, 605.12 tokens per second) 17.16.160.365 I slot print_timing: id 0 | task 18178 | eval time = 22186.92 ms / 435 tokens ( 51.12 ms per token, 19.56 tokens per second) 17.16.160.366 I slot print_timing: id 0 | task 18178 | total time = 22910.75 ms / 873 tokens 17.16.160.367 I slot print_timing: id 0 | task 18178 | graphs reused = 17738 17.16.160.368 I slot print_timing: id 0 | task 18178 | graph reallocs = 0 / 0 (same size) / (changed size) 17.16.160.493 I slot release: id 0 | task 18178 | stop processing: n_tokens = 1568, truncated = 0 17.16.203.634 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.681 17.16.203.676 I slot launch_slot_: id 0 | task 18618 | processing task, is_child = 0 17.17.165.233 I slot print_timing: id 3 | task 18159 | n_gen = 461, tg = 18.65 t/s, tg_3s = 16.59 t/s 17.17.910.793 I slot print_timing: id 2 | task 18249 | n_gen = 389, tg = 19.55 t/s, tg_3s = 16.77 t/s 17.18.967.441 I slot print_timing: id 1 | task 18384 | n_gen = 277, tg = 20.06 t/s, tg_3s = 16.74 t/s 17.19.016.249 I slot print_timing: id 2 | task 18249 | prompt eval time = 810.70 ms / 492 tokens ( 1.65 ms per token, 606.88 tokens per second) 17.19.016.257 I slot print_timing: id 2 | task 18249 | eval time = 20948.69 ms / 412 tokens ( 50.97 ms per token, 19.62 tokens per second) 17.19.016.258 I slot print_timing: id 2 | task 18249 | total time = 21759.40 ms / 904 tokens 17.19.016.259 I slot print_timing: id 2 | task 18249 | graphs reused = 17782 17.19.016.260 I slot print_timing: id 2 | task 18249 | graph reallocs = 0 / 0 (same size) / (changed size) 17.19.016.382 I slot release: id 2 | task 18249 | stop processing: n_tokens = 1576, truncated = 0 17.19.065.323 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.678 17.19.065.368 I slot launch_slot_: id 2 | task 18666 | processing task, is_child = 0 17.20.176.105 I slot print_timing: id 3 | task 18159 | n_gen = 510, tg = 18.40 t/s, tg_3s = 16.27 t/s 17.21.989.038 I slot print_timing: id 1 | task 18384 | n_gen = 327, tg = 19.42 t/s, tg_3s = 16.55 t/s 17.22.267.110 I slot print_timing: id 0 | task 18618 | n_gen = 100, tg = 18.55 t/s, tg_3s = 18.73 t/s 17.23.197.386 I slot print_timing: id 3 | task 18159 | n_gen = 575, tg = 18.70 t/s, tg_3s = 21.51 t/s 17.24.449.231 I slot print_timing: id 2 | task 18666 | n_gen = 100, tg = 21.52 t/s, tg_3s = 21.74 t/s 17.25.030.181 I slot print_timing: id 1 | task 18384 | n_gen = 392, tg = 19.72 t/s, tg_3s = 21.37 t/s 17.25.271.310 I slot print_timing: id 0 | task 18618 | n_gen = 164, tg = 19.54 t/s, tg_3s = 21.30 t/s 17.26.227.460 I slot print_timing: id 3 | task 18159 | n_gen = 639, tg = 18.92 t/s, tg_3s = 21.12 t/s 17.27.469.443 I slot print_timing: id 2 | task 18666 | n_gen = 163, tg = 21.26 t/s, tg_3s = 20.86 t/s 17.28.042.422 I slot print_timing: id 1 | task 18384 | n_gen = 455, tg = 19.88 t/s, tg_3s = 20.91 t/s 17.28.280.996 I slot print_timing: id 0 | task 18618 | n_gen = 227, tg = 19.91 t/s, tg_3s = 20.93 t/s 17.29.241.802 I slot print_timing: id 3 | task 18159 | n_gen = 702, tg = 19.08 t/s, tg_3s = 20.90 t/s 17.30.490.164 I slot print_timing: id 2 | task 18666 | n_gen = 226, tg = 21.14 t/s, tg_3s = 20.86 t/s 17.31.064.722 I slot print_timing: id 1 | task 18384 | n_gen = 518, tg = 19.99 t/s, tg_3s = 20.85 t/s 17.31.302.917 I slot print_timing: id 0 | task 18618 | n_gen = 290, tg = 20.11 t/s, tg_3s = 20.85 t/s 17.32.266.009 I slot print_timing: id 3 | task 18159 | n_gen = 765, tg = 19.22 t/s, tg_3s = 20.83 t/s 17.33.515.988 I slot print_timing: id 2 | task 18666 | n_gen = 289, tg = 21.07 t/s, tg_3s = 20.82 t/s 17.34.092.596 I slot print_timing: id 1 | task 18384 | n_gen = 581, tg = 20.08 t/s, tg_3s = 20.81 t/s 17.34.331.534 I slot print_timing: id 0 | task 18618 | n_gen = 353, tg = 20.23 t/s, tg_3s = 20.80 t/s 17.35.297.646 I slot print_timing: id 3 | task 18159 | n_gen = 828, tg = 19.33 t/s, tg_3s = 20.78 t/s 17.36.544.493 I slot print_timing: id 2 | task 18666 | n_gen = 352, tg = 21.02 t/s, tg_3s = 20.80 t/s 17.37.118.958 I slot print_timing: id 1 | task 18384 | n_gen = 644, tg = 20.15 t/s, tg_3s = 20.82 t/s 17.37.357.605 I slot print_timing: id 0 | task 18618 | n_gen = 416, tg = 20.31 t/s, tg_3s = 20.82 t/s 17.38.325.608 I slot print_timing: id 3 | task 18159 | n_gen = 891, tg = 19.42 t/s, tg_3s = 20.81 t/s 17.39.575.639 I slot print_timing: id 2 | task 18666 | n_gen = 415, tg = 20.99 t/s, tg_3s = 20.78 t/s 17.40.153.619 I slot print_timing: id 1 | task 18384 | n_gen = 707, tg = 20.20 t/s, tg_3s = 20.76 t/s 17.40.393.860 I slot print_timing: id 0 | task 18618 | n_gen = 479, tg = 20.37 t/s, tg_3s = 20.75 t/s 17.41.360.233 I slot print_timing: id 3 | task 18159 | n_gen = 954, tg = 19.51 t/s, tg_3s = 20.76 t/s 17.42.609.446 I slot print_timing: id 2 | task 18666 | n_gen = 478, tg = 20.96 t/s, tg_3s = 20.77 t/s 17.43.187.772 I slot print_timing: id 1 | task 18384 | n_gen = 770, tg = 20.25 t/s, tg_3s = 20.76 t/s 17.43.332.940 I slot print_timing: id 2 | task 18666 | prompt eval time = 783.40 ms / 466 tokens ( 1.68 ms per token, 594.84 tokens per second) 17.43.332.947 I slot print_timing: id 2 | task 18666 | eval time = 23484.15 ms / 493 tokens ( 47.73 ms per token, 20.95 tokens per second) 17.43.332.948 I slot print_timing: id 2 | task 18666 | total time = 24267.56 ms / 959 tokens 17.43.332.949 I slot print_timing: id 2 | task 18666 | graphs reused = 18271 17.43.332.949 I slot print_timing: id 2 | task 18666 | graph reallocs = 0 / 0 (same size) / (changed size) 17.43.333.080 I slot release: id 2 | task 18666 | stop processing: n_tokens = 1631, truncated = 0 17.43.382.312 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.655 17.43.382.356 I slot launch_slot_: id 2 | task 19162 | processing task, is_child = 0 17.44.102.164 I slot print_timing: id 0 | task 18618 | n_gen = 542, tg = 19.91 t/s, tg_3s = 16.99 t/s 17.44.379.295 I slot print_timing: id 3 | task 18159 | n_gen = 1002, tg = 19.30 t/s, tg_3s = 15.90 t/s 17.45.410.392 I slot print_timing: id 3 | task 18159 | prompt eval time = 783.75 ms / 483 tokens ( 1.62 ms per token, 616.26 tokens per second) 17.45.410.394 I slot print_timing: id 3 | task 18159 | eval time = 52903.87 ms / 1024 tokens ( 51.71 ms per token, 19.34 tokens per second) 17.45.410.395 I slot print_timing: id 3 | task 18159 | total time = 53687.63 ms / 1507 tokens 17.45.410.395 I slot print_timing: id 3 | task 18159 | graphs reused = 18296 17.45.410.395 I slot print_timing: id 3 | task 18159 | graph reallocs = 0 / 0 (same size) / (changed size) 17.45.410.461 I slot release: id 3 | task 18159 | stop processing: n_tokens = 2201, truncated = 0 17.45.448.959 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.485 17.45.456.048 I slot launch_slot_: id 3 | task 19192 | processing task, is_child = 0 17.46.230.091 I slot print_timing: id 1 | task 18384 | n_gen = 805, tg = 19.60 t/s, tg_3s = 11.50 t/s 17.47.116.872 I slot print_timing: id 0 | task 18618 | n_gen = 591, tg = 19.54 t/s, tg_3s = 16.25 t/s 17.49.254.375 I slot print_timing: id 1 | task 18384 | n_gen = 869, tg = 19.71 t/s, tg_3s = 21.16 t/s 17.49.544.516 I slot print_timing: id 2 | task 19162 | n_gen = 100, tg = 18.49 t/s, tg_3s = 18.68 t/s 17.50.120.797 I slot print_timing: id 0 | task 18618 | n_gen = 654, tg = 19.67 t/s, tg_3s = 20.97 t/s 17.50.942.708 I slot print_timing: id 3 | task 19192 | n_gen = 100, tg = 21.01 t/s, tg_3s = 21.22 t/s 17.52.289.674 I slot print_timing: id 1 | task 18384 | n_gen = 932, tg = 19.77 t/s, tg_3s = 20.76 t/s 17.52.580.142 I slot print_timing: id 2 | task 19162 | n_gen = 163, tg = 19.31 t/s, tg_3s = 20.75 t/s 17.53.159.418 I slot print_timing: id 0 | task 18618 | n_gen = 717, tg = 19.76 t/s, tg_3s = 20.73 t/s 17.53.979.829 I slot print_timing: id 3 | task 19192 | n_gen = 163, tg = 20.91 t/s, tg_3s = 20.74 t/s 17.55.329.094 I slot print_timing: id 1 | task 18384 | n_gen = 995, tg = 19.83 t/s, tg_3s = 20.73 t/s 17.55.618.984 I slot print_timing: id 2 | task 19162 | n_gen = 226, tg = 19.69 t/s, tg_3s = 20.73 t/s 17.56.197.640 I slot print_timing: id 0 | task 18618 | n_gen = 780, tg = 19.84 t/s, tg_3s = 20.74 t/s 17.56.728.587 I slot print_timing: id 1 | task 18384 | prompt eval time = 822.55 ms / 502 tokens ( 1.64 ms per token, 610.30 tokens per second) 17.56.728.592 I slot print_timing: id 1 | task 18384 | eval time = 51522.97 ms / 1024 tokens ( 50.36 ms per token, 19.86 tokens per second) 17.56.728.593 I slot print_timing: id 1 | task 18384 | total time = 52345.52 ms / 1526 tokens 17.56.728.594 I slot print_timing: id 1 | task 18384 | graphs reused = 18513 17.56.728.595 I slot print_timing: id 1 | task 18384 | graph reallocs = 0 / 0 (same size) / (changed size) 17.56.728.744 I slot release: id 1 | task 18384 | stop processing: n_tokens = 2198, truncated = 0 17.56.778.857 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.486 17.56.790.163 I slot launch_slot_: id 1 | task 19415 | processing task, is_child = 0 17.57.486.994 I slot print_timing: id 3 | task 19192 | n_gen = 222, tg = 19.63 t/s, tg_3s = 16.82 t/s 17.58.619.912 I slot print_timing: id 2 | task 19162 | n_gen = 274, tg = 18.92 t/s, tg_3s = 16.00 t/s 17.59.241.604 I slot print_timing: id 0 | task 18618 | n_gen = 829, tg = 19.57 t/s, tg_3s = 16.10 t/s 18.00.533.719 I slot print_timing: id 3 | task 19192 | n_gen = 285, tg = 19.86 t/s, tg_3s = 20.68 t/s 18.01.635.015 I slot print_timing: id 2 | task 19162 | n_gen = 337, tg = 19.26 t/s, tg_3s = 20.89 t/s 18.02.257.134 I slot print_timing: id 0 | task 18618 | n_gen = 892, tg = 19.66 t/s, tg_3s = 20.89 t/s 18.02.306.023 I slot print_timing: id 1 | task 19415 | n_gen = 100, tg = 20.93 t/s, tg_3s = 21.14 t/s 18.03.560.621 I slot print_timing: id 3 | task 19192 | n_gen = 348, tg = 20.02 t/s, tg_3s = 20.81 t/s 18.04.667.245 I slot print_timing: id 2 | task 19162 | n_gen = 400, tg = 19.49 t/s, tg_3s = 20.78 t/s 18.05.291.585 I slot print_timing: id 0 | task 18618 | n_gen = 955, tg = 19.73 t/s, tg_3s = 20.76 t/s 18.05.340.459 I slot print_timing: id 1 | task 19415 | n_gen = 163, tg = 20.86 t/s, tg_3s = 20.76 t/s 18.06.589.968 I slot print_timing: id 3 | task 19192 | n_gen = 411, tg = 20.14 t/s, tg_3s = 20.80 t/s 18.07.698.568 I slot print_timing: id 2 | task 19162 | n_gen = 463, tg = 19.65 t/s, tg_3s = 20.78 t/s 18.08.320.566 I slot print_timing: id 0 | task 18618 | n_gen = 1018, tg = 19.79 t/s, tg_3s = 20.80 t/s 18.08.369.363 I slot print_timing: id 1 | task 19415 | n_gen = 226, tg = 20.85 t/s, tg_3s = 20.80 t/s 18.08.609.090 I slot print_timing: id 0 | task 18618 | prompt eval time = 725.56 ms / 440 tokens ( 1.65 ms per token, 606.43 tokens per second) 18.08.609.094 I slot print_timing: id 0 | task 18618 | eval time = 51679.85 ms / 1024 tokens ( 50.52 ms per token, 19.79 tokens per second) 18.08.609.095 I slot print_timing: id 0 | task 18618 | total time = 52405.41 ms / 1464 tokens 18.08.609.096 I slot print_timing: id 0 | task 18618 | graphs reused = 18741 18.08.609.097 I slot print_timing: id 0 | task 18618 | graph reallocs = 0 / 0 (same size) / (changed size) 18.08.609.218 I slot release: id 0 | task 18618 | stop processing: n_tokens = 2159, truncated = 0 18.08.652.134 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.495 18.08.654.881 I slot launch_slot_: id 0 | task 19649 | processing task, is_child = 0 18.09.599.724 I slot print_timing: id 3 | task 19192 | n_gen = 460, tg = 19.64 t/s, tg_3s = 16.28 t/s 18.10.734.948 I slot print_timing: id 2 | task 19162 | n_gen = 513, tg = 19.29 t/s, tg_3s = 16.47 t/s 18.11.406.155 I slot print_timing: id 1 | task 19415 | n_gen = 276, tg = 19.88 t/s, tg_3s = 16.46 t/s 18.12.603.136 I slot print_timing: id 3 | task 19192 | n_gen = 523, tg = 19.79 t/s, tg_3s = 20.98 t/s 18.13.754.484 I slot print_timing: id 2 | task 19162 | n_gen = 576, tg = 19.45 t/s, tg_3s = 20.86 t/s 18.14.138.464 I slot print_timing: id 0 | task 19649 | n_gen = 100, tg = 20.95 t/s, tg_3s = 21.16 t/s 18.14.427.861 I slot print_timing: id 1 | task 19415 | n_gen = 339, tg = 20.06 t/s, tg_3s = 20.85 t/s 18.15.627.820 I slot print_timing: id 3 | task 19192 | n_gen = 586, tg = 19.90 t/s, tg_3s = 20.83 t/s 18.16.779.396 I slot print_timing: id 2 | task 19162 | n_gen = 639, tg = 19.58 t/s, tg_3s = 20.83 t/s 18.17.161.427 I slot print_timing: id 0 | task 19649 | n_gen = 163, tg = 20.90 t/s, tg_3s = 20.84 t/s 18.17.448.084 I slot print_timing: id 1 | task 19415 | n_gen = 402, tg = 20.18 t/s, tg_3s = 20.86 t/s 18.18.645.321 I slot print_timing: id 3 | task 19192 | n_gen = 649, tg = 19.99 t/s, tg_3s = 20.88 t/s 18.19.794.423 I slot print_timing: id 2 | task 19162 | n_gen = 702, tg = 19.69 t/s, tg_3s = 20.90 t/s 18.20.176.682 I slot print_timing: id 0 | task 19649 | n_gen = 226, tg = 20.90 t/s, tg_3s = 20.89 t/s 18.20.465.345 I slot print_timing: id 1 | task 19415 | n_gen = 465, tg = 20.27 t/s, tg_3s = 20.88 t/s 18.21.665.320 I slot print_timing: id 3 | task 19192 | n_gen = 712, tg = 20.07 t/s, tg_3s = 20.86 t/s 18.22.822.117 I slot print_timing: id 2 | task 19162 | n_gen = 765, tg = 19.78 t/s, tg_3s = 20.81 t/s 18.23.204.703 I slot print_timing: id 0 | task 19649 | n_gen = 289, tg = 20.88 t/s, tg_3s = 20.81 t/s 18.23.492.738 I slot print_timing: id 1 | task 19415 | n_gen = 528, tg = 20.33 t/s, tg_3s = 20.81 t/s 18.24.690.045 I slot print_timing: id 3 | task 19192 | n_gen = 775, tg = 20.13 t/s, tg_3s = 20.83 t/s 18.25.358.832 I slot print_timing: id 1 | task 19415 | prompt eval time = 785.24 ms / 471 tokens ( 1.67 ms per token, 599.82 tokens per second) 18.25.358.837 I slot print_timing: id 1 | task 19415 | eval time = 27783.42 ms / 567 tokens ( 49.09 ms per token, 20.37 tokens per second) 18.25.358.838 I slot print_timing: id 1 | task 19415 | total time = 28568.66 ms / 1038 tokens 18.25.358.839 I slot print_timing: id 1 | task 19415 | graphs reused = 19073 18.25.358.840 I slot print_timing: id 1 | task 19415 | graph reallocs = 0 / 0 (same size) / (changed size) 18.25.358.952 I slot release: id 1 | task 19415 | stop processing: n_tokens = 1710, truncated = 0 18.25.408.148 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.625 18.25.408.194 I slot launch_slot_: id 1 | task 19986 | processing task, is_child = 0 18.26.139.721 I slot print_timing: id 2 | task 19162 | n_gen = 820, tg = 19.52 t/s, tg_3s = 16.58 t/s 18.26.227.824 I slot print_timing: id 0 | task 19649 | n_gen = 337, tg = 19.98 t/s, tg_3s = 15.88 t/s 18.27.700.002 I slot print_timing: id 3 | task 19192 | n_gen = 823, tg = 19.82 t/s, tg_3s = 15.95 t/s 18.29.141.789 I slot print_timing: id 2 | task 19162 | n_gen = 882, tg = 19.60 t/s, tg_3s = 20.65 t/s 18.29.236.912 I slot print_timing: id 0 | task 19649 | n_gen = 400, tg = 20.13 t/s, tg_3s = 20.94 t/s 18.30.733.876 I slot print_timing: id 3 | task 19192 | n_gen = 886, tg = 19.89 t/s, tg_3s = 20.77 t/s 18.30.972.978 I slot print_timing: id 1 | task 19986 | n_gen = 100, tg = 20.86 t/s, tg_3s = 21.08 t/s 18.32.180.102 I slot print_timing: id 2 | task 19162 | n_gen = 945, tg = 19.67 t/s, tg_3s = 20.74 t/s 18.32.180.661 I slot print_timing: id 3 | task 19192 | prompt eval time = 774.66 ms / 474 tokens ( 1.63 ms per token, 611.88 tokens per second) 18.32.180.665 I slot print_timing: id 3 | task 19192 | eval time = 45949.94 ms / 916 tokens ( 50.22 ms per token, 19.91 tokens per second) 18.32.180.666 I slot print_timing: id 3 | task 19192 | total time = 46724.60 ms / 1390 tokens 18.32.180.667 I slot print_timing: id 3 | task 19192 | graphs reused = 19195 18.32.180.668 I slot print_timing: id 3 | task 19192 | graph reallocs = 0 / 0 (same size) / (changed size) 18.32.180.786 I slot release: id 3 | task 19192 | stop processing: n_tokens = 2084, truncated = 0 18.32.221.764 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.512 18.32.221.801 I slot launch_slot_: id 3 | task 20114 | processing task, is_child = 0 18.32.913.521 I slot print_timing: id 0 | task 19649 | n_gen = 463, tg = 19.66 t/s, tg_3s = 17.14 t/s 18.33.978.744 I slot print_timing: id 1 | task 19986 | n_gen = 149, tg = 19.10 t/s, tg_3s = 16.30 t/s 18.35.190.570 I slot print_timing: id 2 | task 19162 | n_gen = 995, tg = 19.49 t/s, tg_3s = 16.61 t/s 18.35.944.117 I slot print_timing: id 0 | task 19649 | n_gen = 527, tg = 19.83 t/s, tg_3s = 21.12 t/s 18.36.572.069 I slot print_timing: id 2 | task 19162 | prompt eval time = 808.74 ms / 487 tokens ( 1.66 ms per token, 602.17 tokens per second) 18.36.572.074 I slot print_timing: id 2 | task 19162 | eval time = 52380.97 ms / 1024 tokens ( 51.20 ms per token, 19.53 tokens per second) 18.36.572.075 I slot print_timing: id 2 | task 19162 | total time = 53189.70 ms / 1511 tokens 18.36.572.076 I slot print_timing: id 2 | task 19162 | graphs reused = 19270 18.36.572.076 I slot print_timing: id 2 | task 19162 | graph reallocs = 0 / 0 (same size) / (changed size) 18.36.572.190 I slot release: id 2 | task 19162 | stop processing: n_tokens = 2183, truncated = 0 18.36.620.913 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.489 18.36.624.119 I slot launch_slot_: id 2 | task 20194 | processing task, is_child = 0 18.37.343.591 I slot print_timing: id 1 | task 19986 | n_gen = 206, tg = 18.44 t/s, tg_3s = 16.94 t/s 18.38.386.550 I slot print_timing: id 3 | task 20114 | n_gen = 100, tg = 18.37 t/s, tg_3s = 18.55 t/s 18.38.956.103 I slot print_timing: id 0 | task 19649 | n_gen = 575, tg = 19.43 t/s, tg_3s = 15.94 t/s 18.40.346.734 I slot print_timing: id 1 | task 19986 | n_gen = 268, tg = 18.91 t/s, tg_3s = 20.65 t/s 18.41.398.531 I slot print_timing: id 3 | task 20114 | n_gen = 163, tg = 19.28 t/s, tg_3s = 20.92 t/s 18.41.972.804 I slot print_timing: id 0 | task 19649 | n_gen = 638, tg = 19.56 t/s, tg_3s = 20.88 t/s 18.42.165.342 I slot print_timing: id 2 | task 20194 | n_gen = 100, tg = 20.91 t/s, tg_3s = 21.13 t/s 18.43.359.771 I slot print_timing: id 1 | task 19986 | n_gen = 331, tg = 19.26 t/s, tg_3s = 20.91 t/s 18.44.410.985 I slot print_timing: id 3 | task 20114 | n_gen = 226, tg = 19.71 t/s, tg_3s = 20.91 t/s 18.44.984.533 I slot print_timing: id 0 | task 19649 | n_gen = 701, tg = 19.68 t/s, tg_3s = 20.92 t/s 18.45.177.772 I slot print_timing: id 2 | task 20194 | n_gen = 163, tg = 20.91 t/s, tg_3s = 20.91 t/s 18.46.372.113 I slot print_timing: id 1 | task 19986 | n_gen = 394, tg = 19.51 t/s, tg_3s = 20.91 t/s 18.47.426.641 I slot print_timing: id 3 | task 20114 | n_gen = 289, tg = 19.96 t/s, tg_3s = 20.89 t/s 18.47.998.244 I slot print_timing: id 0 | task 19649 | n_gen = 764, tg = 19.77 t/s, tg_3s = 20.90 t/s 18.48.191.057 I slot print_timing: id 2 | task 20194 | n_gen = 226, tg = 20.91 t/s, tg_3s = 20.91 t/s 18.49.387.173 I slot print_timing: id 1 | task 19986 | n_gen = 457, tg = 19.69 t/s, tg_3s = 20.90 t/s 18.50.443.636 I slot print_timing: id 3 | task 20114 | n_gen = 352, tg = 20.12 t/s, tg_3s = 20.88 t/s 18.51.019.620 I slot print_timing: id 0 | task 19649 | n_gen = 827, tg = 19.85 t/s, tg_3s = 20.85 t/s 18.51.214.355 I slot print_timing: id 2 | task 20194 | n_gen = 289, tg = 20.90 t/s, tg_3s = 20.84 t/s 18.52.419.510 I slot print_timing: id 1 | task 19986 | n_gen = 520, tg = 19.82 t/s, tg_3s = 20.78 t/s 18.53.478.126 I slot print_timing: id 3 | task 20114 | n_gen = 415, tg = 20.21 t/s, tg_3s = 20.76 t/s 18.54.053.284 I slot print_timing: id 0 | task 19649 | n_gen = 890, tg = 19.91 t/s, tg_3s = 20.77 t/s 18.54.247.471 I slot print_timing: id 2 | task 20194 | n_gen = 352, tg = 20.87 t/s, tg_3s = 20.77 t/s 18.55.447.801 I slot print_timing: id 1 | task 19986 | n_gen = 583, tg = 19.92 t/s, tg_3s = 20.80 t/s 18.56.170.028 I slot print_timing: id 0 | task 19649 | prompt eval time = 757.12 ms / 465 tokens ( 1.63 ms per token, 614.17 tokens per second) 18.56.170.033 I slot print_timing: id 0 | task 19649 | eval time = 46758.01 ms / 934 tokens ( 50.12 ms per token, 19.95 tokens per second) 18.56.170.034 I slot print_timing: id 0 | task 19649 | total time = 47515.13 ms / 1399 tokens 18.56.170.035 I slot print_timing: id 0 | task 19649 | graphs reused = 19658 18.56.170.035 I slot print_timing: id 0 | task 19649 | graph reallocs = 0 / 0 (same size) / (changed size) 18.56.170.159 I slot release: id 0 | task 19649 | stop processing: n_tokens = 2094, truncated = 0 18.56.213.204 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.510 18.56.213.254 I slot launch_slot_: id 0 | task 20589 | processing task, is_child = 0 18.56.871.465 I slot print_timing: id 3 | task 20114 | n_gen = 473, tg = 19.77 t/s, tg_3s = 17.09 t/s 18.57.251.501 I slot print_timing: id 2 | task 20194 | n_gen = 401, tg = 20.18 t/s, tg_3s = 16.31 t/s 18.58.456.144 I slot print_timing: id 1 | task 19986 | n_gen = 632, tg = 19.58 t/s, tg_3s = 16.29 t/s 18.59.897.846 I slot print_timing: id 3 | task 20114 | n_gen = 535, tg = 19.85 t/s, tg_3s = 20.49 t/s 19.00.280.660 I slot print_timing: id 2 | task 20194 | n_gen = 464, tg = 20.26 t/s, tg_3s = 20.80 t/s 19.01.475.507 I slot print_timing: id 1 | task 19986 | n_gen = 695, tg = 19.69 t/s, tg_3s = 20.87 t/s 19.01.715.157 I slot print_timing: id 0 | task 20589 | n_gen = 100, tg = 20.80 t/s, tg_3s = 21.01 t/s 19.02.527.983 I slot print_timing: id 3 | task 20114 | prompt eval time = 774.34 ms / 472 tokens ( 1.64 ms per token, 609.55 tokens per second) 19.02.527.988 I slot print_timing: id 3 | task 20114 | eval time = 29531.83 ms / 590 tokens ( 50.14 ms per token, 19.94 tokens per second) 19.02.527.989 I slot print_timing: id 3 | task 20114 | total time = 30306.17 ms / 1062 tokens 19.02.527.990 I slot print_timing: id 3 | task 20114 | graphs reused = 19773 19.02.527.991 I slot print_timing: id 3 | task 20114 | graph reallocs = 0 / 0 (same size) / (changed size) 19.02.528.106 I slot release: id 3 | task 20114 | stop processing: n_tokens = 1756, truncated = 0 19.02.568.774 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.608 19.02.568.825 I slot launch_slot_: id 3 | task 20709 | processing task, is_child = 0 19.03.311.025 I slot print_timing: id 2 | task 20194 | n_gen = 514, tg = 19.82 t/s, tg_3s = 16.50 t/s 19.04.519.604 I slot print_timing: id 1 | task 19986 | n_gen = 746, tg = 19.46 t/s, tg_3s = 16.75 t/s 19.04.759.438 I slot print_timing: id 0 | task 20589 | n_gen = 151, tg = 19.22 t/s, tg_3s = 16.75 t/s 19.06.352.192 I slot print_timing: id 2 | task 20194 | n_gen = 578, tg = 19.95 t/s, tg_3s = 21.04 t/s 19.07.552.485 I slot print_timing: id 1 | task 19986 | n_gen = 809, tg = 19.55 t/s, tg_3s = 20.77 t/s 19.07.793.039 I slot print_timing: id 0 | task 20589 | n_gen = 214, tg = 19.66 t/s, tg_3s = 20.77 t/s 19.08.036.038 I slot print_timing: id 3 | task 20709 | n_gen = 100, tg = 20.95 t/s, tg_3s = 21.17 t/s 19.09.377.719 I slot print_timing: id 2 | task 20194 | n_gen = 641, tg = 20.03 t/s, tg_3s = 20.82 t/s 19.10.572.888 I slot print_timing: id 1 | task 19986 | n_gen = 872, tg = 19.64 t/s, tg_3s = 20.86 t/s 19.10.814.412 I slot print_timing: id 0 | task 20589 | n_gen = 277, tg = 19.92 t/s, tg_3s = 20.85 t/s 19.11.055.882 I slot print_timing: id 3 | task 20709 | n_gen = 163, tg = 20.92 t/s, tg_3s = 20.86 t/s 19.12.398.331 I slot print_timing: id 2 | task 20194 | n_gen = 704, tg = 20.10 t/s, tg_3s = 20.86 t/s 19.13.598.387 I slot print_timing: id 1 | task 19986 | n_gen = 935, tg = 19.72 t/s, tg_3s = 20.82 t/s 19.13.837.902 I slot print_timing: id 0 | task 20589 | n_gen = 340, tg = 20.08 t/s, tg_3s = 20.84 t/s 19.14.080.264 I slot print_timing: id 3 | task 20709 | n_gen = 226, tg = 20.89 t/s, tg_3s = 20.83 t/s 19.14.270.949 I slot print_timing: id 2 | task 20194 | prompt eval time = 807.73 ms / 486 tokens ( 1.66 ms per token, 601.69 tokens per second) 19.14.270.957 I slot print_timing: id 2 | task 20194 | eval time = 36839.09 ms / 743 tokens ( 49.65 ms per token, 20.14 tokens per second) 19.14.270.958 I slot print_timing: id 2 | task 20194 | total time = 37646.82 ms / 1229 tokens 19.14.270.959 I slot print_timing: id 2 | task 20194 | graphs reused = 20000 19.14.270.960 I slot print_timing: id 2 | task 20194 | graph reallocs = 0 / 0 (same size) / (changed size) 19.14.271.074 I slot release: id 2 | task 20194 | stop processing: n_tokens = 1901, truncated = 0 19.14.319.888 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.562 19.14.319.938 I slot launch_slot_: id 2 | task 20942 | processing task, is_child = 0 19.16.636.353 I slot print_timing: id 1 | task 19986 | n_gen = 983, tg = 19.48 t/s, tg_3s = 15.80 t/s 19.16.838.616 I slot print_timing: id 0 | task 20589 | n_gen = 387, tg = 19.41 t/s, tg_3s = 15.66 t/s 19.17.081.432 I slot print_timing: id 3 | task 20709 | n_gen = 273, tg = 19.75 t/s, tg_3s = 15.66 t/s 19.18.612.527 I slot print_timing: id 1 | task 19986 | prompt eval time = 819.97 ms / 502 tokens ( 1.63 ms per token, 612.22 tokens per second) 19.18.612.538 I slot print_timing: id 1 | task 19986 | eval time = 52384.35 ms / 1024 tokens ( 51.21 ms per token, 19.53 tokens per second) 19.18.612.539 I slot print_timing: id 1 | task 19986 | total time = 53204.32 ms / 1526 tokens 19.18.612.540 I slot print_timing: id 1 | task 19986 | graphs reused = 20070 19.18.612.541 I slot print_timing: id 1 | task 19986 | graph reallocs = 0 / 0 (same size) / (changed size) 19.18.612.695 I slot release: id 1 | task 19986 | stop processing: n_tokens = 2198, truncated = 0 19.18.661.238 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.486 19.18.672.602 I slot launch_slot_: id 1 | task 21018 | processing task, is_child = 0 19.19.867.900 I slot print_timing: id 0 | task 20589 | n_gen = 436, tg = 18.99 t/s, tg_3s = 16.18 t/s 19.20.101.228 I slot print_timing: id 3 | task 20709 | n_gen = 322, tg = 19.12 t/s, tg_3s = 16.23 t/s 19.20.332.778 I slot print_timing: id 0 | task 20589 | prompt eval time = 742.94 ms / 448 tokens ( 1.66 ms per token, 603.01 tokens per second) 19.20.332.783 I slot print_timing: id 0 | task 20589 | eval time = 23376.58 ms / 446 tokens ( 52.53 ms per token, 19.04 tokens per second) 19.20.332.784 I slot print_timing: id 0 | task 20589 | total time = 24119.52 ms / 894 tokens 19.20.332.784 I slot print_timing: id 0 | task 20589 | graphs reused = 20088 19.20.332.785 I slot print_timing: id 0 | task 20589 | graph reallocs = 0 / 0 (same size) / (changed size) 19.20.332.848 I slot release: id 0 | task 20589 | stop processing: n_tokens = 1589, truncated = 0 19.20.371.937 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.672 19.20.371.964 I slot launch_slot_: id 0 | task 21041 | processing task, is_child = 0 19.21.243.366 I slot print_timing: id 2 | task 20942 | n_gen = 100, tg = 16.47 t/s, tg_3s = 16.64 t/s 19.23.129.678 I slot print_timing: id 3 | task 20709 | n_gen = 373, tg = 18.77 t/s, tg_3s = 16.84 t/s 19.24.280.959 I slot print_timing: id 2 | task 20942 | n_gen = 164, tg = 18.01 t/s, tg_3s = 21.07 t/s 19.24.762.028 I slot print_timing: id 1 | task 21018 | n_gen = 100, tg = 18.63 t/s, tg_3s = 18.82 t/s 19.25.815.837 I slot print_timing: id 0 | task 21041 | n_gen = 100, tg = 21.00 t/s, tg_3s = 21.21 t/s 19.26.155.575 I slot print_timing: id 3 | task 20709 | n_gen = 436, tg = 19.04 t/s, tg_3s = 20.82 t/s 19.27.307.688 I slot print_timing: id 2 | task 20942 | n_gen = 227, tg = 18.72 t/s, tg_3s = 20.81 t/s 19.27.787.727 I slot print_timing: id 1 | task 21018 | n_gen = 163, tg = 19.43 t/s, tg_3s = 20.82 t/s 19.28.840.353 I slot print_timing: id 0 | task 21041 | n_gen = 163, tg = 20.93 t/s, tg_3s = 20.83 t/s 19.29.177.520 I slot print_timing: id 3 | task 20709 | n_gen = 499, tg = 19.25 t/s, tg_3s = 20.85 t/s 19.30.324.688 I slot print_timing: id 2 | task 20942 | n_gen = 290, tg = 19.15 t/s, tg_3s = 20.88 t/s 19.30.802.208 I slot print_timing: id 1 | task 21018 | n_gen = 226, tg = 19.82 t/s, tg_3s = 20.90 t/s 19.31.853.344 I slot print_timing: id 0 | task 21041 | n_gen = 226, tg = 20.93 t/s, tg_3s = 20.91 t/s 19.32.190.757 I slot print_timing: id 3 | task 20709 | n_gen = 562, tg = 19.43 t/s, tg_3s = 20.91 t/s 19.33.340.361 I slot print_timing: id 2 | task 20942 | n_gen = 353, tg = 19.44 t/s, tg_3s = 20.89 t/s 19.33.819.328 I slot print_timing: id 1 | task 21018 | n_gen = 289, tg = 20.04 t/s, tg_3s = 20.88 t/s 19.34.877.293 I slot print_timing: id 0 | task 21041 | n_gen = 289, tg = 20.91 t/s, tg_3s = 20.83 t/s 19.35.216.818 I slot print_timing: id 3 | task 20709 | n_gen = 625, tg = 19.56 t/s, tg_3s = 20.82 t/s 19.36.371.587 I slot print_timing: id 2 | task 20942 | n_gen = 416, tg = 19.63 t/s, tg_3s = 20.78 t/s 19.36.853.414 I slot print_timing: id 1 | task 21018 | n_gen = 352, tg = 20.17 t/s, tg_3s = 20.76 t/s 19.37.908.694 I slot print_timing: id 0 | task 21041 | n_gen = 352, tg = 20.88 t/s, tg_3s = 20.78 t/s 19.38.245.480 I slot print_timing: id 3 | task 20709 | n_gen = 688, tg = 19.67 t/s, tg_3s = 20.80 t/s 19.39.394.922 I slot print_timing: id 2 | task 20942 | n_gen = 479, tg = 19.78 t/s, tg_3s = 20.84 t/s 19.39.874.110 I slot print_timing: id 1 | task 21018 | n_gen = 415, tg = 20.27 t/s, tg_3s = 20.86 t/s 19.40.932.020 I slot print_timing: id 0 | task 21041 | n_gen = 415, tg = 20.88 t/s, tg_3s = 20.84 t/s 19.41.271.933 I slot print_timing: id 3 | task 20709 | n_gen = 751, tg = 19.76 t/s, tg_3s = 20.82 t/s 19.42.430.333 I slot print_timing: id 2 | task 20942 | n_gen = 542, tg = 19.89 t/s, tg_3s = 20.76 t/s 19.42.910.242 I slot print_timing: id 1 | task 21018 | n_gen = 478, tg = 20.33 t/s, tg_3s = 20.75 t/s 19.43.970.613 I slot print_timing: id 0 | task 21041 | n_gen = 478, tg = 20.86 t/s, tg_3s = 20.73 t/s 19.44.308.952 I slot print_timing: id 3 | task 20709 | n_gen = 814, tg = 19.83 t/s, tg_3s = 20.74 t/s 19.45.366.792 I slot print_timing: id 1 | task 21018 | prompt eval time = 775.95 ms / 457 tokens ( 1.70 ms per token, 588.96 tokens per second) 19.45.366.797 I slot print_timing: id 1 | task 21018 | eval time = 25918.22 ms / 529 tokens ( 49.09 ms per token, 20.37 tokens per second) 19.45.366.798 I slot print_timing: id 1 | task 21018 | total time = 26694.17 ms / 986 tokens 19.45.366.799 I slot print_timing: id 1 | task 21018 | graphs reused = 20592 19.45.366.800 I slot print_timing: id 1 | task 21018 | graph reallocs = 0 / 0 (same size) / (changed size) 19.45.366.928 I slot release: id 1 | task 21018 | stop processing: n_tokens = 1658, truncated = 0 19.45.416.551 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.644 19.45.416.595 I slot launch_slot_: id 1 | task 21551 | processing task, is_child = 0 19.46.110.877 I slot print_timing: id 2 | task 20942 | n_gen = 605, tg = 19.56 t/s, tg_3s = 17.12 t/s 19.47.009.258 I slot print_timing: id 0 | task 21041 | n_gen = 527, tg = 20.30 t/s, tg_3s = 16.13 t/s 19.47.348.312 I slot print_timing: id 3 | task 20709 | prompt eval time = 742.53 ms / 443 tokens ( 1.68 ms per token, 596.61 tokens per second) 19.47.348.317 I slot print_timing: id 3 | task 20709 | eval time = 44036.95 ms / 863 tokens ( 51.09 ms per token, 19.57 tokens per second) 19.47.348.318 I slot print_timing: id 3 | task 20709 | total time = 44779.48 ms / 1306 tokens 19.47.348.319 I slot print_timing: id 3 | task 20709 | graphs reused = 20615 19.47.348.320 I slot print_timing: id 3 | task 20709 | graph reallocs = 0 / 0 (same size) / (changed size) 19.47.348.445 I slot release: id 3 | task 20709 | stop processing: n_tokens = 2000, truncated = 0 19.47.389.426 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.534 19.47.389.466 I slot launch_slot_: id 3 | task 21579 | processing task, is_child = 0 19.49.135.989 I slot print_timing: id 2 | task 20942 | n_gen = 654, tg = 19.26 t/s, tg_3s = 16.20 t/s 19.50.021.522 I slot print_timing: id 0 | task 21041 | n_gen = 577, tg = 19.92 t/s, tg_3s = 16.60 t/s 19.51.549.631 I slot print_timing: id 1 | task 21551 | n_gen = 100, tg = 18.51 t/s, tg_3s = 18.69 t/s 19.52.173.846 I slot print_timing: id 2 | task 20942 | n_gen = 718, tg = 19.41 t/s, tg_3s = 21.07 t/s 19.52.844.697 I slot print_timing: id 3 | task 21579 | n_gen = 100, tg = 21.12 t/s, tg_3s = 21.33 t/s 19.53.034.599 I slot print_timing: id 0 | task 21041 | n_gen = 640, tg = 20.01 t/s, tg_3s = 20.91 t/s 19.54.570.059 I slot print_timing: id 1 | task 21551 | n_gen = 163, tg = 19.35 t/s, tg_3s = 20.86 t/s 19.55.192.573 I slot print_timing: id 2 | task 20942 | n_gen = 781, tg = 19.52 t/s, tg_3s = 20.87 t/s 19.55.861.311 I slot print_timing: id 3 | task 21579 | n_gen = 163, tg = 21.03 t/s, tg_3s = 20.88 t/s 19.56.051.080 I slot print_timing: id 0 | task 21041 | n_gen = 703, tg = 20.09 t/s, tg_3s = 20.89 t/s 19.57.584.937 I slot print_timing: id 1 | task 21551 | n_gen = 226, tg = 19.76 t/s, tg_3s = 20.90 t/s 19.58.210.045 I slot print_timing: id 2 | task 20942 | n_gen = 844, tg = 19.61 t/s, tg_3s = 20.88 t/s 19.58.882.361 I slot print_timing: id 3 | task 21579 | n_gen = 226, tg = 20.98 t/s, tg_3s = 20.85 t/s 19.59.072.937 I slot print_timing: id 0 | task 21041 | n_gen = 766, tg = 20.15 t/s, tg_3s = 20.85 t/s 20.00.615.182 I slot print_timing: id 1 | task 21551 | n_gen = 289, tg = 19.98 t/s, tg_3s = 20.79 t/s 20.01.240.514 I slot print_timing: id 2 | task 20942 | n_gen = 907, tg = 19.69 t/s, tg_3s = 20.79 t/s 20.01.917.108 I slot print_timing: id 3 | task 21579 | n_gen = 289, tg = 20.93 t/s, tg_3s = 20.76 t/s 20.02.107.626 I slot print_timing: id 0 | task 21041 | n_gen = 829, tg = 20.19 t/s, tg_3s = 20.76 t/s 20.02.397.197 I slot print_timing: id 1 | task 21551 | prompt eval time = 783.17 ms / 465 tokens ( 1.68 ms per token, 593.74 tokens per second) 20.02.397.206 I slot print_timing: id 1 | task 21551 | eval time = 16197.42 ms / 326 tokens ( 49.84 ms per token, 20.06 tokens per second) 20.02.397.207 I slot print_timing: id 1 | task 21551 | total time = 16980.59 ms / 791 tokens 20.02.397.208 I slot print_timing: id 1 | task 21551 | graphs reused = 20911 20.02.397.209 I slot print_timing: id 1 | task 21551 | graph reallocs = 0 / 0 (same size) / (changed size) 20.02.397.350 I slot release: id 1 | task 21551 | stop processing: n_tokens = 1463, truncated = 0 20.02.447.087 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.730 20.02.447.130 I slot launch_slot_: id 1 | task 21881 | processing task, is_child = 0 20.04.245.099 I slot print_timing: id 2 | task 20942 | n_gen = 955, tg = 19.46 t/s, tg_3s = 15.98 t/s 20.04.956.047 I slot print_timing: id 3 | task 21579 | n_gen = 338, tg = 20.06 t/s, tg_3s = 16.12 t/s 20.05.147.452 I slot print_timing: id 0 | task 21041 | n_gen = 878, tg = 19.91 t/s, tg_3s = 16.12 t/s 20.06.305.182 I slot print_timing: id 2 | task 20942 | prompt eval time = 912.03 ms / 519 tokens ( 1.76 ms per token, 569.06 tokens per second) 20.06.305.191 I slot print_timing: id 2 | task 20942 | eval time = 51073.21 ms / 998 tokens ( 51.23 ms per token, 19.52 tokens per second) 20.06.305.192 I slot print_timing: id 2 | task 20942 | total time = 51985.23 ms / 1517 tokens 20.06.305.193 I slot print_timing: id 2 | task 20942 | graphs reused = 20974 20.06.305.193 I slot print_timing: id 2 | task 20942 | graph reallocs = 0 / 0 (same size) / (changed size) 20.06.305.330 I slot release: id 2 | task 20942 | stop processing: n_tokens = 2189, truncated = 0 20.06.354.715 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.488 20.06.369.838 I slot launch_slot_: id 2 | task 21949 | processing task, is_child = 0 20.07.990.086 I slot print_timing: id 3 | task 21579 | n_gen = 387, tg = 19.46 t/s, tg_3s = 16.15 t/s 20.08.175.898 I slot print_timing: id 0 | task 21041 | n_gen = 927, tg = 19.67 t/s, tg_3s = 16.18 t/s 20.08.642.776 I slot print_timing: id 1 | task 21881 | n_gen = 100, tg = 18.40 t/s, tg_3s = 18.58 t/s 20.10.994.962 I slot print_timing: id 3 | task 21579 | n_gen = 450, tg = 19.66 t/s, tg_3s = 20.97 t/s 20.11.184.274 I slot print_timing: id 0 | task 21041 | n_gen = 990, tg = 19.75 t/s, tg_3s = 20.94 t/s 20.11.664.010 I slot print_timing: id 1 | task 21881 | n_gen = 163, tg = 19.28 t/s, tg_3s = 20.85 t/s 20.11.856.028 I slot print_timing: id 2 | task 21949 | n_gen = 100, tg = 21.03 t/s, tg_3s = 21.24 t/s 20.12.812.481 I slot print_timing: id 0 | task 21041 | prompt eval time = 729.36 ms / 447 tokens ( 1.63 ms per token, 612.87 tokens per second) 20.12.812.488 I slot print_timing: id 0 | task 21041 | eval time = 51711.15 ms / 1024 tokens ( 50.55 ms per token, 19.78 tokens per second) 20.12.812.489 I slot print_timing: id 0 | task 21041 | total time = 52440.51 ms / 1471 tokens 20.12.812.490 I slot print_timing: id 0 | task 21041 | graphs reused = 21091 20.12.812.490 I slot print_timing: id 0 | task 21041 | graph reallocs = 0 / 0 (same size) / (changed size) 20.12.812.585 I slot release: id 0 | task 21041 | stop processing: n_tokens = 2166, truncated = 0 20.12.854.392 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.493 20.12.865.982 I slot launch_slot_: id 0 | task 22072 | processing task, is_child = 0 20.14.015.532 I slot print_timing: id 3 | task 21579 | n_gen = 498, tg = 19.22 t/s, tg_3s = 15.89 t/s 20.14.690.040 I slot print_timing: id 1 | task 21881 | n_gen = 211, tg = 18.37 t/s, tg_3s = 15.86 t/s 20.14.882.670 I slot print_timing: id 2 | task 21949 | n_gen = 148, tg = 19.00 t/s, tg_3s = 15.86 t/s 20.17.031.387 I slot print_timing: id 3 | task 21579 | n_gen = 561, tg = 19.39 t/s, tg_3s = 20.89 t/s 20.17.700.834 I slot print_timing: id 1 | task 21881 | n_gen = 274, tg = 18.91 t/s, tg_3s = 20.92 t/s 20.17.893.356 I slot print_timing: id 2 | task 21949 | n_gen = 211, tg = 19.54 t/s, tg_3s = 20.93 t/s 20.18.468.933 I slot print_timing: id 0 | task 22072 | n_gen = 100, tg = 20.91 t/s, tg_3s = 21.12 t/s 20.18.950.264 I slot print_timing: id 3 | task 21579 | prompt eval time = 767.39 ms / 462 tokens ( 1.66 ms per token, 602.04 tokens per second) 20.18.950.271 I slot print_timing: id 3 | task 21579 | eval time = 30793.39 ms / 601 tokens ( 51.32 ms per token, 19.48 tokens per second) 20.18.950.273 I slot print_timing: id 3 | task 21579 | total time = 31560.79 ms / 1063 tokens 20.18.950.273 I slot print_timing: id 3 | task 21579 | graphs reused = 21200 20.18.950.274 I slot print_timing: id 3 | task 21579 | graph reallocs = 0 / 0 (same size) / (changed size) 20.18.950.386 I slot release: id 3 | task 21579 | stop processing: n_tokens = 1757, truncated = 0 20.18.990.862 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.608 20.18.990.901 I slot launch_slot_: id 3 | task 22186 | processing task, is_child = 0 20.20.733.619 I slot print_timing: id 1 | task 21881 | n_gen = 324, tg = 18.49 t/s, tg_3s = 16.49 t/s 20.20.933.857 I slot print_timing: id 2 | task 21949 | n_gen = 261, tg = 18.86 t/s, tg_3s = 16.44 t/s 20.21.506.917 I slot print_timing: id 0 | task 22072 | n_gen = 150, tg = 19.17 t/s, tg_3s = 16.46 t/s 20.23.762.280 I slot print_timing: id 1 | task 21881 | n_gen = 387, tg = 18.83 t/s, tg_3s = 20.80 t/s 20.23.954.371 I slot print_timing: id 2 | task 21949 | n_gen = 324, tg = 19.22 t/s, tg_3s = 20.86 t/s 20.24.481.714 I slot print_timing: id 3 | task 22186 | n_gen = 100, tg = 20.94 t/s, tg_3s = 21.15 t/s 20.24.527.554 I slot print_timing: id 0 | task 22072 | n_gen = 213, tg = 19.64 t/s, tg_3s = 20.86 t/s 20.26.780.759 I slot print_timing: id 1 | task 21881 | n_gen = 450, tg = 19.09 t/s, tg_3s = 20.87 t/s 20.26.973.749 I slot print_timing: id 2 | task 21949 | n_gen = 387, tg = 19.47 t/s, tg_3s = 20.87 t/s 20.27.500.906 I slot print_timing: id 3 | task 22186 | n_gen = 163, tg = 20.91 t/s, tg_3s = 20.87 t/s 20.27.546.792 I slot print_timing: id 0 | task 22072 | n_gen = 276, tg = 19.91 t/s, tg_3s = 20.87 t/s 20.27.884.804 I slot print_timing: id 2 | task 21949 | prompt eval time = 777.90 ms / 458 tokens ( 1.70 ms per token, 588.76 tokens per second) 20.27.884.809 I slot print_timing: id 2 | task 21949 | eval time = 20737.05 ms / 406 tokens ( 51.20 ms per token, 19.53 tokens per second) 20.27.884.810 I slot print_timing: id 2 | task 21949 | total time = 21514.95 ms / 864 tokens 20.27.884.811 I slot print_timing: id 2 | task 21949 | graphs reused = 21368 20.27.884.812 I slot print_timing: id 2 | task 21949 | graph reallocs = 0 / 0 (same size) / (changed size) 20.27.884.932 I slot release: id 2 | task 21949 | stop processing: n_tokens = 1539, truncated = 0 20.27.934.222 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.694 20.27.934.260 I slot launch_slot_: id 2 | task 22360 | processing task, is_child = 0 20.29.790.422 I slot print_timing: id 1 | task 21881 | n_gen = 498, tg = 18.73 t/s, tg_3s = 15.95 t/s 20.30.536.194 I slot print_timing: id 3 | task 22186 | n_gen = 212, tg = 19.57 t/s, tg_3s = 16.14 t/s 20.30.581.565 I slot print_timing: id 0 | task 22072 | n_gen = 325, tg = 19.23 t/s, tg_3s = 16.15 t/s 20.32.791.173 I slot print_timing: id 1 | task 21881 | n_gen = 561, tg = 18.96 t/s, tg_3s = 20.99 t/s 20.33.462.479 I slot print_timing: id 2 | task 22360 | n_gen = 100, tg = 21.07 t/s, tg_3s = 21.28 t/s 20.33.559.297 I slot print_timing: id 3 | task 22186 | n_gen = 275, tg = 19.85 t/s, tg_3s = 20.84 t/s 20.33.605.284 I slot print_timing: id 0 | task 22072 | n_gen = 388, tg = 19.48 t/s, tg_3s = 20.84 t/s 20.35.285.514 I slot print_timing: id 1 | task 21881 | prompt eval time = 813.80 ms / 492 tokens ( 1.65 ms per token, 604.57 tokens per second) 20.35.285.521 I slot print_timing: id 1 | task 21881 | eval time = 32024.57 ms / 613 tokens ( 52.33 ms per token, 19.11 tokens per second) 20.35.285.522 I slot print_timing: id 1 | task 21881 | total time = 32838.37 ms / 1105 tokens 20.35.285.523 I slot print_timing: id 1 | task 21881 | graphs reused = 21504 20.35.285.524 I slot print_timing: id 1 | task 21881 | graph reallocs = 0 / 0 (same size) / (changed size) 20.35.285.634 I slot release: id 1 | task 21881 | stop processing: n_tokens = 1777, truncated = 0 20.35.334.917 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.601 20.35.334.964 I slot launch_slot_: id 1 | task 22501 | processing task, is_child = 0 20.36.503.003 I slot print_timing: id 2 | task 22360 | n_gen = 149, tg = 19.12 t/s, tg_3s = 16.12 t/s 20.36.595.808 I slot print_timing: id 3 | task 22186 | n_gen = 324, tg = 19.18 t/s, tg_3s = 16.14 t/s 20.36.641.256 I slot print_timing: id 0 | task 22072 | n_gen = 437, tg = 19.03 t/s, tg_3s = 16.14 t/s 20.39.503.104 I slot print_timing: id 2 | task 22360 | n_gen = 212, tg = 19.65 t/s, tg_3s = 21.00 t/s 20.39.599.090 I slot print_timing: id 3 | task 22186 | n_gen = 387, tg = 19.45 t/s, tg_3s = 20.98 t/s 20.39.645.191 I slot print_timing: id 0 | task 22072 | n_gen = 500, tg = 19.26 t/s, tg_3s = 20.97 t/s 20.40.841.274 I slot print_timing: id 1 | task 22501 | n_gen = 100, tg = 21.01 t/s, tg_3s = 21.22 t/s 20.42.519.108 I slot print_timing: id 2 | task 22360 | n_gen = 275, tg = 19.92 t/s, tg_3s = 20.89 t/s 20.42.615.346 I slot print_timing: id 3 | task 22186 | n_gen = 450, tg = 19.64 t/s, tg_3s = 20.89 t/s 20.42.661.511 I slot print_timing: id 0 | task 22072 | n_gen = 563, tg = 19.43 t/s, tg_3s = 20.89 t/s 20.43.867.698 I slot print_timing: id 1 | task 22501 | n_gen = 163, tg = 20.93 t/s, tg_3s = 20.82 t/s 20.45.548.682 I slot print_timing: id 2 | task 22360 | n_gen = 338, tg = 20.08 t/s, tg_3s = 20.79 t/s 20.45.645.287 I slot print_timing: id 3 | task 22186 | n_gen = 513, tg = 19.78 t/s, tg_3s = 20.79 t/s 20.45.691.172 I slot print_timing: id 0 | task 22072 | n_gen = 626, tg = 19.56 t/s, tg_3s = 20.79 t/s 20.46.891.938 I slot print_timing: id 1 | task 22501 | n_gen = 226, tg = 20.91 t/s, tg_3s = 20.83 t/s 20.48.574.002 I slot print_timing: id 2 | task 22360 | n_gen = 401, tg = 20.19 t/s, tg_3s = 20.82 t/s 20.48.670.823 I slot print_timing: id 3 | task 22186 | n_gen = 576, tg = 19.88 t/s, tg_3s = 20.82 t/s 20.48.717.064 I slot print_timing: id 0 | task 22072 | n_gen = 689, tg = 19.67 t/s, tg_3s = 20.82 t/s 20.49.922.081 I slot print_timing: id 1 | task 22501 | n_gen = 289, tg = 20.88 t/s, tg_3s = 20.79 t/s 20.51.607.435 I slot print_timing: id 2 | task 22360 | n_gen = 464, tg = 20.27 t/s, tg_3s = 20.77 t/s 20.51.703.750 I slot print_timing: id 3 | task 22186 | n_gen = 639, tg = 19.97 t/s, tg_3s = 20.77 t/s 20.51.749.506 I slot print_timing: id 0 | task 22072 | n_gen = 752, tg = 19.76 t/s, tg_3s = 20.78 t/s 20.52.953.952 I slot print_timing: id 1 | task 22501 | n_gen = 352, tg = 20.86 t/s, tg_3s = 20.78 t/s 20.54.639.609 I slot print_timing: id 2 | task 22360 | n_gen = 527, tg = 20.33 t/s, tg_3s = 20.78 t/s 20.54.736.855 I slot print_timing: id 3 | task 22186 | n_gen = 702, tg = 20.04 t/s, tg_3s = 20.77 t/s 20.54.783.177 I slot print_timing: id 0 | task 22072 | n_gen = 815, tg = 19.83 t/s, tg_3s = 20.77 t/s 20.55.992.047 I slot print_timing: id 1 | task 22501 | n_gen = 415, tg = 20.84 t/s, tg_3s = 20.74 t/s 20.57.681.467 I slot print_timing: id 2 | task 22360 | n_gen = 590, tg = 20.37 t/s, tg_3s = 20.71 t/s 20.57.778.567 I slot print_timing: id 3 | task 22186 | n_gen = 765, tg = 20.09 t/s, tg_3s = 20.71 t/s 20.57.824.979 I slot print_timing: id 0 | task 22072 | n_gen = 878, tg = 19.89 t/s, tg_3s = 20.71 t/s 20.59.030.411 I slot print_timing: id 1 | task 22501 | n_gen = 478, tg = 20.83 t/s, tg_3s = 20.73 t/s 20.59.702.989 I slot print_timing: id 1 | task 22501 | prompt eval time = 794.24 ms / 479 tokens ( 1.66 ms per token, 603.09 tokens per second) 20.59.702.994 I slot print_timing: id 1 | task 22501 | eval time = 23573.77 ms / 492 tokens ( 48.01 ms per token, 20.83 tokens per second) 20.59.702.996 I slot print_timing: id 1 | task 22501 | total time = 24368.01 ms / 971 tokens 20.59.702.997 I slot print_timing: id 1 | task 22501 | graphs reused = 21992 20.59.702.998 I slot print_timing: id 1 | task 22501 | graph reallocs = 0 / 0 (same size) / (changed size) 20.59.703.126 I slot release: id 1 | task 22501 | stop processing: n_tokens = 1643, truncated = 0 20.59.752.371 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.650 20.59.752.417 I slot launch_slot_: id 1 | task 22996 | processing task, is_child = 0 21.00.720.538 I slot print_timing: id 2 | task 22360 | n_gen = 638, tg = 19.93 t/s, tg_3s = 15.79 t/s 21.00.813.355 I slot print_timing: id 3 | task 22186 | n_gen = 813, tg = 19.78 t/s, tg_3s = 15.82 t/s 21.00.859.062 I slot print_timing: id 0 | task 22072 | n_gen = 926, tg = 19.63 t/s, tg_3s = 15.82 t/s 21.03.759.624 I slot print_timing: id 2 | task 22360 | n_gen = 701, tg = 20.00 t/s, tg_3s = 20.73 t/s 21.03.856.272 I slot print_timing: id 3 | task 22186 | n_gen = 876, tg = 19.84 t/s, tg_3s = 20.70 t/s 21.03.902.710 I slot print_timing: id 0 | task 22072 | n_gen = 989, tg = 19.69 t/s, tg_3s = 20.70 t/s 21.05.349.467 I slot print_timing: id 1 | task 22996 | n_gen = 100, tg = 20.75 t/s, tg_3s = 20.96 t/s 21.05.589.930 I slot print_timing: id 0 | task 22072 | prompt eval time = 868.60 ms / 518 tokens ( 1.68 ms per token, 596.36 tokens per second) 21.05.589.938 I slot print_timing: id 0 | task 22072 | eval time = 51855.33 ms / 1024 tokens ( 50.69 ms per token, 19.73 tokens per second) 21.05.589.939 I slot print_timing: id 0 | task 22072 | total time = 52723.93 ms / 1542 tokens 21.05.589.939 I slot print_timing: id 0 | task 22072 | graphs reused = 22095 21.05.589.940 I slot print_timing: id 0 | task 22072 | graph reallocs = 0 / 0 (same size) / (changed size) 21.05.590.055 I slot release: id 0 | task 22072 | stop processing: n_tokens = 2237, truncated = 0 21.05.632.520 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.477 21.05.643.374 I slot launch_slot_: id 0 | task 23104 | processing task, is_child = 0 21.06.767.584 I slot print_timing: id 2 | task 22360 | n_gen = 750, tg = 19.71 t/s, tg_3s = 16.29 t/s 21.06.861.836 I slot print_timing: id 3 | task 22186 | n_gen = 925, tg = 19.61 t/s, tg_3s = 16.30 t/s 21.08.357.760 I slot print_timing: id 1 | task 22996 | n_gen = 149, tg = 19.03 t/s, tg_3s = 16.29 t/s 21.09.807.152 I slot print_timing: id 2 | task 22360 | n_gen = 813, tg = 19.78 t/s, tg_3s = 20.73 t/s 21.09.903.704 I slot print_timing: id 3 | task 22186 | n_gen = 988, tg = 19.68 t/s, tg_3s = 20.71 t/s 21.10.674.373 I slot print_timing: id 3 | task 22186 | prompt eval time = 763.59 ms / 456 tokens ( 1.67 ms per token, 597.18 tokens per second) 21.10.674.382 I slot print_timing: id 3 | task 22186 | eval time = 50919.87 ms / 1004 tokens ( 50.77 ms per token, 19.70 tokens per second) 21.10.674.383 I slot print_timing: id 3 | task 22186 | total time = 51683.46 ms / 1460 tokens 21.10.674.383 I slot print_timing: id 3 | task 22186 | graphs reused = 22184 21.10.674.384 I slot print_timing: id 3 | task 22186 | graph reallocs = 0 / 0 (same size) / (changed size) 21.10.674.519 I slot release: id 3 | task 22186 | stop processing: n_tokens = 2154, truncated = 0 21.10.715.359 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.496 21.10.717.934 I slot launch_slot_: id 3 | task 23197 | processing task, is_child = 0 21.11.413.823 I slot print_timing: id 1 | task 22996 | n_gen = 199, tg = 18.27 t/s, tg_3s = 16.36 t/s 21.11.822.084 I slot print_timing: id 0 | task 23104 | n_gen = 100, tg = 18.23 t/s, tg_3s = 18.41 t/s 21.12.847.669 I slot print_timing: id 2 | task 22360 | n_gen = 863, tg = 19.55 t/s, tg_3s = 16.44 t/s 21.14.434.595 I slot print_timing: id 1 | task 22996 | n_gen = 263, tg = 18.91 t/s, tg_3s = 21.19 t/s 21.14.854.172 I slot print_timing: id 0 | task 23104 | n_gen = 165, tg = 19.38 t/s, tg_3s = 21.44 t/s 21.15.864.344 I slot print_timing: id 2 | task 22360 | n_gen = 927, tg = 19.66 t/s, tg_3s = 21.22 t/s 21.16.154.120 I slot print_timing: id 3 | task 23197 | n_gen = 100, tg = 21.25 t/s, tg_3s = 21.47 t/s 21.17.446.821 I slot print_timing: id 1 | task 22996 | n_gen = 326, tg = 19.27 t/s, tg_3s = 20.91 t/s 21.17.876.978 I slot print_timing: id 0 | task 23104 | n_gen = 228, tg = 19.76 t/s, tg_3s = 20.84 t/s 21.18.884.241 I slot print_timing: id 2 | task 22360 | n_gen = 990, tg = 19.73 t/s, tg_3s = 20.86 t/s 21.19.172.412 I slot print_timing: id 3 | task 23197 | n_gen = 163, tg = 21.10 t/s, tg_3s = 20.87 t/s 21.20.469.010 I slot print_timing: id 1 | task 22996 | n_gen = 389, tg = 19.51 t/s, tg_3s = 20.85 t/s 21.20.518.107 I slot print_timing: id 2 | task 22360 | prompt eval time = 829.88 ms / 516 tokens ( 1.61 ms per token, 621.78 tokens per second) 21.20.518.115 I slot print_timing: id 2 | task 22360 | eval time = 51753.95 ms / 1024 tokens ( 50.59 ms per token, 19.77 tokens per second) 21.20.518.116 I slot print_timing: id 2 | task 22360 | total time = 52583.84 ms / 1540 tokens 21.20.518.117 I slot print_timing: id 2 | task 22360 | graphs reused = 22372 21.20.518.118 I slot print_timing: id 2 | task 22360 | graph reallocs = 0 / 0 (same size) / (changed size) 21.20.518.257 I slot release: id 2 | task 22360 | stop processing: n_tokens = 2215, truncated = 0 21.20.567.081 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.482 21.20.580.474 I slot launch_slot_: id 2 | task 23391 | processing task, is_child = 0 21.21.271.010 I slot print_timing: id 0 | task 23104 | n_gen = 285, tg = 19.09 t/s, tg_3s = 16.79 t/s 21.22.198.636 I slot print_timing: id 3 | task 23197 | n_gen = 212, tg = 19.71 t/s, tg_3s = 16.19 t/s 21.23.491.889 I slot print_timing: id 1 | task 22996 | n_gen = 438, tg = 19.07 t/s, tg_3s = 16.21 t/s 21.24.305.595 I slot print_timing: id 0 | task 23104 | n_gen = 348, tg = 19.37 t/s, tg_3s = 20.76 t/s 21.25.215.217 I slot print_timing: id 3 | task 23197 | n_gen = 275, tg = 19.97 t/s, tg_3s = 20.88 t/s 21.26.074.942 I slot print_timing: id 2 | task 23391 | n_gen = 100, tg = 21.00 t/s, tg_3s = 21.21 t/s 21.26.505.469 I slot print_timing: id 1 | task 22996 | n_gen = 501, tg = 19.29 t/s, tg_3s = 20.91 t/s 21.27.318.350 I slot print_timing: id 0 | task 23104 | n_gen = 411, tg = 19.59 t/s, tg_3s = 20.91 t/s 21.28.232.673 I slot print_timing: id 3 | task 23197 | n_gen = 338, tg = 20.14 t/s, tg_3s = 20.88 t/s 21.29.095.039 I slot print_timing: id 2 | task 23391 | n_gen = 163, tg = 20.94 t/s, tg_3s = 20.86 t/s 21.29.525.109 I slot print_timing: id 1 | task 22996 | n_gen = 564, tg = 19.45 t/s, tg_3s = 20.86 t/s 21.30.339.034 I slot print_timing: id 0 | task 23104 | n_gen = 474, tg = 19.75 t/s, tg_3s = 20.86 t/s 21.31.255.951 I slot print_timing: id 3 | task 23197 | n_gen = 401, tg = 20.24 t/s, tg_3s = 20.84 t/s 21.32.126.108 I slot print_timing: id 2 | task 23391 | n_gen = 226, tg = 20.90 t/s, tg_3s = 20.78 t/s 21.32.557.714 I slot print_timing: id 1 | task 22996 | n_gen = 627, tg = 19.58 t/s, tg_3s = 20.77 t/s 21.33.374.199 I slot print_timing: id 0 | task 23104 | n_gen = 537, tg = 19.86 t/s, tg_3s = 20.76 t/s 21.34.290.744 I slot print_timing: id 3 | task 23197 | n_gen = 464, tg = 20.31 t/s, tg_3s = 20.76 t/s 21.35.153.129 I slot print_timing: id 2 | task 23391 | n_gen = 289, tg = 20.88 t/s, tg_3s = 20.81 t/s 21.35.491.012 I slot print_timing: id 3 | task 23197 | prompt eval time = 778.12 ms / 479 tokens ( 1.62 ms per token, 615.59 tokens per second) 21.35.491.020 I slot print_timing: id 3 | task 23197 | eval time = 23994.94 ms / 489 tokens ( 49.17 ms per token, 20.34 tokens per second) 21.35.491.021 I slot print_timing: id 3 | task 23197 | total time = 24773.06 ms / 968 tokens 21.35.491.022 I slot print_timing: id 3 | task 23197 | graphs reused = 22665 21.35.491.023 I slot print_timing: id 3 | task 23197 | graph reallocs = 0 / 0 (same size) / (changed size) 21.35.491.158 I slot release: id 3 | task 23197 | stop processing: n_tokens = 1662, truncated = 0 21.35.532.156 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 21.35.532.195 I slot launch_slot_: id 3 | task 23690 | processing task, is_child = 0 21.36.192.663 I slot print_timing: id 1 | task 22996 | n_gen = 690, tg = 19.35 t/s, tg_3s = 17.33 t/s 21.36.415.821 I slot print_timing: id 0 | task 23104 | n_gen = 587, tg = 19.52 t/s, tg_3s = 16.44 t/s 21.38.181.551 I slot print_timing: id 2 | task 23391 | n_gen = 339, tg = 20.09 t/s, tg_3s = 16.51 t/s 21.39.237.735 I slot print_timing: id 1 | task 22996 | n_gen = 753, tg = 19.45 t/s, tg_3s = 20.69 t/s 21.39.429.401 I slot print_timing: id 0 | task 23104 | n_gen = 650, tg = 19.64 t/s, tg_3s = 20.91 t/s 21.41.010.972 I slot print_timing: id 3 | task 23690 | n_gen = 100, tg = 20.90 t/s, tg_3s = 21.11 t/s 21.41.201.806 I slot print_timing: id 2 | task 23391 | n_gen = 402, tg = 20.21 t/s, tg_3s = 20.86 t/s 21.42.256.317 I slot print_timing: id 1 | task 22996 | n_gen = 816, tg = 19.55 t/s, tg_3s = 20.87 t/s 21.42.447.655 I slot print_timing: id 0 | task 23104 | n_gen = 713, tg = 19.75 t/s, tg_3s = 20.87 t/s 21.44.032.197 I slot print_timing: id 3 | task 23690 | n_gen = 163, tg = 20.88 t/s, tg_3s = 20.85 t/s 21.44.222.866 I slot print_timing: id 2 | task 23391 | n_gen = 465, tg = 20.29 t/s, tg_3s = 20.85 t/s 21.45.280.162 I slot print_timing: id 1 | task 22996 | n_gen = 879, tg = 19.64 t/s, tg_3s = 20.83 t/s 21.45.471.715 I slot print_timing: id 0 | task 23104 | n_gen = 776, tg = 19.83 t/s, tg_3s = 20.83 t/s 21.47.066.542 I slot print_timing: id 3 | task 23690 | n_gen = 226, tg = 20.85 t/s, tg_3s = 20.76 t/s 21.47.258.121 I slot print_timing: id 2 | task 23391 | n_gen = 528, tg = 20.35 t/s, tg_3s = 20.76 t/s 21.48.313.656 I slot print_timing: id 1 | task 22996 | n_gen = 942, tg = 19.71 t/s, tg_3s = 20.77 t/s 21.48.505.846 I slot print_timing: id 0 | task 23104 | n_gen = 839, tg = 19.90 t/s, tg_3s = 20.76 t/s 21.50.097.579 I slot print_timing: id 3 | task 23690 | n_gen = 289, tg = 20.84 t/s, tg_3s = 20.78 t/s 21.50.289.550 I slot print_timing: id 2 | task 23391 | n_gen = 591, tg = 20.39 t/s, tg_3s = 20.78 t/s 21.51.351.781 I slot print_timing: id 1 | task 22996 | n_gen = 1005, tg = 19.77 t/s, tg_3s = 20.74 t/s 21.51.544.799 I slot print_timing: id 0 | task 23104 | n_gen = 902, tg = 19.95 t/s, tg_3s = 20.73 t/s 21.52.269.438 I slot print_timing: id 1 | task 22996 | prompt eval time = 826.36 ms / 509 tokens ( 1.62 ms per token, 615.96 tokens per second) 21.52.269.443 I slot print_timing: id 1 | task 22996 | eval time = 51690.65 ms / 1024 tokens ( 50.53 ms per token, 19.79 tokens per second) 21.52.269.444 I slot print_timing: id 1 | task 22996 | total time = 52517.01 ms / 1533 tokens 21.52.269.445 I slot print_timing: id 1 | task 22996 | graphs reused = 22996 21.52.269.446 I slot print_timing: id 1 | task 22996 | graph reallocs = 0 / 0 (same size) / (changed size) 21.52.269.572 I slot release: id 1 | task 22996 | stop processing: n_tokens = 2205, truncated = 0 21.52.318.945 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.484 21.52.330.880 I slot launch_slot_: id 1 | task 24027 | processing task, is_child = 0 21.53.127.070 I slot print_timing: id 3 | task 23690 | n_gen = 337, tg = 19.94 t/s, tg_3s = 15.84 t/s 21.53.315.910 I slot print_timing: id 2 | task 23391 | n_gen = 639, tg = 19.96 t/s, tg_3s = 15.86 t/s 21.54.567.225 I slot print_timing: id 0 | task 23104 | n_gen = 950, tg = 19.70 t/s, tg_3s = 15.88 t/s 21.55.288.493 I slot print_timing: id 3 | task 23690 | prompt eval time = 742.64 ms / 444 tokens ( 1.67 ms per token, 597.87 tokens per second) 21.55.288.501 I slot print_timing: id 3 | task 23690 | eval time = 19013.65 ms / 382 tokens ( 49.90 ms per token, 20.04 tokens per second) 21.55.288.502 I slot print_timing: id 3 | task 23690 | total time = 19756.29 ms / 826 tokens 21.55.288.503 I slot print_timing: id 3 | task 23690 | graphs reused = 23040 21.55.288.504 I slot print_timing: id 3 | task 23690 | graph reallocs = 0 / 0 (same size) / (changed size) 21.55.288.632 I slot release: id 3 | task 23690 | stop processing: n_tokens = 1520, truncated = 0 21.55.329.415 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.703 21.55.329.454 I slot launch_slot_: id 3 | task 24076 | processing task, is_child = 0 21.56.357.707 I slot print_timing: id 2 | task 23391 | n_gen = 689, tg = 19.66 t/s, tg_3s = 16.44 t/s 21.56.918.876 I slot print_timing: id 2 | task 23391 | prompt eval time = 779.22 ms / 464 tokens ( 1.68 ms per token, 595.47 tokens per second) 21.56.918.882 I slot print_timing: id 2 | task 23391 | eval time = 35559.17 ms / 701 tokens ( 50.80 ms per token, 19.69 tokens per second) 21.56.918.882 I slot print_timing: id 2 | task 23391 | total time = 36338.39 ms / 1165 tokens 21.56.918.882 I slot print_timing: id 2 | task 23391 | graphs reused = 23057 21.56.918.883 I slot print_timing: id 2 | task 23391 | graph reallocs = 0 / 0 (same size) / (changed size) 21.56.918.940 I slot release: id 2 | task 23391 | stop processing: n_tokens = 1859, truncated = 0 21.56.964.794 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.575 21.56.964.821 I slot launch_slot_: id 2 | task 24098 | processing task, is_child = 0 21.57.648.323 I slot print_timing: id 0 | task 23104 | n_gen = 988, tg = 19.26 t/s, tg_3s = 12.33 t/s 21.59.141.298 I slot print_timing: id 1 | task 24027 | n_gen = 100, tg = 16.46 t/s, tg_3s = 16.63 t/s 21.59.376.256 I slot print_timing: id 0 | task 23104 | prompt eval time = 747.00 ms / 454 tokens ( 1.65 ms per token, 607.76 tokens per second) 21.59.376.266 I slot print_timing: id 0 | task 23104 | eval time = 52985.86 ms / 1024 tokens ( 51.79 ms per token, 19.31 tokens per second) 21.59.376.268 I slot print_timing: id 0 | task 23104 | total time = 53732.86 ms / 1478 tokens 21.59.376.270 I slot print_timing: id 0 | task 23104 | graphs reused = 23091 21.59.376.272 I slot print_timing: id 0 | task 23104 | graph reallocs = 0 / 0 (same size) / (changed size) 21.59.376.495 I slot release: id 0 | task 23104 | stop processing: n_tokens = 2175, truncated = 0 21.59.422.519 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.491 21.59.425.803 I slot launch_slot_: id 0 | task 24137 | processing task, is_child = 0 22.02.112.070 I slot print_timing: id 3 | task 24076 | n_gen = 100, tg = 16.40 t/s, tg_3s = 16.57 t/s 22.02.158.373 I slot print_timing: id 1 | task 24027 | n_gen = 149, tg = 16.39 t/s, tg_3s = 16.24 t/s 22.03.117.462 I slot print_timing: id 2 | task 24098 | n_gen = 100, tg = 18.40 t/s, tg_3s = 18.59 t/s 22.04.928.494 I slot print_timing: id 0 | task 24137 | n_gen = 100, tg = 21.07 t/s, tg_3s = 21.28 t/s 22.05.121.763 I slot print_timing: id 3 | task 24076 | n_gen = 163, tg = 17.91 t/s, tg_3s = 20.93 t/s 22.05.168.533 I slot print_timing: id 1 | task 24027 | n_gen = 212, tg = 17.52 t/s, tg_3s = 20.93 t/s 22.06.124.750 I slot print_timing: id 2 | task 24098 | n_gen = 163, tg = 19.31 t/s, tg_3s = 20.95 t/s 22.07.946.620 I slot print_timing: id 0 | task 24137 | n_gen = 163, tg = 20.99 t/s, tg_3s = 20.87 t/s 22.08.141.292 I slot print_timing: id 3 | task 24076 | n_gen = 226, tg = 18.65 t/s, tg_3s = 20.86 t/s 22.08.188.227 I slot print_timing: id 1 | task 24027 | n_gen = 275, tg = 18.19 t/s, tg_3s = 20.86 t/s 22.09.147.590 I slot print_timing: id 2 | task 24098 | n_gen = 226, tg = 19.72 t/s, tg_3s = 20.84 t/s 22.10.964.041 I slot print_timing: id 0 | task 24137 | n_gen = 226, tg = 20.96 t/s, tg_3s = 20.88 t/s 22.11.157.208 I slot print_timing: id 3 | task 24076 | n_gen = 289, tg = 19.10 t/s, tg_3s = 20.89 t/s 22.11.203.569 I slot print_timing: id 1 | task 24027 | n_gen = 338, tg = 18.64 t/s, tg_3s = 20.89 t/s 22.12.160.195 I slot print_timing: id 2 | task 24098 | n_gen = 289, tg = 19.97 t/s, tg_3s = 20.91 t/s 22.13.978.433 I slot print_timing: id 0 | task 24137 | n_gen = 289, tg = 20.95 t/s, tg_3s = 20.90 t/s 22.14.172.404 I slot print_timing: id 3 | task 24076 | n_gen = 352, tg = 19.40 t/s, tg_3s = 20.89 t/s 22.14.219.126 I slot print_timing: id 1 | task 24027 | n_gen = 401, tg = 18.96 t/s, tg_3s = 20.89 t/s 22.15.178.851 I slot print_timing: id 2 | task 24098 | n_gen = 352, tg = 20.12 t/s, tg_3s = 20.87 t/s 22.16.996.183 I slot print_timing: id 0 | task 24137 | n_gen = 352, tg = 20.93 t/s, tg_3s = 20.88 t/s 22.17.189.931 I slot print_timing: id 3 | task 24076 | n_gen = 415, tg = 19.61 t/s, tg_3s = 20.88 t/s 22.17.236.484 I slot print_timing: id 1 | task 24027 | n_gen = 464, tg = 19.20 t/s, tg_3s = 20.88 t/s 22.18.191.437 I slot print_timing: id 2 | task 24098 | n_gen = 415, tg = 20.24 t/s, tg_3s = 20.91 t/s 22.20.008.802 I slot print_timing: id 0 | task 24137 | n_gen = 415, tg = 20.93 t/s, tg_3s = 20.91 t/s 22.20.203.363 I slot print_timing: id 3 | task 24076 | n_gen = 478, tg = 19.77 t/s, tg_3s = 20.91 t/s 22.20.250.234 I slot print_timing: id 1 | task 24027 | n_gen = 527, tg = 19.39 t/s, tg_3s = 20.90 t/s 22.21.211.729 I slot print_timing: id 2 | task 24098 | n_gen = 478, tg = 20.32 t/s, tg_3s = 20.86 t/s 22.23.043.904 I slot print_timing: id 0 | task 24137 | n_gen = 478, tg = 20.91 t/s, tg_3s = 20.76 t/s 22.23.238.823 I slot print_timing: id 3 | task 24076 | n_gen = 541, tg = 19.88 t/s, tg_3s = 20.75 t/s 22.23.285.847 I slot print_timing: id 1 | task 24027 | n_gen = 590, tg = 19.53 t/s, tg_3s = 20.75 t/s 22.24.248.399 I slot print_timing: id 2 | task 24098 | n_gen = 541, tg = 20.37 t/s, tg_3s = 20.75 t/s 22.26.079.100 I slot print_timing: id 0 | task 24137 | n_gen = 541, tg = 20.89 t/s, tg_3s = 20.76 t/s 22.26.274.654 I slot print_timing: id 3 | task 24076 | n_gen = 604, tg = 19.97 t/s, tg_3s = 20.75 t/s 22.26.321.488 I slot print_timing: id 1 | task 24027 | n_gen = 653, tg = 19.64 t/s, tg_3s = 20.75 t/s 22.27.287.046 I slot print_timing: id 2 | task 24098 | n_gen = 604, tg = 20.41 t/s, tg_3s = 20.73 t/s 22.29.118.235 I slot print_timing: id 0 | task 24137 | n_gen = 604, tg = 20.87 t/s, tg_3s = 20.73 t/s 22.29.312.651 I slot print_timing: id 3 | task 24076 | n_gen = 667, tg = 20.04 t/s, tg_3s = 20.74 t/s 22.29.359.268 I slot print_timing: id 1 | task 24027 | n_gen = 716, tg = 19.73 t/s, tg_3s = 20.74 t/s 22.30.322.923 I slot print_timing: id 2 | task 24098 | n_gen = 667, tg = 20.44 t/s, tg_3s = 20.75 t/s 22.32.148.469 I slot print_timing: id 0 | task 24137 | n_gen = 667, tg = 20.87 t/s, tg_3s = 20.79 t/s 22.32.342.430 I slot print_timing: id 3 | task 24076 | n_gen = 730, tg = 20.10 t/s, tg_3s = 20.79 t/s 22.32.389.189 I slot print_timing: id 1 | task 24027 | n_gen = 779, tg = 19.82 t/s, tg_3s = 20.79 t/s 22.33.351.723 I slot print_timing: id 2 | task 24098 | n_gen = 730, tg = 20.47 t/s, tg_3s = 20.80 t/s 22.33.544.976 I slot print_timing: id 2 | task 24098 | prompt eval time = 772.52 ms / 455 tokens ( 1.70 ms per token, 588.98 tokens per second) 22.33.544.984 I slot print_timing: id 2 | task 24098 | eval time = 35807.62 ms / 734 tokens ( 48.85 ms per token, 20.47 tokens per second) 22.33.544.987 I slot print_timing: id 2 | task 24098 | total time = 36580.14 ms / 1189 tokens 22.33.544.988 I slot print_timing: id 2 | task 24098 | graphs reused = 23783 22.33.544.989 I slot print_timing: id 2 | task 24098 | graph reallocs = 0 / 0 (same size) / (changed size) 22.33.545.128 I slot release: id 2 | task 24098 | stop processing: n_tokens = 1883, truncated = 0 22.33.594.388 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.567 22.33.594.431 I slot launch_slot_: id 2 | task 24836 | processing task, is_child = 0 22.35.167.800 I slot print_timing: id 0 | task 24137 | n_gen = 716, tg = 20.46 t/s, tg_3s = 16.23 t/s 22.35.355.895 I slot print_timing: id 3 | task 24076 | n_gen = 779, tg = 19.81 t/s, tg_3s = 16.26 t/s 22.35.401.948 I slot print_timing: id 1 | task 24027 | n_gen = 828, tg = 19.56 t/s, tg_3s = 16.26 t/s 22.38.199.510 I slot print_timing: id 0 | task 24137 | n_gen = 779, tg = 20.49 t/s, tg_3s = 20.78 t/s 22.38.393.849 I slot print_timing: id 3 | task 24076 | n_gen = 842, tg = 19.87 t/s, tg_3s = 20.74 t/s 22.38.440.870 I slot print_timing: id 1 | task 24027 | n_gen = 891, tg = 19.64 t/s, tg_3s = 20.73 t/s 22.39.117.098 I slot print_timing: id 2 | task 24836 | n_gen = 100, tg = 20.87 t/s, tg_3s = 21.08 t/s 22.41.235.466 I slot print_timing: id 0 | task 24137 | n_gen = 842, tg = 20.51 t/s, tg_3s = 20.75 t/s 22.41.430.478 I slot print_timing: id 3 | task 24076 | n_gen = 905, tg = 19.93 t/s, tg_3s = 20.75 t/s 22.41.477.509 I slot print_timing: id 1 | task 24027 | n_gen = 954, tg = 19.71 t/s, tg_3s = 20.75 t/s 22.42.154.672 I slot print_timing: id 2 | task 24836 | n_gen = 163, tg = 20.82 t/s, tg_3s = 20.74 t/s 22.44.273.888 I slot print_timing: id 0 | task 24137 | n_gen = 905, tg = 20.52 t/s, tg_3s = 20.73 t/s 22.44.469.379 I slot print_timing: id 3 | task 24076 | n_gen = 968, tg = 19.98 t/s, tg_3s = 20.73 t/s 22.44.516.425 I slot print_timing: id 1 | task 24027 | n_gen = 1017, tg = 19.77 t/s, tg_3s = 20.73 t/s 22.44.852.689 I slot print_timing: id 1 | task 24027 | prompt eval time = 795.63 ms / 481 tokens ( 1.65 ms per token, 604.55 tokens per second) 22.44.852.694 I slot print_timing: id 1 | task 24027 | eval time = 51726.17 ms / 1024 tokens ( 50.56 ms per token, 19.78 tokens per second) 22.44.852.695 I slot print_timing: id 1 | task 24027 | total time = 52521.80 ms / 1505 tokens 22.44.852.696 I slot print_timing: id 1 | task 24027 | graphs reused = 23999 22.44.852.697 I slot print_timing: id 1 | task 24027 | graph reallocs = 0 / 0 (same size) / (changed size) 22.44.852.834 I slot release: id 1 | task 24027 | stop processing: n_tokens = 2177, truncated = 0 22.44.902.543 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.491 22.44.915.308 I slot launch_slot_: id 1 | task 25058 | processing task, is_child = 0 22.45.641.662 I slot print_timing: id 2 | task 24836 | n_gen = 221, tg = 19.52 t/s, tg_3s = 16.63 t/s 22.47.277.940 I slot print_timing: id 0 | task 24137 | n_gen = 953, tg = 20.23 t/s, tg_3s = 15.98 t/s 22.47.465.917 I slot print_timing: id 3 | task 24076 | prompt eval time = 746.15 ms / 448 tokens ( 1.67 ms per token, 600.42 tokens per second) 22.47.465.922 I slot print_timing: id 3 | task 24076 | eval time = 51390.30 ms / 1016 tokens ( 50.63 ms per token, 19.75 tokens per second) 22.47.465.923 I slot print_timing: id 3 | task 24076 | total time = 52136.45 ms / 1464 tokens 22.47.465.923 I slot print_timing: id 3 | task 24076 | graphs reused = 24035 22.47.465.924 I slot print_timing: id 3 | task 24076 | graph reallocs = 0 / 0 (same size) / (changed size) 22.47.465.985 I slot release: id 3 | task 24076 | stop processing: n_tokens = 2158, truncated = 0 22.47.504.338 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.495 22.47.511.307 I slot launch_slot_: id 3 | task 25099 | processing task, is_child = 0 22.48.675.570 I slot print_timing: id 2 | task 24836 | n_gen = 271, tg = 18.88 t/s, tg_3s = 16.48 t/s 22.50.284.205 I slot print_timing: id 0 | task 24137 | n_gen = 1003, tg = 20.02 t/s, tg_3s = 16.63 t/s 22.51.053.712 I slot print_timing: id 1 | task 25058 | n_gen = 100, tg = 18.60 t/s, tg_3s = 18.79 t/s 22.51.293.677 I slot print_timing: id 0 | task 24137 | prompt eval time = 804.08 ms / 513 tokens ( 1.57 ms per token, 638.00 tokens per second) 22.51.293.684 I slot print_timing: id 0 | task 24137 | eval time = 51063.78 ms / 1024 tokens ( 49.92 ms per token, 20.03 tokens per second) 22.51.293.685 I slot print_timing: id 0 | task 24137 | total time = 51867.86 ms / 1537 tokens 22.51.293.686 I slot print_timing: id 0 | task 24137 | graphs reused = 24098 22.51.293.687 I slot print_timing: id 0 | task 24137 | graph reallocs = 0 / 0 (same size) / (changed size) 22.51.293.808 I slot release: id 0 | task 24137 | stop processing: n_tokens = 2234, truncated = 0 22.51.336.551 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.478 22.51.347.913 I slot launch_slot_: id 0 | task 25167 | processing task, is_child = 0 22.52.052.715 I slot print_timing: id 2 | task 24836 | n_gen = 328, tg = 18.50 t/s, tg_3s = 16.88 t/s 22.53.621.076 I slot print_timing: id 3 | task 25099 | n_gen = 100, tg = 18.44 t/s, tg_3s = 18.63 t/s 22.54.085.020 I slot print_timing: id 1 | task 25058 | n_gen = 150, tg = 17.84 t/s, tg_3s = 16.49 t/s 22.55.090.157 I slot print_timing: id 2 | task 24836 | n_gen = 392, tg = 18.87 t/s, tg_3s = 21.07 t/s 22.56.623.860 I slot print_timing: id 3 | task 25099 | n_gen = 163, tg = 19.35 t/s, tg_3s = 20.98 t/s 22.56.813.326 I slot print_timing: id 0 | task 25167 | n_gen = 100, tg = 21.15 t/s, tg_3s = 21.36 t/s 22.57.101.327 I slot print_timing: id 1 | task 25058 | n_gen = 213, tg = 18.64 t/s, tg_3s = 20.89 t/s 22.58.107.998 I slot print_timing: id 2 | task 24836 | n_gen = 455, tg = 19.13 t/s, tg_3s = 20.88 t/s 22.59.639.628 I slot print_timing: id 3 | task 25099 | n_gen = 226, tg = 19.76 t/s, tg_3s = 20.89 t/s 22.59.828.419 I slot print_timing: id 0 | task 25167 | n_gen = 163, tg = 21.05 t/s, tg_3s = 20.89 t/s 22.59.829.687 I slot print_timing: id 2 | task 24836 | prompt eval time = 779.13 ms / 460 tokens ( 1.69 ms per token, 590.40 tokens per second) 22.59.829.691 I slot print_timing: id 2 | task 24836 | eval time = 25456.12 ms / 491 tokens ( 51.95 ms per token, 19.25 tokens per second) 22.59.829.692 I slot print_timing: id 2 | task 24836 | total time = 26235.25 ms / 951 tokens 22.59.829.692 I slot print_timing: id 2 | task 24836 | graphs reused = 24259 22.59.829.693 I slot print_timing: id 2 | task 24836 | graph reallocs = 0 / 0 (same size) / (changed size) 22.59.829.809 I slot release: id 2 | task 24836 | stop processing: n_tokens = 1645, truncated = 0 22.59.878.289 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.649 22.59.878.336 I slot launch_slot_: id 2 | task 25333 | processing task, is_child = 0 23.00.546.390 I slot print_timing: id 1 | task 25058 | n_gen = 272, tg = 18.29 t/s, tg_3s = 17.13 t/s 23.02.214.300 I slot print_timing: id 3 | task 25099 | prompt eval time = 741.98 ms / 443 tokens ( 1.67 ms per token, 597.05 tokens per second) 23.02.214.302 I slot print_timing: id 3 | task 25099 | eval time = 13961.00 ms / 267 tokens ( 52.48 ms per token, 19.05 tokens per second) 23.02.214.303 I slot print_timing: id 3 | task 25099 | total time = 14702.98 ms / 710 tokens 23.02.214.303 I slot print_timing: id 3 | task 25099 | graphs reused = 24292 23.02.214.304 I slot print_timing: id 3 | task 25099 | graph reallocs = 0 / 0 (same size) / (changed size) 23.02.214.371 I slot release: id 3 | task 25099 | stop processing: n_tokens = 1404, truncated = 0 23.02.862.186 I slot print_timing: id 0 | task 25167 | n_gen = 217, tg = 20.13 t/s, tg_3s = 17.80 t/s 23.03.576.546 I slot print_timing: id 1 | task 25058 | n_gen = 343, tg = 19.16 t/s, tg_3s = 23.43 t/s 23.04.668.565 I slot print_timing: id 2 | task 25333 | n_gen = 100, tg = 24.55 t/s, tg_3s = 24.79 t/s 23.05.871.615 I slot print_timing: id 0 | task 25167 | n_gen = 297, tg = 21.54 t/s, tg_3s = 26.58 t/s 23.06.586.890 I slot print_timing: id 1 | task 25058 | n_gen = 423, tg = 20.23 t/s, tg_3s = 26.58 t/s 23.07.679.624 I slot print_timing: id 2 | task 25333 | n_gen = 180, tg = 25.41 t/s, tg_3s = 26.57 t/s 23.07.980.459 I slot print_timing: id 1 | task 25058 | prompt eval time = 815.62 ms / 495 tokens ( 1.65 ms per token, 606.90 tokens per second) 23.07.980.464 I slot print_timing: id 1 | task 25058 | eval time = 22249.51 ms / 460 tokens ( 48.47 ms per token, 20.63 tokens per second) 23.07.980.466 I slot print_timing: id 1 | task 25058 | total time = 23065.14 ms / 955 tokens 23.07.980.467 I slot print_timing: id 1 | task 25058 | graphs reused = 24443 23.07.980.468 I slot print_timing: id 1 | task 25058 | graph reallocs = 0 / 0 (same size) / (changed size) 23.07.980.595 I slot release: id 1 | task 25058 | stop processing: n_tokens = 1627, truncated = 0 23.08.890.283 I slot print_timing: id 0 | task 25167 | n_gen = 377, tg = 22.44 t/s, tg_3s = 26.50 t/s 23.10.715.179 I slot print_timing: id 2 | task 25333 | n_gen = 260, tg = 25.69 t/s, tg_3s = 26.35 t/s 23.11.893.635 I slot print_timing: id 0 | task 25167 | n_gen = 456, tg = 23.02 t/s, tg_3s = 26.30 t/s 23.12.655.944 I slot print_timing: id 2 | task 25333 | prompt eval time = 756.85 ms / 444 tokens ( 1.70 ms per token, 586.64 tokens per second) 23.12.655.951 I slot print_timing: id 2 | task 25333 | eval time = 12020.75 ms / 311 tokens ( 38.78 ms per token, 25.79 tokens per second) 23.12.655.952 I slot print_timing: id 2 | task 25333 | total time = 12777.60 ms / 755 tokens 23.12.655.953 I slot print_timing: id 2 | task 25333 | graphs reused = 24443 23.12.655.955 I slot print_timing: id 2 | task 25333 | graph reallocs = 0 / 0 (same size) / (changed size) 23.12.656.104 I slot release: id 2 | task 25333 | stop processing: n_tokens = 1449, truncated = 0 23.14.900.524 I slot print_timing: id 0 | task 25167 | n_gen = 611, tg = 26.79 t/s, tg_3s = 51.55 t/s 23.17.900.820 I slot print_timing: id 0 | task 25167 | n_gen = 792, tg = 30.70 t/s, tg_3s = 60.33 t/s 23.19.663.727 I slot print_timing: id 0 | task 25167 | prompt eval time = 783.60 ms / 489 tokens ( 1.60 ms per token, 624.04 tokens per second) 23.19.663.732 I slot print_timing: id 0 | task 25167 | eval time = 27532.20 ms / 898 tokens ( 30.69 ms per token, 32.58 tokens per second) 23.19.663.733 I slot print_timing: id 0 | task 25167 | total time = 28315.80 ms / 1387 tokens 23.19.663.734 I slot print_timing: id 0 | task 25167 | graphs reused = 24862 23.19.663.734 I slot print_timing: id 0 | task 25167 | graph reallocs = 0 / 0 (same size) / (changed size) 23.19.663.808 I slot release: id 0 | task 25167 | stop processing: n_tokens = 2084, truncated = 0 23.19.679.598 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1404, t_last = 343743050069 23.19.685.002 I slot launch_slot_: id 3 | task 26068 | processing task, is_child = 0 23.19.701.118 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1627, t_last = 343748816295 23.19.701.244 I slot launch_slot_: id 1 | task 26069 | processing task, is_child = 0 23.19.701.439 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1449, t_last = 343753491802 23.19.701.555 I slot launch_slot_: id 2 | task 26070 | processing task, is_child = 0 23.19.701.664 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2084, t_last = 343760499506 23.19.701.788 I slot launch_slot_: id 0 | task 26071 | processing task, is_child = 0 23.23.746.968 I slot print_timing: id 0 | task 26071 | prompt processing, n_tokens = 940, progress = 1.00, t = 4.05 s / 232.38 tokens per second 23.24.431.427 I slot print_timing: id 1 | task 26069 | prompt processing, n_tokens = 942, progress = 1.00, t = 4.04 s / 232.88 tokens per second 23.24.431.609 I slot print_timing: id 2 | task 26070 | prompt processing, n_tokens = 760, progress = 0.99, t = 4.04 s / 187.89 tokens per second 23.24.431.751 I slot print_timing: id 3 | task 26068 | prompt processing, n_tokens = 754, progress = 0.99, t = 4.04 s / 186.41 tokens per second 23.24.612.557 I slot print_timing: id 0 | task 26071 | prompt eval time = 4863.16 ms / 944 tokens ( 5.15 ms per token, 194.11 tokens per second) 23.24.612.559 I slot print_timing: id 0 | task 26071 | eval time = 47.59 ms / 2 tokens ( 47.59 ms per token, 21.01 tokens per second) 23.24.612.561 I slot print_timing: id 0 | task 26071 | total time = 4910.76 ms / 946 tokens 23.24.612.561 I slot print_timing: id 0 | task 26071 | graphs reused = 24864 23.24.612.562 I slot print_timing: id 0 | task 26071 | graph reallocs = 0 / 0 (same size) / (changed size) 23.24.612.620 I slot release: id 0 | task 26071 | stop processing: n_tokens = 945, truncated = 0 23.24.612.887 I slot print_timing: id 1 | task 26069 | prompt eval time = 4863.28 ms / 946 tokens ( 5.14 ms per token, 194.52 tokens per second) 23.24.612.889 I slot print_timing: id 1 | task 26069 | eval time = 47.63 ms / 2 tokens ( 47.63 ms per token, 21.00 tokens per second) 23.24.612.889 I slot print_timing: id 1 | task 26069 | total time = 4910.91 ms / 948 tokens 23.24.612.889 I slot print_timing: id 1 | task 26069 | graphs reused = 24864 23.24.612.890 I slot print_timing: id 1 | task 26069 | graph reallocs = 0 / 0 (same size) / (changed size) 23.24.612.933 I slot release: id 1 | task 26069 | stop processing: n_tokens = 947, truncated = 0 23.24.613.227 I slot print_timing: id 2 | task 26070 | prompt eval time = 4863.62 ms / 764 tokens ( 6.37 ms per token, 157.08 tokens per second) 23.24.613.232 I slot print_timing: id 2 | task 26070 | eval time = 47.52 ms / 2 tokens ( 47.52 ms per token, 21.04 tokens per second) 23.24.613.232 I slot print_timing: id 2 | task 26070 | total time = 4911.14 ms / 766 tokens 23.24.613.233 I slot print_timing: id 2 | task 26070 | graphs reused = 24864 23.24.613.233 I slot print_timing: id 2 | task 26070 | graph reallocs = 0 / 0 (same size) / (changed size) 23.24.613.270 I slot release: id 2 | task 26070 | stop processing: n_tokens = 765, truncated = 0 23.24.613.561 I slot print_timing: id 3 | task 26068 | prompt eval time = 4864.12 ms / 758 tokens ( 6.42 ms per token, 155.83 tokens per second) 23.24.613.563 I slot print_timing: id 3 | task 26068 | eval time = 47.25 ms / 2 tokens ( 47.25 ms per token, 21.16 tokens per second) 23.24.613.563 I slot print_timing: id 3 | task 26068 | total time = 4911.38 ms / 760 tokens 23.24.613.563 I slot print_timing: id 3 | task 26068 | graphs reused = 24864 23.24.613.564 I slot print_timing: id 3 | task 26068 | graph reallocs = 0 / 0 (same size) / (changed size) 23.24.613.592 I slot release: id 3 | task 26068 | stop processing: n_tokens = 759, truncated = 0 23.24.620.053 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 945, t_last = 343765448318 23.24.622.594 I slot launch_slot_: id 0 | task 26076 | processing task, is_child = 0 23.24.629.279 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 947, t_last = 343765448631 23.24.629.374 I slot launch_slot_: id 1 | task 26077 | processing task, is_child = 0 23.24.629.453 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 765, t_last = 343765448968 23.24.629.527 I slot launch_slot_: id 2 | task 26078 | processing task, is_child = 0 23.24.629.572 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 759, t_last = 343765449290 23.24.629.634 I slot launch_slot_: id 3 | task 26079 | processing task, is_child = 0 23.28.303.253 I slot print_timing: id 0 | task 26076 | prompt processing, n_tokens = 772, progress = 0.99, t = 3.67 s / 210.15 tokens per second 23.28.985.295 I slot print_timing: id 1 | task 26077 | prompt processing, n_tokens = 768, progress = 0.99, t = 3.67 s / 209.06 tokens per second 23.28.985.438 I slot print_timing: id 2 | task 26078 | prompt processing, n_tokens = 821, progress = 1.00, t = 3.67 s / 223.50 tokens per second 23.28.985.577 I slot print_timing: id 3 | task 26079 | prompt processing, n_tokens = 816, progress = 1.00, t = 3.67 s / 222.14 tokens per second 23.29.165.805 I slot print_timing: id 0 | task 26076 | prompt eval time = 4488.80 ms / 776 tokens ( 5.78 ms per token, 172.87 tokens per second) 23.29.165.807 I slot print_timing: id 0 | task 26076 | eval time = 47.36 ms / 2 tokens ( 47.36 ms per token, 21.12 tokens per second) 23.29.165.808 I slot print_timing: id 0 | task 26076 | total time = 4536.16 ms / 778 tokens 23.29.165.808 I slot print_timing: id 0 | task 26076 | graphs reused = 24865 23.29.165.808 I slot print_timing: id 0 | task 26076 | graph reallocs = 0 / 0 (same size) / (changed size) 23.29.165.854 I slot release: id 0 | task 26076 | stop processing: n_tokens = 777, truncated = 0 23.29.166.118 I slot print_timing: id 1 | task 26077 | prompt eval time = 4488.99 ms / 772 tokens ( 5.81 ms per token, 171.98 tokens per second) 23.29.166.120 I slot print_timing: id 1 | task 26077 | eval time = 47.40 ms / 2 tokens ( 47.40 ms per token, 21.10 tokens per second) 23.29.166.120 I slot print_timing: id 1 | task 26077 | total time = 4536.39 ms / 774 tokens 23.29.166.120 I slot print_timing: id 1 | task 26077 | graphs reused = 24865 23.29.166.121 I slot print_timing: id 1 | task 26077 | graph reallocs = 0 / 0 (same size) / (changed size) 23.29.166.152 I slot release: id 1 | task 26077 | stop processing: n_tokens = 773, truncated = 0 23.29.166.431 I slot print_timing: id 2 | task 26078 | prompt eval time = 4489.33 ms / 825 tokens ( 5.44 ms per token, 183.77 tokens per second) 23.29.166.437 I slot print_timing: id 2 | task 26078 | eval time = 47.31 ms / 2 tokens ( 47.31 ms per token, 21.14 tokens per second) 23.29.166.437 I slot print_timing: id 2 | task 26078 | total time = 4536.65 ms / 827 tokens 23.29.166.438 I slot print_timing: id 2 | task 26078 | graphs reused = 24865 23.29.166.438 I slot print_timing: id 2 | task 26078 | graph reallocs = 0 / 0 (same size) / (changed size) 23.29.166.474 I slot release: id 2 | task 26078 | stop processing: n_tokens = 826, truncated = 0 23.29.166.769 I slot print_timing: id 3 | task 26079 | prompt eval time = 4489.70 ms / 820 tokens ( 5.48 ms per token, 182.64 tokens per second) 23.29.166.770 I slot print_timing: id 3 | task 26079 | eval time = 47.23 ms / 2 tokens ( 47.23 ms per token, 21.17 tokens per second) 23.29.166.772 I slot print_timing: id 3 | task 26079 | total time = 4536.94 ms / 822 tokens 23.29.166.772 I slot print_timing: id 3 | task 26079 | graphs reused = 24865 23.29.166.772 I slot print_timing: id 3 | task 26079 | graph reallocs = 0 / 0 (same size) / (changed size) 23.29.166.809 I slot release: id 3 | task 26079 | stop processing: n_tokens = 821, truncated = 0 23.29.173.641 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.898 23.29.173.670 I slot launch_slot_: id 0 | task 26084 | processing task, is_child = 0 23.29.180.226 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 343770001850 23.29.180.313 I slot launch_slot_: id 1 | task 26085 | processing task, is_child = 0 23.29.180.405 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 343770002172 23.29.180.468 I slot launch_slot_: id 2 | task 26086 | processing task, is_child = 0 23.29.180.511 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 821, t_last = 343770002507 23.29.180.571 I slot launch_slot_: id 3 | task 26087 | processing task, is_child = 0 23.33.097.296 I slot print_timing: id 0 | task 26084 | prompt processing, n_tokens = 533, progress = 0.99, t = 3.92 s / 136.08 tokens per second 23.33.778.955 I slot print_timing: id 1 | task 26085 | prompt processing, n_tokens = 927, progress = 1.00, t = 3.92 s / 236.68 tokens per second 23.33.779.127 I slot print_timing: id 2 | task 26086 | prompt processing, n_tokens = 852, progress = 1.00, t = 3.92 s / 217.54 tokens per second 23.33.779.281 I slot print_timing: id 3 | task 26087 | prompt processing, n_tokens = 845, progress = 1.00, t = 3.92 s / 215.76 tokens per second 23.33.959.597 I slot print_timing: id 0 | task 26084 | prompt eval time = 4731.86 ms / 537 tokens ( 8.81 ms per token, 113.49 tokens per second) 23.33.959.600 I slot print_timing: id 0 | task 26084 | eval time = 47.15 ms / 2 tokens ( 47.15 ms per token, 21.21 tokens per second) 23.33.959.600 I slot print_timing: id 0 | task 26084 | total time = 4779.02 ms / 539 tokens 23.33.959.601 I slot print_timing: id 0 | task 26084 | graphs reused = 24867 23.33.959.601 I slot print_timing: id 0 | task 26084 | graph reallocs = 0 / 0 (same size) / (changed size) 23.33.959.653 I slot release: id 0 | task 26084 | stop processing: n_tokens = 798, truncated = 0 23.33.959.917 I slot print_timing: id 1 | task 26085 | prompt eval time = 4732.04 ms / 931 tokens ( 5.08 ms per token, 196.74 tokens per second) 23.33.959.923 I slot print_timing: id 1 | task 26085 | eval time = 47.20 ms / 2 tokens ( 47.20 ms per token, 21.19 tokens per second) 23.33.959.924 I slot print_timing: id 1 | task 26085 | total time = 4779.24 ms / 933 tokens 23.33.959.924 I slot print_timing: id 1 | task 26085 | graphs reused = 24867 23.33.959.924 I slot print_timing: id 1 | task 26085 | graph reallocs = 0 / 0 (same size) / (changed size) 23.33.959.965 I slot release: id 1 | task 26085 | stop processing: n_tokens = 932, truncated = 0 23.33.960.254 I slot print_timing: id 2 | task 26086 | prompt eval time = 4732.27 ms / 856 tokens ( 5.53 ms per token, 180.89 tokens per second) 23.33.960.259 I slot print_timing: id 2 | task 26086 | eval time = 47.23 ms / 2 tokens ( 47.23 ms per token, 21.17 tokens per second) 23.33.960.259 I slot print_timing: id 2 | task 26086 | total time = 4779.50 ms / 858 tokens 23.33.960.260 I slot print_timing: id 2 | task 26086 | graphs reused = 24867 23.33.960.260 I slot print_timing: id 2 | task 26086 | graph reallocs = 0 / 0 (same size) / (changed size) 23.33.960.300 I slot release: id 2 | task 26086 | stop processing: n_tokens = 857, truncated = 0 23.33.960.588 I slot print_timing: id 3 | task 26087 | prompt eval time = 4732.62 ms / 849 tokens ( 5.57 ms per token, 179.39 tokens per second) 23.33.960.590 I slot print_timing: id 3 | task 26087 | eval time = 47.14 ms / 2 tokens ( 47.14 ms per token, 21.21 tokens per second) 23.33.960.591 I slot print_timing: id 3 | task 26087 | total time = 4779.77 ms / 851 tokens 23.33.960.591 I slot print_timing: id 3 | task 26087 | graphs reused = 24867 23.33.960.591 I slot print_timing: id 3 | task 26087 | graph reallocs = 0 / 0 (same size) / (changed size) 23.33.960.628 I slot release: id 3 | task 26087 | stop processing: n_tokens = 850, truncated = 0 23.33.967.328 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 798, t_last = 343774795351 23.33.969.636 I slot launch_slot_: id 0 | task 26093 | processing task, is_child = 0 23.33.976.604 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 343774795663 23.33.976.680 I slot launch_slot_: id 1 | task 26092 | processing task, is_child = 0 23.33.976.773 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 857, t_last = 343774795999 23.33.976.847 I slot launch_slot_: id 2 | task 26094 | processing task, is_child = 0 23.33.976.892 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 850, t_last = 343774796326 23.33.976.952 I slot launch_slot_: id 3 | task 26095 | processing task, is_child = 0 23.39.517.010 I slot print_timing: id 0 | task 26093 | prompt processing, n_tokens = 985, progress = 1.00, t = 5.54 s / 177.80 tokens per second 23.39.830.161 I slot print_timing: id 1 | task 26092 | prompt processing, n_tokens = 950, progress = 1.00, t = 5.54 s / 171.48 tokens per second 23.39.830.323 I slot print_timing: id 2 | task 26094 | prompt processing, n_tokens = 887, progress = 1.00, t = 5.54 s / 160.11 tokens per second 23.39.830.470 I slot print_timing: id 3 | task 26095 | prompt processing, n_tokens = 1226, progress = 0.70, t = 5.54 s / 221.31 tokens per second 23.40.659.710 I slot print_timing: id 3 | task 26095 | prompt processing, n_tokens = 1738, progress = 1.00, t = 6.68 s / 260.12 tokens per second 23.40.740.009 I slot print_timing: id 0 | task 26093 | prompt eval time = 6682.13 ms / 989 tokens ( 6.76 ms per token, 148.01 tokens per second) 23.40.740.012 I slot print_timing: id 0 | task 26093 | eval time = 80.92 ms / 2 tokens ( 80.92 ms per token, 12.36 tokens per second) 23.40.740.012 I slot print_timing: id 0 | task 26093 | total time = 6763.05 ms / 991 tokens 23.40.740.013 I slot print_timing: id 0 | task 26093 | graphs reused = 24868 23.40.740.013 I slot print_timing: id 0 | task 26093 | graph reallocs = 0 / 0 (same size) / (changed size) 23.40.740.068 I slot release: id 0 | task 26093 | stop processing: n_tokens = 990, truncated = 0 23.40.740.336 I slot print_timing: id 1 | task 26092 | prompt eval time = 6682.37 ms / 954 tokens ( 7.00 ms per token, 142.76 tokens per second) 23.40.740.338 I slot print_timing: id 1 | task 26092 | eval time = 80.94 ms / 2 tokens ( 80.94 ms per token, 12.35 tokens per second) 23.40.740.339 I slot print_timing: id 1 | task 26092 | total time = 6763.31 ms / 956 tokens 23.40.740.339 I slot print_timing: id 1 | task 26092 | graphs reused = 24868 23.40.740.339 I slot print_timing: id 1 | task 26092 | graph reallocs = 0 / 0 (same size) / (changed size) 23.40.740.378 I slot release: id 1 | task 26092 | stop processing: n_tokens = 955, truncated = 0 23.40.740.651 I slot print_timing: id 2 | task 26094 | prompt eval time = 6682.61 ms / 891 tokens ( 7.50 ms per token, 133.33 tokens per second) 23.40.740.654 I slot print_timing: id 2 | task 26094 | eval time = 80.95 ms / 2 tokens ( 80.95 ms per token, 12.35 tokens per second) 23.40.740.654 I slot print_timing: id 2 | task 26094 | total time = 6763.56 ms / 893 tokens 23.40.740.662 I slot print_timing: id 2 | task 26094 | graphs reused = 24868 23.40.740.668 I slot print_timing: id 2 | task 26094 | graph reallocs = 0 / 0 (same size) / (changed size) 23.40.740.724 I slot release: id 2 | task 26094 | stop processing: n_tokens = 892, truncated = 0 23.40.759.537 I slot print_timing: id 3 | task 26095 | prompt eval time = 6764.13 ms / 1742 tokens ( 3.88 ms per token, 257.53 tokens per second) 23.40.759.539 I slot print_timing: id 3 | task 26095 | eval time = 18.25 ms / 2 tokens ( 18.25 ms per token, 54.79 tokens per second) 23.40.759.540 I slot print_timing: id 3 | task 26095 | total time = 6782.39 ms / 1744 tokens 23.40.759.540 I slot print_timing: id 3 | task 26095 | graphs reused = 24868 23.40.759.540 I slot print_timing: id 3 | task 26095 | graph reallocs = 0 / 0 (same size) / (changed size) 23.40.759.631 I slot release: id 3 | task 26095 | stop processing: n_tokens = 1743, truncated = 0 23.40.759.639 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 23.40.759.668 I slot launch_slot_: id 2 | task 26101 | processing task, is_child = 0 23.40.771.409 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 990, t_last = 343781575766 23.40.771.490 I slot launch_slot_: id 0 | task 26102 | processing task, is_child = 0 23.40.771.607 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 955, t_last = 343781576076 23.40.771.671 I slot launch_slot_: id 1 | task 26103 | processing task, is_child = 0 23.40.771.740 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1743, t_last = 343781595331 23.40.771.823 I slot launch_slot_: id 3 | task 26104 | processing task, is_child = 0 23.44.254.066 I slot print_timing: id 0 | task 26102 | prompt processing, n_tokens = 723, progress = 0.99, t = 3.48 s / 207.63 tokens per second 23.44.936.838 I slot print_timing: id 1 | task 26103 | prompt processing, n_tokens = 858, progress = 1.00, t = 3.48 s / 246.40 tokens per second 23.44.936.990 I slot print_timing: id 2 | task 26101 | prompt processing, n_tokens = 529, progress = 1.00, t = 3.48 s / 151.92 tokens per second 23.44.937.149 I slot print_timing: id 3 | task 26104 | prompt processing, n_tokens = 696, progress = 0.99, t = 3.48 s / 199.88 tokens per second 23.45.118.011 I slot print_timing: id 0 | task 26102 | prompt eval time = 4298.50 ms / 727 tokens ( 5.91 ms per token, 169.13 tokens per second) 23.45.118.013 I slot print_timing: id 0 | task 26102 | eval time = 47.68 ms / 2 tokens ( 47.68 ms per token, 20.97 tokens per second) 23.45.118.013 I slot print_timing: id 0 | task 26102 | total time = 4346.18 ms / 729 tokens 23.45.118.014 I slot print_timing: id 0 | task 26102 | graphs reused = 24870 23.45.118.014 I slot print_timing: id 0 | task 26102 | graph reallocs = 0 / 0 (same size) / (changed size) 23.45.118.059 I slot release: id 0 | task 26102 | stop processing: n_tokens = 728, truncated = 0 23.45.118.336 I slot print_timing: id 1 | task 26103 | prompt eval time = 4298.73 ms / 862 tokens ( 4.99 ms per token, 200.52 tokens per second) 23.45.118.339 I slot print_timing: id 1 | task 26103 | eval time = 47.70 ms / 2 tokens ( 47.70 ms per token, 20.96 tokens per second) 23.45.118.339 I slot print_timing: id 1 | task 26103 | total time = 4346.43 ms / 864 tokens 23.45.118.339 I slot print_timing: id 1 | task 26103 | graphs reused = 24870 23.45.118.340 I slot print_timing: id 1 | task 26103 | graph reallocs = 0 / 0 (same size) / (changed size) 23.45.118.382 I slot release: id 1 | task 26103 | stop processing: n_tokens = 863, truncated = 0 23.45.118.665 I slot print_timing: id 2 | task 26101 | prompt eval time = 4299.08 ms / 533 tokens ( 8.07 ms per token, 123.98 tokens per second) 23.45.118.666 I slot print_timing: id 2 | task 26101 | eval time = 47.62 ms / 2 tokens ( 47.62 ms per token, 21.00 tokens per second) 23.45.118.672 I slot print_timing: id 2 | task 26101 | total time = 4346.70 ms / 535 tokens 23.45.118.674 I slot print_timing: id 2 | task 26101 | graphs reused = 24870 23.45.118.674 I slot print_timing: id 2 | task 26101 | graph reallocs = 0 / 0 (same size) / (changed size) 23.45.118.720 I slot release: id 2 | task 26101 | stop processing: n_tokens = 909, truncated = 0 23.45.119.017 I slot print_timing: id 3 | task 26104 | prompt eval time = 4299.48 ms / 700 tokens ( 6.14 ms per token, 162.81 tokens per second) 23.45.119.019 I slot print_timing: id 3 | task 26104 | eval time = 47.49 ms / 2 tokens ( 47.49 ms per token, 21.06 tokens per second) 23.45.119.019 I slot print_timing: id 3 | task 26104 | total time = 4346.97 ms / 702 tokens 23.45.119.020 I slot print_timing: id 3 | task 26104 | graphs reused = 24870 23.45.119.020 I slot print_timing: id 3 | task 26104 | graph reallocs = 0 / 0 (same size) / (changed size) 23.45.119.047 I slot release: id 3 | task 26104 | stop processing: n_tokens = 701, truncated = 0 23.45.126.051 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.848 23.45.126.072 I slot launch_slot_: id 0 | task 26109 | processing task, is_child = 0 23.45.132.533 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.880 23.45.132.558 I slot launch_slot_: id 3 | task 26112 | processing task, is_child = 0 23.45.132.645 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 343785954080 23.45.132.703 I slot launch_slot_: id 1 | task 26110 | processing task, is_child = 0 23.45.132.747 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 909, t_last = 343785954420 23.45.133.448 I slot launch_slot_: id 2 | task 26111 | processing task, is_child = 0 23.48.835.765 I slot print_timing: id 1 | task 26110 | prompt processing, n_tokens = 824, progress = 1.00, t = 3.70 s / 222.59 tokens per second 23.48.835.929 I slot print_timing: id 2 | task 26111 | prompt processing, n_tokens = 518, progress = 0.99, t = 3.70 s / 139.93 tokens per second 23.48.836.053 I slot print_timing: id 3 | task 26112 | prompt processing, n_tokens = 516, progress = 0.99, t = 3.70 s / 139.40 tokens per second 23.48.963.151 I slot print_timing: id 0 | task 26109 | prompt eval time = 3702.29 ms / 497 tokens ( 7.45 ms per token, 134.24 tokens per second) 23.48.963.153 I slot print_timing: id 0 | task 26109 | eval time = 127.40 ms / 2 tokens ( 127.40 ms per token, 7.85 tokens per second) 23.48.963.154 I slot print_timing: id 0 | task 26109 | total time = 3829.70 ms / 499 tokens 23.48.963.154 I slot print_timing: id 0 | task 26109 | graphs reused = 24870 23.48.963.155 I slot print_timing: id 0 | task 26109 | graph reallocs = 0 / 0 (same size) / (changed size) 23.48.963.201 I slot release: id 0 | task 26109 | stop processing: n_tokens = 709, truncated = 0 23.49.001.227 I slot print_timing: id 1 | task 26110 | prompt eval time = 3829.93 ms / 828 tokens ( 4.63 ms per token, 216.19 tokens per second) 23.49.001.228 I slot print_timing: id 1 | task 26110 | eval time = 37.71 ms / 2 tokens ( 37.71 ms per token, 26.52 tokens per second) 23.49.001.229 I slot print_timing: id 1 | task 26110 | total time = 3867.63 ms / 830 tokens 23.49.001.229 I slot print_timing: id 1 | task 26110 | graphs reused = 24870 23.49.001.229 I slot print_timing: id 1 | task 26110 | graph reallocs = 0 / 0 (same size) / (changed size) 23.49.001.267 I slot release: id 1 | task 26110 | stop processing: n_tokens = 829, truncated = 0 23.49.001.537 I slot print_timing: id 2 | task 26111 | prompt eval time = 3830.18 ms / 522 tokens ( 7.34 ms per token, 136.29 tokens per second) 23.49.001.539 I slot print_timing: id 2 | task 26111 | eval time = 37.72 ms / 2 tokens ( 37.72 ms per token, 26.51 tokens per second) 23.49.001.540 I slot print_timing: id 2 | task 26111 | total time = 3867.89 ms / 524 tokens 23.49.001.540 I slot print_timing: id 2 | task 26111 | graphs reused = 24870 23.49.001.540 I slot print_timing: id 2 | task 26111 | graph reallocs = 0 / 0 (same size) / (changed size) 23.49.001.577 I slot release: id 2 | task 26111 | stop processing: n_tokens = 707, truncated = 0 23.49.001.845 I slot print_timing: id 3 | task 26112 | prompt eval time = 3830.61 ms / 520 tokens ( 7.37 ms per token, 135.75 tokens per second) 23.49.001.850 I slot print_timing: id 3 | task 26112 | eval time = 37.52 ms / 2 tokens ( 37.52 ms per token, 26.65 tokens per second) 23.49.001.851 I slot print_timing: id 3 | task 26112 | total time = 3868.13 ms / 522 tokens 23.49.001.851 I slot print_timing: id 3 | task 26112 | graphs reused = 24870 23.49.001.851 I slot print_timing: id 3 | task 26112 | graph reallocs = 0 / 0 (same size) / (changed size) 23.49.001.877 I slot release: id 3 | task 26112 | stop processing: n_tokens = 705, truncated = 0 23.49.001.880 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 709, t_last = 343789798899 23.49.004.029 I slot launch_slot_: id 0 | task 26117 | processing task, is_child = 0 23.49.010.605 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 829, t_last = 343789836965 23.49.010.670 I slot launch_slot_: id 1 | task 26118 | processing task, is_child = 0 23.49.010.742 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 343789837275 23.49.010.795 I slot launch_slot_: id 2 | task 26119 | processing task, is_child = 0 23.49.010.832 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 705, t_last = 343789837575 23.49.010.887 I slot launch_slot_: id 3 | task 26120 | processing task, is_child = 0 23.53.747.897 I slot print_timing: id 0 | task 26117 | prompt processing, n_tokens = 913, progress = 1.00, t = 4.74 s / 192.74 tokens per second 23.54.436.437 I slot print_timing: id 1 | task 26118 | prompt processing, n_tokens = 932, progress = 1.00, t = 4.74 s / 196.75 tokens per second 23.54.436.619 I slot print_timing: id 2 | task 26119 | prompt processing, n_tokens = 958, progress = 1.00, t = 4.74 s / 202.24 tokens per second 23.54.436.783 I slot print_timing: id 3 | task 26120 | prompt processing, n_tokens = 922, progress = 1.00, t = 4.74 s / 194.64 tokens per second 23.54.617.640 I slot print_timing: id 0 | task 26117 | prompt eval time = 5559.32 ms / 917 tokens ( 6.06 ms per token, 164.95 tokens per second) 23.54.617.644 I slot print_timing: id 0 | task 26117 | eval time = 47.43 ms / 2 tokens ( 47.43 ms per token, 21.08 tokens per second) 23.54.617.645 I slot print_timing: id 0 | task 26117 | total time = 5606.74 ms / 919 tokens 23.54.617.645 I slot print_timing: id 0 | task 26117 | graphs reused = 24872 23.54.617.646 I slot print_timing: id 0 | task 26117 | graph reallocs = 0 / 0 (same size) / (changed size) 23.54.617.694 I slot release: id 0 | task 26117 | stop processing: n_tokens = 918, truncated = 0 23.54.617.966 I slot print_timing: id 1 | task 26118 | prompt eval time = 5559.56 ms / 936 tokens ( 5.94 ms per token, 168.36 tokens per second) 23.54.617.972 I slot print_timing: id 1 | task 26118 | eval time = 47.45 ms / 2 tokens ( 47.45 ms per token, 21.07 tokens per second) 23.54.617.972 I slot print_timing: id 1 | task 26118 | total time = 5607.01 ms / 938 tokens 23.54.617.972 I slot print_timing: id 1 | task 26118 | graphs reused = 24872 23.54.617.973 I slot print_timing: id 1 | task 26118 | graph reallocs = 0 / 0 (same size) / (changed size) 23.54.618.010 I slot release: id 1 | task 26118 | stop processing: n_tokens = 937, truncated = 0 23.54.618.291 I slot print_timing: id 2 | task 26119 | prompt eval time = 5559.88 ms / 962 tokens ( 5.78 ms per token, 173.03 tokens per second) 23.54.618.294 I slot print_timing: id 2 | task 26119 | eval time = 47.41 ms / 2 tokens ( 47.41 ms per token, 21.09 tokens per second) 23.54.618.294 I slot print_timing: id 2 | task 26119 | total time = 5607.29 ms / 964 tokens 23.54.618.294 I slot print_timing: id 2 | task 26119 | graphs reused = 24872 23.54.618.294 I slot print_timing: id 2 | task 26119 | graph reallocs = 0 / 0 (same size) / (changed size) 23.54.618.340 I slot release: id 2 | task 26119 | stop processing: n_tokens = 963, truncated = 0 23.54.618.663 I slot print_timing: id 3 | task 26120 | prompt eval time = 5560.43 ms / 926 tokens ( 6.00 ms per token, 166.53 tokens per second) 23.54.618.666 I slot print_timing: id 3 | task 26120 | eval time = 47.18 ms / 2 tokens ( 47.18 ms per token, 21.19 tokens per second) 23.54.618.666 I slot print_timing: id 3 | task 26120 | total time = 5607.61 ms / 928 tokens 23.54.618.667 I slot print_timing: id 3 | task 26120 | graphs reused = 24872 23.54.618.667 I slot print_timing: id 3 | task 26120 | graph reallocs = 0 / 0 (same size) / (changed size) 23.54.618.712 I slot release: id 3 | task 26120 | stop processing: n_tokens = 927, truncated = 0 23.54.625.998 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.898 23.54.626.025 I slot launch_slot_: id 0 | task 26125 | processing task, is_child = 0 23.54.634.642 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 937, t_last = 343795453708 23.54.634.734 I slot launch_slot_: id 1 | task 26126 | processing task, is_child = 0 23.54.634.840 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 963, t_last = 343795454040 23.54.634.915 I slot launch_slot_: id 2 | task 26127 | processing task, is_child = 0 23.54.634.964 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 927, t_last = 343795454410 23.54.635.045 I slot launch_slot_: id 3 | task 26128 | processing task, is_child = 0 23.58.701.307 I slot print_timing: id 0 | task 26125 | prompt processing, n_tokens = 519, progress = 1.00, t = 4.07 s / 127.64 tokens per second 23.59.385.804 I slot print_timing: id 1 | task 26126 | prompt processing, n_tokens = 817, progress = 1.00, t = 4.07 s / 200.93 tokens per second 23.59.385.956 I slot print_timing: id 2 | task 26127 | prompt processing, n_tokens = 882, progress = 1.00, t = 4.07 s / 216.92 tokens per second 23.59.386.109 I slot print_timing: id 3 | task 26128 | prompt processing, n_tokens = 996, progress = 1.00, t = 4.07 s / 244.96 tokens per second 23.59.567.105 I slot print_timing: id 0 | task 26125 | prompt eval time = 4884.54 ms / 523 tokens ( 9.34 ms per token, 107.07 tokens per second) 23.59.567.107 I slot print_timing: id 0 | task 26125 | eval time = 47.51 ms / 2 tokens ( 47.51 ms per token, 21.05 tokens per second) 23.59.567.108 I slot print_timing: id 0 | task 26125 | total time = 4932.05 ms / 525 tokens 23.59.567.108 I slot print_timing: id 0 | task 26125 | graphs reused = 24874 23.59.567.108 I slot print_timing: id 0 | task 26125 | graph reallocs = 0 / 0 (same size) / (changed size) 23.59.567.161 I slot release: id 0 | task 26125 | stop processing: n_tokens = 925, truncated = 0 23.59.567.434 I slot print_timing: id 1 | task 26126 | prompt eval time = 4884.75 ms / 821 tokens ( 5.95 ms per token, 168.07 tokens per second) 23.59.567.436 I slot print_timing: id 1 | task 26126 | eval time = 47.54 ms / 2 tokens ( 47.54 ms per token, 21.03 tokens per second) 23.59.567.436 I slot print_timing: id 1 | task 26126 | total time = 4932.29 ms / 823 tokens 23.59.567.436 I slot print_timing: id 1 | task 26126 | graphs reused = 24874 23.59.567.437 I slot print_timing: id 1 | task 26126 | graph reallocs = 0 / 0 (same size) / (changed size) 23.59.567.474 I slot release: id 1 | task 26126 | stop processing: n_tokens = 822, truncated = 0 23.59.567.743 I slot print_timing: id 2 | task 26127 | prompt eval time = 4885.03 ms / 886 tokens ( 5.51 ms per token, 181.37 tokens per second) 23.59.567.745 I slot print_timing: id 2 | task 26127 | eval time = 47.50 ms / 2 tokens ( 47.50 ms per token, 21.05 tokens per second) 23.59.567.746 I slot print_timing: id 2 | task 26127 | total time = 4932.53 ms / 888 tokens 23.59.567.746 I slot print_timing: id 2 | task 26127 | graphs reused = 24874 23.59.567.747 I slot print_timing: id 2 | task 26127 | graph reallocs = 0 / 0 (same size) / (changed size) 23.59.567.791 I slot release: id 2 | task 26127 | stop processing: n_tokens = 887, truncated = 0 23.59.568.112 I slot print_timing: id 3 | task 26128 | prompt eval time = 4885.40 ms / 1000 tokens ( 4.89 ms per token, 204.69 tokens per second) 23.59.568.118 I slot print_timing: id 3 | task 26128 | eval time = 47.44 ms / 2 tokens ( 47.44 ms per token, 21.08 tokens per second) 23.59.568.118 I slot print_timing: id 3 | task 26128 | total time = 4932.83 ms / 1002 tokens 23.59.568.119 I slot print_timing: id 3 | task 26128 | graphs reused = 24874 23.59.568.119 I slot print_timing: id 3 | task 26128 | graph reallocs = 0 / 0 (same size) / (changed size) 23.59.568.169 I slot release: id 3 | task 26128 | stop processing: n_tokens = 1001, truncated = 0 23.59.575.227 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.791 23.59.575.307 I slot launch_slot_: id 3 | task 26133 | processing task, is_child = 0 23.59.582.602 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.891 (> 0.100 thold), f_keep = 0.892 23.59.582.628 I slot launch_slot_: id 2 | task 26134 | processing task, is_child = 0 23.59.582.729 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 925, t_last = 343800402859 23.59.583.616 I slot launch_slot_: id 0 | task 26135 | processing task, is_child = 0 23.59.583.667 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 822, t_last = 343800403172 23.59.583.727 I slot launch_slot_: id 1 | task 26136 | processing task, is_child = 0 24.03.315.764 I slot print_timing: id 0 | task 26135 | prompt processing, n_tokens = 587, progress = 1.00, t = 3.73 s / 157.30 tokens per second 24.03.315.941 I slot print_timing: id 1 | task 26136 | prompt processing, n_tokens = 986, progress = 1.00, t = 3.73 s / 264.23 tokens per second 24.03.316.132 I slot print_timing: id 2 | task 26134 | prompt processing, n_tokens = 514, progress = 1.00, t = 3.73 s / 137.74 tokens per second 24.03.436.695 I slot print_timing: id 3 | task 26133 | prompt eval time = 3731.79 ms / 388 tokens ( 9.62 ms per token, 103.97 tokens per second) 24.03.436.698 I slot print_timing: id 3 | task 26133 | eval time = 120.94 ms / 2 tokens ( 120.94 ms per token, 8.27 tokens per second) 24.03.436.698 I slot print_timing: id 3 | task 26133 | total time = 3852.73 ms / 390 tokens 24.03.436.699 I slot print_timing: id 3 | task 26133 | graphs reused = 24874 24.03.436.699 I slot print_timing: id 3 | task 26133 | graph reallocs = 0 / 0 (same size) / (changed size) 24.03.436.769 I slot release: id 3 | task 26133 | stop processing: n_tokens = 873, truncated = 0 24.03.474.048 I slot print_timing: id 0 | task 26135 | prompt eval time = 3851.89 ms / 591 tokens ( 6.52 ms per token, 153.43 tokens per second) 24.03.474.052 I slot print_timing: id 0 | task 26135 | eval time = 38.42 ms / 2 tokens ( 38.42 ms per token, 26.03 tokens per second) 24.03.474.053 I slot print_timing: id 0 | task 26135 | total time = 3890.31 ms / 593 tokens 24.03.474.053 I slot print_timing: id 0 | task 26135 | graphs reused = 24874 24.03.474.054 I slot print_timing: id 0 | task 26135 | graph reallocs = 0 / 0 (same size) / (changed size) 24.03.474.104 I slot release: id 0 | task 26135 | stop processing: n_tokens = 962, truncated = 0 24.03.474.397 I slot print_timing: id 1 | task 26136 | prompt eval time = 3852.17 ms / 990 tokens ( 3.89 ms per token, 257.00 tokens per second) 24.03.474.398 I slot print_timing: id 1 | task 26136 | eval time = 38.41 ms / 2 tokens ( 38.41 ms per token, 26.03 tokens per second) 24.03.474.398 I slot print_timing: id 1 | task 26136 | total time = 3890.59 ms / 992 tokens 24.03.474.399 I slot print_timing: id 1 | task 26136 | graphs reused = 24874 24.03.474.399 I slot print_timing: id 1 | task 26136 | graph reallocs = 0 / 0 (same size) / (changed size) 24.03.474.446 I slot release: id 1 | task 26136 | stop processing: n_tokens = 991, truncated = 0 24.03.474.729 I slot print_timing: id 2 | task 26134 | prompt eval time = 3852.51 ms / 518 tokens ( 7.44 ms per token, 134.46 tokens per second) 24.03.474.731 I slot print_timing: id 2 | task 26134 | eval time = 38.35 ms / 2 tokens ( 38.35 ms per token, 26.07 tokens per second) 24.03.474.731 I slot print_timing: id 2 | task 26134 | total time = 3890.86 ms / 520 tokens 24.03.474.731 I slot print_timing: id 2 | task 26134 | graphs reused = 24874 24.03.474.732 I slot print_timing: id 2 | task 26134 | graph reallocs = 0 / 0 (same size) / (changed size) 24.03.474.770 I slot release: id 2 | task 26134 | stop processing: n_tokens = 889, truncated = 0 24.03.474.774 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 343804272467 24.03.476.417 I slot launch_slot_: id 3 | task 26141 | processing task, is_child = 0 24.03.485.093 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 343804309804 24.03.485.182 I slot launch_slot_: id 0 | task 26142 | processing task, is_child = 0 24.03.485.272 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 343804310144 24.03.485.336 I slot launch_slot_: id 1 | task 26143 | processing task, is_child = 0 24.03.485.384 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 889, t_last = 343804310468 24.03.485.447 I slot launch_slot_: id 2 | task 26144 | processing task, is_child = 0 24.08.476.663 I slot print_timing: id 0 | task 26142 | prompt processing, n_tokens = 899, progress = 1.00, t = 4.99 s / 180.12 tokens per second 24.09.162.829 I slot print_timing: id 1 | task 26143 | prompt processing, n_tokens = 865, progress = 1.00, t = 4.99 s / 173.31 tokens per second 24.09.162.989 I slot print_timing: id 2 | task 26144 | prompt processing, n_tokens = 1276, progress = 1.00, t = 4.99 s / 255.66 tokens per second 24.09.163.179 I slot print_timing: id 3 | task 26141 | prompt processing, n_tokens = 906, progress = 1.00, t = 4.99 s / 181.53 tokens per second 24.09.344.280 I slot print_timing: id 0 | task 26142 | prompt eval time = 5811.45 ms / 903 tokens ( 6.44 ms per token, 155.38 tokens per second) 24.09.344.282 I slot print_timing: id 0 | task 26142 | eval time = 47.38 ms / 2 tokens ( 47.38 ms per token, 21.11 tokens per second) 24.09.344.283 I slot print_timing: id 0 | task 26142 | total time = 5858.83 ms / 905 tokens 24.09.344.284 I slot print_timing: id 0 | task 26142 | graphs reused = 24876 24.09.344.284 I slot print_timing: id 0 | task 26142 | graph reallocs = 0 / 0 (same size) / (changed size) 24.09.344.341 I slot release: id 0 | task 26142 | stop processing: n_tokens = 904, truncated = 0 24.09.344.622 I slot print_timing: id 1 | task 26143 | prompt eval time = 5811.77 ms / 869 tokens ( 6.69 ms per token, 149.52 tokens per second) 24.09.344.627 I slot print_timing: id 1 | task 26143 | eval time = 47.34 ms / 2 tokens ( 47.34 ms per token, 21.13 tokens per second) 24.09.344.628 I slot print_timing: id 1 | task 26143 | total time = 5859.10 ms / 871 tokens 24.09.344.628 I slot print_timing: id 1 | task 26143 | graphs reused = 24876 24.09.344.629 I slot print_timing: id 1 | task 26143 | graph reallocs = 0 / 0 (same size) / (changed size) 24.09.344.669 I slot release: id 1 | task 26143 | stop processing: n_tokens = 870, truncated = 0 24.09.344.956 I slot print_timing: id 2 | task 26144 | prompt eval time = 5812.01 ms / 1280 tokens ( 4.54 ms per token, 220.23 tokens per second) 24.09.344.958 I slot print_timing: id 2 | task 26144 | eval time = 47.34 ms / 2 tokens ( 47.34 ms per token, 21.12 tokens per second) 24.09.344.959 I slot print_timing: id 2 | task 26144 | total time = 5859.35 ms / 1282 tokens 24.09.344.959 I slot print_timing: id 2 | task 26144 | graphs reused = 24876 24.09.344.959 I slot print_timing: id 2 | task 26144 | graph reallocs = 0 / 0 (same size) / (changed size) 24.09.345.019 I slot release: id 2 | task 26144 | stop processing: n_tokens = 1281, truncated = 0 24.09.345.317 I slot print_timing: id 3 | task 26141 | prompt eval time = 5812.45 ms / 910 tokens ( 6.39 ms per token, 156.56 tokens per second) 24.09.345.320 I slot print_timing: id 3 | task 26141 | eval time = 47.19 ms / 2 tokens ( 47.19 ms per token, 21.19 tokens per second) 24.09.345.320 I slot print_timing: id 3 | task 26141 | total time = 5859.64 ms / 912 tokens 24.09.345.321 I slot print_timing: id 3 | task 26141 | graphs reused = 24876 24.09.345.321 I slot print_timing: id 3 | task 26141 | graph reallocs = 0 / 0 (same size) / (changed size) 24.09.345.363 I slot release: id 3 | task 26141 | stop processing: n_tokens = 911, truncated = 0 24.09.351.440 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 343810180039 24.09.354.211 I slot launch_slot_: id 0 | task 26149 | processing task, is_child = 0 24.09.362.318 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.877 24.09.362.338 I slot launch_slot_: id 2 | task 26150 | processing task, is_child = 0 24.09.362.424 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 870, t_last = 343810180368 24.09.363.970 I slot launch_slot_: id 1 | task 26151 | processing task, is_child = 0 24.09.364.025 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 911, t_last = 343810181061 24.09.364.096 I slot launch_slot_: id 3 | task 26152 | processing task, is_child = 0 24.13.838.805 I slot print_timing: id 0 | task 26149 | prompt processing, n_tokens = 763, progress = 0.99, t = 4.47 s / 170.54 tokens per second 24.13.838.957 I slot print_timing: id 3 | task 26152 | prompt processing, n_tokens = 1283, progress = 1.00, t = 4.47 s / 286.78 tokens per second 24.13.950.027 I slot print_timing: id 1 | task 26151 | prompt eval time = 4474.33 ms / 476 tokens ( 9.40 ms per token, 106.38 tokens per second) 24.13.950.029 I slot print_timing: id 1 | task 26151 | eval time = 111.53 ms / 2 tokens ( 111.53 ms per token, 8.97 tokens per second) 24.13.950.029 I slot print_timing: id 1 | task 26151 | total time = 4585.85 ms / 478 tokens 24.13.950.030 I slot print_timing: id 1 | task 26151 | graphs reused = 24876 24.13.950.030 I slot print_timing: id 1 | task 26151 | graph reallocs = 0 / 0 (same size) / (changed size) 24.13.950.094 I slot release: id 1 | task 26151 | stop processing: n_tokens = 1241, truncated = 0 24.13.950.411 I slot print_timing: id 2 | task 26150 | prompt eval time = 4474.52 ms / 439 tokens ( 10.19 ms per token, 98.11 tokens per second) 24.13.950.421 I slot print_timing: id 2 | task 26150 | eval time = 111.62 ms / 2 tokens ( 111.62 ms per token, 8.96 tokens per second) 24.13.950.422 I slot print_timing: id 2 | task 26150 | total time = 4586.14 ms / 441 tokens 24.13.950.422 I slot print_timing: id 2 | task 26150 | graphs reused = 24876 24.13.950.424 I slot print_timing: id 2 | task 26150 | graph reallocs = 0 / 0 (same size) / (changed size) 24.13.950.467 I slot release: id 2 | task 26150 | stop processing: n_tokens = 1204, truncated = 0 24.13.985.517 I slot print_timing: id 0 | task 26149 | prompt eval time = 4585.63 ms / 767 tokens ( 5.98 ms per token, 167.26 tokens per second) 24.13.985.519 I slot print_timing: id 0 | task 26149 | eval time = 35.79 ms / 2 tokens ( 35.79 ms per token, 27.94 tokens per second) 24.13.985.520 I slot print_timing: id 0 | task 26149 | total time = 4621.41 ms / 769 tokens 24.13.985.521 I slot print_timing: id 0 | task 26149 | graphs reused = 24876 24.13.985.521 I slot print_timing: id 0 | task 26149 | graph reallocs = 0 / 0 (same size) / (changed size) 24.13.985.559 I slot release: id 0 | task 26149 | stop processing: n_tokens = 768, truncated = 0 24.13.985.843 I slot print_timing: id 3 | task 26152 | prompt eval time = 4586.46 ms / 1287 tokens ( 3.56 ms per token, 280.61 tokens per second) 24.13.985.848 I slot print_timing: id 3 | task 26152 | eval time = 35.00 ms / 2 tokens ( 35.00 ms per token, 28.57 tokens per second) 24.13.985.849 I slot print_timing: id 3 | task 26152 | total time = 4621.47 ms / 1289 tokens 24.13.985.849 I slot print_timing: id 3 | task 26152 | graphs reused = 24876 24.13.985.850 I slot print_timing: id 3 | task 26152 | graph reallocs = 0 / 0 (same size) / (changed size) 24.13.985.899 I slot release: id 3 | task 26152 | stop processing: n_tokens = 1288, truncated = 0 24.13.985.903 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 24.13.985.924 I slot launch_slot_: id 0 | task 26157 | processing task, is_child = 0 24.13.994.616 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1241, t_last = 343814785794 24.13.994.707 I slot launch_slot_: id 1 | task 26158 | processing task, is_child = 0 24.13.994.824 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1204, t_last = 343814786165 24.13.994.898 I slot launch_slot_: id 2 | task 26159 | processing task, is_child = 0 24.13.994.956 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1288, t_last = 343814821597 24.13.995.028 I slot launch_slot_: id 3 | task 26160 | processing task, is_child = 0 24.17.852.592 I slot print_timing: id 0 | task 26157 | prompt processing, n_tokens = 528, progress = 0.99, t = 3.86 s / 136.87 tokens per second 24.18.539.143 I slot print_timing: id 1 | task 26158 | prompt processing, n_tokens = 870, progress = 1.00, t = 3.86 s / 225.54 tokens per second 24.18.539.312 I slot print_timing: id 2 | task 26159 | prompt processing, n_tokens = 766, progress = 0.99, t = 3.86 s / 198.58 tokens per second 24.18.539.462 I slot print_timing: id 3 | task 26160 | prompt processing, n_tokens = 840, progress = 1.00, t = 3.86 s / 217.77 tokens per second 24.18.720.111 I slot print_timing: id 0 | task 26157 | prompt eval time = 4677.73 ms / 532 tokens ( 8.79 ms per token, 113.73 tokens per second) 24.18.720.115 I slot print_timing: id 0 | task 26157 | eval time = 47.35 ms / 2 tokens ( 47.35 ms per token, 21.12 tokens per second) 24.18.720.116 I slot print_timing: id 0 | task 26157 | total time = 4725.08 ms / 534 tokens 24.18.720.116 I slot print_timing: id 0 | task 26157 | graphs reused = 24877 24.18.720.117 I slot print_timing: id 0 | task 26157 | graph reallocs = 0 / 0 (same size) / (changed size) 24.18.720.169 I slot release: id 0 | task 26157 | stop processing: n_tokens = 784, truncated = 0 24.18.720.434 I slot print_timing: id 1 | task 26158 | prompt eval time = 4677.94 ms / 874 tokens ( 5.35 ms per token, 186.83 tokens per second) 24.18.720.436 I slot print_timing: id 1 | task 26158 | eval time = 47.37 ms / 2 tokens ( 47.37 ms per token, 21.11 tokens per second) 24.18.720.437 I slot print_timing: id 1 | task 26158 | total time = 4725.32 ms / 876 tokens 24.18.720.437 I slot print_timing: id 1 | task 26158 | graphs reused = 24877 24.18.720.437 I slot print_timing: id 1 | task 26158 | graph reallocs = 0 / 0 (same size) / (changed size) 24.18.720.485 I slot release: id 1 | task 26158 | stop processing: n_tokens = 875, truncated = 0 24.18.720.776 I slot print_timing: id 2 | task 26159 | prompt eval time = 4678.28 ms / 770 tokens ( 6.08 ms per token, 164.59 tokens per second) 24.18.720.779 I slot print_timing: id 2 | task 26159 | eval time = 47.30 ms / 2 tokens ( 47.30 ms per token, 21.14 tokens per second) 24.18.720.779 I slot print_timing: id 2 | task 26159 | total time = 4725.57 ms / 772 tokens 24.18.720.780 I slot print_timing: id 2 | task 26159 | graphs reused = 24877 24.18.720.780 I slot print_timing: id 2 | task 26159 | graph reallocs = 0 / 0 (same size) / (changed size) 24.18.720.818 I slot release: id 2 | task 26159 | stop processing: n_tokens = 771, truncated = 0 24.18.721.137 I slot print_timing: id 3 | task 26160 | prompt eval time = 4678.74 ms / 844 tokens ( 5.54 ms per token, 180.39 tokens per second) 24.18.721.140 I slot print_timing: id 3 | task 26160 | eval time = 47.12 ms / 2 tokens ( 47.12 ms per token, 21.22 tokens per second) 24.18.721.141 I slot print_timing: id 3 | task 26160 | total time = 4725.86 ms / 846 tokens 24.18.721.141 I slot print_timing: id 3 | task 26160 | graphs reused = 24877 24.18.721.141 I slot print_timing: id 3 | task 26160 | graph reallocs = 0 / 0 (same size) / (changed size) 24.18.721.184 I slot release: id 3 | task 26160 | stop processing: n_tokens = 845, truncated = 0 24.18.728.520 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.860 24.18.728.547 I slot launch_slot_: id 2 | task 26165 | processing task, is_child = 0 24.18.736.395 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 784, t_last = 343819555867 24.18.736.475 I slot launch_slot_: id 0 | task 26166 | processing task, is_child = 0 24.18.736.563 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 875, t_last = 343819556183 24.18.736.626 I slot launch_slot_: id 1 | task 26167 | processing task, is_child = 0 24.18.736.674 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 845, t_last = 343819556882 24.18.736.737 I slot launch_slot_: id 3 | task 26168 | processing task, is_child = 0 24.23.033.969 I slot print_timing: id 0 | task 26166 | prompt processing, n_tokens = 752, progress = 0.99, t = 4.30 s / 175.01 tokens per second 24.23.034.133 I slot print_timing: id 1 | task 26167 | prompt processing, n_tokens = 814, progress = 1.00, t = 4.30 s / 189.45 tokens per second 24.23.034.290 I slot print_timing: id 3 | task 26168 | prompt processing, n_tokens = 775, progress = 0.99, t = 4.30 s / 180.38 tokens per second 24.23.165.640 I slot print_timing: id 2 | task 26165 | prompt eval time = 4297.05 ms / 496 tokens ( 8.66 ms per token, 115.43 tokens per second) 24.23.165.643 I slot print_timing: id 2 | task 26165 | eval time = 131.69 ms / 2 tokens ( 131.69 ms per token, 7.59 tokens per second) 24.23.165.644 I slot print_timing: id 2 | task 26165 | total time = 4428.74 ms / 498 tokens 24.23.165.644 I slot print_timing: id 2 | task 26165 | graphs reused = 24877 24.23.165.645 I slot print_timing: id 2 | task 26165 | graph reallocs = 0 / 0 (same size) / (changed size) 24.23.165.700 I slot release: id 2 | task 26165 | stop processing: n_tokens = 751, truncated = 0 24.23.210.815 I slot print_timing: id 0 | task 26166 | prompt eval time = 4428.20 ms / 756 tokens ( 5.86 ms per token, 170.72 tokens per second) 24.23.210.817 I slot print_timing: id 0 | task 26166 | eval time = 45.87 ms / 2 tokens ( 45.87 ms per token, 21.80 tokens per second) 24.23.210.818 I slot print_timing: id 0 | task 26166 | total time = 4474.07 ms / 758 tokens 24.23.210.818 I slot print_timing: id 0 | task 26166 | graphs reused = 24877 24.23.210.819 I slot print_timing: id 0 | task 26166 | graph reallocs = 0 / 0 (same size) / (changed size) 24.23.210.868 I slot release: id 0 | task 26166 | stop processing: n_tokens = 757, truncated = 0 24.23.211.166 I slot print_timing: id 1 | task 26167 | prompt eval time = 4428.50 ms / 818 tokens ( 5.41 ms per token, 184.71 tokens per second) 24.23.211.169 I slot print_timing: id 1 | task 26167 | eval time = 45.83 ms / 2 tokens ( 45.83 ms per token, 21.82 tokens per second) 24.23.211.170 I slot print_timing: id 1 | task 26167 | total time = 4474.33 ms / 820 tokens 24.23.211.170 I slot print_timing: id 1 | task 26167 | graphs reused = 24877 24.23.211.170 I slot print_timing: id 1 | task 26167 | graph reallocs = 0 / 0 (same size) / (changed size) 24.23.211.215 I slot release: id 1 | task 26167 | stop processing: n_tokens = 819, truncated = 0 24.23.211.533 I slot print_timing: id 3 | task 26168 | prompt eval time = 4429.22 ms / 779 tokens ( 5.69 ms per token, 175.88 tokens per second) 24.23.211.535 I slot print_timing: id 3 | task 26168 | eval time = 45.28 ms / 2 tokens ( 45.28 ms per token, 22.08 tokens per second) 24.23.211.535 I slot print_timing: id 3 | task 26168 | total time = 4474.51 ms / 781 tokens 24.23.211.536 I slot print_timing: id 3 | task 26168 | graphs reused = 24877 24.23.211.536 I slot print_timing: id 3 | task 26168 | graph reallocs = 0 / 0 (same size) / (changed size) 24.23.211.574 I slot release: id 3 | task 26168 | stop processing: n_tokens = 780, truncated = 0 24.23.211.578 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 343824001398 24.23.213.593 I slot launch_slot_: id 2 | task 26173 | processing task, is_child = 0 24.23.220.556 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 757, t_last = 343824046566 24.23.220.632 I slot launch_slot_: id 0 | task 26175 | processing task, is_child = 0 24.23.220.716 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 819, t_last = 343824046913 24.23.220.776 I slot launch_slot_: id 1 | task 26174 | processing task, is_child = 0 24.23.220.820 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 343824047272 24.23.220.880 I slot launch_slot_: id 3 | task 26176 | processing task, is_child = 0 24.27.476.055 I slot print_timing: id 0 | task 26175 | prompt processing, n_tokens = 899, progress = 1.00, t = 4.26 s / 211.27 tokens per second 24.28.161.160 I slot print_timing: id 1 | task 26174 | prompt processing, n_tokens = 881, progress = 1.00, t = 4.26 s / 207.05 tokens per second 24.28.161.323 I slot print_timing: id 2 | task 26173 | prompt processing, n_tokens = 893, progress = 1.00, t = 4.26 s / 209.87 tokens per second 24.28.161.479 I slot print_timing: id 3 | task 26176 | prompt processing, n_tokens = 877, progress = 1.00, t = 4.25 s / 206.11 tokens per second 24.28.342.871 I slot print_timing: id 0 | task 26175 | prompt eval time = 5074.23 ms / 903 tokens ( 5.62 ms per token, 177.96 tokens per second) 24.28.342.873 I slot print_timing: id 0 | task 26175 | eval time = 47.75 ms / 2 tokens ( 47.75 ms per token, 20.94 tokens per second) 24.28.342.874 I slot print_timing: id 0 | task 26175 | total time = 5121.98 ms / 905 tokens 24.28.342.874 I slot print_timing: id 0 | task 26175 | graphs reused = 24879 24.28.342.875 I slot print_timing: id 0 | task 26175 | graph reallocs = 0 / 0 (same size) / (changed size) 24.28.342.923 I slot release: id 0 | task 26175 | stop processing: n_tokens = 904, truncated = 0 24.28.343.200 I slot print_timing: id 1 | task 26174 | prompt eval time = 5074.48 ms / 885 tokens ( 5.73 ms per token, 174.40 tokens per second) 24.28.343.202 I slot print_timing: id 1 | task 26174 | eval time = 47.76 ms / 2 tokens ( 47.76 ms per token, 20.94 tokens per second) 24.28.343.202 I slot print_timing: id 1 | task 26174 | total time = 5122.24 ms / 887 tokens 24.28.343.203 I slot print_timing: id 1 | task 26174 | graphs reused = 24879 24.28.343.203 I slot print_timing: id 1 | task 26174 | graph reallocs = 0 / 0 (same size) / (changed size) 24.28.343.247 I slot release: id 1 | task 26174 | stop processing: n_tokens = 886, truncated = 0 24.28.343.512 I slot print_timing: id 2 | task 26173 | prompt eval time = 5074.75 ms / 897 tokens ( 5.66 ms per token, 176.76 tokens per second) 24.28.343.515 I slot print_timing: id 2 | task 26173 | eval time = 47.75 ms / 2 tokens ( 47.75 ms per token, 20.94 tokens per second) 24.28.343.515 I slot print_timing: id 2 | task 26173 | total time = 5122.50 ms / 899 tokens 24.28.343.515 I slot print_timing: id 2 | task 26173 | graphs reused = 24879 24.28.343.516 I slot print_timing: id 2 | task 26173 | graph reallocs = 0 / 0 (same size) / (changed size) 24.28.343.546 I slot release: id 2 | task 26173 | stop processing: n_tokens = 898, truncated = 0 24.28.343.819 I slot print_timing: id 3 | task 26176 | prompt eval time = 5075.37 ms / 881 tokens ( 5.76 ms per token, 173.58 tokens per second) 24.28.343.822 I slot print_timing: id 3 | task 26176 | eval time = 47.38 ms / 2 tokens ( 47.38 ms per token, 21.11 tokens per second) 24.28.343.823 I slot print_timing: id 3 | task 26176 | total time = 5122.75 ms / 883 tokens 24.28.343.823 I slot print_timing: id 3 | task 26176 | graphs reused = 24879 24.28.343.823 I slot print_timing: id 3 | task 26176 | graph reallocs = 0 / 0 (same size) / (changed size) 24.28.343.851 I slot release: id 3 | task 26176 | stop processing: n_tokens = 882, truncated = 0 24.28.350.475 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 343829178621 24.28.353.183 I slot launch_slot_: id 0 | task 26182 | processing task, is_child = 0 24.28.360.557 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 886, t_last = 343829178945 24.28.360.630 I slot launch_slot_: id 1 | task 26181 | processing task, is_child = 0 24.28.360.722 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.895 24.28.360.739 I slot launch_slot_: id 2 | task 26183 | processing task, is_child = 0 24.28.360.782 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 343829179549 24.28.360.848 I slot launch_slot_: id 3 | task 26184 | processing task, is_child = 0 24.31.785.763 I slot print_timing: id 0 | task 26182 | prompt processing, n_tokens = 773, progress = 0.99, t = 3.42 s / 225.70 tokens per second 24.32.471.060 I slot print_timing: id 1 | task 26181 | prompt processing, n_tokens = 773, progress = 0.99, t = 3.42 s / 225.70 tokens per second 24.32.471.215 I slot print_timing: id 2 | task 26183 | prompt processing, n_tokens = 513, progress = 1.00, t = 3.42 s / 149.79 tokens per second 24.32.471.374 I slot print_timing: id 3 | task 26184 | prompt processing, n_tokens = 941, progress = 1.00, t = 3.42 s / 274.77 tokens per second 24.32.652.239 I slot print_timing: id 0 | task 26182 | prompt eval time = 4243.94 ms / 777 tokens ( 5.46 ms per token, 183.08 tokens per second) 24.32.652.242 I slot print_timing: id 0 | task 26182 | eval time = 47.45 ms / 2 tokens ( 47.45 ms per token, 21.08 tokens per second) 24.32.652.243 I slot print_timing: id 0 | task 26182 | total time = 4291.38 ms / 779 tokens 24.32.652.243 I slot print_timing: id 0 | task 26182 | graphs reused = 24881 24.32.652.244 I slot print_timing: id 0 | task 26182 | graph reallocs = 0 / 0 (same size) / (changed size) 24.32.652.293 I slot release: id 0 | task 26182 | stop processing: n_tokens = 778, truncated = 0 24.32.652.567 I slot print_timing: id 1 | task 26181 | prompt eval time = 4244.18 ms / 777 tokens ( 5.46 ms per token, 183.07 tokens per second) 24.32.652.570 I slot print_timing: id 1 | task 26181 | eval time = 47.47 ms / 2 tokens ( 47.47 ms per token, 21.07 tokens per second) 24.32.652.570 I slot print_timing: id 1 | task 26181 | total time = 4291.65 ms / 779 tokens 24.32.652.570 I slot print_timing: id 1 | task 26181 | graphs reused = 24881 24.32.652.571 I slot print_timing: id 1 | task 26181 | graph reallocs = 0 / 0 (same size) / (changed size) 24.32.652.608 I slot release: id 1 | task 26181 | stop processing: n_tokens = 778, truncated = 0 24.32.652.895 I slot print_timing: id 2 | task 26183 | prompt eval time = 4244.42 ms / 517 tokens ( 8.21 ms per token, 121.81 tokens per second) 24.32.652.897 I slot print_timing: id 2 | task 26183 | eval time = 47.49 ms / 2 tokens ( 47.49 ms per token, 21.06 tokens per second) 24.32.652.898 I slot print_timing: id 2 | task 26183 | total time = 4291.91 ms / 519 tokens 24.32.652.898 I slot print_timing: id 2 | task 26183 | graphs reused = 24881 24.32.652.898 I slot print_timing: id 2 | task 26183 | graph reallocs = 0 / 0 (same size) / (changed size) 24.32.652.953 I slot release: id 2 | task 26183 | stop processing: n_tokens = 899, truncated = 0 24.32.653.231 I slot print_timing: id 3 | task 26184 | prompt eval time = 4244.77 ms / 945 tokens ( 4.49 ms per token, 222.63 tokens per second) 24.32.653.234 I slot print_timing: id 3 | task 26184 | eval time = 47.38 ms / 2 tokens ( 47.38 ms per token, 21.10 tokens per second) 24.32.653.235 I slot print_timing: id 3 | task 26184 | total time = 4292.15 ms / 947 tokens 24.32.653.235 I slot print_timing: id 3 | task 26184 | graphs reused = 24881 24.32.653.235 I slot print_timing: id 3 | task 26184 | graph reallocs = 0 / 0 (same size) / (changed size) 24.32.653.282 I slot release: id 3 | task 26184 | stop processing: n_tokens = 946, truncated = 0 24.32.659.491 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.871 24.32.659.513 I slot launch_slot_: id 3 | task 26189 | processing task, is_child = 0 24.32.666.039 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 343833487991 24.32.666.108 I slot launch_slot_: id 0 | task 26190 | processing task, is_child = 0 24.32.666.193 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 343833488306 24.32.666.250 I slot launch_slot_: id 1 | task 26191 | processing task, is_child = 0 24.32.666.295 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 343833488651 24.32.666.355 I slot launch_slot_: id 2 | task 26192 | processing task, is_child = 0 24.37.562.067 I slot print_timing: id 0 | task 26190 | prompt processing, n_tokens = 919, progress = 1.00, t = 4.90 s / 187.73 tokens per second 24.37.562.243 I slot print_timing: id 1 | task 26191 | prompt processing, n_tokens = 876, progress = 1.00, t = 4.90 s / 178.95 tokens per second 24.37.562.406 I slot print_timing: id 2 | task 26192 | prompt processing, n_tokens = 908, progress = 1.00, t = 4.90 s / 185.48 tokens per second 24.37.682.849 I slot print_timing: id 3 | task 26189 | prompt eval time = 4895.54 ms / 500 tokens ( 9.79 ms per token, 102.13 tokens per second) 24.37.682.851 I slot print_timing: id 3 | task 26189 | eval time = 120.79 ms / 2 tokens ( 120.79 ms per token, 8.28 tokens per second) 24.37.682.852 I slot print_timing: id 3 | task 26189 | total time = 5016.33 ms / 502 tokens 24.37.682.853 I slot print_timing: id 3 | task 26189 | graphs reused = 24882 24.37.682.853 I slot print_timing: id 3 | task 26189 | graph reallocs = 0 / 0 (same size) / (changed size) 24.37.682.931 I slot release: id 3 | task 26189 | stop processing: n_tokens = 930, truncated = 0 24.37.719.971 I slot print_timing: id 0 | task 26190 | prompt eval time = 5015.52 ms / 923 tokens ( 5.43 ms per token, 184.03 tokens per second) 24.37.719.973 I slot print_timing: id 0 | task 26190 | eval time = 38.09 ms / 2 tokens ( 38.09 ms per token, 26.25 tokens per second) 24.37.719.973 I slot print_timing: id 0 | task 26190 | total time = 5053.61 ms / 925 tokens 24.37.719.974 I slot print_timing: id 0 | task 26190 | graphs reused = 24882 24.37.719.974 I slot print_timing: id 0 | task 26190 | graph reallocs = 0 / 0 (same size) / (changed size) 24.37.720.020 I slot release: id 0 | task 26190 | stop processing: n_tokens = 924, truncated = 0 24.37.720.291 I slot print_timing: id 1 | task 26191 | prompt eval time = 5015.82 ms / 880 tokens ( 5.70 ms per token, 175.45 tokens per second) 24.37.720.294 I slot print_timing: id 1 | task 26191 | eval time = 38.06 ms / 2 tokens ( 38.06 ms per token, 26.27 tokens per second) 24.37.720.294 I slot print_timing: id 1 | task 26191 | total time = 5053.88 ms / 882 tokens 24.37.720.294 I slot print_timing: id 1 | task 26191 | graphs reused = 24882 24.37.720.295 I slot print_timing: id 1 | task 26191 | graph reallocs = 0 / 0 (same size) / (changed size) 24.37.720.343 I slot release: id 1 | task 26191 | stop processing: n_tokens = 881, truncated = 0 24.37.720.634 I slot print_timing: id 2 | task 26192 | prompt eval time = 5016.10 ms / 912 tokens ( 5.50 ms per token, 181.81 tokens per second) 24.37.720.637 I slot print_timing: id 2 | task 26192 | eval time = 38.07 ms / 2 tokens ( 38.07 ms per token, 26.27 tokens per second) 24.37.720.637 I slot print_timing: id 2 | task 26192 | total time = 5054.17 ms / 914 tokens 24.37.720.637 I slot print_timing: id 2 | task 26192 | graphs reused = 24882 24.37.720.638 I slot print_timing: id 2 | task 26192 | graph reallocs = 0 / 0 (same size) / (changed size) 24.37.720.676 I slot release: id 2 | task 26192 | stop processing: n_tokens = 913, truncated = 0 24.37.720.681 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.891 (> 0.100 thold), f_keep = 0.894 24.37.720.706 I slot launch_slot_: id 1 | task 26197 | processing task, is_child = 0 24.37.729.000 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 930, t_last = 343838518630 24.37.729.079 I slot launch_slot_: id 3 | task 26198 | processing task, is_child = 0 24.37.729.175 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 24.37.729.190 I slot launch_slot_: id 2 | task 26199 | processing task, is_child = 0 24.37.729.235 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 924, t_last = 343838555718 24.37.730.803 I slot launch_slot_: id 0 | task 26200 | processing task, is_child = 0 24.41.630.849 I slot print_timing: id 1 | task 26197 | prompt processing, n_tokens = 516, progress = 1.00, t = 3.90 s / 132.33 tokens per second 24.41.631.010 I slot print_timing: id 3 | task 26198 | prompt processing, n_tokens = 1168, progress = 1.00, t = 3.90 s / 299.56 tokens per second 24.41.752.041 I slot print_timing: id 0 | task 26200 | prompt eval time = 3899.71 ms / 474 tokens ( 8.23 ms per token, 121.55 tokens per second) 24.41.752.043 I slot print_timing: id 0 | task 26200 | eval time = 121.52 ms / 2 tokens ( 121.52 ms per token, 8.23 tokens per second) 24.41.752.044 I slot print_timing: id 0 | task 26200 | total time = 4021.23 ms / 476 tokens 24.41.752.044 I slot print_timing: id 0 | task 26200 | graphs reused = 24882 24.41.752.045 I slot print_timing: id 0 | task 26200 | graph reallocs = 0 / 0 (same size) / (changed size) 24.41.752.111 I slot release: id 0 | task 26200 | stop processing: n_tokens = 871, truncated = 0 24.41.752.890 I slot print_timing: id 2 | task 26199 | prompt eval time = 3899.84 ms / 486 tokens ( 8.02 ms per token, 124.62 tokens per second) 24.41.752.893 I slot print_timing: id 2 | task 26199 | eval time = 122.05 ms / 2 tokens ( 122.05 ms per token, 8.19 tokens per second) 24.41.752.893 I slot print_timing: id 2 | task 26199 | total time = 4021.89 ms / 488 tokens 24.41.752.894 I slot print_timing: id 2 | task 26199 | graphs reused = 24882 24.41.752.894 I slot print_timing: id 2 | task 26199 | graph reallocs = 0 / 0 (same size) / (changed size) 24.41.752.944 I slot release: id 2 | task 26199 | stop processing: n_tokens = 883, truncated = 0 24.41.788.586 I slot print_timing: id 1 | task 26197 | prompt eval time = 4021.58 ms / 520 tokens ( 7.73 ms per token, 129.30 tokens per second) 24.41.788.593 I slot print_timing: id 1 | task 26197 | eval time = 36.08 ms / 2 tokens ( 36.08 ms per token, 27.71 tokens per second) 24.41.788.594 I slot print_timing: id 1 | task 26197 | total time = 4057.66 ms / 522 tokens 24.41.788.595 I slot print_timing: id 1 | task 26197 | graphs reused = 24882 24.41.788.595 I slot print_timing: id 1 | task 26197 | graph reallocs = 0 / 0 (same size) / (changed size) 24.41.788.670 I slot release: id 1 | task 26197 | stop processing: n_tokens = 885, truncated = 0 24.41.789.154 I slot print_timing: id 3 | task 26198 | prompt eval time = 4022.34 ms / 1172 tokens ( 3.43 ms per token, 291.37 tokens per second) 24.41.789.158 I slot print_timing: id 3 | task 26198 | eval time = 35.72 ms / 2 tokens ( 35.72 ms per token, 28.00 tokens per second) 24.41.789.158 I slot print_timing: id 3 | task 26198 | total time = 4058.06 ms / 1174 tokens 24.41.789.159 I slot print_timing: id 3 | task 26198 | graphs reused = 24882 24.41.789.159 I slot print_timing: id 3 | task 26198 | graph reallocs = 0 / 0 (same size) / (changed size) 24.41.789.245 I slot release: id 3 | task 26198 | stop processing: n_tokens = 1173, truncated = 0 24.41.789.252 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.835 (> 0.100 thold), f_keep = 0.883 24.41.789.287 I slot launch_slot_: id 3 | task 26205 | processing task, is_child = 0 24.41.796.863 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 343842587810 24.41.796.963 I slot launch_slot_: id 0 | task 26206 | processing task, is_child = 0 24.42.797.755 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 343842588642 24.42.797.863 I slot launch_slot_: id 2 | task 26208 | processing task, is_child = 0 24.42.797.912 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 885, t_last = 343842624368 24.42.797.990 I slot launch_slot_: id 1 | task 26209 | processing task, is_child = 0 24.45.090.716 I slot print_timing: id 0 | task 26206 | prompt processing, n_tokens = 1175, progress = 1.00, t = 3.29 s / 356.75 tokens per second 24.48.791.186 I slot print_timing: id 1 | task 26209 | prompt processing, n_tokens = 2076, progress = 0.80, t = 5.76 s / 360.65 tokens per second 24.48.791.244 I slot print_timing: id 2 | task 26208 | prompt processing, n_tokens = 1504, progress = 0.60, t = 3.01 s / 499.96 tokens per second 24.51.258.349 I slot print_timing: id 0 | task 26206 | prompt eval time = 6994.08 ms / 1179 tokens ( 5.93 ms per token, 168.57 tokens per second) 24.51.258.354 I slot print_timing: id 0 | task 26206 | eval time = 2467.18 ms / 2 tokens ( 2467.18 ms per token, 0.41 tokens per second) 24.51.258.355 I slot print_timing: id 0 | task 26206 | total time = 9461.26 ms / 1181 tokens 24.51.258.355 I slot print_timing: id 0 | task 26206 | graphs reused = 24882 24.51.258.356 I slot print_timing: id 0 | task 26206 | graph reallocs = 0 / 0 (same size) / (changed size) 24.51.258.423 I slot release: id 0 | task 26206 | stop processing: n_tokens = 1180, truncated = 0 24.51.258.436 I slot print_timing: id 1 | task 26209 | prompt processing, n_tokens = 2588, progress = 1.00, t = 8.22 s / 314.71 tokens per second 24.51.258.823 I slot print_timing: id 2 | task 26208 | prompt processing, n_tokens = 1983, progress = 0.79, t = 5.48 s / 362.16 tokens per second 24.51.258.887 I slot print_timing: id 3 | task 26205 | prompt processing, n_tokens = 580, progress = 1.00, t = 9.46 s / 61.31 tokens per second 24.52.069.538 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1180, t_last = 343852094121 24.52.074.499 I slot launch_slot_: id 0 | task 26214 | processing task, is_child = 0 24.54.871.318 I slot print_timing: id 1 | task 26209 | prompt eval time = 9034.67 ms / 2592 tokens ( 3.49 ms per token, 286.89 tokens per second) 24.54.871.321 I slot print_timing: id 1 | task 26209 | eval time = 2802.10 ms / 2 tokens ( 2802.10 ms per token, 0.36 tokens per second) 24.54.871.322 I slot print_timing: id 1 | task 26209 | total time = 11836.76 ms / 2594 tokens 24.54.871.322 I slot print_timing: id 1 | task 26209 | graphs reused = 24882 24.54.871.322 I slot print_timing: id 1 | task 26209 | graph reallocs = 0 / 0 (same size) / (changed size) 24.54.871.458 I slot release: id 1 | task 26209 | stop processing: n_tokens = 2593, truncated = 0 24.54.871.810 I slot print_timing: id 3 | task 26205 | prompt eval time = 10272.36 ms / 584 tokens ( 17.59 ms per token, 56.85 tokens per second) 24.54.871.813 I slot print_timing: id 3 | task 26205 | eval time = 2802.27 ms / 2 tokens ( 2802.27 ms per token, 0.36 tokens per second) 24.54.871.813 I slot print_timing: id 3 | task 26205 | total time = 13074.63 ms / 586 tokens 24.54.871.814 I slot print_timing: id 3 | task 26205 | graphs reused = 24882 24.54.871.814 I slot print_timing: id 3 | task 26205 | graph reallocs = 0 / 0 (same size) / (changed size) 24.54.871.877 I slot release: id 3 | task 26205 | stop processing: n_tokens = 1241, truncated = 0 24.54.871.899 I slot print_timing: id 2 | task 26208 | prompt processing, n_tokens = 2495, progress = 1.00, t = 6.29 s / 396.89 tokens per second 24.55.265.403 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2593, t_last = 343855707157 24.55.274.740 I slot launch_slot_: id 1 | task 26217 | processing task, is_child = 0 24.55.277.863 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1241, t_last = 343855707577 24.55.279.633 I slot launch_slot_: id 3 | task 26218 | processing task, is_child = 0 24.55.279.643 I slot print_timing: id 0 | task 26214 | prompt processing, n_tokens = 2230, progress = 0.81, t = 3.19 s / 698.93 tokens per second 24.57.953.089 I slot print_timing: id 2 | task 26208 | prompt eval time = 9482.85 ms / 2499 tokens ( 3.79 ms per token, 263.53 tokens per second) 24.57.953.092 I slot print_timing: id 2 | task 26208 | eval time = 2687.69 ms / 2 tokens ( 2687.69 ms per token, 0.37 tokens per second) 24.57.953.093 I slot print_timing: id 2 | task 26208 | total time = 12170.54 ms / 2501 tokens 24.57.953.093 I slot print_timing: id 2 | task 26208 | graphs reused = 24882 24.57.953.094 I slot print_timing: id 2 | task 26208 | graph reallocs = 0 / 0 (same size) / (changed size) 24.57.953.241 I slot release: id 2 | task 26208 | stop processing: n_tokens = 2500, truncated = 0 24.57.953.257 I slot print_timing: id 0 | task 26214 | prompt processing, n_tokens = 2742, progress = 1.00, t = 5.88 s / 466.46 tokens per second 24.59.427.137 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2500, t_last = 343858788940 24.59.429.744 I slot launch_slot_: id 2 | task 26221 | processing task, is_child = 0 24.59.429.756 I slot print_timing: id 1 | task 26217 | prompt processing, n_tokens = 1755, progress = 1.00, t = 4.15 s / 423.19 tokens per second 24.59.430.186 I slot print_timing: id 3 | task 26218 | prompt processing, n_tokens = 562, progress = 1.00, t = 4.15 s / 135.52 tokens per second 25.01.366.162 I slot print_timing: id 0 | task 26214 | prompt eval time = 7352.62 ms / 2746 tokens ( 2.68 ms per token, 373.47 tokens per second) 25.01.366.165 I slot print_timing: id 0 | task 26214 | eval time = 1939.03 ms / 2 tokens ( 1939.03 ms per token, 0.52 tokens per second) 25.01.366.166 I slot print_timing: id 0 | task 26214 | total time = 9291.65 ms / 2748 tokens 25.01.366.166 I slot print_timing: id 0 | task 26214 | graphs reused = 24882 25.01.366.167 I slot print_timing: id 0 | task 26214 | graph reallocs = 0 / 0 (same size) / (changed size) 25.01.366.306 I slot release: id 0 | task 26214 | stop processing: n_tokens = 2747, truncated = 0 25.02.108.232 I slot print_timing: id 1 | task 26217 | prompt eval time = 6087.02 ms / 1759 tokens ( 3.46 ms per token, 288.98 tokens per second) 25.02.108.234 I slot print_timing: id 1 | task 26217 | eval time = 741.51 ms / 2 tokens ( 741.51 ms per token, 1.35 tokens per second) 25.02.108.235 I slot print_timing: id 1 | task 26217 | total time = 6828.54 ms / 1761 tokens 25.02.108.235 I slot print_timing: id 1 | task 26217 | graphs reused = 24882 25.02.108.236 I slot print_timing: id 1 | task 26217 | graph reallocs = 0 / 0 (same size) / (changed size) 25.02.108.337 I slot release: id 1 | task 26217 | stop processing: n_tokens = 1760, truncated = 0 25.02.108.687 I slot print_timing: id 3 | task 26218 | prompt eval time = 6087.34 ms / 566 tokens ( 10.76 ms per token, 92.98 tokens per second) 25.02.108.690 I slot print_timing: id 3 | task 26218 | eval time = 741.48 ms / 2 tokens ( 741.48 ms per token, 1.35 tokens per second) 25.02.108.690 I slot print_timing: id 3 | task 26218 | total time = 6828.82 ms / 568 tokens 25.02.108.691 I slot print_timing: id 3 | task 26218 | graphs reused = 24882 25.02.108.691 I slot print_timing: id 3 | task 26218 | graph reallocs = 0 / 0 (same size) / (changed size) 25.02.108.812 I slot release: id 3 | task 26218 | stop processing: n_tokens = 2643, truncated = 0 25.02.108.819 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.728 (> 0.100 thold), f_keep = 0.830 25.02.108.855 I slot launch_slot_: id 1 | task 26224 | processing task, is_child = 0 25.02.124.810 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2747, t_last = 343862202004 25.02.124.956 I slot launch_slot_: id 0 | task 26225 | processing task, is_child = 0 25.02.125.061 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2643, t_last = 343862944511 25.02.125.184 I slot launch_slot_: id 3 | task 26226 | processing task, is_child = 0 25.05.155.942 I slot print_timing: id 0 | task 26225 | prompt processing, n_tokens = 1313, progress = 0.72, t = 3.03 s / 433.27 tokens per second 25.05.155.996 I slot print_timing: id 1 | task 26224 | prompt processing, n_tokens = 246, progress = 0.74, t = 3.03 s / 81.18 tokens per second 25.05.156.040 I slot print_timing: id 3 | task 26226 | prompt processing, n_tokens = 485, progress = 0.25, t = 3.03 s / 160.07 tokens per second 25.07.837.360 I slot print_timing: id 2 | task 26221 | prompt eval time = 5725.91 ms / 1811 tokens ( 3.16 ms per token, 316.28 tokens per second) 25.07.837.362 I slot print_timing: id 2 | task 26221 | eval time = 2681.43 ms / 2 tokens ( 2681.43 ms per token, 0.37 tokens per second) 25.07.837.363 I slot print_timing: id 2 | task 26221 | total time = 8407.34 ms / 1813 tokens 25.07.837.363 I slot print_timing: id 2 | task 26221 | graphs reused = 24882 25.07.837.364 I slot print_timing: id 2 | task 26221 | graph reallocs = 0 / 0 (same size) / (changed size) 25.07.837.470 I slot release: id 2 | task 26221 | stop processing: n_tokens = 1812, truncated = 0 25.07.837.488 I slot print_timing: id 0 | task 26225 | prompt processing, n_tokens = 1825, progress = 1.00, t = 5.71 s / 319.51 tokens per second 25.07.837.781 I slot print_timing: id 1 | task 26224 | prompt processing, n_tokens = 758, progress = 1.00, t = 5.71 s / 132.71 tokens per second 25.07.838.108 I slot print_timing: id 3 | task 26226 | prompt processing, n_tokens = 1392, progress = 0.73, t = 5.71 s / 243.73 tokens per second 25.08.610.346 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.836 (> 0.100 thold), f_keep = 0.806 25.08.610.380 I slot launch_slot_: id 2 | task 26230 | processing task, is_child = 0 25.08.610.540 I slot print_timing: id 3 | task 26226 | prompt processing, n_tokens = 1904, progress = 1.00, t = 6.48 s / 293.66 tokens per second 25.09.334.823 I slot print_timing: id 0 | task 26225 | prompt eval time = 6484.73 ms / 1829 tokens ( 3.55 ms per token, 282.05 tokens per second) 25.09.334.828 I slot print_timing: id 0 | task 26225 | eval time = 724.90 ms / 2 tokens ( 724.90 ms per token, 1.38 tokens per second) 25.09.334.828 I slot print_timing: id 0 | task 26225 | total time = 7209.63 ms / 1831 tokens 25.09.334.829 I slot print_timing: id 0 | task 26225 | graphs reused = 24882 25.09.334.829 I slot print_timing: id 0 | task 26225 | graph reallocs = 0 / 0 (same size) / (changed size) 25.09.334.936 I slot release: id 0 | task 26225 | stop processing: n_tokens = 1830, truncated = 0 25.09.335.252 I slot print_timing: id 1 | task 26224 | prompt eval time = 6484.97 ms / 762 tokens ( 8.51 ms per token, 117.50 tokens per second) 25.09.335.254 I slot print_timing: id 1 | task 26224 | eval time = 724.91 ms / 2 tokens ( 724.91 ms per token, 1.38 tokens per second) 25.09.335.255 I slot print_timing: id 1 | task 26224 | total time = 7209.88 ms / 764 tokens 25.09.335.255 I slot print_timing: id 1 | task 26224 | graphs reused = 24882 25.09.335.255 I slot print_timing: id 1 | task 26224 | graph reallocs = 0 / 0 (same size) / (changed size) 25.09.335.342 I slot release: id 1 | task 26224 | stop processing: n_tokens = 2006, truncated = 0 25.09.395.008 I slot print_timing: id 3 | task 26226 | prompt eval time = 7209.97 ms / 1908 tokens ( 3.78 ms per token, 264.63 tokens per second) 25.09.395.012 I slot print_timing: id 3 | task 26226 | eval time = 59.29 ms / 2 tokens ( 59.29 ms per token, 16.87 tokens per second) 25.09.395.013 I slot print_timing: id 3 | task 26226 | total time = 7269.26 ms / 1910 tokens 25.09.395.013 I slot print_timing: id 3 | task 26226 | graphs reused = 24882 25.09.395.013 I slot print_timing: id 3 | task 26226 | graph reallocs = 0 / 0 (same size) / (changed size) 25.09.395.103 I slot release: id 3 | task 26226 | stop processing: n_tokens = 1909, truncated = 0 25.09.395.109 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1830, t_last = 343870170635 25.09.401.312 I slot launch_slot_: id 0 | task 26233 | processing task, is_child = 0 25.09.412.476 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2006, t_last = 343870171041 25.09.412.585 I slot launch_slot_: id 1 | task 26234 | processing task, is_child = 0 25.09.412.669 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1909, t_last = 343870230802 25.09.412.770 I slot launch_slot_: id 3 | task 26235 | processing task, is_child = 0 25.10.558.297 I slot print_timing: id 2 | task 26230 | prompt eval time = 784.34 ms / 452 tokens ( 1.74 ms per token, 576.28 tokens per second) 25.10.558.299 I slot print_timing: id 2 | task 26230 | eval time = 1163.56 ms / 2 tokens ( 1163.56 ms per token, 0.86 tokens per second) 25.10.558.300 I slot print_timing: id 2 | task 26230 | total time = 1947.90 ms / 454 tokens 25.10.558.301 I slot print_timing: id 2 | task 26230 | graphs reused = 24882 25.10.558.301 I slot print_timing: id 2 | task 26230 | graph reallocs = 0 / 0 (same size) / (changed size) 25.10.558.411 I slot release: id 2 | task 26230 | stop processing: n_tokens = 1748, truncated = 0 25.11.922.915 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1748, t_last = 343871394109 25.12.602.854 I slot launch_slot_: id 2 | task 26238 | processing task, is_child = 0 25.13.823.436 I slot print_timing: id 0 | task 26233 | prompt eval time = 3676.40 ms / 733 tokens ( 5.02 ms per token, 199.38 tokens per second) 25.13.823.438 I slot print_timing: id 0 | task 26233 | eval time = 734.25 ms / 2 tokens ( 734.25 ms per token, 1.36 tokens per second) 25.13.823.438 I slot print_timing: id 0 | task 26233 | total time = 4410.65 ms / 735 tokens 25.13.823.439 I slot print_timing: id 0 | task 26233 | graphs reused = 24882 25.13.823.439 I slot print_timing: id 0 | task 26233 | graph reallocs = 0 / 0 (same size) / (changed size) 25.13.823.484 I slot release: id 0 | task 26233 | stop processing: n_tokens = 734, truncated = 0 25.13.823.834 I slot print_timing: id 1 | task 26234 | prompt eval time = 3676.63 ms / 711 tokens ( 5.17 ms per token, 193.38 tokens per second) 25.13.823.840 I slot print_timing: id 1 | task 26234 | eval time = 734.30 ms / 2 tokens ( 734.30 ms per token, 1.36 tokens per second) 25.13.823.840 I slot print_timing: id 1 | task 26234 | total time = 4410.93 ms / 713 tokens 25.13.823.841 I slot print_timing: id 1 | task 26234 | graphs reused = 24882 25.13.823.841 I slot print_timing: id 1 | task 26234 | graph reallocs = 0 / 0 (same size) / (changed size) 25.13.823.875 I slot release: id 1 | task 26234 | stop processing: n_tokens = 712, truncated = 0 25.13.824.233 I slot print_timing: id 3 | task 26235 | prompt eval time = 3676.81 ms / 744 tokens ( 4.94 ms per token, 202.35 tokens per second) 25.13.824.242 I slot print_timing: id 3 | task 26235 | eval time = 734.39 ms / 2 tokens ( 734.39 ms per token, 1.36 tokens per second) 25.13.824.242 I slot print_timing: id 3 | task 26235 | total time = 4411.21 ms / 746 tokens 25.13.824.243 I slot print_timing: id 3 | task 26235 | graphs reused = 24882 25.13.824.243 I slot print_timing: id 3 | task 26235 | graph reallocs = 0 / 0 (same size) / (changed size) 25.13.824.290 I slot release: id 3 | task 26235 | stop processing: n_tokens = 745, truncated = 0 25.13.866.893 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 25.13.866.925 I slot launch_slot_: id 0 | task 26242 | processing task, is_child = 0 25.13.870.837 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 712, t_last = 343874659573 25.13.870.905 I slot launch_slot_: id 1 | task 26243 | processing task, is_child = 0 25.13.870.948 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 745, t_last = 343874659988 25.13.871.010 I slot launch_slot_: id 3 | task 26244 | processing task, is_child = 0 25.15.919.337 I slot print_timing: id 2 | task 26238 | prompt eval time = 1263.67 ms / 710 tokens ( 1.78 ms per token, 561.86 tokens per second) 25.15.919.339 I slot print_timing: id 2 | task 26238 | eval time = 2052.44 ms / 2 tokens ( 2052.44 ms per token, 0.49 tokens per second) 25.15.919.340 I slot print_timing: id 2 | task 26238 | total time = 3316.11 ms / 712 tokens 25.15.919.340 I slot print_timing: id 2 | task 26238 | graphs reused = 24882 25.15.919.341 I slot print_timing: id 2 | task 26238 | graph reallocs = 0 / 0 (same size) / (changed size) 25.15.919.383 I slot release: id 2 | task 26238 | stop processing: n_tokens = 711, truncated = 0 25.17.353.490 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 343876755081 25.17.356.949 I slot launch_slot_: id 2 | task 26247 | processing task, is_child = 0 25.17.356.982 I slot print_timing: id 1 | task 26243 | prompt processing, n_tokens = 785, progress = 0.99, t = 3.48 s / 225.44 tokens per second 25.17.357.240 I slot print_timing: id 3 | task 26244 | prompt processing, n_tokens = 1036, progress = 1.00, t = 3.48 s / 297.53 tokens per second 25.17.912.263 I slot print_timing: id 0 | task 26242 | prompt eval time = 3482.47 ms / 509 tokens ( 6.84 ms per token, 146.16 tokens per second) 25.17.912.265 I slot print_timing: id 0 | task 26242 | eval time = 558.78 ms / 2 tokens ( 558.78 ms per token, 1.79 tokens per second) 25.17.912.266 I slot print_timing: id 0 | task 26242 | total time = 4041.25 ms / 511 tokens 25.17.912.266 I slot print_timing: id 0 | task 26242 | graphs reused = 24882 25.17.912.267 I slot print_timing: id 0 | task 26242 | graph reallocs = 0 / 0 (same size) / (changed size) 25.17.912.312 I slot release: id 0 | task 26242 | stop processing: n_tokens = 727, truncated = 0 25.18.637.868 I slot print_timing: id 1 | task 26243 | prompt eval time = 4041.47 ms / 789 tokens ( 5.12 ms per token, 195.23 tokens per second) 25.18.637.871 I slot print_timing: id 1 | task 26243 | eval time = 725.25 ms / 2 tokens ( 725.25 ms per token, 1.38 tokens per second) 25.18.637.872 I slot print_timing: id 1 | task 26243 | total time = 4766.73 ms / 791 tokens 25.18.637.872 I slot print_timing: id 1 | task 26243 | graphs reused = 24882 25.18.637.872 I slot print_timing: id 1 | task 26243 | graph reallocs = 0 / 0 (same size) / (changed size) 25.18.637.921 I slot release: id 1 | task 26243 | stop processing: n_tokens = 790, truncated = 0 25.18.638.266 I slot print_timing: id 3 | task 26244 | prompt eval time = 4041.85 ms / 1040 tokens ( 3.89 ms per token, 257.31 tokens per second) 25.18.638.268 I slot print_timing: id 3 | task 26244 | eval time = 725.23 ms / 2 tokens ( 725.23 ms per token, 1.38 tokens per second) 25.18.638.269 I slot print_timing: id 3 | task 26244 | total time = 4767.08 ms / 1042 tokens 25.18.638.269 I slot print_timing: id 3 | task 26244 | graphs reused = 24882 25.18.638.269 I slot print_timing: id 3 | task 26244 | graph reallocs = 0 / 0 (same size) / (changed size) 25.18.638.323 I slot release: id 3 | task 26244 | stop processing: n_tokens = 1041, truncated = 0 25.18.638.328 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 343878748010 25.18.641.585 I slot launch_slot_: id 0 | task 26250 | processing task, is_child = 0 25.18.646.775 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 343879473619 25.18.646.862 I slot launch_slot_: id 1 | task 26251 | processing task, is_child = 0 25.18.646.910 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1041, t_last = 343879474021 25.18.646.976 I slot launch_slot_: id 3 | task 26252 | processing task, is_child = 0 25.22.208.538 I slot print_timing: id 2 | task 26247 | prompt eval time = 2778.17 ms / 784 tokens ( 3.54 ms per token, 282.20 tokens per second) 25.22.208.540 I slot print_timing: id 2 | task 26247 | eval time = 2073.18 ms / 2 tokens ( 2073.18 ms per token, 0.48 tokens per second) 25.22.208.540 I slot print_timing: id 2 | task 26247 | total time = 4851.35 ms / 786 tokens 25.22.208.541 I slot print_timing: id 2 | task 26247 | graphs reused = 24882 25.22.208.541 I slot print_timing: id 2 | task 26247 | graph reallocs = 0 / 0 (same size) / (changed size) 25.22.208.599 I slot release: id 2 | task 26247 | stop processing: n_tokens = 785, truncated = 0 25.22.208.614 I slot print_timing: id 0 | task 26250 | prompt processing, n_tokens = 772, progress = 0.99, t = 3.56 s / 216.78 tokens per second 25.22.208.766 I slot print_timing: id 1 | task 26251 | prompt processing, n_tokens = 827, progress = 1.00, t = 3.56 s / 232.23 tokens per second 25.22.208.910 I slot print_timing: id 3 | task 26252 | prompt processing, n_tokens = 821, progress = 1.00, t = 3.56 s / 230.56 tokens per second 25.22.320.846 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 785, t_last = 343883044297 25.22.323.889 I slot launch_slot_: id 2 | task 26256 | processing task, is_child = 0 25.22.906.756 I slot print_timing: id 0 | task 26250 | prompt eval time = 3673.07 ms / 776 tokens ( 4.73 ms per token, 211.27 tokens per second) 25.22.906.761 I slot print_timing: id 0 | task 26250 | eval time = 586.69 ms / 2 tokens ( 586.69 ms per token, 1.70 tokens per second) 25.22.906.761 I slot print_timing: id 0 | task 26250 | total time = 4259.77 ms / 778 tokens 25.22.906.762 I slot print_timing: id 0 | task 26250 | graphs reused = 24882 25.22.906.762 I slot print_timing: id 0 | task 26250 | graph reallocs = 0 / 0 (same size) / (changed size) 25.22.906.808 I slot release: id 0 | task 26250 | stop processing: n_tokens = 777, truncated = 0 25.22.907.244 I slot print_timing: id 1 | task 26251 | prompt eval time = 3673.38 ms / 831 tokens ( 4.42 ms per token, 226.22 tokens per second) 25.22.907.246 I slot print_timing: id 1 | task 26251 | eval time = 586.82 ms / 2 tokens ( 586.82 ms per token, 1.70 tokens per second) 25.22.907.252 I slot print_timing: id 1 | task 26251 | total time = 4260.19 ms / 833 tokens 25.22.907.253 I slot print_timing: id 1 | task 26251 | graphs reused = 24882 25.22.907.253 I slot print_timing: id 1 | task 26251 | graph reallocs = 0 / 0 (same size) / (changed size) 25.22.907.301 I slot release: id 1 | task 26251 | stop processing: n_tokens = 832, truncated = 0 25.22.907.795 I slot print_timing: id 3 | task 26252 | prompt eval time = 3673.60 ms / 825 tokens ( 4.45 ms per token, 224.58 tokens per second) 25.22.907.797 I slot print_timing: id 3 | task 26252 | eval time = 586.96 ms / 2 tokens ( 586.96 ms per token, 1.70 tokens per second) 25.22.907.797 I slot print_timing: id 3 | task 26252 | total time = 4260.55 ms / 827 tokens 25.22.907.798 I slot print_timing: id 3 | task 26252 | graphs reused = 24882 25.22.907.798 I slot print_timing: id 3 | task 26252 | graph reallocs = 0 / 0 (same size) / (changed size) 25.22.907.844 I slot release: id 3 | task 26252 | stop processing: n_tokens = 826, truncated = 0 25.23.634.762 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.892 25.23.634.791 I slot launch_slot_: id 3 | task 26260 | processing task, is_child = 0 25.23.639.868 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.885 25.23.639.890 I slot launch_slot_: id 1 | task 26261 | processing task, is_child = 0 25.23.639.935 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 777, t_last = 343883742506 25.23.639.997 I slot launch_slot_: id 0 | task 26262 | processing task, is_child = 0 25.24.398.918 I slot print_timing: id 2 | task 26256 | prompt eval time = 1310.86 ms / 885 tokens ( 1.48 ms per token, 675.13 tokens per second) 25.24.398.922 I slot print_timing: id 2 | task 26256 | eval time = 764.16 ms / 2 tokens ( 764.16 ms per token, 1.31 tokens per second) 25.24.398.922 I slot print_timing: id 2 | task 26256 | total time = 2075.02 ms / 887 tokens 25.24.398.923 I slot print_timing: id 2 | task 26256 | graphs reused = 24882 25.24.398.923 I slot print_timing: id 2 | task 26256 | graph reallocs = 0 / 0 (same size) / (changed size) 25.24.398.973 I slot release: id 2 | task 26256 | stop processing: n_tokens = 886, truncated = 0 25.25.765.886 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 886, t_last = 343885234671 25.26.446.511 I slot launch_slot_: id 2 | task 26265 | processing task, is_child = 0 25.27.751.038 I slot print_timing: id 0 | task 26262 | prompt eval time = 3374.78 ms / 677 tokens ( 4.98 ms per token, 200.61 tokens per second) 25.27.751.040 I slot print_timing: id 0 | task 26262 | eval time = 736.24 ms / 2 tokens ( 736.24 ms per token, 1.36 tokens per second) 25.27.751.041 I slot print_timing: id 0 | task 26262 | total time = 4111.02 ms / 679 tokens 25.27.751.041 I slot print_timing: id 0 | task 26262 | graphs reused = 24882 25.27.751.042 I slot print_timing: id 0 | task 26262 | graph reallocs = 0 / 0 (same size) / (changed size) 25.27.751.092 I slot release: id 0 | task 26262 | stop processing: n_tokens = 678, truncated = 0 25.27.751.428 I slot print_timing: id 1 | task 26261 | prompt eval time = 3375.03 ms / 533 tokens ( 6.33 ms per token, 157.92 tokens per second) 25.27.751.431 I slot print_timing: id 1 | task 26261 | eval time = 736.34 ms / 2 tokens ( 736.34 ms per token, 1.36 tokens per second) 25.27.751.431 I slot print_timing: id 1 | task 26261 | total time = 4111.37 ms / 535 tokens 25.27.751.431 I slot print_timing: id 1 | task 26261 | graphs reused = 24882 25.27.751.432 I slot print_timing: id 1 | task 26261 | graph reallocs = 0 / 0 (same size) / (changed size) 25.27.751.476 I slot release: id 1 | task 26261 | stop processing: n_tokens = 849, truncated = 0 25.27.751.802 I slot print_timing: id 3 | task 26260 | prompt eval time = 3375.41 ms / 583 tokens ( 5.79 ms per token, 172.72 tokens per second) 25.27.751.806 I slot print_timing: id 3 | task 26260 | eval time = 736.25 ms / 2 tokens ( 736.25 ms per token, 1.36 tokens per second) 25.27.751.806 I slot print_timing: id 3 | task 26260 | total time = 4111.67 ms / 585 tokens 25.27.751.806 I slot print_timing: id 3 | task 26260 | graphs reused = 24882 25.27.751.807 I slot print_timing: id 3 | task 26260 | graph reallocs = 0 / 0 (same size) / (changed size) 25.27.751.869 I slot release: id 3 | task 26260 | stop processing: n_tokens = 893, truncated = 0 25.27.794.238 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 343888586790 25.27.795.381 I slot launch_slot_: id 0 | task 26269 | processing task, is_child = 0 25.27.800.436 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 849, t_last = 343888587174 25.27.800.510 I slot launch_slot_: id 1 | task 26270 | processing task, is_child = 0 25.27.800.557 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 893, t_last = 343888587567 25.27.800.622 I slot launch_slot_: id 3 | task 26271 | processing task, is_child = 0 25.29.052.771 I slot print_timing: id 2 | task 26265 | prompt eval time = 1347.32 ms / 792 tokens ( 1.70 ms per token, 587.83 tokens per second) 25.29.052.773 I slot print_timing: id 2 | task 26265 | eval time = 1258.53 ms / 2 tokens ( 1258.53 ms per token, 0.79 tokens per second) 25.29.052.774 I slot print_timing: id 2 | task 26265 | total time = 2605.85 ms / 794 tokens 25.29.052.774 I slot print_timing: id 2 | task 26265 | graphs reused = 24882 25.29.052.775 I slot print_timing: id 2 | task 26265 | graph reallocs = 0 / 0 (same size) / (changed size) 25.29.052.829 I slot release: id 2 | task 26265 | stop processing: n_tokens = 793, truncated = 0 25.30.419.258 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 793, t_last = 343889888527 25.31.099.337 I slot launch_slot_: id 2 | task 26274 | processing task, is_child = 0 25.32.311.557 I slot print_timing: id 0 | task 26269 | prompt eval time = 3775.20 ms / 740 tokens ( 5.10 ms per token, 196.02 tokens per second) 25.32.311.559 I slot print_timing: id 0 | task 26269 | eval time = 735.73 ms / 2 tokens ( 735.73 ms per token, 1.36 tokens per second) 25.32.311.559 I slot print_timing: id 0 | task 26269 | total time = 4510.92 ms / 742 tokens 25.32.311.560 I slot print_timing: id 0 | task 26269 | graphs reused = 24882 25.32.311.560 I slot print_timing: id 0 | task 26269 | graph reallocs = 0 / 0 (same size) / (changed size) 25.32.311.610 I slot release: id 0 | task 26269 | stop processing: n_tokens = 741, truncated = 0 25.32.311.938 I slot print_timing: id 1 | task 26270 | prompt eval time = 3775.47 ms / 813 tokens ( 4.64 ms per token, 215.34 tokens per second) 25.32.311.941 I slot print_timing: id 1 | task 26270 | eval time = 735.78 ms / 2 tokens ( 735.78 ms per token, 1.36 tokens per second) 25.32.311.941 I slot print_timing: id 1 | task 26270 | total time = 4511.26 ms / 815 tokens 25.32.311.941 I slot print_timing: id 1 | task 26270 | graphs reused = 24882 25.32.311.942 I slot print_timing: id 1 | task 26270 | graph reallocs = 0 / 0 (same size) / (changed size) 25.32.311.991 I slot release: id 1 | task 26270 | stop processing: n_tokens = 814, truncated = 0 25.32.312.262 I slot print_timing: id 3 | task 26271 | prompt eval time = 3775.74 ms / 719 tokens ( 5.25 ms per token, 190.43 tokens per second) 25.32.312.265 I slot print_timing: id 3 | task 26271 | eval time = 735.78 ms / 2 tokens ( 735.78 ms per token, 1.36 tokens per second) 25.32.312.265 I slot print_timing: id 3 | task 26271 | total time = 4511.52 ms / 721 tokens 25.32.312.265 I slot print_timing: id 3 | task 26271 | graphs reused = 24882 25.32.312.266 I slot print_timing: id 3 | task 26271 | graph reallocs = 0 / 0 (same size) / (changed size) 25.32.312.318 I slot release: id 3 | task 26271 | stop processing: n_tokens = 720, truncated = 0 25.32.354.709 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 343893147308 25.32.357.154 I slot launch_slot_: id 0 | task 26278 | processing task, is_child = 0 25.32.360.643 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 814, t_last = 343893147689 25.32.360.717 I slot launch_slot_: id 1 | task 26279 | processing task, is_child = 0 25.32.360.762 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 343893148016 25.32.360.834 I slot launch_slot_: id 3 | task 26280 | processing task, is_child = 0 25.33.425.435 I slot print_timing: id 2 | task 26274 | prompt eval time = 1254.99 ms / 694 tokens ( 1.81 ms per token, 552.99 tokens per second) 25.33.425.437 I slot print_timing: id 2 | task 26274 | eval time = 1070.73 ms / 2 tokens ( 1070.73 ms per token, 0.93 tokens per second) 25.33.425.438 I slot print_timing: id 2 | task 26274 | total time = 2325.71 ms / 696 tokens 25.33.425.438 I slot print_timing: id 2 | task 26274 | graphs reused = 24882 25.33.425.439 I slot print_timing: id 2 | task 26274 | graph reallocs = 0 / 0 (same size) / (changed size) 25.33.425.478 I slot release: id 2 | task 26274 | stop processing: n_tokens = 695, truncated = 0 25.34.787.642 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.881 25.34.787.676 I slot launch_slot_: id 2 | task 26283 | processing task, is_child = 0 25.36.349.080 I slot print_timing: id 0 | task 26278 | prompt eval time = 3253.00 ms / 694 tokens ( 4.69 ms per token, 213.34 tokens per second) 25.36.349.082 I slot print_timing: id 0 | task 26278 | eval time = 735.24 ms / 2 tokens ( 735.24 ms per token, 1.36 tokens per second) 25.36.349.083 I slot print_timing: id 0 | task 26278 | total time = 3988.24 ms / 696 tokens 25.36.349.083 I slot print_timing: id 0 | task 26278 | graphs reused = 24882 25.36.349.084 I slot print_timing: id 0 | task 26278 | graph reallocs = 0 / 0 (same size) / (changed size) 25.36.349.132 I slot release: id 0 | task 26278 | stop processing: n_tokens = 695, truncated = 0 25.36.349.413 I slot print_timing: id 1 | task 26279 | prompt eval time = 3253.32 ms / 718 tokens ( 4.53 ms per token, 220.70 tokens per second) 25.36.349.416 I slot print_timing: id 1 | task 26279 | eval time = 735.18 ms / 2 tokens ( 735.18 ms per token, 1.36 tokens per second) 25.36.349.416 I slot print_timing: id 1 | task 26279 | total time = 3988.51 ms / 720 tokens 25.36.349.416 I slot print_timing: id 1 | task 26279 | graphs reused = 24882 25.36.349.417 I slot print_timing: id 1 | task 26279 | graph reallocs = 0 / 0 (same size) / (changed size) 25.36.349.455 I slot release: id 1 | task 26279 | stop processing: n_tokens = 719, truncated = 0 25.36.349.742 I slot print_timing: id 3 | task 26280 | prompt eval time = 3253.69 ms / 693 tokens ( 4.70 ms per token, 212.99 tokens per second) 25.36.349.744 I slot print_timing: id 3 | task 26280 | eval time = 735.10 ms / 2 tokens ( 735.10 ms per token, 1.36 tokens per second) 25.36.349.744 I slot print_timing: id 3 | task 26280 | total time = 3988.78 ms / 695 tokens 25.36.349.744 I slot print_timing: id 3 | task 26280 | graphs reused = 24882 25.36.349.744 I slot print_timing: id 3 | task 26280 | graph reallocs = 0 / 0 (same size) / (changed size) 25.36.349.786 I slot release: id 3 | task 26280 | stop processing: n_tokens = 694, truncated = 0 25.36.392.047 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.885 25.36.392.077 I slot launch_slot_: id 3 | task 26287 | processing task, is_child = 0 25.36.395.933 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.881 25.36.395.954 I slot launch_slot_: id 0 | task 26288 | processing task, is_child = 0 25.36.395.997 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.851 25.36.396.014 I slot launch_slot_: id 1 | task 26289 | processing task, is_child = 0 25.37.855.396 I slot print_timing: id 2 | task 26283 | prompt eval time = 925.50 ms / 518 tokens ( 1.79 ms per token, 559.70 tokens per second) 25.37.855.399 I slot print_timing: id 2 | task 26283 | eval time = 1463.35 ms / 2 tokens ( 1463.35 ms per token, 0.68 tokens per second) 25.37.855.400 I slot print_timing: id 2 | task 26283 | total time = 2388.85 ms / 520 tokens 25.37.855.400 I slot print_timing: id 2 | task 26283 | graphs reused = 24882 25.37.855.401 I slot print_timing: id 2 | task 26283 | graph reallocs = 0 / 0 (same size) / (changed size) 25.37.855.444 I slot release: id 2 | task 26283 | stop processing: n_tokens = 697, truncated = 0 25.38.645.650 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.878 25.38.645.690 I slot launch_slot_: id 2 | task 26292 | processing task, is_child = 0 25.38.745.378 I slot print_timing: id 1 | task 26289 | prompt eval time = 2249.22 ms / 486 tokens ( 4.63 ms per token, 216.08 tokens per second) 25.38.745.381 I slot print_timing: id 1 | task 26289 | eval time = 100.05 ms / 2 tokens ( 100.05 ms per token, 9.99 tokens per second) 25.38.745.382 I slot print_timing: id 1 | task 26289 | total time = 2349.27 ms / 488 tokens 25.38.745.382 I slot print_timing: id 1 | task 26289 | graphs reused = 24882 25.38.745.383 I slot print_timing: id 1 | task 26289 | graph reallocs = 0 / 0 (same size) / (changed size) 25.38.745.441 I slot release: id 1 | task 26289 | stop processing: n_tokens = 689, truncated = 0 25.38.745.800 I slot print_timing: id 3 | task 26287 | prompt eval time = 2249.44 ms / 513 tokens ( 4.38 ms per token, 228.06 tokens per second) 25.38.745.810 I slot print_timing: id 3 | task 26287 | eval time = 100.16 ms / 2 tokens ( 100.16 ms per token, 9.98 tokens per second) 25.38.745.811 I slot print_timing: id 3 | task 26287 | total time = 2349.60 ms / 515 tokens 25.38.745.811 I slot print_timing: id 3 | task 26287 | graphs reused = 24882 25.38.745.812 I slot print_timing: id 3 | task 26287 | graph reallocs = 0 / 0 (same size) / (changed size) 25.38.745.859 I slot release: id 3 | task 26287 | stop processing: n_tokens = 691, truncated = 0 25.39.443.801 I slot print_timing: id 0 | task 26288 | prompt eval time = 2348.96 ms / 523 tokens ( 4.49 ms per token, 222.65 tokens per second) 25.39.443.802 I slot print_timing: id 0 | task 26288 | eval time = 698.82 ms / 2 tokens ( 698.82 ms per token, 1.43 tokens per second) 25.39.443.803 I slot print_timing: id 0 | task 26288 | total time = 3047.78 ms / 525 tokens 25.39.443.803 I slot print_timing: id 0 | task 26288 | graphs reused = 24882 25.39.443.804 I slot print_timing: id 0 | task 26288 | graph reallocs = 0 / 0 (same size) / (changed size) 25.39.443.850 I slot release: id 0 | task 26288 | stop processing: n_tokens = 702, truncated = 0 25.39.443.858 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.872 25.39.443.894 I slot launch_slot_: id 0 | task 26295 | processing task, is_child = 0 25.39.449.328 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.837 (> 0.100 thold), f_keep = 0.888 25.39.449.355 I slot launch_slot_: id 1 | task 26296 | processing task, is_child = 0 25.40.355.830 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 691, t_last = 343899581558 25.40.355.925 I slot launch_slot_: id 3 | task 26298 | processing task, is_child = 0 25.41.655.348 I slot print_timing: id 2 | task 26292 | prompt eval time = 1709.96 ms / 518 tokens ( 3.30 ms per token, 302.93 tokens per second) 25.41.655.350 I slot print_timing: id 2 | task 26292 | eval time = 1299.52 ms / 2 tokens ( 1299.52 ms per token, 0.77 tokens per second) 25.41.655.350 I slot print_timing: id 2 | task 26292 | total time = 3009.48 ms / 520 tokens 25.41.655.351 I slot print_timing: id 2 | task 26292 | graphs reused = 24882 25.41.655.351 I slot print_timing: id 2 | task 26292 | graph reallocs = 0 / 0 (same size) / (changed size) 25.41.655.398 I slot release: id 2 | task 26292 | stop processing: n_tokens = 699, truncated = 0 25.42.400.427 I slot print_timing: id 0 | task 26295 | prompt eval time = 2205.59 ms / 506 tokens ( 4.36 ms per token, 229.42 tokens per second) 25.42.400.430 I slot print_timing: id 0 | task 26295 | eval time = 745.42 ms / 2 tokens ( 745.42 ms per token, 1.34 tokens per second) 25.42.400.430 I slot print_timing: id 0 | task 26295 | total time = 2951.01 ms / 508 tokens 25.42.400.430 I slot print_timing: id 0 | task 26295 | graphs reused = 24882 25.42.400.431 I slot print_timing: id 0 | task 26295 | graph reallocs = 0 / 0 (same size) / (changed size) 25.42.400.470 I slot release: id 0 | task 26295 | stop processing: n_tokens = 692, truncated = 0 25.42.400.900 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 699, t_last = 343902491096 25.42.404.482 I slot launch_slot_: id 2 | task 26301 | processing task, is_child = 0 25.42.999.497 I slot print_timing: id 1 | task 26296 | prompt eval time = 2951.36 ms / 529 tokens ( 5.58 ms per token, 179.24 tokens per second) 25.42.999.502 I slot print_timing: id 1 | task 26296 | eval time = 598.59 ms / 2 tokens ( 598.59 ms per token, 1.67 tokens per second) 25.42.999.502 I slot print_timing: id 1 | task 26296 | total time = 3549.95 ms / 531 tokens 25.42.999.503 I slot print_timing: id 1 | task 26296 | graphs reused = 24882 25.42.999.503 I slot print_timing: id 1 | task 26296 | graph reallocs = 0 / 0 (same size) / (changed size) 25.42.999.545 I slot release: id 1 | task 26296 | stop processing: n_tokens = 732, truncated = 0 25.42.999.921 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 692, t_last = 343903236168 25.43.000.006 I slot launch_slot_: id 0 | task 26303 | processing task, is_child = 0 25.44.633.970 I slot print_timing: id 3 | task 26298 | prompt eval time = 2643.79 ms / 874 tokens ( 3.02 ms per token, 330.59 tokens per second) 25.44.633.973 I slot print_timing: id 3 | task 26298 | eval time = 1634.05 ms / 2 tokens ( 1634.05 ms per token, 0.61 tokens per second) 25.44.633.974 I slot print_timing: id 3 | task 26298 | total time = 4277.84 ms / 876 tokens 25.44.633.974 I slot print_timing: id 3 | task 26298 | graphs reused = 24882 25.44.633.974 I slot print_timing: id 3 | task 26298 | graph reallocs = 0 / 0 (same size) / (changed size) 25.44.634.037 I slot release: id 3 | task 26298 | stop processing: n_tokens = 875, truncated = 0 25.44.634.043 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 343903835243 25.44.634.141 I slot launch_slot_: id 1 | task 26305 | processing task, is_child = 0 25.46.343.046 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 875, t_last = 343905469735 25.46.343.158 I slot launch_slot_: id 3 | task 26307 | processing task, is_child = 0 25.46.343.166 I slot print_timing: id 0 | task 26303 | prompt processing, n_tokens = 1101, progress = 1.00, t = 3.34 s / 329.76 tokens per second 25.48.041.535 I slot print_timing: id 2 | task 26301 | prompt eval time = 3936.72 ms / 861 tokens ( 4.57 ms per token, 218.71 tokens per second) 25.48.041.538 I slot print_timing: id 2 | task 26301 | eval time = 1698.49 ms / 2 tokens ( 1698.49 ms per token, 0.59 tokens per second) 25.48.041.539 I slot print_timing: id 2 | task 26301 | total time = 5635.21 ms / 863 tokens 25.48.041.539 I slot print_timing: id 2 | task 26301 | graphs reused = 24882 25.48.041.539 I slot print_timing: id 2 | task 26301 | graph reallocs = 0 / 0 (same size) / (changed size) 25.48.041.591 I slot release: id 2 | task 26301 | stop processing: n_tokens = 862, truncated = 0 25.48.041.604 I slot print_timing: id 1 | task 26305 | prompt processing, n_tokens = 1092, progress = 1.00, t = 3.40 s / 320.90 tokens per second 25.48.786.793 I slot print_timing: id 0 | task 26303 | prompt eval time = 5037.29 ms / 1105 tokens ( 4.56 ms per token, 219.36 tokens per second) 25.48.786.796 I slot print_timing: id 0 | task 26303 | eval time = 745.53 ms / 2 tokens ( 745.53 ms per token, 1.34 tokens per second) 25.48.786.797 I slot print_timing: id 0 | task 26303 | total time = 5782.82 ms / 1107 tokens 25.48.786.801 I slot print_timing: id 0 | task 26303 | graphs reused = 24882 25.48.786.802 I slot print_timing: id 0 | task 26303 | graph reallocs = 0 / 0 (same size) / (changed size) 25.48.786.861 I slot release: id 0 | task 26303 | stop processing: n_tokens = 1106, truncated = 0 25.48.787.238 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.892 25.48.787.271 I slot launch_slot_: id 0 | task 26310 | processing task, is_child = 0 25.49.520.820 I slot print_timing: id 1 | task 26305 | prompt eval time = 4149.25 ms / 1096 tokens ( 3.79 ms per token, 264.14 tokens per second) 25.49.520.824 I slot print_timing: id 1 | task 26305 | eval time = 733.58 ms / 2 tokens ( 733.58 ms per token, 1.36 tokens per second) 25.49.520.825 I slot print_timing: id 1 | task 26305 | total time = 4882.83 ms / 1098 tokens 25.49.520.825 I slot print_timing: id 1 | task 26305 | graphs reused = 24882 25.49.520.826 I slot print_timing: id 1 | task 26305 | graph reallocs = 0 / 0 (same size) / (changed size) 25.49.520.874 I slot release: id 1 | task 26305 | stop processing: n_tokens = 1097, truncated = 0 25.49.521.199 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.898 25.49.521.228 I slot launch_slot_: id 1 | task 26312 | processing task, is_child = 0 25.50.290.321 I slot print_timing: id 3 | task 26307 | prompt eval time = 3177.81 ms / 1098 tokens ( 2.89 ms per token, 345.52 tokens per second) 25.50.290.326 I slot print_timing: id 3 | task 26307 | eval time = 769.12 ms / 2 tokens ( 769.12 ms per token, 1.30 tokens per second) 25.50.290.327 I slot print_timing: id 3 | task 26307 | total time = 3946.93 ms / 1100 tokens 25.50.290.327 I slot print_timing: id 3 | task 26307 | graphs reused = 24882 25.50.290.328 I slot print_timing: id 3 | task 26307 | graph reallocs = 0 / 0 (same size) / (changed size) 25.50.290.391 I slot release: id 3 | task 26307 | stop processing: n_tokens = 1099, truncated = 0 25.50.290.398 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.897 25.50.290.422 I slot launch_slot_: id 3 | task 26314 | processing task, is_child = 0 25.51.034.802 I slot print_timing: id 0 | task 26310 | prompt eval time = 1499.78 ms / 497 tokens ( 3.02 ms per token, 331.38 tokens per second) 25.51.034.805 I slot print_timing: id 0 | task 26310 | eval time = 744.77 ms / 2 tokens ( 744.77 ms per token, 1.34 tokens per second) 25.51.034.805 I slot print_timing: id 0 | task 26310 | total time = 2244.55 ms / 499 tokens 25.51.034.806 I slot print_timing: id 0 | task 26310 | graphs reused = 24882 25.51.034.806 I slot print_timing: id 0 | task 26310 | graph reallocs = 0 / 0 (same size) / (changed size) 25.51.034.873 I slot release: id 0 | task 26310 | stop processing: n_tokens = 1087, truncated = 0 25.51.035.170 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.907 25.51.035.215 I slot launch_slot_: id 0 | task 26316 | processing task, is_child = 0 25.51.765.973 I slot print_timing: id 1 | task 26312 | prompt eval time = 1513.66 ms / 514 tokens ( 2.94 ms per token, 339.57 tokens per second) 25.51.765.975 I slot print_timing: id 1 | task 26312 | eval time = 730.80 ms / 2 tokens ( 730.80 ms per token, 1.37 tokens per second) 25.51.765.976 I slot print_timing: id 1 | task 26312 | total time = 2244.47 ms / 516 tokens 25.51.765.976 I slot print_timing: id 1 | task 26312 | graphs reused = 24882 25.51.765.976 I slot print_timing: id 1 | task 26312 | graph reallocs = 0 / 0 (same size) / (changed size) 25.51.766.032 I slot release: id 1 | task 26312 | stop processing: n_tokens = 1095, truncated = 0 25.51.766.317 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.900 25.51.766.347 I slot launch_slot_: id 1 | task 26318 | processing task, is_child = 0 25.52.536.861 I slot print_timing: id 3 | task 26314 | prompt eval time = 1475.62 ms / 513 tokens ( 2.88 ms per token, 347.65 tokens per second) 25.52.536.863 I slot print_timing: id 3 | task 26314 | eval time = 770.54 ms / 2 tokens ( 770.54 ms per token, 1.30 tokens per second) 25.52.536.863 I slot print_timing: id 3 | task 26314 | total time = 2246.16 ms / 515 tokens 25.52.536.864 I slot print_timing: id 3 | task 26314 | graphs reused = 24882 25.52.536.864 I slot print_timing: id 3 | task 26314 | graph reallocs = 0 / 0 (same size) / (changed size) 25.52.536.917 I slot release: id 3 | task 26314 | stop processing: n_tokens = 1096, truncated = 0 25.52.536.924 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.894 (> 0.100 thold), f_keep = 0.900 25.52.536.954 I slot launch_slot_: id 3 | task 26320 | processing task, is_child = 0 25.52.643.326 I slot print_timing: id 0 | task 26316 | prompt eval time = 1501.27 ms / 497 tokens ( 3.02 ms per token, 331.05 tokens per second) 25.52.643.327 I slot print_timing: id 0 | task 26316 | eval time = 106.76 ms / 2 tokens ( 106.76 ms per token, 9.37 tokens per second) 25.52.643.328 I slot print_timing: id 0 | task 26316 | total time = 1608.02 ms / 499 tokens 25.52.643.328 I slot print_timing: id 0 | task 26316 | graphs reused = 24882 25.52.643.328 I slot print_timing: id 0 | task 26316 | graph reallocs = 0 / 0 (same size) / (changed size) 25.52.643.380 I slot release: id 0 | task 26316 | stop processing: n_tokens = 1087, truncated = 0 25.52.643.662 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.907 25.52.643.684 I slot launch_slot_: id 0 | task 26322 | processing task, is_child = 0 25.54.027.384 I slot print_timing: id 1 | task 26318 | prompt eval time = 877.03 ms / 515 tokens ( 1.70 ms per token, 587.21 tokens per second) 25.54.027.386 I slot print_timing: id 1 | task 26318 | eval time = 1383.72 ms / 2 tokens ( 1383.72 ms per token, 0.72 tokens per second) 25.54.027.387 I slot print_timing: id 1 | task 26318 | total time = 2260.75 ms / 517 tokens 25.54.027.387 I slot print_timing: id 1 | task 26318 | graphs reused = 24882 25.54.027.388 I slot print_timing: id 1 | task 26318 | graph reallocs = 0 / 0 (same size) / (changed size) 25.54.027.448 I slot release: id 1 | task 26318 | stop processing: n_tokens = 1096, truncated = 0 25.54.027.455 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.900 25.54.027.487 I slot launch_slot_: id 1 | task 26324 | processing task, is_child = 0 25.54.815.988 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 862, t_last = 343908877289 25.54.816.095 I slot launch_slot_: id 2 | task 26326 | processing task, is_child = 0 25.55.824.449 I slot print_timing: id 0 | task 26322 | prompt eval time = 2171.93 ms / 507 tokens ( 4.28 ms per token, 233.43 tokens per second) 25.55.824.453 I slot print_timing: id 0 | task 26322 | eval time = 1008.77 ms / 2 tokens ( 1008.77 ms per token, 0.99 tokens per second) 25.55.824.453 I slot print_timing: id 0 | task 26322 | total time = 3180.70 ms / 509 tokens 25.55.824.454 I slot print_timing: id 0 | task 26322 | graphs reused = 24882 25.55.824.454 I slot print_timing: id 0 | task 26322 | graph reallocs = 0 / 0 (same size) / (changed size) 25.55.824.507 I slot release: id 0 | task 26322 | stop processing: n_tokens = 1097, truncated = 0 25.55.825.112 I slot print_timing: id 3 | task 26320 | prompt eval time = 2278.76 ms / 521 tokens ( 4.37 ms per token, 228.63 tokens per second) 25.55.825.115 I slot print_timing: id 3 | task 26320 | eval time = 1009.13 ms / 2 tokens ( 1009.13 ms per token, 0.99 tokens per second) 25.55.825.115 I slot print_timing: id 3 | task 26320 | total time = 3287.89 ms / 523 tokens 25.55.825.115 I slot print_timing: id 3 | task 26320 | graphs reused = 24882 25.55.825.116 I slot print_timing: id 3 | task 26320 | graph reallocs = 0 / 0 (same size) / (changed size) 25.55.825.172 I slot release: id 3 | task 26320 | stop processing: n_tokens = 1104, truncated = 0 25.56.538.753 I slot print_timing: id 1 | task 26324 | prompt eval time = 1797.09 ms / 508 tokens ( 3.54 ms per token, 282.68 tokens per second) 25.56.538.756 I slot print_timing: id 1 | task 26324 | eval time = 713.92 ms / 2 tokens ( 713.92 ms per token, 1.40 tokens per second) 25.56.538.757 I slot print_timing: id 1 | task 26324 | total time = 2511.02 ms / 510 tokens 25.56.538.757 I slot print_timing: id 1 | task 26324 | graphs reused = 24882 25.56.538.758 I slot print_timing: id 1 | task 26324 | graph reallocs = 0 / 0 (same size) / (changed size) 25.56.538.819 I slot release: id 1 | task 26324 | stop processing: n_tokens = 1089, truncated = 0 25.56.538.828 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.899 25.56.538.859 I slot launch_slot_: id 0 | task 26329 | processing task, is_child = 0 25.56.547.330 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.905 25.56.547.374 I slot launch_slot_: id 1 | task 26330 | processing task, is_child = 0 25.56.547.435 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.893 25.56.547.456 I slot launch_slot_: id 3 | task 26331 | processing task, is_child = 0 25.58.908.537 I slot print_timing: id 2 | task 26326 | prompt eval time = 3959.76 ms / 1089 tokens ( 3.64 ms per token, 275.02 tokens per second) 25.58.908.540 I slot print_timing: id 2 | task 26326 | eval time = 132.48 ms / 2 tokens ( 132.48 ms per token, 7.55 tokens per second) 25.58.908.540 I slot print_timing: id 2 | task 26326 | total time = 4092.24 ms / 1091 tokens 25.58.908.540 I slot print_timing: id 2 | task 26326 | graphs reused = 24882 25.58.908.541 I slot print_timing: id 2 | task 26326 | graph reallocs = 0 / 0 (same size) / (changed size) 25.58.908.610 I slot release: id 2 | task 26326 | stop processing: n_tokens = 1090, truncated = 0 25.58.953.685 I slot print_timing: id 0 | task 26329 | prompt eval time = 2360.44 ms / 503 tokens ( 4.69 ms per token, 213.10 tokens per second) 25.58.953.687 I slot print_timing: id 0 | task 26329 | eval time = 45.78 ms / 2 tokens ( 45.78 ms per token, 21.84 tokens per second) 25.58.953.687 I slot print_timing: id 0 | task 26329 | total time = 2406.22 ms / 505 tokens 25.58.953.688 I slot print_timing: id 0 | task 26329 | graphs reused = 24882 25.58.953.688 I slot print_timing: id 0 | task 26329 | graph reallocs = 0 / 0 (same size) / (changed size) 25.58.953.738 I slot release: id 0 | task 26329 | stop processing: n_tokens = 1093, truncated = 0 25.58.954.088 I slot print_timing: id 1 | task 26330 | prompt eval time = 2360.66 ms / 513 tokens ( 4.60 ms per token, 217.31 tokens per second) 25.58.954.090 I slot print_timing: id 1 | task 26330 | eval time = 45.84 ms / 2 tokens ( 45.84 ms per token, 21.81 tokens per second) 25.58.954.091 I slot print_timing: id 1 | task 26330 | total time = 2406.50 ms / 515 tokens 25.58.954.091 I slot print_timing: id 1 | task 26330 | graphs reused = 24882 25.58.954.091 I slot print_timing: id 1 | task 26330 | graph reallocs = 0 / 0 (same size) / (changed size) 25.58.954.136 I slot release: id 1 | task 26330 | stop processing: n_tokens = 1094, truncated = 0 25.58.954.417 I slot print_timing: id 3 | task 26331 | prompt eval time = 2361.24 ms / 504 tokens ( 4.69 ms per token, 213.45 tokens per second) 25.58.954.421 I slot print_timing: id 3 | task 26331 | eval time = 45.30 ms / 2 tokens ( 45.30 ms per token, 22.08 tokens per second) 25.58.954.421 I slot print_timing: id 3 | task 26331 | total time = 2406.54 ms / 506 tokens 25.58.954.421 I slot print_timing: id 3 | task 26331 | graphs reused = 24882 25.58.954.421 I slot print_timing: id 3 | task 26331 | graph reallocs = 0 / 0 (same size) / (changed size) 25.58.954.471 I slot release: id 3 | task 26331 | stop processing: n_tokens = 1092, truncated = 0 25.58.954.479 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1090, t_last = 343919744308 25.58.958.077 I slot launch_slot_: id 2 | task 26335 | processing task, is_child = 0 25.58.966.431 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1093, t_last = 343919789436 25.58.966.517 I slot launch_slot_: id 0 | task 26336 | processing task, is_child = 0 25.58.966.624 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1094, t_last = 343919789834 25.58.966.700 I slot launch_slot_: id 1 | task 26337 | processing task, is_child = 0 25.58.966.755 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1092, t_last = 343919790169 25.58.966.828 I slot launch_slot_: id 3 | task 26338 | processing task, is_child = 0 26.04.107.808 I slot print_timing: id 0 | task 26336 | prompt processing, n_tokens = 992, progress = 1.00, t = 5.14 s / 192.96 tokens per second 26.04.795.196 I slot print_timing: id 1 | task 26337 | prompt processing, n_tokens = 1033, progress = 1.00, t = 5.14 s / 200.94 tokens per second 26.04.795.380 I slot print_timing: id 2 | task 26335 | prompt processing, n_tokens = 979, progress = 1.00, t = 5.14 s / 190.44 tokens per second 26.04.795.548 I slot print_timing: id 3 | task 26338 | prompt processing, n_tokens = 1062, progress = 1.00, t = 5.14 s / 206.59 tokens per second 26.04.976.696 I slot print_timing: id 0 | task 26336 | prompt eval time = 5962.29 ms / 996 tokens ( 5.99 ms per token, 167.05 tokens per second) 26.04.976.702 I slot print_timing: id 0 | task 26336 | eval time = 47.57 ms / 2 tokens ( 47.57 ms per token, 21.02 tokens per second) 26.04.976.702 I slot print_timing: id 0 | task 26336 | total time = 6009.86 ms / 998 tokens 26.04.976.703 I slot print_timing: id 0 | task 26336 | graphs reused = 24883 26.04.976.703 I slot print_timing: id 0 | task 26336 | graph reallocs = 0 / 0 (same size) / (changed size) 26.04.976.767 I slot release: id 0 | task 26336 | stop processing: n_tokens = 997, truncated = 0 26.04.977.048 I slot print_timing: id 1 | task 26337 | prompt eval time = 5962.50 ms / 1037 tokens ( 5.75 ms per token, 173.92 tokens per second) 26.04.977.050 I slot print_timing: id 1 | task 26337 | eval time = 47.62 ms / 2 tokens ( 47.62 ms per token, 21.00 tokens per second) 26.04.977.051 I slot print_timing: id 1 | task 26337 | total time = 6010.12 ms / 1039 tokens 26.04.977.051 I slot print_timing: id 1 | task 26337 | graphs reused = 24883 26.04.977.051 I slot print_timing: id 1 | task 26337 | graph reallocs = 0 / 0 (same size) / (changed size) 26.04.977.097 I slot release: id 1 | task 26337 | stop processing: n_tokens = 1038, truncated = 0 26.04.977.371 I slot print_timing: id 2 | task 26335 | prompt eval time = 5962.77 ms / 983 tokens ( 6.07 ms per token, 164.86 tokens per second) 26.04.977.373 I slot print_timing: id 2 | task 26335 | eval time = 47.61 ms / 2 tokens ( 47.61 ms per token, 21.00 tokens per second) 26.04.977.374 I slot print_timing: id 2 | task 26335 | total time = 6010.37 ms / 985 tokens 26.04.977.374 I slot print_timing: id 2 | task 26335 | graphs reused = 24883 26.04.977.374 I slot print_timing: id 2 | task 26335 | graph reallocs = 0 / 0 (same size) / (changed size) 26.04.977.414 I slot release: id 2 | task 26335 | stop processing: n_tokens = 984, truncated = 0 26.04.977.715 I slot print_timing: id 3 | task 26338 | prompt eval time = 5963.29 ms / 1066 tokens ( 5.59 ms per token, 178.76 tokens per second) 26.04.977.717 I slot print_timing: id 3 | task 26338 | eval time = 47.35 ms / 2 tokens ( 47.35 ms per token, 21.12 tokens per second) 26.04.977.717 I slot print_timing: id 3 | task 26338 | total time = 6010.65 ms / 1068 tokens 26.04.977.718 I slot print_timing: id 3 | task 26338 | graphs reused = 24883 26.04.977.718 I slot print_timing: id 3 | task 26338 | graph reallocs = 0 / 0 (same size) / (changed size) 26.04.977.765 I slot release: id 3 | task 26338 | stop processing: n_tokens = 1067, truncated = 0 26.04.984.104 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 997, t_last = 343925812466 26.04.986.803 I slot launch_slot_: id 0 | task 26343 | processing task, is_child = 0 26.04.994.482 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1038, t_last = 343925812795 26.04.994.571 I slot launch_slot_: id 1 | task 26344 | processing task, is_child = 0 26.04.994.679 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.886 26.04.994.694 I slot launch_slot_: id 2 | task 26345 | processing task, is_child = 0 26.04.994.745 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.817 26.04.994.760 I slot launch_slot_: id 3 | task 26346 | processing task, is_child = 0 26.08.801.944 I slot print_timing: id 0 | task 26343 | prompt processing, n_tokens = 727, progress = 0.99, t = 3.81 s / 190.97 tokens per second 26.08.802.100 I slot print_timing: id 1 | task 26344 | prompt processing, n_tokens = 770, progress = 0.99, t = 3.81 s / 202.27 tokens per second 26.08.802.242 I slot print_timing: id 2 | task 26345 | prompt processing, n_tokens = 536, progress = 1.00, t = 3.81 s / 140.81 tokens per second 26.08.922.997 I slot print_timing: id 3 | task 26346 | prompt eval time = 3806.93 ms / 444 tokens ( 8.57 ms per token, 116.63 tokens per second) 26.08.923.000 I slot print_timing: id 3 | task 26346 | eval time = 121.06 ms / 2 tokens ( 121.06 ms per token, 8.26 tokens per second) 26.08.923.001 I slot print_timing: id 3 | task 26346 | total time = 3928.00 ms / 446 tokens 26.08.923.001 I slot print_timing: id 3 | task 26346 | graphs reused = 24883 26.08.923.002 I slot print_timing: id 3 | task 26346 | graph reallocs = 0 / 0 (same size) / (changed size) 26.08.923.073 I slot release: id 3 | task 26346 | stop processing: n_tokens = 995, truncated = 0 26.08.960.131 I slot print_timing: id 0 | task 26343 | prompt eval time = 3927.28 ms / 731 tokens ( 5.37 ms per token, 186.13 tokens per second) 26.08.960.132 I slot print_timing: id 0 | task 26343 | eval time = 38.08 ms / 2 tokens ( 38.08 ms per token, 26.26 tokens per second) 26.08.960.133 I slot print_timing: id 0 | task 26343 | total time = 3965.37 ms / 733 tokens 26.08.960.134 I slot print_timing: id 0 | task 26343 | graphs reused = 24883 26.08.960.134 I slot print_timing: id 0 | task 26343 | graph reallocs = 0 / 0 (same size) / (changed size) 26.08.960.181 I slot release: id 0 | task 26343 | stop processing: n_tokens = 732, truncated = 0 26.08.960.462 I slot print_timing: id 1 | task 26344 | prompt eval time = 3927.52 ms / 774 tokens ( 5.07 ms per token, 197.07 tokens per second) 26.08.960.464 I slot print_timing: id 1 | task 26344 | eval time = 38.11 ms / 2 tokens ( 38.11 ms per token, 26.24 tokens per second) 26.08.960.465 I slot print_timing: id 1 | task 26344 | total time = 3965.63 ms / 776 tokens 26.08.960.465 I slot print_timing: id 1 | task 26344 | graphs reused = 24883 26.08.960.466 I slot print_timing: id 1 | task 26344 | graph reallocs = 0 / 0 (same size) / (changed size) 26.08.960.513 I slot release: id 1 | task 26344 | stop processing: n_tokens = 775, truncated = 0 26.08.960.799 I slot print_timing: id 2 | task 26345 | prompt eval time = 3927.77 ms / 540 tokens ( 7.27 ms per token, 137.48 tokens per second) 26.08.960.801 I slot print_timing: id 2 | task 26345 | eval time = 38.11 ms / 2 tokens ( 38.11 ms per token, 26.24 tokens per second) 26.08.960.801 I slot print_timing: id 2 | task 26345 | total time = 3965.89 ms / 542 tokens 26.08.960.802 I slot print_timing: id 2 | task 26345 | graphs reused = 24883 26.08.960.802 I slot print_timing: id 2 | task 26345 | graph reallocs = 0 / 0 (same size) / (changed size) 26.08.960.853 I slot release: id 2 | task 26345 | stop processing: n_tokens = 1008, truncated = 0 26.08.960.858 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.894 (> 0.100 thold), f_keep = 0.862 26.08.960.883 I slot launch_slot_: id 0 | task 26351 | processing task, is_child = 0 26.08.968.915 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.875 (> 0.100 thold), f_keep = 0.814 26.08.968.946 I slot launch_slot_: id 1 | task 26352 | processing task, is_child = 0 26.08.969.043 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 995, t_last = 343929758771 26.08.970.541 I slot launch_slot_: id 3 | task 26353 | processing task, is_child = 0 26.08.970.597 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1008, t_last = 343929796551 26.08.970.664 I slot launch_slot_: id 2 | task 26354 | processing task, is_child = 0 26.12.230.790 I slot print_timing: id 2 | task 26354 | prompt processing, n_tokens = 719, progress = 0.99, t = 3.26 s / 220.63 tokens per second 26.12.317.454 I slot print_timing: id 0 | task 26351 | prompt eval time = 3259.46 ms / 491 tokens ( 6.64 ms per token, 150.64 tokens per second) 26.12.317.457 I slot print_timing: id 0 | task 26351 | eval time = 87.32 ms / 2 tokens ( 87.32 ms per token, 11.45 tokens per second) 26.12.317.457 I slot print_timing: id 0 | task 26351 | total time = 3346.78 ms / 493 tokens 26.12.317.458 I slot print_timing: id 0 | task 26351 | graphs reused = 24883 26.12.317.458 I slot print_timing: id 0 | task 26351 | graph reallocs = 0 / 0 (same size) / (changed size) 26.12.317.500 I slot release: id 0 | task 26351 | stop processing: n_tokens = 707, truncated = 0 26.12.317.811 I slot print_timing: id 1 | task 26352 | prompt eval time = 3259.66 ms / 463 tokens ( 7.04 ms per token, 142.04 tokens per second) 26.12.317.813 I slot print_timing: id 1 | task 26352 | eval time = 87.37 ms / 2 tokens ( 87.37 ms per token, 11.45 tokens per second) 26.12.317.814 I slot print_timing: id 1 | task 26352 | total time = 3347.03 ms / 465 tokens 26.12.317.814 I slot print_timing: id 1 | task 26352 | graphs reused = 24883 26.12.317.814 I slot print_timing: id 1 | task 26352 | graph reallocs = 0 / 0 (same size) / (changed size) 26.12.317.860 I slot release: id 1 | task 26352 | stop processing: n_tokens = 722, truncated = 0 26.12.318.703 I slot print_timing: id 3 | task 26353 | prompt eval time = 3259.83 ms / 457 tokens ( 7.13 ms per token, 140.19 tokens per second) 26.12.318.705 I slot print_timing: id 3 | task 26353 | eval time = 87.93 ms / 2 tokens ( 87.93 ms per token, 11.37 tokens per second) 26.12.318.705 I slot print_timing: id 3 | task 26353 | total time = 3347.75 ms / 459 tokens 26.12.318.706 I slot print_timing: id 3 | task 26353 | graphs reused = 24883 26.12.318.706 I slot print_timing: id 3 | task 26353 | graph reallocs = 0 / 0 (same size) / (changed size) 26.12.318.745 I slot release: id 3 | task 26353 | stop processing: n_tokens = 716, truncated = 0 26.12.336.911 I slot print_timing: id 2 | task 26354 | prompt eval time = 3347.44 ms / 723 tokens ( 4.63 ms per token, 215.99 tokens per second) 26.12.336.914 I slot print_timing: id 2 | task 26354 | eval time = 18.59 ms / 2 tokens ( 18.59 ms per token, 53.80 tokens per second) 26.12.336.914 I slot print_timing: id 2 | task 26354 | total time = 3366.03 ms / 725 tokens 26.12.336.915 I slot print_timing: id 2 | task 26354 | graphs reused = 24883 26.12.336.916 I slot print_timing: id 2 | task 26354 | graph reallocs = 0 / 0 (same size) / (changed size) 26.12.336.956 I slot release: id 2 | task 26354 | stop processing: n_tokens = 724, truncated = 0 26.12.336.962 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.893 26.12.336.986 I slot launch_slot_: id 0 | task 26359 | processing task, is_child = 0 26.12.341.198 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.874 26.12.341.221 I slot launch_slot_: id 1 | task 26360 | processing task, is_child = 0 26.12.341.309 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.872 26.12.341.327 I slot launch_slot_: id 2 | task 26361 | processing task, is_child = 0 26.12.341.369 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 716, t_last = 343933154443 26.12.341.433 I slot launch_slot_: id 3 | task 26362 | processing task, is_child = 0 26.16.208.353 I slot print_timing: id 3 | task 26362 | prompt processing, n_tokens = 940, progress = 1.00, t = 3.87 s / 243.17 tokens per second 26.16.287.962 I slot print_timing: id 0 | task 26359 | prompt eval time = 3866.24 ms / 494 tokens ( 7.83 ms per token, 127.77 tokens per second) 26.16.287.965 I slot print_timing: id 0 | task 26359 | eval time = 80.28 ms / 2 tokens ( 80.28 ms per token, 12.46 tokens per second) 26.16.287.965 I slot print_timing: id 0 | task 26359 | total time = 3946.52 ms / 496 tokens 26.16.287.965 I slot print_timing: id 0 | task 26359 | graphs reused = 24884 26.16.287.966 I slot print_timing: id 0 | task 26359 | graph reallocs = 0 / 0 (same size) / (changed size) 26.16.288.013 I slot release: id 0 | task 26359 | stop processing: n_tokens = 710, truncated = 0 26.16.288.287 I slot print_timing: id 1 | task 26360 | prompt eval time = 3866.43 ms / 473 tokens ( 8.17 ms per token, 122.34 tokens per second) 26.16.288.292 I slot print_timing: id 1 | task 26360 | eval time = 80.30 ms / 2 tokens ( 80.30 ms per token, 12.45 tokens per second) 26.16.288.293 I slot print_timing: id 1 | task 26360 | total time = 3946.73 ms / 475 tokens 26.16.288.294 I slot print_timing: id 1 | task 26360 | graphs reused = 24884 26.16.288.294 I slot print_timing: id 1 | task 26360 | graph reallocs = 0 / 0 (same size) / (changed size) 26.16.288.329 I slot release: id 1 | task 26360 | stop processing: n_tokens = 732, truncated = 0 26.16.288.621 I slot print_timing: id 2 | task 26361 | prompt eval time = 3866.68 ms / 516 tokens ( 7.49 ms per token, 133.45 tokens per second) 26.16.288.624 I slot print_timing: id 2 | task 26361 | eval time = 80.28 ms / 2 tokens ( 80.28 ms per token, 12.46 tokens per second) 26.16.288.624 I slot print_timing: id 2 | task 26361 | total time = 3946.96 ms / 518 tokens 26.16.288.625 I slot print_timing: id 2 | task 26361 | graphs reused = 24884 26.16.288.625 I slot print_timing: id 2 | task 26361 | graph reallocs = 0 / 0 (same size) / (changed size) 26.16.288.667 I slot release: id 2 | task 26361 | stop processing: n_tokens = 724, truncated = 0 26.16.307.502 I slot print_timing: id 3 | task 26362 | prompt eval time = 3947.48 ms / 944 tokens ( 4.18 ms per token, 239.14 tokens per second) 26.16.307.503 I slot print_timing: id 3 | task 26362 | eval time = 18.25 ms / 2 tokens ( 18.25 ms per token, 54.79 tokens per second) 26.16.307.504 I slot print_timing: id 3 | task 26362 | total time = 3965.73 ms / 946 tokens 26.16.307.504 I slot print_timing: id 3 | task 26362 | graphs reused = 24884 26.16.307.505 I slot print_timing: id 3 | task 26362 | graph reallocs = 0 / 0 (same size) / (changed size) 26.16.307.554 I slot release: id 3 | task 26362 | stop processing: n_tokens = 945, truncated = 0 26.16.307.560 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.881 (> 0.100 thold), f_keep = 0.852 26.16.307.584 I slot launch_slot_: id 3 | task 26367 | processing task, is_child = 0 26.16.312.983 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 343937123711 26.16.313.063 I slot launch_slot_: id 0 | task 26368 | processing task, is_child = 0 26.16.313.144 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 343937124027 26.16.313.206 I slot launch_slot_: id 1 | task 26369 | processing task, is_child = 0 26.16.313.250 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 724, t_last = 343937124365 26.16.313.311 I slot launch_slot_: id 2 | task 26370 | processing task, is_child = 0 26.21.645.375 I slot print_timing: id 0 | task 26368 | prompt processing, n_tokens = 995, progress = 1.00, t = 5.33 s / 186.62 tokens per second 26.21.645.564 I slot print_timing: id 1 | task 26369 | prompt processing, n_tokens = 926, progress = 1.00, t = 5.33 s / 173.68 tokens per second 26.21.645.717 I slot print_timing: id 2 | task 26370 | prompt processing, n_tokens = 1047, progress = 1.00, t = 5.33 s / 196.38 tokens per second 26.21.766.777 I slot print_timing: id 3 | task 26367 | prompt eval time = 5331.85 ms / 486 tokens ( 10.97 ms per token, 91.15 tokens per second) 26.21.766.782 I slot print_timing: id 3 | task 26367 | eval time = 121.41 ms / 2 tokens ( 121.41 ms per token, 8.24 tokens per second) 26.21.766.783 I slot print_timing: id 3 | task 26367 | total time = 5453.26 ms / 488 tokens 26.21.766.784 I slot print_timing: id 3 | task 26367 | graphs reused = 24884 26.21.766.784 I slot print_timing: id 3 | task 26367 | graph reallocs = 0 / 0 (same size) / (changed size) 26.21.766.866 I slot release: id 3 | task 26367 | stop processing: n_tokens = 915, truncated = 0 26.21.804.011 I slot print_timing: id 0 | task 26368 | prompt eval time = 5452.26 ms / 999 tokens ( 5.46 ms per token, 183.23 tokens per second) 26.21.804.016 I slot print_timing: id 0 | task 26368 | eval time = 38.43 ms / 2 tokens ( 38.43 ms per token, 26.02 tokens per second) 26.21.804.017 I slot print_timing: id 0 | task 26368 | total time = 5490.69 ms / 1001 tokens 26.21.804.017 I slot print_timing: id 0 | task 26368 | graphs reused = 24884 26.21.804.017 I slot print_timing: id 0 | task 26368 | graph reallocs = 0 / 0 (same size) / (changed size) 26.21.804.069 I slot release: id 0 | task 26368 | stop processing: n_tokens = 1000, truncated = 0 26.21.804.354 I slot print_timing: id 1 | task 26369 | prompt eval time = 5452.59 ms / 930 tokens ( 5.86 ms per token, 170.56 tokens per second) 26.21.804.356 I slot print_timing: id 1 | task 26369 | eval time = 38.38 ms / 2 tokens ( 38.38 ms per token, 26.06 tokens per second) 26.21.804.356 I slot print_timing: id 1 | task 26369 | total time = 5490.96 ms / 932 tokens 26.21.804.356 I slot print_timing: id 1 | task 26369 | graphs reused = 24884 26.21.804.357 I slot print_timing: id 1 | task 26369 | graph reallocs = 0 / 0 (same size) / (changed size) 26.21.804.397 I slot release: id 1 | task 26369 | stop processing: n_tokens = 931, truncated = 0 26.21.804.674 I slot print_timing: id 2 | task 26370 | prompt eval time = 5452.95 ms / 1051 tokens ( 5.19 ms per token, 192.74 tokens per second) 26.21.804.676 I slot print_timing: id 2 | task 26370 | eval time = 38.27 ms / 2 tokens ( 38.27 ms per token, 26.13 tokens per second) 26.21.804.676 I slot print_timing: id 2 | task 26370 | total time = 5491.22 ms / 1053 tokens 26.21.804.676 I slot print_timing: id 2 | task 26370 | graphs reused = 24884 26.21.804.677 I slot print_timing: id 2 | task 26370 | graph reallocs = 0 / 0 (same size) / (changed size) 26.21.804.728 I slot release: id 2 | task 26370 | stop processing: n_tokens = 1052, truncated = 0 26.21.804.732 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.878 26.21.804.759 I slot launch_slot_: id 2 | task 26375 | processing task, is_child = 0 26.21.812.648 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 915, t_last = 343942602566 26.21.812.744 I slot launch_slot_: id 3 | task 26376 | processing task, is_child = 0 26.21.812.839 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1000, t_last = 343942639769 26.21.812.906 I slot launch_slot_: id 0 | task 26377 | processing task, is_child = 0 26.21.812.952 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 343942640095 26.21.813.019 I slot launch_slot_: id 1 | task 26378 | processing task, is_child = 0 26.26.993.561 I slot print_timing: id 0 | task 26377 | prompt processing, n_tokens = 2045, progress = 1.00, t = 5.18 s / 394.75 tokens per second 26.27.632.416 I slot print_timing: id 1 | task 26378 | prompt processing, n_tokens = 1569, progress = 0.75, t = 5.18 s / 302.87 tokens per second 26.30.588.001 I slot print_timing: id 1 | task 26378 | prompt processing, n_tokens = 2081, progress = 1.00, t = 8.77 s / 237.24 tokens per second 26.30.589.016 I slot print_timing: id 2 | task 26375 | prompt processing, n_tokens = 515, progress = 1.00, t = 6.00 s / 85.88 tokens per second 26.30.589.641 I slot print_timing: id 3 | task 26376 | prompt processing, n_tokens = 1499, progress = 0.72, t = 6.00 s / 249.97 tokens per second 26.30.928.576 I slot print_timing: id 0 | task 26377 | prompt eval time = 8774.89 ms / 2049 tokens ( 4.28 ms per token, 233.51 tokens per second) 26.30.928.594 I slot print_timing: id 0 | task 26377 | eval time = 340.63 ms / 2 tokens ( 340.63 ms per token, 2.94 tokens per second) 26.30.928.597 I slot print_timing: id 0 | task 26377 | total time = 9115.52 ms / 2051 tokens 26.30.928.600 I slot print_timing: id 0 | task 26377 | graphs reused = 24884 26.30.928.602 I slot print_timing: id 0 | task 26377 | graph reallocs = 0 / 0 (same size) / (changed size) 26.30.929.176 I slot release: id 0 | task 26377 | stop processing: n_tokens = 2050, truncated = 0 26.30.932.665 I slot print_timing: id 3 | task 26376 | prompt processing, n_tokens = 1555, progress = 0.75, t = 6.34 s / 245.36 tokens per second 26.31.680.483 I slot print_timing: id 1 | task 26378 | prompt eval time = 9118.13 ms / 2085 tokens ( 4.37 ms per token, 228.67 tokens per second) 26.31.680.497 I slot print_timing: id 1 | task 26378 | eval time = 749.20 ms / 2 tokens ( 749.20 ms per token, 1.33 tokens per second) 26.31.680.500 I slot print_timing: id 1 | task 26378 | total time = 9867.33 ms / 2087 tokens 26.31.680.503 I slot print_timing: id 1 | task 26378 | graphs reused = 24884 26.31.680.505 I slot print_timing: id 1 | task 26378 | graph reallocs = 0 / 0 (same size) / (changed size) 26.31.681.129 I slot release: id 1 | task 26378 | stop processing: n_tokens = 2086, truncated = 0 26.31.682.952 I slot print_timing: id 2 | task 26375 | prompt eval time = 6344.63 ms / 519 tokens ( 12.22 ms per token, 81.80 tokens per second) 26.31.682.959 I slot print_timing: id 2 | task 26375 | eval time = 750.31 ms / 2 tokens ( 750.31 ms per token, 1.33 tokens per second) 26.31.682.960 I slot print_timing: id 2 | task 26375 | total time = 7094.94 ms / 521 tokens 26.31.682.961 I slot print_timing: id 2 | task 26375 | graphs reused = 24884 26.31.682.963 I slot print_timing: id 2 | task 26375 | graph reallocs = 0 / 0 (same size) / (changed size) 26.31.683.141 I slot release: id 2 | task 26375 | stop processing: n_tokens = 1055, truncated = 0 26.31.683.175 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.865 26.31.683.316 I slot launch_slot_: id 0 | task 26384 | processing task, is_child = 0 26.31.703.042 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.842 (> 0.100 thold), f_keep = 0.850 26.31.703.116 I slot launch_slot_: id 1 | task 26385 | processing task, is_child = 0 26.31.703.224 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1055, t_last = 343952518842 26.31.706.752 I slot launch_slot_: id 2 | task 26386 | processing task, is_child = 0 26.31.707.327 I slot print_timing: id 3 | task 26376 | prompt processing, n_tokens = 2067, progress = 1.00, t = 7.09 s / 291.56 tokens per second 26.34.310.784 I slot print_timing: id 3 | task 26376 | prompt eval time = 8192.42 ms / 2071 tokens ( 3.96 ms per token, 252.79 tokens per second) 26.34.310.796 I slot print_timing: id 3 | task 26376 | eval time = 1530.25 ms / 2 tokens ( 1530.25 ms per token, 0.65 tokens per second) 26.34.310.798 I slot print_timing: id 3 | task 26376 | total time = 9722.67 ms / 2073 tokens 26.34.310.800 I slot print_timing: id 3 | task 26376 | graphs reused = 24884 26.34.310.801 I slot print_timing: id 3 | task 26376 | graph reallocs = 0 / 0 (same size) / (changed size) 26.34.311.233 I slot release: id 3 | task 26376 | stop processing: n_tokens = 2072, truncated = 0 26.34.412.844 I slot print_timing: id 0 | task 26384 | prompt eval time = 2602.27 ms / 493 tokens ( 5.28 ms per token, 189.45 tokens per second) 26.34.412.856 I slot print_timing: id 0 | task 26384 | eval time = 103.78 ms / 2 tokens ( 103.78 ms per token, 9.64 tokens per second) 26.34.412.860 I slot print_timing: id 0 | task 26384 | total time = 2706.04 ms / 495 tokens 26.34.412.862 I slot print_timing: id 0 | task 26384 | graphs reused = 24884 26.34.412.864 I slot print_timing: id 0 | task 26384 | graph reallocs = 0 / 0 (same size) / (changed size) 26.34.413.228 I slot release: id 0 | task 26384 | stop processing: n_tokens = 2027, truncated = 0 26.34.416.043 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 26.34.416.156 I slot launch_slot_: id 0 | task 26390 | processing task, is_child = 0 26.35.156.487 I slot print_timing: id 1 | task 26385 | prompt eval time = 2707.47 ms / 537 tokens ( 5.04 ms per token, 198.34 tokens per second) 26.35.156.504 I slot print_timing: id 1 | task 26385 | eval time = 741.95 ms / 2 tokens ( 741.95 ms per token, 1.35 tokens per second) 26.35.156.506 I slot print_timing: id 1 | task 26385 | total time = 3449.43 ms / 539 tokens 26.35.156.508 I slot print_timing: id 1 | task 26385 | graphs reused = 24884 26.35.156.509 I slot print_timing: id 1 | task 26385 | graph reallocs = 0 / 0 (same size) / (changed size) 26.35.156.906 I slot release: id 1 | task 26385 | stop processing: n_tokens = 2107, truncated = 0 26.35.158.296 I slot print_timing: id 2 | task 26386 | prompt eval time = 2708.83 ms / 547 tokens ( 4.95 ms per token, 201.93 tokens per second) 26.35.158.302 I slot print_timing: id 2 | task 26386 | eval time = 742.28 ms / 2 tokens ( 742.28 ms per token, 1.35 tokens per second) 26.35.158.303 I slot print_timing: id 2 | task 26386 | total time = 3451.11 ms / 549 tokens 26.35.158.304 I slot print_timing: id 2 | task 26386 | graphs reused = 24884 26.35.158.305 I slot print_timing: id 2 | task 26386 | graph reallocs = 0 / 0 (same size) / (changed size) 26.35.158.557 I slot release: id 2 | task 26386 | stop processing: n_tokens = 2117, truncated = 0 26.35.158.593 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.834 (> 0.100 thold), f_keep = 0.842 26.35.158.718 I slot launch_slot_: id 1 | task 26392 | processing task, is_child = 0 26.35.366.123 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.838 26.35.366.335 I slot launch_slot_: id 2 | task 26394 | processing task, is_child = 0 26.35.366.721 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.805 (> 0.100 thold), f_keep = 0.856 26.35.366.785 I slot launch_slot_: id 3 | task 26395 | processing task, is_child = 0 26.36.984.319 I slot print_timing: id 0 | task 26390 | prompt eval time = 944.10 ms / 514 tokens ( 1.84 ms per token, 544.43 tokens per second) 26.36.984.338 I slot print_timing: id 0 | task 26390 | eval time = 1618.25 ms / 2 tokens ( 1618.25 ms per token, 0.62 tokens per second) 26.36.984.341 I slot print_timing: id 0 | task 26390 | total time = 2562.35 ms / 516 tokens 26.36.984.344 I slot print_timing: id 0 | task 26390 | graphs reused = 24884 26.36.984.346 I slot print_timing: id 0 | task 26390 | graph reallocs = 0 / 0 (same size) / (changed size) 26.36.984.931 I slot release: id 0 | task 26390 | stop processing: n_tokens = 2048, truncated = 0 26.37.801.919 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.866 26.37.802.133 I slot launch_slot_: id 0 | task 26398 | processing task, is_child = 0 26.38.536.039 I slot print_timing: id 1 | task 26392 | prompt eval time = 2626.08 ms / 536 tokens ( 4.90 ms per token, 204.11 tokens per second) 26.38.536.057 I slot print_timing: id 1 | task 26392 | eval time = 735.76 ms / 2 tokens ( 735.76 ms per token, 1.36 tokens per second) 26.38.536.060 I slot print_timing: id 1 | task 26392 | total time = 3361.84 ms / 538 tokens 26.38.536.063 I slot print_timing: id 1 | task 26392 | graphs reused = 24884 26.38.536.065 I slot print_timing: id 1 | task 26392 | graph reallocs = 0 / 0 (same size) / (changed size) 26.38.536.680 I slot release: id 1 | task 26392 | stop processing: n_tokens = 2127, truncated = 0 26.38.538.926 I slot print_timing: id 2 | task 26394 | prompt eval time = 2434.88 ms / 355 tokens ( 6.86 ms per token, 145.80 tokens per second) 26.38.538.933 I slot print_timing: id 2 | task 26394 | eval time = 737.04 ms / 2 tokens ( 737.04 ms per token, 1.36 tokens per second) 26.38.538.934 I slot print_timing: id 2 | task 26394 | total time = 3171.92 ms / 357 tokens 26.38.538.935 I slot print_timing: id 2 | task 26394 | graphs reused = 24884 26.38.538.937 I slot print_timing: id 2 | task 26394 | graph reallocs = 0 / 0 (same size) / (changed size) 26.38.539.223 I slot release: id 2 | task 26394 | stop processing: n_tokens = 1956, truncated = 0 26.38.604.277 I slot print_timing: id 3 | task 26395 | prompt eval time = 3173.61 ms / 649 tokens ( 4.89 ms per token, 204.50 tokens per second) 26.38.604.283 I slot print_timing: id 3 | task 26395 | eval time = 63.28 ms / 2 tokens ( 63.28 ms per token, 15.80 tokens per second) 26.38.604.284 I slot print_timing: id 3 | task 26395 | total time = 3236.89 ms / 651 tokens 26.38.604.285 I slot print_timing: id 3 | task 26395 | graphs reused = 24884 26.38.604.286 I slot print_timing: id 3 | task 26395 | graph reallocs = 0 / 0 (same size) / (changed size) 26.38.604.590 I slot release: id 3 | task 26395 | stop processing: n_tokens = 2205, truncated = 0 26.38.604.611 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.865 (> 0.100 thold), f_keep = 0.834 26.38.604.674 I slot launch_slot_: id 1 | task 26401 | processing task, is_child = 0 26.38.627.781 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.906 26.38.627.838 I slot launch_slot_: id 2 | task 26402 | processing task, is_child = 0 26.38.627.994 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.848 (> 0.100 thold), f_keep = 0.805 26.38.628.031 I slot launch_slot_: id 3 | task 26403 | processing task, is_child = 0 26.40.707.730 I slot print_timing: id 0 | task 26398 | prompt eval time = 801.37 ms / 467 tokens ( 1.72 ms per token, 582.75 tokens per second) 26.40.707.733 I slot print_timing: id 0 | task 26398 | eval time = 2104.19 ms / 2 tokens ( 2104.19 ms per token, 0.48 tokens per second) 26.40.707.733 I slot print_timing: id 0 | task 26398 | total time = 2905.56 ms / 469 tokens 26.40.707.734 I slot print_timing: id 0 | task 26398 | graphs reused = 24885 26.40.707.734 I slot print_timing: id 0 | task 26398 | graph reallocs = 0 / 0 (same size) / (changed size) 26.40.707.843 I slot release: id 0 | task 26398 | stop processing: n_tokens = 2001, truncated = 0 26.40.813.887 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.886 26.40.813.929 I slot launch_slot_: id 0 | task 26406 | processing task, is_child = 0 26.41.461.886 I slot print_timing: id 1 | task 26401 | prompt eval time = 2184.99 ms / 441 tokens ( 4.95 ms per token, 201.83 tokens per second) 26.41.461.889 I slot print_timing: id 1 | task 26401 | eval time = 648.85 ms / 2 tokens ( 648.85 ms per token, 1.54 tokens per second) 26.41.461.890 I slot print_timing: id 1 | task 26401 | total time = 2833.84 ms / 443 tokens 26.41.461.890 I slot print_timing: id 1 | task 26401 | graphs reused = 24885 26.41.461.891 I slot print_timing: id 1 | task 26401 | graph reallocs = 0 / 0 (same size) / (changed size) 26.41.462.002 I slot release: id 1 | task 26401 | stop processing: n_tokens = 2052, truncated = 0 26.41.462.420 I slot print_timing: id 2 | task 26402 | prompt eval time = 2185.14 ms / 397 tokens ( 5.50 ms per token, 181.68 tokens per second) 26.41.462.424 I slot print_timing: id 2 | task 26402 | eval time = 648.98 ms / 2 tokens ( 648.98 ms per token, 1.54 tokens per second) 26.41.462.424 I slot print_timing: id 2 | task 26402 | total time = 2834.13 ms / 399 tokens 26.41.462.424 I slot print_timing: id 2 | task 26402 | graphs reused = 24885 26.41.462.425 I slot print_timing: id 2 | task 26402 | graph reallocs = 0 / 0 (same size) / (changed size) 26.41.462.521 I slot release: id 2 | task 26402 | stop processing: n_tokens = 1998, truncated = 0 26.41.463.094 I slot print_timing: id 3 | task 26403 | prompt eval time = 2185.42 ms / 403 tokens ( 5.42 ms per token, 184.40 tokens per second) 26.41.463.101 I slot print_timing: id 3 | task 26403 | eval time = 649.21 ms / 2 tokens ( 649.21 ms per token, 1.54 tokens per second) 26.41.463.101 I slot print_timing: id 3 | task 26403 | total time = 2834.63 ms / 405 tokens 26.41.463.101 I slot print_timing: id 3 | task 26403 | graphs reused = 24885 26.41.463.102 I slot print_timing: id 3 | task 26403 | graph reallocs = 0 / 0 (same size) / (changed size) 26.41.463.200 I slot release: id 3 | task 26403 | stop processing: n_tokens = 2092, truncated = 0 26.41.505.623 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.864 26.41.505.662 I slot launch_slot_: id 1 | task 26409 | processing task, is_child = 0 26.41.517.618 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.887 26.41.517.641 I slot launch_slot_: id 2 | task 26410 | processing task, is_child = 0 26.41.517.733 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.842 (> 0.100 thold), f_keep = 0.848 26.41.517.751 I slot launch_slot_: id 3 | task 26411 | processing task, is_child = 0 26.43.009.121 I slot print_timing: id 0 | task 26406 | prompt eval time = 691.68 ms / 425 tokens ( 1.63 ms per token, 614.44 tokens per second) 26.43.009.124 I slot print_timing: id 0 | task 26406 | eval time = 1503.50 ms / 2 tokens ( 1503.50 ms per token, 0.67 tokens per second) 26.43.009.124 I slot print_timing: id 0 | task 26406 | total time = 2195.18 ms / 427 tokens 26.43.009.125 I slot print_timing: id 0 | task 26406 | graphs reused = 24885 26.43.009.125 I slot print_timing: id 0 | task 26406 | graph reallocs = 0 / 0 (same size) / (changed size) 26.43.009.238 I slot release: id 0 | task 26406 | stop processing: n_tokens = 1959, truncated = 0 26.43.814.057 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.905 26.43.814.093 I slot launch_slot_: id 0 | task 26414 | processing task, is_child = 0 26.44.503.272 I slot print_timing: id 1 | task 26409 | prompt eval time = 2295.96 ms / 444 tokens ( 5.17 ms per token, 193.38 tokens per second) 26.44.503.277 I slot print_timing: id 1 | task 26409 | eval time = 689.55 ms / 2 tokens ( 689.55 ms per token, 1.45 tokens per second) 26.44.503.278 I slot print_timing: id 1 | task 26409 | total time = 2985.51 ms / 446 tokens 26.44.503.278 I slot print_timing: id 1 | task 26409 | graphs reused = 24885 26.44.503.279 I slot print_timing: id 1 | task 26409 | graph reallocs = 0 / 0 (same size) / (changed size) 26.44.503.394 I slot release: id 1 | task 26409 | stop processing: n_tokens = 2055, truncated = 0 26.44.504.049 I slot print_timing: id 3 | task 26411 | prompt eval time = 2296.09 ms / 418 tokens ( 5.49 ms per token, 182.05 tokens per second) 26.44.504.051 I slot print_timing: id 3 | task 26411 | eval time = 689.99 ms / 2 tokens ( 689.99 ms per token, 1.45 tokens per second) 26.44.504.052 I slot print_timing: id 3 | task 26411 | total time = 2986.09 ms / 420 tokens 26.44.504.052 I slot print_timing: id 3 | task 26411 | graphs reused = 24885 26.44.504.053 I slot print_timing: id 3 | task 26411 | graph reallocs = 0 / 0 (same size) / (changed size) 26.44.504.166 I slot release: id 3 | task 26411 | stop processing: n_tokens = 2107, truncated = 0 26.44.563.754 I slot print_timing: id 2 | task 26410 | prompt eval time = 2985.80 ms / 555 tokens ( 5.38 ms per token, 185.88 tokens per second) 26.44.563.756 I slot print_timing: id 2 | task 26410 | eval time = 60.06 ms / 2 tokens ( 60.06 ms per token, 16.65 tokens per second) 26.44.563.757 I slot print_timing: id 2 | task 26410 | total time = 3045.86 ms / 557 tokens 26.44.563.757 I slot print_timing: id 2 | task 26410 | graphs reused = 24885 26.44.563.758 I slot print_timing: id 2 | task 26410 | graph reallocs = 0 / 0 (same size) / (changed size) 26.44.563.866 I slot release: id 2 | task 26410 | stop processing: n_tokens = 2156, truncated = 0 26.44.563.876 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.863 26.44.563.908 I slot launch_slot_: id 1 | task 26417 | processing task, is_child = 0 26.44.577.325 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.820 (> 0.100 thold), f_keep = 0.842 26.44.577.355 I slot launch_slot_: id 3 | task 26418 | processing task, is_child = 0 26.44.577.457 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.822 26.44.577.474 I slot launch_slot_: id 2 | task 26419 | processing task, is_child = 0 26.46.613.755 I slot print_timing: id 0 | task 26414 | prompt eval time = 749.38 ms / 425 tokens ( 1.76 ms per token, 567.14 tokens per second) 26.46.613.758 I slot print_timing: id 0 | task 26414 | eval time = 2050.28 ms / 2 tokens ( 2050.28 ms per token, 0.49 tokens per second) 26.46.613.759 I slot print_timing: id 0 | task 26414 | total time = 2799.65 ms / 427 tokens 26.46.613.759 I slot print_timing: id 0 | task 26414 | graphs reused = 24885 26.46.613.760 I slot print_timing: id 0 | task 26414 | graph reallocs = 0 / 0 (same size) / (changed size) 26.46.613.870 I slot release: id 0 | task 26414 | stop processing: n_tokens = 1959, truncated = 0 26.46.719.411 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.906 26.46.719.448 I slot launch_slot_: id 0 | task 26422 | processing task, is_child = 0 26.47.415.558 I slot print_timing: id 1 | task 26417 | prompt eval time = 2141.16 ms / 409 tokens ( 5.24 ms per token, 191.02 tokens per second) 26.47.415.569 I slot print_timing: id 1 | task 26417 | eval time = 696.91 ms / 2 tokens ( 696.91 ms per token, 1.43 tokens per second) 26.47.415.569 I slot print_timing: id 1 | task 26417 | total time = 2838.07 ms / 411 tokens 26.47.415.570 I slot print_timing: id 1 | task 26417 | graphs reused = 24885 26.47.415.570 I slot print_timing: id 1 | task 26417 | graph reallocs = 0 / 0 (same size) / (changed size) 26.47.415.685 I slot release: id 1 | task 26417 | stop processing: n_tokens = 2020, truncated = 0 26.47.416.002 I slot print_timing: id 2 | task 26419 | prompt eval time = 2141.34 ms / 338 tokens ( 6.34 ms per token, 157.84 tokens per second) 26.47.416.005 I slot print_timing: id 2 | task 26419 | eval time = 697.04 ms / 2 tokens ( 697.04 ms per token, 1.43 tokens per second) 26.47.416.006 I slot print_timing: id 2 | task 26419 | total time = 2838.38 ms / 340 tokens 26.47.416.006 I slot print_timing: id 2 | task 26419 | graphs reused = 24885 26.47.416.007 I slot print_timing: id 2 | task 26419 | graph reallocs = 0 / 0 (same size) / (changed size) 26.47.416.096 I slot release: id 2 | task 26419 | stop processing: n_tokens = 1978, truncated = 0 26.47.416.462 I slot print_timing: id 3 | task 26418 | prompt eval time = 2141.68 ms / 475 tokens ( 4.51 ms per token, 221.79 tokens per second) 26.47.416.467 I slot print_timing: id 3 | task 26418 | eval time = 697.05 ms / 2 tokens ( 697.05 ms per token, 1.43 tokens per second) 26.47.416.468 I slot print_timing: id 3 | task 26418 | total time = 2838.74 ms / 477 tokens 26.47.416.468 I slot print_timing: id 3 | task 26418 | graphs reused = 24885 26.47.416.468 I slot print_timing: id 3 | task 26418 | graph reallocs = 0 / 0 (same size) / (changed size) 26.47.416.590 I slot release: id 3 | task 26418 | stop processing: n_tokens = 2164, truncated = 0 26.47.459.216 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.878 26.47.459.244 I slot launch_slot_: id 1 | task 26425 | processing task, is_child = 0 26.47.471.628 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.896 26.47.471.658 I slot launch_slot_: id 2 | task 26426 | processing task, is_child = 0 26.47.471.762 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.820 26.47.471.782 I slot launch_slot_: id 3 | task 26427 | processing task, is_child = 0 26.48.924.312 I slot print_timing: id 0 | task 26422 | prompt eval time = 739.76 ms / 471 tokens ( 1.57 ms per token, 636.70 tokens per second) 26.48.924.315 I slot print_timing: id 0 | task 26422 | eval time = 1465.10 ms / 2 tokens ( 1465.10 ms per token, 0.68 tokens per second) 26.48.924.315 I slot print_timing: id 0 | task 26422 | total time = 2204.85 ms / 473 tokens 26.48.924.316 I slot print_timing: id 0 | task 26422 | graphs reused = 24885 26.48.924.316 I slot print_timing: id 0 | task 26422 | graph reallocs = 0 / 0 (same size) / (changed size) 26.48.924.428 I slot release: id 0 | task 26422 | stop processing: n_tokens = 2005, truncated = 0 26.49.029.195 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2005, t_last = 343969760126 26.49.036.592 I slot launch_slot_: id 0 | task 26430 | processing task, is_child = 0 26.50.321.462 I slot print_timing: id 1 | task 26425 | prompt eval time = 1556.71 ms / 281 tokens ( 5.54 ms per token, 180.51 tokens per second) 26.50.321.465 I slot print_timing: id 1 | task 26425 | eval time = 1292.95 ms / 2 tokens ( 1292.95 ms per token, 0.77 tokens per second) 26.50.321.465 I slot print_timing: id 1 | task 26425 | total time = 2849.67 ms / 283 tokens 26.50.321.466 I slot print_timing: id 1 | task 26425 | graphs reused = 24885 26.50.321.466 I slot print_timing: id 1 | task 26425 | graph reallocs = 0 / 0 (same size) / (changed size) 26.50.321.578 I slot release: id 1 | task 26425 | stop processing: n_tokens = 1892, truncated = 0 26.50.321.933 I slot print_timing: id 2 | task 26426 | prompt eval time = 1556.87 ms / 297 tokens ( 5.24 ms per token, 190.77 tokens per second) 26.50.321.935 I slot print_timing: id 2 | task 26426 | eval time = 1293.14 ms / 2 tokens ( 1293.14 ms per token, 0.77 tokens per second) 26.50.321.936 I slot print_timing: id 2 | task 26426 | total time = 2850.01 ms / 299 tokens 26.50.321.936 I slot print_timing: id 2 | task 26426 | graphs reused = 24885 26.50.321.937 I slot print_timing: id 2 | task 26426 | graph reallocs = 0 / 0 (same size) / (changed size) 26.50.322.023 I slot release: id 2 | task 26426 | stop processing: n_tokens = 1937, truncated = 0 26.50.322.522 I slot print_timing: id 3 | task 26427 | prompt eval time = 1557.18 ms / 289 tokens ( 5.39 ms per token, 185.59 tokens per second) 26.50.322.525 I slot print_timing: id 3 | task 26427 | eval time = 1293.33 ms / 2 tokens ( 1293.33 ms per token, 0.77 tokens per second) 26.50.322.526 I slot print_timing: id 3 | task 26427 | total time = 2850.51 ms / 291 tokens 26.50.322.526 I slot print_timing: id 3 | task 26427 | graphs reused = 24885 26.50.322.526 I slot print_timing: id 3 | task 26427 | graph reallocs = 0 / 0 (same size) / (changed size) 26.50.322.631 I slot release: id 3 | task 26427 | stop processing: n_tokens = 1978, truncated = 0 26.50.329.268 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1892, t_last = 343971157276 26.51.016.540 I slot launch_slot_: id 1 | task 26433 | processing task, is_child = 0 26.51.027.995 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1937, t_last = 343971157722 26.51.028.118 I slot launch_slot_: id 2 | task 26434 | processing task, is_child = 0 26.51.028.219 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1978, t_last = 343971158331 26.51.028.336 I slot launch_slot_: id 3 | task 26435 | processing task, is_child = 0 26.54.064.441 I slot print_timing: id 1 | task 26433 | prompt processing, n_tokens = 465, progress = 0.47, t = 3.04 s / 153.19 tokens per second 26.54.064.497 I slot print_timing: id 2 | task 26434 | prompt processing, n_tokens = 982, progress = 0.66, t = 3.04 s / 323.52 tokens per second 26.54.064.541 I slot print_timing: id 3 | task 26435 | prompt processing, n_tokens = 597, progress = 0.37, t = 3.04 s / 196.69 tokens per second 26.56.282.053 I slot print_timing: id 0 | task 26430 | prompt eval time = 5027.83 ms / 1430 tokens ( 3.52 ms per token, 284.42 tokens per second) 26.56.282.056 I slot print_timing: id 0 | task 26430 | eval time = 2217.62 ms / 2 tokens ( 2217.62 ms per token, 0.45 tokens per second) 26.56.282.057 I slot print_timing: id 0 | task 26430 | total time = 7245.45 ms / 1432 tokens 26.56.282.057 I slot print_timing: id 0 | task 26430 | graphs reused = 24886 26.56.282.058 I slot print_timing: id 0 | task 26430 | graph reallocs = 0 / 0 (same size) / (changed size) 26.56.282.138 I slot release: id 0 | task 26430 | stop processing: n_tokens = 1431, truncated = 0 26.56.282.152 I slot print_timing: id 1 | task 26433 | prompt processing, n_tokens = 977, progress = 1.00, t = 5.25 s / 185.98 tokens per second 26.56.282.328 I slot print_timing: id 2 | task 26434 | prompt processing, n_tokens = 1494, progress = 1.00, t = 5.25 s / 284.41 tokens per second 26.56.282.593 I slot print_timing: id 3 | task 26435 | prompt processing, n_tokens = 1111, progress = 0.68, t = 5.25 s / 211.50 tokens per second 26.57.076.956 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1431, t_last = 343977117836 26.57.083.494 I slot launch_slot_: id 0 | task 26439 | processing task, is_child = 0 26.57.083.621 I slot print_timing: id 3 | task 26435 | prompt processing, n_tokens = 1623, progress = 1.00, t = 6.05 s / 268.38 tokens per second 26.57.777.673 I slot print_timing: id 1 | task 26433 | prompt eval time = 6048.00 ms / 981 tokens ( 6.17 ms per token, 162.20 tokens per second) 26.57.777.676 I slot print_timing: id 1 | task 26433 | eval time = 701.11 ms / 2 tokens ( 701.11 ms per token, 1.43 tokens per second) 26.57.777.677 I slot print_timing: id 1 | task 26433 | total time = 6749.10 ms / 983 tokens 26.57.777.677 I slot print_timing: id 1 | task 26433 | graphs reused = 24886 26.57.777.678 I slot print_timing: id 1 | task 26433 | graph reallocs = 0 / 0 (same size) / (changed size) 26.57.777.736 I slot release: id 1 | task 26433 | stop processing: n_tokens = 982, truncated = 0 26.57.778.154 I slot print_timing: id 2 | task 26434 | prompt eval time = 6048.26 ms / 1498 tokens ( 4.04 ms per token, 247.67 tokens per second) 26.57.778.158 I slot print_timing: id 2 | task 26434 | eval time = 701.20 ms / 2 tokens ( 701.20 ms per token, 1.43 tokens per second) 26.57.778.158 I slot print_timing: id 2 | task 26434 | total time = 6749.46 ms / 1500 tokens 26.57.778.159 I slot print_timing: id 2 | task 26434 | graphs reused = 24886 26.57.778.159 I slot print_timing: id 2 | task 26434 | graph reallocs = 0 / 0 (same size) / (changed size) 26.57.778.233 I slot release: id 2 | task 26434 | stop processing: n_tokens = 1499, truncated = 0 26.58.481.974 I slot print_timing: id 3 | task 26435 | prompt eval time = 6749.73 ms / 1627 tokens ( 4.15 ms per token, 241.05 tokens per second) 26.58.481.976 I slot print_timing: id 3 | task 26435 | eval time = 703.42 ms / 2 tokens ( 703.42 ms per token, 1.42 tokens per second) 26.58.481.977 I slot print_timing: id 3 | task 26435 | total time = 7453.14 ms / 1629 tokens 26.58.481.977 I slot print_timing: id 3 | task 26435 | graphs reused = 24886 26.58.481.978 I slot print_timing: id 3 | task 26435 | graph reallocs = 0 / 0 (same size) / (changed size) 26.58.482.061 I slot release: id 3 | task 26435 | stop processing: n_tokens = 1628, truncated = 0 26.58.482.068 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.878 26.58.482.099 I slot launch_slot_: id 1 | task 26442 | processing task, is_child = 0 26.58.493.715 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1499, t_last = 343978613931 26.58.493.819 I slot launch_slot_: id 2 | task 26443 | processing task, is_child = 0 26.58.493.909 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1628, t_last = 343979317760 26.58.494.016 I slot launch_slot_: id 3 | task 26444 | processing task, is_child = 0 27.02.199.346 I slot print_timing: id 0 | task 26439 | prompt eval time = 3631.70 ms / 969 tokens ( 3.75 ms per token, 266.82 tokens per second) 27.02.199.349 I slot print_timing: id 0 | task 26439 | eval time = 1484.14 ms / 2 tokens ( 1484.14 ms per token, 0.67 tokens per second) 27.02.199.349 I slot print_timing: id 0 | task 26439 | total time = 5115.84 ms / 971 tokens 27.02.199.350 I slot print_timing: id 0 | task 26439 | graphs reused = 24886 27.02.199.350 I slot print_timing: id 0 | task 26439 | graph reallocs = 0 / 0 (same size) / (changed size) 27.02.199.418 I slot release: id 0 | task 26439 | stop processing: n_tokens = 970, truncated = 0 27.02.199.766 I slot print_timing: id 2 | task 26443 | prompt processing, n_tokens = 954, progress = 1.00, t = 3.70 s / 257.51 tokens per second 27.02.200.002 I slot print_timing: id 3 | task 26444 | prompt processing, n_tokens = 960, progress = 1.00, t = 3.70 s / 259.14 tokens per second 27.02.293.767 I slot print_timing: id 1 | task 26442 | prompt eval time = 3705.57 ms / 478 tokens ( 7.75 ms per token, 129.00 tokens per second) 27.02.293.770 I slot print_timing: id 1 | task 26442 | eval time = 94.01 ms / 2 tokens ( 94.01 ms per token, 10.64 tokens per second) 27.02.293.771 I slot print_timing: id 1 | task 26442 | total time = 3799.57 ms / 480 tokens 27.02.293.771 I slot print_timing: id 1 | task 26442 | graphs reused = 24886 27.02.293.771 I slot print_timing: id 1 | task 26442 | graph reallocs = 0 / 0 (same size) / (changed size) 27.02.293.829 I slot release: id 1 | task 26442 | stop processing: n_tokens = 944, truncated = 0 27.02.294.676 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.888 27.02.294.736 I slot launch_slot_: id 0 | task 26448 | processing task, is_child = 0 27.02.997.791 I slot print_timing: id 2 | task 26443 | prompt eval time = 3799.90 ms / 958 tokens ( 3.97 ms per token, 252.11 tokens per second) 27.02.997.793 I slot print_timing: id 2 | task 26443 | eval time = 703.56 ms / 2 tokens ( 703.56 ms per token, 1.42 tokens per second) 27.02.997.794 I slot print_timing: id 2 | task 26443 | total time = 4503.46 ms / 960 tokens 27.02.997.794 I slot print_timing: id 2 | task 26443 | graphs reused = 24886 27.02.997.795 I slot print_timing: id 2 | task 26443 | graph reallocs = 0 / 0 (same size) / (changed size) 27.02.997.859 I slot release: id 2 | task 26443 | stop processing: n_tokens = 959, truncated = 0 27.02.998.258 I slot print_timing: id 3 | task 26444 | prompt eval time = 3800.23 ms / 964 tokens ( 3.94 ms per token, 253.67 tokens per second) 27.02.998.260 I slot print_timing: id 3 | task 26444 | eval time = 703.59 ms / 2 tokens ( 703.59 ms per token, 1.42 tokens per second) 27.02.998.261 I slot print_timing: id 3 | task 26444 | total time = 4503.82 ms / 966 tokens 27.02.998.261 I slot print_timing: id 3 | task 26444 | graphs reused = 24886 27.02.998.261 I slot print_timing: id 3 | task 26444 | graph reallocs = 0 / 0 (same size) / (changed size) 27.02.998.309 I slot release: id 3 | task 26444 | stop processing: n_tokens = 965, truncated = 0 27.02.998.315 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.912 27.02.998.352 I slot launch_slot_: id 1 | task 26450 | processing task, is_child = 0 27.03.737.965 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 959, t_last = 343983833557 27.03.738.076 I slot launch_slot_: id 2 | task 26452 | processing task, is_child = 0 27.03.738.131 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 965, t_last = 343983834007 27.03.738.222 I slot launch_slot_: id 3 | task 26453 | processing task, is_child = 0 27.05.907.792 I slot print_timing: id 0 | task 26448 | prompt eval time = 1440.09 ms / 500 tokens ( 2.88 ms per token, 347.20 tokens per second) 27.05.907.794 I slot print_timing: id 0 | task 26448 | eval time = 2169.83 ms / 2 tokens ( 2169.83 ms per token, 0.46 tokens per second) 27.05.907.794 I slot print_timing: id 0 | task 26448 | total time = 3609.92 ms / 502 tokens 27.05.907.795 I slot print_timing: id 0 | task 26448 | graphs reused = 24886 27.05.907.795 I slot print_timing: id 0 | task 26448 | graph reallocs = 0 / 0 (same size) / (changed size) 27.05.907.855 I slot release: id 0 | task 26448 | stop processing: n_tokens = 954, truncated = 0 27.07.325.861 I slot print_timing: id 1 | task 26450 | prompt eval time = 2902.83 ms / 492 tokens ( 5.90 ms per token, 169.49 tokens per second) 27.07.325.864 I slot print_timing: id 1 | task 26450 | eval time = 1417.66 ms / 2 tokens ( 1417.66 ms per token, 0.71 tokens per second) 27.07.325.864 I slot print_timing: id 1 | task 26450 | total time = 4320.49 ms / 494 tokens 27.07.325.864 I slot print_timing: id 1 | task 26450 | graphs reused = 24886 27.07.325.865 I slot print_timing: id 1 | task 26450 | graph reallocs = 0 / 0 (same size) / (changed size) 27.07.325.922 I slot release: id 1 | task 26450 | stop processing: n_tokens = 958, truncated = 0 27.07.325.930 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 343986743553 27.07.330.442 I slot launch_slot_: id 0 | task 26456 | processing task, is_child = 0 27.07.333.294 I slot print_timing: id 2 | task 26452 | prompt processing, n_tokens = 785, progress = 0.99, t = 3.59 s / 218.84 tokens per second 27.07.333.447 I slot print_timing: id 3 | task 26453 | prompt processing, n_tokens = 1619, progress = 1.00, t = 3.59 s / 451.34 tokens per second 27.08.957.399 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 958, t_last = 343988161620 27.08.957.537 I slot launch_slot_: id 1 | task 26458 | processing task, is_child = 0 27.11.285.934 I slot print_timing: id 2 | task 26452 | prompt eval time = 5218.59 ms / 789 tokens ( 6.61 ms per token, 151.19 tokens per second) 27.11.285.945 I slot print_timing: id 2 | task 26452 | eval time = 2328.95 ms / 2 tokens ( 2328.95 ms per token, 0.43 tokens per second) 27.11.285.946 I slot print_timing: id 2 | task 26452 | total time = 7547.54 ms / 791 tokens 27.11.285.946 I slot print_timing: id 2 | task 26452 | graphs reused = 24886 27.11.285.947 I slot print_timing: id 2 | task 26452 | graph reallocs = 0 / 0 (same size) / (changed size) 27.11.285.997 I slot release: id 2 | task 26452 | stop processing: n_tokens = 790, truncated = 0 27.11.286.341 I slot print_timing: id 3 | task 26453 | prompt eval time = 5218.93 ms / 1623 tokens ( 3.22 ms per token, 310.98 tokens per second) 27.11.286.343 I slot print_timing: id 3 | task 26453 | eval time = 2328.95 ms / 2 tokens ( 2328.95 ms per token, 0.43 tokens per second) 27.11.286.344 I slot print_timing: id 3 | task 26453 | total time = 7547.88 ms / 1625 tokens 27.11.286.344 I slot print_timing: id 3 | task 26453 | graphs reused = 24886 27.11.286.344 I slot print_timing: id 3 | task 26453 | graph reallocs = 0 / 0 (same size) / (changed size) 27.11.286.433 I slot release: id 3 | task 26453 | stop processing: n_tokens = 1624, truncated = 0 27.11.286.445 I slot print_timing: id 0 | task 26456 | prompt processing, n_tokens = 1574, progress = 1.00, t = 3.95 s / 398.24 tokens per second 27.12.051.058 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.857 (> 0.100 thold), f_keep = 0.861 27.12.051.105 I slot launch_slot_: id 3 | task 26461 | processing task, is_child = 0 27.12.054.356 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 343992121695 27.12.054.453 I slot launch_slot_: id 2 | task 26462 | processing task, is_child = 0 27.12.054.474 I slot print_timing: id 1 | task 26458 | prompt processing, n_tokens = 1606, progress = 1.00, t = 3.09 s / 519.23 tokens per second 27.13.979.039 I slot print_timing: id 0 | task 26456 | prompt eval time = 4717.84 ms / 1578 tokens ( 2.99 ms per token, 334.48 tokens per second) 27.13.979.041 I slot print_timing: id 0 | task 26456 | eval time = 1927.98 ms / 2 tokens ( 1927.98 ms per token, 0.52 tokens per second) 27.13.979.041 I slot print_timing: id 0 | task 26456 | total time = 6645.82 ms / 1580 tokens 27.13.979.042 I slot print_timing: id 0 | task 26456 | graphs reused = 24886 27.13.979.042 I slot print_timing: id 0 | task 26456 | graph reallocs = 0 / 0 (same size) / (changed size) 27.13.979.138 I slot release: id 0 | task 26456 | stop processing: n_tokens = 1579, truncated = 0 27.15.409.225 I slot print_timing: id 1 | task 26458 | prompt eval time = 5021.97 ms / 1610 tokens ( 3.12 ms per token, 320.59 tokens per second) 27.15.409.227 I slot print_timing: id 1 | task 26458 | eval time = 1429.65 ms / 2 tokens ( 1429.65 ms per token, 0.70 tokens per second) 27.15.409.228 I slot print_timing: id 1 | task 26458 | total time = 6451.62 ms / 1612 tokens 27.15.409.228 I slot print_timing: id 1 | task 26458 | graphs reused = 24886 27.15.409.229 I slot print_timing: id 1 | task 26458 | graph reallocs = 0 / 0 (same size) / (changed size) 27.15.409.334 I slot release: id 1 | task 26458 | stop processing: n_tokens = 1611, truncated = 0 27.15.409.343 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1579, t_last = 343994814837 27.15.415.668 I slot launch_slot_: id 0 | task 26465 | processing task, is_child = 0 27.15.420.145 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1611, t_last = 343996245033 27.15.420.254 I slot launch_slot_: id 1 | task 26466 | processing task, is_child = 0 27.15.420.497 I slot print_timing: id 2 | task 26462 | prompt processing, n_tokens = 1719, progress = 1.00, t = 3.35 s / 512.51 tokens per second 27.15.420.757 I slot print_timing: id 3 | task 26461 | prompt processing, n_tokens = 522, progress = 1.00, t = 3.35 s / 155.63 tokens per second 27.18.057.984 I slot print_timing: id 2 | task 26462 | prompt eval time = 4614.19 ms / 1723 tokens ( 2.68 ms per token, 373.41 tokens per second) 27.18.057.986 I slot print_timing: id 2 | task 26462 | eval time = 1389.00 ms / 2 tokens ( 1389.00 ms per token, 0.72 tokens per second) 27.18.057.987 I slot print_timing: id 2 | task 26462 | total time = 6003.19 ms / 1725 tokens 27.18.057.987 I slot print_timing: id 2 | task 26462 | graphs reused = 24886 27.18.057.988 I slot print_timing: id 2 | task 26462 | graph reallocs = 0 / 0 (same size) / (changed size) 27.18.058.085 I slot release: id 2 | task 26462 | stop processing: n_tokens = 1724, truncated = 0 27.18.058.429 I slot print_timing: id 3 | task 26461 | prompt eval time = 4614.60 ms / 526 tokens ( 8.77 ms per token, 113.99 tokens per second) 27.18.058.431 I slot print_timing: id 3 | task 26461 | eval time = 1388.97 ms / 2 tokens ( 1388.97 ms per token, 0.72 tokens per second) 27.18.058.432 I slot print_timing: id 3 | task 26461 | total time = 6003.57 ms / 528 tokens 27.18.058.432 I slot print_timing: id 3 | task 26461 | graphs reused = 24886 27.18.058.432 I slot print_timing: id 3 | task 26461 | graph reallocs = 0 / 0 (same size) / (changed size) 27.18.058.507 I slot release: id 3 | task 26461 | stop processing: n_tokens = 1634, truncated = 0 27.18.130.769 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1724, t_last = 343998893783 27.18.136.784 I slot launch_slot_: id 2 | task 26470 | processing task, is_child = 0 27.18.141.651 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1634, t_last = 343998894206 27.18.141.761 I slot launch_slot_: id 3 | task 26471 | processing task, is_child = 0 27.19.261.578 I slot print_timing: id 0 | task 26465 | prompt eval time = 2710.13 ms / 826 tokens ( 3.28 ms per token, 304.78 tokens per second) 27.19.261.581 I slot print_timing: id 0 | task 26465 | eval time = 1131.18 ms / 2 tokens ( 1131.18 ms per token, 0.88 tokens per second) 27.19.261.581 I slot print_timing: id 0 | task 26465 | total time = 3841.30 ms / 828 tokens 27.19.261.582 I slot print_timing: id 0 | task 26465 | graphs reused = 24886 27.19.261.582 I slot print_timing: id 0 | task 26465 | graph reallocs = 0 / 0 (same size) / (changed size) 27.19.261.636 I slot release: id 0 | task 26465 | stop processing: n_tokens = 827, truncated = 0 27.19.262.090 I slot print_timing: id 1 | task 26466 | prompt eval time = 2710.38 ms / 854 tokens ( 3.17 ms per token, 315.08 tokens per second) 27.19.262.094 I slot print_timing: id 1 | task 26466 | eval time = 1131.33 ms / 2 tokens ( 1131.33 ms per token, 0.88 tokens per second) 27.19.262.095 I slot print_timing: id 1 | task 26466 | total time = 3841.71 ms / 856 tokens 27.19.262.095 I slot print_timing: id 1 | task 26466 | graphs reused = 24886 27.19.262.095 I slot print_timing: id 1 | task 26466 | graph reallocs = 0 / 0 (same size) / (changed size) 27.19.262.148 I slot release: id 1 | task 26466 | stop processing: n_tokens = 855, truncated = 0 27.19.942.169 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 827, t_last = 344000097334 27.20.624.710 I slot launch_slot_: id 0 | task 26474 | processing task, is_child = 0 27.20.628.435 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 344000097846 27.20.628.536 I slot launch_slot_: id 1 | task 26475 | processing task, is_child = 0 27.23.081.225 I slot print_timing: id 2 | task 26470 | prompt eval time = 3547.28 ms / 828 tokens ( 4.28 ms per token, 233.42 tokens per second) 27.23.081.229 I slot print_timing: id 2 | task 26470 | eval time = 1392.17 ms / 2 tokens ( 1392.17 ms per token, 0.72 tokens per second) 27.23.081.230 I slot print_timing: id 2 | task 26470 | total time = 4939.45 ms / 830 tokens 27.23.081.230 I slot print_timing: id 2 | task 26470 | graphs reused = 24886 27.23.081.231 I slot print_timing: id 2 | task 26470 | graph reallocs = 0 / 0 (same size) / (changed size) 27.23.081.282 I slot release: id 2 | task 26470 | stop processing: n_tokens = 829, truncated = 0 27.23.081.622 I slot print_timing: id 3 | task 26471 | prompt eval time = 3547.54 ms / 847 tokens ( 4.19 ms per token, 238.76 tokens per second) 27.23.081.627 I slot print_timing: id 3 | task 26471 | eval time = 1392.20 ms / 2 tokens ( 1392.20 ms per token, 0.72 tokens per second) 27.23.081.627 I slot print_timing: id 3 | task 26471 | total time = 4939.74 ms / 849 tokens 27.23.081.627 I slot print_timing: id 3 | task 26471 | graphs reused = 24886 27.23.081.628 I slot print_timing: id 3 | task 26471 | graph reallocs = 0 / 0 (same size) / (changed size) 27.23.081.675 I slot release: id 3 | task 26471 | stop processing: n_tokens = 848, truncated = 0 27.23.154.206 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 829, t_last = 344003916980 27.23.156.711 I slot launch_slot_: id 2 | task 26479 | processing task, is_child = 0 27.23.159.194 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 848, t_last = 344003917373 27.23.159.269 I slot launch_slot_: id 3 | task 26480 | processing task, is_child = 0 27.23.908.327 I slot print_timing: id 0 | task 26474 | prompt eval time = 2525.24 ms / 867 tokens ( 2.91 ms per token, 343.33 tokens per second) 27.23.908.332 I slot print_timing: id 0 | task 26474 | eval time = 754.53 ms / 2 tokens ( 754.53 ms per token, 1.33 tokens per second) 27.23.908.333 I slot print_timing: id 0 | task 26474 | total time = 3279.77 ms / 869 tokens 27.23.908.333 I slot print_timing: id 0 | task 26474 | graphs reused = 24886 27.23.908.334 I slot print_timing: id 0 | task 26474 | graph reallocs = 0 / 0 (same size) / (changed size) 27.23.908.385 I slot release: id 0 | task 26474 | stop processing: n_tokens = 868, truncated = 0 27.23.908.846 I slot print_timing: id 1 | task 26475 | prompt eval time = 2525.57 ms / 759 tokens ( 3.33 ms per token, 300.53 tokens per second) 27.23.908.849 I slot print_timing: id 1 | task 26475 | eval time = 754.64 ms / 2 tokens ( 754.64 ms per token, 1.33 tokens per second) 27.23.908.849 I slot print_timing: id 1 | task 26475 | total time = 3280.22 ms / 761 tokens 27.23.908.849 I slot print_timing: id 1 | task 26475 | graphs reused = 24886 27.23.908.850 I slot print_timing: id 1 | task 26475 | graph reallocs = 0 / 0 (same size) / (changed size) 27.23.908.890 I slot release: id 1 | task 26475 | stop processing: n_tokens = 760, truncated = 0 27.24.592.387 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 868, t_last = 344004744083 27.25.276.997 I slot launch_slot_: id 0 | task 26483 | processing task, is_child = 0 27.25.279.987 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 760, t_last = 344004744588 27.25.280.075 I slot launch_slot_: id 1 | task 26484 | processing task, is_child = 0 27.27.422.393 I slot print_timing: id 2 | task 26479 | prompt eval time = 2882.52 ms / 728 tokens ( 3.96 ms per token, 252.56 tokens per second) 27.27.422.399 I slot print_timing: id 2 | task 26479 | eval time = 1380.59 ms / 2 tokens ( 1380.59 ms per token, 0.72 tokens per second) 27.27.422.399 I slot print_timing: id 2 | task 26479 | total time = 4263.12 ms / 730 tokens 27.27.422.399 I slot print_timing: id 2 | task 26479 | graphs reused = 24886 27.27.422.400 I slot print_timing: id 2 | task 26479 | graph reallocs = 0 / 0 (same size) / (changed size) 27.27.422.441 I slot release: id 2 | task 26479 | stop processing: n_tokens = 729, truncated = 0 27.27.422.750 I slot print_timing: id 3 | task 26480 | prompt eval time = 2882.76 ms / 682 tokens ( 4.23 ms per token, 236.58 tokens per second) 27.27.422.754 I slot print_timing: id 3 | task 26480 | eval time = 1380.65 ms / 2 tokens ( 1380.65 ms per token, 0.72 tokens per second) 27.27.422.754 I slot print_timing: id 3 | task 26480 | total time = 4263.41 ms / 684 tokens 27.27.422.755 I slot print_timing: id 3 | task 26480 | graphs reused = 24886 27.27.422.755 I slot print_timing: id 3 | task 26480 | graph reallocs = 0 / 0 (same size) / (changed size) 27.27.422.788 I slot release: id 3 | task 26480 | stop processing: n_tokens = 683, truncated = 0 27.27.523.555 I slot print_timing: id 0 | task 26483 | prompt eval time = 2215.05 ms / 665 tokens ( 3.33 ms per token, 300.22 tokens per second) 27.27.523.557 I slot print_timing: id 0 | task 26483 | eval time = 28.42 ms / 2 tokens ( 28.42 ms per token, 35.19 tokens per second) 27.27.523.557 I slot print_timing: id 0 | task 26483 | total time = 2243.47 ms / 667 tokens 27.27.523.558 I slot print_timing: id 0 | task 26483 | graphs reused = 24886 27.27.523.558 I slot print_timing: id 0 | task 26483 | graph reallocs = 0 / 0 (same size) / (changed size) 27.27.523.600 I slot release: id 0 | task 26483 | stop processing: n_tokens = 666, truncated = 0 27.27.523.878 I slot print_timing: id 1 | task 26484 | prompt eval time = 2215.37 ms / 700 tokens ( 3.16 ms per token, 315.97 tokens per second) 27.27.523.881 I slot print_timing: id 1 | task 26484 | eval time = 28.36 ms / 2 tokens ( 28.36 ms per token, 35.26 tokens per second) 27.27.523.881 I slot print_timing: id 1 | task 26484 | total time = 2243.73 ms / 702 tokens 27.27.523.881 I slot print_timing: id 1 | task 26484 | graphs reused = 24886 27.27.523.882 I slot print_timing: id 1 | task 26484 | graph reallocs = 0 / 0 (same size) / (changed size) 27.27.523.921 I slot release: id 1 | task 26484 | stop processing: n_tokens = 701, truncated = 0 27.30.435.814 I srv operator(): operator(): cleaning up before exit...