/Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/d3334405b962/LFM2.5-24B-A2B-Q4_K_M.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 0.00.049.300 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.049.367 I srv llama_server: initializing ... 0.00.049.371 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.049.453 I srv init_listene: The UI is disabled 0.00.049.455 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.049.488 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) 0.00.051.144 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/d3334405b962/LFM2.5-24B-A2B-Q4_K_M.gguf' 0.01.037.434 I cmn init: llama threadpool init, n_threads = 8 0.01.106.161 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.01.109.094 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.109.109 I srv llama_server: model loaded 0.01.109.115 I srv llama_server: listening on http://127.0.0.1:8091 0.31.194.585 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.194.609 I slot launch_slot_: id 0 | task 1 | processing task, is_child = 0 0.31.194.610 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.194.621 I slot launch_slot_: id 1 | task 3 | processing task, is_child = 0 0.31.194.622 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.194.630 I slot launch_slot_: id 2 | task 0 | processing task, is_child = 0 0.31.194.631 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.194.639 I slot launch_slot_: id 3 | task 2 | processing task, is_child = 0 0.32.140.365 I slot print_timing: id 0 | task 1 | prompt eval time = 906.78 ms / 123 tokens ( 7.37 ms per token, 135.64 tokens per second) 0.32.140.370 I slot print_timing: id 0 | task 1 | eval time = 38.93 ms / 2 tokens ( 38.93 ms per token, 25.69 tokens per second) 0.32.140.371 I slot print_timing: id 0 | task 1 | total time = 945.72 ms / 125 tokens 0.32.140.371 I slot print_timing: id 0 | task 1 | graphs reused = 1 0.32.140.371 I slot print_timing: id 0 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.140.393 I slot release: id 0 | task 1 | stop processing: n_tokens = 124, truncated = 0 0.32.140.656 I slot print_timing: id 1 | task 3 | prompt eval time = 907.12 ms / 117 tokens ( 7.75 ms per token, 128.98 tokens per second) 0.32.140.658 I slot print_timing: id 1 | task 3 | eval time = 38.88 ms / 2 tokens ( 38.88 ms per token, 25.72 tokens per second) 0.32.140.658 I slot print_timing: id 1 | task 3 | total time = 946.00 ms / 119 tokens 0.32.140.658 I slot print_timing: id 1 | task 3 | graphs reused = 1 0.32.140.659 I slot print_timing: id 1 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.140.670 I slot release: id 1 | task 3 | stop processing: n_tokens = 118, truncated = 0 0.32.141.038 I slot print_timing: id 2 | task 0 | prompt eval time = 907.61 ms / 112 tokens ( 8.10 ms per token, 123.40 tokens per second) 0.32.141.040 I slot print_timing: id 2 | task 0 | eval time = 38.78 ms / 2 tokens ( 38.78 ms per token, 25.79 tokens per second) 0.32.141.041 I slot print_timing: id 2 | task 0 | total time = 946.38 ms / 114 tokens 0.32.141.041 I slot print_timing: id 2 | task 0 | graphs reused = 1 0.32.141.041 I slot print_timing: id 2 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.141.057 I slot release: id 2 | task 0 | stop processing: n_tokens = 113, truncated = 0 0.32.141.355 I slot print_timing: id 3 | task 2 | prompt eval time = 908.10 ms / 131 tokens ( 6.93 ms per token, 144.26 tokens per second) 0.32.141.357 I slot print_timing: id 3 | task 2 | eval time = 38.59 ms / 2 tokens ( 38.59 ms per token, 25.91 tokens per second) 0.32.141.357 I slot print_timing: id 3 | task 2 | total time = 946.69 ms / 133 tokens 0.32.141.358 I slot print_timing: id 3 | task 2 | graphs reused = 1 0.32.141.358 I slot print_timing: id 3 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.141.368 I slot release: id 3 | task 2 | stop processing: n_tokens = 132, truncated = 0 0.32.148.040 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.242 0.32.148.336 I slot launch_slot_: id 0 | task 7 | processing task, is_child = 0 0.32.149.374 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.254 0.32.149.408 I slot launch_slot_: id 1 | task 8 | processing task, is_child = 0 0.32.149.439 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.257 0.32.149.469 I slot launch_slot_: id 2 | task 9 | processing task, is_child = 0 0.32.149.487 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.220 0.32.149.513 I slot launch_slot_: id 3 | task 10 | processing task, is_child = 0 0.33.323.026 I slot print_timing: id 0 | task 7 | prompt eval time = 1135.90 ms / 110 tokens ( 10.33 ms per token, 96.84 tokens per second) 0.33.323.028 I slot print_timing: id 0 | task 7 | eval time = 37.61 ms / 2 tokens ( 37.61 ms per token, 26.59 tokens per second) 0.33.323.029 I slot print_timing: id 0 | task 7 | total time = 1173.50 ms / 112 tokens 0.33.323.029 I slot print_timing: id 0 | task 7 | graphs reused = 1 0.33.323.029 I slot print_timing: id 0 | task 7 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.323.047 I slot release: id 0 | task 7 | stop processing: n_tokens = 111, truncated = 0 0.33.323.331 I slot print_timing: id 1 | task 8 | prompt eval time = 1136.17 ms / 161 tokens ( 7.06 ms per token, 141.70 tokens per second) 0.33.323.333 I slot print_timing: id 1 | task 8 | eval time = 37.62 ms / 2 tokens ( 37.62 ms per token, 26.58 tokens per second) 0.33.323.334 I slot print_timing: id 1 | task 8 | total time = 1173.80 ms / 163 tokens 0.33.323.334 I slot print_timing: id 1 | task 8 | graphs reused = 1 0.33.323.334 I slot print_timing: id 1 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.323.351 I slot release: id 1 | task 8 | stop processing: n_tokens = 162, truncated = 0 0.33.323.634 I slot print_timing: id 2 | task 9 | prompt eval time = 1136.46 ms / 161 tokens ( 7.06 ms per token, 141.67 tokens per second) 0.33.323.637 I slot print_timing: id 2 | task 9 | eval time = 37.63 ms / 2 tokens ( 37.63 ms per token, 26.57 tokens per second) 0.33.323.638 I slot print_timing: id 2 | task 9 | total time = 1174.09 ms / 163 tokens 0.33.323.638 I slot print_timing: id 2 | task 9 | graphs reused = 1 0.33.323.638 I slot print_timing: id 2 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.323.653 I slot release: id 2 | task 9 | stop processing: n_tokens = 162, truncated = 0 0.33.323.976 I slot print_timing: id 3 | task 10 | prompt eval time = 1136.78 ms / 199 tokens ( 5.71 ms per token, 175.06 tokens per second) 0.33.323.978 I slot print_timing: id 3 | task 10 | eval time = 37.64 ms / 2 tokens ( 37.64 ms per token, 26.56 tokens per second) 0.33.323.978 I slot print_timing: id 3 | task 10 | total time = 1174.42 ms / 201 tokens 0.33.323.978 I slot print_timing: id 3 | task 10 | graphs reused = 1 0.33.323.979 I slot print_timing: id 3 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.324.002 I slot release: id 3 | task 10 | stop processing: n_tokens = 200, truncated = 0 0.33.329.030 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.270 0.33.329.457 I slot launch_slot_: id 0 | task 15 | processing task, is_child = 0 0.33.330.592 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.179 0.33.330.623 I slot launch_slot_: id 1 | task 14 | processing task, is_child = 0 0.33.330.658 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.179 0.33.330.686 I slot launch_slot_: id 2 | task 16 | processing task, is_child = 0 0.33.330.706 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.145 0.33.330.735 I slot launch_slot_: id 3 | task 17 | processing task, is_child = 0 0.34.338.210 I slot print_timing: id 0 | task 15 | prompt eval time = 969.70 ms / 119 tokens ( 8.15 ms per token, 122.72 tokens per second) 0.34.338.213 I slot print_timing: id 0 | task 15 | eval time = 37.77 ms / 2 tokens ( 37.77 ms per token, 26.48 tokens per second) 0.34.338.213 I slot print_timing: id 0 | task 15 | total time = 1007.47 ms / 121 tokens 0.34.338.214 I slot print_timing: id 0 | task 15 | graphs reused = 1 0.34.338.214 I slot print_timing: id 0 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.338.237 I slot release: id 0 | task 15 | stop processing: n_tokens = 120, truncated = 0 0.34.338.593 I slot print_timing: id 1 | task 14 | prompt eval time = 970.05 ms / 116 tokens ( 8.36 ms per token, 119.58 tokens per second) 0.34.338.595 I slot print_timing: id 1 | task 14 | eval time = 37.79 ms / 2 tokens ( 37.79 ms per token, 26.46 tokens per second) 0.34.338.595 I slot print_timing: id 1 | task 14 | total time = 1007.84 ms / 118 tokens 0.34.338.595 I slot print_timing: id 1 | task 14 | graphs reused = 1 0.34.338.596 I slot print_timing: id 1 | task 14 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.338.609 I slot release: id 1 | task 14 | stop processing: n_tokens = 117, truncated = 0 0.34.338.891 I slot print_timing: id 2 | task 16 | prompt eval time = 970.35 ms / 151 tokens ( 6.43 ms per token, 155.61 tokens per second) 0.34.338.893 I slot print_timing: id 2 | task 16 | eval time = 37.77 ms / 2 tokens ( 37.77 ms per token, 26.47 tokens per second) 0.34.338.893 I slot print_timing: id 2 | task 16 | total time = 1008.13 ms / 153 tokens 0.34.338.897 I slot print_timing: id 2 | task 16 | graphs reused = 1 0.34.338.898 I slot print_timing: id 2 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.338.911 I slot release: id 2 | task 16 | stop processing: n_tokens = 152, truncated = 0 0.34.339.194 I slot print_timing: id 3 | task 17 | prompt eval time = 970.74 ms / 127 tokens ( 7.64 ms per token, 130.83 tokens per second) 0.34.339.196 I slot print_timing: id 3 | task 17 | eval time = 37.68 ms / 2 tokens ( 37.68 ms per token, 26.54 tokens per second) 0.34.339.197 I slot print_timing: id 3 | task 17 | total time = 1008.42 ms / 129 tokens 0.34.339.197 I slot print_timing: id 3 | task 17 | graphs reused = 1 0.34.339.197 I slot print_timing: id 3 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.339.215 I slot release: id 3 | task 17 | stop processing: n_tokens = 128, truncated = 0 0.34.343.046 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.242 0.34.343.428 I slot launch_slot_: id 0 | task 21 | processing task, is_child = 0 0.34.344.555 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.248 0.34.344.585 I slot launch_slot_: id 1 | task 22 | processing task, is_child = 0 0.34.344.617 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.191 0.34.344.645 I slot launch_slot_: id 2 | task 23 | processing task, is_child = 0 0.34.344.662 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.227 0.34.344.689 I slot launch_slot_: id 3 | task 24 | processing task, is_child = 0 0.35.515.807 I slot print_timing: id 0 | task 21 | prompt eval time = 1133.86 ms / 184 tokens ( 6.16 ms per token, 162.28 tokens per second) 0.35.515.812 I slot print_timing: id 0 | task 21 | eval time = 37.25 ms / 2 tokens ( 37.25 ms per token, 26.85 tokens per second) 0.35.515.812 I slot print_timing: id 0 | task 21 | total time = 1171.11 ms / 186 tokens 0.35.515.813 I slot print_timing: id 0 | task 21 | graphs reused = 1 0.35.515.813 I slot print_timing: id 0 | task 21 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.515.839 I slot release: id 0 | task 21 | stop processing: n_tokens = 185, truncated = 0 0.35.516.117 I slot print_timing: id 1 | task 22 | prompt eval time = 1134.13 ms / 135 tokens ( 8.40 ms per token, 119.03 tokens per second) 0.35.516.119 I slot print_timing: id 1 | task 22 | eval time = 37.28 ms / 2 tokens ( 37.28 ms per token, 26.82 tokens per second) 0.35.516.119 I slot print_timing: id 1 | task 22 | total time = 1171.41 ms / 137 tokens 0.35.516.119 I slot print_timing: id 1 | task 22 | graphs reused = 1 0.35.516.120 I slot print_timing: id 1 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.516.135 I slot release: id 1 | task 22 | stop processing: n_tokens = 136, truncated = 0 0.35.516.514 I slot print_timing: id 2 | task 23 | prompt eval time = 1134.48 ms / 143 tokens ( 7.93 ms per token, 126.05 tokens per second) 0.35.516.516 I slot print_timing: id 2 | task 23 | eval time = 37.32 ms / 2 tokens ( 37.32 ms per token, 26.80 tokens per second) 0.35.516.517 I slot print_timing: id 2 | task 23 | total time = 1171.80 ms / 145 tokens 0.35.516.517 I slot print_timing: id 2 | task 23 | graphs reused = 1 0.35.516.517 I slot print_timing: id 2 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.516.533 I slot release: id 2 | task 23 | stop processing: n_tokens = 144, truncated = 0 0.35.516.867 I slot print_timing: id 3 | task 24 | prompt eval time = 1134.76 ms / 120 tokens ( 9.46 ms per token, 105.75 tokens per second) 0.35.516.870 I slot print_timing: id 3 | task 24 | eval time = 37.38 ms / 2 tokens ( 37.38 ms per token, 26.75 tokens per second) 0.35.516.870 I slot print_timing: id 3 | task 24 | total time = 1172.14 ms / 122 tokens 0.35.516.870 I slot print_timing: id 3 | task 24 | graphs reused = 1 0.35.516.871 I slot print_timing: id 3 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.516.884 I slot release: id 3 | task 24 | stop processing: n_tokens = 121, truncated = 0 0.35.520.831 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.157 0.35.521.487 I slot launch_slot_: id 0 | task 29 | processing task, is_child = 0 0.35.522.525 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.213 0.35.522.563 I slot launch_slot_: id 1 | task 28 | processing task, is_child = 0 0.35.522.594 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.201 0.35.522.622 I slot launch_slot_: id 2 | task 30 | processing task, is_child = 0 0.35.522.638 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.240 0.35.522.768 I slot launch_slot_: id 3 | task 31 | processing task, is_child = 0 0.36.671.006 I slot print_timing: id 0 | task 29 | prompt eval time = 1110.57 ms / 125 tokens ( 8.88 ms per token, 112.55 tokens per second) 0.36.671.008 I slot print_timing: id 0 | task 29 | eval time = 37.65 ms / 2 tokens ( 37.65 ms per token, 26.56 tokens per second) 0.36.671.009 I slot print_timing: id 0 | task 29 | total time = 1148.23 ms / 127 tokens 0.36.671.009 I slot print_timing: id 0 | task 29 | graphs reused = 1 0.36.671.010 I slot print_timing: id 0 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.671.031 I slot release: id 0 | task 29 | stop processing: n_tokens = 126, truncated = 0 0.36.671.299 I slot print_timing: id 1 | task 28 | prompt eval time = 1110.83 ms / 141 tokens ( 7.88 ms per token, 126.93 tokens per second) 0.36.671.301 I slot print_timing: id 1 | task 28 | eval time = 37.68 ms / 2 tokens ( 37.68 ms per token, 26.54 tokens per second) 0.36.671.301 I slot print_timing: id 1 | task 28 | total time = 1148.51 ms / 143 tokens 0.36.671.302 I slot print_timing: id 1 | task 28 | graphs reused = 1 0.36.671.302 I slot print_timing: id 1 | task 28 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.671.317 I slot release: id 1 | task 28 | stop processing: n_tokens = 142, truncated = 0 0.36.671.601 I slot print_timing: id 2 | task 30 | prompt eval time = 1111.11 ms / 179 tokens ( 6.21 ms per token, 161.10 tokens per second) 0.36.671.603 I slot print_timing: id 2 | task 30 | eval time = 37.69 ms / 2 tokens ( 37.69 ms per token, 26.53 tokens per second) 0.36.671.603 I slot print_timing: id 2 | task 30 | total time = 1148.80 ms / 181 tokens 0.36.671.603 I slot print_timing: id 2 | task 30 | graphs reused = 1 0.36.671.604 I slot print_timing: id 2 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.671.620 I slot release: id 2 | task 30 | stop processing: n_tokens = 180, truncated = 0 0.36.671.912 I slot print_timing: id 3 | task 31 | prompt eval time = 1111.41 ms / 131 tokens ( 8.48 ms per token, 117.87 tokens per second) 0.36.671.914 I slot print_timing: id 3 | task 31 | eval time = 37.69 ms / 2 tokens ( 37.69 ms per token, 26.53 tokens per second) 0.36.671.915 I slot print_timing: id 3 | task 31 | total time = 1149.10 ms / 133 tokens 0.36.671.915 I slot print_timing: id 3 | task 31 | graphs reused = 1 0.36.671.915 I slot print_timing: id 3 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.671.925 I slot release: id 3 | task 31 | stop processing: n_tokens = 132, truncated = 0 0.36.675.602 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.230 0.36.675.974 I slot launch_slot_: id 0 | task 35 | processing task, is_child = 0 0.36.677.115 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.167 0.36.677.150 I slot launch_slot_: id 2 | task 36 | processing task, is_child = 0 0.36.677.182 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.204 0.36.677.210 I slot launch_slot_: id 1 | task 37 | processing task, is_child = 0 0.36.677.228 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.227 0.36.677.256 I slot launch_slot_: id 3 | task 38 | processing task, is_child = 0 0.37.732.593 I slot print_timing: id 0 | task 35 | prompt eval time = 1017.87 ms / 113 tokens ( 9.01 ms per token, 111.02 tokens per second) 0.37.732.595 I slot print_timing: id 0 | task 35 | eval time = 37.46 ms / 2 tokens ( 37.46 ms per token, 26.69 tokens per second) 0.37.732.596 I slot print_timing: id 0 | task 35 | total time = 1055.33 ms / 115 tokens 0.37.732.596 I slot print_timing: id 0 | task 35 | graphs reused = 1 0.37.732.597 I slot print_timing: id 0 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.732.618 I slot release: id 0 | task 35 | stop processing: n_tokens = 114, truncated = 0 0.37.732.883 I slot print_timing: id 1 | task 37 | prompt eval time = 1018.12 ms / 143 tokens ( 7.12 ms per token, 140.45 tokens per second) 0.37.732.889 I slot print_timing: id 1 | task 37 | eval time = 37.49 ms / 2 tokens ( 37.49 ms per token, 26.68 tokens per second) 0.37.732.889 I slot print_timing: id 1 | task 37 | total time = 1055.61 ms / 145 tokens 0.37.732.889 I slot print_timing: id 1 | task 37 | graphs reused = 1 0.37.732.890 I slot print_timing: id 1 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.732.907 I slot release: id 1 | task 37 | stop processing: n_tokens = 144, truncated = 0 0.37.733.194 I slot print_timing: id 2 | task 36 | prompt eval time = 1018.41 ms / 145 tokens ( 7.02 ms per token, 142.38 tokens per second) 0.37.733.196 I slot print_timing: id 2 | task 36 | eval time = 37.50 ms / 2 tokens ( 37.50 ms per token, 26.67 tokens per second) 0.37.733.197 I slot print_timing: id 2 | task 36 | total time = 1055.91 ms / 147 tokens 0.37.733.197 I slot print_timing: id 2 | task 36 | graphs reused = 1 0.37.733.197 I slot print_timing: id 2 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.733.209 I slot release: id 2 | task 36 | stop processing: n_tokens = 146, truncated = 0 0.37.733.497 I slot print_timing: id 3 | task 38 | prompt eval time = 1018.68 ms / 122 tokens ( 8.35 ms per token, 119.76 tokens per second) 0.37.733.498 I slot print_timing: id 3 | task 38 | eval time = 37.51 ms / 2 tokens ( 37.51 ms per token, 26.66 tokens per second) 0.37.733.499 I slot print_timing: id 3 | task 38 | total time = 1056.19 ms / 124 tokens 0.37.733.499 I slot print_timing: id 3 | task 38 | graphs reused = 1 0.37.733.499 I slot print_timing: id 3 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.733.508 I slot release: id 3 | task 38 | stop processing: n_tokens = 123, truncated = 0 0.37.737.072 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.254 0.37.737.272 I slot launch_slot_: id 0 | task 42 | processing task, is_child = 0 0.37.738.288 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 0.37.738.321 I slot launch_slot_: id 3 | task 43 | processing task, is_child = 0 0.37.738.362 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.201 0.37.738.390 I slot launch_slot_: id 1 | task 44 | processing task, is_child = 0 0.37.738.408 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.199 0.37.738.435 I slot launch_slot_: id 2 | task 45 | processing task, is_child = 0 0.38.748.415 I slot print_timing: id 0 | task 42 | prompt eval time = 972.20 ms / 110 tokens ( 8.84 ms per token, 113.15 tokens per second) 0.38.748.417 I slot print_timing: id 0 | task 42 | eval time = 37.77 ms / 2 tokens ( 37.77 ms per token, 26.48 tokens per second) 0.38.748.418 I slot print_timing: id 0 | task 42 | total time = 1009.97 ms / 112 tokens 0.38.748.418 I slot print_timing: id 0 | task 42 | graphs reused = 1 0.38.748.418 I slot print_timing: id 0 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.748.441 I slot release: id 0 | task 42 | stop processing: n_tokens = 111, truncated = 0 0.38.748.807 I slot print_timing: id 1 | task 44 | prompt eval time = 972.55 ms / 146 tokens ( 6.66 ms per token, 150.12 tokens per second) 0.38.748.809 I slot print_timing: id 1 | task 44 | eval time = 37.81 ms / 2 tokens ( 37.81 ms per token, 26.45 tokens per second) 0.38.748.809 I slot print_timing: id 1 | task 44 | total time = 1010.36 ms / 148 tokens 0.38.748.809 I slot print_timing: id 1 | task 44 | graphs reused = 1 0.38.748.810 I slot print_timing: id 1 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.748.822 I slot release: id 1 | task 44 | stop processing: n_tokens = 147, truncated = 0 0.38.749.107 I slot print_timing: id 2 | task 45 | prompt eval time = 972.85 ms / 123 tokens ( 7.91 ms per token, 126.43 tokens per second) 0.38.749.109 I slot print_timing: id 2 | task 45 | eval time = 37.79 ms / 2 tokens ( 37.79 ms per token, 26.46 tokens per second) 0.38.749.109 I slot print_timing: id 2 | task 45 | total time = 1010.65 ms / 125 tokens 0.38.749.109 I slot print_timing: id 2 | task 45 | graphs reused = 1 0.38.749.110 I slot print_timing: id 2 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.749.128 I slot release: id 2 | task 45 | stop processing: n_tokens = 124, truncated = 0 0.38.749.420 I slot print_timing: id 3 | task 43 | prompt eval time = 973.15 ms / 115 tokens ( 8.46 ms per token, 118.17 tokens per second) 0.38.749.423 I slot print_timing: id 3 | task 43 | eval time = 37.79 ms / 2 tokens ( 37.79 ms per token, 26.46 tokens per second) 0.38.749.423 I slot print_timing: id 3 | task 43 | total time = 1010.95 ms / 117 tokens 0.38.749.424 I slot print_timing: id 3 | task 43 | graphs reused = 1 0.38.749.424 I slot print_timing: id 3 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.749.436 I slot release: id 3 | task 43 | stop processing: n_tokens = 116, truncated = 0 0.38.753.422 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.261 0.38.753.695 I slot launch_slot_: id 0 | task 50 | processing task, is_child = 0 0.38.754.722 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.197 0.38.754.756 I slot launch_slot_: id 1 | task 49 | processing task, is_child = 0 0.38.754.788 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 0.38.754.815 I slot launch_slot_: id 3 | task 51 | processing task, is_child = 0 0.38.754.832 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.234 0.38.754.965 I slot launch_slot_: id 2 | task 52 | processing task, is_child = 0 0.39.835.375 I slot print_timing: id 0 | task 50 | prompt eval time = 1042.98 ms / 103 tokens ( 10.13 ms per token, 98.76 tokens per second) 0.39.835.377 I slot print_timing: id 0 | task 50 | eval time = 37.42 ms / 2 tokens ( 37.42 ms per token, 26.72 tokens per second) 0.39.835.378 I slot print_timing: id 0 | task 50 | total time = 1080.40 ms / 105 tokens 0.39.835.378 I slot print_timing: id 0 | task 50 | graphs reused = 1 0.39.835.379 I slot print_timing: id 0 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.835.400 I slot release: id 0 | task 50 | stop processing: n_tokens = 104, truncated = 0 0.39.835.684 I slot print_timing: id 1 | task 49 | prompt eval time = 1043.24 ms / 137 tokens ( 7.61 ms per token, 131.32 tokens per second) 0.39.835.686 I slot print_timing: id 1 | task 49 | eval time = 37.46 ms / 2 tokens ( 37.46 ms per token, 26.69 tokens per second) 0.39.835.687 I slot print_timing: id 1 | task 49 | total time = 1080.70 ms / 139 tokens 0.39.835.688 I slot print_timing: id 1 | task 49 | graphs reused = 1 0.39.835.688 I slot print_timing: id 1 | task 49 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.835.705 I slot release: id 1 | task 49 | stop processing: n_tokens = 138, truncated = 0 0.39.835.992 I slot print_timing: id 2 | task 52 | prompt eval time = 1043.54 ms / 114 tokens ( 9.15 ms per token, 109.24 tokens per second) 0.39.835.993 I slot print_timing: id 2 | task 52 | eval time = 37.46 ms / 2 tokens ( 37.46 ms per token, 26.69 tokens per second) 0.39.835.994 I slot print_timing: id 2 | task 52 | total time = 1081.00 ms / 116 tokens 0.39.835.994 I slot print_timing: id 2 | task 52 | graphs reused = 1 0.39.835.994 I slot print_timing: id 2 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.836.005 I slot release: id 2 | task 52 | stop processing: n_tokens = 115, truncated = 0 0.39.836.304 I slot print_timing: id 3 | task 51 | prompt eval time = 1043.85 ms / 131 tokens ( 7.97 ms per token, 125.50 tokens per second) 0.39.836.306 I slot print_timing: id 3 | task 51 | eval time = 37.45 ms / 2 tokens ( 37.45 ms per token, 26.70 tokens per second) 0.39.836.307 I slot print_timing: id 3 | task 51 | total time = 1081.31 ms / 133 tokens 0.39.836.307 I slot print_timing: id 3 | task 51 | graphs reused = 1 0.39.836.307 I slot print_timing: id 3 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.836.324 I slot release: id 3 | task 51 | stop processing: n_tokens = 132, truncated = 0 0.39.840.362 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 0.39.840.563 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.39.841.636 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.210 0.39.841.669 I slot launch_slot_: id 1 | task 58 | processing task, is_child = 0 0.39.841.702 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.252 0.39.841.855 I slot launch_slot_: id 2 | task 57 | processing task, is_child = 0 0.39.841.874 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.220 0.39.841.901 I slot launch_slot_: id 3 | task 59 | processing task, is_child = 0 0.41.041.329 I slot print_timing: id 0 | task 56 | prompt eval time = 1161.77 ms / 132 tokens ( 8.80 ms per token, 113.62 tokens per second) 0.41.041.332 I slot print_timing: id 0 | task 56 | eval time = 37.65 ms / 2 tokens ( 37.65 ms per token, 26.56 tokens per second) 0.41.041.332 I slot print_timing: id 0 | task 56 | total time = 1199.42 ms / 134 tokens 0.41.041.333 I slot print_timing: id 0 | task 56 | graphs reused = 1 0.41.041.333 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.041.354 I slot release: id 0 | task 56 | stop processing: n_tokens = 133, truncated = 0 0.41.041.643 I slot print_timing: id 1 | task 58 | prompt eval time = 1162.05 ms / 178 tokens ( 6.53 ms per token, 153.18 tokens per second) 0.41.041.645 I slot print_timing: id 1 | task 58 | eval time = 37.68 ms / 2 tokens ( 37.68 ms per token, 26.54 tokens per second) 0.41.041.646 I slot print_timing: id 1 | task 58 | total time = 1199.73 ms / 180 tokens 0.41.041.646 I slot print_timing: id 1 | task 58 | graphs reused = 1 0.41.041.646 I slot print_timing: id 1 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.041.665 I slot release: id 1 | task 58 | stop processing: n_tokens = 179, truncated = 0 0.41.041.946 I slot print_timing: id 2 | task 57 | prompt eval time = 1162.34 ms / 186 tokens ( 6.25 ms per token, 160.02 tokens per second) 0.41.041.948 I slot print_timing: id 2 | task 57 | eval time = 37.68 ms / 2 tokens ( 37.68 ms per token, 26.54 tokens per second) 0.41.041.948 I slot print_timing: id 2 | task 57 | total time = 1200.02 ms / 188 tokens 0.41.041.948 I slot print_timing: id 2 | task 57 | graphs reused = 1 0.41.041.949 I slot print_timing: id 2 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.041.962 I slot release: id 2 | task 57 | stop processing: n_tokens = 187, truncated = 0 0.41.042.254 I slot print_timing: id 3 | task 59 | prompt eval time = 1162.65 ms / 168 tokens ( 6.92 ms per token, 144.50 tokens per second) 0.41.042.256 I slot print_timing: id 3 | task 59 | eval time = 37.67 ms / 2 tokens ( 37.67 ms per token, 26.55 tokens per second) 0.41.042.257 I slot print_timing: id 3 | task 59 | total time = 1200.32 ms / 170 tokens 0.41.042.257 I slot print_timing: id 3 | task 59 | graphs reused = 1 0.41.042.257 I slot print_timing: id 3 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.042.278 I slot release: id 3 | task 59 | stop processing: n_tokens = 169, truncated = 0 0.41.046.433 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 0.41.046.966 I slot launch_slot_: id 0 | task 64 | processing task, is_child = 0 0.41.048.103 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.162 0.41.048.138 I slot launch_slot_: id 1 | task 63 | processing task, is_child = 0 0.41.048.174 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.155 0.41.048.203 I slot launch_slot_: id 2 | task 65 | processing task, is_child = 0 0.41.048.222 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.172 0.41.048.250 I slot launch_slot_: id 3 | task 66 | processing task, is_child = 0 0.42.211.368 I slot print_timing: id 0 | task 64 | prompt eval time = 1125.51 ms / 141 tokens ( 7.98 ms per token, 125.28 tokens per second) 0.42.211.370 I slot print_timing: id 0 | task 64 | eval time = 37.60 ms / 2 tokens ( 37.60 ms per token, 26.60 tokens per second) 0.42.211.371 I slot print_timing: id 0 | task 64 | total time = 1163.11 ms / 143 tokens 0.42.211.371 I slot print_timing: id 0 | task 64 | graphs reused = 1 0.42.211.372 I slot print_timing: id 0 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.211.392 I slot release: id 0 | task 64 | stop processing: n_tokens = 142, truncated = 0 0.42.211.659 I slot print_timing: id 1 | task 63 | prompt eval time = 1125.77 ms / 150 tokens ( 7.51 ms per token, 133.24 tokens per second) 0.42.211.661 I slot print_timing: id 1 | task 63 | eval time = 37.63 ms / 2 tokens ( 37.63 ms per token, 26.58 tokens per second) 0.42.211.662 I slot print_timing: id 1 | task 63 | total time = 1163.39 ms / 152 tokens 0.42.211.662 I slot print_timing: id 1 | task 63 | graphs reused = 1 0.42.211.662 I slot print_timing: id 1 | task 63 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.211.675 I slot release: id 1 | task 63 | stop processing: n_tokens = 151, truncated = 0 0.42.211.956 I slot print_timing: id 2 | task 65 | prompt eval time = 1126.03 ms / 168 tokens ( 6.70 ms per token, 149.20 tokens per second) 0.42.211.958 I slot print_timing: id 2 | task 65 | eval time = 37.64 ms / 2 tokens ( 37.64 ms per token, 26.57 tokens per second) 0.42.211.959 I slot print_timing: id 2 | task 65 | total time = 1163.67 ms / 170 tokens 0.42.211.959 I slot print_timing: id 2 | task 65 | graphs reused = 1 0.42.211.960 I slot print_timing: id 2 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.211.977 I slot release: id 2 | task 65 | stop processing: n_tokens = 169, truncated = 0 0.42.212.299 I slot print_timing: id 3 | task 66 | prompt eval time = 1126.36 ms / 124 tokens ( 9.08 ms per token, 110.09 tokens per second) 0.42.212.301 I slot print_timing: id 3 | task 66 | eval time = 37.65 ms / 2 tokens ( 37.65 ms per token, 26.56 tokens per second) 0.42.212.302 I slot print_timing: id 3 | task 66 | total time = 1164.01 ms / 126 tokens 0.42.212.302 I slot print_timing: id 3 | task 66 | graphs reused = 1 0.42.212.302 I slot print_timing: id 3 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.212.316 I slot release: id 3 | task 66 | stop processing: n_tokens = 125, truncated = 0 0.42.217.035 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 0.42.217.442 I slot launch_slot_: id 3 | task 70 | processing task, is_child = 0 0.42.218.622 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.270 (> 0.100 thold), f_keep = 0.211 0.42.218.657 I slot launch_slot_: id 0 | task 71 | processing task, is_child = 0 0.42.218.691 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.192 0.42.218.724 I slot launch_slot_: id 1 | task 72 | processing task, is_child = 0 0.42.218.743 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 0.42.218.771 I slot launch_slot_: id 2 | task 73 | processing task, is_child = 0 0.43.345.076 I slot print_timing: id 0 | task 71 | prompt eval time = 1088.51 ms / 111 tokens ( 9.81 ms per token, 101.97 tokens per second) 0.43.345.079 I slot print_timing: id 0 | task 71 | eval time = 37.78 ms / 2 tokens ( 37.78 ms per token, 26.47 tokens per second) 0.43.345.079 I slot print_timing: id 0 | task 71 | total time = 1126.30 ms / 113 tokens 0.43.345.080 I slot print_timing: id 0 | task 71 | graphs reused = 1 0.43.345.080 I slot print_timing: id 0 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.345.097 I slot release: id 0 | task 71 | stop processing: n_tokens = 112, truncated = 0 0.43.345.453 I slot print_timing: id 1 | task 72 | prompt eval time = 1088.86 ms / 131 tokens ( 8.31 ms per token, 120.31 tokens per second) 0.43.345.455 I slot print_timing: id 1 | task 72 | eval time = 37.81 ms / 2 tokens ( 37.81 ms per token, 26.45 tokens per second) 0.43.345.455 I slot print_timing: id 1 | task 72 | total time = 1126.66 ms / 133 tokens 0.43.345.455 I slot print_timing: id 1 | task 72 | graphs reused = 1 0.43.345.456 I slot print_timing: id 1 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.345.468 I slot release: id 1 | task 72 | stop processing: n_tokens = 132, truncated = 0 0.43.345.759 I slot print_timing: id 2 | task 73 | prompt eval time = 1089.13 ms / 160 tokens ( 6.81 ms per token, 146.91 tokens per second) 0.43.345.761 I slot print_timing: id 2 | task 73 | eval time = 37.83 ms / 2 tokens ( 37.83 ms per token, 26.44 tokens per second) 0.43.345.761 I slot print_timing: id 2 | task 73 | total time = 1126.96 ms / 162 tokens 0.43.345.762 I slot print_timing: id 2 | task 73 | graphs reused = 1 0.43.345.762 I slot print_timing: id 2 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.345.775 I slot release: id 2 | task 73 | stop processing: n_tokens = 161, truncated = 0 0.43.346.068 I slot print_timing: id 3 | task 70 | prompt eval time = 1089.43 ms / 164 tokens ( 6.64 ms per token, 150.54 tokens per second) 0.43.346.069 I slot print_timing: id 3 | task 70 | eval time = 37.82 ms / 2 tokens ( 37.82 ms per token, 26.44 tokens per second) 0.43.346.070 I slot print_timing: id 3 | task 70 | total time = 1127.25 ms / 166 tokens 0.43.346.070 I slot print_timing: id 3 | task 70 | graphs reused = 1 0.43.346.070 I slot print_timing: id 3 | task 70 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.346.085 I slot release: id 3 | task 70 | stop processing: n_tokens = 165, truncated = 0 0.43.349.954 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 0.43.350.496 I slot launch_slot_: id 2 | task 77 | processing task, is_child = 0 0.43.351.454 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.259 0.43.351.489 I slot launch_slot_: id 0 | task 78 | processing task, is_child = 0 0.43.351.523 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 0.43.351.552 I slot launch_slot_: id 3 | task 79 | processing task, is_child = 0 0.43.351.572 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.220 0.43.351.599 I slot launch_slot_: id 1 | task 80 | processing task, is_child = 0 0.44.486.960 I slot print_timing: id 0 | task 78 | prompt eval time = 1097.77 ms / 112 tokens ( 9.80 ms per token, 102.03 tokens per second) 0.44.486.963 I slot print_timing: id 0 | task 78 | eval time = 37.59 ms / 2 tokens ( 37.59 ms per token, 26.61 tokens per second) 0.44.486.964 I slot print_timing: id 0 | task 78 | total time = 1135.35 ms / 114 tokens 0.44.486.964 I slot print_timing: id 0 | task 78 | graphs reused = 1 0.44.486.965 I slot print_timing: id 0 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.486.983 I slot release: id 0 | task 78 | stop processing: n_tokens = 113, truncated = 0 0.44.487.260 I slot print_timing: id 1 | task 80 | prompt eval time = 1098.05 ms / 166 tokens ( 6.61 ms per token, 151.18 tokens per second) 0.44.487.262 I slot print_timing: id 1 | task 80 | eval time = 37.59 ms / 2 tokens ( 37.59 ms per token, 26.60 tokens per second) 0.44.487.262 I slot print_timing: id 1 | task 80 | total time = 1135.65 ms / 168 tokens 0.44.487.262 I slot print_timing: id 1 | task 80 | graphs reused = 1 0.44.487.263 I slot print_timing: id 1 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.487.277 I slot release: id 1 | task 80 | stop processing: n_tokens = 167, truncated = 0 0.44.487.552 I slot print_timing: id 2 | task 77 | prompt eval time = 1098.35 ms / 111 tokens ( 9.89 ms per token, 101.06 tokens per second) 0.44.487.554 I slot print_timing: id 2 | task 77 | eval time = 37.58 ms / 2 tokens ( 37.58 ms per token, 26.61 tokens per second) 0.44.487.554 I slot print_timing: id 2 | task 77 | total time = 1135.93 ms / 113 tokens 0.44.487.555 I slot print_timing: id 2 | task 77 | graphs reused = 1 0.44.487.555 I slot print_timing: id 2 | task 77 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.487.565 I slot release: id 2 | task 77 | stop processing: n_tokens = 112, truncated = 0 0.44.487.881 I slot print_timing: id 3 | task 79 | prompt eval time = 1098.64 ms / 166 tokens ( 6.62 ms per token, 151.10 tokens per second) 0.44.487.884 I slot print_timing: id 3 | task 79 | eval time = 37.59 ms / 2 tokens ( 37.59 ms per token, 26.60 tokens per second) 0.44.487.884 I slot print_timing: id 3 | task 79 | total time = 1136.24 ms / 168 tokens 0.44.487.885 I slot print_timing: id 3 | task 79 | graphs reused = 1 0.44.487.885 I slot print_timing: id 3 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.487.899 I slot release: id 3 | task 79 | stop processing: n_tokens = 167, truncated = 0 0.44.492.294 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.257 0.44.492.685 I slot launch_slot_: id 0 | task 84 | processing task, is_child = 0 0.44.493.878 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.174 0.44.493.913 I slot launch_slot_: id 1 | task 85 | processing task, is_child = 0 0.44.493.946 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.259 0.44.493.974 I slot launch_slot_: id 2 | task 86 | processing task, is_child = 0 0.44.493.993 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 0.44.494.146 I slot launch_slot_: id 3 | task 87 | processing task, is_child = 0 0.45.466.990 I slot print_timing: id 0 | task 84 | prompt eval time = 934.11 ms / 122 tokens ( 7.66 ms per token, 130.61 tokens per second) 0.45.466.993 I slot print_timing: id 0 | task 84 | eval time = 38.72 ms / 2 tokens ( 38.72 ms per token, 25.83 tokens per second) 0.45.466.995 I slot print_timing: id 0 | task 84 | total time = 972.84 ms / 124 tokens 0.45.466.995 I slot print_timing: id 0 | task 84 | graphs reused = 1 0.45.466.996 I slot print_timing: id 0 | task 84 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.467.021 I slot release: id 0 | task 84 | stop processing: n_tokens = 123, truncated = 0 0.45.467.341 I slot print_timing: id 1 | task 85 | prompt eval time = 934.48 ms / 145 tokens ( 6.44 ms per token, 155.17 tokens per second) 0.45.467.343 I slot print_timing: id 1 | task 85 | eval time = 38.69 ms / 2 tokens ( 38.69 ms per token, 25.84 tokens per second) 0.45.467.343 I slot print_timing: id 1 | task 85 | total time = 973.18 ms / 147 tokens 0.45.467.344 I slot print_timing: id 1 | task 85 | graphs reused = 1 0.45.467.344 I slot print_timing: id 1 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.467.359 I slot release: id 1 | task 85 | stop processing: n_tokens = 146, truncated = 0 0.45.467.702 I slot print_timing: id 2 | task 86 | prompt eval time = 934.87 ms / 133 tokens ( 7.03 ms per token, 142.27 tokens per second) 0.45.467.705 I slot print_timing: id 2 | task 86 | eval time = 38.66 ms / 2 tokens ( 38.66 ms per token, 25.87 tokens per second) 0.45.467.705 I slot print_timing: id 2 | task 86 | total time = 973.53 ms / 135 tokens 0.45.467.706 I slot print_timing: id 2 | task 86 | graphs reused = 1 0.45.467.706 I slot print_timing: id 2 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.467.726 I slot release: id 2 | task 86 | stop processing: n_tokens = 134, truncated = 0 0.45.468.086 I slot print_timing: id 3 | task 87 | prompt eval time = 935.35 ms / 127 tokens ( 7.36 ms per token, 135.78 tokens per second) 0.45.468.088 I slot print_timing: id 3 | task 87 | eval time = 38.55 ms / 2 tokens ( 38.55 ms per token, 25.94 tokens per second) 0.45.468.088 I slot print_timing: id 3 | task 87 | total time = 973.90 ms / 129 tokens 0.45.468.089 I slot print_timing: id 3 | task 87 | graphs reused = 1 0.45.468.089 I slot print_timing: id 3 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.468.105 I slot release: id 3 | task 87 | stop processing: n_tokens = 128, truncated = 0 0.45.472.708 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 0.45.473.135 I slot launch_slot_: id 3 | task 91 | processing task, is_child = 0 0.45.474.368 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.236 0.45.474.574 I slot launch_slot_: id 0 | task 92 | processing task, is_child = 0 0.45.474.623 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.199 0.45.474.663 I slot launch_slot_: id 1 | task 93 | processing task, is_child = 0 0.45.474.684 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.216 0.45.474.879 I slot launch_slot_: id 2 | task 94 | processing task, is_child = 0 0.46.464.958 I slot print_timing: id 0 | task 92 | prompt eval time = 952.20 ms / 140 tokens ( 6.80 ms per token, 147.03 tokens per second) 0.46.464.961 I slot print_timing: id 0 | task 92 | eval time = 37.87 ms / 2 tokens ( 37.87 ms per token, 26.41 tokens per second) 0.46.464.961 I slot print_timing: id 0 | task 92 | total time = 990.07 ms / 142 tokens 0.46.464.962 I slot print_timing: id 0 | task 92 | graphs reused = 1 0.46.464.962 I slot print_timing: id 0 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.464.984 I slot release: id 0 | task 92 | stop processing: n_tokens = 141, truncated = 0 0.46.465.259 I slot print_timing: id 1 | task 93 | prompt eval time = 952.46 ms / 126 tokens ( 7.56 ms per token, 132.29 tokens per second) 0.46.465.262 I slot print_timing: id 1 | task 93 | eval time = 37.89 ms / 2 tokens ( 37.89 ms per token, 26.39 tokens per second) 0.46.465.263 I slot print_timing: id 1 | task 93 | total time = 990.35 ms / 128 tokens 0.46.465.263 I slot print_timing: id 1 | task 93 | graphs reused = 1 0.46.465.263 I slot print_timing: id 1 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.465.276 I slot release: id 1 | task 93 | stop processing: n_tokens = 127, truncated = 0 0.46.465.671 I slot print_timing: id 2 | task 94 | prompt eval time = 952.83 ms / 133 tokens ( 7.16 ms per token, 139.58 tokens per second) 0.46.465.673 I slot print_timing: id 2 | task 94 | eval time = 37.92 ms / 2 tokens ( 37.92 ms per token, 26.37 tokens per second) 0.46.465.673 I slot print_timing: id 2 | task 94 | total time = 990.75 ms / 135 tokens 0.46.465.673 I slot print_timing: id 2 | task 94 | graphs reused = 1 0.46.465.674 I slot print_timing: id 2 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.465.688 I slot release: id 2 | task 94 | stop processing: n_tokens = 134, truncated = 0 0.46.465.977 I slot print_timing: id 3 | task 91 | prompt eval time = 953.25 ms / 146 tokens ( 6.53 ms per token, 153.16 tokens per second) 0.46.465.979 I slot print_timing: id 3 | task 91 | eval time = 37.79 ms / 2 tokens ( 37.79 ms per token, 26.46 tokens per second) 0.46.465.979 I slot print_timing: id 3 | task 91 | total time = 991.04 ms / 148 tokens 0.46.465.979 I slot print_timing: id 3 | task 91 | graphs reused = 1 0.46.465.980 I slot print_timing: id 3 | task 91 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.465.996 I slot release: id 3 | task 91 | stop processing: n_tokens = 147, truncated = 0 0.46.469.790 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.224 0.46.470.227 I slot launch_slot_: id 2 | task 99 | processing task, is_child = 0 0.46.471.350 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.206 0.46.471.391 I slot launch_slot_: id 0 | task 100 | processing task, is_child = 0 0.46.471.425 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.204 0.46.471.455 I slot launch_slot_: id 3 | task 98 | processing task, is_child = 0 0.46.471.477 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.170 (> 0.100 thold), f_keep = 0.228 0.46.471.506 I slot launch_slot_: id 1 | task 101 | processing task, is_child = 0 0.47.573.528 I slot print_timing: id 0 | task 100 | prompt eval time = 1064.41 ms / 123 tokens ( 8.65 ms per token, 115.56 tokens per second) 0.47.573.531 I slot print_timing: id 0 | task 100 | eval time = 37.60 ms / 2 tokens ( 37.60 ms per token, 26.59 tokens per second) 0.47.573.531 I slot print_timing: id 0 | task 100 | total time = 1102.02 ms / 125 tokens 0.47.573.531 I slot print_timing: id 0 | task 100 | graphs reused = 1 0.47.573.532 I slot print_timing: id 0 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.573.551 I slot release: id 0 | task 100 | stop processing: n_tokens = 124, truncated = 0 0.47.573.834 I slot print_timing: id 1 | task 101 | prompt eval time = 1064.69 ms / 171 tokens ( 6.23 ms per token, 160.61 tokens per second) 0.47.573.836 I slot print_timing: id 1 | task 101 | eval time = 37.62 ms / 2 tokens ( 37.62 ms per token, 26.58 tokens per second) 0.47.573.836 I slot print_timing: id 1 | task 101 | total time = 1102.31 ms / 173 tokens 0.47.573.836 I slot print_timing: id 1 | task 101 | graphs reused = 1 0.47.573.837 I slot print_timing: id 1 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.573.852 I slot release: id 1 | task 101 | stop processing: n_tokens = 172, truncated = 0 0.47.574.128 I slot print_timing: id 2 | task 99 | prompt eval time = 1064.98 ms / 110 tokens ( 9.68 ms per token, 103.29 tokens per second) 0.47.574.129 I slot print_timing: id 2 | task 99 | eval time = 37.61 ms / 2 tokens ( 37.61 ms per token, 26.59 tokens per second) 0.47.574.130 I slot print_timing: id 2 | task 99 | total time = 1102.59 ms / 112 tokens 0.47.574.130 I slot print_timing: id 2 | task 99 | graphs reused = 1 0.47.574.131 I slot print_timing: id 2 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.574.142 I slot release: id 2 | task 99 | stop processing: n_tokens = 111, truncated = 0 0.47.574.417 I slot print_timing: id 3 | task 98 | prompt eval time = 1065.31 ms / 120 tokens ( 8.88 ms per token, 112.64 tokens per second) 0.47.574.419 I slot print_timing: id 3 | task 98 | eval time = 37.57 ms / 2 tokens ( 37.57 ms per token, 26.62 tokens per second) 0.47.574.419 I slot print_timing: id 3 | task 98 | total time = 1102.87 ms / 122 tokens 0.47.574.419 I slot print_timing: id 3 | task 98 | graphs reused = 1 0.47.574.419 I slot print_timing: id 3 | task 98 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.574.432 I slot release: id 3 | task 98 | stop processing: n_tokens = 121, truncated = 0 0.47.578.285 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.270 0.47.578.519 I slot launch_slot_: id 2 | task 106 | processing task, is_child = 0 0.47.579.655 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.256 (> 0.100 thold), f_keep = 0.248 0.47.579.689 I slot launch_slot_: id 3 | task 105 | processing task, is_child = 0 0.47.579.723 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.234 0.47.579.762 I slot launch_slot_: id 0 | task 107 | processing task, is_child = 0 0.47.579.781 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.125 (> 0.100 thold), f_keep = 0.169 0.47.579.810 I slot launch_slot_: id 1 | task 108 | processing task, is_child = 0 0.48.960.512 I slot print_timing: id 0 | task 107 | prompt eval time = 1342.97 ms / 176 tokens ( 7.63 ms per token, 131.05 tokens per second) 0.48.960.515 I slot print_timing: id 0 | task 107 | eval time = 37.72 ms / 2 tokens ( 37.72 ms per token, 26.51 tokens per second) 0.48.960.515 I slot print_timing: id 0 | task 107 | total time = 1380.69 ms / 178 tokens 0.48.960.516 I slot print_timing: id 0 | task 107 | graphs reused = 1 0.48.960.516 I slot print_timing: id 0 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.960.539 I slot release: id 0 | task 107 | stop processing: n_tokens = 177, truncated = 0 0.48.960.818 I slot print_timing: id 1 | task 108 | prompt eval time = 1343.23 ms / 232 tokens ( 5.79 ms per token, 172.72 tokens per second) 0.48.960.822 I slot print_timing: id 1 | task 108 | eval time = 37.76 ms / 2 tokens ( 37.76 ms per token, 26.48 tokens per second) 0.48.960.822 I slot print_timing: id 1 | task 108 | total time = 1380.99 ms / 234 tokens 0.48.960.823 I slot print_timing: id 1 | task 108 | graphs reused = 1 0.48.960.823 I slot print_timing: id 1 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.960.845 I slot release: id 1 | task 108 | stop processing: n_tokens = 233, truncated = 0 0.48.961.125 I slot print_timing: id 2 | task 106 | prompt eval time = 1343.49 ms / 138 tokens ( 9.74 ms per token, 102.72 tokens per second) 0.48.961.128 I slot print_timing: id 2 | task 106 | eval time = 37.78 ms / 2 tokens ( 37.78 ms per token, 26.47 tokens per second) 0.48.961.128 I slot print_timing: id 2 | task 106 | total time = 1381.28 ms / 140 tokens 0.48.961.129 I slot print_timing: id 2 | task 106 | graphs reused = 1 0.48.961.129 I slot print_timing: id 2 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.961.144 I slot release: id 2 | task 106 | stop processing: n_tokens = 139, truncated = 0 0.48.961.427 I slot print_timing: id 3 | task 105 | prompt eval time = 1343.79 ms / 117 tokens ( 11.49 ms per token, 87.07 tokens per second) 0.48.961.430 I slot print_timing: id 3 | task 105 | eval time = 37.79 ms / 2 tokens ( 37.79 ms per token, 26.46 tokens per second) 0.48.961.430 I slot print_timing: id 3 | task 105 | total time = 1381.57 ms / 119 tokens 0.48.961.431 I slot print_timing: id 3 | task 105 | graphs reused = 1 0.48.961.431 I slot print_timing: id 3 | task 105 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.961.441 I slot release: id 3 | task 105 | stop processing: n_tokens = 118, truncated = 0 0.48.965.823 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.263 0.48.966.276 I slot launch_slot_: id 3 | task 112 | processing task, is_child = 0 0.48.967.629 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.164 0.48.967.664 I slot launch_slot_: id 0 | task 113 | processing task, is_child = 0 0.48.967.700 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.216 0.48.967.849 I slot launch_slot_: id 2 | task 114 | processing task, is_child = 0 0.48.967.871 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.124 0.48.967.902 I slot launch_slot_: id 1 | task 115 | processing task, is_child = 0 0.50.399.258 I slot print_timing: id 0 | task 113 | prompt eval time = 1393.71 ms / 158 tokens ( 8.82 ms per token, 113.37 tokens per second) 0.50.399.262 I slot print_timing: id 0 | task 113 | eval time = 37.63 ms / 2 tokens ( 37.63 ms per token, 26.57 tokens per second) 0.50.399.262 I slot print_timing: id 0 | task 113 | total time = 1431.35 ms / 160 tokens 0.50.399.263 I slot print_timing: id 0 | task 113 | graphs reused = 1 0.50.399.263 I slot print_timing: id 0 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.399.283 I slot release: id 0 | task 113 | stop processing: n_tokens = 159, truncated = 0 0.50.399.583 I slot print_timing: id 1 | task 115 | prompt eval time = 1393.98 ms / 227 tokens ( 6.14 ms per token, 162.84 tokens per second) 0.50.399.585 I slot print_timing: id 1 | task 115 | eval time = 37.68 ms / 2 tokens ( 37.68 ms per token, 26.54 tokens per second) 0.50.399.586 I slot print_timing: id 1 | task 115 | total time = 1431.66 ms / 229 tokens 0.50.399.589 I slot print_timing: id 1 | task 115 | graphs reused = 1 0.50.399.590 I slot print_timing: id 1 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.399.609 I slot release: id 1 | task 115 | stop processing: n_tokens = 228, truncated = 0 0.50.399.927 I slot print_timing: id 2 | task 114 | prompt eval time = 1394.25 ms / 143 tokens ( 9.75 ms per token, 102.56 tokens per second) 0.50.399.929 I slot print_timing: id 2 | task 114 | eval time = 37.74 ms / 2 tokens ( 37.74 ms per token, 26.50 tokens per second) 0.50.399.930 I slot print_timing: id 2 | task 114 | total time = 1431.99 ms / 145 tokens 0.50.399.930 I slot print_timing: id 2 | task 114 | graphs reused = 1 0.50.399.931 I slot print_timing: id 2 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.399.954 I slot release: id 2 | task 114 | stop processing: n_tokens = 144, truncated = 0 0.50.400.387 I slot print_timing: id 3 | task 112 | prompt eval time = 1394.63 ms / 156 tokens ( 8.94 ms per token, 111.86 tokens per second) 0.50.400.389 I slot print_timing: id 3 | task 112 | eval time = 37.81 ms / 2 tokens ( 37.81 ms per token, 26.45 tokens per second) 0.50.400.389 I slot print_timing: id 3 | task 112 | total time = 1432.44 ms / 158 tokens 0.50.400.390 I slot print_timing: id 3 | task 112 | graphs reused = 1 0.50.400.390 I slot print_timing: id 3 | task 112 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.400.405 I slot release: id 3 | task 112 | stop processing: n_tokens = 157, truncated = 0 0.50.404.447 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.299 (> 0.100 thold), f_keep = 0.222 0.50.404.875 I slot launch_slot_: id 2 | task 119 | processing task, is_child = 0 0.50.406.232 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.153 (> 0.100 thold), f_keep = 0.182 0.50.406.381 I slot launch_slot_: id 0 | task 121 | processing task, is_child = 0 0.50.406.418 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.127 0.50.406.450 I slot launch_slot_: id 1 | task 122 | processing task, is_child = 0 0.50.406.469 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.256 (> 0.100 thold), f_keep = 0.191 0.50.406.499 I slot launch_slot_: id 3 | task 120 | processing task, is_child = 0 0.51.581.269 I slot print_timing: id 0 | task 121 | prompt eval time = 1137.30 ms / 189 tokens ( 6.02 ms per token, 166.18 tokens per second) 0.51.581.271 I slot print_timing: id 0 | task 121 | eval time = 37.46 ms / 2 tokens ( 37.46 ms per token, 26.69 tokens per second) 0.51.581.271 I slot print_timing: id 0 | task 121 | total time = 1174.76 ms / 191 tokens 0.51.581.272 I slot print_timing: id 0 | task 121 | graphs reused = 1 0.51.581.272 I slot print_timing: id 0 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.581.296 I slot release: id 0 | task 121 | stop processing: n_tokens = 190, truncated = 0 0.51.581.580 I slot print_timing: id 1 | task 122 | prompt eval time = 1137.58 ms / 143 tokens ( 7.96 ms per token, 125.71 tokens per second) 0.51.581.582 I slot print_timing: id 1 | task 122 | eval time = 37.49 ms / 2 tokens ( 37.49 ms per token, 26.68 tokens per second) 0.51.581.582 I slot print_timing: id 1 | task 122 | total time = 1175.07 ms / 145 tokens 0.51.581.582 I slot print_timing: id 1 | task 122 | graphs reused = 1 0.51.581.583 I slot print_timing: id 1 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.581.597 I slot release: id 1 | task 122 | stop processing: n_tokens = 144, truncated = 0 0.51.581.868 I slot print_timing: id 2 | task 119 | prompt eval time = 1137.84 ms / 107 tokens ( 10.63 ms per token, 94.04 tokens per second) 0.51.581.870 I slot print_timing: id 2 | task 119 | eval time = 37.50 ms / 2 tokens ( 37.50 ms per token, 26.67 tokens per second) 0.51.581.871 I slot print_timing: id 2 | task 119 | total time = 1175.34 ms / 109 tokens 0.51.581.871 I slot print_timing: id 2 | task 119 | graphs reused = 1 0.51.581.871 I slot print_timing: id 2 | task 119 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.581.881 I slot release: id 2 | task 119 | stop processing: n_tokens = 108, truncated = 0 0.51.582.187 I slot print_timing: id 3 | task 120 | prompt eval time = 1138.14 ms / 117 tokens ( 9.73 ms per token, 102.80 tokens per second) 0.51.582.189 I slot print_timing: id 3 | task 120 | eval time = 37.51 ms / 2 tokens ( 37.51 ms per token, 26.66 tokens per second) 0.51.582.189 I slot print_timing: id 3 | task 120 | total time = 1175.65 ms / 119 tokens 0.51.582.189 I slot print_timing: id 3 | task 120 | graphs reused = 1 0.51.582.189 I slot print_timing: id 3 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.582.198 I slot release: id 3 | task 120 | stop processing: n_tokens = 118, truncated = 0 0.51.586.248 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.153 0.51.586.686 I slot launch_slot_: id 0 | task 126 | processing task, is_child = 0 0.51.587.351 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.244 (> 0.100 thold), f_keep = 0.278 0.51.587.386 I slot launch_slot_: id 2 | task 127 | processing task, is_child = 0 0.51.587.419 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.201 0.51.587.448 I slot launch_slot_: id 1 | task 128 | processing task, is_child = 0 0.51.587.466 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.254 0.51.587.494 I slot launch_slot_: id 3 | task 129 | processing task, is_child = 0 0.52.817.067 I slot print_timing: id 0 | task 126 | prompt eval time = 1191.92 ms / 173 tokens ( 6.89 ms per token, 145.14 tokens per second) 0.52.817.069 I slot print_timing: id 0 | task 126 | eval time = 37.64 ms / 2 tokens ( 37.64 ms per token, 26.57 tokens per second) 0.52.817.070 I slot print_timing: id 0 | task 126 | total time = 1229.56 ms / 175 tokens 0.52.817.070 I slot print_timing: id 0 | task 126 | graphs reused = 1 0.52.817.071 I slot print_timing: id 0 | task 126 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.817.093 I slot release: id 0 | task 126 | stop processing: n_tokens = 174, truncated = 0 0.52.817.373 I slot print_timing: id 1 | task 128 | prompt eval time = 1192.18 ms / 138 tokens ( 8.64 ms per token, 115.75 tokens per second) 0.52.817.379 I slot print_timing: id 1 | task 128 | eval time = 37.67 ms / 2 tokens ( 37.67 ms per token, 26.55 tokens per second) 0.52.817.379 I slot print_timing: id 1 | task 128 | total time = 1229.85 ms / 140 tokens 0.52.817.379 I slot print_timing: id 1 | task 128 | graphs reused = 1 0.52.817.379 I slot print_timing: id 1 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.817.396 I slot release: id 1 | task 128 | stop processing: n_tokens = 139, truncated = 0 0.52.817.672 I slot print_timing: id 2 | task 127 | prompt eval time = 1192.47 ms / 123 tokens ( 9.69 ms per token, 103.15 tokens per second) 0.52.817.674 I slot print_timing: id 2 | task 127 | eval time = 37.68 ms / 2 tokens ( 37.68 ms per token, 26.54 tokens per second) 0.52.817.675 I slot print_timing: id 2 | task 127 | total time = 1230.15 ms / 125 tokens 0.52.817.675 I slot print_timing: id 2 | task 127 | graphs reused = 1 0.52.817.675 I slot print_timing: id 2 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.817.688 I slot release: id 2 | task 127 | stop processing: n_tokens = 124, truncated = 0 0.52.817.982 I slot print_timing: id 3 | task 129 | prompt eval time = 1192.75 ms / 110 tokens ( 10.84 ms per token, 92.22 tokens per second) 0.52.817.985 I slot print_timing: id 3 | task 129 | eval time = 37.69 ms / 2 tokens ( 37.69 ms per token, 26.53 tokens per second) 0.52.817.986 I slot print_timing: id 3 | task 129 | total time = 1230.45 ms / 112 tokens 0.52.817.986 I slot print_timing: id 3 | task 129 | graphs reused = 1 0.52.817.986 I slot print_timing: id 3 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.817.996 I slot release: id 3 | task 129 | stop processing: n_tokens = 111, truncated = 0 0.52.822.341 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 0.52.822.833 I slot launch_slot_: id 0 | task 134 | processing task, is_child = 0 0.52.823.725 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.209 0.52.823.759 I slot launch_slot_: id 1 | task 135 | processing task, is_child = 0 0.52.823.793 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.234 0.52.823.822 I slot launch_slot_: id 2 | task 133 | processing task, is_child = 0 0.52.823.839 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.270 0.52.823.987 I slot launch_slot_: id 3 | task 136 | processing task, is_child = 0 0.53.903.169 I slot print_timing: id 0 | task 134 | prompt eval time = 1041.36 ms / 161 tokens ( 6.47 ms per token, 154.60 tokens per second) 0.53.903.172 I slot print_timing: id 0 | task 134 | eval time = 37.81 ms / 2 tokens ( 37.81 ms per token, 26.45 tokens per second) 0.53.903.172 I slot print_timing: id 0 | task 134 | total time = 1079.17 ms / 163 tokens 0.53.903.173 I slot print_timing: id 0 | task 134 | graphs reused = 1 0.53.903.173 I slot print_timing: id 0 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.903.196 I slot release: id 0 | task 134 | stop processing: n_tokens = 162, truncated = 0 0.53.903.482 I slot print_timing: id 1 | task 135 | prompt eval time = 1041.63 ms / 136 tokens ( 7.66 ms per token, 130.56 tokens per second) 0.53.903.485 I slot print_timing: id 1 | task 135 | eval time = 37.84 ms / 2 tokens ( 37.84 ms per token, 26.42 tokens per second) 0.53.903.486 I slot print_timing: id 1 | task 135 | total time = 1079.48 ms / 138 tokens 0.53.903.486 I slot print_timing: id 1 | task 135 | graphs reused = 1 0.53.903.486 I slot print_timing: id 1 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.903.500 I slot release: id 1 | task 135 | stop processing: n_tokens = 137, truncated = 0 0.53.903.805 I slot print_timing: id 2 | task 133 | prompt eval time = 1041.91 ms / 134 tokens ( 7.78 ms per token, 128.61 tokens per second) 0.53.903.807 I slot print_timing: id 2 | task 133 | eval time = 37.87 ms / 2 tokens ( 37.87 ms per token, 26.40 tokens per second) 0.53.903.807 I slot print_timing: id 2 | task 133 | total time = 1079.79 ms / 136 tokens 0.53.903.807 I slot print_timing: id 2 | task 133 | graphs reused = 1 0.53.903.808 I slot print_timing: id 2 | task 133 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.903.825 I slot release: id 2 | task 133 | stop processing: n_tokens = 135, truncated = 0 0.53.904.149 I slot print_timing: id 3 | task 136 | prompt eval time = 1042.20 ms / 122 tokens ( 8.54 ms per token, 117.06 tokens per second) 0.53.904.152 I slot print_timing: id 3 | task 136 | eval time = 37.92 ms / 2 tokens ( 37.92 ms per token, 26.37 tokens per second) 0.53.904.152 I slot print_timing: id 3 | task 136 | total time = 1080.12 ms / 124 tokens 0.53.904.152 I slot print_timing: id 3 | task 136 | graphs reused = 1 0.53.904.153 I slot print_timing: id 3 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.904.168 I slot release: id 3 | task 136 | stop processing: n_tokens = 123, truncated = 0 0.53.908.717 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.170 (> 0.100 thold), f_keep = 0.179 0.53.909.177 I slot launch_slot_: id 0 | task 143 | processing task, is_child = 0 0.53.910.208 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.212 0.53.910.241 I slot launch_slot_: id 1 | task 141 | processing task, is_child = 0 0.53.910.275 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.215 0.53.910.304 I slot launch_slot_: id 2 | task 142 | processing task, is_child = 0 0.53.910.323 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.236 0.53.910.352 I slot launch_slot_: id 3 | task 140 | processing task, is_child = 0 0.55.156.582 I slot print_timing: id 0 | task 143 | prompt eval time = 1208.50 ms / 171 tokens ( 7.07 ms per token, 141.50 tokens per second) 0.55.156.584 I slot print_timing: id 0 | task 143 | eval time = 37.72 ms / 2 tokens ( 37.72 ms per token, 26.51 tokens per second) 0.55.156.584 I slot print_timing: id 0 | task 143 | total time = 1246.22 ms / 173 tokens 0.55.156.585 I slot print_timing: id 0 | task 143 | graphs reused = 1 0.55.156.585 I slot print_timing: id 0 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.156.607 I slot release: id 0 | task 143 | stop processing: n_tokens = 172, truncated = 0 0.55.156.887 I slot print_timing: id 1 | task 141 | prompt eval time = 1208.77 ms / 181 tokens ( 6.68 ms per token, 149.74 tokens per second) 0.55.156.890 I slot print_timing: id 1 | task 141 | eval time = 37.74 ms / 2 tokens ( 37.74 ms per token, 26.49 tokens per second) 0.55.156.891 I slot print_timing: id 1 | task 141 | total time = 1246.51 ms / 183 tokens 0.55.156.891 I slot print_timing: id 1 | task 141 | graphs reused = 1 0.55.156.891 I slot print_timing: id 1 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.156.912 I slot release: id 1 | task 141 | stop processing: n_tokens = 182, truncated = 0 0.55.157.203 I slot print_timing: id 2 | task 142 | prompt eval time = 1209.05 ms / 131 tokens ( 9.23 ms per token, 108.35 tokens per second) 0.55.157.205 I slot print_timing: id 2 | task 142 | eval time = 37.77 ms / 2 tokens ( 37.77 ms per token, 26.48 tokens per second) 0.55.157.205 I slot print_timing: id 2 | task 142 | total time = 1246.82 ms / 133 tokens 0.55.157.205 I slot print_timing: id 2 | task 142 | graphs reused = 1 0.55.157.206 I slot print_timing: id 2 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.157.218 I slot release: id 2 | task 142 | stop processing: n_tokens = 132, truncated = 0 0.55.157.518 I slot print_timing: id 3 | task 140 | prompt eval time = 1209.36 ms / 175 tokens ( 6.91 ms per token, 144.71 tokens per second) 0.55.157.521 I slot print_timing: id 3 | task 140 | eval time = 37.77 ms / 2 tokens ( 37.77 ms per token, 26.48 tokens per second) 0.55.157.522 I slot print_timing: id 3 | task 140 | total time = 1247.12 ms / 177 tokens 0.55.157.522 I slot print_timing: id 3 | task 140 | graphs reused = 1 0.55.157.522 I slot print_timing: id 3 | task 140 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.157.539 I slot release: id 3 | task 140 | stop processing: n_tokens = 176, truncated = 0 0.55.161.918 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 0.55.162.401 I slot launch_slot_: id 0 | task 147 | processing task, is_child = 0 0.55.163.689 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.159 0.55.163.726 I slot launch_slot_: id 1 | task 148 | processing task, is_child = 0 0.55.163.761 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.220 0.55.163.922 I slot launch_slot_: id 2 | task 149 | processing task, is_child = 0 0.55.163.942 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.165 0.55.164.081 I slot launch_slot_: id 3 | task 150 | processing task, is_child = 0 0.56.004.094 I slot print_timing: id 0 | task 147 | prompt eval time = 802.30 ms / 125 tokens ( 6.42 ms per token, 155.80 tokens per second) 0.56.004.097 I slot print_timing: id 0 | task 147 | eval time = 37.70 ms / 2 tokens ( 37.70 ms per token, 26.52 tokens per second) 0.56.004.097 I slot print_timing: id 0 | task 147 | total time = 840.00 ms / 127 tokens 0.56.004.098 I slot print_timing: id 0 | task 147 | graphs reused = 1 0.56.004.098 I slot print_timing: id 0 | task 147 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.004.117 I slot release: id 0 | task 147 | stop processing: n_tokens = 126, truncated = 0 0.56.004.386 I slot print_timing: id 1 | task 148 | prompt eval time = 802.57 ms / 115 tokens ( 6.98 ms per token, 143.29 tokens per second) 0.56.004.388 I slot print_timing: id 1 | task 148 | eval time = 37.72 ms / 2 tokens ( 37.72 ms per token, 26.51 tokens per second) 0.56.004.388 I slot print_timing: id 1 | task 148 | total time = 840.29 ms / 117 tokens 0.56.004.388 I slot print_timing: id 1 | task 148 | graphs reused = 1 0.56.004.389 I slot print_timing: id 1 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.004.400 I slot release: id 1 | task 148 | stop processing: n_tokens = 116, truncated = 0 0.56.004.781 I slot print_timing: id 2 | task 149 | prompt eval time = 802.93 ms / 116 tokens ( 6.92 ms per token, 144.47 tokens per second) 0.56.004.783 I slot print_timing: id 2 | task 149 | eval time = 37.74 ms / 2 tokens ( 37.74 ms per token, 26.50 tokens per second) 0.56.004.783 I slot print_timing: id 2 | task 149 | total time = 840.67 ms / 118 tokens 0.56.004.783 I slot print_timing: id 2 | task 149 | graphs reused = 1 0.56.004.784 I slot print_timing: id 2 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.004.797 I slot release: id 2 | task 149 | stop processing: n_tokens = 117, truncated = 0 0.56.005.114 I slot print_timing: id 3 | task 150 | prompt eval time = 803.22 ms / 123 tokens ( 6.53 ms per token, 153.13 tokens per second) 0.56.005.116 I slot print_timing: id 3 | task 150 | eval time = 37.78 ms / 2 tokens ( 37.78 ms per token, 26.47 tokens per second) 0.56.005.117 I slot print_timing: id 3 | task 150 | total time = 840.99 ms / 125 tokens 0.56.005.117 I slot print_timing: id 3 | task 150 | graphs reused = 1 0.56.005.117 I slot print_timing: id 3 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.005.133 I slot release: id 3 | task 150 | stop processing: n_tokens = 124, truncated = 0 0.56.009.040 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.230 0.56.009.295 I slot launch_slot_: id 0 | task 154 | processing task, is_child = 0 0.56.010.015 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.256 (> 0.100 thold), f_keep = 0.282 0.56.010.050 I slot launch_slot_: id 2 | task 155 | processing task, is_child = 0 0.56.010.083 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.223 (> 0.100 thold), f_keep = 0.250 0.56.010.112 I slot launch_slot_: id 1 | task 156 | processing task, is_child = 0 0.56.010.130 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.223 (> 0.100 thold), f_keep = 0.234 0.56.010.281 I slot launch_slot_: id 3 | task 157 | processing task, is_child = 0 0.56.878.473 I slot print_timing: id 0 | task 154 | prompt eval time = 830.46 ms / 143 tokens ( 5.81 ms per token, 172.19 tokens per second) 0.56.878.475 I slot print_timing: id 0 | task 154 | eval time = 37.72 ms / 2 tokens ( 37.72 ms per token, 26.51 tokens per second) 0.56.878.476 I slot print_timing: id 0 | task 154 | total time = 868.18 ms / 145 tokens 0.56.878.476 I slot print_timing: id 0 | task 154 | graphs reused = 1 0.56.878.476 I slot print_timing: id 0 | task 154 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.878.497 I slot release: id 0 | task 154 | stop processing: n_tokens = 144, truncated = 0 0.56.878.778 I slot print_timing: id 1 | task 156 | prompt eval time = 830.75 ms / 130 tokens ( 6.39 ms per token, 156.49 tokens per second) 0.56.878.780 I slot print_timing: id 1 | task 156 | eval time = 37.73 ms / 2 tokens ( 37.73 ms per token, 26.50 tokens per second) 0.56.878.781 I slot print_timing: id 1 | task 156 | total time = 868.48 ms / 132 tokens 0.56.878.781 I slot print_timing: id 1 | task 156 | graphs reused = 1 0.56.878.781 I slot print_timing: id 1 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.878.793 I slot release: id 1 | task 156 | stop processing: n_tokens = 131, truncated = 0 0.56.879.188 I slot print_timing: id 2 | task 155 | prompt eval time = 831.12 ms / 129 tokens ( 6.44 ms per token, 155.21 tokens per second) 0.56.879.193 I slot print_timing: id 2 | task 155 | eval time = 37.76 ms / 2 tokens ( 37.76 ms per token, 26.48 tokens per second) 0.56.879.194 I slot print_timing: id 2 | task 155 | total time = 868.88 ms / 131 tokens 0.56.879.194 I slot print_timing: id 2 | task 155 | graphs reused = 1 0.56.879.194 I slot print_timing: id 2 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.879.208 I slot release: id 2 | task 155 | stop processing: n_tokens = 130, truncated = 0 0.56.879.509 I slot print_timing: id 3 | task 157 | prompt eval time = 831.43 ms / 130 tokens ( 6.40 ms per token, 156.36 tokens per second) 0.56.879.514 I slot print_timing: id 3 | task 157 | eval time = 37.76 ms / 2 tokens ( 37.76 ms per token, 26.48 tokens per second) 0.56.879.514 I slot print_timing: id 3 | task 157 | total time = 869.19 ms / 132 tokens 0.56.879.514 I slot print_timing: id 3 | task 157 | graphs reused = 1 0.56.879.515 I slot print_timing: id 3 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.879.524 I slot release: id 3 | task 157 | stop processing: n_tokens = 131, truncated = 0 0.56.882.861 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.286 (> 0.100 thold), f_keep = 0.231 0.56.883.273 I slot launch_slot_: id 2 | task 161 | processing task, is_child = 0 0.56.884.361 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.225 (> 0.100 thold), f_keep = 0.201 0.56.884.398 I slot launch_slot_: id 0 | task 162 | processing task, is_child = 0 0.56.884.431 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.221 0.56.884.462 I slot launch_slot_: id 1 | task 163 | processing task, is_child = 0 0.56.884.479 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.221 0.56.884.511 I slot launch_slot_: id 3 | task 164 | processing task, is_child = 0 0.58.027.300 I slot print_timing: id 0 | task 162 | prompt eval time = 1104.90 ms / 129 tokens ( 8.57 ms per token, 116.75 tokens per second) 0.58.027.302 I slot print_timing: id 0 | task 162 | eval time = 37.88 ms / 2 tokens ( 37.88 ms per token, 26.40 tokens per second) 0.58.027.303 I slot print_timing: id 0 | task 162 | total time = 1142.78 ms / 131 tokens 0.58.027.303 I slot print_timing: id 0 | task 162 | graphs reused = 1 0.58.027.304 I slot print_timing: id 0 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.027.324 I slot release: id 0 | task 162 | stop processing: n_tokens = 130, truncated = 0 0.58.027.610 I slot print_timing: id 1 | task 163 | prompt eval time = 1105.18 ms / 161 tokens ( 6.86 ms per token, 145.68 tokens per second) 0.58.027.612 I slot print_timing: id 1 | task 163 | eval time = 37.90 ms / 2 tokens ( 37.90 ms per token, 26.39 tokens per second) 0.58.027.613 I slot print_timing: id 1 | task 163 | total time = 1143.08 ms / 163 tokens 0.58.027.613 I slot print_timing: id 1 | task 163 | graphs reused = 1 0.58.027.613 I slot print_timing: id 1 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.027.630 I slot release: id 1 | task 163 | stop processing: n_tokens = 162, truncated = 0 0.58.027.912 I slot print_timing: id 2 | task 161 | prompt eval time = 1105.46 ms / 105 tokens ( 10.53 ms per token, 94.98 tokens per second) 0.58.027.914 I slot print_timing: id 2 | task 161 | eval time = 37.91 ms / 2 tokens ( 37.91 ms per token, 26.38 tokens per second) 0.58.027.914 I slot print_timing: id 2 | task 161 | total time = 1143.37 ms / 107 tokens 0.58.027.914 I slot print_timing: id 2 | task 161 | graphs reused = 1 0.58.027.914 I slot print_timing: id 2 | task 161 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.027.931 I slot release: id 2 | task 161 | stop processing: n_tokens = 106, truncated = 0 0.58.028.237 I slot print_timing: id 3 | task 164 | prompt eval time = 1105.87 ms / 124 tokens ( 8.92 ms per token, 112.13 tokens per second) 0.58.028.238 I slot print_timing: id 3 | task 164 | eval time = 37.82 ms / 2 tokens ( 37.82 ms per token, 26.44 tokens per second) 0.58.028.238 I slot print_timing: id 3 | task 164 | total time = 1143.68 ms / 126 tokens 0.58.028.239 I slot print_timing: id 3 | task 164 | graphs reused = 1 0.58.028.239 I slot print_timing: id 3 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.028.253 I slot release: id 3 | task 164 | stop processing: n_tokens = 125, truncated = 0 0.58.032.277 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 0.58.032.540 I slot launch_slot_: id 2 | task 168 | processing task, is_child = 0 0.58.033.692 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 0.58.033.835 I slot launch_slot_: id 0 | task 169 | processing task, is_child = 0 0.58.033.869 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.179 0.58.033.900 I slot launch_slot_: id 1 | task 170 | processing task, is_child = 0 0.58.033.918 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.232 0.58.033.947 I slot launch_slot_: id 3 | task 171 | processing task, is_child = 0 0.59.277.430 I slot print_timing: id 0 | task 169 | prompt eval time = 1205.65 ms / 143 tokens ( 8.43 ms per token, 118.61 tokens per second) 0.59.277.433 I slot print_timing: id 0 | task 169 | eval time = 37.82 ms / 2 tokens ( 37.82 ms per token, 26.44 tokens per second) 0.59.277.433 I slot print_timing: id 0 | task 169 | total time = 1243.47 ms / 145 tokens 0.59.277.434 I slot print_timing: id 0 | task 169 | graphs reused = 1 0.59.277.434 I slot print_timing: id 0 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.277.455 I slot release: id 0 | task 169 | stop processing: n_tokens = 144, truncated = 0 0.59.277.726 I slot print_timing: id 1 | task 170 | prompt eval time = 1205.92 ms / 169 tokens ( 7.14 ms per token, 140.14 tokens per second) 0.59.277.729 I slot print_timing: id 1 | task 170 | eval time = 37.84 ms / 2 tokens ( 37.84 ms per token, 26.42 tokens per second) 0.59.277.729 I slot print_timing: id 1 | task 170 | total time = 1243.76 ms / 171 tokens 0.59.277.729 I slot print_timing: id 1 | task 170 | graphs reused = 1 0.59.277.730 I slot print_timing: id 1 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.277.746 I slot release: id 1 | task 170 | stop processing: n_tokens = 170, truncated = 0 0.59.278.007 I slot print_timing: id 2 | task 168 | prompt eval time = 1206.18 ms / 113 tokens ( 10.67 ms per token, 93.68 tokens per second) 0.59.278.008 I slot print_timing: id 2 | task 168 | eval time = 37.85 ms / 2 tokens ( 37.85 ms per token, 26.42 tokens per second) 0.59.278.009 I slot print_timing: id 2 | task 168 | total time = 1244.03 ms / 115 tokens 0.59.278.009 I slot print_timing: id 2 | task 168 | graphs reused = 1 0.59.278.009 I slot print_timing: id 2 | task 168 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.278.027 I slot release: id 2 | task 168 | stop processing: n_tokens = 114, truncated = 0 0.59.278.314 I slot print_timing: id 3 | task 171 | prompt eval time = 1206.51 ms / 155 tokens ( 7.78 ms per token, 128.47 tokens per second) 0.59.278.316 I slot print_timing: id 3 | task 171 | eval time = 37.82 ms / 2 tokens ( 37.82 ms per token, 26.44 tokens per second) 0.59.278.317 I slot print_timing: id 3 | task 171 | total time = 1244.33 ms / 157 tokens 0.59.278.317 I slot print_timing: id 3 | task 171 | graphs reused = 1 0.59.278.317 I slot print_timing: id 3 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.278.331 I slot release: id 3 | task 171 | stop processing: n_tokens = 156, truncated = 0 0.59.282.590 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 0.59.282.916 I slot launch_slot_: id 2 | task 175 | processing task, is_child = 0 0.59.284.075 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 0.59.284.106 I slot launch_slot_: id 0 | task 176 | processing task, is_child = 0 0.59.284.141 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.171 0.59.284.172 I slot launch_slot_: id 1 | task 177 | processing task, is_child = 0 0.59.284.191 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.186 0.59.284.221 I slot launch_slot_: id 3 | task 178 | processing task, is_child = 0 1.00.347.205 I slot print_timing: id 0 | task 176 | prompt eval time = 1025.11 ms / 111 tokens ( 9.24 ms per token, 108.28 tokens per second) 1.00.347.208 I slot print_timing: id 0 | task 176 | eval time = 37.87 ms / 2 tokens ( 37.87 ms per token, 26.41 tokens per second) 1.00.347.208 I slot print_timing: id 0 | task 176 | total time = 1062.98 ms / 113 tokens 1.00.347.209 I slot print_timing: id 0 | task 176 | graphs reused = 1 1.00.347.209 I slot print_timing: id 0 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.347.227 I slot release: id 0 | task 176 | stop processing: n_tokens = 112, truncated = 0 1.00.347.505 I slot print_timing: id 1 | task 177 | prompt eval time = 1025.38 ms / 150 tokens ( 6.84 ms per token, 146.29 tokens per second) 1.00.347.507 I slot print_timing: id 1 | task 177 | eval time = 37.89 ms / 2 tokens ( 37.89 ms per token, 26.39 tokens per second) 1.00.347.508 I slot print_timing: id 1 | task 177 | total time = 1063.27 ms / 152 tokens 1.00.347.508 I slot print_timing: id 1 | task 177 | graphs reused = 1 1.00.347.508 I slot print_timing: id 1 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.347.526 I slot release: id 1 | task 177 | stop processing: n_tokens = 151, truncated = 0 1.00.347.798 I slot print_timing: id 2 | task 175 | prompt eval time = 1025.63 ms / 113 tokens ( 9.08 ms per token, 110.18 tokens per second) 1.00.347.801 I slot print_timing: id 2 | task 175 | eval time = 37.91 ms / 2 tokens ( 37.91 ms per token, 26.37 tokens per second) 1.00.347.801 I slot print_timing: id 2 | task 175 | total time = 1063.55 ms / 115 tokens 1.00.347.801 I slot print_timing: id 2 | task 175 | graphs reused = 1 1.00.347.802 I slot print_timing: id 2 | task 175 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.347.821 I slot release: id 2 | task 175 | stop processing: n_tokens = 114, truncated = 0 1.00.348.116 I slot print_timing: id 3 | task 178 | prompt eval time = 1025.96 ms / 138 tokens ( 7.43 ms per token, 134.51 tokens per second) 1.00.348.119 I slot print_timing: id 3 | task 178 | eval time = 37.90 ms / 2 tokens ( 37.90 ms per token, 26.39 tokens per second) 1.00.348.119 I slot print_timing: id 3 | task 178 | total time = 1063.86 ms / 140 tokens 1.00.348.119 I slot print_timing: id 3 | task 178 | graphs reused = 1 1.00.348.119 I slot print_timing: id 3 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.348.137 I slot release: id 3 | task 178 | stop processing: n_tokens = 139, truncated = 0 1.00.352.670 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 1.00.353.090 I slot launch_slot_: id 2 | task 182 | processing task, is_child = 0 1.00.354.049 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.259 1.00.354.083 I slot launch_slot_: id 0 | task 183 | processing task, is_child = 0 1.00.354.118 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.192 1.00.354.148 I slot launch_slot_: id 1 | task 184 | processing task, is_child = 0 1.00.354.167 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 1.00.354.197 I slot launch_slot_: id 3 | task 185 | processing task, is_child = 0 1.01.437.465 I slot print_timing: id 0 | task 183 | prompt eval time = 1045.54 ms / 131 tokens ( 7.98 ms per token, 125.29 tokens per second) 1.01.437.468 I slot print_timing: id 0 | task 183 | eval time = 37.72 ms / 2 tokens ( 37.72 ms per token, 26.51 tokens per second) 1.01.437.469 I slot print_timing: id 0 | task 183 | total time = 1083.26 ms / 133 tokens 1.01.437.469 I slot print_timing: id 0 | task 183 | graphs reused = 1 1.01.437.469 I slot print_timing: id 0 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.437.489 I slot release: id 0 | task 183 | stop processing: n_tokens = 132, truncated = 0 1.01.437.771 I slot print_timing: id 1 | task 184 | prompt eval time = 1045.84 ms / 153 tokens ( 6.84 ms per token, 146.29 tokens per second) 1.01.437.773 I slot print_timing: id 1 | task 184 | eval time = 37.71 ms / 2 tokens ( 37.71 ms per token, 26.52 tokens per second) 1.01.437.773 I slot print_timing: id 1 | task 184 | total time = 1083.56 ms / 155 tokens 1.01.437.774 I slot print_timing: id 1 | task 184 | graphs reused = 1 1.01.437.774 I slot print_timing: id 1 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.437.788 I slot release: id 1 | task 184 | stop processing: n_tokens = 154, truncated = 0 1.01.438.065 I slot print_timing: id 2 | task 182 | prompt eval time = 1046.13 ms / 114 tokens ( 9.18 ms per token, 108.97 tokens per second) 1.01.438.067 I slot print_timing: id 2 | task 182 | eval time = 37.71 ms / 2 tokens ( 37.71 ms per token, 26.52 tokens per second) 1.01.438.067 I slot print_timing: id 2 | task 182 | total time = 1083.84 ms / 116 tokens 1.01.438.068 I slot print_timing: id 2 | task 182 | graphs reused = 1 1.01.438.068 I slot print_timing: id 2 | task 182 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.438.080 I slot release: id 2 | task 182 | stop processing: n_tokens = 115, truncated = 0 1.01.438.368 I slot print_timing: id 3 | task 185 | prompt eval time = 1046.40 ms / 126 tokens ( 8.30 ms per token, 120.41 tokens per second) 1.01.438.370 I slot print_timing: id 3 | task 185 | eval time = 37.73 ms / 2 tokens ( 37.73 ms per token, 26.51 tokens per second) 1.01.438.371 I slot print_timing: id 3 | task 185 | total time = 1084.13 ms / 128 tokens 1.01.438.371 I slot print_timing: id 3 | task 185 | graphs reused = 1 1.01.438.371 I slot print_timing: id 3 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.438.387 I slot release: id 3 | task 185 | stop processing: n_tokens = 127, truncated = 0 1.01.443.333 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.185 (> 0.100 thold), f_keep = 0.220 1.01.443.793 I slot launch_slot_: id 0 | task 189 | processing task, is_child = 0 1.01.444.943 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 1.01.444.978 I slot launch_slot_: id 2 | task 190 | processing task, is_child = 0 1.01.445.013 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.223 (> 0.100 thold), f_keep = 0.188 1.01.445.044 I slot launch_slot_: id 1 | task 191 | processing task, is_child = 0 1.01.445.063 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 1.01.445.092 I slot launch_slot_: id 3 | task 192 | processing task, is_child = 0 1.02.651.478 I slot print_timing: id 0 | task 189 | prompt eval time = 1168.33 ms / 157 tokens ( 7.44 ms per token, 134.38 tokens per second) 1.02.651.480 I slot print_timing: id 0 | task 189 | eval time = 38.05 ms / 2 tokens ( 38.05 ms per token, 26.28 tokens per second) 1.02.651.480 I slot print_timing: id 0 | task 189 | total time = 1206.38 ms / 159 tokens 1.02.651.480 I slot print_timing: id 0 | task 189 | graphs reused = 1 1.02.651.481 I slot print_timing: id 0 | task 189 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.651.504 I slot release: id 0 | task 189 | stop processing: n_tokens = 158, truncated = 0 1.02.651.770 I slot print_timing: id 1 | task 191 | prompt eval time = 1168.59 ms / 130 tokens ( 8.99 ms per token, 111.25 tokens per second) 1.02.651.777 I slot print_timing: id 1 | task 191 | eval time = 38.08 ms / 2 tokens ( 38.08 ms per token, 26.26 tokens per second) 1.02.651.777 I slot print_timing: id 1 | task 191 | total time = 1206.66 ms / 132 tokens 1.02.651.777 I slot print_timing: id 1 | task 191 | graphs reused = 1 1.02.651.778 I slot print_timing: id 1 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.651.790 I slot release: id 1 | task 191 | stop processing: n_tokens = 131, truncated = 0 1.02.652.069 I slot print_timing: id 2 | task 190 | prompt eval time = 1168.87 ms / 119 tokens ( 9.82 ms per token, 101.81 tokens per second) 1.02.652.071 I slot print_timing: id 2 | task 190 | eval time = 38.07 ms / 2 tokens ( 38.07 ms per token, 26.27 tokens per second) 1.02.652.072 I slot print_timing: id 2 | task 190 | total time = 1206.95 ms / 121 tokens 1.02.652.072 I slot print_timing: id 2 | task 190 | graphs reused = 1 1.02.652.072 I slot print_timing: id 2 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.652.084 I slot release: id 2 | task 190 | stop processing: n_tokens = 120, truncated = 0 1.02.652.388 I slot print_timing: id 3 | task 192 | prompt eval time = 1169.18 ms / 170 tokens ( 6.88 ms per token, 145.40 tokens per second) 1.02.652.394 I slot print_timing: id 3 | task 192 | eval time = 38.07 ms / 2 tokens ( 38.07 ms per token, 26.27 tokens per second) 1.02.652.395 I slot print_timing: id 3 | task 192 | total time = 1207.26 ms / 172 tokens 1.02.652.395 I slot print_timing: id 3 | task 192 | graphs reused = 1 1.02.652.395 I slot print_timing: id 3 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.652.418 I slot release: id 3 | task 192 | stop processing: n_tokens = 171, truncated = 0 1.02.657.267 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.184 1.02.657.899 I slot launch_slot_: id 0 | task 196 | processing task, is_child = 0 1.02.659.031 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.221 1.02.659.066 I slot launch_slot_: id 1 | task 197 | processing task, is_child = 0 1.02.659.101 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.242 1.02.659.131 I slot launch_slot_: id 2 | task 198 | processing task, is_child = 0 1.02.659.151 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.159 (> 0.100 thold), f_keep = 0.170 1.02.659.182 I slot launch_slot_: id 3 | task 199 | processing task, is_child = 0 1.03.887.388 I slot print_timing: id 0 | task 196 | prompt eval time = 1190.78 ms / 135 tokens ( 8.82 ms per token, 113.37 tokens per second) 1.03.887.390 I slot print_timing: id 0 | task 196 | eval time = 37.42 ms / 2 tokens ( 37.42 ms per token, 26.72 tokens per second) 1.03.887.391 I slot print_timing: id 0 | task 196 | total time = 1228.20 ms / 137 tokens 1.03.887.391 I slot print_timing: id 0 | task 196 | graphs reused = 1 1.03.887.392 I slot print_timing: id 0 | task 196 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.887.411 I slot release: id 0 | task 196 | stop processing: n_tokens = 136, truncated = 0 1.03.887.707 I slot print_timing: id 1 | task 197 | prompt eval time = 1191.05 ms / 110 tokens ( 10.83 ms per token, 92.36 tokens per second) 1.03.887.709 I slot print_timing: id 1 | task 197 | eval time = 37.46 ms / 2 tokens ( 37.46 ms per token, 26.70 tokens per second) 1.03.887.710 I slot print_timing: id 1 | task 197 | total time = 1228.51 ms / 112 tokens 1.03.887.710 I slot print_timing: id 1 | task 197 | graphs reused = 1 1.03.887.710 I slot print_timing: id 1 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.887.723 I slot release: id 1 | task 197 | stop processing: n_tokens = 111, truncated = 0 1.03.888.021 I slot print_timing: id 2 | task 198 | prompt eval time = 1191.37 ms / 155 tokens ( 7.69 ms per token, 130.10 tokens per second) 1.03.888.023 I slot print_timing: id 2 | task 198 | eval time = 37.45 ms / 2 tokens ( 37.45 ms per token, 26.71 tokens per second) 1.03.888.024 I slot print_timing: id 2 | task 198 | total time = 1228.81 ms / 157 tokens 1.03.888.024 I slot print_timing: id 2 | task 198 | graphs reused = 1 1.03.888.024 I slot print_timing: id 2 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.888.043 I slot release: id 2 | task 198 | stop processing: n_tokens = 156, truncated = 0 1.03.888.367 I slot print_timing: id 3 | task 199 | prompt eval time = 1191.67 ms / 182 tokens ( 6.55 ms per token, 152.73 tokens per second) 1.03.888.369 I slot print_timing: id 3 | task 199 | eval time = 37.48 ms / 2 tokens ( 37.48 ms per token, 26.68 tokens per second) 1.03.888.369 I slot print_timing: id 3 | task 199 | total time = 1229.15 ms / 184 tokens 1.03.888.369 I slot print_timing: id 3 | task 199 | graphs reused = 1 1.03.888.369 I slot print_timing: id 3 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.888.383 I slot release: id 3 | task 199 | stop processing: n_tokens = 183, truncated = 0 1.03.892.552 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.213 1.03.892.983 I slot launch_slot_: id 0 | task 203 | processing task, is_child = 0 1.03.894.025 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.261 1.03.894.065 I slot launch_slot_: id 1 | task 204 | processing task, is_child = 0 1.03.894.102 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.186 1.03.894.256 I slot launch_slot_: id 2 | task 205 | processing task, is_child = 0 1.03.894.276 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.158 1.03.894.307 I slot launch_slot_: id 3 | task 206 | processing task, is_child = 0 1.04.977.394 I slot print_timing: id 0 | task 203 | prompt eval time = 1044.89 ms / 134 tokens ( 7.80 ms per token, 128.24 tokens per second) 1.04.977.397 I slot print_timing: id 0 | task 203 | eval time = 38.18 ms / 2 tokens ( 38.18 ms per token, 26.19 tokens per second) 1.04.977.397 I slot print_timing: id 0 | task 203 | total time = 1083.08 ms / 136 tokens 1.04.977.398 I slot print_timing: id 0 | task 203 | graphs reused = 1 1.04.977.398 I slot print_timing: id 0 | task 203 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.977.431 I slot release: id 0 | task 203 | stop processing: n_tokens = 135, truncated = 0 1.04.977.721 I slot print_timing: id 1 | task 204 | prompt eval time = 1045.27 ms / 136 tokens ( 7.69 ms per token, 130.11 tokens per second) 1.04.977.723 I slot print_timing: id 1 | task 204 | eval time = 38.13 ms / 2 tokens ( 38.13 ms per token, 26.22 tokens per second) 1.04.977.723 I slot print_timing: id 1 | task 204 | total time = 1083.40 ms / 138 tokens 1.04.977.723 I slot print_timing: id 1 | task 204 | graphs reused = 1 1.04.977.724 I slot print_timing: id 1 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.977.737 I slot release: id 1 | task 204 | stop processing: n_tokens = 137, truncated = 0 1.04.978.025 I slot print_timing: id 2 | task 205 | prompt eval time = 1045.64 ms / 117 tokens ( 8.94 ms per token, 111.89 tokens per second) 1.04.978.027 I slot print_timing: id 2 | task 205 | eval time = 38.05 ms / 2 tokens ( 38.05 ms per token, 26.28 tokens per second) 1.04.978.028 I slot print_timing: id 2 | task 205 | total time = 1083.69 ms / 119 tokens 1.04.978.028 I slot print_timing: id 2 | task 205 | graphs reused = 1 1.04.978.028 I slot print_timing: id 2 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.978.041 I slot release: id 2 | task 205 | stop processing: n_tokens = 118, truncated = 0 1.04.978.328 I slot print_timing: id 3 | task 206 | prompt eval time = 1046.12 ms / 160 tokens ( 6.54 ms per token, 152.95 tokens per second) 1.04.978.331 I slot print_timing: id 3 | task 206 | eval time = 37.87 ms / 2 tokens ( 37.87 ms per token, 26.41 tokens per second) 1.04.978.331 I slot print_timing: id 3 | task 206 | total time = 1083.98 ms / 162 tokens 1.04.978.331 I slot print_timing: id 3 | task 206 | graphs reused = 1 1.04.978.332 I slot print_timing: id 3 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.978.344 I slot release: id 3 | task 206 | stop processing: n_tokens = 161, truncated = 0 1.04.982.545 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.254 1.04.983.049 I slot launch_slot_: id 2 | task 210 | processing task, is_child = 0 1.04.984.143 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.215 1.04.984.291 I slot launch_slot_: id 0 | task 211 | processing task, is_child = 0 1.04.984.328 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.212 1.04.984.359 I slot launch_slot_: id 1 | task 212 | processing task, is_child = 0 1.04.984.379 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.180 1.04.984.410 I slot launch_slot_: id 3 | task 213 | processing task, is_child = 0 1.06.126.978 I slot print_timing: id 0 | task 211 | prompt eval time = 1104.59 ms / 118 tokens ( 9.36 ms per token, 106.83 tokens per second) 1.06.126.979 I slot print_timing: id 0 | task 211 | eval time = 37.96 ms / 2 tokens ( 37.96 ms per token, 26.34 tokens per second) 1.06.126.980 I slot print_timing: id 0 | task 211 | total time = 1142.55 ms / 120 tokens 1.06.126.980 I slot print_timing: id 0 | task 211 | graphs reused = 1 1.06.126.981 I slot print_timing: id 0 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.127.004 I slot release: id 0 | task 211 | stop processing: n_tokens = 119, truncated = 0 1.06.127.267 I slot print_timing: id 1 | task 212 | prompt eval time = 1104.89 ms / 156 tokens ( 7.08 ms per token, 141.19 tokens per second) 1.06.127.269 I slot print_timing: id 1 | task 212 | eval time = 37.94 ms / 2 tokens ( 37.94 ms per token, 26.36 tokens per second) 1.06.127.269 I slot print_timing: id 1 | task 212 | total time = 1142.84 ms / 158 tokens 1.06.127.270 I slot print_timing: id 1 | task 212 | graphs reused = 1 1.06.127.270 I slot print_timing: id 1 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.127.286 I slot release: id 1 | task 212 | stop processing: n_tokens = 157, truncated = 0 1.06.127.563 I slot print_timing: id 2 | task 210 | prompt eval time = 1105.16 ms / 124 tokens ( 8.91 ms per token, 112.20 tokens per second) 1.06.127.565 I slot print_timing: id 2 | task 210 | eval time = 37.96 ms / 2 tokens ( 37.96 ms per token, 26.34 tokens per second) 1.06.127.565 I slot print_timing: id 2 | task 210 | total time = 1143.12 ms / 126 tokens 1.06.127.566 I slot print_timing: id 2 | task 210 | graphs reused = 1 1.06.127.566 I slot print_timing: id 2 | task 210 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.127.581 I slot release: id 2 | task 210 | stop processing: n_tokens = 125, truncated = 0 1.06.127.881 I slot print_timing: id 3 | task 213 | prompt eval time = 1105.55 ms / 151 tokens ( 7.32 ms per token, 136.58 tokens per second) 1.06.127.884 I slot print_timing: id 3 | task 213 | eval time = 37.88 ms / 2 tokens ( 37.88 ms per token, 26.40 tokens per second) 1.06.127.884 I slot print_timing: id 3 | task 213 | total time = 1143.43 ms / 153 tokens 1.06.127.884 I slot print_timing: id 3 | task 213 | graphs reused = 1 1.06.127.885 I slot print_timing: id 3 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.127.906 I slot release: id 3 | task 213 | stop processing: n_tokens = 152, truncated = 0 1.06.132.381 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.244 1.06.132.635 I slot launch_slot_: id 0 | task 217 | processing task, is_child = 0 1.06.133.914 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.185 1.06.133.953 I slot launch_slot_: id 1 | task 218 | processing task, is_child = 0 1.06.133.988 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.232 1.06.134.018 I slot launch_slot_: id 2 | task 219 | processing task, is_child = 0 1.06.134.037 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.191 1.06.134.071 I slot launch_slot_: id 3 | task 220 | processing task, is_child = 0 1.07.270.637 I slot print_timing: id 1 | task 218 | prompt eval time = 1098.89 ms / 154 tokens ( 7.14 ms per token, 140.14 tokens per second) 1.07.270.640 I slot print_timing: id 1 | task 218 | eval time = 37.65 ms / 2 tokens ( 37.65 ms per token, 26.56 tokens per second) 1.07.270.641 I slot print_timing: id 1 | task 218 | total time = 1136.55 ms / 156 tokens 1.07.270.641 I slot print_timing: id 1 | task 218 | graphs reused = 1 1.07.270.642 I slot print_timing: id 1 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.270.663 I slot release: id 1 | task 218 | stop processing: n_tokens = 155, truncated = 0 1.07.270.929 I slot print_timing: id 2 | task 219 | prompt eval time = 1099.16 ms / 149 tokens ( 7.38 ms per token, 135.56 tokens per second) 1.07.270.931 I slot print_timing: id 2 | task 219 | eval time = 37.66 ms / 2 tokens ( 37.66 ms per token, 26.55 tokens per second) 1.07.270.931 I slot print_timing: id 2 | task 219 | total time = 1136.83 ms / 151 tokens 1.07.270.931 I slot print_timing: id 2 | task 219 | graphs reused = 1 1.07.270.932 I slot print_timing: id 2 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.270.956 I slot release: id 2 | task 219 | stop processing: n_tokens = 150, truncated = 0 1.07.271.241 I slot print_timing: id 3 | task 220 | prompt eval time = 1099.46 ms / 156 tokens ( 7.05 ms per token, 141.89 tokens per second) 1.07.271.243 I slot print_timing: id 3 | task 220 | eval time = 37.67 ms / 2 tokens ( 37.67 ms per token, 26.55 tokens per second) 1.07.271.244 I slot print_timing: id 3 | task 220 | total time = 1137.13 ms / 158 tokens 1.07.271.244 I slot print_timing: id 3 | task 220 | graphs reused = 1 1.07.271.244 I slot print_timing: id 3 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.271.257 I slot release: id 3 | task 220 | stop processing: n_tokens = 157, truncated = 0 1.07.286.054 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.187 1.07.286.501 I slot launch_slot_: id 1 | task 225 | processing task, is_child = 0 1.07.287.331 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.193 1.07.287.371 I slot launch_slot_: id 2 | task 226 | processing task, is_child = 0 1.07.287.393 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.185 1.07.287.430 I slot launch_slot_: id 3 | task 227 | processing task, is_child = 0 1.08.205.411 I slot print_timing: id 1 | task 225 | prompt eval time = 879.96 ms / 108 tokens ( 8.15 ms per token, 122.73 tokens per second) 1.08.205.414 I slot print_timing: id 1 | task 225 | eval time = 38.02 ms / 2 tokens ( 38.02 ms per token, 26.30 tokens per second) 1.08.205.415 I slot print_timing: id 1 | task 225 | total time = 917.98 ms / 110 tokens 1.08.205.415 I slot print_timing: id 1 | task 225 | graphs reused = 1 1.08.205.416 I slot print_timing: id 1 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.205.433 I slot release: id 1 | task 225 | stop processing: n_tokens = 109, truncated = 0 1.08.205.722 I slot print_timing: id 2 | task 226 | prompt eval time = 880.23 ms / 115 tokens ( 7.65 ms per token, 130.65 tokens per second) 1.08.205.724 I slot print_timing: id 2 | task 226 | eval time = 38.03 ms / 2 tokens ( 38.03 ms per token, 26.29 tokens per second) 1.08.205.725 I slot print_timing: id 2 | task 226 | total time = 918.26 ms / 117 tokens 1.08.205.725 I slot print_timing: id 2 | task 226 | graphs reused = 1 1.08.205.725 I slot print_timing: id 2 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.205.738 I slot release: id 2 | task 226 | stop processing: n_tokens = 116, truncated = 0 1.08.206.102 I slot print_timing: id 3 | task 227 | prompt eval time = 880.60 ms / 186 tokens ( 4.73 ms per token, 211.22 tokens per second) 1.08.206.105 I slot print_timing: id 3 | task 227 | eval time = 38.02 ms / 2 tokens ( 38.02 ms per token, 26.30 tokens per second) 1.08.206.105 I slot print_timing: id 3 | task 227 | total time = 918.63 ms / 188 tokens 1.08.206.105 I slot print_timing: id 3 | task 227 | graphs reused = 1 1.08.206.106 I slot print_timing: id 3 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.206.151 I slot release: id 3 | task 227 | stop processing: n_tokens = 187, truncated = 0 1.08.221.289 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.266 1.08.221.615 I slot launch_slot_: id 1 | task 232 | processing task, is_child = 0 1.08.222.283 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 1.08.222.451 I slot launch_slot_: id 2 | task 233 | processing task, is_child = 0 1.08.222.474 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.155 1.08.222.654 I slot launch_slot_: id 3 | task 234 | processing task, is_child = 0 1.09.002.134 I slot print_timing: id 1 | task 232 | prompt eval time = 741.27 ms / 103 tokens ( 7.20 ms per token, 138.95 tokens per second) 1.09.002.140 I slot print_timing: id 1 | task 232 | eval time = 38.20 ms / 2 tokens ( 38.20 ms per token, 26.18 tokens per second) 1.09.002.140 I slot print_timing: id 1 | task 232 | total time = 779.47 ms / 105 tokens 1.09.002.141 I slot print_timing: id 1 | task 232 | graphs reused = 1 1.09.002.141 I slot print_timing: id 1 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.002.160 I slot release: id 1 | task 232 | stop processing: n_tokens = 104, truncated = 0 1.09.002.438 I slot print_timing: id 2 | task 233 | prompt eval time = 741.55 ms / 113 tokens ( 6.56 ms per token, 152.38 tokens per second) 1.09.002.443 I slot print_timing: id 2 | task 233 | eval time = 38.22 ms / 2 tokens ( 38.22 ms per token, 26.17 tokens per second) 1.09.002.443 I slot print_timing: id 2 | task 233 | total time = 779.76 ms / 115 tokens 1.09.002.444 I slot print_timing: id 2 | task 233 | graphs reused = 1 1.09.002.444 I slot print_timing: id 2 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.002.456 I slot release: id 2 | task 233 | stop processing: n_tokens = 114, truncated = 0 1.09.002.741 I slot print_timing: id 3 | task 234 | prompt eval time = 741.83 ms / 122 tokens ( 6.08 ms per token, 164.46 tokens per second) 1.09.002.744 I slot print_timing: id 3 | task 234 | eval time = 38.22 ms / 2 tokens ( 38.22 ms per token, 26.16 tokens per second) 1.09.002.745 I slot print_timing: id 3 | task 234 | total time = 780.05 ms / 124 tokens 1.09.002.745 I slot print_timing: id 3 | task 234 | graphs reused = 1 1.09.002.745 I slot print_timing: id 3 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.002.771 I slot release: id 3 | task 234 | stop processing: n_tokens = 123, truncated = 0 1.09.017.552 I slot print_timing: id 0 | task 217 | prompt eval time = 1098.63 ms / 162 tokens ( 6.78 ms per token, 147.46 tokens per second) 1.09.017.554 I slot print_timing: id 0 | task 217 | eval time = 1784.84 ms / 11 tokens ( 178.48 ms per token, 5.60 tokens per second) 1.09.017.555 I slot print_timing: id 0 | task 217 | total time = 2883.47 ms / 173 tokens 1.09.017.555 I slot print_timing: id 0 | task 217 | graphs reused = 1 1.09.017.555 I slot print_timing: id 0 | task 217 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.017.572 I slot release: id 0 | task 217 | stop processing: n_tokens = 172, truncated = 0 1.09.017.577 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.174 1.09.018.027 I slot launch_slot_: id 0 | task 239 | processing task, is_child = 0 1.09.018.589 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.288 1.09.018.630 I slot launch_slot_: id 1 | task 240 | processing task, is_child = 0 1.09.018.672 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.254 1.09.018.709 I slot launch_slot_: id 2 | task 241 | processing task, is_child = 0 1.09.641.431 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.236 1.09.641.491 I slot launch_slot_: id 3 | task 243 | processing task, is_child = 0 1.10.201.465 I slot print_timing: id 0 | task 239 | prompt eval time = 1118.61 ms / 128 tokens ( 8.74 ms per token, 114.43 tokens per second) 1.10.201.471 I slot print_timing: id 0 | task 239 | eval time = 64.12 ms / 2 tokens ( 64.12 ms per token, 15.59 tokens per second) 1.10.201.471 I slot print_timing: id 0 | task 239 | total time = 1182.73 ms / 130 tokens 1.10.201.471 I slot print_timing: id 0 | task 239 | graphs reused = 1 1.10.201.472 I slot print_timing: id 0 | task 239 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.201.495 I slot release: id 0 | task 239 | stop processing: n_tokens = 129, truncated = 0 1.10.201.783 I slot print_timing: id 1 | task 240 | prompt eval time = 1118.88 ms / 139 tokens ( 8.05 ms per token, 124.23 tokens per second) 1.10.201.785 I slot print_timing: id 1 | task 240 | eval time = 64.14 ms / 2 tokens ( 64.14 ms per token, 15.59 tokens per second) 1.10.201.785 I slot print_timing: id 1 | task 240 | total time = 1183.03 ms / 141 tokens 1.10.201.785 I slot print_timing: id 1 | task 240 | graphs reused = 1 1.10.201.786 I slot print_timing: id 1 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.201.799 I slot release: id 1 | task 240 | stop processing: n_tokens = 140, truncated = 0 1.10.202.082 I slot print_timing: id 2 | task 241 | prompt eval time = 1119.16 ms / 163 tokens ( 6.87 ms per token, 145.64 tokens per second) 1.10.202.084 I slot print_timing: id 2 | task 241 | eval time = 64.15 ms / 2 tokens ( 64.15 ms per token, 15.59 tokens per second) 1.10.202.085 I slot print_timing: id 2 | task 241 | total time = 1183.32 ms / 165 tokens 1.10.202.085 I slot print_timing: id 2 | task 241 | graphs reused = 1 1.10.202.085 I slot print_timing: id 2 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.202.099 I slot release: id 2 | task 241 | stop processing: n_tokens = 164, truncated = 0 1.10.217.497 I slot print_timing: id 3 | task 243 | prompt eval time = 428.75 ms / 127 tokens ( 3.38 ms per token, 296.21 tokens per second) 1.10.217.502 I slot print_timing: id 3 | task 243 | eval time = 14.96 ms / 2 tokens ( 14.96 ms per token, 66.85 tokens per second) 1.10.217.503 I slot print_timing: id 3 | task 243 | total time = 443.71 ms / 129 tokens 1.10.217.503 I slot print_timing: id 3 | task 243 | graphs reused = 1 1.10.217.503 I slot print_timing: id 3 | task 243 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.217.522 I slot release: id 3 | task 243 | stop processing: n_tokens = 128, truncated = 0 1.10.217.526 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.214 1.10.218.039 I slot launch_slot_: id 1 | task 247 | processing task, is_child = 0 1.10.219.199 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.225 1.10.219.355 I slot launch_slot_: id 0 | task 248 | processing task, is_child = 0 1.10.219.396 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.240 (> 0.100 thold), f_keep = 0.177 1.10.219.432 I slot launch_slot_: id 2 | task 249 | processing task, is_child = 0 1.10.864.998 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.227 1.10.865.051 I slot launch_slot_: id 3 | task 251 | processing task, is_child = 0 1.11.435.905 I slot print_timing: id 0 | task 248 | prompt eval time = 1152.44 ms / 159 tokens ( 7.25 ms per token, 137.97 tokens per second) 1.11.435.911 I slot print_timing: id 0 | task 248 | eval time = 64.01 ms / 2 tokens ( 64.01 ms per token, 15.62 tokens per second) 1.11.435.911 I slot print_timing: id 0 | task 248 | total time = 1216.45 ms / 161 tokens 1.11.435.912 I slot print_timing: id 0 | task 248 | graphs reused = 1 1.11.435.912 I slot print_timing: id 0 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.435.935 I slot release: id 0 | task 248 | stop processing: n_tokens = 160, truncated = 0 1.11.436.224 I slot print_timing: id 1 | task 247 | prompt eval time = 1152.74 ms / 136 tokens ( 8.48 ms per token, 117.98 tokens per second) 1.11.436.228 I slot print_timing: id 1 | task 247 | eval time = 64.02 ms / 2 tokens ( 64.02 ms per token, 15.62 tokens per second) 1.11.436.230 I slot print_timing: id 1 | task 247 | total time = 1216.76 ms / 138 tokens 1.11.436.230 I slot print_timing: id 1 | task 247 | graphs reused = 1 1.11.436.230 I slot print_timing: id 1 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.436.247 I slot release: id 1 | task 247 | stop processing: n_tokens = 137, truncated = 0 1.11.436.531 I slot print_timing: id 2 | task 249 | prompt eval time = 1153.00 ms / 121 tokens ( 9.53 ms per token, 104.94 tokens per second) 1.11.436.536 I slot print_timing: id 2 | task 249 | eval time = 64.05 ms / 2 tokens ( 64.05 ms per token, 15.61 tokens per second) 1.11.436.536 I slot print_timing: id 2 | task 249 | total time = 1217.05 ms / 123 tokens 1.11.436.537 I slot print_timing: id 2 | task 249 | graphs reused = 1 1.11.436.537 I slot print_timing: id 2 | task 249 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.436.551 I slot release: id 2 | task 249 | stop processing: n_tokens = 122, truncated = 0 1.11.452.310 I slot print_timing: id 3 | task 251 | prompt eval time = 443.92 ms / 142 tokens ( 3.13 ms per token, 319.88 tokens per second) 1.11.452.312 I slot print_timing: id 3 | task 251 | eval time = 15.33 ms / 2 tokens ( 15.33 ms per token, 65.24 tokens per second) 1.11.452.312 I slot print_timing: id 3 | task 251 | total time = 459.25 ms / 144 tokens 1.11.452.313 I slot print_timing: id 3 | task 251 | graphs reused = 1 1.11.452.313 I slot print_timing: id 3 | task 251 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.452.332 I slot release: id 3 | task 251 | stop processing: n_tokens = 143, truncated = 0 1.11.452.336 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.181 1.11.452.750 I slot launch_slot_: id 0 | task 255 | processing task, is_child = 0 1.11.453.903 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.212 1.11.453.941 I slot launch_slot_: id 1 | task 256 | processing task, is_child = 0 1.11.453.986 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.238 1.11.454.017 I slot launch_slot_: id 2 | task 257 | processing task, is_child = 0 1.12.178.000 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.203 1.12.178.075 I slot launch_slot_: id 3 | task 259 | processing task, is_child = 0 1.12.707.379 I slot print_timing: id 0 | task 255 | prompt eval time = 1188.73 ms / 120 tokens ( 9.91 ms per token, 100.95 tokens per second) 1.12.707.383 I slot print_timing: id 0 | task 255 | eval time = 64.61 ms / 2 tokens ( 64.61 ms per token, 15.48 tokens per second) 1.12.707.383 I slot print_timing: id 0 | task 255 | total time = 1253.34 ms / 122 tokens 1.12.707.383 I slot print_timing: id 0 | task 255 | graphs reused = 1 1.12.707.384 I slot print_timing: id 0 | task 255 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.707.406 I slot release: id 0 | task 255 | stop processing: n_tokens = 121, truncated = 0 1.12.707.689 I slot print_timing: id 1 | task 256 | prompt eval time = 1188.99 ms / 184 tokens ( 6.46 ms per token, 154.75 tokens per second) 1.12.707.691 I slot print_timing: id 1 | task 256 | eval time = 64.64 ms / 2 tokens ( 64.64 ms per token, 15.47 tokens per second) 1.12.707.691 I slot print_timing: id 1 | task 256 | total time = 1253.63 ms / 186 tokens 1.12.707.691 I slot print_timing: id 1 | task 256 | graphs reused = 1 1.12.707.691 I slot print_timing: id 1 | task 256 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.707.710 I slot release: id 1 | task 256 | stop processing: n_tokens = 185, truncated = 0 1.12.732.304 I slot print_timing: id 3 | task 259 | prompt eval time = 451.71 ms / 158 tokens ( 2.86 ms per token, 349.78 tokens per second) 1.12.732.309 I slot print_timing: id 3 | task 259 | eval time = 24.00 ms / 2 tokens ( 24.00 ms per token, 41.67 tokens per second) 1.12.732.309 I slot print_timing: id 3 | task 259 | total time = 475.71 ms / 160 tokens 1.12.732.310 I slot print_timing: id 3 | task 259 | graphs reused = 1 1.12.732.310 I slot print_timing: id 3 | task 259 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.732.327 I slot release: id 3 | task 259 | stop processing: n_tokens = 159, truncated = 0 1.12.732.331 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.240 1.12.732.684 I slot launch_slot_: id 0 | task 263 | processing task, is_child = 0 1.12.733.623 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.157 1.12.733.663 I slot launch_slot_: id 1 | task 264 | processing task, is_child = 0 1.13.253.914 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.182 1.13.253.966 I slot launch_slot_: id 3 | task 266 | processing task, is_child = 0 1.13.658.005 I slot print_timing: id 0 | task 263 | prompt eval time = 859.87 ms / 134 tokens ( 6.42 ms per token, 155.84 tokens per second) 1.13.658.010 I slot print_timing: id 0 | task 263 | eval time = 64.44 ms / 2 tokens ( 64.44 ms per token, 15.52 tokens per second) 1.13.658.010 I slot print_timing: id 0 | task 263 | total time = 924.31 ms / 136 tokens 1.13.658.011 I slot print_timing: id 0 | task 263 | graphs reused = 1 1.13.658.011 I slot print_timing: id 0 | task 263 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.658.031 I slot release: id 0 | task 263 | stop processing: n_tokens = 135, truncated = 0 1.13.658.297 I slot print_timing: id 1 | task 264 | prompt eval time = 860.15 ms / 103 tokens ( 8.35 ms per token, 119.75 tokens per second) 1.13.658.299 I slot print_timing: id 1 | task 264 | eval time = 64.44 ms / 2 tokens ( 64.44 ms per token, 15.52 tokens per second) 1.13.658.300 I slot print_timing: id 1 | task 264 | total time = 924.59 ms / 105 tokens 1.13.658.300 I slot print_timing: id 1 | task 264 | graphs reused = 1 1.13.658.300 I slot print_timing: id 1 | task 264 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.658.315 I slot release: id 1 | task 264 | stop processing: n_tokens = 104, truncated = 0 1.13.683.082 I slot print_timing: id 3 | task 266 | prompt eval time = 404.92 ms / 125 tokens ( 3.24 ms per token, 308.70 tokens per second) 1.13.683.084 I slot print_timing: id 3 | task 266 | eval time = 24.07 ms / 2 tokens ( 24.07 ms per token, 41.54 tokens per second) 1.13.683.085 I slot print_timing: id 3 | task 266 | total time = 429.00 ms / 127 tokens 1.13.683.085 I slot print_timing: id 3 | task 266 | graphs reused = 1 1.13.683.086 I slot print_timing: id 3 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.683.104 I slot release: id 3 | task 266 | stop processing: n_tokens = 126, truncated = 0 1.13.683.108 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.215 1.13.683.496 I slot launch_slot_: id 0 | task 270 | processing task, is_child = 0 1.14.055.259 I slot print_timing: id 0 | task 270 | prompt eval time = 341.95 ms / 145 tokens ( 2.36 ms per token, 424.04 tokens per second) 1.14.055.264 I slot print_timing: id 0 | task 270 | eval time = 29.26 ms / 2 tokens ( 29.26 ms per token, 34.18 tokens per second) 1.14.055.265 I slot print_timing: id 0 | task 270 | total time = 371.20 ms / 147 tokens 1.14.055.265 I slot print_timing: id 0 | task 270 | graphs reused = 1 1.14.055.265 I slot print_timing: id 0 | task 270 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.055.282 I slot release: id 0 | task 270 | stop processing: n_tokens = 146, truncated = 0 1.14.121.557 I slot print_timing: id 2 | task 257 | prompt eval time = 1189.26 ms / 170 tokens ( 7.00 ms per token, 142.95 tokens per second) 1.14.121.561 I slot print_timing: id 2 | task 257 | eval time = 1478.23 ms / 15 tokens ( 105.59 ms per token, 9.47 tokens per second) 1.14.121.562 I slot print_timing: id 2 | task 257 | total time = 2667.48 ms / 185 tokens 1.14.121.562 I slot print_timing: id 2 | task 257 | graphs reused = 6 1.14.121.562 I slot print_timing: id 2 | task 257 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.121.578 I slot release: id 2 | task 257 | stop processing: n_tokens = 184, truncated = 0 1.14.138.023 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 104, t_last = 344922009521 1.14.138.096 I slot launch_slot_: id 1 | task 279 | processing task, is_child = 0 1.14.139.109 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 126, t_last = 344922034310 1.14.139.153 I slot launch_slot_: id 3 | task 280 | processing task, is_child = 0 1.14.139.209 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 146, t_last = 344922406488 1.14.139.251 I slot launch_slot_: id 0 | task 282 | processing task, is_child = 0 1.14.139.280 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 184, t_last = 344922472784 1.14.139.327 I slot launch_slot_: id 2 | task 281 | processing task, is_child = 0 1.19.352.682 I slot print_timing: id 0 | task 282 | prompt processing, n_tokens = 1155, progress = 1.00, t = 5.21 s / 221.55 tokens per second 1.19.570.161 I slot print_timing: id 1 | task 279 | prompt processing, n_tokens = 1149, progress = 1.00, t = 5.21 s / 220.40 tokens per second 1.19.570.359 I slot print_timing: id 2 | task 281 | prompt processing, n_tokens = 1129, progress = 1.00, t = 5.21 s / 216.56 tokens per second 1.19.570.540 I slot print_timing: id 3 | task 280 | prompt processing, n_tokens = 632, progress = 0.55, t = 5.21 s / 121.23 tokens per second 1.20.311.073 I slot print_timing: id 3 | task 280 | prompt processing, n_tokens = 1144, progress = 1.00, t = 6.17 s / 185.39 tokens per second 1.24.127.120 I slot print_timing: id 0 | task 282 | n_gen = 100, tg = 25.94 t/s, tg_3s = 26.20 t/s 1.24.127.703 I slot print_timing: id 1 | task 279 | n_gen = 100, tg = 25.94 t/s, tg_3s = 26.20 t/s 1.24.128.256 I slot print_timing: id 2 | task 281 | n_gen = 100, tg = 25.94 t/s, tg_3s = 26.20 t/s 1.24.167.441 I slot print_timing: id 3 | task 280 | n_gen = 100, tg = 26.12 t/s, tg_3s = 26.38 t/s 1.27.165.400 I slot print_timing: id 0 | task 282 | n_gen = 179, tg = 25.97 t/s, tg_3s = 26.00 t/s 1.27.165.977 I slot print_timing: id 1 | task 279 | n_gen = 179, tg = 25.97 t/s, tg_3s = 26.00 t/s 1.27.166.553 I slot print_timing: id 2 | task 281 | n_gen = 179, tg = 25.96 t/s, tg_3s = 26.00 t/s 1.27.205.609 I slot print_timing: id 3 | task 280 | n_gen = 179, tg = 26.07 t/s, tg_3s = 26.00 t/s 1.30.173.438 I slot print_timing: id 0 | task 282 | n_gen = 257, tg = 25.96 t/s, tg_3s = 25.93 t/s 1.30.174.044 I slot print_timing: id 1 | task 279 | n_gen = 257, tg = 25.95 t/s, tg_3s = 25.93 t/s 1.30.174.621 I slot print_timing: id 2 | task 281 | n_gen = 257, tg = 25.95 t/s, tg_3s = 25.93 t/s 1.30.213.934 I slot print_timing: id 3 | task 280 | n_gen = 257, tg = 26.02 t/s, tg_3s = 25.93 t/s 1.30.828.440 I slot print_timing: id 3 | task 280 | prompt eval time = 6237.59 ms / 1148 tokens ( 5.43 ms per token, 184.05 tokens per second) 1.30.828.447 I slot print_timing: id 3 | task 280 | eval time = 10451.43 ms / 273 tokens ( 38.42 ms per token, 26.03 tokens per second) 1.30.828.448 I slot print_timing: id 3 | task 280 | total time = 16689.02 ms / 1421 tokens 1.30.828.449 I slot print_timing: id 3 | task 280 | graphs reused = 278 1.30.828.450 I slot print_timing: id 3 | task 280 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.828.556 I slot release: id 3 | task 280 | stop processing: n_tokens = 1420, truncated = 0 1.30.861.976 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.752 1.30.862.007 I slot launch_slot_: id 3 | task 560 | processing task, is_child = 0 1.33.190.827 I slot print_timing: id 0 | task 282 | n_gen = 315, tg = 24.38 t/s, tg_3s = 19.22 t/s 1.33.191.342 I slot print_timing: id 1 | task 279 | n_gen = 315, tg = 24.38 t/s, tg_3s = 19.22 t/s 1.33.191.920 I slot print_timing: id 2 | task 281 | n_gen = 315, tg = 24.38 t/s, tg_3s = 19.22 t/s 1.35.583.890 I slot print_timing: id 3 | task 560 | n_gen = 100, tg = 25.97 t/s, tg_3s = 26.23 t/s 1.36.200.384 I slot print_timing: id 0 | task 282 | n_gen = 393, tg = 24.67 t/s, tg_3s = 25.92 t/s 1.36.200.967 I slot print_timing: id 1 | task 279 | n_gen = 393, tg = 24.67 t/s, tg_3s = 25.92 t/s 1.36.201.558 I slot print_timing: id 2 | task 281 | n_gen = 393, tg = 24.67 t/s, tg_3s = 25.92 t/s 1.38.621.406 I slot print_timing: id 3 | task 560 | n_gen = 179, tg = 25.99 t/s, tg_3s = 26.01 t/s 1.39.237.013 I slot print_timing: id 0 | task 282 | n_gen = 472, tg = 24.89 t/s, tg_3s = 26.02 t/s 1.39.237.622 I slot print_timing: id 1 | task 279 | n_gen = 472, tg = 24.89 t/s, tg_3s = 26.02 t/s 1.39.238.188 I slot print_timing: id 2 | task 281 | n_gen = 472, tg = 24.88 t/s, tg_3s = 26.02 t/s 1.41.628.327 I slot print_timing: id 3 | task 560 | n_gen = 257, tg = 25.97 t/s, tg_3s = 25.94 t/s 1.41.704.621 I slot print_timing: id 1 | task 279 | prompt eval time = 6171.39 ms / 1153 tokens ( 5.35 ms per token, 186.83 tokens per second) 1.41.704.629 I slot print_timing: id 1 | task 279 | eval time = 21393.87 ms / 536 tokens ( 39.99 ms per token, 25.01 tokens per second) 1.41.704.630 I slot print_timing: id 1 | task 279 | total time = 27565.26 ms / 1689 tokens 1.41.704.630 I slot print_timing: id 1 | task 279 | graphs reused = 534 1.41.704.631 I slot print_timing: id 1 | task 279 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.704.745 I slot release: id 1 | task 279 | stop processing: n_tokens = 1688, truncated = 0 1.41.745.789 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.633 1.41.745.825 I slot launch_slot_: id 1 | task 823 | processing task, is_child = 0 1.42.621.783 I slot print_timing: id 0 | task 282 | n_gen = 539, tg = 24.11 t/s, tg_3s = 19.79 t/s 1.42.622.077 I slot print_timing: id 2 | task 281 | n_gen = 539, tg = 24.11 t/s, tg_3s = 19.80 t/s 1.44.631.350 I slot print_timing: id 3 | task 560 | n_gen = 313, tg = 24.26 t/s, tg_3s = 18.65 t/s 1.45.629.248 I slot print_timing: id 0 | task 282 | n_gen = 616, tg = 24.29 t/s, tg_3s = 25.60 t/s 1.45.630.408 I slot print_timing: id 2 | task 281 | n_gen = 616, tg = 24.29 t/s, tg_3s = 25.60 t/s 1.46.517.299 I slot print_timing: id 1 | task 823 | n_gen = 100, tg = 25.90 t/s, tg_3s = 26.17 t/s 1.47.325.504 I slot print_timing: id 3 | task 560 | prompt eval time = 909.87 ms / 539 tokens ( 1.69 ms per token, 592.39 tokens per second) 1.47.325.510 I slot print_timing: id 3 | task 560 | eval time = 15553.61 ms / 383 tokens ( 40.72 ms per token, 24.56 tokens per second) 1.47.325.511 I slot print_timing: id 3 | task 560 | total time = 16463.49 ms / 922 tokens 1.47.325.512 I slot print_timing: id 3 | task 560 | graphs reused = 652 1.47.325.513 I slot print_timing: id 3 | task 560 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.325.617 I slot release: id 3 | task 560 | stop processing: n_tokens = 1553, truncated = 0 1.47.359.050 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.688 1.47.359.079 I slot launch_slot_: id 3 | task 948 | processing task, is_child = 0 1.48.357.836 I slot print_timing: id 2 | task 281 | prompt eval time = 6171.67 ms / 1133 tokens ( 5.45 ms per token, 183.58 tokens per second) 1.48.357.838 I slot print_timing: id 2 | task 281 | eval time = 28046.78 ms / 668 tokens ( 42.05 ms per token, 23.78 tokens per second) 1.48.357.839 I slot print_timing: id 2 | task 281 | total time = 34218.45 ms / 1801 tokens 1.48.357.839 I slot print_timing: id 2 | task 281 | graphs reused = 655 1.48.357.840 I slot print_timing: id 2 | task 281 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.357.903 I slot release: id 2 | task 281 | stop processing: n_tokens = 1800, truncated = 0 1.48.396.050 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.593 1.48.396.076 I slot launch_slot_: id 2 | task 957 | processing task, is_child = 0 1.49.242.630 I slot print_timing: id 0 | task 282 | n_gen = 671, tg = 23.16 t/s, tg_3s = 15.22 t/s 1.49.542.912 I slot print_timing: id 1 | task 823 | n_gen = 139, tg = 20.15 t/s, tg_3s = 12.89 t/s 1.52.280.145 I slot print_timing: id 0 | task 282 | n_gen = 749, tg = 23.40 t/s, tg_3s = 25.68 t/s 1.52.549.679 I slot print_timing: id 1 | task 823 | n_gen = 217, tg = 21.92 t/s, tg_3s = 25.94 t/s 1.52.819.687 I slot print_timing: id 3 | task 948 | n_gen = 100, tg = 21.46 t/s, tg_3s = 21.68 t/s 1.53.128.111 I slot print_timing: id 2 | task 957 | n_gen = 100, tg = 25.97 t/s, tg_3s = 26.23 t/s 1.55.318.268 I slot print_timing: id 0 | task 282 | n_gen = 828, tg = 23.62 t/s, tg_3s = 26.00 t/s 1.55.587.409 I slot print_timing: id 1 | task 823 | n_gen = 296, tg = 22.88 t/s, tg_3s = 26.01 t/s 1.55.858.395 I slot print_timing: id 3 | task 948 | n_gen = 179, tg = 23.26 t/s, tg_3s = 26.00 t/s 1.56.128.552 I slot print_timing: id 2 | task 957 | n_gen = 178, tg = 25.98 t/s, tg_3s = 26.00 t/s 1.58.331.530 I slot print_timing: id 0 | task 282 | n_gen = 906, tg = 23.80 t/s, tg_3s = 25.89 t/s 1.58.603.609 I slot print_timing: id 1 | task 823 | n_gen = 374, tg = 23.45 t/s, tg_3s = 25.86 t/s 1.58.876.294 I slot print_timing: id 3 | task 948 | n_gen = 257, tg = 23.99 t/s, tg_3s = 25.85 t/s 1.59.146.944 I slot print_timing: id 2 | task 957 | n_gen = 256, tg = 25.94 t/s, tg_3s = 25.84 t/s 2.01.350.085 I slot print_timing: id 0 | task 282 | n_gen = 984, tg = 23.95 t/s, tg_3s = 25.84 t/s 2.01.466.777 I slot print_timing: id 2 | task 957 | prompt eval time = 919.63 ms / 538 tokens ( 1.71 ms per token, 585.02 tokens per second) 2.01.466.784 I slot print_timing: id 2 | task 957 | eval time = 12151.07 ms / 316 tokens ( 38.57 ms per token, 25.92 tokens per second) 2.01.466.786 I slot print_timing: id 2 | task 957 | total time = 13070.70 ms / 854 tokens 2.01.466.787 I slot print_timing: id 2 | task 957 | graphs reused = 968 2.01.466.788 I slot print_timing: id 2 | task 957 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.466.888 I slot release: id 2 | task 957 | stop processing: n_tokens = 1470, truncated = 0 2.01.507.210 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.727 2.01.507.247 I slot launch_slot_: id 2 | task 1277 | processing task, is_child = 0 2.01.714.522 I slot print_timing: id 1 | task 823 | n_gen = 450, tg = 23.61 t/s, tg_3s = 24.43 t/s 2.02.398.772 I slot print_timing: id 3 | task 948 | n_gen = 327, tg = 22.97 t/s, tg_3s = 19.87 t/s 2.03.744.986 I slot print_timing: id 0 | task 282 | prompt eval time = 6171.09 ms / 1159 tokens ( 5.32 ms per token, 187.81 tokens per second) 2.03.744.993 I slot print_timing: id 0 | task 282 | eval time = 43434.56 ms / 1024 tokens ( 42.46 ms per token, 23.55 tokens per second) 2.03.744.994 I slot print_timing: id 0 | task 282 | total time = 49605.65 ms / 2183 tokens 2.03.744.995 I slot print_timing: id 0 | task 282 | graphs reused = 1000 2.03.744.995 I slot print_timing: id 0 | task 282 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.745.097 I slot release: id 0 | task 282 | stop processing: n_tokens = 2182, truncated = 0 2.03.780.151 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.489 2.03.785.469 I slot launch_slot_: id 0 | task 1315 | processing task, is_child = 0 2.04.746.527 I slot print_timing: id 1 | task 823 | n_gen = 489, tg = 22.13 t/s, tg_3s = 12.86 t/s 2.05.402.199 I slot print_timing: id 3 | task 948 | n_gen = 382, tg = 22.16 t/s, tg_3s = 18.31 t/s 2.07.136.847 I slot print_timing: id 2 | task 1277 | n_gen = 100, tg = 21.22 t/s, tg_3s = 21.43 t/s 2.07.754.296 I slot print_timing: id 1 | task 823 | n_gen = 567, tg = 22.59 t/s, tg_3s = 25.93 t/s 2.08.411.650 I slot print_timing: id 3 | task 948 | n_gen = 460, tg = 22.72 t/s, tg_3s = 25.92 t/s 2.08.564.690 I slot print_timing: id 0 | task 1315 | n_gen = 100, tg = 25.93 t/s, tg_3s = 26.19 t/s 2.10.145.883 I slot print_timing: id 2 | task 1277 | n_gen = 178, tg = 23.06 t/s, tg_3s = 25.92 t/s 2.10.762.346 I slot print_timing: id 1 | task 823 | n_gen = 645, tg = 22.95 t/s, tg_3s = 25.93 t/s 2.11.417.954 I slot print_timing: id 3 | task 948 | n_gen = 538, tg = 23.14 t/s, tg_3s = 25.95 t/s 2.11.570.233 I slot print_timing: id 0 | task 1315 | n_gen = 178, tg = 25.94 t/s, tg_3s = 25.95 t/s 2.13.147.697 I slot print_timing: id 2 | task 1277 | n_gen = 256, tg = 23.88 t/s, tg_3s = 25.98 t/s 2.13.456.513 I slot print_timing: id 3 | task 948 | prompt eval time = 847.48 ms / 526 tokens ( 1.61 ms per token, 620.66 tokens per second) 2.13.456.521 I slot print_timing: id 3 | task 948 | eval time = 25249.95 ms / 591 tokens ( 42.80 ms per token, 23.37 tokens per second) 2.13.456.521 I slot print_timing: id 3 | task 948 | total time = 26097.43 ms / 1117 tokens 2.13.456.522 I slot print_timing: id 3 | task 948 | graphs reused = 1225 2.13.456.523 I slot print_timing: id 3 | task 948 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.456.635 I slot release: id 3 | task 948 | stop processing: n_tokens = 1771, truncated = 0 2.13.490.368 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.603 2.13.490.405 I slot launch_slot_: id 3 | task 1546 | processing task, is_child = 0 2.14.159.050 I slot print_timing: id 1 | task 823 | n_gen = 717, tg = 22.76 t/s, tg_3s = 21.20 t/s 2.14.571.740 I slot print_timing: id 0 | task 1315 | n_gen = 239, tg = 24.22 t/s, tg_3s = 20.32 t/s 2.16.153.216 I slot print_timing: id 2 | task 1277 | n_gen = 317, tg = 23.10 t/s, tg_3s = 20.30 t/s 2.17.193.196 I slot print_timing: id 1 | task 823 | n_gen = 795, tg = 23.02 t/s, tg_3s = 25.71 t/s 2.17.577.457 I slot print_timing: id 0 | task 1315 | n_gen = 317, tg = 24.63 t/s, tg_3s = 25.95 t/s 2.18.044.187 I slot print_timing: id 3 | task 1546 | n_gen = 100, tg = 25.93 t/s, tg_3s = 26.19 t/s 2.19.163.466 I slot print_timing: id 2 | task 1277 | n_gen = 395, tg = 23.60 t/s, tg_3s = 25.91 t/s 2.20.210.805 I slot print_timing: id 1 | task 823 | n_gen = 873, tg = 23.24 t/s, tg_3s = 25.85 t/s 2.20.596.455 I slot print_timing: id 0 | task 1315 | n_gen = 395, tg = 24.86 t/s, tg_3s = 25.84 t/s 2.21.060.207 I slot print_timing: id 3 | task 1546 | n_gen = 178, tg = 25.90 t/s, tg_3s = 25.86 t/s 2.22.136.229 I slot print_timing: id 2 | task 1277 | prompt eval time = 963.97 ms / 547 tokens ( 1.76 ms per token, 567.44 tokens per second) 2.22.136.237 I slot print_timing: id 2 | task 1277 | eval time = 19665.00 ms / 472 tokens ( 41.75 ms per token, 23.95 tokens per second) 2.22.136.238 I slot print_timing: id 2 | task 1277 | total time = 20628.97 ms / 1019 tokens 2.22.136.239 I slot print_timing: id 2 | task 1277 | graphs reused = 1428 2.22.136.239 I slot print_timing: id 2 | task 1277 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.136.361 I slot release: id 2 | task 1277 | stop processing: n_tokens = 1657, truncated = 0 2.22.177.070 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.645 2.22.177.105 I slot launch_slot_: id 2 | task 1755 | processing task, is_child = 0 2.23.214.154 I slot print_timing: id 1 | task 823 | n_gen = 934, tg = 23.03 t/s, tg_3s = 20.31 t/s 2.23.598.183 I slot print_timing: id 0 | task 1315 | n_gen = 456, tg = 24.14 t/s, tg_3s = 20.32 t/s 2.24.063.754 I slot print_timing: id 3 | task 1546 | n_gen = 239, tg = 24.19 t/s, tg_3s = 20.31 t/s 2.26.232.118 I slot print_timing: id 1 | task 823 | n_gen = 1012, tg = 23.22 t/s, tg_3s = 25.85 t/s 2.26.619.133 I slot print_timing: id 0 | task 1315 | n_gen = 534, tg = 24.37 t/s, tg_3s = 25.82 t/s 2.26.697.018 I slot print_timing: id 1 | task 823 | prompt eval time = 949.74 ms / 543 tokens ( 1.75 ms per token, 571.74 tokens per second) 2.26.697.022 I slot print_timing: id 1 | task 823 | eval time = 44001.44 ms / 1024 tokens ( 43.01 ms per token, 23.25 tokens per second) 2.26.697.023 I slot print_timing: id 1 | task 823 | total time = 44951.18 ms / 1567 tokens 2.26.697.024 I slot print_timing: id 1 | task 823 | graphs reused = 1525 2.26.697.025 I slot print_timing: id 1 | task 823 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.697.135 I slot release: id 1 | task 823 | stop processing: n_tokens = 2203, truncated = 0 2.26.737.378 I slot print_timing: id 2 | task 1755 | n_gen = 100, tg = 25.78 t/s, tg_3s = 26.04 t/s 2.26.737.921 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.485 2.26.744.267 I slot launch_slot_: id 1 | task 1857 | processing task, is_child = 0 2.27.393.691 I slot print_timing: id 3 | task 1546 | n_gen = 309, tg = 23.39 t/s, tg_3s = 21.02 t/s 2.29.629.684 I slot print_timing: id 0 | task 1315 | n_gen = 595, tg = 23.87 t/s, tg_3s = 20.26 t/s 2.29.745.568 I slot print_timing: id 2 | task 1755 | n_gen = 161, tg = 23.36 t/s, tg_3s = 20.28 t/s 2.30.399.964 I slot print_timing: id 3 | task 1546 | n_gen = 386, tg = 23.80 t/s, tg_3s = 25.61 t/s 2.31.282.033 I slot print_timing: id 1 | task 1857 | n_gen = 100, tg = 25.95 t/s, tg_3s = 26.21 t/s 2.31.897.152 I slot print_timing: id 0 | task 1315 | prompt eval time = 960.78 ms / 568 tokens ( 1.69 ms per token, 591.19 tokens per second) 2.31.897.159 I slot print_timing: id 0 | task 1315 | eval time = 27150.89 ms / 654 tokens ( 41.58 ms per token, 24.05 tokens per second) 2.31.897.160 I slot print_timing: id 0 | task 1315 | total time = 28111.67 ms / 1222 tokens 2.31.897.161 I slot print_timing: id 0 | task 1315 | graphs reused = 1638 2.31.897.162 I slot print_timing: id 0 | task 1315 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.897.269 I slot release: id 0 | task 1315 | stop processing: n_tokens = 1864, truncated = 0 2.31.932.209 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.573 2.31.932.240 I slot launch_slot_: id 0 | task 1976 | processing task, is_child = 0 2.32.746.944 I slot print_timing: id 2 | task 1755 | n_gen = 224, tg = 22.64 t/s, tg_3s = 20.99 t/s 2.33.402.757 I slot print_timing: id 3 | task 1546 | n_gen = 449, tg = 23.36 t/s, tg_3s = 20.98 t/s 2.33.939.146 I slot print_timing: id 3 | task 1546 | prompt eval time = 735.94 ms / 503 tokens ( 1.46 ms per token, 683.48 tokens per second) 2.33.939.153 I slot print_timing: id 3 | task 1546 | eval time = 19712.79 ms / 463 tokens ( 42.67 ms per token, 23.44 tokens per second) 2.33.939.154 I slot print_timing: id 3 | task 1546 | total time = 20448.73 ms / 966 tokens 2.33.939.155 I slot print_timing: id 3 | task 1546 | graphs reused = 1673 2.33.939.156 I slot print_timing: id 3 | task 1546 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.939.257 I slot release: id 3 | task 1546 | stop processing: n_tokens = 1630, truncated = 0 2.33.972.754 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.655 2.33.972.789 I slot launch_slot_: id 3 | task 2015 | processing task, is_child = 0 2.34.641.340 I slot print_timing: id 1 | task 1857 | n_gen = 156, tg = 21.60 t/s, tg_3s = 16.67 t/s 2.35.748.800 I slot print_timing: id 2 | task 1755 | n_gen = 285, tg = 22.10 t/s, tg_3s = 20.32 t/s 2.37.055.857 I slot print_timing: id 0 | task 1976 | n_gen = 100, tg = 22.19 t/s, tg_3s = 22.42 t/s 2.37.670.186 I slot print_timing: id 1 | task 1857 | n_gen = 234, tg = 22.84 t/s, tg_3s = 25.75 t/s 2.38.514.880 I slot print_timing: id 3 | task 2015 | n_gen = 100, tg = 26.01 t/s, tg_3s = 26.27 t/s 2.38.782.433 I slot print_timing: id 2 | task 1755 | n_gen = 364, tg = 22.85 t/s, tg_3s = 26.04 t/s 2.39.586.621 I slot print_timing: id 2 | task 1755 | prompt eval time = 719.63 ms / 475 tokens ( 1.52 ms per token, 660.06 tokens per second) 2.39.586.628 I slot print_timing: id 2 | task 1755 | eval time = 16689.88 ms / 385 tokens ( 43.46 ms per token, 23.01 tokens per second) 2.39.586.629 I slot print_timing: id 2 | task 1755 | total time = 17409.51 ms / 860 tokens 2.39.586.630 I slot print_timing: id 2 | task 1755 | graphs reused = 1799 2.39.586.631 I slot print_timing: id 2 | task 1755 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.586.749 I slot release: id 2 | task 1755 | stop processing: n_tokens = 1529, truncated = 0 2.39.627.250 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.698 2.39.627.293 I slot launch_slot_: id 2 | task 2146 | processing task, is_child = 0 2.40.388.428 I slot print_timing: id 0 | task 1976 | n_gen = 169, tg = 21.56 t/s, tg_3s = 20.70 t/s 2.40.692.279 I slot print_timing: id 1 | task 1857 | n_gen = 294, tg = 22.15 t/s, tg_3s = 19.85 t/s 2.41.541.512 I slot print_timing: id 3 | task 2015 | n_gen = 160, tg = 23.27 t/s, tg_3s = 19.82 t/s 2.43.388.451 I slot print_timing: id 0 | task 1976 | n_gen = 246, tg = 22.70 t/s, tg_3s = 25.67 t/s 2.43.696.759 I slot print_timing: id 1 | task 1857 | n_gen = 372, tg = 22.86 t/s, tg_3s = 25.96 t/s 2.44.275.058 I slot print_timing: id 2 | task 2146 | n_gen = 100, tg = 25.96 t/s, tg_3s = 26.22 t/s 2.44.544.910 I slot print_timing: id 3 | task 2015 | n_gen = 238, tg = 24.09 t/s, tg_3s = 25.97 t/s 2.46.426.639 I slot print_timing: id 0 | task 1976 | n_gen = 325, tg = 23.42 t/s, tg_3s = 26.00 t/s 2.46.735.089 I slot print_timing: id 1 | task 1857 | n_gen = 451, tg = 23.35 t/s, tg_3s = 26.00 t/s 2.47.313.459 I slot print_timing: id 2 | task 2146 | n_gen = 179, tg = 25.98 t/s, tg_3s = 26.00 t/s 2.47.546.357 I slot print_timing: id 3 | task 2015 | n_gen = 316, tg = 24.54 t/s, tg_3s = 25.99 t/s 2.49.169.337 I slot print_timing: id 3 | task 2015 | prompt eval time = 735.38 ms / 501 tokens ( 1.47 ms per token, 681.28 tokens per second) 2.49.169.345 I slot print_timing: id 3 | task 2015 | eval time = 14461.16 ms / 358 tokens ( 40.51 ms per token, 24.69 tokens per second) 2.49.169.346 I slot print_timing: id 3 | task 2015 | total time = 15196.54 ms / 859 tokens 2.49.169.346 I slot print_timing: id 3 | task 2015 | graphs reused = 2023 2.49.169.347 I slot print_timing: id 3 | task 2015 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.169.452 I slot release: id 3 | task 2015 | stop processing: n_tokens = 1523, truncated = 0 2.49.202.722 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.701 2.49.202.757 I slot launch_slot_: id 3 | task 2377 | processing task, is_child = 0 2.49.835.015 I slot print_timing: id 0 | task 1976 | n_gen = 398, tg = 23.03 t/s, tg_3s = 21.42 t/s 2.49.835.313 I slot print_timing: id 1 | task 1857 | n_gen = 516, tg = 23.02 t/s, tg_3s = 20.97 t/s 2.50.323.711 I slot print_timing: id 2 | task 2146 | n_gen = 241, tg = 24.34 t/s, tg_3s = 20.60 t/s 2.52.093.814 I slot print_timing: id 1 | task 1857 | prompt eval time = 722.73 ms / 479 tokens ( 1.51 ms per token, 662.76 tokens per second) 2.52.093.818 I slot print_timing: id 1 | task 1857 | eval time = 24626.80 ms / 574 tokens ( 42.98 ms per token, 23.27 tokens per second) 2.52.093.820 I slot print_timing: id 1 | task 1857 | total time = 25349.53 ms / 1053 tokens 2.52.093.821 I slot print_timing: id 1 | task 1857 | graphs reused = 2079 2.52.093.821 I slot print_timing: id 1 | task 1857 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.093.930 I slot release: id 1 | task 1857 | stop processing: n_tokens = 1716, truncated = 0 2.52.134.960 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.622 2.52.134.997 I slot launch_slot_: id 1 | task 2438 | processing task, is_child = 0 2.52.887.656 I slot print_timing: id 0 | task 1976 | n_gen = 459, tg = 22.57 t/s, tg_3s = 19.98 t/s 2.53.349.941 I slot print_timing: id 2 | task 2146 | n_gen = 302, tg = 23.35 t/s, tg_3s = 20.16 t/s 2.54.386.793 I slot print_timing: id 3 | task 2377 | n_gen = 100, tg = 22.07 t/s, tg_3s = 22.29 t/s 2.55.887.712 I slot print_timing: id 0 | task 1976 | n_gen = 537, tg = 23.01 t/s, tg_3s = 26.00 t/s 2.56.353.017 I slot print_timing: id 2 | task 2146 | n_gen = 380, tg = 23.85 t/s, tg_3s = 25.97 t/s 2.56.699.088 I slot print_timing: id 1 | task 2438 | n_gen = 100, tg = 25.98 t/s, tg_3s = 26.24 t/s 2.57.389.353 I slot print_timing: id 3 | task 2377 | n_gen = 178, tg = 23.64 t/s, tg_3s = 25.98 t/s 2.57.732.610 I slot print_timing: id 0 | task 1976 | prompt eval time = 662.99 ms / 442 tokens ( 1.50 ms per token, 666.68 tokens per second) 2.57.732.613 I slot print_timing: id 0 | task 1976 | eval time = 25137.37 ms / 585 tokens ( 43.04 ms per token, 23.23 tokens per second) 2.57.732.614 I slot print_timing: id 0 | task 1976 | total time = 25800.36 ms / 1027 tokens 2.57.732.615 I slot print_timing: id 0 | task 1976 | graphs reused = 2204 2.57.732.616 I slot print_timing: id 0 | task 1976 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.732.720 I slot release: id 0 | task 1976 | stop processing: n_tokens = 1721, truncated = 0 2.57.767.725 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.621 2.57.767.756 I slot launch_slot_: id 0 | task 2568 | processing task, is_child = 0 2.59.365.281 I slot print_timing: id 2 | task 2146 | n_gen = 443, tg = 23.38 t/s, tg_3s = 20.91 t/s 2.59.710.558 I slot print_timing: id 1 | task 2438 | n_gen = 163, tg = 23.74 t/s, tg_3s = 20.92 t/s 3.00.403.635 I slot print_timing: id 3 | task 2377 | n_gen = 241, tg = 22.85 t/s, tg_3s = 20.90 t/s 3.02.250.937 I slot print_timing: id 0 | task 2568 | n_gen = 100, tg = 25.94 t/s, tg_3s = 26.20 t/s 3.02.368.472 I slot print_timing: id 2 | task 2146 | n_gen = 521, tg = 23.74 t/s, tg_3s = 25.97 t/s 3.02.714.147 I slot print_timing: id 1 | task 2438 | n_gen = 241, tg = 24.42 t/s, tg_3s = 25.97 t/s 3.03.409.208 I slot print_timing: id 3 | task 2377 | n_gen = 319, tg = 23.54 t/s, tg_3s = 25.95 t/s 3.03.986.418 I slot print_timing: id 3 | task 2377 | prompt eval time = 698.50 ms / 463 tokens ( 1.51 ms per token, 662.84 tokens per second) 3.03.986.424 I slot print_timing: id 3 | task 2377 | eval time = 14085.15 ms / 334 tokens ( 42.30 ms per token, 23.64 tokens per second) 3.03.986.425 I slot print_timing: id 3 | task 2377 | total time = 14783.65 ms / 797 tokens 3.03.986.426 I slot print_timing: id 3 | task 2377 | graphs reused = 2348 3.03.986.426 I slot print_timing: id 3 | task 2377 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.986.529 I slot release: id 3 | task 2377 | stop processing: n_tokens = 1461, truncated = 0 3.04.020.208 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.731 3.04.020.240 I slot launch_slot_: id 3 | task 2716 | processing task, is_child = 0 3.05.261.079 I slot print_timing: id 0 | task 2568 | n_gen = 162, tg = 23.58 t/s, tg_3s = 20.60 t/s 3.05.378.399 I slot print_timing: id 2 | task 2146 | n_gen = 583, tg = 23.36 t/s, tg_3s = 20.60 t/s 3.05.725.312 I slot print_timing: id 1 | task 2438 | n_gen = 303, tg = 23.53 t/s, tg_3s = 20.59 t/s 3.08.269.932 I slot print_timing: id 0 | task 2568 | n_gen = 240, tg = 24.30 t/s, tg_3s = 25.92 t/s 3.08.386.429 I slot print_timing: id 2 | task 2146 | n_gen = 661, tg = 23.63 t/s, tg_3s = 25.93 t/s 3.08.541.487 I slot print_timing: id 3 | task 2716 | n_gen = 100, tg = 25.89 t/s, tg_3s = 26.15 t/s 3.08.733.194 I slot print_timing: id 1 | task 2438 | n_gen = 381, tg = 23.98 t/s, tg_3s = 25.93 t/s 3.11.278.205 I slot print_timing: id 0 | task 2568 | n_gen = 318, tg = 24.68 t/s, tg_3s = 25.93 t/s 3.11.395.508 I slot print_timing: id 2 | task 2146 | n_gen = 739, tg = 23.86 t/s, tg_3s = 25.92 t/s 3.11.550.132 I slot print_timing: id 3 | task 2716 | n_gen = 178, tg = 25.91 t/s, tg_3s = 25.93 t/s 3.11.741.405 I slot print_timing: id 1 | task 2438 | n_gen = 459, tg = 24.29 t/s, tg_3s = 25.93 t/s 3.12.049.942 I slot print_timing: id 1 | task 2438 | prompt eval time = 753.00 ms / 506 tokens ( 1.49 ms per token, 671.98 tokens per second) 3.12.049.949 I slot print_timing: id 1 | task 2438 | eval time = 19161.94 ms / 467 tokens ( 41.12 ms per token, 24.32 tokens per second) 3.12.049.949 I slot print_timing: id 1 | task 2438 | total time = 19914.94 ms / 973 tokens 3.12.049.950 I slot print_timing: id 1 | task 2438 | graphs reused = 2536 3.12.049.951 I slot print_timing: id 1 | task 2438 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.050.056 I slot release: id 1 | task 2438 | stop processing: n_tokens = 1636, truncated = 0 3.12.090.808 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.653 3.12.090.845 I slot launch_slot_: id 1 | task 2910 | processing task, is_child = 0 3.14.283.500 I slot print_timing: id 0 | task 2568 | n_gen = 379, tg = 23.85 t/s, tg_3s = 20.30 t/s 3.14.400.593 I slot print_timing: id 2 | task 2146 | n_gen = 800, tg = 23.54 t/s, tg_3s = 20.30 t/s 3.14.556.255 I slot print_timing: id 3 | task 2716 | n_gen = 239, tg = 24.19 t/s, tg_3s = 20.29 t/s 3.15.249.204 I slot print_timing: id 0 | task 2568 | prompt eval time = 666.14 ms / 447 tokens ( 1.49 ms per token, 671.03 tokens per second) 3.15.249.208 I slot print_timing: id 0 | task 2568 | eval time = 16815.29 ms / 404 tokens ( 41.73 ms per token, 23.97 tokens per second) 3.15.249.209 I slot print_timing: id 0 | task 2568 | total time = 17481.44 ms / 851 tokens 3.15.249.210 I slot print_timing: id 0 | task 2568 | graphs reused = 2598 3.15.249.210 I slot print_timing: id 0 | task 2568 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.249.307 I slot release: id 0 | task 2568 | stop processing: n_tokens = 1545, truncated = 0 3.15.284.414 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.691 3.15.284.448 I slot launch_slot_: id 0 | task 2977 | processing task, is_child = 0 3.17.220.838 I slot print_timing: id 1 | task 2910 | n_gen = 100, tg = 22.47 t/s, tg_3s = 22.70 t/s 3.17.417.756 I slot print_timing: id 2 | task 2146 | n_gen = 863, tg = 23.32 t/s, tg_3s = 20.88 t/s 3.17.573.029 I slot print_timing: id 3 | task 2716 | n_gen = 302, tg = 23.41 t/s, tg_3s = 20.88 t/s 3.19.775.420 I slot print_timing: id 0 | task 2977 | n_gen = 100, tg = 25.86 t/s, tg_3s = 26.12 t/s 3.20.237.910 I slot print_timing: id 1 | task 2910 | n_gen = 178, tg = 23.84 t/s, tg_3s = 25.85 t/s 3.20.429.997 I slot print_timing: id 2 | task 2146 | n_gen = 941, tg = 23.52 t/s, tg_3s = 25.89 t/s 3.20.545.647 I slot print_timing: id 2 | task 2146 | prompt eval time = 834.11 ms / 521 tokens ( 1.60 ms per token, 624.62 tokens per second) 3.20.545.654 I slot print_timing: id 2 | task 2146 | eval time = 40084.24 ms / 944 tokens ( 42.51 ms per token, 23.53 tokens per second) 3.20.545.655 I slot print_timing: id 2 | task 2146 | total time = 40918.35 ms / 1465 tokens 3.20.545.656 I slot print_timing: id 2 | task 2146 | graphs reused = 2716 3.20.545.657 I slot print_timing: id 2 | task 2146 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.545.770 I slot release: id 2 | task 2146 | stop processing: n_tokens = 2134, truncated = 0 3.20.586.130 I slot print_timing: id 3 | task 2716 | n_gen = 380, tg = 23.88 t/s, tg_3s = 25.89 t/s 3.20.586.137 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.500 3.20.586.170 I slot launch_slot_: id 2 | task 3100 | processing task, is_child = 0 3.22.805.818 I slot print_timing: id 0 | task 2977 | n_gen = 161, tg = 23.33 t/s, tg_3s = 20.13 t/s 3.23.269.011 I slot print_timing: id 1 | task 2910 | n_gen = 239, tg = 22.77 t/s, tg_3s = 20.12 t/s 3.23.617.424 I slot print_timing: id 3 | task 2716 | n_gen = 441, tg = 23.28 t/s, tg_3s = 20.12 t/s 3.25.157.763 I slot print_timing: id 2 | task 3100 | n_gen = 100, tg = 25.90 t/s, tg_3s = 26.16 t/s 3.25.807.626 I slot print_timing: id 0 | task 2977 | n_gen = 239, tg = 24.14 t/s, tg_3s = 25.98 t/s 3.26.269.599 I slot print_timing: id 1 | task 2910 | n_gen = 317, tg = 23.49 t/s, tg_3s = 25.99 t/s 3.26.618.006 I slot print_timing: id 3 | task 2716 | n_gen = 519, tg = 23.65 t/s, tg_3s = 25.99 t/s 3.28.163.529 I slot print_timing: id 2 | task 3100 | n_gen = 178, tg = 25.92 t/s, tg_3s = 25.95 t/s 3.28.820.970 I slot print_timing: id 0 | task 2977 | n_gen = 317, tg = 24.55 t/s, tg_3s = 25.88 t/s 3.29.284.176 I slot print_timing: id 1 | task 2910 | n_gen = 395, tg = 23.92 t/s, tg_3s = 25.87 t/s 3.29.630.461 I slot print_timing: id 3 | task 2716 | n_gen = 597, tg = 23.92 t/s, tg_3s = 25.89 t/s 3.30.242.628 I slot print_timing: id 1 | task 2910 | prompt eval time = 724.01 ms / 481 tokens ( 1.51 ms per token, 664.35 tokens per second) 3.30.242.635 I slot print_timing: id 1 | task 2910 | eval time = 17427.76 ms / 420 tokens ( 41.59 ms per token, 24.04 tokens per second) 3.30.242.637 I slot print_timing: id 1 | task 2910 | total time = 18151.77 ms / 901 tokens 3.30.242.637 I slot print_timing: id 1 | task 2910 | graphs reused = 2945 3.30.242.638 I slot print_timing: id 1 | task 2910 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.242.732 I slot release: id 1 | task 2910 | stop processing: n_tokens = 1564, truncated = 0 3.30.283.153 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.683 3.30.283.191 I slot launch_slot_: id 1 | task 3335 | processing task, is_child = 0 3.31.190.954 I slot print_timing: id 2 | task 3100 | n_gen = 240, tg = 24.25 t/s, tg_3s = 20.48 t/s 3.31.853.704 I slot print_timing: id 0 | task 2977 | n_gen = 379, tg = 23.76 t/s, tg_3s = 20.44 t/s 3.32.662.119 I slot print_timing: id 3 | task 2716 | n_gen = 659, tg = 23.55 t/s, tg_3s = 20.45 t/s 3.33.853.596 I slot print_timing: id 3 | task 2716 | prompt eval time = 697.47 ms / 463 tokens ( 1.51 ms per token, 663.83 tokens per second) 3.33.853.600 I slot print_timing: id 3 | task 2716 | eval time = 29135.88 ms / 690 tokens ( 42.29 ms per token, 23.65 tokens per second) 3.33.853.601 I slot print_timing: id 3 | task 2716 | total time = 29833.35 ms / 1153 tokens 3.33.853.602 I slot print_timing: id 3 | task 2716 | graphs reused = 3017 3.33.853.603 I slot print_timing: id 3 | task 2716 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.853.705 I slot release: id 3 | task 2716 | stop processing: n_tokens = 1817, truncated = 0 3.33.887.052 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.588 3.33.887.089 I slot launch_slot_: id 3 | task 3413 | processing task, is_child = 0 3.34.523.393 I slot print_timing: id 2 | task 3100 | n_gen = 311, tg = 23.51 t/s, tg_3s = 21.31 t/s 3.34.854.364 I slot print_timing: id 0 | task 2977 | n_gen = 441, tg = 23.27 t/s, tg_3s = 20.66 t/s 3.35.439.477 I slot print_timing: id 1 | task 3335 | n_gen = 100, tg = 22.30 t/s, tg_3s = 22.52 t/s 3.37.558.855 I slot print_timing: id 2 | task 3100 | n_gen = 389, tg = 23.92 t/s, tg_3s = 25.70 t/s 3.37.865.221 I slot print_timing: id 0 | task 2977 | n_gen = 519, tg = 23.63 t/s, tg_3s = 25.91 t/s 3.38.403.947 I slot print_timing: id 3 | task 3413 | n_gen = 100, tg = 25.96 t/s, tg_3s = 26.22 t/s 3.38.441.170 I slot print_timing: id 1 | task 3335 | n_gen = 178, tg = 23.78 t/s, tg_3s = 25.99 t/s 3.40.559.125 I slot print_timing: id 2 | task 3100 | n_gen = 467, tg = 24.24 t/s, tg_3s = 26.00 t/s 3.40.867.112 I slot print_timing: id 0 | task 2977 | n_gen = 597, tg = 23.92 t/s, tg_3s = 25.98 t/s 3.41.409.095 I slot print_timing: id 3 | task 3413 | n_gen = 178, tg = 25.96 t/s, tg_3s = 25.96 t/s 3.41.446.598 I slot print_timing: id 1 | task 3335 | n_gen = 256, tg = 24.41 t/s, tg_3s = 25.95 t/s 3.43.572.176 I slot print_timing: id 2 | task 3100 | n_gen = 545, tg = 24.46 t/s, tg_3s = 25.89 t/s 3.43.879.262 I slot print_timing: id 0 | task 2977 | n_gen = 675, tg = 24.13 t/s, tg_3s = 25.90 t/s 3.44.422.295 I slot print_timing: id 3 | task 3413 | n_gen = 256, tg = 25.94 t/s, tg_3s = 25.89 t/s 3.44.460.029 I slot print_timing: id 1 | task 3335 | n_gen = 334, tg = 24.74 t/s, tg_3s = 25.88 t/s 3.45.616.746 I slot print_timing: id 0 | task 2977 | prompt eval time = 663.01 ms / 443 tokens ( 1.50 ms per token, 668.16 tokens per second) 3.45.616.752 I slot print_timing: id 0 | task 2977 | eval time = 29669.27 ms / 720 tokens ( 41.26 ms per token, 24.23 tokens per second) 3.45.616.753 I slot print_timing: id 0 | task 2977 | total time = 30332.29 ms / 1163 tokens 3.45.616.754 I slot print_timing: id 0 | task 2977 | graphs reused = 3301 3.45.616.755 I slot print_timing: id 0 | task 2977 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.616.850 I slot release: id 0 | task 2977 | stop processing: n_tokens = 1857, truncated = 0 3.45.652.051 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.575 3.45.652.084 I slot launch_slot_: id 0 | task 3703 | processing task, is_child = 0 3.46.610.890 I slot print_timing: id 2 | task 3100 | n_gen = 609, tg = 24.05 t/s, tg_3s = 21.06 t/s 3.47.340.465 I slot print_timing: id 1 | task 3335 | prompt eval time = 716.24 ms / 469 tokens ( 1.53 ms per token, 654.81 tokens per second) 3.47.340.469 I slot print_timing: id 1 | task 3335 | eval time = 16341.02 ms / 394 tokens ( 41.58 ms per token, 24.05 tokens per second) 3.47.340.470 I slot print_timing: id 1 | task 3335 | total time = 17057.26 ms / 863 tokens 3.47.340.471 I slot print_timing: id 1 | task 3335 | graphs reused = 3327 3.47.340.471 I slot print_timing: id 1 | task 3335 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.340.572 I slot release: id 1 | task 3335 | stop processing: n_tokens = 1526, truncated = 0 3.47.380.650 I slot print_timing: id 2 | task 3100 | prompt eval time = 749.01 ms / 505 tokens ( 1.48 ms per token, 674.22 tokens per second) 3.47.380.656 I slot print_timing: id 2 | task 3100 | eval time = 26045.46 ms / 629 tokens ( 41.47 ms per token, 24.11 tokens per second) 3.47.380.657 I slot print_timing: id 2 | task 3100 | total time = 26794.47 ms / 1134 tokens 3.47.380.658 I slot print_timing: id 2 | task 3100 | graphs reused = 3327 3.47.380.659 I slot print_timing: id 2 | task 3100 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.380.761 I slot release: id 2 | task 3100 | stop processing: n_tokens = 1808, truncated = 0 3.47.381.301 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.701 3.47.381.337 I slot launch_slot_: id 1 | task 3734 | processing task, is_child = 0 3.48.057.950 I slot print_timing: id 3 | task 3413 | n_gen = 319, tg = 23.61 t/s, tg_3s = 17.33 t/s 3.48.057.956 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.591 3.48.057.979 I slot launch_slot_: id 2 | task 3736 | processing task, is_child = 0 3.51.075.417 I slot print_timing: id 3 | task 3413 | n_gen = 379, tg = 22.93 t/s, tg_3s = 19.88 t/s 3.51.459.217 I slot print_timing: id 0 | task 3703 | n_gen = 100, tg = 19.22 t/s, tg_3s = 19.41 t/s 3.52.616.274 I slot print_timing: id 1 | task 3734 | n_gen = 100, tg = 25.77 t/s, tg_3s = 26.03 t/s 3.52.655.051 I slot print_timing: id 2 | task 3736 | n_gen = 100, tg = 26.00 t/s, tg_3s = 26.26 t/s 3.54.081.421 I slot print_timing: id 3 | task 3413 | n_gen = 457, tg = 23.40 t/s, tg_3s = 25.95 t/s 3.54.465.880 I slot print_timing: id 0 | task 3703 | n_gen = 178, tg = 21.69 t/s, tg_3s = 25.94 t/s 3.55.621.179 I slot print_timing: id 1 | task 3734 | n_gen = 178, tg = 25.85 t/s, tg_3s = 25.96 t/s 3.55.660.190 I slot print_timing: id 2 | task 3736 | n_gen = 178, tg = 25.98 t/s, tg_3s = 25.96 t/s 3.57.087.840 I slot print_timing: id 3 | task 3413 | n_gen = 535, tg = 23.74 t/s, tg_3s = 25.94 t/s 3.57.471.407 I slot print_timing: id 0 | task 3703 | n_gen = 256, tg = 22.84 t/s, tg_3s = 25.95 t/s 3.58.623.158 I slot print_timing: id 1 | task 3734 | n_gen = 256, tg = 25.89 t/s, tg_3s = 25.98 t/s 3.58.661.913 I slot print_timing: id 2 | task 3736 | n_gen = 256, tg = 25.98 t/s, tg_3s = 25.99 t/s 4.00.081.785 I slot print_timing: id 0 | task 3703 | prompt eval time = 655.12 ms / 435 tokens ( 1.51 ms per token, 664.00 tokens per second) 4.00.081.789 I slot print_timing: id 0 | task 3703 | eval time = 13774.57 ms / 324 tokens ( 42.65 ms per token, 23.45 tokens per second) 4.00.081.790 I slot print_timing: id 0 | task 3703 | total time = 14429.69 ms / 759 tokens 4.00.081.790 I slot print_timing: id 0 | task 3703 | graphs reused = 3617 4.00.081.791 I slot print_timing: id 0 | task 3703 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.081.889 I slot release: id 0 | task 3703 | stop processing: n_tokens = 1453, truncated = 0 4.00.116.751 I slot print_timing: id 3 | task 3413 | n_gen = 614, tg = 24.01 t/s, tg_3s = 26.08 t/s 4.00.116.757 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.735 4.00.116.785 I slot launch_slot_: id 0 | task 4032 | processing task, is_child = 0 4.01.653.305 I slot print_timing: id 1 | task 3734 | n_gen = 318, tg = 24.61 t/s, tg_3s = 20.46 t/s 4.01.692.032 I slot print_timing: id 2 | task 3736 | n_gen = 318, tg = 24.68 t/s, tg_3s = 20.46 t/s 4.02.155.916 I slot print_timing: id 3 | task 3413 | prompt eval time = 703.10 ms / 472 tokens ( 1.49 ms per token, 671.31 tokens per second) 4.02.155.932 I slot print_timing: id 3 | task 3413 | eval time = 27565.71 ms / 650 tokens ( 42.47 ms per token, 23.54 tokens per second) 4.02.155.934 I slot print_timing: id 3 | task 3413 | total time = 28268.82 ms / 1122 tokens 4.02.155.935 I slot print_timing: id 3 | task 3413 | graphs reused = 3651 4.02.155.936 I slot print_timing: id 3 | task 3413 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.156.036 I slot release: id 3 | task 3413 | stop processing: n_tokens = 1786, truncated = 0 4.02.189.537 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.598 4.02.189.574 I slot launch_slot_: id 3 | task 4070 | processing task, is_child = 0 4.04.659.737 I slot print_timing: id 1 | task 3734 | n_gen = 380, tg = 23.86 t/s, tg_3s = 20.62 t/s 4.04.698.917 I slot print_timing: id 2 | task 3736 | n_gen = 380, tg = 23.91 t/s, tg_3s = 20.62 t/s 4.05.276.163 I slot print_timing: id 0 | task 4032 | n_gen = 100, tg = 22.31 t/s, tg_3s = 22.53 t/s 4.06.699.655 I slot print_timing: id 3 | task 4070 | n_gen = 100, tg = 26.02 t/s, tg_3s = 26.28 t/s 4.07.661.846 I slot print_timing: id 1 | task 3734 | n_gen = 458, tg = 24.20 t/s, tg_3s = 25.98 t/s 4.07.701.274 I slot print_timing: id 2 | task 3736 | n_gen = 458, tg = 24.24 t/s, tg_3s = 25.98 t/s 4.08.314.295 I slot print_timing: id 0 | task 4032 | n_gen = 179, tg = 23.81 t/s, tg_3s = 26.00 t/s 4.09.707.368 I slot print_timing: id 3 | task 4070 | n_gen = 178, tg = 25.98 t/s, tg_3s = 25.93 t/s 4.10.669.287 I slot print_timing: id 1 | task 3734 | n_gen = 536, tg = 24.44 t/s, tg_3s = 25.94 t/s 4.10.708.665 I slot print_timing: id 2 | task 3736 | n_gen = 536, tg = 24.47 t/s, tg_3s = 25.94 t/s 4.11.326.161 I slot print_timing: id 0 | task 4032 | n_gen = 257, tg = 24.41 t/s, tg_3s = 25.90 t/s 4.12.723.666 I slot print_timing: id 3 | task 4070 | n_gen = 256, tg = 25.94 t/s, tg_3s = 25.86 t/s 4.13.688.571 I slot print_timing: id 1 | task 3734 | n_gen = 614, tg = 24.60 t/s, tg_3s = 25.83 t/s 4.13.727.666 I slot print_timing: id 2 | task 3736 | n_gen = 614, tg = 24.64 t/s, tg_3s = 25.84 t/s 4.14.347.204 I slot print_timing: id 0 | task 4032 | n_gen = 335, tg = 24.72 t/s, tg_3s = 25.82 t/s 4.15.741.828 I slot print_timing: id 3 | task 4070 | n_gen = 334, tg = 25.92 t/s, tg_3s = 25.84 t/s 4.16.707.557 I slot print_timing: id 1 | task 3734 | n_gen = 692, tg = 24.74 t/s, tg_3s = 25.84 t/s 4.16.746.848 I slot print_timing: id 2 | task 3736 | n_gen = 692, tg = 24.77 t/s, tg_3s = 25.83 t/s 4.17.363.509 I slot print_timing: id 0 | task 4032 | n_gen = 413, tg = 24.93 t/s, tg_3s = 25.86 t/s 4.18.757.803 I slot print_timing: id 3 | task 4070 | n_gen = 412, tg = 25.91 t/s, tg_3s = 25.86 t/s 4.19.723.730 I slot print_timing: id 1 | task 3734 | n_gen = 770, tg = 24.85 t/s, tg_3s = 25.86 t/s 4.19.762.812 I slot print_timing: id 2 | task 3736 | n_gen = 770, tg = 24.87 t/s, tg_3s = 25.86 t/s 4.20.381.777 I slot print_timing: id 0 | task 4032 | n_gen = 491, tg = 25.07 t/s, tg_3s = 25.84 t/s 4.21.735.540 I slot print_timing: id 3 | task 4070 | prompt eval time = 705.38 ms / 472 tokens ( 1.49 ms per token, 669.15 tokens per second) 4.21.735.547 I slot print_timing: id 3 | task 4070 | eval time = 18840.58 ms / 489 tokens ( 38.61 ms per token, 25.90 tokens per second) 4.21.735.548 I slot print_timing: id 3 | task 4070 | total time = 19545.96 ms / 961 tokens 4.21.735.548 I slot print_timing: id 3 | task 4070 | graphs reused = 4136 4.21.735.549 I slot print_timing: id 3 | task 4070 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.735.644 I slot release: id 3 | task 4070 | stop processing: n_tokens = 1625, truncated = 0 4.21.769.693 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.657 4.21.769.726 I slot launch_slot_: id 3 | task 4562 | processing task, is_child = 0 4.22.735.564 I slot print_timing: id 1 | task 3734 | n_gen = 832, tg = 24.47 t/s, tg_3s = 20.59 t/s 4.22.781.880 I slot print_timing: id 2 | task 3736 | n_gen = 832, tg = 24.49 t/s, tg_3s = 20.54 t/s 4.23.401.126 I slot print_timing: id 0 | task 4032 | n_gen = 553, tg = 24.47 t/s, tg_3s = 20.53 t/s 4.25.753.718 I slot print_timing: id 1 | task 3734 | n_gen = 910, tg = 24.58 t/s, tg_3s = 25.84 t/s 4.25.792.630 I slot print_timing: id 2 | task 3736 | n_gen = 910, tg = 24.60 t/s, tg_3s = 25.91 t/s 4.26.297.636 I slot print_timing: id 3 | task 4562 | n_gen = 100, tg = 25.86 t/s, tg_3s = 26.12 t/s 4.26.412.266 I slot print_timing: id 0 | task 4032 | n_gen = 631, tg = 24.63 t/s, tg_3s = 25.90 t/s 4.28.778.425 I slot print_timing: id 1 | task 3734 | n_gen = 988, tg = 24.67 t/s, tg_3s = 25.79 t/s 4.28.817.778 I slot print_timing: id 2 | task 3736 | n_gen = 988, tg = 24.69 t/s, tg_3s = 25.78 t/s 4.29.322.770 I slot print_timing: id 3 | task 4562 | n_gen = 178, tg = 25.82 t/s, tg_3s = 25.78 t/s 4.29.437.323 I slot print_timing: id 0 | task 4032 | n_gen = 709, tg = 24.76 t/s, tg_3s = 25.78 t/s 4.30.175.964 I slot print_timing: id 1 | task 3734 | prompt eval time = 1388.21 ms / 509 tokens ( 2.73 ms per token, 366.66 tokens per second) 4.30.175.977 I slot print_timing: id 1 | task 3734 | eval time = 41401.44 ms / 1024 tokens ( 40.47 ms per token, 24.71 tokens per second) 4.30.175.979 I slot print_timing: id 1 | task 3734 | total time = 42789.65 ms / 1533 tokens 4.30.175.980 I slot print_timing: id 1 | task 3734 | graphs reused = 4333 4.30.175.981 I slot print_timing: id 1 | task 3734 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.176.105 I slot release: id 1 | task 3734 | stop processing: n_tokens = 2196, truncated = 0 4.30.216.760 I slot print_timing: id 2 | task 3736 | prompt eval time = 788.60 ms / 501 tokens ( 1.57 ms per token, 635.30 tokens per second) 4.30.216.764 I slot print_timing: id 2 | task 3736 | eval time = 41369.98 ms / 1024 tokens ( 40.44 ms per token, 24.73 tokens per second) 4.30.216.765 I slot print_timing: id 2 | task 3736 | total time = 42158.58 ms / 1525 tokens 4.30.216.766 I slot print_timing: id 2 | task 3736 | graphs reused = 4333 4.30.216.766 I slot print_timing: id 2 | task 3736 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.216.864 I slot release: id 2 | task 3736 | stop processing: n_tokens = 2199, truncated = 0 4.30.217.455 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 4.30.223.354 I slot launch_slot_: id 1 | task 4765 | processing task, is_child = 0 4.30.228.678 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.486 4.30.228.857 I slot launch_slot_: id 2 | task 4766 | processing task, is_child = 0 4.32.330.938 I slot print_timing: id 3 | task 4562 | n_gen = 222, tg = 22.41 t/s, tg_3s = 14.63 t/s 4.32.445.095 I slot print_timing: id 0 | task 4032 | n_gen = 753, tg = 23.79 t/s, tg_3s = 14.63 t/s 4.34.862.462 I slot print_timing: id 3 | task 4562 | prompt eval time = 699.19 ms / 466 tokens ( 1.50 ms per token, 666.49 tokens per second) 4.34.862.466 I slot print_timing: id 3 | task 4562 | eval time = 12393.54 ms / 288 tokens ( 43.18 ms per token, 23.16 tokens per second) 4.34.862.467 I slot print_timing: id 3 | task 4562 | total time = 13092.73 ms / 754 tokens 4.34.862.468 I slot print_timing: id 3 | task 4562 | graphs reused = 4417 4.34.862.469 I slot print_timing: id 3 | task 4562 | graph reallocs = 0 / 0 (same size) / (changed size) 4.34.862.568 I slot release: id 3 | task 4562 | stop processing: n_tokens = 1418, truncated = 0 4.34.896.070 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.754 4.34.896.104 I slot launch_slot_: id 3 | task 4855 | processing task, is_child = 0 4.35.555.959 I slot print_timing: id 0 | task 4032 | n_gen = 818, tg = 23.53 t/s, tg_3s = 20.89 t/s 4.36.047.145 I slot print_timing: id 1 | task 4765 | n_gen = 100, tg = 22.25 t/s, tg_3s = 22.48 t/s 4.36.047.884 I slot print_timing: id 2 | task 4766 | n_gen = 100, tg = 22.25 t/s, tg_3s = 22.48 t/s 4.38.559.746 I slot print_timing: id 0 | task 4032 | n_gen = 895, tg = 23.70 t/s, tg_3s = 25.63 t/s 4.39.061.364 I slot print_timing: id 1 | task 4765 | n_gen = 178, tg = 23.72 t/s, tg_3s = 25.88 t/s 4.39.061.952 I slot print_timing: id 2 | task 4766 | n_gen = 178, tg = 23.72 t/s, tg_3s = 25.88 t/s 4.39.445.487 I slot print_timing: id 3 | task 4855 | n_gen = 100, tg = 25.90 t/s, tg_3s = 26.16 t/s 4.40.835.381 I slot print_timing: id 0 | task 4032 | prompt eval time = 721.55 ms / 494 tokens ( 1.46 ms per token, 684.64 tokens per second) 4.40.835.389 I slot print_timing: id 0 | task 4032 | eval time = 39997.04 ms / 954 tokens ( 41.97 ms per token, 23.83 tokens per second) 4.40.835.390 I slot print_timing: id 0 | task 4032 | total time = 40718.59 ms / 1448 tokens 4.40.835.391 I slot print_timing: id 0 | task 4032 | graphs reused = 4550 4.40.835.391 I slot print_timing: id 0 | task 4032 | graph reallocs = 0 / 0 (same size) / (changed size) 4.40.835.509 I slot release: id 0 | task 4032 | stop processing: n_tokens = 2142, truncated = 0 4.40.870.937 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.499 4.40.876.645 I slot launch_slot_: id 0 | task 4994 | processing task, is_child = 0 4.42.067.875 I slot print_timing: id 1 | task 4765 | n_gen = 240, tg = 22.83 t/s, tg_3s = 20.62 t/s 4.42.068.462 I slot print_timing: id 2 | task 4766 | n_gen = 240, tg = 22.83 t/s, tg_3s = 20.62 t/s 4.42.453.064 I slot print_timing: id 3 | task 4855 | n_gen = 162, tg = 23.57 t/s, tg_3s = 20.61 t/s 4.45.105.145 I slot print_timing: id 1 | task 4765 | n_gen = 319, tg = 23.54 t/s, tg_3s = 26.01 t/s 4.45.105.733 I slot print_timing: id 2 | task 4766 | n_gen = 319, tg = 23.54 t/s, tg_3s = 26.01 t/s 4.45.373.571 I slot print_timing: id 0 | task 4994 | n_gen = 100, tg = 26.03 t/s, tg_3s = 26.29 t/s 4.45.450.543 I slot print_timing: id 1 | task 4765 | prompt eval time = 1369.26 ms / 479 tokens ( 2.86 ms per token, 349.83 tokens per second) 4.45.450.552 I slot print_timing: id 1 | task 4765 | eval time = 13852.42 ms / 328 tokens ( 42.36 ms per token, 23.61 tokens per second) 4.45.450.552 I slot print_timing: id 1 | task 4765 | total time = 15221.68 ms / 807 tokens 4.45.450.553 I slot print_timing: id 1 | task 4765 | graphs reused = 4651 4.45.450.554 I slot print_timing: id 1 | task 4765 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.450.655 I slot release: id 1 | task 4765 | stop processing: n_tokens = 1470, truncated = 0 4.45.491.851 I slot print_timing: id 3 | task 4855 | n_gen = 241, tg = 24.32 t/s, tg_3s = 26.00 t/s 4.45.491.861 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.727 4.45.491.893 I slot launch_slot_: id 1 | task 5099 | processing task, is_child = 0 4.48.143.965 I slot print_timing: id 2 | task 4766 | n_gen = 381, tg = 22.97 t/s, tg_3s = 20.41 t/s 4.48.373.858 I slot print_timing: id 0 | task 4994 | n_gen = 161, tg = 23.52 t/s, tg_3s = 20.33 t/s 4.48.493.300 I slot print_timing: id 3 | task 4855 | n_gen = 302, tg = 23.39 t/s, tg_3s = 20.32 t/s 4.50.033.919 I slot print_timing: id 1 | task 5099 | n_gen = 100, tg = 25.90 t/s, tg_3s = 26.16 t/s 4.51.152.584 I slot print_timing: id 2 | task 4766 | n_gen = 459, tg = 23.42 t/s, tg_3s = 25.93 t/s 4.51.385.349 I slot print_timing: id 0 | task 4994 | n_gen = 239, tg = 24.25 t/s, tg_3s = 25.90 t/s 4.51.503.924 I slot print_timing: id 3 | task 4855 | n_gen = 380, tg = 23.87 t/s, tg_3s = 25.91 t/s 4.51.658.464 I slot print_timing: id 2 | task 4766 | prompt eval time = 1369.37 ms / 473 tokens ( 2.90 ms per token, 345.41 tokens per second) 4.51.658.472 I slot print_timing: id 2 | task 4766 | eval time = 20059.90 ms / 472 tokens ( 42.59 ms per token, 23.48 tokens per second) 4.51.658.473 I slot print_timing: id 2 | task 4766 | total time = 21429.28 ms / 945 tokens 4.51.658.474 I slot print_timing: id 2 | task 4766 | graphs reused = 4790 4.51.658.474 I slot print_timing: id 2 | task 4766 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.658.578 I slot release: id 2 | task 4766 | stop processing: n_tokens = 1619, truncated = 0 4.51.699.273 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.660 4.51.699.319 I slot launch_slot_: id 2 | task 5244 | processing task, is_child = 0 4.53.040.596 I slot print_timing: id 1 | task 5099 | n_gen = 161, tg = 23.43 t/s, tg_3s = 20.29 t/s 4.54.389.628 I slot print_timing: id 0 | task 4994 | n_gen = 300, tg = 23.32 t/s, tg_3s = 20.30 t/s 4.54.507.366 I slot print_timing: id 3 | task 4855 | n_gen = 441, tg = 23.30 t/s, tg_3s = 20.31 t/s 4.56.046.487 I slot print_timing: id 1 | task 5099 | n_gen = 239, tg = 24.20 t/s, tg_3s = 25.95 t/s 4.56.241.153 I slot print_timing: id 2 | task 5244 | n_gen = 100, tg = 25.91 t/s, tg_3s = 26.17 t/s 4.57.394.014 I slot print_timing: id 0 | task 4994 | n_gen = 378, tg = 23.83 t/s, tg_3s = 25.96 t/s 4.57.510.938 I slot print_timing: id 3 | task 4855 | n_gen = 519, tg = 23.67 t/s, tg_3s = 25.97 t/s 4.59.055.761 I slot print_timing: id 1 | task 5099 | n_gen = 317, tg = 24.60 t/s, tg_3s = 25.92 t/s 4.59.249.612 I slot print_timing: id 2 | task 5244 | n_gen = 178, tg = 25.92 t/s, tg_3s = 25.93 t/s 5.00.255.223 I slot print_timing: id 3 | task 4855 | prompt eval time = 727.34 ms / 488 tokens ( 1.49 ms per token, 670.94 tokens per second) 5.00.255.231 I slot print_timing: id 3 | task 4855 | eval time = 24631.76 ms / 590 tokens ( 41.82 ms per token, 23.91 tokens per second) 5.00.255.232 I slot print_timing: id 3 | task 4855 | total time = 25359.11 ms / 1078 tokens 5.00.255.232 I slot print_timing: id 3 | task 4855 | graphs reused = 4992 5.00.255.238 I slot print_timing: id 3 | task 4855 | graph reallocs = 0 / 0 (same size) / (changed size) 5.00.255.350 I slot release: id 3 | task 4855 | stop processing: n_tokens = 1742, truncated = 0 5.00.288.751 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.613 5.00.288.782 I slot launch_slot_: id 3 | task 5451 | processing task, is_child = 0 5.01.055.706 I slot print_timing: id 0 | task 4994 | n_gen = 455, tg = 23.30 t/s, tg_3s = 21.03 t/s 5.02.088.992 I slot print_timing: id 1 | task 5099 | n_gen = 377, tg = 23.68 t/s, tg_3s = 19.78 t/s 5.02.282.276 I slot print_timing: id 2 | task 5244 | n_gen = 238, tg = 24.03 t/s, tg_3s = 19.78 t/s 5.04.093.324 I slot print_timing: id 0 | task 4994 | n_gen = 533, tg = 23.62 t/s, tg_3s = 25.68 t/s 5.04.942.361 I slot print_timing: id 3 | task 5451 | n_gen = 100, tg = 25.92 t/s, tg_3s = 26.18 t/s 5.05.095.991 I slot print_timing: id 1 | task 5099 | n_gen = 455, tg = 24.04 t/s, tg_3s = 25.94 t/s 5.05.289.481 I slot print_timing: id 2 | task 5244 | n_gen = 316, tg = 24.48 t/s, tg_3s = 25.94 t/s 5.07.104.678 I slot print_timing: id 0 | task 4994 | n_gen = 611, tg = 23.89 t/s, tg_3s = 25.90 t/s 5.07.953.504 I slot print_timing: id 3 | task 5451 | n_gen = 178, tg = 25.91 t/s, tg_3s = 25.90 t/s 5.08.105.645 I slot print_timing: id 1 | task 5099 | n_gen = 533, tg = 24.30 t/s, tg_3s = 25.92 t/s 5.08.298.714 I slot print_timing: id 2 | task 5244 | n_gen = 394, tg = 24.75 t/s, tg_3s = 25.92 t/s 5.09.179.587 I slot print_timing: id 0 | task 4994 | prompt eval time = 693.80 ms / 471 tokens ( 1.47 ms per token, 678.87 tokens per second) 5.09.179.591 I slot print_timing: id 0 | task 4994 | eval time = 27609.13 ms / 665 tokens ( 41.58 ms per token, 24.05 tokens per second) 5.09.179.592 I slot print_timing: id 0 | task 4994 | total time = 28302.93 ms / 1136 tokens 5.09.179.593 I slot print_timing: id 0 | task 4994 | graphs reused = 5199 5.09.179.594 I slot print_timing: id 0 | task 4994 | graph reallocs = 0 / 0 (same size) / (changed size) 5.09.179.698 I slot release: id 0 | task 4994 | stop processing: n_tokens = 1830, truncated = 0 5.09.214.498 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.584 5.09.214.531 I slot launch_slot_: id 0 | task 5665 | processing task, is_child = 0 5.10.958.590 I slot print_timing: id 3 | task 5451 | n_gen = 240, tg = 24.30 t/s, tg_3s = 20.63 t/s 5.11.112.247 I slot print_timing: id 1 | task 5099 | n_gen = 595, tg = 23.85 t/s, tg_3s = 20.62 t/s 5.11.304.915 I slot print_timing: id 2 | task 5244 | n_gen = 456, tg = 24.09 t/s, tg_3s = 20.62 t/s 5.11.803.312 I slot print_timing: id 2 | task 5244 | prompt eval time = 721.39 ms / 480 tokens ( 1.50 ms per token, 665.38 tokens per second) 5.11.803.319 I slot print_timing: id 2 | task 5244 | eval time = 19382.60 ms / 469 tokens ( 41.42 ms per token, 24.15 tokens per second) 5.11.803.321 I slot print_timing: id 2 | task 5244 | total time = 20103.99 ms / 949 tokens 5.11.803.322 I slot print_timing: id 2 | task 5244 | graphs reused = 5248 5.11.803.322 I slot print_timing: id 2 | task 5244 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.803.418 I slot release: id 2 | task 5244 | stop processing: n_tokens = 1623, truncated = 0 5.11.843.646 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.658 5.11.843.688 I slot launch_slot_: id 2 | task 5718 | processing task, is_child = 0 5.13.993.680 I slot print_timing: id 3 | task 5451 | n_gen = 302, tg = 23.39 t/s, tg_3s = 20.43 t/s 5.14.149.190 I slot print_timing: id 1 | task 5099 | n_gen = 657, tg = 23.48 t/s, tg_3s = 20.42 t/s 5.14.380.276 I slot print_timing: id 0 | task 5665 | n_gen = 100, tg = 22.17 t/s, tg_3s = 22.39 t/s 5.16.385.186 I slot print_timing: id 2 | task 5718 | n_gen = 100, tg = 25.93 t/s, tg_3s = 26.20 t/s 5.17.001.212 I slot print_timing: id 3 | task 5451 | n_gen = 380, tg = 23.87 t/s, tg_3s = 25.93 t/s 5.17.154.367 I slot print_timing: id 1 | task 5099 | n_gen = 735, tg = 23.72 t/s, tg_3s = 25.96 t/s 5.17.384.626 I slot print_timing: id 0 | task 5665 | n_gen = 178, tg = 23.69 t/s, tg_3s = 25.96 t/s 5.19.386.813 I slot print_timing: id 2 | task 5718 | n_gen = 178, tg = 25.96 t/s, tg_3s = 25.99 t/s 5.20.007.373 I slot print_timing: id 3 | task 5451 | n_gen = 458, tg = 24.20 t/s, tg_3s = 25.95 t/s 5.20.158.998 I slot print_timing: id 1 | task 5099 | n_gen = 813, tg = 23.92 t/s, tg_3s = 25.96 t/s 5.20.388.482 I slot print_timing: id 0 | task 5665 | n_gen = 256, tg = 24.34 t/s, tg_3s = 25.97 t/s 5.22.386.885 I slot print_timing: id 2 | task 5718 | n_gen = 256, tg = 25.97 t/s, tg_3s = 26.00 t/s 5.23.044.697 I slot print_timing: id 3 | task 5451 | n_gen = 537, tg = 24.45 t/s, tg_3s = 26.01 t/s 5.23.159.090 I slot print_timing: id 1 | task 5099 | n_gen = 891, tg = 24.09 t/s, tg_3s = 26.00 t/s 5.23.390.710 I slot print_timing: id 0 | task 5665 | n_gen = 334, tg = 24.71 t/s, tg_3s = 25.98 t/s 5.25.401.207 I slot print_timing: id 2 | task 5718 | n_gen = 334, tg = 25.95 t/s, tg_3s = 25.88 t/s 5.26.058.407 I slot print_timing: id 3 | task 5451 | n_gen = 615, tg = 24.62 t/s, tg_3s = 25.88 t/s 5.26.173.479 I slot print_timing: id 1 | task 5099 | n_gen = 969, tg = 24.22 t/s, tg_3s = 25.88 t/s 5.26.406.047 I slot print_timing: id 0 | task 5665 | n_gen = 412, tg = 24.92 t/s, tg_3s = 25.87 t/s 5.28.309.606 I slot print_timing: id 1 | task 5099 | prompt eval time = 719.74 ms / 473 tokens ( 1.52 ms per token, 657.18 tokens per second) 5.28.309.613 I slot print_timing: id 1 | task 5099 | eval time = 42097.97 ms / 1024 tokens ( 41.15 ms per token, 24.30 tokens per second) 5.28.309.615 I slot print_timing: id 1 | task 5099 | total time = 42817.71 ms / 1497 tokens 5.28.309.616 I slot print_timing: id 1 | task 5099 | graphs reused = 5653 5.28.309.617 I slot print_timing: id 1 | task 5099 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.309.719 I slot release: id 1 | task 5099 | stop processing: n_tokens = 2160, truncated = 0 5.28.350.651 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.494 5.28.356.501 I slot launch_slot_: id 1 | task 6130 | processing task, is_child = 0 5.29.035.827 I slot print_timing: id 2 | task 5718 | n_gen = 411, tg = 24.90 t/s, tg_3s = 21.19 t/s 5.29.109.720 I slot print_timing: id 3 | task 5451 | n_gen = 676, tg = 24.12 t/s, tg_3s = 19.99 t/s 5.29.413.750 I slot print_timing: id 0 | task 5665 | n_gen = 472, tg = 24.15 t/s, tg_3s = 19.95 t/s 5.32.042.316 I slot print_timing: id 2 | task 5718 | n_gen = 488, tg = 25.01 t/s, tg_3s = 25.61 t/s 5.32.120.192 I slot print_timing: id 3 | task 5451 | n_gen = 754, tg = 24.29 t/s, tg_3s = 25.91 t/s 5.32.427.655 I slot print_timing: id 0 | task 5665 | n_gen = 550, tg = 24.39 t/s, tg_3s = 25.88 t/s 5.32.930.820 I slot print_timing: id 1 | task 6130 | n_gen = 100, tg = 25.90 t/s, tg_3s = 26.17 t/s 5.35.057.356 I slot print_timing: id 2 | task 5718 | n_gen = 566, tg = 25.12 t/s, tg_3s = 25.87 t/s 5.35.134.753 I slot print_timing: id 3 | task 5451 | n_gen = 832, tg = 24.43 t/s, tg_3s = 25.87 t/s 5.35.442.271 I slot print_timing: id 0 | task 5665 | n_gen = 628, tg = 24.56 t/s, tg_3s = 25.87 t/s 5.35.944.713 I slot print_timing: id 1 | task 6130 | n_gen = 178, tg = 25.89 t/s, tg_3s = 25.88 t/s 5.37.413.867 I slot print_timing: id 2 | task 5718 | prompt eval time = 723.99 ms / 484 tokens ( 1.50 ms per token, 668.52 tokens per second) 5.37.413.875 I slot print_timing: id 2 | task 5718 | eval time = 24846.18 ms / 627 tokens ( 39.69 ms per token, 25.20 tokens per second) 5.37.413.876 I slot print_timing: id 2 | task 5718 | total time = 25570.17 ms / 1111 tokens 5.37.413.876 I slot print_timing: id 2 | task 5718 | graphs reused = 5866 5.37.413.877 I slot print_timing: id 2 | task 5718 | graph reallocs = 0 / 0 (same size) / (changed size) 5.37.414.004 I slot release: id 2 | task 5718 | stop processing: n_tokens = 1785, truncated = 0 5.37.454.473 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.598 5.37.454.510 I slot launch_slot_: id 2 | task 6349 | processing task, is_child = 0 5.38.205.774 I slot print_timing: id 3 | task 5451 | n_gen = 894, tg = 24.08 t/s, tg_3s = 20.19 t/s 5.38.476.122 I slot print_timing: id 0 | task 5665 | n_gen = 689, tg = 24.09 t/s, tg_3s = 20.11 t/s 5.38.634.445 I slot print_timing: id 3 | task 5451 | prompt eval time = 834.44 ms / 524 tokens ( 1.59 ms per token, 627.97 tokens per second) 5.38.634.450 I slot print_timing: id 3 | task 5451 | eval time = 37511.22 ms / 905 tokens ( 41.49 ms per token, 24.10 tokens per second) 5.38.634.450 I slot print_timing: id 3 | task 5451 | total time = 38345.66 ms / 1429 tokens 5.38.634.451 I slot print_timing: id 3 | task 5451 | graphs reused = 5876 5.38.634.452 I slot print_timing: id 3 | task 5451 | graph reallocs = 0 / 0 (same size) / (changed size) 5.38.634.553 I slot release: id 3 | task 5451 | stop processing: n_tokens = 2093, truncated = 0 5.38.668.228 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.510 5.38.668.256 I slot launch_slot_: id 3 | task 6364 | processing task, is_child = 0 5.39.301.065 I slot print_timing: id 1 | task 6130 | n_gen = 232, tg = 22.66 t/s, tg_3s = 16.09 t/s 5.41.494.461 I slot print_timing: id 0 | task 5665 | n_gen = 751, tg = 23.75 t/s, tg_3s = 20.54 t/s 5.42.304.731 I slot print_timing: id 1 | task 6130 | n_gen = 309, tg = 23.34 t/s, tg_3s = 25.64 t/s 5.42.651.643 I slot print_timing: id 2 | task 6349 | n_gen = 100, tg = 22.27 t/s, tg_3s = 22.49 t/s 5.43.192.045 I slot print_timing: id 3 | task 6364 | n_gen = 100, tg = 25.89 t/s, tg_3s = 26.15 t/s 5.44.498.919 I slot print_timing: id 0 | task 5665 | n_gen = 829, tg = 23.94 t/s, tg_3s = 25.96 t/s 5.44.769.475 I slot print_timing: id 0 | task 5665 | prompt eval time = 699.32 ms / 478 tokens ( 1.46 ms per token, 683.52 tokens per second) 5.44.769.483 I slot print_timing: id 0 | task 5665 | eval time = 34855.61 ms / 836 tokens ( 41.74 ms per token, 23.96 tokens per second) 5.44.769.484 I slot print_timing: id 0 | task 5665 | total time = 35554.93 ms / 1314 tokens 5.44.769.485 I slot print_timing: id 0 | task 5665 | graphs reused = 6015 5.44.769.486 I slot print_timing: id 0 | task 5665 | graph reallocs = 0 / 0 (same size) / (changed size) 5.44.769.586 I slot release: id 0 | task 5665 | stop processing: n_tokens = 2008, truncated = 0 5.44.804.423 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.532 5.44.804.453 I slot launch_slot_: id 0 | task 6508 | processing task, is_child = 0 5.45.418.006 I slot print_timing: id 1 | task 6130 | n_gen = 375, tg = 22.93 t/s, tg_3s = 21.20 t/s 5.45.671.191 I slot print_timing: id 2 | task 6349 | n_gen = 163, tg = 21.70 t/s, tg_3s = 20.86 t/s 5.46.205.622 I slot print_timing: id 3 | task 6364 | n_gen = 163, tg = 23.69 t/s, tg_3s = 20.91 t/s 5.48.430.352 I slot print_timing: id 1 | task 6130 | n_gen = 453, tg = 23.39 t/s, tg_3s = 25.89 t/s 5.48.700.557 I slot print_timing: id 2 | task 6349 | n_gen = 242, tg = 22.96 t/s, tg_3s = 26.08 t/s 5.49.240.315 I slot print_timing: id 3 | task 6364 | n_gen = 242, tg = 24.41 t/s, tg_3s = 26.03 t/s 5.49.277.444 I slot print_timing: id 0 | task 6508 | n_gen = 100, tg = 26.09 t/s, tg_3s = 26.35 t/s 5.51.433.247 I slot print_timing: id 1 | task 6130 | n_gen = 531, tg = 23.74 t/s, tg_3s = 25.97 t/s 5.51.703.000 I slot print_timing: id 2 | task 6349 | n_gen = 320, tg = 23.63 t/s, tg_3s = 25.98 t/s 5.52.242.715 I slot print_timing: id 3 | task 6364 | n_gen = 320, tg = 24.78 t/s, tg_3s = 25.98 t/s 5.52.279.583 I slot print_timing: id 0 | task 6508 | n_gen = 178, tg = 26.04 t/s, tg_3s = 25.98 t/s 5.54.468.899 I slot print_timing: id 1 | task 6130 | n_gen = 610, tg = 24.01 t/s, tg_3s = 26.02 t/s 5.54.739.853 I slot print_timing: id 2 | task 6349 | n_gen = 399, tg = 24.07 t/s, tg_3s = 26.01 t/s 5.55.242.971 I slot print_timing: id 3 | task 6364 | n_gen = 398, tg = 25.01 t/s, tg_3s = 26.00 t/s 5.55.279.672 I slot print_timing: id 0 | task 6508 | n_gen = 256, tg = 26.03 t/s, tg_3s = 26.00 t/s 5.57.482.628 I slot print_timing: id 1 | task 6130 | n_gen = 688, tg = 24.21 t/s, tg_3s = 25.88 t/s 5.57.754.560 I slot print_timing: id 2 | task 6349 | n_gen = 477, tg = 24.35 t/s, tg_3s = 25.87 t/s 5.58.260.293 I slot print_timing: id 3 | task 6364 | n_gen = 476, tg = 25.14 t/s, tg_3s = 25.85 t/s 5.58.296.992 I slot print_timing: id 0 | task 6508 | n_gen = 334, tg = 25.99 t/s, tg_3s = 25.85 t/s 5.59.576.233 I slot print_timing: id 3 | task 6364 | prompt eval time = 700.00 ms / 466 tokens ( 1.50 ms per token, 665.71 tokens per second) 5.59.576.240 I slot print_timing: id 3 | task 6364 | eval time = 20207.96 ms / 510 tokens ( 39.70 ms per token, 25.19 tokens per second) 5.59.576.241 I slot print_timing: id 3 | task 6364 | total time = 20907.96 ms / 976 tokens 5.59.576.242 I slot print_timing: id 3 | task 6364 | graphs reused = 6380 5.59.576.243 I slot print_timing: id 3 | task 6364 | graph reallocs = 0 / 0 (same size) / (changed size) 5.59.576.355 I slot release: id 3 | task 6364 | stop processing: n_tokens = 1648, truncated = 0 5.59.610.162 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.648 5.59.610.189 I slot launch_slot_: id 3 | task 6878 | processing task, is_child = 0 6.00.500.964 I slot print_timing: id 1 | task 6130 | n_gen = 750, tg = 23.86 t/s, tg_3s = 20.54 t/s 6.00.775.801 I slot print_timing: id 2 | task 6349 | n_gen = 539, tg = 23.84 t/s, tg_3s = 20.52 t/s 6.01.313.884 I slot print_timing: id 0 | task 6508 | n_gen = 396, tg = 24.95 t/s, tg_3s = 20.55 t/s 6.03.465.454 I slot print_timing: id 0 | task 6508 | prompt eval time = 678.25 ms / 453 tokens ( 1.50 ms per token, 667.90 tokens per second) 6.03.465.461 I slot print_timing: id 0 | task 6508 | eval time = 17982.75 ms / 452 tokens ( 39.87 ms per token, 25.08 tokens per second) 6.03.465.462 I slot print_timing: id 0 | task 6508 | total time = 18660.99 ms / 905 tokens 6.03.465.462 I slot print_timing: id 0 | task 6508 | graphs reused = 6461 6.03.465.463 I slot print_timing: id 0 | task 6508 | graph reallocs = 0 / 0 (same size) / (changed size) 6.03.465.566 I slot release: id 0 | task 6508 | stop processing: n_tokens = 1599, truncated = 0 6.03.500.713 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.668 6.03.500.759 I slot launch_slot_: id 0 | task 6964 | processing task, is_child = 0 6.04.102.947 I slot print_timing: id 1 | task 6130 | n_gen = 829, tg = 23.66 t/s, tg_3s = 21.93 t/s 6.04.103.249 I slot print_timing: id 2 | task 6349 | n_gen = 611, tg = 23.55 t/s, tg_3s = 21.64 t/s 6.04.706.115 I slot print_timing: id 3 | task 6878 | n_gen = 100, tg = 22.53 t/s, tg_3s = 22.75 t/s 6.07.125.395 I slot print_timing: id 1 | task 6130 | n_gen = 907, tg = 23.83 t/s, tg_3s = 25.81 t/s 6.07.125.924 I slot print_timing: id 2 | task 6349 | n_gen = 689, tg = 23.79 t/s, tg_3s = 25.80 t/s 6.07.240.946 I slot print_timing: id 2 | task 6349 | prompt eval time = 751.00 ms / 505 tokens ( 1.49 ms per token, 672.43 tokens per second) 6.07.240.950 I slot print_timing: id 2 | task 6349 | eval time = 29035.43 ms / 692 tokens ( 42.02 ms per token, 23.80 tokens per second) 6.07.240.951 I slot print_timing: id 2 | task 6349 | total time = 29786.43 ms / 1197 tokens 6.07.240.952 I slot print_timing: id 2 | task 6349 | graphs reused = 6540 6.07.240.952 I slot print_timing: id 2 | task 6349 | graph reallocs = 0 / 0 (same size) / (changed size) 6.07.241.065 I slot release: id 2 | task 6349 | stop processing: n_tokens = 1871, truncated = 0 6.07.281.433 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.571 6.07.281.472 I slot launch_slot_: id 2 | task 7048 | processing task, is_child = 0 6.07.928.005 I slot print_timing: id 3 | task 6878 | n_gen = 168, tg = 21.93 t/s, tg_3s = 21.11 t/s 6.08.621.532 I slot print_timing: id 0 | task 6964 | n_gen = 100, tg = 22.22 t/s, tg_3s = 22.45 t/s 6.10.133.000 I slot print_timing: id 1 | task 6130 | n_gen = 968, tg = 23.57 t/s, tg_3s = 20.28 t/s 6.10.947.253 I slot print_timing: id 3 | task 6878 | n_gen = 245, tg = 22.94 t/s, tg_3s = 25.50 t/s 6.11.640.097 I slot print_timing: id 0 | task 6964 | n_gen = 178, tg = 23.69 t/s, tg_3s = 25.84 t/s 6.11.834.613 I slot print_timing: id 2 | task 7048 | n_gen = 100, tg = 25.82 t/s, tg_3s = 26.08 t/s 6.12.299.963 I slot print_timing: id 1 | task 6130 | prompt eval time = 752.61 ms / 507 tokens ( 1.48 ms per token, 673.66 tokens per second) 6.12.299.970 I slot print_timing: id 1 | task 6130 | eval time = 43190.84 ms / 1024 tokens ( 42.22 ms per token, 23.69 tokens per second) 6.12.299.971 I slot print_timing: id 1 | task 6130 | total time = 43943.45 ms / 1531 tokens 6.12.299.972 I slot print_timing: id 1 | task 6130 | graphs reused = 6650 6.12.299.973 I slot print_timing: id 1 | task 6130 | graph reallocs = 0 / 0 (same size) / (changed size) 6.12.300.109 I slot release: id 1 | task 6130 | stop processing: n_tokens = 2194, truncated = 0 6.12.341.219 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.487 6.12.347.461 I slot launch_slot_: id 1 | task 7163 | processing task, is_child = 0 6.13.981.888 I slot print_timing: id 3 | task 6878 | n_gen = 306, tg = 22.31 t/s, tg_3s = 20.10 t/s 6.14.670.534 I slot print_timing: id 0 | task 6964 | n_gen = 239, tg = 22.66 t/s, tg_3s = 20.13 t/s 6.14.863.664 I slot print_timing: id 2 | task 7048 | n_gen = 161, tg = 23.31 t/s, tg_3s = 20.14 t/s 6.16.905.358 I slot print_timing: id 1 | task 7163 | n_gen = 100, tg = 25.99 t/s, tg_3s = 26.25 t/s 6.16.983.216 I slot print_timing: id 3 | task 6878 | n_gen = 384, tg = 22.97 t/s, tg_3s = 25.99 t/s 6.17.673.212 I slot print_timing: id 0 | task 6964 | n_gen = 317, tg = 23.40 t/s, tg_3s = 25.98 t/s 6.17.865.659 I slot print_timing: id 2 | task 7048 | n_gen = 239, tg = 24.12 t/s, tg_3s = 25.98 t/s 6.19.934.657 I slot print_timing: id 1 | task 7163 | n_gen = 179, tg = 26.03 t/s, tg_3s = 26.08 t/s 6.20.013.019 I slot print_timing: id 3 | task 6878 | n_gen = 463, tg = 23.45 t/s, tg_3s = 26.07 t/s 6.20.701.700 I slot print_timing: id 0 | task 6964 | n_gen = 396, tg = 23.89 t/s, tg_3s = 26.09 t/s 6.20.778.499 I slot print_timing: id 0 | task 6964 | prompt eval time = 666.32 ms / 448 tokens ( 1.49 ms per token, 672.35 tokens per second) 6.20.778.505 I slot print_timing: id 0 | task 6964 | eval time = 16611.41 ms / 398 tokens ( 41.84 ms per token, 23.90 tokens per second) 6.20.778.506 I slot print_timing: id 0 | task 6964 | total time = 17277.73 ms / 846 tokens 6.20.778.507 I slot print_timing: id 0 | task 6964 | graphs reused = 6848 6.20.778.508 I slot print_timing: id 0 | task 6964 | graph reallocs = 0 / 0 (same size) / (changed size) 6.20.778.604 I slot release: id 0 | task 6964 | stop processing: n_tokens = 1540, truncated = 0 6.20.813.664 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.694 6.20.813.696 I slot launch_slot_: id 0 | task 7367 | processing task, is_child = 0 6.21.441.615 I slot print_timing: id 2 | task 7048 | n_gen = 317, tg = 23.51 t/s, tg_3s = 21.81 t/s 6.22.940.424 I slot print_timing: id 1 | task 7163 | n_gen = 241, tg = 24.38 t/s, tg_3s = 20.63 t/s 6.23.018.558 I slot print_timing: id 3 | task 6878 | n_gen = 525, tg = 23.08 t/s, tg_3s = 20.63 t/s 6.24.442.506 I slot print_timing: id 2 | task 7048 | n_gen = 394, tg = 23.90 t/s, tg_3s = 25.66 t/s 6.25.328.087 I slot print_timing: id 0 | task 7367 | n_gen = 100, tg = 25.90 t/s, tg_3s = 26.16 t/s 6.25.946.696 I slot print_timing: id 1 | task 7163 | n_gen = 319, tg = 24.75 t/s, tg_3s = 25.95 t/s 6.26.025.712 I slot print_timing: id 3 | task 6878 | n_gen = 603, tg = 23.41 t/s, tg_3s = 25.94 t/s 6.27.457.842 I slot print_timing: id 2 | task 7048 | n_gen = 472, tg = 24.21 t/s, tg_3s = 25.87 t/s 6.28.348.021 I slot print_timing: id 0 | task 7367 | n_gen = 178, tg = 25.87 t/s, tg_3s = 25.83 t/s 6.28.964.697 I slot print_timing: id 1 | task 7163 | n_gen = 397, tg = 24.95 t/s, tg_3s = 25.84 t/s 6.29.042.968 I slot print_timing: id 3 | task 6878 | n_gen = 681, tg = 23.67 t/s, tg_3s = 25.85 t/s 6.30.465.291 I slot print_timing: id 2 | task 7048 | n_gen = 550, tg = 24.44 t/s, tg_3s = 25.94 t/s 6.31.385.695 I slot print_timing: id 0 | task 7367 | n_gen = 257, tg = 25.91 t/s, tg_3s = 26.01 t/s 6.32.001.792 I slot print_timing: id 1 | task 7163 | n_gen = 476, tg = 25.12 t/s, tg_3s = 26.01 t/s 6.32.079.194 I slot print_timing: id 3 | task 6878 | n_gen = 760, tg = 23.89 t/s, tg_3s = 26.02 t/s 6.32.385.159 I slot print_timing: id 2 | task 7048 | prompt eval time = 718.38 ms / 476 tokens ( 1.51 ms per token, 662.60 tokens per second) 6.32.385.171 I slot print_timing: id 2 | task 7048 | eval time = 24385.29 ms / 600 tokens ( 40.71 ms per token, 24.56 tokens per second) 6.32.385.172 I slot print_timing: id 2 | task 7048 | total time = 25103.68 ms / 1076 tokens 6.32.385.172 I slot print_timing: id 2 | task 7048 | graphs reused = 7129 6.32.385.173 I slot print_timing: id 2 | task 7048 | graph reallocs = 0 / 0 (same size) / (changed size) 6.32.385.278 I slot release: id 2 | task 7048 | stop processing: n_tokens = 1750, truncated = 0 6.32.425.676 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.610 6.32.425.717 I slot launch_slot_: id 2 | task 7653 | processing task, is_child = 0 6.33.414.692 I slot print_timing: id 3 | task 6878 | prompt eval time = 701.22 ms / 469 tokens ( 1.50 ms per token, 668.83 tokens per second) 6.33.414.698 I slot print_timing: id 3 | task 6878 | eval time = 33103.27 ms / 778 tokens ( 42.60 ms per token, 23.47 tokens per second) 6.33.414.699 I slot print_timing: id 3 | task 6878 | total time = 33804.49 ms / 1247 tokens 6.33.414.699 I slot print_timing: id 3 | task 6878 | graphs reused = 7135 6.33.414.700 I slot print_timing: id 3 | task 6878 | graph reallocs = 0 / 0 (same size) / (changed size) 6.33.414.825 I slot release: id 3 | task 6878 | stop processing: n_tokens = 1919, truncated = 0 6.33.448.971 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.557 6.33.449.005 I slot launch_slot_: id 3 | task 7664 | processing task, is_child = 0 6.34.406.683 I slot print_timing: id 0 | task 7367 | n_gen = 303, tg = 23.41 t/s, tg_3s = 15.23 t/s 6.35.030.281 I slot print_timing: id 1 | task 7163 | n_gen = 522, tg = 23.75 t/s, tg_3s = 15.19 t/s 6.35.068.939 I slot print_timing: id 1 | task 7163 | prompt eval time = 748.54 ms / 502 tokens ( 1.49 ms per token, 670.64 tokens per second) 6.35.068.946 I slot print_timing: id 1 | task 7163 | eval time = 21972.93 ms / 523 tokens ( 42.09 ms per token, 23.76 tokens per second) 6.35.068.947 I slot print_timing: id 1 | task 7163 | total time = 22721.47 ms / 1025 tokens 6.35.068.948 I slot print_timing: id 1 | task 7163 | graphs reused = 7158 6.35.068.948 I slot print_timing: id 1 | task 7163 | graph reallocs = 0 / 0 (same size) / (changed size) 6.35.069.065 I slot release: id 1 | task 7163 | stop processing: n_tokens = 1688, truncated = 0 6.35.109.486 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.633 6.35.109.521 I slot launch_slot_: id 1 | task 7692 | processing task, is_child = 0 6.37.430.285 I slot print_timing: id 0 | task 7367 | n_gen = 364, tg = 22.80 t/s, tg_3s = 20.17 t/s 6.38.242.595 I slot print_timing: id 2 | task 7653 | n_gen = 100, tg = 19.41 t/s, tg_3s = 19.61 t/s 6.38.626.611 I slot print_timing: id 3 | task 7664 | n_gen = 100, tg = 22.08 t/s, tg_3s = 22.31 t/s 6.39.664.500 I slot print_timing: id 1 | task 7692 | n_gen = 100, tg = 25.94 t/s, tg_3s = 26.20 t/s 6.40.433.640 I slot print_timing: id 0 | task 7367 | n_gen = 442, tg = 23.30 t/s, tg_3s = 25.97 t/s 6.41.278.985 I slot print_timing: id 2 | task 7653 | n_gen = 179, tg = 21.88 t/s, tg_3s = 26.02 t/s 6.41.662.119 I slot print_timing: id 3 | task 7664 | n_gen = 179, tg = 23.68 t/s, tg_3s = 26.03 t/s 6.42.664.943 I slot print_timing: id 1 | task 7692 | n_gen = 178, tg = 25.96 t/s, tg_3s = 26.00 t/s 6.43.435.620 I slot print_timing: id 0 | task 7367 | n_gen = 520, tg = 23.67 t/s, tg_3s = 25.98 t/s 6.44.282.809 I slot print_timing: id 2 | task 7653 | n_gen = 257, tg = 22.98 t/s, tg_3s = 25.97 t/s 6.44.669.266 I slot print_timing: id 3 | task 7664 | n_gen = 257, tg = 24.32 t/s, tg_3s = 25.94 t/s 6.45.551.508 I slot print_timing: id 0 | task 7367 | prompt eval time = 692.33 ms / 471 tokens ( 1.47 ms per token, 680.31 tokens per second) 6.45.551.515 I slot print_timing: id 0 | task 7367 | eval time = 24045.47 ms / 575 tokens ( 41.89 ms per token, 23.87 tokens per second) 6.45.551.516 I slot print_timing: id 0 | task 7367 | total time = 24737.80 ms / 1046 tokens 6.45.551.516 I slot print_timing: id 0 | task 7367 | graphs reused = 7408 6.45.551.517 I slot print_timing: id 0 | task 7367 | graph reallocs = 0 / 0 (same size) / (changed size) 6.45.551.626 I slot release: id 0 | task 7367 | stop processing: n_tokens = 1740, truncated = 0 6.45.586.572 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.614 6.45.586.608 I slot launch_slot_: id 0 | task 7948 | processing task, is_child = 0 6.46.185.919 I slot print_timing: id 1 | task 7692 | n_gen = 255, tg = 24.57 t/s, tg_3s = 21.87 t/s 6.47.291.352 I slot print_timing: id 2 | task 7653 | n_gen = 320, tg = 22.55 t/s, tg_3s = 20.94 t/s 6.47.677.171 I slot print_timing: id 3 | task 7664 | n_gen = 320, tg = 23.57 t/s, tg_3s = 20.94 t/s 6.49.213.374 I slot print_timing: id 1 | task 7692 | n_gen = 333, tg = 24.84 t/s, tg_3s = 25.76 t/s 6.50.061.620 I slot print_timing: id 0 | task 7948 | n_gen = 100, tg = 25.98 t/s, tg_3s = 26.24 t/s 6.50.293.513 I slot print_timing: id 2 | task 7653 | n_gen = 398, tg = 23.15 t/s, tg_3s = 25.98 t/s 6.50.677.842 I slot print_timing: id 3 | task 7664 | n_gen = 398, tg = 24.01 t/s, tg_3s = 25.99 t/s 6.52.247.583 I slot print_timing: id 1 | task 7692 | n_gen = 412, tg = 25.06 t/s, tg_3s = 26.04 t/s 6.52.286.664 I slot print_timing: id 2 | task 7653 | prompt eval time = 716.86 ms / 474 tokens ( 1.51 ms per token, 661.21 tokens per second) 6.52.286.675 I slot print_timing: id 2 | task 7653 | eval time = 19144.08 ms / 450 tokens ( 42.64 ms per token, 23.45 tokens per second) 6.52.286.676 I slot print_timing: id 2 | task 7653 | total time = 19860.94 ms / 924 tokens 6.52.286.678 I slot print_timing: id 2 | task 7653 | graphs reused = 7564 6.52.286.679 I slot print_timing: id 2 | task 7653 | graph reallocs = 0 / 0 (same size) / (changed size) 6.52.286.781 I slot release: id 2 | task 7653 | stop processing: n_tokens = 1598, truncated = 0 6.52.327.231 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.668 6.52.327.269 I slot launch_slot_: id 2 | task 8109 | processing task, is_child = 0 6.53.084.259 I slot print_timing: id 0 | task 7948 | n_gen = 162, tg = 23.56 t/s, tg_3s = 20.51 t/s 6.53.701.856 I slot print_timing: id 3 | task 7664 | n_gen = 460, tg = 23.47 t/s, tg_3s = 20.50 t/s 6.55.284.617 I slot print_timing: id 1 | task 7692 | n_gen = 474, tg = 24.34 t/s, tg_3s = 20.41 t/s 6.56.092.715 I slot print_timing: id 0 | task 7948 | n_gen = 240, tg = 24.28 t/s, tg_3s = 25.93 t/s 6.56.710.283 I slot print_timing: id 3 | task 7664 | n_gen = 538, tg = 23.80 t/s, tg_3s = 25.93 t/s 6.56.864.007 I slot print_timing: id 2 | task 8109 | n_gen = 100, tg = 25.92 t/s, tg_3s = 26.18 t/s 6.58.289.077 I slot print_timing: id 1 | task 7692 | n_gen = 552, tg = 24.55 t/s, tg_3s = 25.96 t/s 6.59.098.169 I slot print_timing: id 0 | task 7948 | n_gen = 318, tg = 24.67 t/s, tg_3s = 25.95 t/s 6.59.715.585 I slot print_timing: id 3 | task 7664 | n_gen = 616, tg = 24.05 t/s, tg_3s = 25.95 t/s 6.59.869.779 I slot print_timing: id 2 | task 8109 | n_gen = 178, tg = 25.93 t/s, tg_3s = 25.95 t/s 7.00.910.726 I slot print_timing: id 3 | task 7664 | prompt eval time = 694.79 ms / 457 tokens ( 1.52 ms per token, 657.75 tokens per second) 7.00.910.732 I slot print_timing: id 3 | task 7664 | eval time = 26766.92 ms / 647 tokens ( 41.43 ms per token, 24.13 tokens per second) 7.00.910.733 I slot print_timing: id 3 | task 7664 | total time = 27461.71 ms / 1104 tokens 7.00.910.734 I slot print_timing: id 3 | task 7664 | graphs reused = 7767 7.00.910.735 I slot print_timing: id 3 | task 7664 | graph reallocs = 0 / 0 (same size) / (changed size) 7.00.910.831 I slot release: id 3 | task 7664 | stop processing: n_tokens = 1776, truncated = 0 7.00.944.549 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.601 7.00.944.586 I slot launch_slot_: id 3 | task 8317 | processing task, is_child = 0 7.01.609.727 I slot print_timing: id 1 | task 7692 | n_gen = 622, tg = 24.11 t/s, tg_3s = 21.08 t/s 7.02.103.981 I slot print_timing: id 0 | task 7948 | n_gen = 379, tg = 23.84 t/s, tg_3s = 20.29 t/s 7.02.880.208 I slot print_timing: id 2 | task 8109 | n_gen = 239, tg = 24.20 t/s, tg_3s = 20.26 t/s 7.04.615.752 I slot print_timing: id 1 | task 7692 | n_gen = 699, tg = 24.26 t/s, tg_3s = 25.62 t/s 7.05.115.235 I slot print_timing: id 0 | task 7948 | n_gen = 457, tg = 24.17 t/s, tg_3s = 25.90 t/s 7.05.502.316 I slot print_timing: id 3 | task 8317 | n_gen = 100, tg = 25.88 t/s, tg_3s = 26.14 t/s 7.05.886.014 I slot print_timing: id 2 | task 8109 | n_gen = 317, tg = 24.61 t/s, tg_3s = 25.95 t/s 7.06.539.325 I slot print_timing: id 1 | task 7692 | prompt eval time = 738.47 ms / 487 tokens ( 1.52 ms per token, 659.47 tokens per second) 7.06.539.331 I slot print_timing: id 1 | task 7692 | eval time = 30691.32 ms / 749 tokens ( 41.03 ms per token, 24.37 tokens per second) 7.06.539.332 I slot print_timing: id 1 | task 7692 | total time = 31429.79 ms / 1236 tokens 7.06.539.333 I slot print_timing: id 1 | task 7692 | graphs reused = 7891 7.06.539.334 I slot print_timing: id 1 | task 7692 | graph reallocs = 0 / 0 (same size) / (changed size) 7.06.539.457 I slot release: id 1 | task 7692 | stop processing: n_tokens = 1899, truncated = 0 7.06.580.192 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.562 7.06.580.231 I slot launch_slot_: id 1 | task 8447 | processing task, is_child = 0 7.08.119.550 I slot print_timing: id 0 | task 7948 | n_gen = 518, tg = 23.64 t/s, tg_3s = 20.30 t/s 7.08.507.397 I slot print_timing: id 3 | task 8317 | n_gen = 161, tg = 23.42 t/s, tg_3s = 20.30 t/s 7.08.891.867 I slot print_timing: id 2 | task 8109 | n_gen = 378, tg = 23.79 t/s, tg_3s = 20.29 t/s 7.11.127.296 I slot print_timing: id 0 | task 7948 | n_gen = 596, tg = 23.92 t/s, tg_3s = 25.93 t/s 7.11.127.863 I slot print_timing: id 1 | task 8447 | n_gen = 100, tg = 25.89 t/s, tg_3s = 26.15 t/s 7.11.434.852 I slot print_timing: id 2 | task 8109 | prompt eval time = 717.15 ms / 459 tokens ( 1.56 ms per token, 640.04 tokens per second) 7.11.434.860 I slot print_timing: id 2 | task 8109 | eval time = 18390.43 ms / 444 tokens ( 41.51 ms per token, 24.09 tokens per second) 7.11.434.860 I slot print_timing: id 2 | task 8109 | total time = 19107.57 ms / 903 tokens 7.11.434.861 I slot print_timing: id 2 | task 8109 | graphs reused = 7997 7.11.434.862 I slot print_timing: id 2 | task 8109 | graph reallocs = 0 / 0 (same size) / (changed size) 7.11.434.972 I slot release: id 2 | task 8109 | stop processing: n_tokens = 1577, truncated = 0 7.11.474.822 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.677 7.11.474.866 I slot launch_slot_: id 2 | task 8558 | processing task, is_child = 0 7.12.109.029 I slot print_timing: id 3 | task 8317 | n_gen = 239, tg = 22.81 t/s, tg_3s = 21.66 t/s 7.13.176.480 I slot print_timing: id 0 | task 7948 | prompt eval time = 664.09 ms / 444 tokens ( 1.50 ms per token, 668.59 tokens per second) 7.13.176.488 I slot print_timing: id 0 | task 7948 | eval time = 26925.78 ms / 633 tokens ( 42.60 ms per token, 23.47 tokens per second) 7.13.176.488 I slot print_timing: id 0 | task 7948 | total time = 27589.86 ms / 1077 tokens 7.13.176.489 I slot print_timing: id 0 | task 7948 | graphs reused = 8022 7.13.176.490 I slot print_timing: id 0 | task 7948 | graph reallocs = 0 / 0 (same size) / (changed size) 7.13.176.590 I slot release: id 0 | task 7948 | stop processing: n_tokens = 1771, truncated = 0 7.13.211.775 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.603 7.13.211.806 I slot launch_slot_: id 0 | task 8588 | processing task, is_child = 0 7.14.024.788 I slot print_timing: id 3 | task 8317 | prompt eval time = 732.13 ms / 494 tokens ( 1.48 ms per token, 674.74 tokens per second) 7.14.024.796 I slot print_timing: id 3 | task 8317 | eval time = 12348.06 ms / 271 tokens ( 45.73 ms per token, 21.87 tokens per second) 7.14.024.796 I slot print_timing: id 3 | task 8317 | total time = 13080.19 ms / 765 tokens 7.14.024.797 I slot print_timing: id 3 | task 8317 | graphs reused = 8024 7.14.024.798 I slot print_timing: id 3 | task 8317 | graph reallocs = 0 / 0 (same size) / (changed size) 7.14.024.913 I slot release: id 3 | task 8317 | stop processing: n_tokens = 1437, truncated = 0 7.14.059.020 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.743 7.14.059.056 I slot launch_slot_: id 3 | task 8594 | processing task, is_child = 0 7.14.705.893 I slot print_timing: id 1 | task 8447 | n_gen = 144, tg = 19.32 t/s, tg_3s = 12.30 t/s 7.17.277.129 I slot print_timing: id 2 | task 8558 | n_gen = 100, tg = 19.43 t/s, tg_3s = 19.62 t/s 7.17.737.844 I slot print_timing: id 1 | task 8447 | n_gen = 222, tg = 21.18 t/s, tg_3s = 25.73 t/s 7.18.390.229 I slot print_timing: id 0 | task 8588 | n_gen = 100, tg = 22.24 t/s, tg_3s = 22.46 t/s 7.18.584.358 I slot print_timing: id 3 | task 8594 | n_gen = 100, tg = 25.97 t/s, tg_3s = 26.24 t/s 7.20.282.225 I slot print_timing: id 2 | task 8558 | n_gen = 178, tg = 21.85 t/s, tg_3s = 25.96 t/s 7.20.741.079 I slot print_timing: id 1 | task 8447 | n_gen = 300, tg = 22.25 t/s, tg_3s = 25.97 t/s 7.21.394.637 I slot print_timing: id 0 | task 8588 | n_gen = 178, tg = 23.74 t/s, tg_3s = 25.96 t/s 7.21.588.812 I slot print_timing: id 3 | task 8594 | n_gen = 178, tg = 25.97 t/s, tg_3s = 25.96 t/s 7.23.316.289 I slot print_timing: id 2 | task 8558 | n_gen = 257, tg = 22.99 t/s, tg_3s = 26.04 t/s 7.23.777.544 I slot print_timing: id 1 | task 8447 | n_gen = 379, tg = 22.95 t/s, tg_3s = 26.02 t/s 7.24.396.998 I slot print_timing: id 0 | task 8588 | n_gen = 256, tg = 24.38 t/s, tg_3s = 25.98 t/s 7.24.591.316 I slot print_timing: id 3 | task 8594 | n_gen = 256, tg = 25.97 t/s, tg_3s = 25.98 t/s 7.25.517.367 I slot print_timing: id 2 | task 8558 | prompt eval time = 706.14 ms / 460 tokens ( 1.54 ms per token, 651.43 tokens per second) 7.25.517.375 I slot print_timing: id 2 | task 8558 | eval time = 13336.35 ms / 314 tokens ( 42.61 ms per token, 23.47 tokens per second) 7.25.517.376 I slot print_timing: id 2 | task 8558 | total time = 14042.49 ms / 774 tokens 7.25.517.376 I slot print_timing: id 2 | task 8558 | graphs reused = 8301 7.25.517.377 I slot print_timing: id 2 | task 8558 | graph reallocs = 0 / 0 (same size) / (changed size) 7.25.517.479 I slot release: id 2 | task 8558 | stop processing: n_tokens = 1448, truncated = 0 7.25.558.066 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.738 7.25.558.099 I slot launch_slot_: id 2 | task 8877 | processing task, is_child = 0 7.26.783.219 I slot print_timing: id 1 | task 8447 | n_gen = 437, tg = 22.38 t/s, tg_3s = 19.30 t/s 7.27.398.972 I slot print_timing: id 0 | task 8588 | n_gen = 314, tg = 23.25 t/s, tg_3s = 19.32 t/s 7.27.593.170 I slot print_timing: id 3 | task 8594 | n_gen = 314, tg = 24.41 t/s, tg_3s = 19.32 t/s 7.29.633.098 I slot print_timing: id 1 | task 8447 | prompt eval time = 723.56 ms / 485 tokens ( 1.49 ms per token, 670.30 tokens per second) 7.29.633.105 I slot print_timing: id 1 | task 8447 | eval time = 22329.30 ms / 511 tokens ( 43.78 ms per token, 22.84 tokens per second) 7.29.633.106 I slot print_timing: id 1 | task 8447 | total time = 23052.86 ms / 996 tokens 7.29.633.107 I slot print_timing: id 1 | task 8447 | graphs reused = 8383 7.29.633.107 I slot print_timing: id 1 | task 8447 | graph reallocs = 0 / 0 (same size) / (changed size) 7.29.633.215 I slot release: id 1 | task 8447 | stop processing: n_tokens = 1659, truncated = 0 7.29.674.347 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.644 7.29.674.382 I slot launch_slot_: id 1 | task 8965 | processing task, is_child = 0 7.30.432.545 I slot print_timing: id 0 | task 8588 | n_gen = 375, tg = 22.67 t/s, tg_3s = 20.11 t/s 7.30.631.427 I slot print_timing: id 3 | task 8594 | n_gen = 375, tg = 23.58 t/s, tg_3s = 20.08 t/s 7.30.940.714 I slot print_timing: id 2 | task 8877 | n_gen = 100, tg = 21.95 t/s, tg_3s = 22.17 t/s 7.33.441.618 I slot print_timing: id 0 | task 8588 | n_gen = 453, tg = 23.18 t/s, tg_3s = 25.92 t/s 7.33.634.752 I slot print_timing: id 3 | task 8594 | n_gen = 453, tg = 23.96 t/s, tg_3s = 25.97 t/s 7.33.942.028 I slot print_timing: id 2 | task 8877 | n_gen = 178, tg = 23.56 t/s, tg_3s = 25.99 t/s 7.34.249.099 I slot print_timing: id 1 | task 8965 | n_gen = 100, tg = 25.94 t/s, tg_3s = 26.21 t/s 7.36.446.466 I slot print_timing: id 0 | task 8588 | n_gen = 531, tg = 23.55 t/s, tg_3s = 25.96 t/s 7.36.640.888 I slot print_timing: id 3 | task 8594 | n_gen = 531, tg = 24.24 t/s, tg_3s = 25.95 t/s 7.36.948.843 I slot print_timing: id 2 | task 8877 | n_gen = 256, tg = 24.24 t/s, tg_3s = 25.94 t/s 7.37.257.979 I slot print_timing: id 1 | task 8965 | n_gen = 178, tg = 25.94 t/s, tg_3s = 25.92 t/s 7.39.462.971 I slot print_timing: id 0 | task 8588 | n_gen = 609, tg = 23.82 t/s, tg_3s = 25.86 t/s 7.39.659.713 I slot print_timing: id 3 | task 8594 | n_gen = 609, tg = 24.43 t/s, tg_3s = 25.84 t/s 7.39.967.738 I slot print_timing: id 2 | task 8877 | n_gen = 334, tg = 24.60 t/s, tg_3s = 25.84 t/s 7.40.276.220 I slot print_timing: id 1 | task 8965 | n_gen = 256, tg = 25.91 t/s, tg_3s = 25.84 t/s 7.42.467.253 I slot print_timing: id 0 | task 8588 | n_gen = 687, tg = 24.05 t/s, tg_3s = 25.96 t/s 7.42.660.796 I slot print_timing: id 3 | task 8594 | n_gen = 687, tg = 24.60 t/s, tg_3s = 25.99 t/s 7.42.969.968 I slot print_timing: id 2 | task 8877 | n_gen = 412, tg = 24.85 t/s, tg_3s = 25.98 t/s 7.43.278.224 I slot print_timing: id 1 | task 8965 | n_gen = 334, tg = 25.92 t/s, tg_3s = 25.98 t/s 7.43.896.298 I slot print_timing: id 3 | task 8594 | prompt eval time = 713.89 ms / 483 tokens ( 1.48 ms per token, 676.57 tokens per second) 7.43.896.305 I slot print_timing: id 3 | task 8594 | eval time = 29123.34 ms / 719 tokens ( 40.56 ms per token, 24.65 tokens per second) 7.43.896.306 I slot print_timing: id 3 | task 8594 | total time = 29837.23 ms / 1202 tokens 7.43.896.307 I slot print_timing: id 3 | task 8594 | graphs reused = 8730 7.43.896.308 I slot print_timing: id 3 | task 8594 | graph reallocs = 0 / 0 (same size) / (changed size) 7.43.896.407 I slot release: id 3 | task 8594 | stop processing: n_tokens = 1874, truncated = 0 7.43.930.162 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.570 7.43.930.205 I slot launch_slot_: id 3 | task 9318 | processing task, is_child = 0 7.45.471.230 I slot print_timing: id 0 | task 8588 | n_gen = 748, tg = 23.69 t/s, tg_3s = 20.31 t/s 7.45.970.042 I slot print_timing: id 2 | task 8877 | n_gen = 473, tg = 24.16 t/s, tg_3s = 20.33 t/s 7.46.315.512 I slot print_timing: id 1 | task 8965 | n_gen = 396, tg = 24.87 t/s, tg_3s = 20.41 t/s 7.48.481.405 I slot print_timing: id 0 | task 8588 | n_gen = 826, tg = 23.88 t/s, tg_3s = 25.91 t/s 7.48.483.136 I slot print_timing: id 3 | task 9318 | n_gen = 100, tg = 25.91 t/s, tg_3s = 26.17 t/s 7.48.987.530 I slot print_timing: id 2 | task 8877 | n_gen = 551, tg = 24.38 t/s, tg_3s = 25.85 t/s 7.49.335.218 I slot print_timing: id 1 | task 8965 | n_gen = 474, tg = 25.02 t/s, tg_3s = 25.83 t/s 7.50.264.992 I slot print_timing: id 1 | task 8965 | prompt eval time = 758.89 ms / 499 tokens ( 1.52 ms per token, 657.54 tokens per second) 7.50.264.999 I slot print_timing: id 1 | task 8965 | eval time = 19831.71 ms / 498 tokens ( 39.90 ms per token, 25.06 tokens per second) 7.50.265.000 I slot print_timing: id 1 | task 8965 | total time = 20590.60 ms / 997 tokens 7.50.265.001 I slot print_timing: id 1 | task 8965 | graphs reused = 8873 7.50.265.002 I slot print_timing: id 1 | task 8965 | graph reallocs = 0 / 0 (same size) / (changed size) 7.50.265.141 I slot release: id 1 | task 8965 | stop processing: n_tokens = 1660, truncated = 0 7.50.306.113 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.643 7.50.306.153 I slot launch_slot_: id 1 | task 9467 | processing task, is_child = 0 7.51.485.187 I slot print_timing: id 0 | task 8588 | n_gen = 887, tg = 23.60 t/s, tg_3s = 20.31 t/s 7.51.486.890 I slot print_timing: id 3 | task 9318 | n_gen = 161, tg = 23.44 t/s, tg_3s = 20.31 t/s 7.51.990.693 I slot print_timing: id 2 | task 8877 | n_gen = 612, tg = 23.90 t/s, tg_3s = 20.31 t/s 7.54.497.384 I slot print_timing: id 0 | task 8588 | n_gen = 965, tg = 23.77 t/s, tg_3s = 25.89 t/s 7.54.499.055 I slot print_timing: id 3 | task 9318 | n_gen = 239, tg = 24.19 t/s, tg_3s = 25.89 t/s 7.54.846.154 I slot print_timing: id 1 | task 9467 | n_gen = 100, tg = 25.85 t/s, tg_3s = 26.11 t/s 7.55.001.562 I slot print_timing: id 2 | task 8877 | n_gen = 690, tg = 24.11 t/s, tg_3s = 25.91 t/s 7.56.780.712 I slot print_timing: id 0 | task 8588 | prompt eval time = 726.41 ms / 489 tokens ( 1.49 ms per token, 673.17 tokens per second) 7.56.780.717 I slot print_timing: id 0 | task 8588 | eval time = 42842.48 ms / 1024 tokens ( 41.88 ms per token, 23.88 tokens per second) 7.56.780.718 I slot print_timing: id 0 | task 8588 | total time = 43568.90 ms / 1513 tokens 7.56.780.719 I slot print_timing: id 0 | task 8588 | graphs reused = 9021 7.56.780.720 I slot print_timing: id 0 | task 8588 | graph reallocs = 0 / 0 (same size) / (changed size) 7.56.780.817 I slot release: id 0 | task 8588 | stop processing: n_tokens = 2207, truncated = 0 7.56.815.853 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.484 7.56.821.609 I slot launch_slot_: id 0 | task 9620 | processing task, is_child = 0 7.57.529.784 I slot print_timing: id 3 | task 9318 | n_gen = 302, tg = 23.39 t/s, tg_3s = 20.79 t/s 7.57.873.496 I slot print_timing: id 1 | task 9467 | n_gen = 163, tg = 23.62 t/s, tg_3s = 20.81 t/s 7.58.027.594 I slot print_timing: id 2 | task 8877 | n_gen = 753, tg = 23.80 t/s, tg_3s = 20.82 t/s 8.00.532.233 I slot print_timing: id 3 | task 9318 | n_gen = 380, tg = 23.88 t/s, tg_3s = 25.98 t/s 8.00.877.334 I slot print_timing: id 1 | task 9467 | n_gen = 241, tg = 24.34 t/s, tg_3s = 25.97 t/s 8.01.031.597 I slot print_timing: id 2 | task 8877 | n_gen = 831, tg = 23.99 t/s, tg_3s = 25.97 t/s 8.01.298.862 I slot print_timing: id 0 | task 9620 | n_gen = 100, tg = 25.99 t/s, tg_3s = 26.26 t/s 8.03.550.100 I slot print_timing: id 3 | task 9318 | n_gen = 458, tg = 24.20 t/s, tg_3s = 25.85 t/s 8.03.898.391 I slot print_timing: id 1 | task 9467 | n_gen = 319, tg = 24.69 t/s, tg_3s = 25.82 t/s 8.04.053.740 I slot print_timing: id 2 | task 8877 | n_gen = 909, tg = 24.13 t/s, tg_3s = 25.81 t/s 8.04.323.657 I slot print_timing: id 0 | task 9620 | n_gen = 178, tg = 25.90 t/s, tg_3s = 25.79 t/s 8.06.568.816 I slot print_timing: id 3 | task 9318 | n_gen = 536, tg = 24.42 t/s, tg_3s = 25.84 t/s 8.06.915.858 I slot print_timing: id 1 | task 9467 | n_gen = 397, tg = 24.91 t/s, tg_3s = 25.85 t/s 8.07.070.909 I slot print_timing: id 2 | task 8877 | n_gen = 987, tg = 24.26 t/s, tg_3s = 25.85 t/s 8.07.340.280 I slot print_timing: id 0 | task 9620 | n_gen = 256, tg = 25.89 t/s, tg_3s = 25.86 t/s 8.08.501.795 I slot print_timing: id 2 | task 8877 | prompt eval time = 871.91 ms / 528 tokens ( 1.65 ms per token, 605.56 tokens per second) 8.08.501.806 I slot print_timing: id 2 | task 8877 | eval time = 42071.77 ms / 1024 tokens ( 41.13 ms per token, 24.32 tokens per second) 8.08.501.807 I slot print_timing: id 2 | task 8877 | total time = 42943.69 ms / 1552 tokens 8.08.501.814 I slot print_timing: id 2 | task 8877 | graphs reused = 9305 8.08.501.815 I slot print_timing: id 2 | task 8877 | graph reallocs = 0 / 0 (same size) / (changed size) 8.08.501.921 I slot release: id 2 | task 8877 | stop processing: n_tokens = 2226, truncated = 0 8.08.542.344 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 8.08.548.527 I slot launch_slot_: id 2 | task 9909 | processing task, is_child = 0 8.09.586.077 I slot print_timing: id 3 | task 9318 | n_gen = 597, tg = 23.91 t/s, tg_3s = 20.22 t/s 8.09.931.361 I slot print_timing: id 1 | task 9467 | n_gen = 458, tg = 24.16 t/s, tg_3s = 20.23 t/s 8.10.354.709 I slot print_timing: id 0 | task 9620 | n_gen = 317, tg = 24.56 t/s, tg_3s = 20.24 t/s 8.10.392.945 I slot print_timing: id 0 | task 9620 | prompt eval time = 668.61 ms / 452 tokens ( 1.48 ms per token, 676.03 tokens per second) 8.10.392.949 I slot print_timing: id 0 | task 9620 | eval time = 12902.71 ms / 318 tokens ( 40.70 ms per token, 24.57 tokens per second) 8.10.392.949 I slot print_timing: id 0 | task 9620 | total time = 13571.32 ms / 770 tokens 8.10.392.950 I slot print_timing: id 0 | task 9620 | graphs reused = 9333 8.10.392.951 I slot print_timing: id 0 | task 9620 | graph reallocs = 0 / 0 (same size) / (changed size) 8.10.393.053 I slot release: id 0 | task 9620 | stop processing: n_tokens = 1464, truncated = 0 8.10.428.111 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.730 8.10.428.144 I slot launch_slot_: id 0 | task 9942 | processing task, is_child = 0 8.12.605.745 I slot print_timing: id 3 | task 9318 | n_gen = 660, tg = 23.58 t/s, tg_3s = 20.86 t/s 8.12.950.412 I slot print_timing: id 1 | task 9467 | n_gen = 521, tg = 23.71 t/s, tg_3s = 20.87 t/s 8.13.680.355 I slot print_timing: id 2 | task 9909 | n_gen = 100, tg = 22.45 t/s, tg_3s = 22.68 t/s 8.14.910.399 I slot print_timing: id 0 | task 9942 | n_gen = 100, tg = 25.95 t/s, tg_3s = 26.21 t/s 8.15.641.131 I slot print_timing: id 3 | task 9318 | n_gen = 739, tg = 23.82 t/s, tg_3s = 26.03 t/s 8.15.985.047 I slot print_timing: id 1 | task 9467 | n_gen = 600, tg = 23.99 t/s, tg_3s = 26.03 t/s 8.16.713.974 I slot print_timing: id 2 | task 9909 | n_gen = 179, tg = 23.92 t/s, tg_3s = 26.04 t/s 8.17.019.638 I slot print_timing: id 1 | task 9467 | prompt eval time = 709.92 ms / 460 tokens ( 1.54 ms per token, 647.96 tokens per second) 8.17.019.644 I slot print_timing: id 1 | task 9467 | eval time = 26003.56 ms / 627 tokens ( 41.54 ms per token, 24.07 tokens per second) 8.17.019.645 I slot print_timing: id 1 | task 9467 | total time = 26713.48 ms / 1087 tokens 8.17.019.646 I slot print_timing: id 1 | task 9467 | graphs reused = 9486 8.17.019.647 I slot print_timing: id 1 | task 9467 | graph reallocs = 0 / 0 (same size) / (changed size) 8.17.019.750 I slot release: id 1 | task 9467 | stop processing: n_tokens = 1750, truncated = 0 8.17.060.592 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.610 8.17.060.628 I slot launch_slot_: id 1 | task 10100 | processing task, is_child = 0 8.17.925.480 I slot print_timing: id 0 | task 9942 | n_gen = 161, tg = 23.43 t/s, tg_3s = 20.23 t/s 8.18.662.798 I slot print_timing: id 3 | task 9318 | n_gen = 800, tg = 23.50 t/s, tg_3s = 20.19 t/s 8.19.740.167 I slot print_timing: id 2 | task 9909 | n_gen = 240, tg = 22.83 t/s, tg_3s = 20.16 t/s 8.20.929.939 I slot print_timing: id 0 | task 9942 | n_gen = 239, tg = 24.20 t/s, tg_3s = 25.96 t/s 8.21.621.325 I slot print_timing: id 1 | task 10100 | n_gen = 100, tg = 25.98 t/s, tg_3s = 26.25 t/s 8.21.699.474 I slot print_timing: id 3 | task 9318 | n_gen = 879, tg = 23.71 t/s, tg_3s = 26.02 t/s 8.22.744.791 I slot print_timing: id 2 | task 9909 | n_gen = 318, tg = 23.53 t/s, tg_3s = 25.96 t/s 8.23.942.377 I slot print_timing: id 0 | task 9942 | n_gen = 317, tg = 24.60 t/s, tg_3s = 25.89 t/s 8.24.641.816 I slot print_timing: id 1 | task 10100 | n_gen = 178, tg = 25.91 t/s, tg_3s = 25.82 t/s 8.24.720.664 I slot print_timing: id 3 | task 9318 | n_gen = 957, tg = 23.87 t/s, tg_3s = 25.82 t/s 8.25.767.329 I slot print_timing: id 2 | task 9909 | n_gen = 396, tg = 23.95 t/s, tg_3s = 25.81 t/s 8.26.971.029 I slot print_timing: id 0 | task 9942 | n_gen = 395, tg = 24.82 t/s, tg_3s = 25.75 t/s 8.27.322.560 I slot print_timing: id 3 | task 9318 | prompt eval time = 731.90 ms / 493 tokens ( 1.48 ms per token, 673.59 tokens per second) 8.27.322.568 I slot print_timing: id 3 | task 9318 | eval time = 42660.44 ms / 1024 tokens ( 41.70 ms per token, 23.98 tokens per second) 8.27.322.569 I slot print_timing: id 3 | task 9318 | total time = 43392.35 ms / 1517 tokens 8.27.322.569 I slot print_timing: id 3 | task 9318 | graphs reused = 9730 8.27.322.570 I slot print_timing: id 3 | task 9318 | graph reallocs = 0 / 0 (same size) / (changed size) 8.27.322.673 I slot release: id 3 | task 9318 | stop processing: n_tokens = 2189, truncated = 0 8.27.355.924 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 8.27.361.921 I slot launch_slot_: id 3 | task 10350 | processing task, is_child = 0 8.28.024.479 I slot print_timing: id 1 | task 10100 | n_gen = 249, tg = 24.28 t/s, tg_3s = 20.99 t/s 8.28.784.394 I slot print_timing: id 2 | task 9909 | n_gen = 457, tg = 23.37 t/s, tg_3s = 20.22 t/s 8.29.974.688 I slot print_timing: id 0 | task 9942 | n_gen = 456, tg = 24.10 t/s, tg_3s = 20.31 t/s 8.30.631.231 I slot print_timing: id 1 | task 10100 | prompt eval time = 750.52 ms / 501 tokens ( 1.50 ms per token, 667.54 tokens per second) 8.30.631.240 I slot print_timing: id 1 | task 10100 | eval time = 12820.08 ms / 316 tokens ( 40.70 ms per token, 24.57 tokens per second) 8.30.631.241 I slot print_timing: id 1 | task 10100 | total time = 13570.59 ms / 817 tokens 8.30.631.241 I slot print_timing: id 1 | task 10100 | graphs reused = 9795 8.30.631.242 I slot print_timing: id 1 | task 10100 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.631.363 I slot release: id 1 | task 10100 | stop processing: n_tokens = 1480, truncated = 0 8.30.672.456 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.722 8.30.672.491 I slot launch_slot_: id 1 | task 10420 | processing task, is_child = 0 8.31.801.357 I slot print_timing: id 2 | task 9909 | n_gen = 518, tg = 22.95 t/s, tg_3s = 20.22 t/s 8.32.571.044 I slot print_timing: id 3 | task 10350 | n_gen = 100, tg = 22.10 t/s, tg_3s = 22.33 t/s 8.32.989.108 I slot print_timing: id 0 | task 9942 | n_gen = 517, tg = 23.57 t/s, tg_3s = 20.24 t/s 8.34.443.325 I slot print_timing: id 2 | task 9909 | prompt eval time = 722.88 ms / 479 tokens ( 1.51 ms per token, 662.63 tokens per second) 8.34.443.329 I slot print_timing: id 2 | task 9909 | eval time = 25171.91 ms / 587 tokens ( 42.96 ms per token, 23.28 tokens per second) 8.34.443.330 I slot print_timing: id 2 | task 9909 | total time = 25894.79 ms / 1066 tokens 8.34.443.331 I slot print_timing: id 2 | task 9909 | graphs reused = 9873 8.34.443.332 I slot print_timing: id 2 | task 9909 | graph reallocs = 0 / 0 (same size) / (changed size) 8.34.443.441 I slot release: id 2 | task 9909 | stop processing: n_tokens = 1752, truncated = 0 8.34.483.361 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.610 8.34.483.398 I slot launch_slot_: id 2 | task 10503 | processing task, is_child = 0 8.35.602.265 I slot print_timing: id 3 | task 10350 | n_gen = 163, tg = 21.57 t/s, tg_3s = 20.78 t/s 8.35.830.628 I slot print_timing: id 1 | task 10420 | n_gen = 100, tg = 22.41 t/s, tg_3s = 22.63 t/s 8.36.020.962 I slot print_timing: id 0 | task 9942 | n_gen = 580, tg = 23.23 t/s, tg_3s = 20.78 t/s 8.38.627.750 I slot print_timing: id 3 | task 10350 | n_gen = 242, tg = 22.87 t/s, tg_3s = 26.11 t/s 8.38.859.598 I slot print_timing: id 1 | task 10420 | n_gen = 179, tg = 23.90 t/s, tg_3s = 26.08 t/s 8.38.975.127 I slot print_timing: id 2 | task 10503 | n_gen = 100, tg = 26.05 t/s, tg_3s = 26.31 t/s 8.39.050.863 I slot print_timing: id 0 | task 9942 | n_gen = 659, tg = 23.54 t/s, tg_3s = 26.07 t/s 8.41.666.066 I slot print_timing: id 3 | task 10350 | n_gen = 321, tg = 23.57 t/s, tg_3s = 26.00 t/s 8.41.895.213 I slot print_timing: id 1 | task 10420 | n_gen = 258, tg = 24.52 t/s, tg_3s = 26.02 t/s 8.42.010.240 I slot print_timing: id 2 | task 10503 | n_gen = 179, tg = 26.04 t/s, tg_3s = 26.03 t/s 8.42.086.139 I slot print_timing: id 0 | task 9942 | n_gen = 738, tg = 23.78 t/s, tg_3s = 26.03 t/s 8.44.667.077 I slot print_timing: id 3 | task 10350 | n_gen = 399, tg = 24.01 t/s, tg_3s = 25.99 t/s 8.44.898.307 I slot print_timing: id 1 | task 10420 | n_gen = 336, tg = 24.84 t/s, tg_3s = 25.97 t/s 8.45.015.401 I slot print_timing: id 2 | task 10503 | n_gen = 257, tg = 26.01 t/s, tg_3s = 25.96 t/s 8.45.091.878 I slot print_timing: id 0 | task 9942 | n_gen = 816, tg = 23.97 t/s, tg_3s = 25.95 t/s 8.47.676.896 I slot print_timing: id 3 | task 10350 | n_gen = 477, tg = 24.30 t/s, tg_3s = 25.92 t/s 8.47.907.912 I slot print_timing: id 1 | task 10420 | n_gen = 414, tg = 25.04 t/s, tg_3s = 25.92 t/s 8.48.024.495 I slot print_timing: id 2 | task 10503 | n_gen = 335, tg = 25.99 t/s, tg_3s = 25.92 t/s 8.48.100.519 I slot print_timing: id 0 | task 9942 | n_gen = 894, tg = 24.13 t/s, tg_3s = 25.93 t/s 8.48.721.434 I slot print_timing: id 3 | task 10350 | prompt eval time = 729.85 ms / 491 tokens ( 1.49 ms per token, 672.74 tokens per second) 8.48.721.442 I slot print_timing: id 3 | task 10350 | eval time = 20629.65 ms / 504 tokens ( 41.01 ms per token, 24.38 tokens per second) 8.48.721.443 I slot print_timing: id 3 | task 10350 | total time = 21359.50 ms / 995 tokens 8.48.721.443 I slot print_timing: id 3 | task 10350 | graphs reused = 10222 8.48.721.444 I slot print_timing: id 3 | task 10350 | graph reallocs = 0 / 0 (same size) / (changed size) 8.48.721.545 I slot release: id 3 | task 10350 | stop processing: n_tokens = 1667, truncated = 0 8.48.755.166 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.881 (> 0.100 thold), f_keep = 0.641 8.48.755.194 I slot launch_slot_: id 3 | task 10859 | processing task, is_child = 0 8.50.935.535 I slot print_timing: id 1 | task 10420 | n_gen = 472, tg = 24.13 t/s, tg_3s = 19.16 t/s 8.51.052.961 I slot print_timing: id 2 | task 10503 | n_gen = 393, tg = 24.69 t/s, tg_3s = 19.15 t/s 8.51.129.647 I slot print_timing: id 0 | task 9942 | n_gen = 952, tg = 23.75 t/s, tg_3s = 19.15 t/s 8.51.130.201 I slot print_timing: id 1 | task 10420 | prompt eval time = 739.94 ms / 488 tokens ( 1.52 ms per token, 659.52 tokens per second) 8.51.130.211 I slot print_timing: id 1 | task 10420 | eval time = 19717.76 ms / 477 tokens ( 41.42 ms per token, 24.14 tokens per second) 8.51.130.215 I slot print_timing: id 1 | task 10420 | total time = 20457.70 ms / 965 tokens 8.51.130.216 I slot print_timing: id 1 | task 10420 | graphs reused = 10259 8.51.130.217 I slot print_timing: id 1 | task 10420 | graph reallocs = 0 / 0 (same size) / (changed size) 8.51.130.347 I slot release: id 1 | task 10420 | stop processing: n_tokens = 1628, truncated = 0 8.51.171.811 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.656 8.51.171.843 I slot launch_slot_: id 1 | task 10902 | processing task, is_child = 0 8.54.063.298 I slot print_timing: id 2 | task 10503 | n_gen = 454, tg = 23.98 t/s, tg_3s = 20.26 t/s 8.54.139.852 I slot print_timing: id 0 | task 9942 | n_gen = 1013, tg = 23.51 t/s, tg_3s = 20.26 t/s 8.54.141.522 I slot print_timing: id 3 | task 10859 | n_gen = 100, tg = 22.12 t/s, tg_3s = 22.34 t/s 8.54.564.407 I slot print_timing: id 0 | task 9942 | prompt eval time = 667.52 ms / 449 tokens ( 1.49 ms per token, 672.64 tokens per second) 8.54.564.414 I slot print_timing: id 0 | task 9942 | eval time = 43468.74 ms / 1024 tokens ( 42.49 ms per token, 23.53 tokens per second) 8.54.564.415 I slot print_timing: id 0 | task 9942 | total time = 44136.25 ms / 1473 tokens 8.54.564.416 I slot print_timing: id 0 | task 9942 | graphs reused = 10327 8.54.564.417 I slot print_timing: id 0 | task 9942 | graph reallocs = 0 / 0 (same size) / (changed size) 8.54.564.515 I slot release: id 0 | task 9942 | stop processing: n_tokens = 2167, truncated = 0 8.54.599.734 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.493 8.54.605.477 I slot launch_slot_: id 0 | task 10975 | processing task, is_child = 0 8.56.296.998 I slot print_timing: id 1 | task 10902 | n_gen = 100, tg = 22.47 t/s, tg_3s = 22.70 t/s 8.57.067.304 I slot print_timing: id 2 | task 10503 | n_gen = 517, tg = 23.57 t/s, tg_3s = 20.97 t/s 8.57.145.134 I slot print_timing: id 3 | task 10859 | n_gen = 163, tg = 21.66 t/s, tg_3s = 20.97 t/s 8.58.065.979 I slot print_timing: id 2 | task 10503 | prompt eval time = 691.36 ms / 453 tokens ( 1.53 ms per token, 655.23 tokens per second) 8.58.065.987 I slot print_timing: id 2 | task 10503 | eval time = 22891.21 ms / 543 tokens ( 42.23 ms per token, 23.68 tokens per second) 8.58.065.987 I slot print_timing: id 2 | task 10503 | total time = 23582.57 ms / 996 tokens 8.58.065.988 I slot print_timing: id 2 | task 10503 | graphs reused = 10400 8.58.065.989 I slot print_timing: id 2 | task 10503 | graph reallocs = 0 / 0 (same size) / (changed size) 8.58.066.092 I slot release: id 2 | task 10503 | stop processing: n_tokens = 1682, truncated = 0 8.58.106.615 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.635 8.58.106.647 I slot launch_slot_: id 2 | task 11052 | processing task, is_child = 0 8.59.328.184 I slot print_timing: id 1 | task 10902 | n_gen = 162, tg = 21.65 t/s, tg_3s = 20.45 t/s 8.59.712.170 I slot print_timing: id 0 | task 10975 | n_gen = 100, tg = 22.24 t/s, tg_3s = 22.46 t/s 9.00.174.032 I slot print_timing: id 3 | task 10859 | n_gen = 225, tg = 21.32 t/s, tg_3s = 20.47 t/s 9.02.362.151 I slot print_timing: id 1 | task 10902 | n_gen = 241, tg = 22.92 t/s, tg_3s = 26.04 t/s 9.02.633.091 I slot print_timing: id 2 | task 11052 | n_gen = 100, tg = 25.97 t/s, tg_3s = 26.23 t/s 9.02.747.021 I slot print_timing: id 0 | task 10975 | n_gen = 179, tg = 23.78 t/s, tg_3s = 26.03 t/s 9.03.210.932 I slot print_timing: id 3 | task 10859 | n_gen = 304, tg = 22.37 t/s, tg_3s = 26.01 t/s 9.05.368.416 I slot print_timing: id 1 | task 10902 | n_gen = 319, tg = 23.59 t/s, tg_3s = 25.95 t/s 9.05.639.568 I slot print_timing: id 2 | task 11052 | n_gen = 178, tg = 25.96 t/s, tg_3s = 25.94 t/s 9.05.754.067 I slot print_timing: id 0 | task 10975 | n_gen = 257, tg = 24.40 t/s, tg_3s = 25.94 t/s 9.06.218.919 I slot print_timing: id 3 | task 10859 | n_gen = 382, tg = 23.02 t/s, tg_3s = 25.93 t/s 9.06.295.939 I slot print_timing: id 3 | task 10859 | prompt eval time = 910.75 ms / 539 tokens ( 1.69 ms per token, 591.82 tokens per second) 9.06.295.944 I slot print_timing: id 3 | task 10859 | eval time = 16629.99 ms / 384 tokens ( 43.42 ms per token, 23.03 tokens per second) 9.06.295.945 I slot print_timing: id 3 | task 10859 | total time = 17540.74 ms / 923 tokens 9.06.295.945 I slot print_timing: id 3 | task 10859 | graphs reused = 10592 9.06.295.946 I slot print_timing: id 3 | task 10859 | graph reallocs = 0 / 0 (same size) / (changed size) 9.06.296.061 I slot release: id 3 | task 10859 | stop processing: n_tokens = 1595, truncated = 0 9.06.329.791 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.670 9.06.329.821 I slot launch_slot_: id 3 | task 11250 | processing task, is_child = 0 9.08.394.502 I slot print_timing: id 1 | task 10902 | n_gen = 382, tg = 23.09 t/s, tg_3s = 20.82 t/s 9.08.664.048 I slot print_timing: id 2 | task 11052 | n_gen = 241, tg = 24.38 t/s, tg_3s = 20.83 t/s 9.08.778.332 I slot print_timing: id 0 | task 10975 | n_gen = 320, tg = 23.60 t/s, tg_3s = 20.83 t/s 9.09.705.556 I slot print_timing: id 1 | task 10902 | prompt eval time = 718.94 ms / 471 tokens ( 1.53 ms per token, 655.13 tokens per second) 9.09.705.563 I slot print_timing: id 1 | task 10902 | eval time = 17814.76 ms / 416 tokens ( 42.93 ms per token, 23.30 tokens per second) 9.09.705.564 I slot print_timing: id 1 | task 10902 | total time = 18533.70 ms / 887 tokens 9.09.705.565 I slot print_timing: id 1 | task 10902 | graphs reused = 10660 9.09.705.566 I slot print_timing: id 1 | task 10902 | graph reallocs = 0 / 0 (same size) / (changed size) 9.09.705.674 I slot release: id 1 | task 10902 | stop processing: n_tokens = 1550, truncated = 0 9.09.746.304 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.689 9.09.746.341 I slot launch_slot_: id 1 | task 11324 | processing task, is_child = 0 9.11.483.290 I slot print_timing: id 3 | task 11250 | n_gen = 100, tg = 22.12 t/s, tg_3s = 22.34 t/s 9.11.675.558 I slot print_timing: id 2 | task 11052 | n_gen = 302, tg = 23.42 t/s, tg_3s = 20.26 t/s 9.11.790.328 I slot print_timing: id 0 | task 10975 | n_gen = 381, tg = 22.99 t/s, tg_3s = 20.25 t/s 9.14.295.893 I slot print_timing: id 1 | task 11324 | n_gen = 100, tg = 25.93 t/s, tg_3s = 26.20 t/s 9.14.490.479 I slot print_timing: id 3 | task 11250 | n_gen = 178, tg = 23.65 t/s, tg_3s = 25.94 t/s 9.14.682.717 I slot print_timing: id 2 | task 11052 | n_gen = 380, tg = 23.89 t/s, tg_3s = 25.94 t/s 9.14.797.208 I slot print_timing: id 0 | task 10975 | n_gen = 459, tg = 23.44 t/s, tg_3s = 25.94 t/s 9.15.990.974 I slot print_timing: id 0 | task 10975 | prompt eval time = 655.15 ms / 429 tokens ( 1.53 ms per token, 654.81 tokens per second) 9.15.990.981 I slot print_timing: id 0 | task 10975 | eval time = 20730.33 ms / 490 tokens ( 42.39 ms per token, 23.59 tokens per second) 9.15.990.982 I slot print_timing: id 0 | task 10975 | total time = 21385.49 ms / 919 tokens 9.15.990.982 I slot print_timing: id 0 | task 10975 | graphs reused = 10801 9.15.990.983 I slot print_timing: id 0 | task 10975 | graph reallocs = 0 / 0 (same size) / (changed size) 9.15.991.081 I slot release: id 0 | task 10975 | stop processing: n_tokens = 1613, truncated = 0 9.16.025.945 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.662 9.16.025.976 I slot launch_slot_: id 0 | task 11471 | processing task, is_child = 0 9.17.307.103 I slot print_timing: id 1 | task 11324 | n_gen = 163, tg = 23.72 t/s, tg_3s = 20.92 t/s 9.17.500.060 I slot print_timing: id 3 | task 11250 | n_gen = 241, tg = 22.87 t/s, tg_3s = 20.93 t/s 9.17.691.880 I slot print_timing: id 2 | task 11052 | n_gen = 443, tg = 23.42 t/s, tg_3s = 20.94 t/s 9.20.343.690 I slot print_timing: id 1 | task 11324 | n_gen = 242, tg = 24.43 t/s, tg_3s = 26.02 t/s 9.20.496.573 I slot print_timing: id 0 | task 11471 | n_gen = 100, tg = 26.02 t/s, tg_3s = 26.29 t/s 9.20.536.618 I slot print_timing: id 3 | task 11250 | n_gen = 320, tg = 23.58 t/s, tg_3s = 26.02 t/s 9.20.728.092 I slot print_timing: id 2 | task 11052 | n_gen = 522, tg = 23.78 t/s, tg_3s = 26.02 t/s 9.23.351.531 I slot print_timing: id 1 | task 11324 | n_gen = 320, tg = 24.78 t/s, tg_3s = 25.93 t/s 9.23.506.514 I slot print_timing: id 0 | task 11471 | n_gen = 178, tg = 25.97 t/s, tg_3s = 25.91 t/s 9.23.547.275 I slot print_timing: id 3 | task 11250 | n_gen = 398, tg = 24.00 t/s, tg_3s = 25.91 t/s 9.23.739.847 I slot print_timing: id 2 | task 11052 | n_gen = 600, tg = 24.04 t/s, tg_3s = 25.90 t/s 9.26.365.633 I slot print_timing: id 1 | task 11324 | n_gen = 398, tg = 24.99 t/s, tg_3s = 25.88 t/s 9.26.520.128 I slot print_timing: id 0 | task 11471 | n_gen = 256, tg = 25.95 t/s, tg_3s = 25.88 t/s 9.26.560.549 I slot print_timing: id 3 | task 11250 | n_gen = 476, tg = 24.29 t/s, tg_3s = 25.89 t/s 9.26.753.452 I slot print_timing: id 2 | task 11052 | n_gen = 678, tg = 24.24 t/s, tg_3s = 25.88 t/s 9.28.992.294 I slot print_timing: id 3 | task 11250 | prompt eval time = 676.86 ms / 446 tokens ( 1.52 ms per token, 658.92 tokens per second) 9.28.992.299 I slot print_timing: id 3 | task 11250 | eval time = 21985.60 ms / 539 tokens ( 40.87 ms per token, 24.47 tokens per second) 9.28.992.300 I slot print_timing: id 3 | task 11250 | total time = 22662.46 ms / 985 tokens 9.28.992.301 I slot print_timing: id 3 | task 11250 | graphs reused = 11119 9.28.992.302 I slot print_timing: id 3 | task 11250 | graph reallocs = 0 / 0 (same size) / (changed size) 9.28.992.415 I slot release: id 3 | task 11250 | stop processing: n_tokens = 1680, truncated = 0 9.29.026.510 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.636 9.29.026.545 I slot launch_slot_: id 3 | task 11794 | processing task, is_child = 0 9.29.656.935 I slot print_timing: id 0 | task 11471 | n_gen = 322, tg = 24.76 t/s, tg_3s = 21.04 t/s 9.29.657.229 I slot print_timing: id 1 | task 11324 | n_gen = 468, tg = 24.35 t/s, tg_3s = 21.27 t/s 9.29.762.826 I slot print_timing: id 2 | task 11052 | n_gen = 740, tg = 23.88 t/s, tg_3s = 20.60 t/s 9.30.224.142 I slot print_timing: id 2 | task 11052 | prompt eval time = 714.62 ms / 469 tokens ( 1.52 ms per token, 656.29 tokens per second) 9.30.224.147 I slot print_timing: id 2 | task 11052 | eval time = 31402.86 ms / 752 tokens ( 41.81 ms per token, 23.92 tokens per second) 9.30.224.148 I slot print_timing: id 2 | task 11052 | total time = 32117.48 ms / 1221 tokens 9.30.224.149 I slot print_timing: id 2 | task 11052 | graphs reused = 11131 9.30.224.150 I slot print_timing: id 2 | task 11052 | graph reallocs = 0 / 0 (same size) / (changed size) 9.30.224.278 I slot release: id 2 | task 11052 | stop processing: n_tokens = 1907, truncated = 0 9.30.264.712 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.560 9.30.264.755 I slot launch_slot_: id 2 | task 11811 | processing task, is_child = 0 9.32.291.463 I slot print_timing: id 0 | task 11471 | prompt eval time = 666.29 ms / 446 tokens ( 1.49 ms per token, 669.38 tokens per second) 9.32.291.470 I slot print_timing: id 0 | task 11471 | eval time = 15599.19 ms / 373 tokens ( 41.93 ms per token, 23.85 tokens per second) 9.32.291.471 I slot print_timing: id 0 | task 11471 | total time = 16265.48 ms / 819 tokens 9.32.291.472 I slot print_timing: id 0 | task 11471 | graphs reused = 11164 9.32.291.473 I slot print_timing: id 0 | task 11471 | graph reallocs = 0 / 0 (same size) / (changed size) 9.32.291.572 I slot release: id 0 | task 11471 | stop processing: n_tokens = 1513, truncated = 0 9.32.326.822 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.706 9.32.326.849 I slot launch_slot_: id 0 | task 11849 | processing task, is_child = 0 9.32.962.730 I slot print_timing: id 1 | task 11324 | n_gen = 521, tg = 23.13 t/s, tg_3s = 16.03 t/s 9.34.796.324 I slot print_timing: id 3 | task 11794 | n_gen = 100, tg = 19.52 t/s, tg_3s = 19.72 t/s 9.35.408.274 I slot print_timing: id 2 | task 11811 | n_gen = 100, tg = 22.36 t/s, tg_3s = 22.59 t/s 9.35.983.516 I slot print_timing: id 1 | task 11324 | n_gen = 599, tg = 23.45 t/s, tg_3s = 25.82 t/s 9.36.825.007 I slot print_timing: id 0 | task 11849 | n_gen = 100, tg = 26.07 t/s, tg_3s = 26.33 t/s 9.37.822.887 I slot print_timing: id 3 | task 11794 | n_gen = 179, tg = 21.98 t/s, tg_3s = 26.10 t/s 9.38.437.883 I slot print_timing: id 2 | task 11811 | n_gen = 179, tg = 23.87 t/s, tg_3s = 26.08 t/s 9.39.013.760 I slot print_timing: id 1 | task 11324 | n_gen = 678, tg = 23.73 t/s, tg_3s = 26.07 t/s 9.39.857.709 I slot print_timing: id 0 | task 11849 | n_gen = 179, tg = 26.06 t/s, tg_3s = 26.05 t/s 9.40.853.896 I slot print_timing: id 3 | task 11794 | n_gen = 258, tg = 23.09 t/s, tg_3s = 26.06 t/s 9.41.469.775 I slot print_timing: id 2 | task 11811 | n_gen = 258, tg = 24.50 t/s, tg_3s = 26.06 t/s 9.42.046.354 I slot print_timing: id 1 | task 11324 | n_gen = 757, tg = 23.95 t/s, tg_3s = 26.05 t/s 9.42.892.920 I slot print_timing: id 0 | task 11849 | n_gen = 258, tg = 26.05 t/s, tg_3s = 26.03 t/s 9.43.861.649 I slot print_timing: id 3 | task 11794 | n_gen = 336, tg = 23.70 t/s, tg_3s = 25.93 t/s 9.44.480.709 I slot print_timing: id 2 | task 11811 | n_gen = 336, tg = 24.81 t/s, tg_3s = 25.91 t/s 9.45.059.196 I slot print_timing: id 1 | task 11324 | n_gen = 835, tg = 24.12 t/s, tg_3s = 25.89 t/s 9.45.908.093 I slot print_timing: id 0 | task 11849 | n_gen = 336, tg = 26.01 t/s, tg_3s = 25.87 t/s 9.46.872.229 I slot print_timing: id 3 | task 11794 | n_gen = 414, tg = 24.08 t/s, tg_3s = 25.91 t/s 9.47.488.031 I slot print_timing: id 2 | task 11811 | n_gen = 414, tg = 25.02 t/s, tg_3s = 25.94 t/s 9.47.645.344 I slot print_timing: id 1 | task 11324 | prompt eval time = 732.25 ms / 485 tokens ( 1.51 ms per token, 662.34 tokens per second) 9.47.645.349 I slot print_timing: id 1 | task 11324 | eval time = 37166.74 ms / 902 tokens ( 41.25 ms per token, 24.24 tokens per second) 9.47.645.350 I slot print_timing: id 1 | task 11324 | total time = 37899.00 ms / 1387 tokens 9.47.645.350 I slot print_timing: id 1 | task 11324 | graphs reused = 11542 9.47.645.351 I slot print_timing: id 1 | task 11324 | graph reallocs = 0 / 0 (same size) / (changed size) 9.47.645.460 I slot release: id 1 | task 11324 | stop processing: n_tokens = 2050, truncated = 0 9.47.686.529 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.521 9.47.686.566 I slot launch_slot_: id 1 | task 12233 | processing task, is_child = 0 9.48.932.709 I slot print_timing: id 0 | task 11849 | n_gen = 397, tg = 24.90 t/s, tg_3s = 20.17 t/s 9.49.899.455 I slot print_timing: id 3 | task 11794 | prompt eval time = 697.63 ms / 459 tokens ( 1.52 ms per token, 657.95 tokens per second) 9.49.899.462 I slot print_timing: id 3 | task 11794 | eval time = 20175.28 ms / 475 tokens ( 42.56 ms per token, 23.49 tokens per second) 9.49.899.463 I slot print_timing: id 3 | task 11794 | total time = 20872.90 ms / 934 tokens 9.49.899.463 I slot print_timing: id 3 | task 11794 | graphs reused = 11579 9.49.899.464 I slot print_timing: id 3 | task 11794 | graph reallocs = 0 / 0 (same size) / (changed size) 9.49.899.566 I slot release: id 3 | task 11794 | stop processing: n_tokens = 1629, truncated = 0 9.49.933.361 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.656 9.49.933.396 I slot launch_slot_: id 3 | task 12275 | processing task, is_child = 0 9.50.562.217 I slot print_timing: id 2 | task 11811 | n_gen = 461, tg = 23.49 t/s, tg_3s = 15.29 t/s 9.51.940.443 I slot print_timing: id 0 | task 11849 | n_gen = 459, tg = 24.22 t/s, tg_3s = 20.61 t/s 9.52.861.669 I slot print_timing: id 1 | task 12233 | n_gen = 100, tg = 22.34 t/s, tg_3s = 22.57 t/s 9.53.592.141 I slot print_timing: id 2 | task 11811 | n_gen = 539, tg = 23.79 t/s, tg_3s = 25.74 t/s 9.54.442.814 I slot print_timing: id 3 | task 12275 | n_gen = 100, tg = 25.96 t/s, tg_3s = 26.22 t/s 9.54.943.562 I slot print_timing: id 0 | task 11849 | n_gen = 537, tg = 24.46 t/s, tg_3s = 25.97 t/s 9.55.869.229 I slot print_timing: id 1 | task 12233 | n_gen = 178, tg = 23.80 t/s, tg_3s = 25.93 t/s 9.56.599.220 I slot print_timing: id 2 | task 11811 | n_gen = 617, tg = 24.05 t/s, tg_3s = 25.94 t/s 9.57.021.888 I slot print_timing: id 2 | task 11811 | prompt eval time = 715.89 ms / 471 tokens ( 1.52 ms per token, 657.92 tokens per second) 9.57.021.902 I slot print_timing: id 2 | task 11811 | eval time = 26041.24 ms / 628 tokens ( 41.53 ms per token, 24.08 tokens per second) 9.57.021.903 I slot print_timing: id 2 | task 11811 | total time = 26757.13 ms / 1099 tokens 9.57.021.903 I slot print_timing: id 2 | task 11811 | graphs reused = 11744 9.57.021.904 I slot print_timing: id 2 | task 11811 | graph reallocs = 0 / 0 (same size) / (changed size) 9.57.022.005 I slot release: id 2 | task 11811 | stop processing: n_tokens = 1785, truncated = 0 9.57.062.400 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.598 9.57.062.434 I slot launch_slot_: id 2 | task 12445 | processing task, is_child = 0 9.57.694.073 I slot print_timing: id 3 | task 12275 | n_gen = 169, tg = 23.78 t/s, tg_3s = 21.22 t/s 9.57.955.203 I slot print_timing: id 0 | task 11849 | n_gen = 599, tg = 23.99 t/s, tg_3s = 20.59 t/s 9.58.888.508 I slot print_timing: id 1 | task 12233 | n_gen = 240, tg = 22.85 t/s, tg_3s = 20.53 t/s 10.00.730.732 I slot print_timing: id 3 | task 12275 | n_gen = 247, tg = 24.35 t/s, tg_3s = 25.69 t/s 10.00.958.155 I slot print_timing: id 0 | task 11849 | n_gen = 677, tg = 24.20 t/s, tg_3s = 25.97 t/s 10.01.571.964 I slot print_timing: id 0 | task 11849 | prompt eval time = 700.82 ms / 483 tokens ( 1.45 ms per token, 689.20 tokens per second) 10.01.571.970 I slot print_timing: id 0 | task 11849 | eval time = 28544.29 ms / 693 tokens ( 41.25 ms per token, 24.24 tokens per second) 10.01.571.971 I slot print_timing: id 0 | task 11849 | total time = 29245.10 ms / 1176 tokens 10.01.571.972 I slot print_timing: id 0 | task 11849 | graphs reused = 11841 10.01.571.973 I slot print_timing: id 0 | task 11849 | graph reallocs = 0 / 0 (same size) / (changed size) 10.01.572.075 I slot release: id 0 | task 11849 | stop processing: n_tokens = 1870, truncated = 0 10.01.573.220 I slot print_timing: id 2 | task 12445 | n_gen = 100, tg = 26.00 t/s, tg_3s = 26.27 t/s 10.01.607.534 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.571 10.01.607.566 I slot launch_slot_: id 0 | task 12548 | processing task, is_child = 0 10.02.206.775 I slot print_timing: id 1 | task 12233 | n_gen = 312, tg = 22.58 t/s, tg_3s = 21.70 t/s 10.02.574.347 I slot print_timing: id 3 | task 12275 | prompt eval time = 695.26 ms / 456 tokens ( 1.52 ms per token, 655.87 tokens per second) 10.02.574.350 I slot print_timing: id 3 | task 12275 | eval time = 11945.69 ms / 280 tokens ( 42.82 ms per token, 23.36 tokens per second) 10.02.574.356 I slot print_timing: id 3 | task 12275 | total time = 12640.94 ms / 736 tokens 10.02.574.357 I slot print_timing: id 3 | task 12275 | graphs reused = 11849 10.02.574.358 I slot print_timing: id 3 | task 12275 | graph reallocs = 0 / 0 (same size) / (changed size) 10.02.574.451 I slot release: id 3 | task 12275 | stop processing: n_tokens = 1431, truncated = 0 10.02.607.497 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.746 10.02.607.536 I slot launch_slot_: id 3 | task 12560 | processing task, is_child = 0 10.04.600.184 I slot print_timing: id 2 | task 12445 | n_gen = 147, tg = 21.36 t/s, tg_3s = 15.53 t/s 10.05.215.083 I slot print_timing: id 1 | task 12233 | n_gen = 373, tg = 22.16 t/s, tg_3s = 20.28 t/s 10.06.716.358 I slot print_timing: id 0 | task 12548 | n_gen = 100, tg = 22.27 t/s, tg_3s = 22.50 t/s 10.07.143.403 I slot print_timing: id 3 | task 12560 | n_gen = 100, tg = 25.94 t/s, tg_3s = 26.20 t/s 10.07.604.473 I slot print_timing: id 2 | task 12445 | n_gen = 225, tg = 22.77 t/s, tg_3s = 25.96 t/s 10.08.219.886 I slot print_timing: id 1 | task 12233 | n_gen = 451, tg = 22.74 t/s, tg_3s = 25.96 t/s 10.09.721.629 I slot print_timing: id 0 | task 12548 | n_gen = 178, tg = 23.76 t/s, tg_3s = 25.95 t/s 10.10.146.211 I slot print_timing: id 3 | task 12560 | n_gen = 178, tg = 25.96 t/s, tg_3s = 25.98 t/s 10.10.607.860 I slot print_timing: id 2 | task 12445 | n_gen = 303, tg = 23.52 t/s, tg_3s = 25.97 t/s 10.11.225.584 I slot print_timing: id 1 | task 12233 | n_gen = 529, tg = 23.16 t/s, tg_3s = 25.95 t/s 10.12.729.232 I slot print_timing: id 0 | task 12548 | n_gen = 256, tg = 24.38 t/s, tg_3s = 25.93 t/s 10.13.154.751 I slot print_timing: id 3 | task 12560 | n_gen = 256, tg = 25.95 t/s, tg_3s = 25.93 t/s 10.13.617.236 I slot print_timing: id 2 | task 12445 | n_gen = 381, tg = 23.97 t/s, tg_3s = 25.92 t/s 10.14.234.304 I slot print_timing: id 1 | task 12233 | n_gen = 607, tg = 23.49 t/s, tg_3s = 25.92 t/s 10.15.739.177 I slot print_timing: id 0 | task 12548 | n_gen = 334, tg = 24.73 t/s, tg_3s = 25.91 t/s 10.16.167.513 I slot print_timing: id 3 | task 12560 | n_gen = 334, tg = 25.93 t/s, tg_3s = 25.89 t/s 10.16.630.798 I slot print_timing: id 2 | task 12445 | n_gen = 459, tg = 24.28 t/s, tg_3s = 25.88 t/s 10.17.170.446 I slot print_timing: id 2 | task 12445 | prompt eval time = 703.80 ms / 455 tokens ( 1.55 ms per token, 646.49 tokens per second) 10.17.170.454 I slot print_timing: id 2 | task 12445 | eval time = 19404.20 ms / 473 tokens ( 41.11 ms per token, 24.32 tokens per second) 10.17.170.454 I slot print_timing: id 2 | task 12445 | total time = 20108.00 ms / 928 tokens 10.17.170.455 I slot print_timing: id 2 | task 12445 | graphs reused = 12205 10.17.170.456 I slot print_timing: id 2 | task 12445 | graph reallocs = 0 / 0 (same size) / (changed size) 10.17.170.573 I slot release: id 2 | task 12445 | stop processing: n_tokens = 1614, truncated = 0 10.17.211.115 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.662 10.17.211.158 I slot launch_slot_: id 2 | task 12923 | processing task, is_child = 0 10.17.292.667 I slot print_timing: id 1 | task 12233 | n_gen = 685, tg = 23.70 t/s, tg_3s = 25.50 t/s 10.18.747.049 I slot print_timing: id 0 | task 12548 | n_gen = 393, tg = 23.79 t/s, tg_3s = 19.62 t/s 10.19.172.559 I slot print_timing: id 3 | task 12560 | n_gen = 393, tg = 24.74 t/s, tg_3s = 19.63 t/s 10.20.292.880 I slot print_timing: id 1 | task 12233 | n_gen = 745, tg = 23.35 t/s, tg_3s = 20.00 t/s 10.21.763.227 I slot print_timing: id 0 | task 12548 | n_gen = 471, tg = 24.11 t/s, tg_3s = 25.86 t/s 10.21.880.788 I slot print_timing: id 2 | task 12923 | n_gen = 100, tg = 25.86 t/s, tg_3s = 26.12 t/s 10.22.191.798 I slot print_timing: id 3 | task 12560 | n_gen = 471, tg = 24.91 t/s, tg_3s = 25.83 t/s 10.23.310.309 I slot print_timing: id 1 | task 12233 | n_gen = 823, tg = 23.57 t/s, tg_3s = 25.85 t/s 10.24.779.813 I slot print_timing: id 0 | task 12548 | n_gen = 549, tg = 24.35 t/s, tg_3s = 25.86 t/s 10.24.896.823 I slot print_timing: id 2 | task 12923 | n_gen = 178, tg = 25.86 t/s, tg_3s = 25.86 t/s 10.25.208.892 I slot print_timing: id 3 | task 12560 | n_gen = 549, tg = 25.04 t/s, tg_3s = 25.85 t/s 10.26.332.647 I slot print_timing: id 1 | task 12233 | n_gen = 901, tg = 23.75 t/s, tg_3s = 25.81 t/s 10.27.803.360 I slot print_timing: id 0 | task 12548 | n_gen = 627, tg = 24.52 t/s, tg_3s = 25.80 t/s 10.27.920.332 I slot print_timing: id 2 | task 12923 | n_gen = 256, tg = 25.84 t/s, tg_3s = 25.80 t/s 10.28.230.773 I slot print_timing: id 3 | task 12560 | n_gen = 627, tg = 25.14 t/s, tg_3s = 25.81 t/s 10.29.353.943 I slot print_timing: id 1 | task 12233 | n_gen = 979, tg = 23.90 t/s, tg_3s = 25.82 t/s 10.29.392.955 I slot print_timing: id 1 | task 12233 | prompt eval time = 744.14 ms / 494 tokens ( 1.51 ms per token, 663.85 tokens per second) 10.29.392.958 I slot print_timing: id 1 | task 12233 | eval time = 40962.24 ms / 980 tokens ( 41.84 ms per token, 23.90 tokens per second) 10.29.392.959 I slot print_timing: id 1 | task 12233 | total time = 41706.38 ms / 1474 tokens 10.29.392.960 I slot print_timing: id 1 | task 12233 | graphs reused = 12496 10.29.392.961 I slot print_timing: id 1 | task 12233 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.393.079 I slot release: id 1 | task 12233 | stop processing: n_tokens = 2137, truncated = 0 10.29.433.552 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.500 10.29.439.846 I slot launch_slot_: id 1 | task 13221 | processing task, is_child = 0 10.30.803.450 I slot print_timing: id 0 | task 12548 | n_gen = 687, tg = 24.04 t/s, tg_3s = 20.00 t/s 10.30.958.424 I slot print_timing: id 2 | task 12923 | n_gen = 317, tg = 24.48 t/s, tg_3s = 20.08 t/s 10.31.266.354 I slot print_timing: id 3 | task 12560 | n_gen = 688, tg = 24.59 t/s, tg_3s = 20.09 t/s 10.33.812.711 I slot print_timing: id 0 | task 12548 | n_gen = 765, tg = 24.22 t/s, tg_3s = 25.92 t/s 10.33.968.754 I slot print_timing: id 2 | task 12923 | n_gen = 395, tg = 24.75 t/s, tg_3s = 25.91 t/s 10.34.007.025 I slot print_timing: id 1 | task 13221 | n_gen = 100, tg = 25.90 t/s, tg_3s = 26.16 t/s 10.34.277.869 I slot print_timing: id 3 | task 12560 | n_gen = 766, tg = 24.72 t/s, tg_3s = 25.90 t/s 10.36.830.689 I slot print_timing: id 0 | task 12548 | n_gen = 843, tg = 24.36 t/s, tg_3s = 25.85 t/s 10.36.985.544 I slot print_timing: id 2 | task 12923 | n_gen = 473, tg = 24.93 t/s, tg_3s = 25.86 t/s 10.37.023.312 I slot print_timing: id 1 | task 13221 | n_gen = 178, tg = 25.88 t/s, tg_3s = 25.86 t/s 10.37.294.630 I slot print_timing: id 3 | task 12560 | n_gen = 844, tg = 24.82 t/s, tg_3s = 25.86 t/s 10.39.851.628 I slot print_timing: id 0 | task 12548 | n_gen = 921, tg = 24.48 t/s, tg_3s = 25.82 t/s 10.40.008.126 I slot print_timing: id 2 | task 12923 | n_gen = 551, tg = 25.05 t/s, tg_3s = 25.81 t/s 10.40.046.397 I slot print_timing: id 1 | task 13221 | n_gen = 256, tg = 25.86 t/s, tg_3s = 25.80 t/s 10.40.317.520 I slot print_timing: id 3 | task 12560 | n_gen = 922, tg = 24.90 t/s, tg_3s = 25.80 t/s 10.42.013.776 I slot print_timing: id 3 | task 12560 | prompt eval time = 719.36 ms / 471 tokens ( 1.53 ms per token, 654.75 tokens per second) 10.42.013.784 I slot print_timing: id 3 | task 12560 | eval time = 38686.87 ms / 966 tokens ( 40.09 ms per token, 24.94 tokens per second) 10.42.013.785 I slot print_timing: id 3 | task 12560 | total time = 39406.23 ms / 1437 tokens 10.42.013.785 I slot print_timing: id 3 | task 12560 | graphs reused = 12800 10.42.013.786 I slot print_timing: id 3 | task 12560 | graph reallocs = 0 / 0 (same size) / (changed size) 10.42.013.898 I slot release: id 3 | task 12560 | stop processing: n_tokens = 2132, truncated = 0 10.42.047.959 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.501 10.42.048.005 I slot launch_slot_: id 3 | task 13531 | processing task, is_child = 0 10.42.879.193 I slot print_timing: id 0 | task 12548 | n_gen = 984, tg = 24.21 t/s, tg_3s = 20.81 t/s 10.43.032.553 I slot print_timing: id 2 | task 12923 | n_gen = 614, tg = 24.54 t/s, tg_3s = 20.83 t/s 10.43.072.369 I slot print_timing: id 1 | task 13221 | n_gen = 319, tg = 24.67 t/s, tg_3s = 20.82 t/s 10.44.435.289 I slot print_timing: id 0 | task 12548 | prompt eval time = 663.89 ms / 443 tokens ( 1.50 ms per token, 667.28 tokens per second) 10.44.435.296 I slot print_timing: id 0 | task 12548 | eval time = 42163.82 ms / 1024 tokens ( 41.22 ms per token, 24.26 tokens per second) 10.44.435.298 I slot print_timing: id 0 | task 12548 | total time = 42827.71 ms / 1467 tokens 10.44.435.299 I slot print_timing: id 0 | task 12548 | graphs reused = 12843 10.44.435.300 I slot print_timing: id 0 | task 12548 | graph reallocs = 0 / 0 (same size) / (changed size) 10.44.435.402 I slot release: id 0 | task 12548 | stop processing: n_tokens = 2161, truncated = 0 10.44.470.900 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.494 10.44.476.513 I slot launch_slot_: id 0 | task 13579 | processing task, is_child = 0 10.46.045.614 I slot print_timing: id 2 | task 12923 | n_gen = 676, tg = 24.11 t/s, tg_3s = 20.58 t/s 10.46.083.700 I slot print_timing: id 1 | task 13221 | n_gen = 381, tg = 23.90 t/s, tg_3s = 20.59 t/s 10.47.163.476 I slot print_timing: id 3 | task 13531 | n_gen = 100, tg = 22.31 t/s, tg_3s = 22.54 t/s 10.48.972.098 I slot print_timing: id 0 | task 13579 | n_gen = 100, tg = 25.95 t/s, tg_3s = 26.21 t/s 10.49.050.575 I slot print_timing: id 2 | task 12923 | n_gen = 754, tg = 24.29 t/s, tg_3s = 25.96 t/s 10.49.088.786 I slot print_timing: id 1 | task 13221 | n_gen = 459, tg = 24.23 t/s, tg_3s = 25.96 t/s 10.50.171.221 I slot print_timing: id 3 | task 13531 | n_gen = 178, tg = 23.78 t/s, tg_3s = 25.93 t/s 10.51.982.684 I slot print_timing: id 0 | task 13579 | n_gen = 178, tg = 25.93 t/s, tg_3s = 25.91 t/s 10.52.060.768 I slot print_timing: id 2 | task 12923 | n_gen = 832, tg = 24.44 t/s, tg_3s = 25.91 t/s 10.52.098.839 I slot print_timing: id 1 | task 13221 | n_gen = 537, tg = 24.46 t/s, tg_3s = 25.91 t/s 10.53.185.349 I slot print_timing: id 3 | task 13531 | n_gen = 256, tg = 24.38 t/s, tg_3s = 25.88 t/s 10.54.999.476 I slot print_timing: id 0 | task 13579 | n_gen = 256, tg = 25.91 t/s, tg_3s = 25.86 t/s 10.55.077.464 I slot print_timing: id 2 | task 12923 | n_gen = 910, tg = 24.55 t/s, tg_3s = 25.86 t/s 10.55.115.544 I slot print_timing: id 1 | task 13221 | n_gen = 615, tg = 24.63 t/s, tg_3s = 25.86 t/s 10.56.200.416 I slot print_timing: id 3 | task 13531 | n_gen = 334, tg = 24.71 t/s, tg_3s = 25.87 t/s 10.58.023.776 I slot print_timing: id 0 | task 13579 | n_gen = 334, tg = 25.88 t/s, tg_3s = 25.79 t/s 10.58.102.341 I slot print_timing: id 2 | task 12923 | n_gen = 988, tg = 24.64 t/s, tg_3s = 25.79 t/s 10.58.140.211 I slot print_timing: id 1 | task 13221 | n_gen = 693, tg = 24.75 t/s, tg_3s = 25.79 t/s 10.59.106.140 I slot print_timing: id 3 | task 13531 | prompt eval time = 678.54 ms / 448 tokens ( 1.51 ms per token, 660.24 tokens per second) 10.59.106.149 I slot print_timing: id 3 | task 13531 | eval time = 16379.58 ms / 409 tokens ( 40.15 ms per token, 24.91 tokens per second) 10.59.106.149 I slot print_timing: id 3 | task 13531 | total time = 17058.12 ms / 857 tokens 10.59.106.150 I slot print_timing: id 3 | task 13531 | graphs reused = 13203 10.59.106.151 I slot print_timing: id 3 | task 13531 | graph reallocs = 0 / 0 (same size) / (changed size) 10.59.106.256 I slot release: id 3 | task 13531 | stop processing: n_tokens = 1552, truncated = 0 10.59.139.913 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.688 10.59.139.940 I slot launch_slot_: id 3 | task 13944 | processing task, is_child = 0 11.00.121.925 I slot print_timing: id 2 | task 12923 | prompt eval time = 841.10 ms / 522 tokens ( 1.61 ms per token, 620.62 tokens per second) 11.00.121.934 I slot print_timing: id 2 | task 12923 | eval time = 42069.66 ms / 1024 tokens ( 41.12 ms per token, 24.32 tokens per second) 11.00.121.939 I slot print_timing: id 2 | task 12923 | total time = 42910.75 ms / 1546 tokens 11.00.121.940 I slot print_timing: id 2 | task 12923 | graphs reused = 13209 11.00.121.941 I slot print_timing: id 2 | task 12923 | graph reallocs = 0 / 0 (same size) / (changed size) 11.00.122.097 I slot release: id 2 | task 12923 | stop processing: n_tokens = 2232, truncated = 0 11.00.169.635 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.478 11.00.177.614 I slot launch_slot_: id 2 | task 13955 | processing task, is_child = 0 11.01.037.451 I slot print_timing: id 0 | task 13579 | n_gen = 379, tg = 23.80 t/s, tg_3s = 14.93 t/s 11.01.153.061 I slot print_timing: id 1 | task 13221 | n_gen = 738, tg = 23.80 t/s, tg_3s = 14.94 t/s 11.01.806.147 I slot print_timing: id 1 | task 13221 | prompt eval time = 744.10 ms / 494 tokens ( 1.51 ms per token, 663.89 tokens per second) 11.01.806.151 I slot print_timing: id 1 | task 13221 | eval time = 31622.19 ms / 755 tokens ( 41.94 ms per token, 23.84 tokens per second) 11.01.806.152 I slot print_timing: id 1 | task 13221 | total time = 32366.29 ms / 1249 tokens 11.01.806.153 I slot print_timing: id 1 | task 13221 | graphs reused = 13232 11.01.806.153 I slot print_timing: id 1 | task 13221 | graph reallocs = 0 / 0 (same size) / (changed size) 11.01.806.252 I slot release: id 1 | task 13221 | stop processing: n_tokens = 1912, truncated = 0 11.01.847.065 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.559 11.01.847.107 I slot launch_slot_: id 1 | task 13983 | processing task, is_child = 0 11.04.060.936 I slot print_timing: id 0 | task 13579 | n_gen = 440, tg = 23.22 t/s, tg_3s = 20.18 t/s 11.04.986.333 I slot print_timing: id 3 | task 13944 | n_gen = 100, tg = 19.28 t/s, tg_3s = 19.48 t/s 11.05.371.098 I slot print_timing: id 2 | task 13955 | n_gen = 100, tg = 22.07 t/s, tg_3s = 22.30 t/s 11.06.408.492 I slot print_timing: id 1 | task 13983 | n_gen = 100, tg = 25.94 t/s, tg_3s = 26.20 t/s 11.07.099.322 I slot print_timing: id 0 | task 13579 | n_gen = 519, tg = 23.61 t/s, tg_3s = 26.00 t/s 11.08.021.142 I slot print_timing: id 3 | task 13944 | n_gen = 179, tg = 21.79 t/s, tg_3s = 26.03 t/s 11.08.402.161 I slot print_timing: id 2 | task 13955 | n_gen = 179, tg = 23.68 t/s, tg_3s = 26.06 t/s 11.09.438.339 I slot print_timing: id 1 | task 13983 | n_gen = 179, tg = 26.00 t/s, tg_3s = 26.07 t/s 11.10.131.872 I slot print_timing: id 0 | task 13579 | n_gen = 598, tg = 23.90 t/s, tg_3s = 26.05 t/s 11.11.058.439 I slot print_timing: id 3 | task 13944 | n_gen = 258, tg = 22.93 t/s, tg_3s = 26.01 t/s 11.11.095.170 I slot print_timing: id 0 | task 13579 | prompt eval time = 680.91 ms / 455 tokens ( 1.50 ms per token, 668.23 tokens per second) 11.11.095.173 I slot print_timing: id 0 | task 13579 | eval time = 25937.74 ms / 623 tokens ( 41.70 ms per token, 23.98 tokens per second) 11.11.095.174 I slot print_timing: id 0 | task 13579 | total time = 26618.65 ms / 1078 tokens 11.11.095.175 I slot print_timing: id 0 | task 13579 | graphs reused = 13452 11.11.095.176 I slot print_timing: id 0 | task 13579 | graph reallocs = 0 / 0 (same size) / (changed size) 11.11.095.278 I slot release: id 0 | task 13579 | stop processing: n_tokens = 1772, truncated = 0 11.11.130.426 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.603 11.11.130.455 I slot launch_slot_: id 0 | task 14208 | processing task, is_child = 0 11.11.756.976 I slot print_timing: id 2 | task 13955 | n_gen = 251, tg = 23.00 t/s, tg_3s = 21.46 t/s 11.12.476.619 I slot print_timing: id 1 | task 13983 | n_gen = 242, tg = 24.38 t/s, tg_3s = 20.74 t/s 11.14.094.539 I slot print_timing: id 3 | task 13944 | n_gen = 321, tg = 22.47 t/s, tg_3s = 20.75 t/s 11.14.786.728 I slot print_timing: id 2 | task 13955 | n_gen = 329, tg = 23.60 t/s, tg_3s = 25.74 t/s 11.15.478.058 I slot print_timing: id 1 | task 13983 | n_gen = 320, tg = 24.76 t/s, tg_3s = 25.99 t/s 11.15.557.753 I slot print_timing: id 2 | task 13955 | prompt eval time = 708.31 ms / 457 tokens ( 1.55 ms per token, 645.20 tokens per second) 11.15.557.757 I slot print_timing: id 2 | task 13955 | eval time = 14671.80 ms / 349 tokens ( 42.16 ms per token, 23.72 tokens per second) 11.15.557.758 I slot print_timing: id 2 | task 13955 | total time = 15380.11 ms / 806 tokens 11.15.557.759 I slot print_timing: id 2 | task 13955 | graphs reused = 13548 11.15.557.759 I slot print_timing: id 2 | task 13955 | graph reallocs = 0 / 0 (same size) / (changed size) 11.15.557.860 I slot release: id 2 | task 13955 | stop processing: n_tokens = 1498, truncated = 0 11.15.597.612 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.713 11.15.597.659 I slot launch_slot_: id 2 | task 14309 | processing task, is_child = 0 11.16.238.180 I slot print_timing: id 0 | task 14208 | n_gen = 100, tg = 22.41 t/s, tg_3s = 22.64 t/s 11.17.116.908 I slot print_timing: id 3 | task 13944 | n_gen = 383, tg = 22.13 t/s, tg_3s = 20.51 t/s 11.18.497.109 I slot print_timing: id 1 | task 13983 | n_gen = 382, tg = 23.96 t/s, tg_3s = 20.54 t/s 11.19.266.028 I slot print_timing: id 0 | task 14208 | n_gen = 178, tg = 23.77 t/s, tg_3s = 25.76 t/s 11.20.115.168 I slot print_timing: id 2 | task 14309 | n_gen = 100, tg = 26.02 t/s, tg_3s = 26.28 t/s 11.20.154.404 I slot print_timing: id 3 | task 13944 | n_gen = 462, tg = 22.71 t/s, tg_3s = 26.01 t/s 11.21.502.204 I slot print_timing: id 1 | task 13983 | n_gen = 460, tg = 24.27 t/s, tg_3s = 25.96 t/s 11.22.269.561 I slot print_timing: id 0 | task 14208 | n_gen = 256, tg = 24.41 t/s, tg_3s = 25.97 t/s 11.23.152.267 I slot print_timing: id 2 | task 14309 | n_gen = 179, tg = 26.02 t/s, tg_3s = 26.01 t/s 11.23.191.115 I slot print_timing: id 3 | task 13944 | n_gen = 541, tg = 23.14 t/s, tg_3s = 26.01 t/s 11.24.534.662 I slot print_timing: id 1 | task 13983 | n_gen = 539, tg = 24.52 t/s, tg_3s = 26.05 t/s 11.25.304.796 I slot print_timing: id 0 | task 14208 | n_gen = 335, tg = 24.77 t/s, tg_3s = 26.03 t/s 11.26.159.764 I slot print_timing: id 2 | task 14309 | n_gen = 257, tg = 25.99 t/s, tg_3s = 25.94 t/s 11.26.198.607 I slot print_timing: id 3 | task 13944 | n_gen = 619, tg = 23.46 t/s, tg_3s = 25.94 t/s 11.27.548.511 I slot print_timing: id 1 | task 13983 | n_gen = 617, tg = 24.68 t/s, tg_3s = 25.88 t/s 11.28.320.659 I slot print_timing: id 0 | task 14208 | n_gen = 413, tg = 24.97 t/s, tg_3s = 25.86 t/s 11.28.937.599 I slot print_timing: id 1 | task 13983 | prompt eval time = 745.21 ms / 496 tokens ( 1.50 ms per token, 665.58 tokens per second) 11.28.937.606 I slot print_timing: id 1 | task 13983 | eval time = 26345.27 ms / 653 tokens ( 40.41 ms per token, 24.75 tokens per second) 11.28.937.607 I slot print_timing: id 1 | task 13983 | total time = 27090.48 ms / 1149 tokens 11.28.937.608 I slot print_timing: id 1 | task 13983 | graphs reused = 13874 11.28.937.609 I slot print_timing: id 1 | task 13983 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.937.736 I slot release: id 1 | task 13983 | stop processing: n_tokens = 1812, truncated = 0 11.28.978.323 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.589 11.28.978.359 I slot launch_slot_: id 1 | task 14641 | processing task, is_child = 0 11.29.629.133 I slot print_timing: id 2 | task 14309 | n_gen = 331, tg = 24.78 t/s, tg_3s = 21.33 t/s 11.29.629.405 I slot print_timing: id 3 | task 13944 | n_gen = 692, tg = 23.21 t/s, tg_3s = 21.28 t/s 11.31.330.389 I slot print_timing: id 0 | task 14208 | n_gen = 474, tg = 24.24 t/s, tg_3s = 20.27 t/s 11.32.643.678 I slot print_timing: id 2 | task 14309 | n_gen = 408, tg = 24.92 t/s, tg_3s = 25.54 t/s 11.32.644.232 I slot print_timing: id 3 | task 13944 | n_gen = 769, tg = 23.42 t/s, tg_3s = 25.54 t/s 11.33.528.303 I slot print_timing: id 1 | task 14641 | n_gen = 100, tg = 25.88 t/s, tg_3s = 26.14 t/s 11.33.876.630 I slot print_timing: id 0 | task 14208 | prompt eval time = 690.69 ms / 467 tokens ( 1.48 ms per token, 676.14 tokens per second) 11.33.876.636 I slot print_timing: id 0 | task 14208 | eval time = 22055.48 ms / 540 tokens ( 40.92 ms per token, 24.44 tokens per second) 11.33.876.637 I slot print_timing: id 0 | task 14208 | total time = 22746.17 ms / 1007 tokens 11.33.876.638 I slot print_timing: id 0 | task 14208 | graphs reused = 13981 11.33.876.639 I slot print_timing: id 0 | task 14208 | graph reallocs = 0 / 0 (same size) / (changed size) 11.33.876.747 I slot release: id 0 | task 14208 | stop processing: n_tokens = 1701, truncated = 0 11.33.911.847 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.628 11.33.911.880 I slot launch_slot_: id 0 | task 14753 | processing task, is_child = 0 11.35.652.556 I slot print_timing: id 2 | task 14309 | n_gen = 470, tg = 24.25 t/s, tg_3s = 20.61 t/s 11.35.653.085 I slot print_timing: id 3 | task 13944 | n_gen = 831, tg = 23.18 t/s, tg_3s = 20.61 t/s 11.36.538.120 I slot print_timing: id 1 | task 14641 | n_gen = 162, tg = 23.55 t/s, tg_3s = 20.60 t/s 11.38.429.980 I slot print_timing: id 0 | task 14753 | n_gen = 100, tg = 25.87 t/s, tg_3s = 26.13 t/s 11.38.660.759 I slot print_timing: id 2 | task 14309 | n_gen = 548, tg = 24.47 t/s, tg_3s = 25.93 t/s 11.38.661.202 I slot print_timing: id 3 | task 13944 | n_gen = 909, tg = 23.40 t/s, tg_3s = 25.93 t/s 11.39.548.801 I slot print_timing: id 1 | task 14641 | n_gen = 240, tg = 24.27 t/s, tg_3s = 25.91 t/s 11.40.560.950 I slot print_timing: id 2 | task 14309 | prompt eval time = 712.83 ms / 469 tokens ( 1.52 ms per token, 657.94 tokens per second) 11.40.560.957 I slot print_timing: id 2 | task 14309 | eval time = 24250.45 ms / 597 tokens ( 40.69 ms per token, 24.58 tokens per second) 11.40.560.958 I slot print_timing: id 2 | task 14309 | total time = 24963.28 ms / 1066 tokens 11.40.560.958 I slot print_timing: id 2 | task 14309 | graphs reused = 14134 11.40.560.959 I slot print_timing: id 2 | task 14309 | graph reallocs = 0 / 0 (same size) / (changed size) 11.40.561.065 I slot release: id 2 | task 14309 | stop processing: n_tokens = 1758, truncated = 0 11.40.601.779 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.608 11.40.601.821 I slot launch_slot_: id 2 | task 14911 | processing task, is_child = 0 11.41.463.416 I slot print_timing: id 0 | task 14753 | n_gen = 162, tg = 23.47 t/s, tg_3s = 20.44 t/s 11.41.664.370 I slot print_timing: id 3 | task 13944 | n_gen = 970, tg = 23.18 t/s, tg_3s = 20.31 t/s 11.42.556.508 I slot print_timing: id 1 | task 14641 | n_gen = 301, tg = 23.34 t/s, tg_3s = 20.28 t/s 11.43.754.368 I slot print_timing: id 3 | task 13944 | prompt eval time = 712.43 ms / 483 tokens ( 1.48 ms per token, 677.96 tokens per second) 11.43.754.376 I slot print_timing: id 3 | task 13944 | eval time = 43901.99 ms / 1024 tokens ( 42.91 ms per token, 23.30 tokens per second) 11.43.754.377 I slot print_timing: id 3 | task 13944 | total time = 44614.42 ms / 1507 tokens 11.43.754.377 I slot print_timing: id 3 | task 13944 | graphs reused = 14196 11.43.754.378 I slot print_timing: id 3 | task 13944 | graph reallocs = 0 / 0 (same size) / (changed size) 11.43.754.480 I slot release: id 3 | task 13944 | stop processing: n_tokens = 2202, truncated = 0 11.43.787.786 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.485 11.43.793.670 I slot launch_slot_: id 3 | task 14978 | processing task, is_child = 0 11.44.470.565 I slot print_timing: id 0 | task 14753 | n_gen = 224, tg = 22.60 t/s, tg_3s = 20.62 t/s 11.45.592.874 I slot print_timing: id 1 | task 14641 | n_gen = 364, tg = 22.84 t/s, tg_3s = 20.75 t/s 11.45.747.864 I slot print_timing: id 2 | task 14911 | n_gen = 100, tg = 22.31 t/s, tg_3s = 22.54 t/s 11.47.481.488 I slot print_timing: id 0 | task 14753 | n_gen = 302, tg = 23.37 t/s, tg_3s = 25.91 t/s 11.48.292.895 I slot print_timing: id 3 | task 14978 | n_gen = 100, tg = 25.91 t/s, tg_3s = 26.17 t/s 11.48.330.373 I slot print_timing: id 1 | task 14641 | prompt eval time = 724.23 ms / 481 tokens ( 1.51 ms per token, 664.15 tokens per second) 11.48.330.376 I slot print_timing: id 1 | task 14641 | eval time = 18627.77 ms / 435 tokens ( 42.92 ms per token, 23.30 tokens per second) 11.48.330.377 I slot print_timing: id 1 | task 14641 | total time = 19352.01 ms / 916 tokens 11.48.330.378 I slot print_timing: id 1 | task 14641 | graphs reused = 14294 11.48.330.379 I slot print_timing: id 1 | task 14641 | graph reallocs = 0 / 0 (same size) / (changed size) 11.48.330.486 I slot release: id 1 | task 14641 | stop processing: n_tokens = 1579, truncated = 0 11.48.371.464 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.676 11.48.371.498 I slot launch_slot_: id 1 | task 15082 | processing task, is_child = 0 11.49.017.949 I slot print_timing: id 2 | task 14911 | n_gen = 169, tg = 21.80 t/s, tg_3s = 21.10 t/s 11.50.518.541 I slot print_timing: id 0 | task 14753 | n_gen = 364, tg = 22.81 t/s, tg_3s = 20.41 t/s 11.51.330.638 I slot print_timing: id 3 | task 14978 | n_gen = 162, tg = 23.47 t/s, tg_3s = 20.41 t/s 11.52.021.197 I slot print_timing: id 2 | task 14911 | n_gen = 246, tg = 22.88 t/s, tg_3s = 25.64 t/s 11.52.903.425 I slot print_timing: id 1 | task 15082 | n_gen = 100, tg = 25.97 t/s, tg_3s = 26.23 t/s 11.53.556.180 I slot print_timing: id 0 | task 14753 | n_gen = 443, tg = 23.32 t/s, tg_3s = 26.01 t/s 11.54.363.968 I slot print_timing: id 3 | task 14978 | n_gen = 241, tg = 24.26 t/s, tg_3s = 26.04 t/s 11.55.052.642 I slot print_timing: id 2 | task 14911 | n_gen = 325, tg = 23.58 t/s, tg_3s = 26.06 t/s 11.55.936.901 I slot print_timing: id 1 | task 15082 | n_gen = 179, tg = 26.00 t/s, tg_3s = 26.04 t/s 11.56.591.057 I slot print_timing: id 0 | task 14753 | n_gen = 522, tg = 23.70 t/s, tg_3s = 26.03 t/s 11.57.400.332 I slot print_timing: id 3 | task 14978 | n_gen = 320, tg = 24.67 t/s, tg_3s = 26.02 t/s 11.58.058.185 I slot print_timing: id 2 | task 14911 | n_gen = 403, tg = 24.00 t/s, tg_3s = 25.95 t/s 11.58.945.438 I slot print_timing: id 1 | task 15082 | n_gen = 257, tg = 25.98 t/s, tg_3s = 25.93 t/s 11.59.596.951 I slot print_timing: id 0 | task 14753 | n_gen = 600, tg = 23.97 t/s, tg_3s = 25.95 t/s 11.59.751.708 I slot print_timing: id 2 | task 14911 | prompt eval time = 709.08 ms / 459 tokens ( 1.54 ms per token, 647.32 tokens per second) 11.59.751.716 I slot print_timing: id 2 | task 14911 | eval time = 18440.80 ms / 447 tokens ( 41.35 ms per token, 24.19 tokens per second) 11.59.751.717 I slot print_timing: id 2 | task 14911 | total time = 19149.88 ms / 906 tokens 11.59.751.718 I slot print_timing: id 2 | task 14911 | graphs reused = 14569 11.59.751.718 I slot print_timing: id 2 | task 14911 | graph reallocs = 0 / 0 (same size) / (changed size) 11.59.751.837 I slot release: id 2 | task 14911 | stop processing: n_tokens = 1598, truncated = 0 11.59.792.690 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.668 11.59.792.724 I slot launch_slot_: id 2 | task 15363 | processing task, is_child = 0 12.00.474.907 I slot print_timing: id 3 | task 14978 | n_gen = 383, tg = 23.87 t/s, tg_3s = 20.49 t/s 12.00.774.267 I slot print_timing: id 1 | task 15082 | prompt eval time = 719.81 ms / 475 tokens ( 1.52 ms per token, 659.90 tokens per second) 12.00.774.274 I slot print_timing: id 1 | task 15082 | eval time = 11682.95 ms / 287 tokens ( 40.85 ms per token, 24.48 tokens per second) 12.00.774.275 I slot print_timing: id 1 | task 15082 | total time = 12402.76 ms / 762 tokens 12.00.774.276 I slot print_timing: id 1 | task 15082 | graphs reused = 14574 12.00.774.277 I slot print_timing: id 1 | task 15082 | graph reallocs = 0 / 0 (same size) / (changed size) 12.00.774.421 I slot release: id 1 | task 15082 | stop processing: n_tokens = 1425, truncated = 0 12.00.817.267 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.749 12.00.817.309 I slot launch_slot_: id 1 | task 15373 | processing task, is_child = 0 12.02.381.573 I slot print_timing: id 3 | task 14978 | prompt eval time = 677.68 ms / 446 tokens ( 1.52 ms per token, 658.12 tokens per second) 12.02.381.579 I slot print_timing: id 3 | task 14978 | eval time = 17910.21 ms / 414 tokens ( 43.37 ms per token, 23.06 tokens per second) 12.02.381.580 I slot print_timing: id 3 | task 14978 | total time = 18587.89 ms / 860 tokens 12.02.381.580 I slot print_timing: id 3 | task 14978 | graphs reused = 14593 12.02.381.581 I slot print_timing: id 3 | task 14978 | graph reallocs = 0 / 0 (same size) / (changed size) 12.02.381.692 I slot release: id 3 | task 14978 | stop processing: n_tokens = 1555, truncated = 0 12.02.415.157 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.687 12.02.415.186 I slot launch_slot_: id 3 | task 15398 | processing task, is_child = 0 12.03.048.147 I slot print_timing: id 0 | task 14753 | n_gen = 639, tg = 22.43 t/s, tg_3s = 11.30 t/s 12.03.191.470 I slot print_timing: id 0 | task 14753 | prompt eval time = 691.48 ms / 467 tokens ( 1.48 ms per token, 675.37 tokens per second) 12.03.191.476 I slot print_timing: id 0 | task 14753 | eval time = 28588.11 ms / 642 tokens ( 44.60 ms per token, 22.42 tokens per second) 12.03.191.477 I slot print_timing: id 0 | task 14753 | total time = 29279.58 ms / 1109 tokens 12.03.191.478 I slot print_timing: id 0 | task 14753 | graphs reused = 14594 12.03.191.478 I slot print_timing: id 0 | task 14753 | graph reallocs = 0 / 0 (same size) / (changed size) 12.03.191.537 I slot release: id 0 | task 14753 | stop processing: n_tokens = 1803, truncated = 0 12.03.224.383 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.592 12.03.224.404 I slot launch_slot_: id 0 | task 15404 | processing task, is_child = 0 12.06.238.437 I slot print_timing: id 2 | task 15363 | n_gen = 100, tg = 17.39 t/s, tg_3s = 17.57 t/s 12.06.583.040 I slot print_timing: id 1 | task 15373 | n_gen = 100, tg = 19.72 t/s, tg_3s = 19.92 t/s 12.07.503.407 I slot print_timing: id 3 | task 15398 | n_gen = 100, tg = 22.56 t/s, tg_3s = 22.79 t/s 12.07.693.854 I slot print_timing: id 0 | task 15404 | n_gen = 100, tg = 26.03 t/s, tg_3s = 26.30 t/s 12.09.270.475 I slot print_timing: id 2 | task 15363 | n_gen = 179, tg = 20.40 t/s, tg_3s = 26.06 t/s 12.09.616.316 I slot print_timing: id 1 | task 15373 | n_gen = 179, tg = 22.10 t/s, tg_3s = 26.04 t/s 12.10.505.953 I slot print_timing: id 3 | task 15398 | n_gen = 178, tg = 23.95 t/s, tg_3s = 25.98 t/s 12.10.695.130 I slot print_timing: id 0 | task 15404 | n_gen = 178, tg = 26.01 t/s, tg_3s = 25.99 t/s 12.12.274.113 I slot print_timing: id 2 | task 15363 | n_gen = 257, tg = 21.83 t/s, tg_3s = 25.97 t/s 12.12.620.281 I slot print_timing: id 1 | task 15373 | n_gen = 257, tg = 23.15 t/s, tg_3s = 25.97 t/s 12.13.543.223 I slot print_timing: id 3 | task 15398 | n_gen = 257, tg = 24.55 t/s, tg_3s = 26.01 t/s 12.13.695.901 I slot print_timing: id 0 | task 15404 | n_gen = 256, tg = 26.01 t/s, tg_3s = 25.99 t/s 12.15.282.986 I slot print_timing: id 2 | task 15363 | n_gen = 335, tg = 22.67 t/s, tg_3s = 25.92 t/s 12.15.630.664 I slot print_timing: id 1 | task 15373 | n_gen = 335, tg = 23.74 t/s, tg_3s = 25.91 t/s 12.16.558.117 I slot print_timing: id 3 | task 15398 | n_gen = 335, tg = 24.85 t/s, tg_3s = 25.87 t/s 12.16.710.957 I slot print_timing: id 0 | task 15404 | n_gen = 334, tg = 25.98 t/s, tg_3s = 25.87 t/s 12.17.596.398 I slot print_timing: id 0 | task 15404 | prompt eval time = 666.66 ms / 452 tokens ( 1.47 ms per token, 678.01 tokens per second) 12.17.596.405 I slot print_timing: id 0 | task 15404 | eval time = 13705.33 ms / 357 tokens ( 38.50 ms per token, 25.98 tokens per second) 12.17.596.406 I slot print_timing: id 0 | task 15404 | total time = 14371.99 ms / 809 tokens 12.17.596.407 I slot print_timing: id 0 | task 15404 | graphs reused = 14948 12.17.596.408 I slot print_timing: id 0 | task 15404 | graph reallocs = 0 / 0 (same size) / (changed size) 12.17.596.508 I slot release: id 0 | task 15404 | stop processing: n_tokens = 1503, truncated = 0 12.17.631.937 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.711 12.17.631.980 I slot launch_slot_: id 0 | task 15764 | processing task, is_child = 0 12.18.322.526 I slot print_timing: id 2 | task 15363 | n_gen = 398, tg = 22.33 t/s, tg_3s = 20.73 t/s 12.18.666.297 I slot print_timing: id 1 | task 15373 | n_gen = 398, tg = 23.21 t/s, tg_3s = 20.75 t/s 12.19.593.476 I slot print_timing: id 3 | task 15398 | n_gen = 398, tg = 24.09 t/s, tg_3s = 20.76 t/s 12.21.323.848 I slot print_timing: id 2 | task 15363 | n_gen = 476, tg = 22.86 t/s, tg_3s = 25.99 t/s 12.21.670.725 I slot print_timing: id 1 | task 15373 | n_gen = 476, tg = 23.62 t/s, tg_3s = 25.96 t/s 12.22.134.589 I slot print_timing: id 0 | task 15764 | n_gen = 100, tg = 25.97 t/s, tg_3s = 26.23 t/s 12.22.596.564 I slot print_timing: id 3 | task 15398 | n_gen = 476, tg = 24.38 t/s, tg_3s = 25.97 t/s 12.24.327.956 I slot print_timing: id 2 | task 15363 | n_gen = 554, tg = 23.25 t/s, tg_3s = 25.96 t/s 12.24.673.908 I slot print_timing: id 1 | task 15373 | n_gen = 554, tg = 23.93 t/s, tg_3s = 25.97 t/s 12.25.135.443 I slot print_timing: id 0 | task 15764 | n_gen = 178, tg = 25.98 t/s, tg_3s = 25.99 t/s 12.25.601.132 I slot print_timing: id 3 | task 15398 | n_gen = 554, tg = 24.59 t/s, tg_3s = 25.96 t/s 12.27.342.710 I slot print_timing: id 2 | task 15363 | n_gen = 632, tg = 23.55 t/s, tg_3s = 25.87 t/s 12.27.689.387 I slot print_timing: id 1 | task 15373 | n_gen = 632, tg = 24.15 t/s, tg_3s = 25.87 t/s 12.28.152.411 I slot print_timing: id 0 | task 15764 | n_gen = 256, tg = 25.94 t/s, tg_3s = 25.85 t/s 12.28.619.315 I slot print_timing: id 3 | task 15398 | n_gen = 632, tg = 24.74 t/s, tg_3s = 25.84 t/s 12.30.359.404 I slot print_timing: id 2 | task 15363 | n_gen = 710, tg = 23.78 t/s, tg_3s = 25.86 t/s 12.30.706.386 I slot print_timing: id 1 | task 15373 | n_gen = 710, tg = 24.33 t/s, tg_3s = 25.85 t/s 12.31.171.121 I slot print_timing: id 0 | task 15764 | n_gen = 334, tg = 25.92 t/s, tg_3s = 25.84 t/s 12.31.637.555 I slot print_timing: id 3 | task 15398 | n_gen = 710, tg = 24.86 t/s, tg_3s = 25.84 t/s 12.31.790.499 I slot print_timing: id 0 | task 15764 | prompt eval time = 690.05 ms / 465 tokens ( 1.48 ms per token, 673.86 tokens per second) 12.31.790.505 I slot print_timing: id 0 | task 15764 | eval time = 13468.46 ms / 350 tokens ( 38.59 ms per token, 25.91 tokens per second) 12.31.790.506 I slot print_timing: id 0 | task 15764 | total time = 14158.51 ms / 815 tokens 12.31.790.506 I slot print_timing: id 0 | task 15764 | graphs reused = 15296 12.31.790.507 I slot print_timing: id 0 | task 15764 | graph reallocs = 0 / 0 (same size) / (changed size) 12.31.790.609 I slot release: id 0 | task 15764 | stop processing: n_tokens = 1509, truncated = 0 12.31.826.222 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.708 12.31.826.252 I slot launch_slot_: id 0 | task 16117 | processing task, is_child = 0 12.33.372.907 I slot print_timing: id 2 | task 15363 | n_gen = 773, tg = 23.52 t/s, tg_3s = 20.91 t/s 12.33.719.741 I slot print_timing: id 1 | task 15373 | n_gen = 773, tg = 24.01 t/s, tg_3s = 20.91 t/s 12.34.647.563 I slot print_timing: id 3 | task 15398 | n_gen = 773, tg = 24.48 t/s, tg_3s = 20.93 t/s 12.36.313.676 I slot print_timing: id 0 | task 16117 | n_gen = 100, tg = 25.86 t/s, tg_3s = 26.12 t/s 12.36.392.794 I slot print_timing: id 2 | task 15363 | n_gen = 851, tg = 23.71 t/s, tg_3s = 25.83 t/s 12.36.741.311 I slot print_timing: id 1 | task 15373 | n_gen = 851, tg = 24.16 t/s, tg_3s = 25.81 t/s 12.37.675.113 I slot print_timing: id 3 | task 15398 | n_gen = 851, tg = 24.60 t/s, tg_3s = 25.76 t/s 12.39.343.321 I slot print_timing: id 0 | task 16117 | n_gen = 178, tg = 25.81 t/s, tg_3s = 25.75 t/s 12.39.422.945 I slot print_timing: id 2 | task 15363 | n_gen = 929, tg = 23.87 t/s, tg_3s = 25.74 t/s 12.39.773.138 I slot print_timing: id 1 | task 15373 | n_gen = 929, tg = 24.29 t/s, tg_3s = 25.73 t/s 12.40.708.743 I slot print_timing: id 3 | task 15398 | n_gen = 929, tg = 24.69 t/s, tg_3s = 25.71 t/s 12.42.380.409 I slot print_timing: id 0 | task 16117 | n_gen = 256, tg = 25.77 t/s, tg_3s = 25.68 t/s 12.42.460.119 I slot print_timing: id 2 | task 15363 | n_gen = 1007, tg = 24.00 t/s, tg_3s = 25.68 t/s 12.42.811.748 I slot print_timing: id 1 | task 15373 | n_gen = 1007, tg = 24.39 t/s, tg_3s = 25.67 t/s 12.43.125.069 I slot print_timing: id 2 | task 15363 | prompt eval time = 754.30 ms / 511 tokens ( 1.48 ms per token, 677.45 tokens per second) 12.43.125.073 I slot print_timing: id 2 | task 15363 | eval time = 42578.04 ms / 1024 tokens ( 41.62 ms per token, 24.03 tokens per second) 12.43.125.074 I slot print_timing: id 2 | task 15363 | total time = 43332.34 ms / 1535 tokens 12.43.125.074 I slot print_timing: id 2 | task 15363 | graphs reused = 15569 12.43.125.075 I slot print_timing: id 2 | task 15363 | graph reallocs = 0 / 0 (same size) / (changed size) 12.43.125.180 I slot release: id 2 | task 15363 | stop processing: n_tokens = 2227, truncated = 0 12.43.165.984 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 12.43.174.184 I slot launch_slot_: id 2 | task 16395 | processing task, is_child = 0 12.43.821.562 I slot print_timing: id 3 | task 15398 | n_gen = 993, tg = 24.37 t/s, tg_3s = 20.56 t/s 12.44.135.400 I slot print_timing: id 1 | task 15373 | prompt eval time = 745.16 ms / 494 tokens ( 1.51 ms per token, 662.95 tokens per second) 12.44.135.412 I slot print_timing: id 1 | task 15373 | eval time = 42572.92 ms / 1024 tokens ( 41.62 ms per token, 24.03 tokens per second) 12.44.135.413 I slot print_timing: id 1 | task 15373 | total time = 43318.08 ms / 1518 tokens 12.44.135.413 I slot print_timing: id 1 | task 15373 | graphs reused = 15574 12.44.135.414 I slot print_timing: id 1 | task 15373 | graph reallocs = 0 / 0 (same size) / (changed size) 12.44.135.545 I slot release: id 1 | task 15373 | stop processing: n_tokens = 2181, truncated = 0 12.44.176.877 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.490 12.44.183.206 I slot launch_slot_: id 1 | task 16405 | processing task, is_child = 0 12.45.401.002 I slot print_timing: id 0 | task 16117 | n_gen = 300, tg = 23.15 t/s, tg_3s = 14.57 t/s 12.45.714.491 I slot print_timing: id 3 | task 15398 | prompt eval time = 700.66 ms / 463 tokens ( 1.51 ms per token, 660.81 tokens per second) 12.45.714.499 I slot print_timing: id 3 | task 15398 | eval time = 42598.63 ms / 1024 tokens ( 41.64 ms per token, 24.01 tokens per second) 12.45.714.500 I slot print_timing: id 3 | task 15398 | total time = 43299.29 ms / 1487 tokens 12.45.714.501 I slot print_timing: id 3 | task 15398 | graphs reused = 15594 12.45.714.502 I slot print_timing: id 3 | task 15398 | graph reallocs = 0 / 0 (same size) / (changed size) 12.45.714.626 I slot release: id 3 | task 15398 | stop processing: n_tokens = 2182, truncated = 0 12.45.748.395 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.891 (> 0.100 thold), f_keep = 0.489 12.45.754.450 I slot launch_slot_: id 3 | task 16430 | processing task, is_child = 0 12.48.417.211 I slot print_timing: id 0 | task 16117 | n_gen = 361, tg = 22.60 t/s, tg_3s = 20.22 t/s 12.49.036.245 I slot print_timing: id 2 | task 16395 | n_gen = 100, tg = 19.25 t/s, tg_3s = 19.45 t/s 12.49.383.435 I slot print_timing: id 1 | task 16405 | n_gen = 100, tg = 22.07 t/s, tg_3s = 22.29 t/s 12.50.040.711 I slot print_timing: id 0 | task 16117 | prompt eval time = 658.38 ms / 434 tokens ( 1.52 ms per token, 659.19 tokens per second) 12.50.040.718 I slot print_timing: id 0 | task 16117 | eval time = 17556.06 ms / 403 tokens ( 43.67 ms per token, 22.90 tokens per second) 12.50.040.719 I slot print_timing: id 0 | task 16117 | total time = 18214.45 ms / 837 tokens 12.50.040.720 I slot print_timing: id 0 | task 16117 | graphs reused = 15685 12.50.040.721 I slot print_timing: id 0 | task 16117 | graph reallocs = 0 / 0 (same size) / (changed size) 12.50.040.824 I slot release: id 0 | task 16117 | stop processing: n_tokens = 1531, truncated = 0 12.50.075.835 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.698 12.50.075.878 I slot launch_slot_: id 0 | task 16526 | processing task, is_child = 0 12.50.917.096 I slot print_timing: id 3 | task 16430 | n_gen = 100, tg = 22.38 t/s, tg_3s = 22.60 t/s 12.52.072.667 I slot print_timing: id 2 | task 16395 | n_gen = 163, tg = 19.81 t/s, tg_3s = 20.75 t/s 12.52.420.212 I slot print_timing: id 1 | task 16405 | n_gen = 163, tg = 21.54 t/s, tg_3s = 20.75 t/s 12.53.921.726 I slot print_timing: id 3 | task 16430 | n_gen = 178, tg = 23.83 t/s, tg_3s = 25.96 t/s 12.54.576.854 I slot print_timing: id 0 | task 16526 | n_gen = 100, tg = 25.97 t/s, tg_3s = 26.24 t/s 12.55.077.545 I slot print_timing: id 2 | task 16395 | n_gen = 241, tg = 21.46 t/s, tg_3s = 25.96 t/s 12.55.423.173 I slot print_timing: id 1 | task 16405 | n_gen = 241, tg = 22.80 t/s, tg_3s = 25.97 t/s 12.56.926.190 I slot print_timing: id 3 | task 16430 | n_gen = 256, tg = 24.44 t/s, tg_3s = 25.96 t/s 12.57.577.818 I slot print_timing: id 0 | task 16526 | n_gen = 178, tg = 25.98 t/s, tg_3s = 25.99 t/s 12.58.078.284 I slot print_timing: id 2 | task 16395 | n_gen = 319, tg = 22.42 t/s, tg_3s = 25.99 t/s 12.58.425.042 I slot print_timing: id 1 | task 16405 | n_gen = 319, tg = 23.51 t/s, tg_3s = 25.98 t/s 12.59.930.510 I slot print_timing: id 3 | task 16430 | n_gen = 334, tg = 24.78 t/s, tg_3s = 25.96 t/s 13.00.585.988 I slot print_timing: id 0 | task 16526 | n_gen = 256, tg = 25.97 t/s, tg_3s = 25.93 t/s 13.01.090.359 I slot print_timing: id 2 | task 16395 | n_gen = 397, tg = 23.03 t/s, tg_3s = 25.90 t/s 13.01.436.650 I slot print_timing: id 1 | task 16405 | n_gen = 397, tg = 23.94 t/s, tg_3s = 25.90 t/s 13.02.713.157 I slot print_timing: id 1 | task 16405 | prompt eval time = 714.53 ms / 467 tokens ( 1.53 ms per token, 653.57 tokens per second) 13.02.713.165 I slot print_timing: id 1 | task 16405 | eval time = 17815.40 ms / 430 tokens ( 41.53 ms per token, 24.08 tokens per second) 13.02.713.166 I slot print_timing: id 1 | task 16405 | total time = 18529.94 ms / 897 tokens 13.02.713.167 I slot print_timing: id 1 | task 16405 | graphs reused = 15994 13.02.713.168 I slot print_timing: id 1 | task 16405 | graph reallocs = 0 / 0 (same size) / (changed size) 13.02.713.266 I slot release: id 1 | task 16405 | stop processing: n_tokens = 1560, truncated = 0 13.02.753.742 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.685 13.02.753.785 I slot launch_slot_: id 1 | task 16840 | processing task, is_child = 0 13.03.420.552 I slot print_timing: id 3 | task 16430 | n_gen = 408, tg = 24.04 t/s, tg_3s = 21.20 t/s 13.03.607.594 I slot print_timing: id 0 | task 16526 | n_gen = 317, tg = 24.61 t/s, tg_3s = 20.19 t/s 13.04.111.360 I slot print_timing: id 2 | task 16395 | n_gen = 458, tg = 22.60 t/s, tg_3s = 20.19 t/s 13.06.431.484 I slot print_timing: id 3 | task 16430 | n_gen = 485, tg = 24.27 t/s, tg_3s = 25.57 t/s 13.06.622.778 I slot print_timing: id 0 | task 16526 | n_gen = 395, tg = 24.85 t/s, tg_3s = 25.87 t/s 13.07.124.661 I slot print_timing: id 2 | task 16395 | n_gen = 536, tg = 23.03 t/s, tg_3s = 25.89 t/s 13.07.316.454 I slot print_timing: id 1 | task 16840 | n_gen = 100, tg = 25.90 t/s, tg_3s = 26.16 t/s 13.08.432.549 I slot print_timing: id 0 | task 16526 | prompt eval time = 689.38 ms / 465 tokens ( 1.48 ms per token, 674.52 tokens per second) 13.08.432.556 I slot print_timing: id 0 | task 16526 | eval time = 17667.28 ms / 442 tokens ( 40.06 ms per token, 24.96 tokens per second) 13.08.432.557 I slot print_timing: id 0 | task 16526 | total time = 18356.66 ms / 907 tokens 13.08.432.558 I slot print_timing: id 0 | task 16526 | graphs reused = 16121 13.08.432.558 I slot print_timing: id 0 | task 16526 | graph reallocs = 0 / 0 (same size) / (changed size) 13.08.432.657 I slot release: id 0 | task 16526 | stop processing: n_tokens = 1601, truncated = 0 13.08.467.713 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.667 13.08.467.745 I slot launch_slot_: id 0 | task 16972 | processing task, is_child = 0 13.09.436.645 I slot print_timing: id 3 | task 16430 | n_gen = 547, tg = 23.80 t/s, tg_3s = 20.63 t/s 13.10.134.455 I slot print_timing: id 2 | task 16395 | n_gen = 598, tg = 22.75 t/s, tg_3s = 20.60 t/s 13.10.326.671 I slot print_timing: id 1 | task 16840 | n_gen = 162, tg = 23.56 t/s, tg_3s = 20.60 t/s 13.12.452.833 I slot print_timing: id 3 | task 16430 | n_gen = 625, tg = 24.04 t/s, tg_3s = 25.86 t/s 13.12.990.436 I slot print_timing: id 0 | task 16972 | n_gen = 100, tg = 25.92 t/s, tg_3s = 26.18 t/s 13.13.145.879 I slot print_timing: id 2 | task 16395 | n_gen = 676, tg = 23.08 t/s, tg_3s = 25.90 t/s 13.13.339.217 I slot print_timing: id 1 | task 16840 | n_gen = 240, tg = 24.28 t/s, tg_3s = 25.89 t/s 13.15.458.288 I slot print_timing: id 3 | task 16430 | n_gen = 703, tg = 24.24 t/s, tg_3s = 25.95 t/s 13.15.995.377 I slot print_timing: id 0 | task 16972 | n_gen = 178, tg = 25.94 t/s, tg_3s = 25.96 t/s 13.16.151.308 I slot print_timing: id 2 | task 16395 | n_gen = 754, tg = 23.34 t/s, tg_3s = 25.95 t/s 13.16.343.620 I slot print_timing: id 1 | task 16840 | n_gen = 318, tg = 24.67 t/s, tg_3s = 25.96 t/s 13.18.473.060 I slot print_timing: id 3 | task 16430 | n_gen = 781, tg = 24.39 t/s, tg_3s = 25.87 t/s 13.19.013.802 I slot print_timing: id 0 | task 16972 | n_gen = 256, tg = 25.91 t/s, tg_3s = 25.84 t/s 13.19.168.976 I slot print_timing: id 2 | task 16395 | n_gen = 832, tg = 23.56 t/s, tg_3s = 25.85 t/s 13.19.361.824 I slot print_timing: id 1 | task 16840 | n_gen = 396, tg = 24.89 t/s, tg_3s = 25.84 t/s 13.21.492.423 I slot print_timing: id 3 | task 16430 | n_gen = 859, tg = 24.51 t/s, tg_3s = 25.83 t/s 13.22.032.848 I slot print_timing: id 0 | task 16972 | n_gen = 334, tg = 25.89 t/s, tg_3s = 25.84 t/s 13.22.188.650 I slot print_timing: id 2 | task 16395 | n_gen = 910, tg = 23.74 t/s, tg_3s = 25.83 t/s 13.22.381.775 I slot print_timing: id 1 | task 16840 | n_gen = 474, tg = 25.04 t/s, tg_3s = 25.83 t/s 13.22.693.352 I slot print_timing: id 3 | task 16430 | prompt eval time = 738.59 ms / 502 tokens ( 1.47 ms per token, 679.67 tokens per second) 13.22.693.357 I slot print_timing: id 3 | task 16430 | eval time = 36200.30 ms / 890 tokens ( 40.72 ms per token, 24.56 tokens per second) 13.22.693.358 I slot print_timing: id 3 | task 16430 | total time = 36938.89 ms / 1392 tokens 13.22.693.359 I slot print_timing: id 3 | task 16430 | graphs reused = 16469 13.22.693.359 I slot print_timing: id 3 | task 16430 | graph reallocs = 0 / 0 (same size) / (changed size) 13.22.693.462 I slot release: id 3 | task 16430 | stop processing: n_tokens = 2087, truncated = 0 13.22.727.171 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.512 13.22.727.201 I slot launch_slot_: id 3 | task 17326 | processing task, is_child = 0 13.25.060.300 I slot print_timing: id 0 | task 16972 | n_gen = 397, tg = 24.92 t/s, tg_3s = 20.81 t/s 13.25.216.912 I slot print_timing: id 2 | task 16395 | n_gen = 973, tg = 23.52 t/s, tg_3s = 20.80 t/s 13.25.410.846 I slot print_timing: id 1 | task 16840 | n_gen = 537, tg = 24.46 t/s, tg_3s = 20.80 t/s 13.27.200.862 I slot print_timing: id 2 | task 16395 | prompt eval time = 719.96 ms / 476 tokens ( 1.51 ms per token, 661.15 tokens per second) 13.27.200.873 I slot print_timing: id 2 | task 16395 | eval time = 43306.71 ms / 1024 tokens ( 42.33 ms per token, 23.62 tokens per second) 13.27.200.874 I slot print_timing: id 2 | task 16395 | total time = 44026.67 ms / 1500 tokens 13.27.200.875 I slot print_timing: id 2 | task 16395 | graphs reused = 16566 13.27.200.875 I slot print_timing: id 2 | task 16395 | graph reallocs = 0 / 0 (same size) / (changed size) 13.27.200.982 I slot release: id 2 | task 16395 | stop processing: n_tokens = 2194, truncated = 0 13.27.241.106 I slot print_timing: id 3 | task 17326 | n_gen = 100, tg = 25.76 t/s, tg_3s = 26.02 t/s 13.27.241.117 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 13.27.247.423 I slot launch_slot_: id 2 | task 17428 | processing task, is_child = 0 13.28.077.523 I slot print_timing: id 0 | task 16972 | n_gen = 458, tg = 24.17 t/s, tg_3s = 20.22 t/s 13.28.437.328 I slot print_timing: id 1 | task 16840 | n_gen = 598, tg = 23.93 t/s, tg_3s = 20.16 t/s 13.30.247.817 I slot print_timing: id 3 | task 17326 | n_gen = 161, tg = 23.36 t/s, tg_3s = 20.29 t/s 13.31.093.487 I slot print_timing: id 0 | task 16972 | n_gen = 536, tg = 24.40 t/s, tg_3s = 25.86 t/s 13.31.440.728 I slot print_timing: id 1 | task 16840 | n_gen = 676, tg = 24.15 t/s, tg_3s = 25.97 t/s 13.31.789.391 I slot print_timing: id 2 | task 17428 | n_gen = 100, tg = 25.87 t/s, tg_3s = 26.13 t/s 13.33.256.397 I slot print_timing: id 3 | task 17326 | n_gen = 239, tg = 24.14 t/s, tg_3s = 25.93 t/s 13.34.104.520 I slot print_timing: id 0 | task 16972 | n_gen = 614, tg = 24.59 t/s, tg_3s = 25.90 t/s 13.34.452.801 I slot print_timing: id 1 | task 16840 | n_gen = 754, tg = 24.32 t/s, tg_3s = 25.90 t/s 13.34.801.279 I slot print_timing: id 2 | task 17428 | n_gen = 178, tg = 25.88 t/s, tg_3s = 25.90 t/s 13.36.269.962 I slot print_timing: id 3 | task 17326 | n_gen = 317, tg = 24.55 t/s, tg_3s = 25.88 t/s 13.37.115.282 I slot print_timing: id 0 | task 16972 | n_gen = 692, tg = 24.73 t/s, tg_3s = 25.91 t/s 13.37.269.146 I slot print_timing: id 1 | task 16840 | prompt eval time = 740.14 ms / 488 tokens ( 1.52 ms per token, 659.34 tokens per second) 13.37.269.151 I slot print_timing: id 1 | task 16840 | eval time = 33775.21 ms / 827 tokens ( 40.89 ms per token, 24.46 tokens per second) 13.37.269.152 I slot print_timing: id 1 | task 16840 | total time = 34515.35 ms / 1315 tokens 13.37.269.152 I slot print_timing: id 1 | task 16840 | graphs reused = 16805 13.37.269.153 I slot print_timing: id 1 | task 16840 | graph reallocs = 0 / 0 (same size) / (changed size) 13.37.269.254 I slot release: id 1 | task 16840 | stop processing: n_tokens = 1978, truncated = 0 13.37.309.803 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.540 13.37.309.840 I slot launch_slot_: id 1 | task 17673 | processing task, is_child = 0 13.37.993.356 I slot print_timing: id 2 | task 17428 | n_gen = 244, tg = 24.23 t/s, tg_3s = 20.68 t/s 13.39.300.941 I slot print_timing: id 3 | task 17326 | n_gen = 378, tg = 23.71 t/s, tg_3s = 20.13 t/s 13.40.148.043 I slot print_timing: id 0 | task 16972 | n_gen = 753, tg = 24.28 t/s, tg_3s = 20.11 t/s 13.40.995.933 I slot print_timing: id 2 | task 17428 | n_gen = 321, tg = 24.55 t/s, tg_3s = 25.64 t/s 13.41.341.498 I slot print_timing: id 3 | task 17326 | prompt eval time = 671.23 ms / 438 tokens ( 1.53 ms per token, 652.53 tokens per second) 13.41.341.505 I slot print_timing: id 3 | task 17326 | eval time = 17943.06 ms / 431 tokens ( 41.73 ms per token, 23.96 tokens per second) 13.41.341.505 I slot print_timing: id 3 | task 17326 | total time = 18614.29 ms / 869 tokens 13.41.341.506 I slot print_timing: id 3 | task 17326 | graphs reused = 16889 13.41.341.507 I slot print_timing: id 3 | task 17326 | graph reallocs = 0 / 0 (same size) / (changed size) 13.41.341.607 I slot release: id 3 | task 17326 | stop processing: n_tokens = 1564, truncated = 0 13.41.375.097 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.683 13.41.375.127 I slot launch_slot_: id 3 | task 17762 | processing task, is_child = 0 13.42.467.091 I slot print_timing: id 1 | task 17673 | n_gen = 100, tg = 22.50 t/s, tg_3s = 22.73 t/s 13.43.160.080 I slot print_timing: id 0 | task 16972 | n_gen = 816, tg = 23.98 t/s, tg_3s = 20.92 t/s 13.44.009.732 I slot print_timing: id 2 | task 17428 | n_gen = 384, tg = 23.87 t/s, tg_3s = 20.90 t/s 13.45.478.531 I slot print_timing: id 1 | task 17673 | n_gen = 178, tg = 23.88 t/s, tg_3s = 25.90 t/s 13.45.865.095 I slot print_timing: id 3 | task 17762 | n_gen = 100, tg = 25.93 t/s, tg_3s = 26.19 t/s 13.46.172.172 I slot print_timing: id 0 | task 16972 | n_gen = 894, tg = 24.13 t/s, tg_3s = 25.90 t/s 13.47.019.316 I slot print_timing: id 2 | task 17428 | n_gen = 462, tg = 24.19 t/s, tg_3s = 25.92 t/s 13.47.251.786 I slot print_timing: id 2 | task 17428 | prompt eval time = 715.62 ms / 470 tokens ( 1.52 ms per token, 656.77 tokens per second) 13.47.251.793 I slot print_timing: id 2 | task 17428 | eval time = 19288.72 ms / 468 tokens ( 41.30 ms per token, 24.21 tokens per second) 13.47.251.794 I slot print_timing: id 2 | task 17428 | total time = 20004.35 ms / 938 tokens 13.47.251.795 I slot print_timing: id 2 | task 17428 | graphs reused = 17022 13.47.251.796 I slot print_timing: id 2 | task 17428 | graph reallocs = 0 / 0 (same size) / (changed size) 13.47.251.924 I slot release: id 2 | task 17428 | stop processing: n_tokens = 1632, truncated = 0 13.47.292.053 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.654 13.47.292.089 I slot launch_slot_: id 2 | task 17901 | processing task, is_child = 0 13.48.516.001 I slot print_timing: id 1 | task 17673 | n_gen = 241, tg = 22.97 t/s, tg_3s = 20.74 t/s 13.48.901.098 I slot print_timing: id 3 | task 17762 | n_gen = 163, tg = 23.64 t/s, tg_3s = 20.75 t/s 13.49.206.110 I slot print_timing: id 0 | task 16972 | n_gen = 957, tg = 23.88 t/s, tg_3s = 20.77 t/s 13.49.513.566 I slot print_timing: id 0 | task 16972 | prompt eval time = 702.88 ms / 483 tokens ( 1.46 ms per token, 687.17 tokens per second) 13.49.513.569 I slot print_timing: id 0 | task 16972 | eval time = 40342.93 ms / 965 tokens ( 41.85 ms per token, 23.90 tokens per second) 13.49.513.570 I slot print_timing: id 0 | task 16972 | total time = 41045.81 ms / 1448 tokens 13.49.513.571 I slot print_timing: id 0 | task 16972 | graphs reused = 17061 13.49.513.572 I slot print_timing: id 0 | task 16972 | graph reallocs = 0 / 0 (same size) / (changed size) 13.49.513.669 I slot release: id 0 | task 16972 | stop processing: n_tokens = 2142, truncated = 0 13.49.548.473 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.499 13.49.550.677 I slot launch_slot_: id 0 | task 17945 | processing task, is_child = 0 13.51.548.203 I slot print_timing: id 1 | task 17673 | n_gen = 304, tg = 22.48 t/s, tg_3s = 20.78 t/s 13.51.931.859 I slot print_timing: id 3 | task 17762 | n_gen = 226, tg = 22.76 t/s, tg_3s = 20.79 t/s 13.52.390.711 I slot print_timing: id 2 | task 17901 | n_gen = 100, tg = 22.43 t/s, tg_3s = 22.66 t/s 13.54.042.953 I slot print_timing: id 0 | task 17945 | n_gen = 100, tg = 26.03 t/s, tg_3s = 26.30 t/s 13.54.584.401 I slot print_timing: id 1 | task 17673 | n_gen = 383, tg = 23.13 t/s, tg_3s = 26.02 t/s 13.54.934.514 I slot print_timing: id 3 | task 17762 | n_gen = 304, tg = 23.51 t/s, tg_3s = 25.98 t/s 13.55.399.521 I slot print_timing: id 2 | task 17901 | n_gen = 178, tg = 23.85 t/s, tg_3s = 25.92 t/s 13.57.055.874 I slot print_timing: id 0 | task 17945 | n_gen = 178, tg = 25.97 t/s, tg_3s = 25.89 t/s 13.57.595.480 I slot print_timing: id 1 | task 17673 | n_gen = 461, tg = 23.56 t/s, tg_3s = 25.90 t/s 13.57.941.209 I slot print_timing: id 3 | task 17762 | n_gen = 382, tg = 23.97 t/s, tg_3s = 25.94 t/s 13.58.403.874 I slot print_timing: id 2 | task 17901 | n_gen = 256, tg = 24.46 t/s, tg_3s = 25.96 t/s 14.00.062.204 I slot print_timing: id 0 | task 17945 | n_gen = 256, tg = 25.96 t/s, tg_3s = 25.95 t/s 14.00.370.927 I slot print_timing: id 3 | task 17762 | prompt eval time = 672.17 ms / 440 tokens ( 1.53 ms per token, 654.59 tokens per second) 14.00.370.932 I slot print_timing: id 3 | task 17762 | eval time = 18323.62 ms / 445 tokens ( 41.27 ms per token, 24.23 tokens per second) 14.00.370.933 I slot print_timing: id 3 | task 17762 | total time = 18995.79 ms / 885 tokens 14.00.370.933 I slot print_timing: id 3 | task 17762 | graphs reused = 17323 14.00.370.934 I slot print_timing: id 3 | task 17762 | graph reallocs = 0 / 0 (same size) / (changed size) 14.00.371.034 I slot release: id 3 | task 17762 | stop processing: n_tokens = 1580, truncated = 0 14.00.404.485 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.676 14.00.404.512 I slot launch_slot_: id 3 | task 18212 | processing task, is_child = 0 14.01.043.859 I slot print_timing: id 1 | task 17673 | n_gen = 535, tg = 23.24 t/s, tg_3s = 21.46 t/s 14.01.417.192 I slot print_timing: id 2 | task 17901 | n_gen = 318, tg = 23.59 t/s, tg_3s = 20.58 t/s 14.03.084.570 I slot print_timing: id 0 | task 17945 | n_gen = 318, tg = 24.68 t/s, tg_3s = 20.51 t/s 14.04.049.535 I slot print_timing: id 1 | task 17673 | n_gen = 612, tg = 23.52 t/s, tg_3s = 25.62 t/s 14.04.437.965 I slot print_timing: id 2 | task 17901 | n_gen = 396, tg = 24.00 t/s, tg_3s = 25.82 t/s 14.04.939.705 I slot print_timing: id 3 | task 18212 | n_gen = 100, tg = 25.86 t/s, tg_3s = 26.12 t/s 14.06.093.528 I slot print_timing: id 0 | task 17945 | n_gen = 396, tg = 24.92 t/s, tg_3s = 25.92 t/s 14.07.060.214 I slot print_timing: id 1 | task 17673 | n_gen = 690, tg = 23.76 t/s, tg_3s = 25.91 t/s 14.07.445.807 I slot print_timing: id 2 | task 17901 | n_gen = 474, tg = 24.30 t/s, tg_3s = 25.93 t/s 14.07.947.314 I slot print_timing: id 3 | task 18212 | n_gen = 178, tg = 25.89 t/s, tg_3s = 25.93 t/s 14.09.108.759 I slot print_timing: id 0 | task 17945 | n_gen = 474, tg = 25.07 t/s, tg_3s = 25.87 t/s 14.10.035.340 I slot print_timing: id 2 | task 17901 | prompt eval time = 685.46 ms / 444 tokens ( 1.54 ms per token, 647.74 tokens per second) 14.10.035.344 I slot print_timing: id 2 | task 17901 | eval time = 22057.78 ms / 541 tokens ( 40.85 ms per token, 24.48 tokens per second) 14.10.035.345 I slot print_timing: id 2 | task 17901 | total time = 22743.24 ms / 985 tokens 14.10.035.345 I slot print_timing: id 2 | task 17901 | graphs reused = 17552 14.10.035.346 I slot print_timing: id 2 | task 17901 | graph reallocs = 0 / 0 (same size) / (changed size) 14.10.035.456 I slot release: id 2 | task 17901 | stop processing: n_tokens = 1679, truncated = 0 14.10.075.581 I slot print_timing: id 1 | task 17673 | n_gen = 768, tg = 23.96 t/s, tg_3s = 25.87 t/s 14.10.076.164 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.636 14.10.076.201 I slot launch_slot_: id 2 | task 18447 | processing task, is_child = 0 14.10.957.067 I slot print_timing: id 3 | task 18212 | n_gen = 240, tg = 24.27 t/s, tg_3s = 20.60 t/s 14.12.117.266 I slot print_timing: id 0 | task 17945 | n_gen = 536, tg = 24.45 t/s, tg_3s = 20.61 t/s 14.13.083.614 I slot print_timing: id 1 | task 17673 | n_gen = 830, tg = 23.67 t/s, tg_3s = 20.61 t/s 14.13.968.391 I slot print_timing: id 3 | task 18212 | n_gen = 318, tg = 24.66 t/s, tg_3s = 25.90 t/s 14.14.585.559 I slot print_timing: id 2 | task 18447 | n_gen = 100, tg = 25.92 t/s, tg_3s = 26.18 t/s 14.15.129.139 I slot print_timing: id 0 | task 17945 | n_gen = 614, tg = 24.63 t/s, tg_3s = 25.90 t/s 14.16.100.531 I slot print_timing: id 1 | task 17673 | n_gen = 908, tg = 23.85 t/s, tg_3s = 25.85 t/s 14.16.993.788 I slot print_timing: id 3 | task 18212 | n_gen = 396, tg = 24.87 t/s, tg_3s = 25.78 t/s 14.17.614.289 I slot print_timing: id 2 | task 18447 | n_gen = 178, tg = 25.85 t/s, tg_3s = 25.75 t/s 14.18.156.133 I slot print_timing: id 0 | task 17945 | n_gen = 692, tg = 24.75 t/s, tg_3s = 25.77 t/s 14.19.128.777 I slot print_timing: id 1 | task 17673 | n_gen = 986, tg = 23.99 t/s, tg_3s = 25.76 t/s 14.20.023.718 I slot print_timing: id 3 | task 18212 | n_gen = 474, tg = 25.01 t/s, tg_3s = 25.74 t/s 14.20.605.548 I slot print_timing: id 1 | task 17673 | prompt eval time = 757.19 ms / 511 tokens ( 1.48 ms per token, 674.86 tokens per second) 14.20.605.555 I slot print_timing: id 1 | task 17673 | eval time = 42538.50 ms / 1024 tokens ( 41.58 ms per token, 24.05 tokens per second) 14.20.605.556 I slot print_timing: id 1 | task 17673 | total time = 43295.70 ms / 1535 tokens 14.20.605.556 I slot print_timing: id 1 | task 17673 | graphs reused = 17804 14.20.605.557 I slot print_timing: id 1 | task 17673 | graph reallocs = 0 / 0 (same size) / (changed size) 14.20.605.661 I slot release: id 1 | task 17673 | stop processing: n_tokens = 2198, truncated = 0 14.20.646.185 I slot print_timing: id 2 | task 18447 | n_gen = 256, tg = 25.81 t/s, tg_3s = 25.73 t/s 14.20.646.794 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.486 14.20.653.263 I slot launch_slot_: id 1 | task 18705 | processing task, is_child = 0 14.21.326.492 I slot print_timing: id 0 | task 17945 | n_gen = 757, tg = 24.32 t/s, tg_3s = 20.50 t/s 14.23.027.806 I slot print_timing: id 3 | task 18212 | n_gen = 534, tg = 24.32 t/s, tg_3s = 19.97 t/s 14.23.682.180 I slot print_timing: id 2 | task 18447 | n_gen = 317, tg = 24.47 t/s, tg_3s = 20.09 t/s 14.24.336.871 I slot print_timing: id 0 | task 17945 | n_gen = 834, tg = 24.43 t/s, tg_3s = 25.58 t/s 14.25.226.173 I slot print_timing: id 1 | task 18705 | n_gen = 100, tg = 25.88 t/s, tg_3s = 26.14 t/s 14.26.035.841 I slot print_timing: id 3 | task 18212 | n_gen = 612, tg = 24.51 t/s, tg_3s = 25.93 t/s 14.26.696.054 I slot print_timing: id 2 | task 18447 | n_gen = 395, tg = 24.73 t/s, tg_3s = 25.88 t/s 14.27.352.477 I slot print_timing: id 0 | task 17945 | n_gen = 912, tg = 24.55 t/s, tg_3s = 25.87 t/s 14.27.507.569 I slot print_timing: id 2 | task 18447 | prompt eval time = 690.12 ms / 449 tokens ( 1.54 ms per token, 650.61 tokens per second) 14.27.507.573 I slot print_timing: id 2 | task 18447 | eval time = 16741.23 ms / 416 tokens ( 40.34 ms per token, 24.79 tokens per second) 14.27.507.573 I slot print_timing: id 2 | task 18447 | total time = 17431.35 ms / 865 tokens 14.27.507.574 I slot print_timing: id 2 | task 18447 | graphs reused = 17960 14.27.507.575 I slot print_timing: id 2 | task 18447 | graph reallocs = 0 / 0 (same size) / (changed size) 14.27.507.679 I slot release: id 2 | task 18447 | stop processing: n_tokens = 1559, truncated = 0 14.27.547.922 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.685 14.27.547.959 I slot launch_slot_: id 2 | task 18867 | processing task, is_child = 0 14.28.270.351 I slot print_timing: id 1 | task 18705 | n_gen = 162, tg = 23.43 t/s, tg_3s = 20.37 t/s 14.29.044.169 I slot print_timing: id 3 | task 18212 | n_gen = 673, tg = 24.06 t/s, tg_3s = 20.28 t/s 14.30.359.738 I slot print_timing: id 0 | task 17945 | n_gen = 973, tg = 24.23 t/s, tg_3s = 20.28 t/s 14.31.290.259 I slot print_timing: id 1 | task 18705 | n_gen = 240, tg = 24.17 t/s, tg_3s = 25.83 t/s 14.32.063.536 I slot print_timing: id 3 | task 18212 | n_gen = 751, tg = 24.23 t/s, tg_3s = 25.83 t/s 14.32.101.654 I slot print_timing: id 2 | task 18867 | n_gen = 100, tg = 25.84 t/s, tg_3s = 26.10 t/s 14.32.332.687 I slot print_timing: id 0 | task 17945 | prompt eval time = 689.44 ms / 465 tokens ( 1.48 ms per token, 674.46 tokens per second) 14.32.332.694 I slot print_timing: id 0 | task 17945 | eval time = 42092.56 ms / 1024 tokens ( 41.15 ms per token, 24.30 tokens per second) 14.32.332.695 I slot print_timing: id 0 | task 17945 | total time = 42782.00 ms / 1489 tokens 14.32.332.696 I slot print_timing: id 0 | task 17945 | graphs reused = 18064 14.32.332.697 I slot print_timing: id 0 | task 17945 | graph reallocs = 0 / 0 (same size) / (changed size) 14.32.332.794 I slot release: id 0 | task 17945 | stop processing: n_tokens = 2183, truncated = 0 14.32.367.982 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.489 14.32.373.758 I slot launch_slot_: id 0 | task 18976 | processing task, is_child = 0 14.34.302.954 I slot print_timing: id 1 | task 18705 | n_gen = 302, tg = 23.33 t/s, tg_3s = 20.58 t/s 14.35.073.493 I slot print_timing: id 3 | task 18212 | n_gen = 813, tg = 23.91 t/s, tg_3s = 20.60 t/s 14.35.111.604 I slot print_timing: id 2 | task 18867 | n_gen = 162, tg = 23.53 t/s, tg_3s = 20.60 t/s 14.36.881.859 I slot print_timing: id 0 | task 18976 | n_gen = 100, tg = 25.96 t/s, tg_3s = 26.23 t/s 14.37.308.343 I slot print_timing: id 1 | task 18705 | n_gen = 380, tg = 23.82 t/s, tg_3s = 25.95 t/s 14.38.086.613 I slot print_timing: id 3 | task 18212 | n_gen = 891, tg = 24.07 t/s, tg_3s = 25.89 t/s 14.38.124.970 I slot print_timing: id 2 | task 18867 | n_gen = 240, tg = 24.25 t/s, tg_3s = 25.88 t/s 14.39.906.599 I slot print_timing: id 0 | task 18976 | n_gen = 178, tg = 25.89 t/s, tg_3s = 25.79 t/s 14.40.332.194 I slot print_timing: id 1 | task 18705 | n_gen = 458, tg = 24.14 t/s, tg_3s = 25.79 t/s 14.41.108.182 I slot print_timing: id 3 | task 18212 | n_gen = 969, tg = 24.20 t/s, tg_3s = 25.81 t/s 14.41.146.019 I slot print_timing: id 2 | task 18867 | n_gen = 318, tg = 24.62 t/s, tg_3s = 25.82 t/s 14.42.930.637 I slot print_timing: id 0 | task 18976 | n_gen = 256, tg = 25.86 t/s, tg_3s = 25.79 t/s 14.43.242.112 I slot print_timing: id 3 | task 18212 | prompt eval time = 706.61 ms / 473 tokens ( 1.49 ms per token, 669.39 tokens per second) 14.43.242.120 I slot print_timing: id 3 | task 18212 | eval time = 42130.98 ms / 1024 tokens ( 41.18 ms per token, 24.28 tokens per second) 14.43.242.121 I slot print_timing: id 3 | task 18212 | total time = 42837.59 ms / 1497 tokens 14.43.242.121 I slot print_timing: id 3 | task 18212 | graphs reused = 18326 14.43.242.122 I slot print_timing: id 3 | task 18212 | graph reallocs = 0 / 0 (same size) / (changed size) 14.43.242.236 I slot release: id 3 | task 18212 | stop processing: n_tokens = 2192, truncated = 0 14.43.276.103 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.487 14.43.282.225 I slot launch_slot_: id 3 | task 19243 | processing task, is_child = 0 14.43.915.330 I slot print_timing: id 1 | task 18705 | n_gen = 535, tg = 23.72 t/s, tg_3s = 21.49 t/s 14.44.172.032 I slot print_timing: id 2 | task 18867 | n_gen = 380, tg = 23.83 t/s, tg_3s = 20.49 t/s 14.45.957.073 I slot print_timing: id 0 | task 18976 | n_gen = 318, tg = 24.60 t/s, tg_3s = 20.49 t/s 14.46.920.907 I slot print_timing: id 1 | task 18705 | n_gen = 612, tg = 23.94 t/s, tg_3s = 25.62 t/s 14.47.190.524 I slot print_timing: id 2 | task 18867 | n_gen = 458, tg = 24.15 t/s, tg_3s = 25.84 t/s 14.47.805.890 I slot print_timing: id 3 | task 19243 | n_gen = 100, tg = 25.89 t/s, tg_3s = 26.16 t/s 14.48.957.713 I slot print_timing: id 0 | task 18976 | n_gen = 396, tg = 24.86 t/s, tg_3s = 25.99 t/s 14.49.958.900 I slot print_timing: id 1 | task 18705 | n_gen = 691, tg = 24.16 t/s, tg_3s = 26.00 t/s 14.50.190.713 I slot print_timing: id 2 | task 18867 | n_gen = 536, tg = 24.41 t/s, tg_3s = 26.00 t/s 14.50.839.462 I slot print_timing: id 3 | task 19243 | n_gen = 179, tg = 25.96 t/s, tg_3s = 26.04 t/s 14.51.996.036 I slot print_timing: id 0 | task 18976 | n_gen = 475, tg = 25.04 t/s, tg_3s = 26.00 t/s 14.52.965.973 I slot print_timing: id 1 | task 18705 | n_gen = 769, tg = 24.33 t/s, tg_3s = 25.94 t/s 14.53.198.345 I slot print_timing: id 2 | task 18867 | n_gen = 614, tg = 24.59 t/s, tg_3s = 25.93 t/s 14.53.852.763 I slot print_timing: id 3 | task 19243 | n_gen = 257, tg = 25.94 t/s, tg_3s = 25.89 t/s 14.55.009.099 I slot print_timing: id 0 | task 18976 | n_gen = 553, tg = 25.16 t/s, tg_3s = 25.89 t/s 14.55.970.919 I slot print_timing: id 1 | task 18705 | n_gen = 847, tg = 24.47 t/s, tg_3s = 25.96 t/s 14.56.202.293 I slot print_timing: id 2 | task 18867 | n_gen = 692, tg = 24.74 t/s, tg_3s = 25.97 t/s 14.56.859.806 I slot print_timing: id 3 | task 19243 | n_gen = 335, tg = 25.94 t/s, tg_3s = 25.94 t/s 14.58.020.072 I slot print_timing: id 0 | task 18976 | n_gen = 631, tg = 25.25 t/s, tg_3s = 25.91 t/s 14.58.990.180 I slot print_timing: id 1 | task 18705 | n_gen = 925, tg = 24.58 t/s, tg_3s = 25.83 t/s 14.59.224.331 I slot print_timing: id 2 | task 18867 | n_gen = 770, tg = 24.84 t/s, tg_3s = 25.81 t/s 14.59.886.221 I slot print_timing: id 3 | task 19243 | n_gen = 413, tg = 25.91 t/s, tg_3s = 25.77 t/s 15.01.049.964 I slot print_timing: id 0 | task 18976 | n_gen = 709, tg = 25.30 t/s, tg_3s = 25.74 t/s 15.02.024.894 I slot print_timing: id 1 | task 18705 | n_gen = 1003, tg = 24.66 t/s, tg_3s = 25.70 t/s 15.02.258.020 I slot print_timing: id 2 | task 18867 | n_gen = 848, tg = 24.92 t/s, tg_3s = 25.71 t/s 15.02.839.289 I slot print_timing: id 1 | task 18705 | prompt eval time = 746.95 ms / 497 tokens ( 1.50 ms per token, 665.38 tokens per second) 15.02.839.293 I slot print_timing: id 1 | task 18705 | eval time = 41439.07 ms / 1024 tokens ( 40.51 ms per token, 24.69 tokens per second) 15.02.839.296 I slot print_timing: id 1 | task 18705 | total time = 42186.01 ms / 1521 tokens 15.02.839.296 I slot print_timing: id 1 | task 18705 | graphs reused = 18811 15.02.839.297 I slot print_timing: id 1 | task 18705 | graph reallocs = 0 / 0 (same size) / (changed size) 15.02.839.420 I slot release: id 1 | task 18705 | stop processing: n_tokens = 2184, truncated = 0 15.02.879.966 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.489 15.02.886.061 I slot launch_slot_: id 1 | task 19735 | processing task, is_child = 0 15.03.535.923 I slot print_timing: id 3 | task 19243 | n_gen = 491, tg = 25.06 t/s, tg_3s = 21.37 t/s 15.04.084.960 I slot print_timing: id 0 | task 18976 | n_gen = 770, tg = 24.79 t/s, tg_3s = 20.10 t/s 15.05.282.164 I slot print_timing: id 2 | task 18867 | n_gen = 909, tg = 24.53 t/s, tg_3s = 20.17 t/s 15.05.321.351 I slot print_timing: id 3 | task 19243 | prompt eval time = 700.34 ms / 463 tokens ( 1.51 ms per token, 661.11 tokens per second) 15.05.321.357 I slot print_timing: id 3 | task 19243 | eval time = 21338.78 ms / 536 tokens ( 39.89 ms per token, 25.07 tokens per second) 15.05.321.358 I slot print_timing: id 3 | task 19243 | total time = 22039.12 ms / 999 tokens 15.05.321.359 I slot print_timing: id 3 | task 19243 | graphs reused = 18853 15.05.321.360 I slot print_timing: id 3 | task 19243 | graph reallocs = 0 / 0 (same size) / (changed size) 15.05.321.469 I slot release: id 3 | task 19243 | stop processing: n_tokens = 1694, truncated = 0 15.05.355.187 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.630 15.05.355.216 I slot launch_slot_: id 3 | task 19783 | processing task, is_child = 0 15.07.110.882 I slot print_timing: id 0 | task 18976 | n_gen = 833, tg = 24.44 t/s, tg_3s = 20.82 t/s 15.08.034.681 I slot print_timing: id 1 | task 19735 | n_gen = 100, tg = 22.37 t/s, tg_3s = 22.60 t/s 15.08.149.246 I slot print_timing: id 0 | task 18976 | prompt eval time = 695.01 ms / 472 tokens ( 1.47 ms per token, 679.13 tokens per second) 15.08.149.253 I slot print_timing: id 0 | task 18976 | eval time = 35080.47 ms / 860 tokens ( 40.84 ms per token, 24.49 tokens per second) 15.08.149.253 I slot print_timing: id 0 | task 18976 | total time = 35775.48 ms / 1332 tokens 15.08.149.254 I slot print_timing: id 0 | task 18976 | graphs reused = 18907 15.08.149.255 I slot print_timing: id 0 | task 18976 | graph reallocs = 0 / 0 (same size) / (changed size) 15.08.149.353 I slot release: id 0 | task 18976 | stop processing: n_tokens = 2026, truncated = 0 15.08.183.755 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.527 15.08.183.790 I slot launch_slot_: id 0 | task 19842 | processing task, is_child = 0 15.08.842.984 I slot print_timing: id 2 | task 18867 | n_gen = 970, tg = 23.88 t/s, tg_3s = 17.13 t/s 15.10.493.299 I slot print_timing: id 3 | task 19783 | n_gen = 100, tg = 22.18 t/s, tg_3s = 22.40 t/s 15.10.954.735 I slot print_timing: id 2 | task 18867 | prompt eval time = 722.70 ms / 480 tokens ( 1.51 ms per token, 664.18 tokens per second) 15.10.954.739 I slot print_timing: id 2 | task 18867 | eval time = 42684.07 ms / 1024 tokens ( 41.72 ms per token, 23.97 tokens per second) 15.10.954.740 I slot print_timing: id 2 | task 18867 | total time = 43406.76 ms / 1504 tokens 15.10.954.741 I slot print_timing: id 2 | task 18867 | graphs reused = 18960 15.10.954.741 I slot print_timing: id 2 | task 18867 | graph reallocs = 0 / 0 (same size) / (changed size) 15.10.954.842 I slot release: id 2 | task 18867 | stop processing: n_tokens = 2198, truncated = 0 15.10.994.328 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.486 15.11.000.327 I slot launch_slot_: id 2 | task 19899 | processing task, is_child = 0 15.11.607.526 I slot print_timing: id 1 | task 19735 | n_gen = 161, tg = 20.00 t/s, tg_3s = 17.07 t/s 15.13.331.456 I slot print_timing: id 0 | task 19842 | n_gen = 100, tg = 22.38 t/s, tg_3s = 22.60 t/s 15.13.526.239 I slot print_timing: id 3 | task 19783 | n_gen = 163, tg = 21.61 t/s, tg_3s = 20.77 t/s 15.14.642.137 I slot print_timing: id 1 | task 19735 | n_gen = 239, tg = 21.57 t/s, tg_3s = 25.70 t/s 15.15.489.965 I slot print_timing: id 2 | task 19899 | n_gen = 100, tg = 25.99 t/s, tg_3s = 26.25 t/s 15.16.368.218 I slot print_timing: id 0 | task 19842 | n_gen = 179, tg = 23.86 t/s, tg_3s = 26.01 t/s 15.16.561.962 I slot print_timing: id 3 | task 19783 | n_gen = 242, tg = 22.88 t/s, tg_3s = 26.02 t/s 15.17.676.215 I slot print_timing: id 1 | task 19735 | n_gen = 318, tg = 22.54 t/s, tg_3s = 26.04 t/s 15.18.523.211 I slot print_timing: id 2 | task 19899 | n_gen = 179, tg = 26.01 t/s, tg_3s = 26.04 t/s 15.19.405.170 I slot print_timing: id 0 | task 19842 | n_gen = 258, tg = 24.48 t/s, tg_3s = 26.01 t/s 15.19.598.884 I slot print_timing: id 3 | task 19783 | n_gen = 321, tg = 23.58 t/s, tg_3s = 26.01 t/s 15.20.677.436 I slot print_timing: id 1 | task 19735 | n_gen = 396, tg = 23.14 t/s, tg_3s = 25.99 t/s 15.21.294.404 I slot print_timing: id 1 | task 19735 | prompt eval time = 723.29 ms / 480 tokens ( 1.51 ms per token, 663.63 tokens per second) 15.21.294.411 I slot print_timing: id 1 | task 19735 | eval time = 17685.04 ms / 412 tokens ( 43.03 ms per token, 23.24 tokens per second) 15.21.294.412 I slot print_timing: id 1 | task 19735 | total time = 18408.33 ms / 892 tokens 15.21.294.413 I slot print_timing: id 1 | task 19735 | graphs reused = 19208 15.21.294.414 I slot print_timing: id 1 | task 19735 | graph reallocs = 0 / 0 (same size) / (changed size) 15.21.294.525 I slot release: id 1 | task 19735 | stop processing: n_tokens = 1555, truncated = 0 15.21.336.285 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.687 15.21.336.340 I slot launch_slot_: id 1 | task 20153 | processing task, is_child = 0 15.21.987.366 I slot print_timing: id 2 | task 19899 | n_gen = 253, tg = 24.45 t/s, tg_3s = 21.36 t/s 15.22.413.642 I slot print_timing: id 0 | task 19842 | n_gen = 319, tg = 23.54 t/s, tg_3s = 20.28 t/s 15.22.608.603 I slot print_timing: id 3 | task 19783 | n_gen = 382, tg = 22.98 t/s, tg_3s = 20.27 t/s 15.24.999.836 I slot print_timing: id 2 | task 19899 | n_gen = 330, tg = 24.70 t/s, tg_3s = 25.56 t/s 15.25.420.860 I slot print_timing: id 0 | task 19842 | n_gen = 397, tg = 23.98 t/s, tg_3s = 25.94 t/s 15.25.615.641 I slot print_timing: id 3 | task 19783 | n_gen = 460, tg = 23.43 t/s, tg_3s = 25.94 t/s 15.25.883.580 I slot print_timing: id 1 | task 20153 | n_gen = 100, tg = 25.89 t/s, tg_3s = 26.16 t/s 15.28.008.558 I slot print_timing: id 2 | task 19899 | n_gen = 408, tg = 24.93 t/s, tg_3s = 25.92 t/s 15.28.431.815 I slot print_timing: id 0 | task 19842 | n_gen = 475, tg = 24.28 t/s, tg_3s = 25.91 t/s 15.28.626.931 I slot print_timing: id 3 | task 19783 | n_gen = 538, tg = 23.76 t/s, tg_3s = 25.90 t/s 15.28.896.514 I slot print_timing: id 1 | task 20153 | n_gen = 178, tg = 25.89 t/s, tg_3s = 25.89 t/s 15.31.021.614 I slot print_timing: id 2 | task 19899 | n_gen = 486, tg = 25.08 t/s, tg_3s = 25.89 t/s 15.31.445.148 I slot print_timing: id 0 | task 19842 | n_gen = 553, tg = 24.49 t/s, tg_3s = 25.88 t/s 15.31.640.757 I slot print_timing: id 3 | task 19783 | n_gen = 616, tg = 24.01 t/s, tg_3s = 25.88 t/s 15.31.909.358 I slot print_timing: id 1 | task 20153 | n_gen = 256, tg = 25.89 t/s, tg_3s = 25.89 t/s 15.34.039.703 I slot print_timing: id 2 | task 19899 | n_gen = 564, tg = 25.18 t/s, tg_3s = 25.84 t/s 15.34.462.710 I slot print_timing: id 0 | task 19842 | n_gen = 631, tg = 24.65 t/s, tg_3s = 25.85 t/s 15.34.658.605 I slot print_timing: id 3 | task 19783 | n_gen = 694, tg = 24.21 t/s, tg_3s = 25.85 t/s 15.34.851.670 I slot print_timing: id 2 | task 19899 | prompt eval time = 679.83 ms / 435 tokens ( 1.56 ms per token, 639.87 tokens per second) 15.34.851.677 I slot print_timing: id 2 | task 19899 | eval time = 23171.50 ms / 585 tokens ( 39.68 ms per token, 25.20 tokens per second) 15.34.851.678 I slot print_timing: id 2 | task 19899 | total time = 23851.33 ms / 1020 tokens 15.34.851.679 I slot print_timing: id 2 | task 19899 | graphs reused = 19536 15.34.851.679 I slot print_timing: id 2 | task 19899 | graph reallocs = 0 / 0 (same size) / (changed size) 15.34.851.779 I slot release: id 2 | task 19899 | stop processing: n_tokens = 1714, truncated = 0 15.34.891.749 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.623 15.34.891.784 I slot launch_slot_: id 2 | task 20488 | processing task, is_child = 0 15.35.503.420 I slot print_timing: id 1 | task 20153 | n_gen = 334, tg = 24.77 t/s, tg_3s = 21.70 t/s 15.37.469.495 I slot print_timing: id 0 | task 19842 | n_gen = 693, tg = 24.23 t/s, tg_3s = 20.62 t/s 15.37.664.759 I slot print_timing: id 3 | task 19783 | n_gen = 756, tg = 23.87 t/s, tg_3s = 20.62 t/s 15.38.512.084 I slot print_timing: id 1 | task 20153 | n_gen = 411, tg = 24.92 t/s, tg_3s = 25.59 t/s 15.39.401.826 I slot print_timing: id 2 | task 20488 | n_gen = 100, tg = 25.88 t/s, tg_3s = 26.14 t/s 15.40.480.633 I slot print_timing: id 0 | task 19842 | n_gen = 771, tg = 24.39 t/s, tg_3s = 25.90 t/s 15.40.675.319 I slot print_timing: id 3 | task 19783 | n_gen = 834, tg = 24.04 t/s, tg_3s = 25.91 t/s 15.41.526.412 I slot print_timing: id 1 | task 20153 | n_gen = 489, tg = 25.07 t/s, tg_3s = 25.88 t/s 15.42.418.369 I slot print_timing: id 2 | task 20488 | n_gen = 178, tg = 25.87 t/s, tg_3s = 25.86 t/s 15.43.505.894 I slot print_timing: id 0 | task 19842 | n_gen = 849, tg = 24.51 t/s, tg_3s = 25.78 t/s 15.43.704.188 I slot print_timing: id 3 | task 19783 | n_gen = 912, tg = 24.18 t/s, tg_3s = 25.75 t/s 15.44.557.429 I slot print_timing: id 1 | task 20153 | n_gen = 567, tg = 25.16 t/s, tg_3s = 25.73 t/s 15.44.790.531 I slot print_timing: id 3 | task 19783 | prompt eval time = 673.76 ms / 442 tokens ( 1.52 ms per token, 656.02 tokens per second) 15.44.790.538 I slot print_timing: id 3 | task 19783 | eval time = 38761.55 ms / 940 tokens ( 41.28 ms per token, 24.23 tokens per second) 15.44.790.539 I slot print_timing: id 3 | task 19783 | total time = 39435.31 ms / 1382 tokens 15.44.790.540 I slot print_timing: id 3 | task 19783 | graphs reused = 19772 15.44.790.541 I slot print_timing: id 3 | task 19783 | graph reallocs = 0 / 0 (same size) / (changed size) 15.44.790.641 I slot release: id 3 | task 19783 | stop processing: n_tokens = 2077, truncated = 0 15.44.824.303 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.514 15.44.824.335 I slot launch_slot_: id 3 | task 20730 | processing task, is_child = 0 15.45.454.746 I slot print_timing: id 2 | task 20488 | n_gen = 241, tg = 24.29 t/s, tg_3s = 20.75 t/s 15.46.530.263 I slot print_timing: id 0 | task 19842 | n_gen = 911, tg = 24.19 t/s, tg_3s = 20.50 t/s 15.47.576.351 I slot print_timing: id 1 | task 20153 | n_gen = 629, tg = 24.61 t/s, tg_3s = 20.54 t/s 15.48.467.916 I slot print_timing: id 2 | task 20488 | n_gen = 318, tg = 24.59 t/s, tg_3s = 25.55 t/s 15.49.359.403 I slot print_timing: id 3 | task 20730 | n_gen = 100, tg = 25.80 t/s, tg_3s = 26.06 t/s 15.49.552.173 I slot print_timing: id 0 | task 19842 | n_gen = 989, tg = 24.31 t/s, tg_3s = 25.81 t/s 15.49.980.749 I slot print_timing: id 2 | task 20488 | prompt eval time = 684.24 ms / 443 tokens ( 1.54 ms per token, 647.43 tokens per second) 15.49.980.755 I slot print_timing: id 2 | task 20488 | eval time = 14404.72 ms / 357 tokens ( 40.46 ms per token, 24.71 tokens per second) 15.49.980.756 I slot print_timing: id 2 | task 20488 | total time = 15088.96 ms / 800 tokens 15.49.980.757 I slot print_timing: id 2 | task 20488 | graphs reused = 19886 15.49.980.757 I slot print_timing: id 2 | task 20488 | graph reallocs = 0 / 0 (same size) / (changed size) 15.49.980.858 I slot release: id 2 | task 20488 | stop processing: n_tokens = 1494, truncated = 0 15.50.021.436 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.715 15.50.021.471 I slot launch_slot_: id 2 | task 20849 | processing task, is_child = 0 15.50.664.220 I slot print_timing: id 1 | task 20153 | n_gen = 693, tg = 24.19 t/s, tg_3s = 20.73 t/s 15.51.554.870 I slot print_timing: id 0 | task 19842 | prompt eval time = 723.10 ms / 497 tokens ( 1.45 ms per token, 687.32 tokens per second) 15.51.554.875 I slot print_timing: id 0 | task 19842 | eval time = 42647.97 ms / 1024 tokens ( 41.69 ms per token, 23.99 tokens per second) 15.51.554.875 I slot print_timing: id 0 | task 19842 | total time = 43371.07 ms / 1521 tokens 15.51.554.876 I slot print_timing: id 0 | task 19842 | graphs reused = 19906 15.51.554.877 I slot print_timing: id 0 | task 19842 | graph reallocs = 0 / 0 (same size) / (changed size) 15.51.554.974 I slot release: id 0 | task 19842 | stop processing: n_tokens = 2215, truncated = 0 15.51.589.859 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.482 15.51.595.701 I slot launch_slot_: id 0 | task 20874 | processing task, is_child = 0 15.52.373.146 I slot print_timing: id 3 | task 20730 | n_gen = 146, tg = 21.16 t/s, tg_3s = 15.26 t/s 15.53.687.153 I slot print_timing: id 1 | task 20153 | n_gen = 755, tg = 23.84 t/s, tg_3s = 20.51 t/s 15.55.148.524 I slot print_timing: id 2 | task 20849 | n_gen = 100, tg = 22.44 t/s, tg_3s = 22.67 t/s 15.55.381.043 I slot print_timing: id 3 | task 20730 | n_gen = 224, tg = 22.62 t/s, tg_3s = 25.93 t/s 15.56.070.829 I slot print_timing: id 0 | task 20874 | n_gen = 100, tg = 25.97 t/s, tg_3s = 26.23 t/s 15.56.688.783 I slot print_timing: id 1 | task 20153 | n_gen = 833, tg = 24.03 t/s, tg_3s = 25.99 t/s 15.58.153.960 I slot print_timing: id 2 | task 20849 | n_gen = 178, tg = 23.86 t/s, tg_3s = 25.95 t/s 15.58.385.552 I slot print_timing: id 3 | task 20730 | n_gen = 302, tg = 23.40 t/s, tg_3s = 25.96 t/s 15.59.078.287 I slot print_timing: id 0 | task 20874 | n_gen = 178, tg = 25.95 t/s, tg_3s = 25.94 t/s 15.59.701.709 I slot print_timing: id 1 | task 20153 | n_gen = 911, tg = 24.18 t/s, tg_3s = 25.89 t/s 16.01.177.017 I slot print_timing: id 2 | task 20849 | n_gen = 256, tg = 24.43 t/s, tg_3s = 25.80 t/s 16.01.408.891 I slot print_timing: id 3 | task 20730 | n_gen = 380, tg = 23.86 t/s, tg_3s = 25.80 t/s 16.02.102.825 I slot print_timing: id 0 | task 20874 | n_gen = 256, tg = 25.90 t/s, tg_3s = 25.79 t/s 16.02.722.691 I slot print_timing: id 1 | task 20153 | n_gen = 989, tg = 24.30 t/s, tg_3s = 25.82 t/s 16.03.494.928 I slot print_timing: id 0 | task 20874 | prompt eval time = 662.34 ms / 439 tokens ( 1.51 ms per token, 662.81 tokens per second) 16.03.494.935 I slot print_timing: id 0 | task 20874 | eval time = 11236.88 ms / 292 tokens ( 38.61 ms per token, 25.90 tokens per second) 16.03.494.936 I slot print_timing: id 0 | task 20874 | total time = 11899.22 ms / 731 tokens 16.03.494.937 I slot print_timing: id 0 | task 20874 | graphs reused = 20196 16.03.494.938 I slot print_timing: id 0 | task 20874 | graph reallocs = 0 / 0 (same size) / (changed size) 16.03.495.031 I slot release: id 0 | task 20874 | stop processing: n_tokens = 1425, truncated = 0 16.03.530.419 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.749 16.03.530.457 I slot launch_slot_: id 0 | task 21169 | processing task, is_child = 0 16.04.261.135 I slot print_timing: id 2 | task 20849 | n_gen = 319, tg = 23.51 t/s, tg_3s = 20.43 t/s 16.04.440.803 I slot print_timing: id 3 | task 20730 | n_gen = 441, tg = 23.26 t/s, tg_3s = 20.12 t/s 16.04.744.717 I slot print_timing: id 1 | task 20153 | prompt eval time = 724.00 ms / 479 tokens ( 1.51 ms per token, 661.61 tokens per second) 16.04.744.729 I slot print_timing: id 1 | task 20153 | eval time = 42684.36 ms / 1024 tokens ( 41.72 ms per token, 23.97 tokens per second) 16.04.744.731 I slot print_timing: id 1 | task 20153 | total time = 43408.35 ms / 1503 tokens 16.04.744.732 I slot print_timing: id 1 | task 20153 | graphs reused = 20207 16.04.744.733 I slot print_timing: id 1 | task 20153 | graph reallocs = 0 / 0 (same size) / (changed size) 16.04.744.883 I slot release: id 1 | task 20153 | stop processing: n_tokens = 2166, truncated = 0 16.04.789.419 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.493 16.04.796.970 I slot launch_slot_: id 1 | task 21185 | processing task, is_child = 0 16.07.275.520 I slot print_timing: id 2 | task 20849 | n_gen = 379, tg = 22.86 t/s, tg_3s = 19.90 t/s 16.07.469.420 I slot print_timing: id 3 | task 20730 | n_gen = 502, tg = 22.83 t/s, tg_3s = 20.14 t/s 16.08.818.894 I slot print_timing: id 0 | task 21169 | n_gen = 100, tg = 22.03 t/s, tg_3s = 22.26 t/s 16.09.360.103 I slot print_timing: id 1 | task 21185 | n_gen = 100, tg = 25.89 t/s, tg_3s = 26.15 t/s 16.10.287.963 I slot print_timing: id 2 | task 20849 | n_gen = 457, tg = 23.32 t/s, tg_3s = 25.89 t/s 16.10.481.286 I slot print_timing: id 3 | task 20730 | n_gen = 580, tg = 23.20 t/s, tg_3s = 25.90 t/s 16.11.829.249 I slot print_timing: id 0 | task 21169 | n_gen = 178, tg = 23.59 t/s, tg_3s = 25.91 t/s 16.12.370.709 I slot print_timing: id 1 | task 21185 | n_gen = 178, tg = 25.90 t/s, tg_3s = 25.91 t/s 16.13.298.435 I slot print_timing: id 2 | task 20849 | n_gen = 535, tg = 23.67 t/s, tg_3s = 25.91 t/s 16.13.492.864 I slot print_timing: id 3 | task 20730 | n_gen = 658, tg = 23.49 t/s, tg_3s = 25.90 t/s 16.13.686.637 I slot print_timing: id 3 | task 20730 | prompt eval time = 697.37 ms / 461 tokens ( 1.51 ms per token, 661.06 tokens per second) 16.13.686.641 I slot print_timing: id 3 | task 20730 | eval time = 28164.92 ms / 663 tokens ( 42.55 ms per token, 23.50 tokens per second) 16.13.686.641 I slot print_timing: id 3 | task 20730 | total time = 28862.29 ms / 1124 tokens 16.13.686.642 I slot print_timing: id 3 | task 20730 | graphs reused = 20416 16.13.686.643 I slot print_timing: id 3 | task 20730 | graph reallocs = 0 / 0 (same size) / (changed size) 16.13.686.741 I slot release: id 3 | task 20730 | stop processing: n_tokens = 1819, truncated = 0 16.13.720.472 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.587 16.13.720.508 I slot launch_slot_: id 3 | task 21400 | processing task, is_child = 0 16.14.840.799 I slot print_timing: id 0 | task 21169 | n_gen = 239, tg = 22.63 t/s, tg_3s = 20.26 t/s 16.15.382.337 I slot print_timing: id 1 | task 21185 | n_gen = 239, tg = 24.17 t/s, tg_3s = 20.25 t/s 16.16.312.185 I slot print_timing: id 2 | task 20849 | n_gen = 596, tg = 23.26 t/s, tg_3s = 20.24 t/s 16.17.854.849 I slot print_timing: id 0 | task 21169 | n_gen = 317, tg = 23.36 t/s, tg_3s = 25.88 t/s 16.18.281.891 I slot print_timing: id 3 | task 21400 | n_gen = 100, tg = 25.85 t/s, tg_3s = 26.11 t/s 16.18.397.301 I slot print_timing: id 1 | task 21185 | n_gen = 317, tg = 24.57 t/s, tg_3s = 25.87 t/s 16.19.325.261 I slot print_timing: id 2 | task 20849 | n_gen = 674, tg = 23.54 t/s, tg_3s = 25.89 t/s 16.20.863.460 I slot print_timing: id 0 | task 21169 | n_gen = 395, tg = 23.82 t/s, tg_3s = 25.93 t/s 16.21.287.893 I slot print_timing: id 3 | task 21400 | n_gen = 178, tg = 25.89 t/s, tg_3s = 25.95 t/s 16.21.401.919 I slot print_timing: id 1 | task 21185 | n_gen = 395, tg = 24.83 t/s, tg_3s = 25.96 t/s 16.22.329.850 I slot print_timing: id 2 | task 20849 | n_gen = 752, tg = 23.77 t/s, tg_3s = 25.96 t/s 16.23.872.257 I slot print_timing: id 0 | task 21169 | n_gen = 473, tg = 24.15 t/s, tg_3s = 25.92 t/s 16.24.298.848 I slot print_timing: id 3 | task 21400 | n_gen = 256, tg = 25.90 t/s, tg_3s = 25.91 t/s 16.24.413.277 I slot print_timing: id 1 | task 21185 | n_gen = 473, tg = 25.00 t/s, tg_3s = 25.90 t/s 16.25.347.182 I slot print_timing: id 2 | task 20849 | n_gen = 830, tg = 23.95 t/s, tg_3s = 25.85 t/s 16.26.890.138 I slot print_timing: id 0 | task 21169 | n_gen = 551, tg = 24.37 t/s, tg_3s = 25.85 t/s 16.27.317.224 I slot print_timing: id 3 | task 21400 | n_gen = 334, tg = 25.88 t/s, tg_3s = 25.84 t/s 16.27.432.360 I slot print_timing: id 1 | task 21185 | n_gen = 551, tg = 25.12 t/s, tg_3s = 25.84 t/s 16.28.365.657 I slot print_timing: id 2 | task 20849 | n_gen = 908, tg = 24.10 t/s, tg_3s = 25.84 t/s 16.29.920.373 I slot print_timing: id 0 | task 21169 | n_gen = 629, tg = 24.54 t/s, tg_3s = 25.74 t/s 16.30.350.425 I slot print_timing: id 3 | task 21400 | n_gen = 412, tg = 25.85 t/s, tg_3s = 25.72 t/s 16.30.466.053 I slot print_timing: id 1 | task 21185 | n_gen = 629, tg = 25.19 t/s, tg_3s = 25.71 t/s 16.31.399.858 I slot print_timing: id 2 | task 20849 | n_gen = 986, tg = 24.22 t/s, tg_3s = 25.71 t/s 16.32.875.427 I slot print_timing: id 2 | task 20849 | prompt eval time = 715.65 ms / 470 tokens ( 1.52 ms per token, 656.74 tokens per second) 16.32.875.435 I slot print_timing: id 2 | task 20849 | eval time = 42138.29 ms / 1024 tokens ( 41.19 ms per token, 24.28 tokens per second) 16.32.875.437 I slot print_timing: id 2 | task 20849 | total time = 42853.94 ms / 1494 tokens 16.32.875.438 I slot print_timing: id 2 | task 20849 | graphs reused = 20889 16.32.875.439 I slot print_timing: id 2 | task 20849 | graph reallocs = 0 / 0 (same size) / (changed size) 16.32.875.553 I slot release: id 2 | task 20849 | stop processing: n_tokens = 2188, truncated = 0 16.32.916.355 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.488 16.32.922.263 I slot launch_slot_: id 2 | task 21880 | processing task, is_child = 0 16.33.556.140 I slot print_timing: id 0 | task 21169 | n_gen = 707, tg = 24.15 t/s, tg_3s = 21.45 t/s 16.33.556.477 I slot print_timing: id 1 | task 21185 | n_gen = 693, tg = 24.70 t/s, tg_3s = 20.71 t/s 16.33.556.779 I slot print_timing: id 3 | task 21400 | n_gen = 479, tg = 25.02 t/s, tg_3s = 20.90 t/s 16.36.573.886 I slot print_timing: id 0 | task 21169 | n_gen = 784, tg = 24.28 t/s, tg_3s = 25.52 t/s 16.36.574.494 I slot print_timing: id 1 | task 21185 | n_gen = 770, tg = 24.78 t/s, tg_3s = 25.51 t/s 16.36.575.589 I slot print_timing: id 3 | task 21400 | n_gen = 556, tg = 25.09 t/s, tg_3s = 25.51 t/s 16.37.466.541 I slot print_timing: id 2 | task 21880 | n_gen = 100, tg = 25.80 t/s, tg_3s = 26.06 t/s 16.39.600.018 I slot print_timing: id 0 | task 21169 | n_gen = 862, tg = 24.41 t/s, tg_3s = 25.78 t/s 16.39.600.573 I slot print_timing: id 1 | task 21185 | n_gen = 848, tg = 24.86 t/s, tg_3s = 25.78 t/s 16.39.601.743 I slot print_timing: id 3 | task 21400 | n_gen = 634, tg = 25.17 t/s, tg_3s = 25.78 t/s 16.40.497.058 I slot print_timing: id 2 | task 21880 | n_gen = 178, tg = 25.77 t/s, tg_3s = 25.74 t/s 16.42.635.844 I slot print_timing: id 0 | task 21169 | n_gen = 940, tg = 24.51 t/s, tg_3s = 25.69 t/s 16.42.636.404 I slot print_timing: id 1 | task 21185 | n_gen = 926, tg = 24.93 t/s, tg_3s = 25.69 t/s 16.42.637.583 I slot print_timing: id 3 | task 21400 | n_gen = 712, tg = 25.23 t/s, tg_3s = 25.69 t/s 16.43.531.304 I slot print_timing: id 2 | task 21880 | n_gen = 256, tg = 25.75 t/s, tg_3s = 25.71 t/s 16.45.663.260 I slot print_timing: id 0 | task 21169 | n_gen = 1018, tg = 24.60 t/s, tg_3s = 25.76 t/s 16.45.663.822 I slot print_timing: id 1 | task 21185 | n_gen = 1004, tg = 25.00 t/s, tg_3s = 25.76 t/s 16.45.664.947 I slot print_timing: id 3 | task 21400 | n_gen = 790, tg = 25.28 t/s, tg_3s = 25.76 t/s 16.45.895.762 I slot print_timing: id 0 | task 21169 | prompt eval time = 795.24 ms / 519 tokens ( 1.53 ms per token, 652.64 tokens per second) 16.45.895.768 I slot print_timing: id 0 | task 21169 | eval time = 41570.06 ms / 1024 tokens ( 40.64 ms per token, 24.61 tokens per second) 16.45.895.769 I slot print_timing: id 0 | task 21169 | total time = 42365.30 ms / 1543 tokens 16.45.895.770 I slot print_timing: id 0 | task 21169 | graphs reused = 21203 16.45.895.771 I slot print_timing: id 0 | task 21169 | graph reallocs = 0 / 0 (same size) / (changed size) 16.45.895.882 I slot release: id 0 | task 21169 | stop processing: n_tokens = 2237, truncated = 0 16.45.931.572 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.477 16.45.937.948 I slot launch_slot_: id 0 | task 22200 | processing task, is_child = 0 16.46.573.075 I slot print_timing: id 2 | task 21880 | n_gen = 319, tg = 24.57 t/s, tg_3s = 20.71 t/s 16.47.068.873 I slot print_timing: id 1 | task 21185 | prompt eval time = 739.51 ms / 487 tokens ( 1.52 ms per token, 658.54 tokens per second) 16.47.068.878 I slot print_timing: id 1 | task 21185 | eval time = 41532.37 ms / 1024 tokens ( 40.60 ms per token, 24.63 tokens per second) 16.47.068.878 I slot print_timing: id 1 | task 21185 | total time = 42271.88 ms / 1511 tokens 16.47.068.879 I slot print_timing: id 1 | task 21185 | graphs reused = 21214 16.47.068.880 I slot print_timing: id 1 | task 21185 | graph reallocs = 0 / 0 (same size) / (changed size) 16.47.069.003 I slot release: id 1 | task 21185 | stop processing: n_tokens = 2174, truncated = 0 16.47.110.244 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.491 16.47.116.641 I slot launch_slot_: id 1 | task 22215 | processing task, is_child = 0 16.48.669.051 I slot print_timing: id 3 | task 21400 | n_gen = 834, tg = 24.34 t/s, tg_3s = 14.65 t/s 16.49.596.317 I slot print_timing: id 2 | task 21880 | n_gen = 379, tg = 23.67 t/s, tg_3s = 19.85 t/s 16.51.136.855 I slot print_timing: id 0 | task 22200 | n_gen = 100, tg = 22.00 t/s, tg_3s = 22.23 t/s 16.51.678.147 I slot print_timing: id 1 | task 22215 | n_gen = 100, tg = 25.90 t/s, tg_3s = 26.17 t/s 16.51.679.163 I slot print_timing: id 3 | task 21400 | n_gen = 912, tg = 24.47 t/s, tg_3s = 25.91 t/s 16.52.610.707 I slot print_timing: id 2 | task 21880 | n_gen = 457, tg = 24.02 t/s, tg_3s = 25.88 t/s 16.54.153.584 I slot print_timing: id 0 | task 22200 | n_gen = 178, tg = 23.55 t/s, tg_3s = 25.86 t/s 16.54.695.612 I slot print_timing: id 1 | task 22215 | n_gen = 178, tg = 25.88 t/s, tg_3s = 25.85 t/s 16.54.696.700 I slot print_timing: id 3 | task 21400 | n_gen = 990, tg = 24.57 t/s, tg_3s = 25.85 t/s 16.55.625.813 I slot print_timing: id 2 | task 21880 | n_gen = 535, tg = 24.28 t/s, tg_3s = 25.87 t/s 16.56.014.638 I slot print_timing: id 3 | task 21400 | prompt eval time = 730.99 ms / 496 tokens ( 1.47 ms per token, 678.53 tokens per second) 16.56.014.643 I slot print_timing: id 3 | task 21400 | eval time = 41563.13 ms / 1024 tokens ( 40.63 ms per token, 24.61 tokens per second) 16.56.014.644 I slot print_timing: id 3 | task 21400 | total time = 42294.12 ms / 1520 tokens 16.56.014.645 I slot print_timing: id 3 | task 21400 | graphs reused = 21423 16.56.014.645 I slot print_timing: id 3 | task 21400 | graph reallocs = 0 / 0 (same size) / (changed size) 16.56.014.760 I slot release: id 3 | task 21400 | stop processing: n_tokens = 2215, truncated = 0 16.56.048.432 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.482 16.56.054.559 I slot launch_slot_: id 3 | task 22430 | processing task, is_child = 0 16.57.185.874 I slot print_timing: id 0 | task 22200 | n_gen = 240, tg = 22.66 t/s, tg_3s = 20.45 t/s 16.57.725.519 I slot print_timing: id 1 | task 22215 | n_gen = 240, tg = 24.22 t/s, tg_3s = 20.46 t/s 16.58.652.142 I slot print_timing: id 2 | task 21880 | n_gen = 597, tg = 23.82 t/s, tg_3s = 20.49 t/s 17.00.189.950 I slot print_timing: id 0 | task 22200 | n_gen = 318, tg = 23.39 t/s, tg_3s = 25.96 t/s 17.00.578.051 I slot print_timing: id 3 | task 22430 | n_gen = 100, tg = 25.96 t/s, tg_3s = 26.22 t/s 17.00.730.847 I slot print_timing: id 1 | task 22215 | n_gen = 318, tg = 24.62 t/s, tg_3s = 25.95 t/s 17.01.654.294 I slot print_timing: id 2 | task 21880 | n_gen = 675, tg = 24.05 t/s, tg_3s = 25.98 t/s 17.03.195.789 I slot print_timing: id 0 | task 22200 | n_gen = 396, tg = 23.86 t/s, tg_3s = 25.95 t/s 17.03.585.466 I slot print_timing: id 3 | task 22430 | n_gen = 178, tg = 25.95 t/s, tg_3s = 25.94 t/s 17.03.738.898 I slot print_timing: id 1 | task 22215 | n_gen = 396, tg = 24.87 t/s, tg_3s = 25.93 t/s 17.04.668.767 I slot print_timing: id 2 | task 21880 | n_gen = 753, tg = 24.23 t/s, tg_3s = 25.88 t/s 17.06.213.398 I slot print_timing: id 0 | task 22200 | n_gen = 474, tg = 24.16 t/s, tg_3s = 25.85 t/s 17.06.599.644 I slot print_timing: id 3 | task 22430 | n_gen = 256, tg = 25.93 t/s, tg_3s = 25.88 t/s 17.06.752.780 I slot print_timing: id 1 | task 22215 | n_gen = 474, tg = 25.03 t/s, tg_3s = 25.88 t/s 17.07.679.968 I slot print_timing: id 2 | task 21880 | n_gen = 831, tg = 24.38 t/s, tg_3s = 25.90 t/s 17.09.224.259 I slot print_timing: id 0 | task 22200 | n_gen = 552, tg = 24.40 t/s, tg_3s = 25.91 t/s 17.09.610.832 I slot print_timing: id 3 | task 22430 | n_gen = 334, tg = 25.92 t/s, tg_3s = 25.90 t/s 17.09.764.728 I slot print_timing: id 1 | task 22215 | n_gen = 552, tg = 25.15 t/s, tg_3s = 25.90 t/s 17.10.693.821 I slot print_timing: id 2 | task 21880 | n_gen = 909, tg = 24.50 t/s, tg_3s = 25.88 t/s 17.10.848.849 I slot print_timing: id 2 | task 21880 | prompt eval time = 707.12 ms / 457 tokens ( 1.55 ms per token, 646.29 tokens per second) 17.10.848.854 I slot print_timing: id 2 | task 21880 | eval time = 37219.46 ms / 913 tokens ( 40.81 ms per token, 24.50 tokens per second) 17.10.848.855 I slot print_timing: id 2 | task 21880 | total time = 37926.57 ms / 1370 tokens 17.10.848.856 I slot print_timing: id 2 | task 21880 | graphs reused = 21785 17.10.848.856 I slot print_timing: id 2 | task 21880 | graph reallocs = 0 / 0 (same size) / (changed size) 17.10.848.972 I slot release: id 2 | task 21880 | stop processing: n_tokens = 2064, truncated = 0 17.10.889.372 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.517 17.10.889.403 I slot launch_slot_: id 2 | task 22799 | processing task, is_child = 0 17.12.257.324 I slot print_timing: id 0 | task 22200 | n_gen = 614, tg = 23.93 t/s, tg_3s = 20.44 t/s 17.12.644.078 I slot print_timing: id 3 | task 22430 | n_gen = 396, tg = 24.87 t/s, tg_3s = 20.44 t/s 17.12.797.419 I slot print_timing: id 1 | task 22215 | n_gen = 614, tg = 24.58 t/s, tg_3s = 20.44 t/s 17.15.264.395 I slot print_timing: id 0 | task 22200 | n_gen = 692, tg = 24.14 t/s, tg_3s = 25.94 t/s 17.15.418.806 I slot print_timing: id 2 | task 22799 | n_gen = 100, tg = 25.93 t/s, tg_3s = 26.19 t/s 17.15.651.301 I slot print_timing: id 3 | task 22430 | n_gen = 474, tg = 25.04 t/s, tg_3s = 25.94 t/s 17.15.804.645 I slot print_timing: id 1 | task 22215 | n_gen = 692, tg = 24.72 t/s, tg_3s = 25.94 t/s 17.18.276.417 I slot print_timing: id 0 | task 22200 | n_gen = 770, tg = 24.31 t/s, tg_3s = 25.90 t/s 17.18.432.290 I slot print_timing: id 2 | task 22799 | n_gen = 178, tg = 25.91 t/s, tg_3s = 25.88 t/s 17.18.663.913 I slot print_timing: id 3 | task 22430 | n_gen = 552, tg = 25.16 t/s, tg_3s = 25.89 t/s 17.18.816.640 I slot print_timing: id 1 | task 22215 | n_gen = 770, tg = 24.84 t/s, tg_3s = 25.90 t/s 17.20.092.733 I slot print_timing: id 3 | task 22430 | prompt eval time = 709.98 ms / 478 tokens ( 1.49 ms per token, 673.26 tokens per second) 17.20.092.739 I slot print_timing: id 3 | task 22430 | eval time = 23328.18 ms / 589 tokens ( 39.67 ms per token, 25.21 tokens per second) 17.20.092.740 I slot print_timing: id 3 | task 22430 | total time = 24038.16 ms / 1067 tokens 17.20.092.741 I slot print_timing: id 3 | task 22430 | graphs reused = 22003 17.20.092.741 I slot print_timing: id 3 | task 22430 | graph reallocs = 0 / 0 (same size) / (changed size) 17.20.092.857 I slot release: id 3 | task 22430 | stop processing: n_tokens = 1762, truncated = 0 17.20.126.502 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.606 17.20.126.542 I slot launch_slot_: id 3 | task 23023 | processing task, is_child = 0 17.21.297.472 I slot print_timing: id 0 | task 22200 | n_gen = 833, tg = 24.00 t/s, tg_3s = 20.85 t/s 17.21.453.595 I slot print_timing: id 2 | task 22799 | n_gen = 241, tg = 24.36 t/s, tg_3s = 20.85 t/s 17.21.839.517 I slot print_timing: id 1 | task 22215 | n_gen = 833, tg = 24.48 t/s, tg_3s = 20.84 t/s 17.24.315.039 I slot print_timing: id 0 | task 22200 | n_gen = 911, tg = 24.15 t/s, tg_3s = 25.85 t/s 17.24.469.652 I slot print_timing: id 2 | task 22799 | n_gen = 319, tg = 24.71 t/s, tg_3s = 25.86 t/s 17.24.624.251 I slot print_timing: id 3 | task 23023 | n_gen = 100, tg = 25.88 t/s, tg_3s = 26.15 t/s 17.24.855.440 I slot print_timing: id 1 | task 22215 | n_gen = 911, tg = 24.60 t/s, tg_3s = 25.86 t/s 17.27.330.085 I slot print_timing: id 0 | task 22200 | n_gen = 989, tg = 24.28 t/s, tg_3s = 25.87 t/s 17.27.487.100 I slot print_timing: id 2 | task 22799 | n_gen = 397, tg = 24.93 t/s, tg_3s = 25.85 t/s 17.27.642.659 I slot print_timing: id 3 | task 23023 | n_gen = 178, tg = 25.87 t/s, tg_3s = 25.84 t/s 17.27.873.118 I slot print_timing: id 1 | task 22215 | n_gen = 989, tg = 24.69 t/s, tg_3s = 25.85 t/s 17.28.689.014 I slot print_timing: id 0 | task 22200 | prompt eval time = 699.78 ms / 484 tokens ( 1.45 ms per token, 691.65 tokens per second) 17.28.689.021 I slot print_timing: id 0 | task 22200 | eval time = 42051.27 ms / 1024 tokens ( 41.11 ms per token, 24.33 tokens per second) 17.28.689.022 I slot print_timing: id 0 | task 22200 | total time = 42751.05 ms / 1508 tokens 17.28.689.023 I slot print_timing: id 0 | task 22200 | graphs reused = 22205 17.28.689.023 I slot print_timing: id 0 | task 22200 | graph reallocs = 0 / 0 (same size) / (changed size) 17.28.689.124 I slot release: id 0 | task 22200 | stop processing: n_tokens = 2205, truncated = 0 17.28.724.493 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.484 17.28.731.090 I slot launch_slot_: id 0 | task 23231 | processing task, is_child = 0 17.29.837.974 I slot print_timing: id 1 | task 22215 | prompt eval time = 739.69 ms / 488 tokens ( 1.52 ms per token, 659.73 tokens per second) 17.29.837.989 I slot print_timing: id 1 | task 22215 | eval time = 41981.62 ms / 1024 tokens ( 41.04 ms per token, 24.37 tokens per second) 17.29.837.993 I slot print_timing: id 1 | task 22215 | total time = 42721.32 ms / 1512 tokens 17.29.837.994 I slot print_timing: id 1 | task 22215 | graphs reused = 22216 17.29.837.997 I slot print_timing: id 1 | task 22215 | graph reallocs = 0 / 0 (same size) / (changed size) 17.29.838.127 I slot release: id 1 | task 22215 | stop processing: n_tokens = 2175, truncated = 0 17.29.879.852 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.491 17.29.886.651 I slot launch_slot_: id 1 | task 23246 | processing task, is_child = 0 17.30.536.466 I slot print_timing: id 2 | task 22799 | n_gen = 444, tg = 23.40 t/s, tg_3s = 15.41 t/s 17.30.649.263 I slot print_timing: id 3 | task 23023 | n_gen = 223, tg = 22.54 t/s, tg_3s = 14.97 t/s 17.33.572.979 I slot print_timing: id 2 | task 22799 | n_gen = 522, tg = 23.71 t/s, tg_3s = 25.69 t/s 17.33.650.665 I slot print_timing: id 3 | task 23023 | n_gen = 301, tg = 23.34 t/s, tg_3s = 25.99 t/s 17.33.880.522 I slot print_timing: id 0 | task 23231 | n_gen = 100, tg = 22.18 t/s, tg_3s = 22.40 t/s 17.34.420.878 I slot print_timing: id 1 | task 23246 | n_gen = 100, tg = 25.98 t/s, tg_3s = 26.24 t/s 17.36.581.148 I slot print_timing: id 2 | task 22799 | n_gen = 600, tg = 23.98 t/s, tg_3s = 25.93 t/s 17.36.659.065 I slot print_timing: id 3 | task 23023 | n_gen = 379, tg = 23.83 t/s, tg_3s = 25.93 t/s 17.36.888.833 I slot print_timing: id 0 | task 23231 | n_gen = 178, tg = 23.69 t/s, tg_3s = 25.93 t/s 17.37.429.563 I slot print_timing: id 1 | task 23246 | n_gen = 178, tg = 25.96 t/s, tg_3s = 25.92 t/s 17.38.821.423 I slot print_timing: id 3 | task 23023 | prompt eval time = 672.98 ms / 443 tokens ( 1.52 ms per token, 658.26 tokens per second) 17.38.821.431 I slot print_timing: id 3 | task 23023 | eval time = 18021.89 ms / 435 tokens ( 41.53 ms per token, 24.08 tokens per second) 17.38.821.431 I slot print_timing: id 3 | task 23023 | total time = 18694.87 ms / 878 tokens 17.38.821.432 I slot print_timing: id 3 | task 23023 | graphs reused = 22427 17.38.821.433 I slot print_timing: id 3 | task 23023 | graph reallocs = 0 / 0 (same size) / (changed size) 17.38.821.533 I slot release: id 3 | task 23023 | stop processing: n_tokens = 1573, truncated = 0 17.38.855.078 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.679 17.38.855.105 I slot launch_slot_: id 3 | task 23463 | processing task, is_child = 0 17.39.585.181 I slot print_timing: id 2 | task 22799 | n_gen = 662, tg = 23.62 t/s, tg_3s = 20.64 t/s 17.39.893.807 I slot print_timing: id 0 | task 23231 | n_gen = 240, tg = 22.81 t/s, tg_3s = 20.63 t/s 17.39.934.669 I slot print_timing: id 2 | task 22799 | prompt eval time = 711.52 ms / 464 tokens ( 1.53 ms per token, 652.13 tokens per second) 17.39.934.678 I slot print_timing: id 2 | task 22799 | eval time = 28333.74 ms / 671 tokens ( 42.29 ms per token, 23.65 tokens per second) 17.39.934.681 I slot print_timing: id 2 | task 22799 | total time = 29045.26 ms / 1135 tokens 17.39.934.682 I slot print_timing: id 2 | task 22799 | graphs reused = 22436 17.39.934.683 I slot print_timing: id 2 | task 22799 | graph reallocs = 0 / 0 (same size) / (changed size) 17.39.934.818 I slot release: id 2 | task 22799 | stop processing: n_tokens = 1829, truncated = 0 17.39.976.974 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.584 17.39.977.015 I slot launch_slot_: id 2 | task 23477 | processing task, is_child = 0 17.40.663.537 I slot print_timing: id 1 | task 23246 | n_gen = 229, tg = 22.68 t/s, tg_3s = 15.77 t/s 17.42.929.563 I slot print_timing: id 0 | task 23231 | n_gen = 301, tg = 22.20 t/s, tg_3s = 20.09 t/s 17.43.663.810 I slot print_timing: id 1 | task 23246 | n_gen = 306, tg = 23.37 t/s, tg_3s = 25.66 t/s 17.44.050.204 I slot print_timing: id 3 | task 23463 | n_gen = 100, tg = 21.98 t/s, tg_3s = 22.20 t/s 17.44.547.443 I slot print_timing: id 2 | task 23477 | n_gen = 100, tg = 25.97 t/s, tg_3s = 26.24 t/s 17.45.963.762 I slot print_timing: id 0 | task 23231 | n_gen = 380, tg = 22.90 t/s, tg_3s = 26.04 t/s 17.46.466.577 I slot print_timing: id 1 | task 23246 | prompt eval time = 723.62 ms / 479 tokens ( 1.51 ms per token, 661.95 tokens per second) 17.46.466.584 I slot print_timing: id 1 | task 23246 | eval time = 15856.30 ms / 379 tokens ( 41.95 ms per token, 23.84 tokens per second) 17.46.466.585 I slot print_timing: id 1 | task 23246 | total time = 16579.91 ms / 858 tokens 17.46.466.586 I slot print_timing: id 1 | task 23246 | graphs reused = 22583 17.46.466.587 I slot print_timing: id 1 | task 23246 | graph reallocs = 0 / 0 (same size) / (changed size) 17.46.466.689 I slot release: id 1 | task 23246 | stop processing: n_tokens = 1521, truncated = 0 17.46.507.194 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.702 17.46.507.242 I slot launch_slot_: id 1 | task 23630 | processing task, is_child = 0 17.47.175.239 I slot print_timing: id 3 | task 23463 | n_gen = 165, tg = 21.50 t/s, tg_3s = 20.80 t/s 17.47.553.943 I slot print_timing: id 2 | task 23477 | n_gen = 161, tg = 23.47 t/s, tg_3s = 20.29 t/s 17.48.972.392 I slot print_timing: id 0 | task 23231 | n_gen = 441, tg = 22.50 t/s, tg_3s = 20.28 t/s 17.50.201.735 I slot print_timing: id 3 | task 23463 | n_gen = 243, tg = 22.71 t/s, tg_3s = 25.77 t/s 17.50.585.416 I slot print_timing: id 2 | task 23477 | n_gen = 240, tg = 24.27 t/s, tg_3s = 26.06 t/s 17.51.045.195 I slot print_timing: id 1 | task 23630 | n_gen = 100, tg = 26.07 t/s, tg_3s = 26.33 t/s 17.52.005.052 I slot print_timing: id 0 | task 23231 | n_gen = 520, tg = 22.98 t/s, tg_3s = 26.05 t/s 17.53.204.309 I slot print_timing: id 3 | task 23463 | n_gen = 321, tg = 23.43 t/s, tg_3s = 25.98 t/s 17.53.590.242 I slot print_timing: id 2 | task 23477 | n_gen = 318, tg = 24.66 t/s, tg_3s = 25.96 t/s 17.54.054.406 I slot print_timing: id 1 | task 23630 | n_gen = 178, tg = 26.00 t/s, tg_3s = 25.92 t/s 17.55.018.551 I slot print_timing: id 0 | task 23231 | n_gen = 598, tg = 23.32 t/s, tg_3s = 25.88 t/s 17.56.213.182 I slot print_timing: id 3 | task 23463 | n_gen = 399, tg = 23.88 t/s, tg_3s = 25.92 t/s 17.56.597.335 I slot print_timing: id 2 | task 23477 | n_gen = 396, tg = 24.90 t/s, tg_3s = 25.94 t/s 17.57.062.842 I slot print_timing: id 1 | task 23630 | n_gen = 256, tg = 25.98 t/s, tg_3s = 25.93 t/s 17.58.029.015 I slot print_timing: id 0 | task 23231 | n_gen = 676, tg = 23.59 t/s, tg_3s = 25.91 t/s 17.59.230.255 I slot print_timing: id 3 | task 23463 | n_gen = 477, tg = 24.18 t/s, tg_3s = 25.85 t/s 17.59.617.972 I slot print_timing: id 2 | task 23477 | n_gen = 474, tg = 25.05 t/s, tg_3s = 25.82 t/s 18.00.084.179 I slot print_timing: id 1 | task 23630 | n_gen = 334, tg = 25.94 t/s, tg_3s = 25.82 t/s 18.01.050.521 I slot print_timing: id 0 | task 23231 | n_gen = 754, tg = 23.80 t/s, tg_3s = 25.81 t/s 18.02.246.229 I slot print_timing: id 3 | task 23463 | n_gen = 555, tg = 24.41 t/s, tg_3s = 25.86 t/s 18.02.633.091 I slot print_timing: id 2 | task 23477 | n_gen = 552, tg = 25.16 t/s, tg_3s = 25.87 t/s 18.03.096.370 I slot print_timing: id 1 | task 23630 | n_gen = 412, tg = 25.93 t/s, tg_3s = 25.89 t/s 18.04.060.953 I slot print_timing: id 0 | task 23231 | n_gen = 832, tg = 23.99 t/s, tg_3s = 25.91 t/s 18.04.830.745 I slot print_timing: id 1 | task 23630 | prompt eval time = 740.65 ms / 491 tokens ( 1.51 ms per token, 662.93 tokens per second) 18.04.830.755 I slot print_timing: id 1 | task 23630 | eval time = 17582.84 ms / 457 tokens ( 38.56 ms per token, 25.93 tokens per second) 18.04.830.756 I slot print_timing: id 1 | task 23630 | total time = 18323.49 ms / 948 tokens 18.04.830.757 I slot print_timing: id 1 | task 23630 | graphs reused = 23037 18.04.830.758 I slot print_timing: id 1 | task 23630 | graph reallocs = 0 / 0 (same size) / (changed size) 18.04.830.855 I slot release: id 1 | task 23630 | stop processing: n_tokens = 1611, truncated = 0 18.04.871.686 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.663 18.04.871.725 I slot launch_slot_: id 1 | task 24090 | processing task, is_child = 0 18.05.549.893 I slot print_timing: id 3 | task 23463 | n_gen = 624, tg = 23.96 t/s, tg_3s = 20.89 t/s 18.05.661.780 I slot print_timing: id 2 | task 23477 | n_gen = 613, tg = 24.55 t/s, tg_3s = 20.14 t/s 18.07.083.299 I slot print_timing: id 0 | task 23231 | n_gen = 893, tg = 23.68 t/s, tg_3s = 20.18 t/s 18.08.566.215 I slot print_timing: id 3 | task 23463 | n_gen = 701, tg = 24.12 t/s, tg_3s = 25.53 t/s 18.08.681.012 I slot print_timing: id 2 | task 23477 | n_gen = 691, tg = 24.69 t/s, tg_3s = 25.83 t/s 18.09.457.441 I slot print_timing: id 1 | task 24090 | n_gen = 100, tg = 25.82 t/s, tg_3s = 26.08 t/s 18.10.116.691 I slot print_timing: id 0 | task 23231 | n_gen = 971, tg = 23.83 t/s, tg_3s = 25.71 t/s 18.11.593.397 I slot print_timing: id 3 | task 23463 | n_gen = 779, tg = 24.28 t/s, tg_3s = 25.77 t/s 18.11.708.924 I slot print_timing: id 2 | task 23477 | n_gen = 769, tg = 24.80 t/s, tg_3s = 25.76 t/s 18.12.171.428 I slot print_timing: id 0 | task 23231 | prompt eval time = 685.24 ms / 456 tokens ( 1.50 ms per token, 665.46 tokens per second) 18.12.171.433 I slot print_timing: id 0 | task 23231 | eval time = 42755.09 ms / 1024 tokens ( 41.79 ms per token, 23.93 tokens per second) 18.12.171.433 I slot print_timing: id 0 | task 23231 | total time = 43440.33 ms / 1480 tokens 18.12.171.434 I slot print_timing: id 0 | task 23231 | graphs reused = 23204 18.12.171.435 I slot print_timing: id 0 | task 23231 | graph reallocs = 0 / 0 (same size) / (changed size) 18.12.171.536 I slot release: id 0 | task 23231 | stop processing: n_tokens = 2177, truncated = 0 18.12.206.406 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.491 18.12.212.144 I slot launch_slot_: id 0 | task 24263 | processing task, is_child = 0 18.12.807.913 I slot print_timing: id 1 | task 24090 | n_gen = 172, tg = 23.80 t/s, tg_3s = 21.49 t/s 18.14.604.600 I slot print_timing: id 3 | task 23463 | n_gen = 842, tg = 23.99 t/s, tg_3s = 20.92 t/s 18.14.719.943 I slot print_timing: id 2 | task 23477 | n_gen = 832, tg = 24.45 t/s, tg_3s = 20.92 t/s 18.15.844.979 I slot print_timing: id 1 | task 24090 | n_gen = 250, tg = 24.36 t/s, tg_3s = 25.68 t/s 18.16.693.892 I slot print_timing: id 0 | task 24263 | n_gen = 100, tg = 25.90 t/s, tg_3s = 26.17 t/s 18.17.616.452 I slot print_timing: id 3 | task 23463 | n_gen = 920, tg = 24.14 t/s, tg_3s = 25.90 t/s 18.17.730.666 I slot print_timing: id 2 | task 23477 | n_gen = 910, tg = 24.57 t/s, tg_3s = 25.91 t/s 18.18.847.280 I slot print_timing: id 1 | task 24090 | n_gen = 328, tg = 24.73 t/s, tg_3s = 25.98 t/s 18.19.700.555 I slot print_timing: id 0 | task 24263 | n_gen = 178, tg = 25.92 t/s, tg_3s = 25.94 t/s 18.20.631.789 I slot print_timing: id 3 | task 23463 | n_gen = 998, tg = 24.27 t/s, tg_3s = 25.87 t/s 18.20.746.932 I slot print_timing: id 2 | task 23477 | n_gen = 988, tg = 24.67 t/s, tg_3s = 25.86 t/s 18.21.639.762 I slot print_timing: id 3 | task 23463 | prompt eval time = 691.22 ms / 454 tokens ( 1.52 ms per token, 656.81 tokens per second) 18.21.639.767 I slot print_timing: id 3 | task 23463 | eval time = 42093.43 ms / 1024 tokens ( 41.15 ms per token, 24.30 tokens per second) 18.21.639.768 I slot print_timing: id 3 | task 23463 | total time = 42784.65 ms / 1478 tokens 18.21.639.769 I slot print_timing: id 3 | task 23463 | graphs reused = 23430 18.21.639.769 I slot print_timing: id 3 | task 23463 | graph reallocs = 0 / 0 (same size) / (changed size) 18.21.639.889 I slot release: id 3 | task 23463 | stop processing: n_tokens = 2173, truncated = 0 18.21.673.546 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.491 18.21.679.548 I slot launch_slot_: id 3 | task 24494 | processing task, is_child = 0 18.22.342.560 I slot print_timing: id 1 | task 24090 | n_gen = 402, tg = 23.98 t/s, tg_3s = 21.17 t/s 18.22.712.571 I slot print_timing: id 0 | task 24263 | n_gen = 239, tg = 24.19 t/s, tg_3s = 20.25 t/s 18.22.800.375 I slot print_timing: id 2 | task 23477 | prompt eval time = 759.02 ms / 516 tokens ( 1.47 ms per token, 679.82 tokens per second) 18.22.800.380 I slot print_timing: id 2 | task 23477 | eval time = 42064.33 ms / 1024 tokens ( 41.12 ms per token, 24.32 tokens per second) 18.22.800.381 I slot print_timing: id 2 | task 23477 | total time = 42823.35 ms / 1540 tokens 18.22.800.382 I slot print_timing: id 2 | task 23477 | graphs reused = 23439 18.22.800.383 I slot print_timing: id 2 | task 23477 | graph reallocs = 0 / 0 (same size) / (changed size) 18.22.800.530 I slot release: id 2 | task 23477 | stop processing: n_tokens = 2234, truncated = 0 18.22.842.155 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.478 18.22.848.949 I slot launch_slot_: id 2 | task 24508 | processing task, is_child = 0 18.25.347.874 I slot print_timing: id 1 | task 24090 | n_gen = 463, tg = 23.42 t/s, tg_3s = 20.30 t/s 18.25.731.238 I slot print_timing: id 0 | task 24263 | n_gen = 301, tg = 23.33 t/s, tg_3s = 20.54 t/s 18.26.116.299 I slot print_timing: id 1 | task 24090 | prompt eval time = 751.41 ms / 504 tokens ( 1.49 ms per token, 670.74 tokens per second) 18.26.116.306 I slot print_timing: id 1 | task 24090 | eval time = 20493.15 ms / 483 tokens ( 42.52 ms per token, 23.52 tokens per second) 18.26.116.307 I slot print_timing: id 1 | task 24090 | total time = 21244.57 ms / 987 tokens 18.26.116.308 I slot print_timing: id 1 | task 24090 | graphs reused = 23505 18.26.116.309 I slot print_timing: id 1 | task 24090 | graph reallocs = 0 / 0 (same size) / (changed size) 18.26.116.423 I slot release: id 1 | task 24090 | stop processing: n_tokens = 1650, truncated = 0 18.26.886.616 I slot print_timing: id 3 | task 24494 | n_gen = 100, tg = 22.11 t/s, tg_3s = 22.34 t/s 18.27.420.888 I slot print_timing: id 2 | task 24508 | n_gen = 100, tg = 25.49 t/s, tg_3s = 25.75 t/s 18.28.731.886 I slot print_timing: id 0 | task 24263 | n_gen = 375, tg = 23.58 t/s, tg_3s = 24.66 t/s 18.29.918.140 I slot print_timing: id 3 | task 24494 | n_gen = 174, tg = 23.04 t/s, tg_3s = 24.41 t/s 18.30.449.305 I slot print_timing: id 2 | task 24508 | n_gen = 174, tg = 25.03 t/s, tg_3s = 24.44 t/s 18.31.758.553 I slot print_timing: id 0 | task 24263 | n_gen = 449, tg = 23.72 t/s, tg_3s = 24.45 t/s 18.32.957.430 I slot print_timing: id 3 | task 24494 | n_gen = 248, tg = 23.42 t/s, tg_3s = 24.35 t/s 18.33.488.617 I slot print_timing: id 2 | task 24508 | n_gen = 248, tg = 24.82 t/s, tg_3s = 24.35 t/s 18.34.763.361 I slot print_timing: id 0 | task 24263 | n_gen = 522, tg = 23.80 t/s, tg_3s = 24.29 t/s 18.35.960.391 I slot print_timing: id 3 | task 24494 | n_gen = 321, tg = 23.62 t/s, tg_3s = 24.31 t/s 18.36.494.794 I slot print_timing: id 2 | task 24508 | n_gen = 321, tg = 24.69 t/s, tg_3s = 24.28 t/s 18.37.764.965 I slot print_timing: id 0 | task 24263 | n_gen = 595, tg = 23.86 t/s, tg_3s = 24.32 t/s 18.38.996.911 I slot print_timing: id 3 | task 24494 | n_gen = 395, tg = 23.75 t/s, tg_3s = 24.37 t/s 18.39.532.971 I slot print_timing: id 2 | task 24508 | n_gen = 395, tg = 24.63 t/s, tg_3s = 24.36 t/s 18.40.802.765 I slot print_timing: id 0 | task 24263 | n_gen = 669, tg = 23.92 t/s, tg_3s = 24.36 t/s 18.40.926.815 I slot print_timing: id 3 | task 24494 | prompt eval time = 730.29 ms / 491 tokens ( 1.49 ms per token, 672.34 tokens per second) 18.40.926.824 I slot print_timing: id 3 | task 24494 | eval time = 18516.96 ms / 442 tokens ( 41.99 ms per token, 23.82 tokens per second) 18.40.926.825 I slot print_timing: id 3 | task 24494 | total time = 19247.25 ms / 933 tokens 18.40.926.826 I slot print_timing: id 3 | task 24494 | graphs reused = 23505 18.40.926.827 I slot print_timing: id 3 | task 24494 | graph reallocs = 0 / 0 (same size) / (changed size) 18.40.926.962 I slot release: id 3 | task 24494 | stop processing: n_tokens = 1628, truncated = 0 18.42.275.343 I slot print_timing: id 2 | task 24508 | prompt eval time = 687.73 ms / 444 tokens ( 1.55 ms per token, 645.60 tokens per second) 18.42.275.348 I slot print_timing: id 2 | task 24508 | eval time = 18738.64 ms / 472 tokens ( 39.78 ms per token, 25.14 tokens per second) 18.42.275.350 I slot print_timing: id 2 | task 24508 | total time = 19426.37 ms / 916 tokens 18.42.275.350 I slot print_timing: id 2 | task 24508 | graphs reused = 23505 18.42.275.351 I slot print_timing: id 2 | task 24508 | graph reallocs = 0 / 0 (same size) / (changed size) 18.42.275.482 I slot release: id 2 | task 24508 | stop processing: n_tokens = 1610, truncated = 0 18.43.810.432 I slot print_timing: id 0 | task 24263 | n_gen = 830, tg = 26.80 t/s, tg_3s = 53.53 t/s 18.46.399.399 I slot print_timing: id 0 | task 24263 | prompt eval time = 660.07 ms / 440 tokens ( 1.50 ms per token, 666.60 tokens per second) 18.46.399.409 I slot print_timing: id 0 | task 24263 | eval time = 33527.18 ms / 1024 tokens ( 32.77 ms per token, 30.51 tokens per second) 18.46.399.410 I slot print_timing: id 0 | task 24263 | total time = 34187.25 ms / 1464 tokens 18.46.399.412 I slot print_timing: id 0 | task 24263 | graphs reused = 23812 18.46.399.414 I slot print_timing: id 0 | task 24263 | graph reallocs = 0 / 0 (same size) / (changed size) 18.46.399.483 I slot release: id 0 | task 24263 | stop processing: n_tokens = 2161, truncated = 0 18.46.416.633 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1650, t_last = 345954467629 18.46.420.143 I slot launch_slot_: id 1 | task 25291 | processing task, is_child = 0 18.46.430.751 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1628, t_last = 345969278168 18.46.430.868 I slot launch_slot_: id 3 | task 25292 | processing task, is_child = 0 18.46.431.058 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1610, t_last = 345970626688 18.46.431.160 I slot launch_slot_: id 2 | task 25293 | processing task, is_child = 0 18.46.431.267 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2161, t_last = 345974750689 18.46.431.386 I slot launch_slot_: id 0 | task 25294 | processing task, is_child = 0 18.50.263.996 I slot print_timing: id 0 | task 25294 | prompt processing, n_tokens = 940, progress = 1.00, t = 3.83 s / 245.26 tokens per second 18.50.901.406 I slot print_timing: id 1 | task 25291 | prompt processing, n_tokens = 754, progress = 0.99, t = 3.83 s / 196.74 tokens per second 18.50.901.551 I slot print_timing: id 2 | task 25293 | prompt processing, n_tokens = 942, progress = 1.00, t = 3.83 s / 245.81 tokens per second 18.50.901.706 I slot print_timing: id 3 | task 25292 | prompt processing, n_tokens = 760, progress = 0.99, t = 3.83 s / 198.32 tokens per second 18.51.043.548 I slot print_timing: id 0 | task 25294 | prompt eval time = 4574.14 ms / 944 tokens ( 4.85 ms per token, 206.38 tokens per second) 18.51.043.551 I slot print_timing: id 0 | task 25294 | eval time = 38.02 ms / 2 tokens ( 38.02 ms per token, 26.30 tokens per second) 18.51.043.551 I slot print_timing: id 0 | task 25294 | total time = 4612.16 ms / 946 tokens 18.51.043.552 I slot print_timing: id 0 | task 25294 | graphs reused = 23814 18.51.043.552 I slot print_timing: id 0 | task 25294 | graph reallocs = 0 / 0 (same size) / (changed size) 18.51.043.606 I slot release: id 0 | task 25294 | stop processing: n_tokens = 945, truncated = 0 18.51.043.875 I slot print_timing: id 1 | task 25291 | prompt eval time = 4574.26 ms / 758 tokens ( 6.03 ms per token, 165.71 tokens per second) 18.51.043.877 I slot print_timing: id 1 | task 25291 | eval time = 38.05 ms / 2 tokens ( 38.05 ms per token, 26.28 tokens per second) 18.51.043.878 I slot print_timing: id 1 | task 25291 | total time = 4612.31 ms / 760 tokens 18.51.043.878 I slot print_timing: id 1 | task 25291 | graphs reused = 23814 18.51.043.878 I slot print_timing: id 1 | task 25291 | graph reallocs = 0 / 0 (same size) / (changed size) 18.51.043.915 I slot release: id 1 | task 25291 | stop processing: n_tokens = 759, truncated = 0 18.51.044.193 I slot print_timing: id 2 | task 25293 | prompt eval time = 4574.42 ms / 946 tokens ( 4.84 ms per token, 206.80 tokens per second) 18.51.044.195 I slot print_timing: id 2 | task 25293 | eval time = 38.08 ms / 2 tokens ( 38.08 ms per token, 26.26 tokens per second) 18.51.044.196 I slot print_timing: id 2 | task 25293 | total time = 4612.51 ms / 948 tokens 18.51.044.196 I slot print_timing: id 2 | task 25293 | graphs reused = 23814 18.51.044.197 I slot print_timing: id 2 | task 25293 | graph reallocs = 0 / 0 (same size) / (changed size) 18.51.044.240 I slot release: id 2 | task 25293 | stop processing: n_tokens = 947, truncated = 0 18.51.044.536 I slot print_timing: id 3 | task 25292 | prompt eval time = 4574.78 ms / 764 tokens ( 5.99 ms per token, 167.00 tokens per second) 18.51.044.538 I slot print_timing: id 3 | task 25292 | eval time = 37.95 ms / 2 tokens ( 37.95 ms per token, 26.35 tokens per second) 18.51.044.539 I slot print_timing: id 3 | task 25292 | total time = 4612.73 ms / 766 tokens 18.51.044.539 I slot print_timing: id 3 | task 25292 | graphs reused = 23814 18.51.044.539 I slot print_timing: id 3 | task 25292 | graph reallocs = 0 / 0 (same size) / (changed size) 18.51.044.574 I slot release: id 3 | task 25292 | stop processing: n_tokens = 765, truncated = 0 18.51.051.126 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 945, t_last = 345979394812 18.51.052.927 I slot launch_slot_: id 0 | task 25299 | processing task, is_child = 0 18.51.057.503 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 759, t_last = 345979395121 18.51.057.574 I slot launch_slot_: id 1 | task 25300 | processing task, is_child = 0 18.51.057.659 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 947, t_last = 345979395446 18.51.057.723 I slot launch_slot_: id 2 | task 25302 | processing task, is_child = 0 18.51.057.766 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 765, t_last = 345979395780 18.51.057.822 I slot launch_slot_: id 3 | task 25301 | processing task, is_child = 0 18.54.461.534 I slot print_timing: id 0 | task 25299 | prompt processing, n_tokens = 772, progress = 0.99, t = 3.40 s / 226.81 tokens per second 18.55.099.551 I slot print_timing: id 1 | task 25300 | prompt processing, n_tokens = 768, progress = 0.99, t = 3.40 s / 225.64 tokens per second 18.55.099.697 I slot print_timing: id 2 | task 25302 | prompt processing, n_tokens = 821, progress = 1.00, t = 3.40 s / 241.22 tokens per second 18.55.099.844 I slot print_timing: id 3 | task 25301 | prompt processing, n_tokens = 816, progress = 1.00, t = 3.40 s / 239.75 tokens per second 18.55.241.678 I slot print_timing: id 0 | task 25299 | prompt eval time = 4145.85 ms / 776 tokens ( 5.34 ms per token, 187.18 tokens per second) 18.55.241.680 I slot print_timing: id 0 | task 25299 | eval time = 38.00 ms / 2 tokens ( 38.00 ms per token, 26.31 tokens per second) 18.55.241.681 I slot print_timing: id 0 | task 25299 | total time = 4183.85 ms / 778 tokens 18.55.241.681 I slot print_timing: id 0 | task 25299 | graphs reused = 23815 18.55.241.682 I slot print_timing: id 0 | task 25299 | graph reallocs = 0 / 0 (same size) / (changed size) 18.55.241.727 I slot release: id 0 | task 25299 | stop processing: n_tokens = 777, truncated = 0 18.55.241.988 I slot print_timing: id 1 | task 25300 | prompt eval time = 4146.06 ms / 772 tokens ( 5.37 ms per token, 186.20 tokens per second) 18.55.241.990 I slot print_timing: id 1 | task 25300 | eval time = 38.03 ms / 2 tokens ( 38.03 ms per token, 26.30 tokens per second) 18.55.241.990 I slot print_timing: id 1 | task 25300 | total time = 4184.09 ms / 774 tokens 18.55.241.990 I slot print_timing: id 1 | task 25300 | graphs reused = 23815 18.55.241.991 I slot print_timing: id 1 | task 25300 | graph reallocs = 0 / 0 (same size) / (changed size) 18.55.242.024 I slot release: id 1 | task 25300 | stop processing: n_tokens = 773, truncated = 0 18.55.242.297 I slot print_timing: id 2 | task 25302 | prompt eval time = 4146.31 ms / 825 tokens ( 5.03 ms per token, 198.97 tokens per second) 18.55.242.299 I slot print_timing: id 2 | task 25302 | eval time = 38.03 ms / 2 tokens ( 38.03 ms per token, 26.29 tokens per second) 18.55.242.300 I slot print_timing: id 2 | task 25302 | total time = 4184.35 ms / 827 tokens 18.55.242.300 I slot print_timing: id 2 | task 25302 | graphs reused = 23815 18.55.242.300 I slot print_timing: id 2 | task 25302 | graph reallocs = 0 / 0 (same size) / (changed size) 18.55.242.333 I slot release: id 2 | task 25302 | stop processing: n_tokens = 826, truncated = 0 18.55.242.617 I slot print_timing: id 3 | task 25301 | prompt eval time = 4146.54 ms / 820 tokens ( 5.06 ms per token, 197.76 tokens per second) 18.55.242.620 I slot print_timing: id 3 | task 25301 | eval time = 38.06 ms / 2 tokens ( 38.06 ms per token, 26.27 tokens per second) 18.55.242.620 I slot print_timing: id 3 | task 25301 | total time = 4184.60 ms / 822 tokens 18.55.242.620 I slot print_timing: id 3 | task 25301 | graphs reused = 23815 18.55.242.620 I slot print_timing: id 3 | task 25301 | graph reallocs = 0 / 0 (same size) / (changed size) 18.55.242.656 I slot release: id 3 | task 25301 | stop processing: n_tokens = 821, truncated = 0 18.55.249.626 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 18.55.249.648 I slot launch_slot_: id 0 | task 25307 | processing task, is_child = 0 18.55.254.888 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 345983593230 18.55.254.967 I slot launch_slot_: id 1 | task 25308 | processing task, is_child = 0 18.55.255.050 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 345983593539 18.55.255.107 I slot launch_slot_: id 2 | task 25309 | processing task, is_child = 0 18.55.255.150 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 821, t_last = 345983593862 18.55.255.209 I slot launch_slot_: id 3 | task 25310 | processing task, is_child = 0 18.58.872.376 I slot print_timing: id 0 | task 25307 | prompt processing, n_tokens = 533, progress = 0.99, t = 3.62 s / 147.35 tokens per second 18.59.507.306 I slot print_timing: id 1 | task 25308 | prompt processing, n_tokens = 845, progress = 1.00, t = 3.62 s / 233.62 tokens per second 18.59.507.465 I slot print_timing: id 2 | task 25309 | prompt processing, n_tokens = 927, progress = 1.00, t = 3.62 s / 256.29 tokens per second 18.59.507.631 I slot print_timing: id 3 | task 25310 | prompt processing, n_tokens = 852, progress = 1.00, t = 3.62 s / 235.56 tokens per second 18.59.649.635 I slot print_timing: id 0 | task 25307 | prompt eval time = 4356.30 ms / 537 tokens ( 8.11 ms per token, 123.27 tokens per second) 18.59.649.641 I slot print_timing: id 0 | task 25307 | eval time = 38.12 ms / 2 tokens ( 38.12 ms per token, 26.23 tokens per second) 18.59.649.641 I slot print_timing: id 0 | task 25307 | total time = 4394.42 ms / 539 tokens 18.59.649.642 I slot print_timing: id 0 | task 25307 | graphs reused = 23817 18.59.649.642 I slot print_timing: id 0 | task 25307 | graph reallocs = 0 / 0 (same size) / (changed size) 18.59.649.691 I slot release: id 0 | task 25307 | stop processing: n_tokens = 798, truncated = 0 18.59.649.969 I slot print_timing: id 1 | task 25308 | prompt eval time = 4356.51 ms / 849 tokens ( 5.13 ms per token, 194.88 tokens per second) 18.59.649.973 I slot print_timing: id 1 | task 25308 | eval time = 38.16 ms / 2 tokens ( 38.16 ms per token, 26.21 tokens per second) 18.59.649.974 I slot print_timing: id 1 | task 25308 | total time = 4394.66 ms / 851 tokens 18.59.649.975 I slot print_timing: id 1 | task 25308 | graphs reused = 23817 18.59.649.975 I slot print_timing: id 1 | task 25308 | graph reallocs = 0 / 0 (same size) / (changed size) 18.59.650.016 I slot release: id 1 | task 25308 | stop processing: n_tokens = 850, truncated = 0 18.59.650.295 I slot print_timing: id 2 | task 25309 | prompt eval time = 4356.76 ms / 931 tokens ( 4.68 ms per token, 213.69 tokens per second) 18.59.650.296 I slot print_timing: id 2 | task 25309 | eval time = 38.18 ms / 2 tokens ( 38.18 ms per token, 26.19 tokens per second) 18.59.650.297 I slot print_timing: id 2 | task 25309 | total time = 4394.94 ms / 933 tokens 18.59.650.297 I slot print_timing: id 2 | task 25309 | graphs reused = 23817 18.59.650.298 I slot print_timing: id 2 | task 25309 | graph reallocs = 0 / 0 (same size) / (changed size) 18.59.650.335 I slot release: id 2 | task 25309 | stop processing: n_tokens = 932, truncated = 0 18.59.650.674 I slot print_timing: id 3 | task 25310 | prompt eval time = 4357.04 ms / 856 tokens ( 5.09 ms per token, 196.46 tokens per second) 18.59.650.677 I slot print_timing: id 3 | task 25310 | eval time = 38.23 ms / 2 tokens ( 38.23 ms per token, 26.16 tokens per second) 18.59.650.678 I slot print_timing: id 3 | task 25310 | total time = 4395.26 ms / 858 tokens 18.59.650.678 I slot print_timing: id 3 | task 25310 | graphs reused = 23817 18.59.650.678 I slot print_timing: id 3 | task 25310 | graph reallocs = 0 / 0 (same size) / (changed size) 18.59.650.719 I slot release: id 3 | task 25310 | stop processing: n_tokens = 857, truncated = 0 18.59.657.655 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 798, t_last = 345988000897 18.59.659.403 I slot launch_slot_: id 0 | task 25315 | processing task, is_child = 0 18.59.664.666 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 850, t_last = 345988001222 18.59.664.731 I slot launch_slot_: id 1 | task 25316 | processing task, is_child = 0 18.59.664.816 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 345988001541 18.59.664.876 I slot launch_slot_: id 2 | task 25317 | processing task, is_child = 0 18.59.664.920 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 857, t_last = 345988001925 18.59.664.979 I slot launch_slot_: id 3 | task 25318 | processing task, is_child = 0 19.04.812.456 I slot print_timing: id 0 | task 25315 | prompt processing, n_tokens = 985, progress = 1.00, t = 5.15 s / 191.36 tokens per second 19.05.098.743 I slot print_timing: id 1 | task 25316 | prompt processing, n_tokens = 950, progress = 1.00, t = 5.15 s / 184.56 tokens per second 19.05.098.914 I slot print_timing: id 2 | task 25317 | prompt processing, n_tokens = 887, progress = 1.00, t = 5.15 s / 172.32 tokens per second 19.05.099.072 I slot print_timing: id 3 | task 25318 | prompt processing, n_tokens = 1226, progress = 0.70, t = 5.15 s / 238.18 tokens per second 19.05.851.537 I slot print_timing: id 3 | task 25318 | prompt processing, n_tokens = 1738, progress = 1.00, t = 6.19 s / 280.98 tokens per second 19.05.916.884 I slot print_timing: id 0 | task 25315 | prompt eval time = 6185.97 ms / 989 tokens ( 6.25 ms per token, 159.88 tokens per second) 19.05.916.889 I slot print_timing: id 0 | task 25315 | eval time = 65.93 ms / 2 tokens ( 65.93 ms per token, 15.17 tokens per second) 19.05.916.889 I slot print_timing: id 0 | task 25315 | total time = 6251.90 ms / 991 tokens 19.05.916.890 I slot print_timing: id 0 | task 25315 | graphs reused = 23818 19.05.916.890 I slot print_timing: id 0 | task 25315 | graph reallocs = 0 / 0 (same size) / (changed size) 19.05.916.943 I slot release: id 0 | task 25315 | stop processing: n_tokens = 990, truncated = 0 19.05.917.219 I slot print_timing: id 1 | task 25316 | prompt eval time = 6186.21 ms / 954 tokens ( 6.48 ms per token, 154.21 tokens per second) 19.05.917.222 I slot print_timing: id 1 | task 25316 | eval time = 65.97 ms / 2 tokens ( 65.97 ms per token, 15.16 tokens per second) 19.05.917.222 I slot print_timing: id 1 | task 25316 | total time = 6252.18 ms / 956 tokens 19.05.917.222 I slot print_timing: id 1 | task 25316 | graphs reused = 23818 19.05.917.223 I slot print_timing: id 1 | task 25316 | graph reallocs = 0 / 0 (same size) / (changed size) 19.05.917.287 I slot release: id 1 | task 25316 | stop processing: n_tokens = 955, truncated = 0 19.05.917.564 I slot print_timing: id 2 | task 25317 | prompt eval time = 6186.43 ms / 891 tokens ( 6.94 ms per token, 144.02 tokens per second) 19.05.917.566 I slot print_timing: id 2 | task 25317 | eval time = 66.04 ms / 2 tokens ( 66.04 ms per token, 15.14 tokens per second) 19.05.917.567 I slot print_timing: id 2 | task 25317 | total time = 6252.47 ms / 893 tokens 19.05.917.567 I slot print_timing: id 2 | task 25317 | graphs reused = 23818 19.05.917.567 I slot print_timing: id 2 | task 25317 | graph reallocs = 0 / 0 (same size) / (changed size) 19.05.917.611 I slot release: id 2 | task 25317 | stop processing: n_tokens = 892, truncated = 0 19.05.933.599 I slot print_timing: id 3 | task 25318 | prompt eval time = 6252.83 ms / 1742 tokens ( 3.59 ms per token, 278.59 tokens per second) 19.05.933.601 I slot print_timing: id 3 | task 25318 | eval time = 15.61 ms / 2 tokens ( 15.61 ms per token, 64.05 tokens per second) 19.05.933.602 I slot print_timing: id 3 | task 25318 | total time = 6268.44 ms / 1744 tokens 19.05.933.602 I slot print_timing: id 3 | task 25318 | graphs reused = 23818 19.05.933.603 I slot print_timing: id 3 | task 25318 | graph reallocs = 0 / 0 (same size) / (changed size) 19.05.933.698 I slot release: id 3 | task 25318 | stop processing: n_tokens = 1743, truncated = 0 19.05.933.705 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 990, t_last = 345994268149 19.05.935.882 I slot launch_slot_: id 0 | task 25324 | processing task, is_child = 0 19.05.942.766 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 955, t_last = 345994268493 19.05.942.835 I slot launch_slot_: id 1 | task 25325 | processing task, is_child = 0 19.05.942.951 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 19.05.942.964 I slot launch_slot_: id 2 | task 25326 | processing task, is_child = 0 19.05.943.034 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1743, t_last = 345994284906 19.05.943.122 I slot launch_slot_: id 3 | task 25327 | processing task, is_child = 0 19.09.162.593 I slot print_timing: id 0 | task 25324 | prompt processing, n_tokens = 723, progress = 0.99, t = 3.22 s / 224.57 tokens per second 19.09.797.139 I slot print_timing: id 1 | task 25325 | prompt processing, n_tokens = 858, progress = 1.00, t = 3.22 s / 266.51 tokens per second 19.09.797.307 I slot print_timing: id 2 | task 25326 | prompt processing, n_tokens = 529, progress = 1.00, t = 3.22 s / 164.32 tokens per second 19.09.797.462 I slot print_timing: id 3 | task 25327 | prompt processing, n_tokens = 696, progress = 0.99, t = 3.22 s / 216.20 tokens per second 19.09.939.275 I slot print_timing: id 0 | task 25324 | prompt eval time = 3958.16 ms / 727 tokens ( 5.44 ms per token, 183.67 tokens per second) 19.09.939.277 I slot print_timing: id 0 | task 25324 | eval time = 37.98 ms / 2 tokens ( 37.98 ms per token, 26.33 tokens per second) 19.09.939.278 I slot print_timing: id 0 | task 25324 | total time = 3996.14 ms / 729 tokens 19.09.939.279 I slot print_timing: id 0 | task 25324 | graphs reused = 23820 19.09.939.279 I slot print_timing: id 0 | task 25324 | graph reallocs = 0 / 0 (same size) / (changed size) 19.09.939.321 I slot release: id 0 | task 25324 | stop processing: n_tokens = 728, truncated = 0 19.09.939.588 I slot print_timing: id 1 | task 25325 | prompt eval time = 3958.36 ms / 862 tokens ( 4.59 ms per token, 217.77 tokens per second) 19.09.939.592 I slot print_timing: id 1 | task 25325 | eval time = 38.03 ms / 2 tokens ( 38.03 ms per token, 26.30 tokens per second) 19.09.939.592 I slot print_timing: id 1 | task 25325 | total time = 3996.39 ms / 864 tokens 19.09.939.592 I slot print_timing: id 1 | task 25325 | graphs reused = 23820 19.09.939.593 I slot print_timing: id 1 | task 25325 | graph reallocs = 0 / 0 (same size) / (changed size) 19.09.939.638 I slot release: id 1 | task 25325 | stop processing: n_tokens = 863, truncated = 0 19.09.939.916 I slot print_timing: id 2 | task 25326 | prompt eval time = 3958.57 ms / 533 tokens ( 7.43 ms per token, 134.64 tokens per second) 19.09.939.919 I slot print_timing: id 2 | task 25326 | eval time = 38.07 ms / 2 tokens ( 38.07 ms per token, 26.27 tokens per second) 19.09.939.919 I slot print_timing: id 2 | task 25326 | total time = 3996.64 ms / 535 tokens 19.09.939.920 I slot print_timing: id 2 | task 25326 | graphs reused = 23820 19.09.939.920 I slot print_timing: id 2 | task 25326 | graph reallocs = 0 / 0 (same size) / (changed size) 19.09.939.973 I slot release: id 2 | task 25326 | stop processing: n_tokens = 909, truncated = 0 19.09.940.278 I slot print_timing: id 3 | task 25327 | prompt eval time = 3958.90 ms / 700 tokens ( 5.66 ms per token, 176.82 tokens per second) 19.09.940.280 I slot print_timing: id 3 | task 25327 | eval time = 38.02 ms / 2 tokens ( 38.02 ms per token, 26.30 tokens per second) 19.09.940.281 I slot print_timing: id 3 | task 25327 | total time = 3996.92 ms / 702 tokens 19.09.940.281 I slot print_timing: id 3 | task 25327 | graphs reused = 23820 19.09.940.281 I slot print_timing: id 3 | task 25327 | graph reallocs = 0 / 0 (same size) / (changed size) 19.09.940.315 I slot release: id 3 | task 25327 | stop processing: n_tokens = 701, truncated = 0 19.09.947.994 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.848 19.09.948.014 I slot launch_slot_: id 0 | task 25334 | processing task, is_child = 0 19.09.952.638 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.874 (> 0.100 thold), f_keep = 0.880 19.09.952.656 I slot launch_slot_: id 3 | task 25332 | processing task, is_child = 0 19.09.952.744 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 345998290844 19.09.953.372 I slot launch_slot_: id 1 | task 25333 | processing task, is_child = 0 19.09.953.420 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 909, t_last = 345998291180 19.09.953.478 I slot launch_slot_: id 2 | task 25335 | processing task, is_child = 0 19.13.217.481 I slot print_timing: id 1 | task 25333 | prompt processing, n_tokens = 520, progress = 0.99, t = 3.26 s / 159.33 tokens per second 19.13.217.638 I slot print_timing: id 2 | task 25335 | prompt processing, n_tokens = 824, progress = 1.00, t = 3.26 s / 252.49 tokens per second 19.13.217.783 I slot print_timing: id 3 | task 25332 | prompt processing, n_tokens = 518, progress = 0.99, t = 3.26 s / 158.73 tokens per second 19.13.318.117 I slot print_timing: id 0 | task 25334 | prompt eval time = 3263.99 ms / 493 tokens ( 6.62 ms per token, 151.04 tokens per second) 19.13.318.119 I slot print_timing: id 0 | task 25334 | eval time = 100.65 ms / 2 tokens ( 100.65 ms per token, 9.94 tokens per second) 19.13.318.120 I slot print_timing: id 0 | task 25334 | total time = 3364.63 ms / 495 tokens 19.13.318.120 I slot print_timing: id 0 | task 25334 | graphs reused = 23820 19.13.318.120 I slot print_timing: id 0 | task 25334 | graph reallocs = 0 / 0 (same size) / (changed size) 19.13.318.166 I slot release: id 0 | task 25334 | stop processing: n_tokens = 705, truncated = 0 19.13.349.241 I slot print_timing: id 1 | task 25333 | prompt eval time = 3364.85 ms / 524 tokens ( 6.42 ms per token, 155.73 tokens per second) 19.13.349.246 I slot print_timing: id 1 | task 25333 | eval time = 30.80 ms / 2 tokens ( 30.80 ms per token, 32.47 tokens per second) 19.13.349.246 I slot print_timing: id 1 | task 25333 | total time = 3395.65 ms / 526 tokens 19.13.349.247 I slot print_timing: id 1 | task 25333 | graphs reused = 23820 19.13.349.247 I slot print_timing: id 1 | task 25333 | graph reallocs = 0 / 0 (same size) / (changed size) 19.13.349.283 I slot release: id 1 | task 25333 | stop processing: n_tokens = 709, truncated = 0 19.13.349.562 I slot print_timing: id 2 | task 25335 | prompt eval time = 3365.10 ms / 828 tokens ( 4.06 ms per token, 246.06 tokens per second) 19.13.349.564 I slot print_timing: id 2 | task 25335 | eval time = 30.81 ms / 2 tokens ( 30.81 ms per token, 32.46 tokens per second) 19.13.349.564 I slot print_timing: id 2 | task 25335 | total time = 3395.91 ms / 830 tokens 19.13.349.565 I slot print_timing: id 2 | task 25335 | graphs reused = 23820 19.13.349.565 I slot print_timing: id 2 | task 25335 | graph reallocs = 0 / 0 (same size) / (changed size) 19.13.349.608 I slot release: id 2 | task 25335 | stop processing: n_tokens = 829, truncated = 0 19.13.349.898 I slot print_timing: id 3 | task 25332 | prompt eval time = 3365.43 ms / 522 tokens ( 6.45 ms per token, 155.11 tokens per second) 19.13.349.908 I slot print_timing: id 3 | task 25332 | eval time = 30.75 ms / 2 tokens ( 30.75 ms per token, 32.52 tokens per second) 19.13.349.910 I slot print_timing: id 3 | task 25332 | total time = 3396.18 ms / 524 tokens 19.13.349.910 I slot print_timing: id 3 | task 25332 | graphs reused = 23820 19.13.349.910 I slot print_timing: id 3 | task 25332 | graph reallocs = 0 / 0 (same size) / (changed size) 19.13.349.939 I slot release: id 3 | task 25332 | stop processing: n_tokens = 707, truncated = 0 19.13.349.943 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 705, t_last = 346001669372 19.13.351.607 I slot launch_slot_: id 0 | task 25340 | processing task, is_child = 0 19.13.356.395 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 709, t_last = 346001700489 19.13.356.452 I slot launch_slot_: id 1 | task 25342 | processing task, is_child = 0 19.13.356.531 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 829, t_last = 346001700815 19.13.356.588 I slot launch_slot_: id 2 | task 25341 | processing task, is_child = 0 19.13.356.625 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 346001701146 19.13.356.694 I slot launch_slot_: id 3 | task 25343 | processing task, is_child = 0 19.17.641.848 I slot print_timing: id 0 | task 25340 | prompt processing, n_tokens = 913, progress = 1.00, t = 4.29 s / 213.06 tokens per second 19.18.280.523 I slot print_timing: id 1 | task 25342 | prompt processing, n_tokens = 932, progress = 1.00, t = 4.29 s / 217.50 tokens per second 19.18.280.689 I slot print_timing: id 2 | task 25341 | prompt processing, n_tokens = 922, progress = 1.00, t = 4.29 s / 215.17 tokens per second 19.18.280.846 I slot print_timing: id 3 | task 25343 | prompt processing, n_tokens = 958, progress = 1.00, t = 4.28 s / 223.57 tokens per second 19.18.423.451 I slot print_timing: id 0 | task 25340 | prompt eval time = 5028.34 ms / 917 tokens ( 5.48 ms per token, 182.37 tokens per second) 19.18.423.453 I slot print_timing: id 0 | task 25340 | eval time = 38.41 ms / 2 tokens ( 38.41 ms per token, 26.04 tokens per second) 19.18.423.454 I slot print_timing: id 0 | task 25340 | total time = 5066.75 ms / 919 tokens 19.18.423.454 I slot print_timing: id 0 | task 25340 | graphs reused = 23822 19.18.423.455 I slot print_timing: id 0 | task 25340 | graph reallocs = 0 / 0 (same size) / (changed size) 19.18.423.508 I slot release: id 0 | task 25340 | stop processing: n_tokens = 918, truncated = 0 19.18.423.792 I slot print_timing: id 1 | task 25342 | prompt eval time = 5028.66 ms / 936 tokens ( 5.37 ms per token, 186.13 tokens per second) 19.18.423.794 I slot print_timing: id 1 | task 25342 | eval time = 38.38 ms / 2 tokens ( 38.38 ms per token, 26.05 tokens per second) 19.18.423.795 I slot print_timing: id 1 | task 25342 | total time = 5067.04 ms / 938 tokens 19.18.423.795 I slot print_timing: id 1 | task 25342 | graphs reused = 23822 19.18.423.795 I slot print_timing: id 1 | task 25342 | graph reallocs = 0 / 0 (same size) / (changed size) 19.18.423.835 I slot release: id 1 | task 25342 | stop processing: n_tokens = 937, truncated = 0 19.18.424.126 I slot print_timing: id 2 | task 25341 | prompt eval time = 5029.05 ms / 926 tokens ( 5.43 ms per token, 184.13 tokens per second) 19.18.424.128 I slot print_timing: id 2 | task 25341 | eval time = 38.28 ms / 2 tokens ( 38.28 ms per token, 26.12 tokens per second) 19.18.424.128 I slot print_timing: id 2 | task 25341 | total time = 5067.33 ms / 928 tokens 19.18.424.128 I slot print_timing: id 2 | task 25341 | graphs reused = 23822 19.18.424.129 I slot print_timing: id 2 | task 25341 | graph reallocs = 0 / 0 (same size) / (changed size) 19.18.424.161 I slot release: id 2 | task 25341 | stop processing: n_tokens = 927, truncated = 0 19.18.424.459 I slot print_timing: id 3 | task 25343 | prompt eval time = 5029.53 ms / 962 tokens ( 5.23 ms per token, 191.27 tokens per second) 19.18.424.462 I slot print_timing: id 3 | task 25343 | eval time = 38.08 ms / 2 tokens ( 38.08 ms per token, 26.26 tokens per second) 19.18.424.462 I slot print_timing: id 3 | task 25343 | total time = 5067.61 ms / 964 tokens 19.18.424.462 I slot print_timing: id 3 | task 25343 | graphs reused = 23822 19.18.424.463 I slot print_timing: id 3 | task 25343 | graph reallocs = 0 / 0 (same size) / (changed size) 19.18.424.501 I slot release: id 3 | task 25343 | stop processing: n_tokens = 963, truncated = 0 19.18.431.148 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 918, t_last = 346006774714 19.18.433.075 I slot launch_slot_: id 0 | task 25348 | processing task, is_child = 0 19.18.438.564 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.879 19.18.438.583 I slot launch_slot_: id 1 | task 25349 | processing task, is_child = 0 19.18.438.670 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 927, t_last = 346006775367 19.18.438.747 I slot launch_slot_: id 2 | task 25350 | processing task, is_child = 0 19.18.438.793 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 963, t_last = 346006775707 19.18.438.855 I slot launch_slot_: id 3 | task 25351 | processing task, is_child = 0 19.22.928.314 I slot print_timing: id 0 | task 25348 | prompt processing, n_tokens = 817, progress = 1.00, t = 4.49 s / 181.99 tokens per second 19.22.928.471 I slot print_timing: id 2 | task 25350 | prompt processing, n_tokens = 882, progress = 1.00, t = 4.49 s / 196.48 tokens per second 19.22.928.639 I slot print_timing: id 3 | task 25351 | prompt processing, n_tokens = 996, progress = 1.00, t = 4.49 s / 221.88 tokens per second 19.23.035.708 I slot print_timing: id 1 | task 25349 | prompt eval time = 4489.35 ms / 504 tokens ( 8.91 ms per token, 112.27 tokens per second) 19.23.035.710 I slot print_timing: id 1 | task 25349 | eval time = 107.41 ms / 2 tokens ( 107.41 ms per token, 9.31 tokens per second) 19.23.035.711 I slot print_timing: id 1 | task 25349 | total time = 4596.76 ms / 506 tokens 19.23.035.711 I slot print_timing: id 1 | task 25349 | graphs reused = 23822 19.23.035.712 I slot print_timing: id 1 | task 25349 | graph reallocs = 0 / 0 (same size) / (changed size) 19.23.035.761 I slot release: id 1 | task 25349 | stop processing: n_tokens = 925, truncated = 0 19.23.072.902 I slot print_timing: id 0 | task 25348 | prompt eval time = 4596.59 ms / 821 tokens ( 5.60 ms per token, 178.61 tokens per second) 19.23.072.904 I slot print_timing: id 0 | task 25348 | eval time = 37.45 ms / 2 tokens ( 37.45 ms per token, 26.71 tokens per second) 19.23.072.905 I slot print_timing: id 0 | task 25348 | total time = 4634.04 ms / 823 tokens 19.23.072.905 I slot print_timing: id 0 | task 25348 | graphs reused = 23822 19.23.072.905 I slot print_timing: id 0 | task 25348 | graph reallocs = 0 / 0 (same size) / (changed size) 19.23.072.945 I slot release: id 0 | task 25348 | stop processing: n_tokens = 822, truncated = 0 19.23.073.214 I slot print_timing: id 2 | task 25350 | prompt eval time = 4596.99 ms / 886 tokens ( 5.19 ms per token, 192.73 tokens per second) 19.23.073.217 I slot print_timing: id 2 | task 25350 | eval time = 37.16 ms / 2 tokens ( 37.16 ms per token, 26.91 tokens per second) 19.23.073.218 I slot print_timing: id 2 | task 25350 | total time = 4634.15 ms / 888 tokens 19.23.073.219 I slot print_timing: id 2 | task 25350 | graphs reused = 23822 19.23.073.219 I slot print_timing: id 2 | task 25350 | graph reallocs = 0 / 0 (same size) / (changed size) 19.23.073.259 I slot release: id 2 | task 25350 | stop processing: n_tokens = 887, truncated = 0 19.23.073.538 I slot print_timing: id 3 | task 25351 | prompt eval time = 4597.22 ms / 1000 tokens ( 4.60 ms per token, 217.52 tokens per second) 19.23.073.540 I slot print_timing: id 3 | task 25351 | eval time = 37.19 ms / 2 tokens ( 37.19 ms per token, 26.89 tokens per second) 19.23.073.541 I slot print_timing: id 3 | task 25351 | total time = 4634.41 ms / 1002 tokens 19.23.073.541 I slot print_timing: id 3 | task 25351 | graphs reused = 23822 19.23.073.541 I slot print_timing: id 3 | task 25351 | graph reallocs = 0 / 0 (same size) / (changed size) 19.23.073.580 I slot release: id 3 | task 25351 | stop processing: n_tokens = 1001, truncated = 0 19.23.073.585 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.799 (> 0.100 thold), f_keep = 0.892 19.23.073.607 I slot launch_slot_: id 2 | task 25356 | processing task, is_child = 0 19.23.079.652 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 19.23.079.669 I slot launch_slot_: id 3 | task 25357 | processing task, is_child = 0 19.23.079.758 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 925, t_last = 346011386967 19.23.080.577 I slot launch_slot_: id 1 | task 25358 | processing task, is_child = 0 19.23.080.623 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 822, t_last = 346011424151 19.23.080.680 I slot launch_slot_: id 0 | task 25359 | processing task, is_child = 0 19.26.465.855 I slot print_timing: id 0 | task 25359 | prompt processing, n_tokens = 957, progress = 1.00, t = 3.38 s / 282.76 tokens per second 19.26.466.033 I slot print_timing: id 2 | task 25356 | prompt processing, n_tokens = 616, progress = 1.00, t = 3.38 s / 182.01 tokens per second 19.26.561.878 I slot print_timing: id 1 | task 25358 | prompt eval time = 3384.78 ms / 404 tokens ( 8.38 ms per token, 119.36 tokens per second) 19.26.561.884 I slot print_timing: id 1 | task 25358 | eval time = 96.33 ms / 2 tokens ( 96.33 ms per token, 10.38 tokens per second) 19.26.561.885 I slot print_timing: id 1 | task 25358 | total time = 3481.12 ms / 406 tokens 19.26.561.886 I slot print_timing: id 1 | task 25358 | graphs reused = 23822 19.26.561.887 I slot print_timing: id 1 | task 25358 | graph reallocs = 0 / 0 (same size) / (changed size) 19.26.561.947 I slot release: id 1 | task 25358 | stop processing: n_tokens = 889, truncated = 0 19.26.562.840 I slot print_timing: id 3 | task 25357 | prompt eval time = 3384.89 ms / 388 tokens ( 8.72 ms per token, 114.63 tokens per second) 19.26.562.843 I slot print_timing: id 3 | task 25357 | eval time = 97.00 ms / 2 tokens ( 97.00 ms per token, 10.31 tokens per second) 19.26.562.844 I slot print_timing: id 3 | task 25357 | total time = 3481.89 ms / 390 tokens 19.26.562.844 I slot print_timing: id 3 | task 25357 | graphs reused = 23822 19.26.562.844 I slot print_timing: id 3 | task 25357 | graph reallocs = 0 / 0 (same size) / (changed size) 19.26.562.896 I slot release: id 3 | task 25357 | stop processing: n_tokens = 873, truncated = 0 19.26.591.970 I slot print_timing: id 0 | task 25359 | prompt eval time = 3480.83 ms / 961 tokens ( 3.62 ms per token, 276.08 tokens per second) 19.26.591.974 I slot print_timing: id 0 | task 25359 | eval time = 30.45 ms / 2 tokens ( 30.45 ms per token, 32.84 tokens per second) 19.26.591.975 I slot print_timing: id 0 | task 25359 | total time = 3511.28 ms / 963 tokens 19.26.591.975 I slot print_timing: id 0 | task 25359 | graphs reused = 23822 19.26.591.976 I slot print_timing: id 0 | task 25359 | graph reallocs = 0 / 0 (same size) / (changed size) 19.26.592.057 I slot release: id 0 | task 25359 | stop processing: n_tokens = 962, truncated = 0 19.26.592.621 I slot print_timing: id 2 | task 25356 | prompt eval time = 3481.60 ms / 620 tokens ( 5.62 ms per token, 178.08 tokens per second) 19.26.592.624 I slot print_timing: id 2 | task 25356 | eval time = 30.16 ms / 2 tokens ( 30.16 ms per token, 33.16 tokens per second) 19.26.592.625 I slot print_timing: id 2 | task 25356 | total time = 3511.76 ms / 622 tokens 19.26.592.625 I slot print_timing: id 2 | task 25356 | graphs reused = 23822 19.26.592.626 I slot print_timing: id 2 | task 25356 | graph reallocs = 0 / 0 (same size) / (changed size) 19.26.592.700 I slot release: id 2 | task 25356 | stop processing: n_tokens = 991, truncated = 0 19.26.592.707 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 889, t_last = 346014913153 19.26.593.837 I slot launch_slot_: id 1 | task 25364 | processing task, is_child = 0 19.26.602.446 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 346014914102 19.26.602.573 I slot launch_slot_: id 3 | task 25365 | processing task, is_child = 0 19.26.602.754 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 346014943263 19.26.602.873 I slot launch_slot_: id 0 | task 25366 | processing task, is_child = 0 19.26.602.963 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 346014943907 19.26.603.085 I slot launch_slot_: id 2 | task 25367 | processing task, is_child = 0 19.31.150.431 I slot print_timing: id 0 | task 25366 | prompt processing, n_tokens = 899, progress = 1.00, t = 4.55 s / 197.70 tokens per second 19.31.789.212 I slot print_timing: id 1 | task 25364 | prompt processing, n_tokens = 906, progress = 1.00, t = 4.55 s / 199.24 tokens per second 19.31.789.376 I slot print_timing: id 2 | task 25367 | prompt processing, n_tokens = 1276, progress = 1.00, t = 4.55 s / 280.62 tokens per second 19.31.789.591 I slot print_timing: id 3 | task 25365 | prompt processing, n_tokens = 865, progress = 1.00, t = 4.55 s / 190.24 tokens per second 19.31.931.579 I slot print_timing: id 0 | task 25366 | prompt eval time = 5290.36 ms / 903 tokens ( 5.86 ms per token, 170.69 tokens per second) 19.31.931.581 I slot print_timing: id 0 | task 25366 | eval time = 38.12 ms / 2 tokens ( 38.12 ms per token, 26.23 tokens per second) 19.31.931.581 I slot print_timing: id 0 | task 25366 | total time = 5328.48 ms / 905 tokens 19.31.931.582 I slot print_timing: id 0 | task 25366 | graphs reused = 23824 19.31.931.582 I slot print_timing: id 0 | task 25366 | graph reallocs = 0 / 0 (same size) / (changed size) 19.31.931.634 I slot release: id 0 | task 25366 | stop processing: n_tokens = 904, truncated = 0 19.31.931.910 I slot print_timing: id 1 | task 25364 | prompt eval time = 5290.49 ms / 910 tokens ( 5.81 ms per token, 172.01 tokens per second) 19.31.931.912 I slot print_timing: id 1 | task 25364 | eval time = 38.18 ms / 2 tokens ( 38.18 ms per token, 26.19 tokens per second) 19.31.931.913 I slot print_timing: id 1 | task 25364 | total time = 5328.67 ms / 912 tokens 19.31.931.913 I slot print_timing: id 1 | task 25364 | graphs reused = 23824 19.31.931.913 I slot print_timing: id 1 | task 25364 | graph reallocs = 0 / 0 (same size) / (changed size) 19.31.931.948 I slot release: id 1 | task 25364 | stop processing: n_tokens = 911, truncated = 0 19.31.932.236 I slot print_timing: id 2 | task 25367 | prompt eval time = 5290.68 ms / 1280 tokens ( 4.13 ms per token, 241.93 tokens per second) 19.31.932.241 I slot print_timing: id 2 | task 25367 | eval time = 38.21 ms / 2 tokens ( 38.21 ms per token, 26.17 tokens per second) 19.31.932.241 I slot print_timing: id 2 | task 25367 | total time = 5328.89 ms / 1282 tokens 19.31.932.241 I slot print_timing: id 2 | task 25367 | graphs reused = 23824 19.31.932.241 I slot print_timing: id 2 | task 25367 | graph reallocs = 0 / 0 (same size) / (changed size) 19.31.932.300 I slot release: id 2 | task 25367 | stop processing: n_tokens = 1281, truncated = 0 19.31.932.635 I slot print_timing: id 3 | task 25365 | prompt eval time = 5290.99 ms / 869 tokens ( 6.09 ms per token, 164.24 tokens per second) 19.31.932.637 I slot print_timing: id 3 | task 25365 | eval time = 38.17 ms / 2 tokens ( 38.17 ms per token, 26.20 tokens per second) 19.31.932.638 I slot print_timing: id 3 | task 25365 | total time = 5329.16 ms / 871 tokens 19.31.932.638 I slot print_timing: id 3 | task 25365 | graphs reused = 23824 19.31.932.638 I slot print_timing: id 3 | task 25365 | graph reallocs = 0 / 0 (same size) / (changed size) 19.31.932.675 I slot release: id 3 | task 25365 | stop processing: n_tokens = 870, truncated = 0 19.31.939.022 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 19.31.939.099 I slot launch_slot_: id 2 | task 25372 | processing task, is_child = 0 19.31.944.142 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 346020282840 19.31.944.212 I slot launch_slot_: id 0 | task 25373 | processing task, is_child = 0 19.31.944.302 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 911, t_last = 346020283154 19.31.944.367 I slot launch_slot_: id 1 | task 25374 | processing task, is_child = 0 19.31.944.415 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 870, t_last = 346020283881 19.31.944.475 I slot launch_slot_: id 3 | task 25375 | processing task, is_child = 0 19.36.293.095 I slot print_timing: id 0 | task 25373 | prompt processing, n_tokens = 1236, progress = 1.00, t = 4.35 s / 284.25 tokens per second 19.36.293.310 I slot print_timing: id 1 | task 25374 | prompt processing, n_tokens = 763, progress = 0.99, t = 4.35 s / 175.47 tokens per second 19.36.293.448 I slot print_timing: id 3 | task 25375 | prompt processing, n_tokens = 771, progress = 0.60, t = 4.35 s / 177.32 tokens per second 19.37.015.997 I slot print_timing: id 2 | task 25372 | prompt eval time = 4348.45 ms / 439 tokens ( 9.91 ms per token, 100.96 tokens per second) 19.37.016.000 I slot print_timing: id 2 | task 25372 | eval time = 722.92 ms / 2 tokens ( 722.92 ms per token, 1.38 tokens per second) 19.37.016.001 I slot print_timing: id 2 | task 25372 | total time = 5071.37 ms / 441 tokens 19.37.016.001 I slot print_timing: id 2 | task 25372 | graphs reused = 23824 19.37.016.001 I slot print_timing: id 2 | task 25372 | graph reallocs = 0 / 0 (same size) / (changed size) 19.37.016.063 I slot release: id 2 | task 25372 | stop processing: n_tokens = 1204, truncated = 0 19.37.016.076 I slot print_timing: id 3 | task 25375 | prompt processing, n_tokens = 1283, progress = 1.00, t = 5.07 s / 253.04 tokens per second 19.37.072.323 I slot print_timing: id 0 | task 25373 | prompt eval time = 5070.96 ms / 1240 tokens ( 4.09 ms per token, 244.53 tokens per second) 19.37.072.326 I slot print_timing: id 0 | task 25373 | eval time = 56.88 ms / 2 tokens ( 56.88 ms per token, 17.58 tokens per second) 19.37.072.327 I slot print_timing: id 0 | task 25373 | total time = 5127.84 ms / 1242 tokens 19.37.072.327 I slot print_timing: id 0 | task 25373 | graphs reused = 23824 19.37.072.328 I slot print_timing: id 0 | task 25373 | graph reallocs = 0 / 0 (same size) / (changed size) 19.37.072.388 I slot release: id 0 | task 25373 | stop processing: n_tokens = 1241, truncated = 0 19.37.072.664 I slot print_timing: id 1 | task 25374 | prompt eval time = 5071.17 ms / 767 tokens ( 6.61 ms per token, 151.25 tokens per second) 19.37.072.665 I slot print_timing: id 1 | task 25374 | eval time = 56.94 ms / 2 tokens ( 56.94 ms per token, 17.56 tokens per second) 19.37.072.666 I slot print_timing: id 1 | task 25374 | total time = 5128.11 ms / 769 tokens 19.37.072.666 I slot print_timing: id 1 | task 25374 | graphs reused = 23824 19.37.072.666 I slot print_timing: id 1 | task 25374 | graph reallocs = 0 / 0 (same size) / (changed size) 19.37.072.702 I slot release: id 1 | task 25374 | stop processing: n_tokens = 768, truncated = 0 19.37.073.029 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.872 (> 0.100 thold), f_keep = 0.889 19.37.073.073 I slot launch_slot_: id 1 | task 25380 | processing task, is_child = 0 19.37.077.855 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1204, t_last = 346025367269 19.37.077.938 I slot launch_slot_: id 2 | task 25381 | processing task, is_child = 0 19.37.077.993 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1241, t_last = 346025423594 19.37.078.081 I slot launch_slot_: id 0 | task 25382 | processing task, is_child = 0 19.38.170.518 I slot print_timing: id 3 | task 25375 | prompt eval time = 5128.27 ms / 1287 tokens ( 3.98 ms per token, 250.96 tokens per second) 19.38.170.521 I slot print_timing: id 3 | task 25375 | eval time = 1097.50 ms / 2 tokens ( 1097.50 ms per token, 0.91 tokens per second) 19.38.170.521 I slot print_timing: id 3 | task 25375 | total time = 6225.77 ms / 1289 tokens 19.38.170.522 I slot print_timing: id 3 | task 25375 | graphs reused = 23824 19.38.170.522 I slot print_timing: id 3 | task 25375 | graph reallocs = 0 / 0 (same size) / (changed size) 19.38.170.592 I slot release: id 3 | task 25375 | stop processing: n_tokens = 1288, truncated = 0 19.40.119.283 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1288, t_last = 346026521798 19.40.163.527 I slot launch_slot_: id 3 | task 25385 | processing task, is_child = 0 19.40.163.539 I slot print_timing: id 0 | task 25382 | prompt processing, n_tokens = 840, progress = 1.00, t = 3.04 s / 276.21 tokens per second 19.40.163.699 I slot print_timing: id 1 | task 25380 | prompt processing, n_tokens = 528, progress = 0.99, t = 3.04 s / 173.62 tokens per second 19.40.163.845 I slot print_timing: id 2 | task 25381 | prompt processing, n_tokens = 870, progress = 1.00, t = 3.04 s / 286.09 tokens per second 19.41.316.547 I slot print_timing: id 0 | task 25382 | prompt eval time = 3565.96 ms / 844 tokens ( 4.23 ms per token, 236.68 tokens per second) 19.41.316.552 I slot print_timing: id 0 | task 25382 | eval time = 672.50 ms / 2 tokens ( 672.50 ms per token, 1.49 tokens per second) 19.41.316.553 I slot print_timing: id 0 | task 25382 | total time = 4238.46 ms / 846 tokens 19.41.316.553 I slot print_timing: id 0 | task 25382 | graphs reused = 23825 19.41.316.554 I slot print_timing: id 0 | task 25382 | graph reallocs = 0 / 0 (same size) / (changed size) 19.41.316.604 I slot release: id 0 | task 25382 | stop processing: n_tokens = 845, truncated = 0 19.41.316.878 I slot print_timing: id 1 | task 25380 | prompt eval time = 3566.15 ms / 532 tokens ( 6.70 ms per token, 149.18 tokens per second) 19.41.316.880 I slot print_timing: id 1 | task 25380 | eval time = 672.55 ms / 2 tokens ( 672.55 ms per token, 1.49 tokens per second) 19.41.316.881 I slot print_timing: id 1 | task 25380 | total time = 4238.70 ms / 534 tokens 19.41.316.881 I slot print_timing: id 1 | task 25380 | graphs reused = 23825 19.41.316.882 I slot print_timing: id 1 | task 25380 | graph reallocs = 0 / 0 (same size) / (changed size) 19.41.316.921 I slot release: id 1 | task 25380 | stop processing: n_tokens = 784, truncated = 0 19.41.317.204 I slot print_timing: id 2 | task 25381 | prompt eval time = 3566.44 ms / 874 tokens ( 4.08 ms per token, 245.06 tokens per second) 19.41.317.208 I slot print_timing: id 2 | task 25381 | eval time = 672.50 ms / 2 tokens ( 672.50 ms per token, 1.49 tokens per second) 19.41.317.208 I slot print_timing: id 2 | task 25381 | total time = 4238.95 ms / 876 tokens 19.41.317.208 I slot print_timing: id 2 | task 25381 | graphs reused = 23825 19.41.317.209 I slot print_timing: id 2 | task 25381 | graph reallocs = 0 / 0 (same size) / (changed size) 19.41.317.247 I slot release: id 2 | task 25381 | stop processing: n_tokens = 875, truncated = 0 19.41.351.512 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 845, t_last = 346029667811 19.41.353.307 I slot launch_slot_: id 0 | task 25389 | processing task, is_child = 0 19.41.356.745 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 784, t_last = 346029668127 19.41.356.812 I slot launch_slot_: id 1 | task 25390 | processing task, is_child = 0 19.41.356.858 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 875, t_last = 346029668453 19.41.356.920 I slot launch_slot_: id 2 | task 25391 | processing task, is_child = 0 19.42.592.709 I slot print_timing: id 3 | task 25385 | prompt eval time = 1187.47 ms / 770 tokens ( 1.54 ms per token, 648.44 tokens per second) 19.42.592.711 I slot print_timing: id 3 | task 25385 | eval time = 1241.20 ms / 2 tokens ( 1241.20 ms per token, 0.81 tokens per second) 19.42.592.712 I slot print_timing: id 3 | task 25385 | total time = 2428.67 ms / 772 tokens 19.42.592.712 I slot print_timing: id 3 | task 25385 | graphs reused = 23825 19.42.592.713 I slot print_timing: id 3 | task 25385 | graph reallocs = 0 / 0 (same size) / (changed size) 19.42.592.761 I slot release: id 3 | task 25385 | stop processing: n_tokens = 771, truncated = 0 19.44.535.394 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.851 (> 0.100 thold), f_keep = 0.860 19.44.535.439 I slot launch_slot_: id 3 | task 25394 | processing task, is_child = 0 19.44.535.450 I slot print_timing: id 0 | task 25389 | prompt processing, n_tokens = 814, progress = 1.00, t = 3.18 s / 256.10 tokens per second 19.44.578.971 I slot print_timing: id 1 | task 25390 | prompt processing, n_tokens = 752, progress = 0.99, t = 3.18 s / 236.60 tokens per second 19.44.579.100 I slot print_timing: id 2 | task 25391 | prompt processing, n_tokens = 746, progress = 0.99, t = 3.18 s / 234.71 tokens per second 19.45.390.330 I slot print_timing: id 0 | task 25389 | prompt eval time = 3360.47 ms / 818 tokens ( 4.11 ms per token, 243.42 tokens per second) 19.45.390.335 I slot print_timing: id 0 | task 25389 | eval time = 672.93 ms / 2 tokens ( 672.93 ms per token, 1.49 tokens per second) 19.45.390.335 I slot print_timing: id 0 | task 25389 | total time = 4033.40 ms / 820 tokens 19.45.390.336 I slot print_timing: id 0 | task 25389 | graphs reused = 23825 19.45.390.336 I slot print_timing: id 0 | task 25389 | graph reallocs = 0 / 0 (same size) / (changed size) 19.45.390.386 I slot release: id 0 | task 25389 | stop processing: n_tokens = 819, truncated = 0 19.45.390.686 I slot print_timing: id 1 | task 25390 | prompt eval time = 3360.77 ms / 756 tokens ( 4.45 ms per token, 224.95 tokens per second) 19.45.390.688 I slot print_timing: id 1 | task 25390 | eval time = 672.92 ms / 2 tokens ( 672.92 ms per token, 1.49 tokens per second) 19.45.390.688 I slot print_timing: id 1 | task 25390 | total time = 4033.69 ms / 758 tokens 19.45.390.688 I slot print_timing: id 1 | task 25390 | graphs reused = 23825 19.45.390.689 I slot print_timing: id 1 | task 25390 | graph reallocs = 0 / 0 (same size) / (changed size) 19.45.390.721 I slot release: id 1 | task 25390 | stop processing: n_tokens = 757, truncated = 0 19.45.390.996 I slot print_timing: id 2 | task 25391 | prompt eval time = 3361.00 ms / 750 tokens ( 4.48 ms per token, 223.15 tokens per second) 19.45.391.002 I slot print_timing: id 2 | task 25391 | eval time = 672.95 ms / 2 tokens ( 672.95 ms per token, 1.49 tokens per second) 19.45.391.003 I slot print_timing: id 2 | task 25391 | total time = 4033.95 ms / 752 tokens 19.45.391.003 I slot print_timing: id 2 | task 25391 | graphs reused = 23825 19.45.391.003 I slot print_timing: id 2 | task 25391 | graph reallocs = 0 / 0 (same size) / (changed size) 19.45.391.035 I slot release: id 2 | task 25391 | stop processing: n_tokens = 751, truncated = 0 19.45.425.164 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 819, t_last = 346033741593 19.45.426.907 I slot launch_slot_: id 0 | task 25398 | processing task, is_child = 0 19.45.429.981 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 757, t_last = 346033741927 19.45.430.043 I slot launch_slot_: id 1 | task 25399 | processing task, is_child = 0 19.45.430.085 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 346033742241 19.45.430.143 I slot launch_slot_: id 2 | task 25400 | processing task, is_child = 0 19.47.116.033 I slot print_timing: id 3 | task 25394 | prompt eval time = 845.93 ms / 525 tokens ( 1.61 ms per token, 620.62 tokens per second) 19.47.116.036 I slot print_timing: id 3 | task 25394 | eval time = 1690.87 ms / 2 tokens ( 1690.87 ms per token, 0.59 tokens per second) 19.47.116.037 I slot print_timing: id 3 | task 25394 | total time = 2536.80 ms / 527 tokens 19.47.116.037 I slot print_timing: id 3 | task 25394 | graphs reused = 23825 19.47.116.038 I slot print_timing: id 3 | task 25394 | graph reallocs = 0 / 0 (same size) / (changed size) 19.47.116.087 I slot release: id 3 | task 25394 | stop processing: n_tokens = 780, truncated = 0 19.49.058.683 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 346035467293 19.49.102.681 I slot launch_slot_: id 3 | task 25403 | processing task, is_child = 0 19.49.102.692 I slot print_timing: id 0 | task 25398 | prompt processing, n_tokens = 893, progress = 1.00, t = 3.63 s / 246.11 tokens per second 19.49.102.855 I slot print_timing: id 1 | task 25399 | prompt processing, n_tokens = 877, progress = 1.00, t = 3.63 s / 241.70 tokens per second 19.49.103.009 I slot print_timing: id 2 | task 25400 | prompt processing, n_tokens = 899, progress = 1.00, t = 3.63 s / 247.77 tokens per second 19.50.374.596 I slot print_timing: id 0 | task 25398 | prompt eval time = 4268.38 ms / 897 tokens ( 4.76 ms per token, 210.15 tokens per second) 19.50.374.603 I slot print_timing: id 0 | task 25398 | eval time = 676.06 ms / 2 tokens ( 676.06 ms per token, 1.48 tokens per second) 19.50.374.603 I slot print_timing: id 0 | task 25398 | total time = 4944.44 ms / 899 tokens 19.50.374.604 I slot print_timing: id 0 | task 25398 | graphs reused = 23826 19.50.374.604 I slot print_timing: id 0 | task 25398 | graph reallocs = 0 / 0 (same size) / (changed size) 19.50.374.657 I slot release: id 0 | task 25398 | stop processing: n_tokens = 898, truncated = 0 19.50.374.935 I slot print_timing: id 1 | task 25399 | prompt eval time = 4268.63 ms / 881 tokens ( 4.85 ms per token, 206.39 tokens per second) 19.50.374.937 I slot print_timing: id 1 | task 25399 | eval time = 676.10 ms / 2 tokens ( 676.10 ms per token, 1.48 tokens per second) 19.50.374.938 I slot print_timing: id 1 | task 25399 | total time = 4944.73 ms / 883 tokens 19.50.374.939 I slot print_timing: id 1 | task 25399 | graphs reused = 23826 19.50.374.939 I slot print_timing: id 1 | task 25399 | graph reallocs = 0 / 0 (same size) / (changed size) 19.50.374.977 I slot release: id 1 | task 25399 | stop processing: n_tokens = 882, truncated = 0 19.50.375.269 I slot print_timing: id 2 | task 25400 | prompt eval time = 4268.96 ms / 903 tokens ( 4.73 ms per token, 211.53 tokens per second) 19.50.375.273 I slot print_timing: id 2 | task 25400 | eval time = 676.05 ms / 2 tokens ( 676.05 ms per token, 1.48 tokens per second) 19.50.375.274 I slot print_timing: id 2 | task 25400 | total time = 4945.01 ms / 905 tokens 19.50.375.274 I slot print_timing: id 2 | task 25400 | graphs reused = 23826 19.50.375.274 I slot print_timing: id 2 | task 25400 | graph reallocs = 0 / 0 (same size) / (changed size) 19.50.375.314 I slot release: id 2 | task 25400 | stop processing: n_tokens = 904, truncated = 0 19.50.409.756 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 898, t_last = 346038725863 19.50.411.655 I slot launch_slot_: id 0 | task 25407 | processing task, is_child = 0 19.50.414.999 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 346038726183 19.50.415.068 I slot launch_slot_: id 1 | task 25408 | processing task, is_child = 0 19.50.415.121 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.889 19.50.415.138 I slot launch_slot_: id 2 | task 25409 | processing task, is_child = 0 19.51.851.060 I slot print_timing: id 3 | task 25403 | prompt eval time = 1306.59 ms / 885 tokens ( 1.48 ms per token, 677.34 tokens per second) 19.51.851.062 I slot print_timing: id 3 | task 25403 | eval time = 1441.30 ms / 2 tokens ( 1441.30 ms per token, 0.69 tokens per second) 19.51.851.063 I slot print_timing: id 3 | task 25403 | total time = 2747.89 ms / 887 tokens 19.51.851.063 I slot print_timing: id 3 | task 25403 | graphs reused = 23826 19.51.851.064 I slot print_timing: id 3 | task 25403 | graph reallocs = 0 / 0 (same size) / (changed size) 19.51.851.114 I slot release: id 3 | task 25403 | stop processing: n_tokens = 886, truncated = 0 19.53.185.157 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 886, t_last = 346040202320 19.53.187.561 I slot launch_slot_: id 3 | task 25412 | processing task, is_child = 0 19.53.817.563 I slot print_timing: id 2 | task 25409 | prompt eval time = 2769.87 ms / 511 tokens ( 5.42 ms per token, 184.48 tokens per second) 19.53.817.565 I slot print_timing: id 2 | task 25409 | eval time = 632.40 ms / 2 tokens ( 632.40 ms per token, 1.58 tokens per second) 19.53.817.566 I slot print_timing: id 2 | task 25409 | total time = 3402.28 ms / 513 tokens 19.53.817.566 I slot print_timing: id 2 | task 25409 | graphs reused = 23826 19.53.817.567 I slot print_timing: id 2 | task 25409 | graph reallocs = 0 / 0 (same size) / (changed size) 19.53.817.630 I slot release: id 2 | task 25409 | stop processing: n_tokens = 899, truncated = 0 19.54.475.639 I slot print_timing: id 0 | task 25407 | prompt eval time = 3401.74 ms / 777 tokens ( 4.38 ms per token, 228.41 tokens per second) 19.54.475.643 I slot print_timing: id 0 | task 25407 | eval time = 658.74 ms / 2 tokens ( 658.74 ms per token, 1.52 tokens per second) 19.54.475.643 I slot print_timing: id 0 | task 25407 | total time = 4060.48 ms / 779 tokens 19.54.475.644 I slot print_timing: id 0 | task 25407 | graphs reused = 23826 19.54.475.644 I slot print_timing: id 0 | task 25407 | graph reallocs = 0 / 0 (same size) / (changed size) 19.54.475.697 I slot release: id 0 | task 25407 | stop processing: n_tokens = 778, truncated = 0 19.54.475.991 I slot print_timing: id 1 | task 25408 | prompt eval time = 3402.06 ms / 777 tokens ( 4.38 ms per token, 228.39 tokens per second) 19.54.475.993 I slot print_timing: id 1 | task 25408 | eval time = 658.72 ms / 2 tokens ( 658.72 ms per token, 1.52 tokens per second) 19.54.475.994 I slot print_timing: id 1 | task 25408 | total time = 4060.78 ms / 779 tokens 19.54.475.994 I slot print_timing: id 1 | task 25408 | graphs reused = 23826 19.54.475.995 I slot print_timing: id 1 | task 25408 | graph reallocs = 0 / 0 (same size) / (changed size) 19.54.476.032 I slot release: id 1 | task 25408 | stop processing: n_tokens = 778, truncated = 0 19.54.476.036 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 346042168838 19.54.479.191 I slot launch_slot_: id 2 | task 25415 | processing task, is_child = 0 19.54.482.438 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 346042826903 19.54.482.503 I slot launch_slot_: id 0 | task 25416 | processing task, is_child = 0 19.54.482.557 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 346042827238 19.54.482.614 I slot launch_slot_: id 1 | task 25417 | processing task, is_child = 0 19.58.338.764 I slot print_timing: id 3 | task 25412 | prompt eval time = 3142.09 ms / 945 tokens ( 3.32 ms per token, 300.75 tokens per second) 19.58.338.767 I slot print_timing: id 3 | task 25412 | eval time = 2008.76 ms / 2 tokens ( 2008.76 ms per token, 0.50 tokens per second) 19.58.338.768 I slot print_timing: id 3 | task 25412 | total time = 5150.85 ms / 947 tokens 19.58.338.768 I slot print_timing: id 3 | task 25412 | graphs reused = 23827 19.58.338.769 I slot print_timing: id 3 | task 25412 | graph reallocs = 0 / 0 (same size) / (changed size) 19.58.338.821 I slot release: id 3 | task 25412 | stop processing: n_tokens = 946, truncated = 0 19.58.338.835 I slot print_timing: id 0 | task 25416 | prompt processing, n_tokens = 925, progress = 1.00, t = 3.86 s / 239.89 tokens per second 19.58.339.001 I slot print_timing: id 1 | task 25417 | prompt processing, n_tokens = 908, progress = 1.00, t = 3.86 s / 235.49 tokens per second 19.58.339.153 I slot print_timing: id 2 | task 25415 | prompt processing, n_tokens = 919, progress = 1.00, t = 3.86 s / 238.35 tokens per second 19.58.420.579 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 946, t_last = 346046690027 19.58.423.262 I slot launch_slot_: id 3 | task 25421 | processing task, is_child = 0 19.58.947.883 I slot print_timing: id 0 | task 25416 | prompt eval time = 3937.19 ms / 929 tokens ( 4.24 ms per token, 235.96 tokens per second) 19.58.947.887 I slot print_timing: id 0 | task 25416 | eval time = 528.06 ms / 2 tokens ( 528.06 ms per token, 1.89 tokens per second) 19.58.947.887 I slot print_timing: id 0 | task 25416 | total time = 4465.25 ms / 931 tokens 19.58.947.888 I slot print_timing: id 0 | task 25416 | graphs reused = 23827 19.58.947.888 I slot print_timing: id 0 | task 25416 | graph reallocs = 0 / 0 (same size) / (changed size) 19.58.947.938 I slot release: id 0 | task 25416 | stop processing: n_tokens = 930, truncated = 0 19.58.948.227 I slot print_timing: id 1 | task 25417 | prompt eval time = 3937.52 ms / 912 tokens ( 4.32 ms per token, 231.62 tokens per second) 19.58.948.229 I slot print_timing: id 1 | task 25417 | eval time = 528.02 ms / 2 tokens ( 528.02 ms per token, 1.89 tokens per second) 19.58.948.229 I slot print_timing: id 1 | task 25417 | total time = 4465.54 ms / 914 tokens 19.58.948.229 I slot print_timing: id 1 | task 25417 | graphs reused = 23827 19.58.948.230 I slot print_timing: id 1 | task 25417 | graph reallocs = 0 / 0 (same size) / (changed size) 19.58.948.286 I slot release: id 1 | task 25417 | stop processing: n_tokens = 913, truncated = 0 19.58.948.572 I slot print_timing: id 2 | task 25415 | prompt eval time = 3937.84 ms / 923 tokens ( 4.27 ms per token, 234.39 tokens per second) 19.58.948.574 I slot print_timing: id 2 | task 25415 | eval time = 528.00 ms / 2 tokens ( 528.00 ms per token, 1.89 tokens per second) 19.58.948.575 I slot print_timing: id 2 | task 25415 | total time = 4465.83 ms / 925 tokens 19.58.948.575 I slot print_timing: id 2 | task 25415 | graphs reused = 23827 19.58.948.575 I slot print_timing: id 2 | task 25415 | graph reallocs = 0 / 0 (same size) / (changed size) 19.58.948.621 I slot release: id 2 | task 25415 | stop processing: n_tokens = 924, truncated = 0 19.59.619.059 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.891 (> 0.100 thold), f_keep = 0.863 19.59.619.084 I slot launch_slot_: id 1 | task 25425 | processing task, is_child = 0 19.59.623.986 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 930, t_last = 346047299144 19.59.624.060 I slot launch_slot_: id 0 | task 25426 | processing task, is_child = 0 19.59.624.109 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 924, t_last = 346047299827 19.59.624.176 I slot launch_slot_: id 2 | task 25427 | processing task, is_child = 0 20.01.502.196 I slot print_timing: id 3 | task 25421 | prompt eval time = 1195.79 ms / 880 tokens ( 1.36 ms per token, 735.92 tokens per second) 20.01.502.200 I slot print_timing: id 3 | task 25421 | eval time = 1883.13 ms / 2 tokens ( 1883.13 ms per token, 0.53 tokens per second) 20.01.502.201 I slot print_timing: id 3 | task 25421 | total time = 3078.92 ms / 882 tokens 20.01.502.201 I slot print_timing: id 3 | task 25421 | graphs reused = 23827 20.01.502.202 I slot print_timing: id 3 | task 25421 | graph reallocs = 0 / 0 (same size) / (changed size) 20.01.502.271 I slot release: id 3 | task 25421 | stop processing: n_tokens = 881, truncated = 0 20.02.845.313 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 346049853478 20.02.847.934 I slot launch_slot_: id 3 | task 25430 | processing task, is_child = 0 20.02.847.958 I slot print_timing: id 0 | task 25426 | prompt processing, n_tokens = 878, progress = 1.00, t = 3.22 s / 272.60 tokens per second 20.02.848.163 I slot print_timing: id 2 | task 25427 | prompt processing, n_tokens = 866, progress = 1.00, t = 3.22 s / 268.89 tokens per second 20.03.863.326 I slot print_timing: id 1 | task 25425 | prompt eval time = 3221.05 ms / 488 tokens ( 6.60 ms per token, 151.50 tokens per second) 20.03.863.328 I slot print_timing: id 1 | task 25425 | eval time = 1018.02 ms / 2 tokens ( 1018.02 ms per token, 0.98 tokens per second) 20.03.863.329 I slot print_timing: id 1 | task 25425 | total time = 4239.07 ms / 490 tokens 20.03.863.329 I slot print_timing: id 1 | task 25425 | graphs reused = 23827 20.03.863.330 I slot print_timing: id 1 | task 25425 | graph reallocs = 0 / 0 (same size) / (changed size) 20.03.863.384 I slot release: id 1 | task 25425 | stop processing: n_tokens = 885, truncated = 0 20.04.540.017 I slot print_timing: id 0 | task 25426 | prompt eval time = 4238.88 ms / 882 tokens ( 4.81 ms per token, 208.07 tokens per second) 20.04.540.024 I slot print_timing: id 0 | task 25426 | eval time = 676.95 ms / 2 tokens ( 676.95 ms per token, 1.48 tokens per second) 20.04.540.024 I slot print_timing: id 0 | task 25426 | total time = 4915.83 ms / 884 tokens 20.04.540.025 I slot print_timing: id 0 | task 25426 | graphs reused = 23827 20.04.540.026 I slot print_timing: id 0 | task 25426 | graph reallocs = 0 / 0 (same size) / (changed size) 20.04.540.080 I slot release: id 0 | task 25426 | stop processing: n_tokens = 883, truncated = 0 20.04.540.363 I slot print_timing: id 2 | task 25427 | prompt eval time = 4239.39 ms / 870 tokens ( 4.87 ms per token, 205.22 tokens per second) 20.04.540.366 I slot print_timing: id 2 | task 25427 | eval time = 676.60 ms / 2 tokens ( 676.60 ms per token, 1.48 tokens per second) 20.04.540.366 I slot print_timing: id 2 | task 25427 | total time = 4915.99 ms / 872 tokens 20.04.540.367 I slot print_timing: id 2 | task 25427 | graphs reused = 23827 20.04.540.367 I slot print_timing: id 2 | task 25427 | graph reallocs = 0 / 0 (same size) / (changed size) 20.04.540.412 I slot release: id 2 | task 25427 | stop processing: n_tokens = 871, truncated = 0 20.04.540.417 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 885, t_last = 346052214591 20.04.543.055 I slot launch_slot_: id 1 | task 25433 | processing task, is_child = 0 20.04.546.487 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 346052891286 20.04.546.567 I slot launch_slot_: id 0 | task 25434 | processing task, is_child = 0 20.06.447.516 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 346052891618 20.06.447.619 I slot launch_slot_: id 2 | task 25436 | processing task, is_child = 0 20.09.100.675 I slot print_timing: id 3 | task 25430 | prompt eval time = 3599.13 ms / 1172 tokens ( 3.07 ms per token, 325.63 tokens per second) 20.09.100.678 I slot print_timing: id 3 | task 25430 | eval time = 2653.16 ms / 2 tokens ( 2653.16 ms per token, 0.38 tokens per second) 20.09.100.678 I slot print_timing: id 3 | task 25430 | total time = 6252.29 ms / 1174 tokens 20.09.100.679 I slot print_timing: id 3 | task 25430 | graphs reused = 23828 20.09.100.679 I slot print_timing: id 3 | task 25430 | graph reallocs = 0 / 0 (same size) / (changed size) 20.09.100.747 I slot release: id 3 | task 25430 | stop processing: n_tokens = 1173, truncated = 0 20.09.100.760 I slot print_timing: id 0 | task 25434 | prompt processing, n_tokens = 1236, progress = 1.00, t = 4.55 s / 271.42 tokens per second 20.09.100.973 I slot print_timing: id 1 | task 25433 | prompt processing, n_tokens = 1175, progress = 1.00, t = 4.55 s / 258.03 tokens per second 20.10.621.740 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1173, t_last = 346057451953 20.10.625.763 I slot launch_slot_: id 3 | task 25439 | processing task, is_child = 0 20.10.625.791 I slot print_timing: id 2 | task 25436 | prompt processing, n_tokens = 2076, progress = 0.80, t = 4.17 s / 497.45 tokens per second 20.13.243.242 I slot print_timing: id 0 | task 25434 | prompt eval time = 6074.71 ms / 1240 tokens ( 4.90 ms per token, 204.12 tokens per second) 20.13.243.245 I slot print_timing: id 0 | task 25434 | eval time = 2621.91 ms / 2 tokens ( 2621.91 ms per token, 0.38 tokens per second) 20.13.243.245 I slot print_timing: id 0 | task 25434 | total time = 8696.62 ms / 1242 tokens 20.13.243.246 I slot print_timing: id 0 | task 25434 | graphs reused = 23828 20.13.243.246 I slot print_timing: id 0 | task 25434 | graph reallocs = 0 / 0 (same size) / (changed size) 20.13.243.316 I slot release: id 0 | task 25434 | stop processing: n_tokens = 1241, truncated = 0 20.13.243.603 I slot print_timing: id 1 | task 25433 | prompt eval time = 6075.04 ms / 1179 tokens ( 5.15 ms per token, 194.07 tokens per second) 20.13.243.607 I slot print_timing: id 1 | task 25433 | eval time = 2621.87 ms / 2 tokens ( 2621.87 ms per token, 0.38 tokens per second) 20.13.243.607 I slot print_timing: id 1 | task 25433 | total time = 8696.91 ms / 1181 tokens 20.13.243.608 I slot print_timing: id 1 | task 25433 | graphs reused = 23828 20.13.243.608 I slot print_timing: id 1 | task 25433 | graph reallocs = 0 / 0 (same size) / (changed size) 20.13.243.659 I slot release: id 1 | task 25433 | stop processing: n_tokens = 1180, truncated = 0 20.13.243.672 I slot print_timing: id 2 | task 25436 | prompt processing, n_tokens = 2588, progress = 1.00, t = 6.80 s / 380.86 tokens per second 20.13.887.394 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1241, t_last = 346061594523 20.13.891.360 I slot launch_slot_: id 0 | task 25442 | processing task, is_child = 0 20.13.894.131 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1180, t_last = 346061594865 20.13.894.217 I slot launch_slot_: id 1 | task 25443 | processing task, is_child = 0 20.16.479.215 I slot print_timing: id 2 | task 25436 | prompt eval time = 7439.67 ms / 2592 tokens ( 2.87 ms per token, 348.40 tokens per second) 20.16.479.220 I slot print_timing: id 2 | task 25436 | eval time = 2591.82 ms / 2 tokens ( 2591.82 ms per token, 0.39 tokens per second) 20.16.479.221 I slot print_timing: id 2 | task 25436 | total time = 10031.49 ms / 2594 tokens 20.16.479.221 I slot print_timing: id 2 | task 25436 | graphs reused = 23828 20.16.479.222 I slot print_timing: id 2 | task 25436 | graph reallocs = 0 / 0 (same size) / (changed size) 20.16.479.355 I slot release: id 2 | task 25436 | stop processing: n_tokens = 2593, truncated = 0 20.18.700.560 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2593, t_last = 346064830562 20.19.200.980 I slot launch_slot_: id 2 | task 25446 | processing task, is_child = 0 20.19.201.008 I slot print_timing: id 0 | task 25442 | prompt processing, n_tokens = 2126, progress = 0.80, t = 4.81 s / 442.33 tokens per second 20.19.201.336 I slot print_timing: id 3 | task 25439 | prompt processing, n_tokens = 1983, progress = 0.79, t = 3.26 s / 608.06 tokens per second 20.21.484.935 I slot print_timing: id 0 | task 25442 | prompt processing, n_tokens = 2638, progress = 1.00, t = 7.59 s / 347.53 tokens per second 20.22.085.327 I slot print_timing: id 1 | task 25443 | prompt processing, n_tokens = 2230, progress = 0.81, t = 5.01 s / 445.51 tokens per second 20.22.085.409 I slot print_timing: id 3 | task 25439 | prompt processing, n_tokens = 2015, progress = 0.81, t = 10.86 s / 185.56 tokens per second 20.24.294.567 I slot print_timing: id 1 | task 25443 | prompt processing, n_tokens = 2742, progress = 1.00, t = 7.81 s / 350.87 tokens per second 20.24.294.971 I slot print_timing: id 2 | task 25446 | prompt processing, n_tokens = 1755, progress = 1.00, t = 5.09 s / 344.58 tokens per second 20.24.295.268 I slot print_timing: id 3 | task 25439 | prompt processing, n_tokens = 2495, progress = 1.00, t = 13.67 s / 182.54 tokens per second 20.24.400.987 I slot print_timing: id 0 | task 25442 | prompt eval time = 10400.33 ms / 2642 tokens ( 3.94 ms per token, 254.03 tokens per second) 20.24.400.993 I slot print_timing: id 0 | task 25442 | eval time = 106.44 ms / 2 tokens ( 106.44 ms per token, 9.40 tokens per second) 20.24.400.993 I slot print_timing: id 0 | task 25442 | total time = 10506.76 ms / 2644 tokens 20.24.400.994 I slot print_timing: id 0 | task 25442 | graphs reused = 23828 20.24.400.994 I slot print_timing: id 0 | task 25442 | graph reallocs = 0 / 0 (same size) / (changed size) 20.24.401.128 I slot release: id 0 | task 25442 | stop processing: n_tokens = 2643, truncated = 0 20.24.433.147 I slot print_timing: id 1 | task 25443 | prompt eval time = 7922.14 ms / 2746 tokens ( 2.88 ms per token, 346.62 tokens per second) 20.24.433.150 I slot print_timing: id 1 | task 25443 | eval time = 31.62 ms / 2 tokens ( 31.62 ms per token, 31.62 tokens per second) 20.24.433.150 I slot print_timing: id 1 | task 25443 | total time = 7953.77 ms / 2748 tokens 20.24.433.150 I slot print_timing: id 1 | task 25443 | graphs reused = 23828 20.24.433.151 I slot print_timing: id 1 | task 25443 | graph reallocs = 0 / 0 (same size) / (changed size) 20.24.433.276 I slot release: id 1 | task 25443 | stop processing: n_tokens = 2747, truncated = 0 20.24.433.577 I slot print_timing: id 2 | task 25446 | prompt eval time = 5200.82 ms / 1759 tokens ( 2.96 ms per token, 338.22 tokens per second) 20.24.433.579 I slot print_timing: id 2 | task 25446 | eval time = 31.63 ms / 2 tokens ( 31.63 ms per token, 31.61 tokens per second) 20.24.433.580 I slot print_timing: id 2 | task 25446 | total time = 5232.45 ms / 1761 tokens 20.24.433.580 I slot print_timing: id 2 | task 25446 | graphs reused = 23828 20.24.433.580 I slot print_timing: id 2 | task 25446 | graph reallocs = 0 / 0 (same size) / (changed size) 20.24.433.678 I slot release: id 2 | task 25446 | stop processing: n_tokens = 1760, truncated = 0 20.24.433.963 I slot print_timing: id 3 | task 25439 | prompt eval time = 13776.58 ms / 2499 tokens ( 5.51 ms per token, 181.39 tokens per second) 20.24.433.966 I slot print_timing: id 3 | task 25439 | eval time = 31.49 ms / 2 tokens ( 31.49 ms per token, 31.76 tokens per second) 20.24.433.972 I slot print_timing: id 3 | task 25439 | total time = 13808.07 ms / 2501 tokens 20.24.433.972 I slot print_timing: id 3 | task 25439 | graphs reused = 23828 20.24.433.972 I slot print_timing: id 3 | task 25439 | graph reallocs = 0 / 0 (same size) / (changed size) 20.24.434.074 I slot release: id 3 | task 25439 | stop processing: n_tokens = 2500, truncated = 0 20.24.434.081 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.806 (> 0.100 thold), f_keep = 0.830 20.24.434.114 I slot launch_slot_: id 2 | task 25451 | processing task, is_child = 0 20.24.448.511 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2643, t_last = 346072752335 20.24.448.654 I slot launch_slot_: id 0 | task 25452 | processing task, is_child = 0 20.24.448.861 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2747, t_last = 346072784483 20.24.448.986 I slot launch_slot_: id 1 | task 25453 | processing task, is_child = 0 20.24.449.084 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2500, t_last = 346072785281 20.24.449.217 I slot launch_slot_: id 3 | task 25454 | processing task, is_child = 0 20.29.581.383 I slot print_timing: id 0 | task 25452 | prompt processing, n_tokens = 1825, progress = 1.00, t = 5.13 s / 355.60 tokens per second 20.29.978.733 I slot print_timing: id 1 | task 25453 | prompt processing, n_tokens = 1392, progress = 0.73, t = 5.13 s / 271.24 tokens per second 20.32.356.858 I slot print_timing: id 1 | task 25453 | prompt processing, n_tokens = 1904, progress = 1.00, t = 7.91 s / 240.80 tokens per second 20.32.357.161 I slot print_timing: id 2 | task 25451 | prompt processing, n_tokens = 564, progress = 1.00, t = 5.25 s / 107.53 tokens per second 20.32.357.438 I slot print_timing: id 3 | task 25454 | prompt processing, n_tokens = 1489, progress = 0.74, t = 5.24 s / 283.89 tokens per second 20.33.111.332 I slot print_timing: id 0 | task 25452 | prompt eval time = 7907.62 ms / 1829 tokens ( 4.32 ms per token, 231.30 tokens per second) 20.33.111.336 I slot print_timing: id 0 | task 25452 | eval time = 754.48 ms / 2 tokens ( 754.48 ms per token, 1.33 tokens per second) 20.33.111.337 I slot print_timing: id 0 | task 25452 | total time = 8662.10 ms / 1831 tokens 20.33.111.337 I slot print_timing: id 0 | task 25452 | graphs reused = 23829 20.33.111.338 I slot print_timing: id 0 | task 25452 | graph reallocs = 0 / 0 (same size) / (changed size) 20.33.111.445 I slot release: id 0 | task 25452 | stop processing: n_tokens = 1830, truncated = 0 20.33.112.061 I slot print_timing: id 3 | task 25454 | prompt processing, n_tokens = 2001, progress = 1.00, t = 6.00 s / 333.53 tokens per second 20.33.170.561 I slot print_timing: id 1 | task 25453 | prompt eval time = 8662.34 ms / 1908 tokens ( 4.54 ms per token, 220.26 tokens per second) 20.33.170.563 I slot print_timing: id 1 | task 25453 | eval time = 58.80 ms / 2 tokens ( 58.80 ms per token, 17.01 tokens per second) 20.33.170.563 I slot print_timing: id 1 | task 25453 | total time = 8721.14 ms / 1910 tokens 20.33.170.564 I slot print_timing: id 1 | task 25453 | graphs reused = 23829 20.33.170.564 I slot print_timing: id 1 | task 25453 | graph reallocs = 0 / 0 (same size) / (changed size) 20.33.170.660 I slot release: id 1 | task 25453 | stop processing: n_tokens = 1909, truncated = 0 20.33.170.938 I slot print_timing: id 2 | task 25451 | prompt eval time = 6000.59 ms / 568 tokens ( 10.56 ms per token, 94.66 tokens per second) 20.33.170.940 I slot print_timing: id 2 | task 25451 | eval time = 58.89 ms / 2 tokens ( 58.89 ms per token, 16.98 tokens per second) 20.33.170.940 I slot print_timing: id 2 | task 25451 | total time = 6059.48 ms / 570 tokens 20.33.170.940 I slot print_timing: id 2 | task 25451 | graphs reused = 23829 20.33.170.941 I slot print_timing: id 2 | task 25451 | graph reallocs = 0 / 0 (same size) / (changed size) 20.33.171.021 I slot release: id 2 | task 25451 | stop processing: n_tokens = 1812, truncated = 0 20.33.171.428 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.836 (> 0.100 thold), f_keep = 0.798 20.33.171.463 I slot launch_slot_: id 0 | task 25460 | processing task, is_child = 0 20.33.178.019 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1909, t_last = 346081521866 20.33.178.129 I slot launch_slot_: id 1 | task 25461 | processing task, is_child = 0 20.33.178.204 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1812, t_last = 346081522228 20.33.178.297 I slot launch_slot_: id 2 | task 25462 | processing task, is_child = 0 20.34.597.812 I slot print_timing: id 3 | task 25454 | prompt eval time = 6059.87 ms / 2005 tokens ( 3.02 ms per token, 330.87 tokens per second) 20.34.597.814 I slot print_timing: id 3 | task 25454 | eval time = 1426.39 ms / 2 tokens ( 1426.39 ms per token, 0.70 tokens per second) 20.34.597.815 I slot print_timing: id 3 | task 25454 | total time = 7486.25 ms / 2007 tokens 20.34.597.816 I slot print_timing: id 3 | task 25454 | graphs reused = 23829 20.34.597.816 I slot print_timing: id 3 | task 25454 | graph reallocs = 0 / 0 (same size) / (changed size) 20.34.597.942 I slot release: id 3 | task 25454 | stop processing: n_tokens = 2006, truncated = 0 20.35.937.027 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2006, t_last = 346082949149 20.35.943.096 I slot launch_slot_: id 3 | task 25465 | processing task, is_child = 0 20.36.394.089 I slot print_timing: id 0 | task 25460 | prompt eval time = 2758.72 ms / 434 tokens ( 6.36 ms per token, 157.32 tokens per second) 20.36.394.093 I slot print_timing: id 0 | task 25460 | eval time = 457.06 ms / 2 tokens ( 457.06 ms per token, 2.19 tokens per second) 20.36.394.094 I slot print_timing: id 0 | task 25460 | total time = 3215.78 ms / 436 tokens 20.36.394.094 I slot print_timing: id 0 | task 25460 | graphs reused = 23829 20.36.394.095 I slot print_timing: id 0 | task 25460 | graph reallocs = 0 / 0 (same size) / (changed size) 20.36.394.194 I slot release: id 0 | task 25460 | stop processing: n_tokens = 1748, truncated = 0 20.37.059.232 I slot print_timing: id 1 | task 25461 | prompt eval time = 3216.05 ms / 733 tokens ( 4.39 ms per token, 227.92 tokens per second) 20.37.059.234 I slot print_timing: id 1 | task 25461 | eval time = 664.73 ms / 2 tokens ( 664.73 ms per token, 1.50 tokens per second) 20.37.059.235 I slot print_timing: id 1 | task 25461 | total time = 3880.79 ms / 735 tokens 20.37.059.235 I slot print_timing: id 1 | task 25461 | graphs reused = 23829 20.37.059.236 I slot print_timing: id 1 | task 25461 | graph reallocs = 0 / 0 (same size) / (changed size) 20.37.059.294 I slot release: id 1 | task 25461 | stop processing: n_tokens = 734, truncated = 0 20.37.059.594 I slot print_timing: id 2 | task 25462 | prompt eval time = 3216.23 ms / 711 tokens ( 4.52 ms per token, 221.07 tokens per second) 20.37.059.599 I slot print_timing: id 2 | task 25462 | eval time = 664.79 ms / 2 tokens ( 664.79 ms per token, 1.50 tokens per second) 20.37.059.599 I slot print_timing: id 2 | task 25462 | total time = 3881.03 ms / 713 tokens 20.37.059.599 I slot print_timing: id 2 | task 25462 | graphs reused = 23829 20.37.059.600 I slot print_timing: id 2 | task 25462 | graph reallocs = 0 / 0 (same size) / (changed size) 20.37.059.640 I slot release: id 2 | task 25462 | stop processing: n_tokens = 712, truncated = 0 20.37.059.646 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.854 20.37.059.675 I slot launch_slot_: id 1 | task 25468 | processing task, is_child = 0 20.37.718.479 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1748, t_last = 346084745401 20.37.718.598 I slot launch_slot_: id 0 | task 25469 | processing task, is_child = 0 20.37.718.642 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.864 (> 0.100 thold), f_keep = 0.881 20.37.718.659 I slot launch_slot_: id 2 | task 25471 | processing task, is_child = 0 20.38.275.182 I slot print_timing: id 3 | task 25465 | prompt eval time = 1775.05 ms / 744 tokens ( 2.39 ms per token, 419.14 tokens per second) 20.38.275.185 I slot print_timing: id 3 | task 25465 | eval time = 556.71 ms / 2 tokens ( 556.71 ms per token, 1.80 tokens per second) 20.38.275.186 I slot print_timing: id 3 | task 25465 | total time = 2331.76 ms / 746 tokens 20.38.275.187 I slot print_timing: id 3 | task 25465 | graphs reused = 23829 20.38.275.187 I slot print_timing: id 3 | task 25465 | graph reallocs = 0 / 0 (same size) / (changed size) 20.38.275.231 I slot release: id 3 | task 25465 | stop processing: n_tokens = 745, truncated = 0 20.39.562.625 I slot print_timing: id 1 | task 25468 | prompt eval time = 1208.06 ms / 493 tokens ( 2.45 ms per token, 408.09 tokens per second) 20.39.562.628 I slot print_timing: id 1 | task 25468 | eval time = 1287.72 ms / 2 tokens ( 1287.72 ms per token, 0.78 tokens per second) 20.39.562.629 I slot print_timing: id 1 | task 25468 | total time = 2495.78 ms / 495 tokens 20.39.562.629 I slot print_timing: id 1 | task 25468 | graphs reused = 23829 20.39.562.630 I slot print_timing: id 1 | task 25468 | graph reallocs = 0 / 0 (same size) / (changed size) 20.39.562.677 I slot release: id 1 | task 25468 | stop processing: n_tokens = 711, truncated = 0 20.39.562.684 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 745, t_last = 346086626437 20.39.565.517 I slot launch_slot_: id 3 | task 25474 | processing task, is_child = 0 20.39.568.814 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 346087913883 20.39.568.884 I slot launch_slot_: id 1 | task 25475 | processing task, is_child = 0 20.42.058.356 I slot print_timing: id 0 | task 25469 | prompt eval time = 3024.14 ms / 789 tokens ( 3.83 ms per token, 260.90 tokens per second) 20.42.058.360 I slot print_timing: id 0 | task 25469 | eval time = 1315.55 ms / 2 tokens ( 1315.55 ms per token, 0.76 tokens per second) 20.42.058.360 I slot print_timing: id 0 | task 25469 | total time = 4339.69 ms / 791 tokens 20.42.058.364 I slot print_timing: id 0 | task 25469 | graphs reused = 23829 20.42.058.365 I slot print_timing: id 0 | task 25469 | graph reallocs = 0 / 0 (same size) / (changed size) 20.42.058.419 I slot release: id 0 | task 25469 | stop processing: n_tokens = 790, truncated = 0 20.42.058.720 I slot print_timing: id 2 | task 25471 | prompt eval time = 3024.27 ms / 531 tokens ( 5.70 ms per token, 175.58 tokens per second) 20.42.058.723 I slot print_timing: id 2 | task 25471 | eval time = 1315.53 ms / 2 tokens ( 1315.53 ms per token, 0.76 tokens per second) 20.42.058.723 I slot print_timing: id 2 | task 25471 | total time = 4339.80 ms / 533 tokens 20.42.058.723 I slot print_timing: id 2 | task 25471 | graphs reused = 23829 20.42.058.724 I slot print_timing: id 2 | task 25471 | graph reallocs = 0 / 0 (same size) / (changed size) 20.42.058.761 I slot release: id 2 | task 25471 | stop processing: n_tokens = 727, truncated = 0 20.42.126.191 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 346090409625 20.42.128.601 I slot launch_slot_: id 0 | task 25479 | processing task, is_child = 0 20.42.131.054 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 346090409967 20.42.131.131 I slot launch_slot_: id 2 | task 25480 | processing task, is_child = 0 20.42.994.445 I slot print_timing: id 1 | task 25475 | prompt eval time = 2556.73 ms / 784 tokens ( 3.26 ms per token, 306.64 tokens per second) 20.42.994.448 I slot print_timing: id 1 | task 25475 | eval time = 868.68 ms / 2 tokens ( 868.68 ms per token, 1.15 tokens per second) 20.42.994.448 I slot print_timing: id 1 | task 25475 | total time = 3425.41 ms / 786 tokens 20.42.994.449 I slot print_timing: id 1 | task 25475 | graphs reused = 23829 20.42.994.449 I slot print_timing: id 1 | task 25475 | graph reallocs = 0 / 0 (same size) / (changed size) 20.42.994.501 I slot release: id 1 | task 25475 | stop processing: n_tokens = 785, truncated = 0 20.42.994.961 I slot print_timing: id 3 | task 25474 | prompt eval time = 2556.98 ms / 1040 tokens ( 2.46 ms per token, 406.73 tokens per second) 20.42.994.963 I slot print_timing: id 3 | task 25474 | eval time = 868.77 ms / 2 tokens ( 868.77 ms per token, 1.15 tokens per second) 20.42.994.964 I slot print_timing: id 3 | task 25474 | total time = 3425.75 ms / 1042 tokens 20.42.994.964 I slot print_timing: id 3 | task 25474 | graphs reused = 23829 20.42.994.964 I slot print_timing: id 3 | task 25474 | graph reallocs = 0 / 0 (same size) / (changed size) 20.42.995.015 I slot release: id 3 | task 25474 | stop processing: n_tokens = 1041, truncated = 0 20.43.631.786 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 785, t_last = 346091345707 20.44.264.768 I slot launch_slot_: id 1 | task 25483 | processing task, is_child = 0 20.44.269.857 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1041, t_last = 346091346221 20.44.269.953 I slot launch_slot_: id 3 | task 25484 | processing task, is_child = 0 20.46.607.400 I slot print_timing: id 0 | task 25479 | prompt eval time = 3163.08 ms / 776 tokens ( 4.08 ms per token, 245.33 tokens per second) 20.46.607.403 I slot print_timing: id 0 | task 25479 | eval time = 1313.18 ms / 2 tokens ( 1313.18 ms per token, 0.76 tokens per second) 20.46.607.404 I slot print_timing: id 0 | task 25479 | total time = 4476.26 ms / 778 tokens 20.46.607.404 I slot print_timing: id 0 | task 25479 | graphs reused = 23829 20.46.607.404 I slot print_timing: id 0 | task 25479 | graph reallocs = 0 / 0 (same size) / (changed size) 20.46.607.455 I slot release: id 0 | task 25479 | stop processing: n_tokens = 777, truncated = 0 20.46.607.775 I slot print_timing: id 2 | task 25480 | prompt eval time = 3163.42 ms / 831 tokens ( 3.81 ms per token, 262.69 tokens per second) 20.46.607.778 I slot print_timing: id 2 | task 25480 | eval time = 1313.15 ms / 2 tokens ( 1313.15 ms per token, 0.76 tokens per second) 20.46.607.779 I slot print_timing: id 2 | task 25480 | total time = 4476.57 ms / 833 tokens 20.46.607.779 I slot print_timing: id 2 | task 25480 | graphs reused = 23829 20.46.607.779 I slot print_timing: id 2 | task 25480 | graph reallocs = 0 / 0 (same size) / (changed size) 20.46.607.826 I slot release: id 2 | task 25480 | stop processing: n_tokens = 832, truncated = 0 20.46.675.370 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.885 20.46.675.400 I slot launch_slot_: id 2 | task 25488 | processing task, is_child = 0 20.46.677.788 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 777, t_last = 346094958661 20.46.677.856 I slot launch_slot_: id 0 | task 25489 | processing task, is_child = 0 20.47.301.681 I slot print_timing: id 1 | task 25483 | prompt eval time = 2404.83 ms / 825 tokens ( 2.91 ms per token, 343.06 tokens per second) 20.47.301.685 I slot print_timing: id 1 | task 25483 | eval time = 626.71 ms / 2 tokens ( 626.71 ms per token, 1.60 tokens per second) 20.47.301.685 I slot print_timing: id 1 | task 25483 | total time = 3031.54 ms / 827 tokens 20.47.301.686 I slot print_timing: id 1 | task 25483 | graphs reused = 23829 20.47.301.686 I slot print_timing: id 1 | task 25483 | graph reallocs = 0 / 0 (same size) / (changed size) 20.47.301.735 I slot release: id 1 | task 25483 | stop processing: n_tokens = 826, truncated = 0 20.47.302.203 I slot print_timing: id 3 | task 25484 | prompt eval time = 2405.01 ms / 885 tokens ( 2.72 ms per token, 367.98 tokens per second) 20.47.302.205 I slot print_timing: id 3 | task 25484 | eval time = 626.84 ms / 2 tokens ( 626.84 ms per token, 1.60 tokens per second) 20.47.302.206 I slot print_timing: id 3 | task 25484 | total time = 3031.85 ms / 887 tokens 20.47.302.206 I slot print_timing: id 3 | task 25484 | graphs reused = 23829 20.47.302.206 I slot print_timing: id 3 | task 25484 | graph reallocs = 0 / 0 (same size) / (changed size) 20.47.302.246 I slot release: id 3 | task 25484 | stop processing: n_tokens = 886, truncated = 0 20.47.938.803 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 346095652941 20.48.571.761 I slot launch_slot_: id 1 | task 25492 | processing task, is_child = 0 20.48.576.326 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 886, t_last = 346095653452 20.48.576.413 I slot launch_slot_: id 3 | task 25493 | processing task, is_child = 0 20.50.680.638 I slot print_timing: id 0 | task 25489 | prompt eval time = 2693.84 ms / 892 tokens ( 3.02 ms per token, 331.13 tokens per second) 20.50.680.641 I slot print_timing: id 0 | task 25489 | eval time = 1308.93 ms / 2 tokens ( 1308.93 ms per token, 0.76 tokens per second) 20.50.680.641 I slot print_timing: id 0 | task 25489 | total time = 4002.77 ms / 894 tokens 20.50.680.642 I slot print_timing: id 0 | task 25489 | graphs reused = 23829 20.50.680.642 I slot print_timing: id 0 | task 25489 | graph reallocs = 0 / 0 (same size) / (changed size) 20.50.680.703 I slot release: id 0 | task 25489 | stop processing: n_tokens = 893, truncated = 0 20.50.681.040 I slot print_timing: id 2 | task 25488 | prompt eval time = 2694.19 ms / 533 tokens ( 5.05 ms per token, 197.83 tokens per second) 20.50.681.046 I slot print_timing: id 2 | task 25488 | eval time = 1308.92 ms / 2 tokens ( 1308.92 ms per token, 0.76 tokens per second) 20.50.681.048 I slot print_timing: id 2 | task 25488 | total time = 4003.12 ms / 535 tokens 20.50.681.048 I slot print_timing: id 2 | task 25488 | graphs reused = 23829 20.50.681.048 I slot print_timing: id 2 | task 25488 | graph reallocs = 0 / 0 (same size) / (changed size) 20.50.681.087 I slot release: id 2 | task 25488 | stop processing: n_tokens = 849, truncated = 0 20.50.747.729 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 893, t_last = 346099031909 20.50.750.454 I slot launch_slot_: id 0 | task 25497 | processing task, is_child = 0 20.50.752.776 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 849, t_last = 346099032293 20.50.752.849 I slot launch_slot_: id 2 | task 25498 | processing task, is_child = 0 20.51.563.586 I slot print_timing: id 1 | task 25492 | prompt eval time = 2170.73 ms / 677 tokens ( 3.21 ms per token, 311.88 tokens per second) 20.51.563.588 I slot print_timing: id 1 | task 25492 | eval time = 816.23 ms / 2 tokens ( 816.23 ms per token, 1.23 tokens per second) 20.51.563.588 I slot print_timing: id 1 | task 25492 | total time = 2986.96 ms / 679 tokens 20.51.563.589 I slot print_timing: id 1 | task 25492 | graphs reused = 23829 20.51.563.589 I slot print_timing: id 1 | task 25492 | graph reallocs = 0 / 0 (same size) / (changed size) 20.51.563.638 I slot release: id 1 | task 25492 | stop processing: n_tokens = 678, truncated = 0 20.51.564.056 I slot print_timing: id 3 | task 25493 | prompt eval time = 2170.89 ms / 792 tokens ( 2.74 ms per token, 364.83 tokens per second) 20.51.564.059 I slot print_timing: id 3 | task 25493 | eval time = 816.33 ms / 2 tokens ( 816.33 ms per token, 1.22 tokens per second) 20.51.564.059 I slot print_timing: id 3 | task 25493 | total time = 2987.22 ms / 794 tokens 20.51.564.060 I slot print_timing: id 3 | task 25493 | graphs reused = 23829 20.51.564.060 I slot print_timing: id 3 | task 25493 | graph reallocs = 0 / 0 (same size) / (changed size) 20.51.564.110 I slot release: id 3 | task 25493 | stop processing: n_tokens = 793, truncated = 0 20.52.198.179 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 346099914844 20.52.829.955 I slot launch_slot_: id 1 | task 25501 | processing task, is_child = 0 20.52.833.079 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 793, t_last = 346099915316 20.52.833.172 I slot launch_slot_: id 3 | task 25502 | processing task, is_child = 0 20.54.891.101 I slot print_timing: id 0 | task 25497 | prompt eval time = 2830.01 ms / 740 tokens ( 3.82 ms per token, 261.48 tokens per second) 20.54.891.104 I slot print_timing: id 0 | task 25497 | eval time = 1308.23 ms / 2 tokens ( 1308.23 ms per token, 0.76 tokens per second) 20.54.891.105 I slot print_timing: id 0 | task 25497 | total time = 4138.24 ms / 742 tokens 20.54.891.105 I slot print_timing: id 0 | task 25497 | graphs reused = 23829 20.54.891.106 I slot print_timing: id 0 | task 25497 | graph reallocs = 0 / 0 (same size) / (changed size) 20.54.891.158 I slot release: id 0 | task 25497 | stop processing: n_tokens = 741, truncated = 0 20.54.891.479 I slot print_timing: id 2 | task 25498 | prompt eval time = 2830.28 ms / 813 tokens ( 3.48 ms per token, 287.25 tokens per second) 20.54.891.481 I slot print_timing: id 2 | task 25498 | eval time = 1308.27 ms / 2 tokens ( 1308.27 ms per token, 0.76 tokens per second) 20.54.891.482 I slot print_timing: id 2 | task 25498 | total time = 4138.56 ms / 815 tokens 20.54.891.482 I slot print_timing: id 2 | task 25498 | graphs reused = 23829 20.54.891.482 I slot print_timing: id 2 | task 25498 | graph reallocs = 0 / 0 (same size) / (changed size) 20.54.891.526 I slot release: id 2 | task 25498 | stop processing: n_tokens = 814, truncated = 0 20.54.958.574 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 346103242364 20.54.960.730 I slot launch_slot_: id 0 | task 25506 | processing task, is_child = 0 20.54.963.149 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 814, t_last = 346103242732 20.54.963.221 I slot launch_slot_: id 2 | task 25507 | processing task, is_child = 0 20.55.650.651 I slot print_timing: id 1 | task 25501 | prompt eval time = 2124.82 ms / 694 tokens ( 3.06 ms per token, 326.62 tokens per second) 20.55.650.653 I slot print_timing: id 1 | task 25501 | eval time = 692.45 ms / 2 tokens ( 692.45 ms per token, 1.44 tokens per second) 20.55.650.653 I slot print_timing: id 1 | task 25501 | total time = 2817.27 ms / 696 tokens 20.55.650.654 I slot print_timing: id 1 | task 25501 | graphs reused = 23829 20.55.650.654 I slot print_timing: id 1 | task 25501 | graph reallocs = 0 / 0 (same size) / (changed size) 20.55.650.699 I slot release: id 1 | task 25501 | stop processing: n_tokens = 695, truncated = 0 20.55.651.105 I slot print_timing: id 3 | task 25502 | prompt eval time = 2124.96 ms / 719 tokens ( 2.96 ms per token, 338.36 tokens per second) 20.55.651.107 I slot print_timing: id 3 | task 25502 | eval time = 692.53 ms / 2 tokens ( 692.53 ms per token, 1.44 tokens per second) 20.55.651.108 I slot print_timing: id 3 | task 25502 | total time = 2817.49 ms / 721 tokens 20.55.651.108 I slot print_timing: id 3 | task 25502 | graphs reused = 23829 20.55.651.108 I slot print_timing: id 3 | task 25502 | graph reallocs = 0 / 0 (same size) / (changed size) 20.55.651.145 I slot release: id 3 | task 25502 | stop processing: n_tokens = 720, truncated = 0 20.56.285.574 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.881 20.56.285.610 I slot launch_slot_: id 1 | task 25510 | processing task, is_child = 0 20.56.917.697 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 346104002351 20.56.917.781 I slot launch_slot_: id 3 | task 25511 | processing task, is_child = 0 20.58.668.673 I slot print_timing: id 0 | task 25506 | prompt eval time = 3001.39 ms / 694 tokens ( 4.32 ms per token, 231.23 tokens per second) 20.58.668.675 I slot print_timing: id 0 | task 25506 | eval time = 704.05 ms / 2 tokens ( 704.05 ms per token, 1.42 tokens per second) 20.58.668.676 I slot print_timing: id 0 | task 25506 | total time = 3705.44 ms / 696 tokens 20.58.668.676 I slot print_timing: id 0 | task 25506 | graphs reused = 23829 20.58.668.677 I slot print_timing: id 0 | task 25506 | graph reallocs = 0 / 0 (same size) / (changed size) 20.58.668.721 I slot release: id 0 | task 25506 | stop processing: n_tokens = 695, truncated = 0 20.58.669.328 I slot print_timing: id 2 | task 25507 | prompt eval time = 3001.65 ms / 718 tokens ( 4.18 ms per token, 239.20 tokens per second) 20.58.669.335 I slot print_timing: id 2 | task 25507 | eval time = 704.39 ms / 2 tokens ( 704.39 ms per token, 1.42 tokens per second) 20.58.669.336 I slot print_timing: id 2 | task 25507 | total time = 3706.04 ms / 720 tokens 20.58.669.336 I slot print_timing: id 2 | task 25507 | graphs reused = 23829 20.58.669.336 I slot print_timing: id 2 | task 25507 | graph reallocs = 0 / 0 (same size) / (changed size) 20.58.669.380 I slot release: id 2 | task 25507 | stop processing: n_tokens = 719, truncated = 0 20.58.716.994 I slot print_timing: id 1 | task 25510 | prompt eval time = 1751.08 ms / 515 tokens ( 3.40 ms per token, 294.10 tokens per second) 20.58.716.997 I slot print_timing: id 1 | task 25510 | eval time = 47.92 ms / 2 tokens ( 47.92 ms per token, 20.87 tokens per second) 20.58.716.997 I slot print_timing: id 1 | task 25510 | total time = 1799.01 ms / 517 tokens 20.58.716.998 I slot print_timing: id 1 | task 25510 | graphs reused = 23829 20.58.716.998 I slot print_timing: id 1 | task 25510 | graph reallocs = 0 / 0 (same size) / (changed size) 20.58.717.038 I slot release: id 1 | task 25510 | stop processing: n_tokens = 694, truncated = 0 20.58.717.421 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.885 20.58.717.451 I slot launch_slot_: id 1 | task 25515 | processing task, is_child = 0 20.58.721.612 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.881 20.58.721.640 I slot launch_slot_: id 0 | task 25516 | processing task, is_child = 0 20.58.721.683 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.851 20.58.721.701 I slot launch_slot_: id 2 | task 25517 | processing task, is_child = 0 21.00.762.195 I slot print_timing: id 3 | task 25511 | prompt eval time = 1799.04 ms / 696 tokens ( 2.58 ms per token, 386.87 tokens per second) 21.00.762.200 I slot print_timing: id 3 | task 25511 | eval time = 2044.77 ms / 2 tokens ( 2044.77 ms per token, 0.49 tokens per second) 21.00.762.201 I slot print_timing: id 3 | task 25511 | total time = 3843.81 ms / 698 tokens 21.00.762.201 I slot print_timing: id 3 | task 25511 | graphs reused = 23829 21.00.762.202 I slot print_timing: id 3 | task 25511 | graph reallocs = 0 / 0 (same size) / (changed size) 21.00.762.251 I slot release: id 3 | task 25511 | stop processing: n_tokens = 697, truncated = 0 21.00.843.860 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.878 21.00.843.922 I slot launch_slot_: id 3 | task 25520 | processing task, is_child = 0 21.00.893.101 I slot print_timing: id 0 | task 25516 | prompt eval time = 2121.45 ms / 510 tokens ( 4.16 ms per token, 240.40 tokens per second) 21.00.893.103 I slot print_timing: id 0 | task 25516 | eval time = 49.94 ms / 2 tokens ( 49.94 ms per token, 20.02 tokens per second) 21.00.893.104 I slot print_timing: id 0 | task 25516 | total time = 2171.39 ms / 512 tokens 21.00.893.104 I slot print_timing: id 0 | task 25516 | graphs reused = 23829 21.00.893.105 I slot print_timing: id 0 | task 25516 | graph reallocs = 0 / 0 (same size) / (changed size) 21.00.893.149 I slot release: id 0 | task 25516 | stop processing: n_tokens = 689, truncated = 0 21.00.893.414 I slot print_timing: id 1 | task 25515 | prompt eval time = 2121.62 ms / 512 tokens ( 4.14 ms per token, 241.32 tokens per second) 21.00.893.416 I slot print_timing: id 1 | task 25515 | eval time = 49.95 ms / 2 tokens ( 49.95 ms per token, 20.02 tokens per second) 21.00.893.416 I slot print_timing: id 1 | task 25515 | total time = 2171.57 ms / 514 tokens 21.00.893.417 I slot print_timing: id 1 | task 25515 | graphs reused = 23829 21.00.893.417 I slot print_timing: id 1 | task 25515 | graph reallocs = 0 / 0 (same size) / (changed size) 21.00.893.449 I slot release: id 1 | task 25515 | stop processing: n_tokens = 691, truncated = 0 21.00.893.730 I slot print_timing: id 2 | task 25517 | prompt eval time = 2121.90 ms / 499 tokens ( 4.25 ms per token, 235.17 tokens per second) 21.00.893.734 I slot print_timing: id 2 | task 25517 | eval time = 49.88 ms / 2 tokens ( 49.88 ms per token, 20.05 tokens per second) 21.00.893.735 I slot print_timing: id 2 | task 25517 | total time = 2171.78 ms / 501 tokens 21.00.893.736 I slot print_timing: id 2 | task 25517 | graphs reused = 23829 21.00.893.736 I slot print_timing: id 2 | task 25517 | graph reallocs = 0 / 0 (same size) / (changed size) 21.00.893.763 I slot release: id 2 | task 25517 | stop processing: n_tokens = 702, truncated = 0 21.01.560.945 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.837 (> 0.100 thold), f_keep = 0.888 21.01.560.976 I slot launch_slot_: id 0 | task 25524 | processing task, is_child = 0 21.01.564.816 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 691, t_last = 346109244655 21.01.564.887 I slot launch_slot_: id 1 | task 25525 | processing task, is_child = 0 21.01.564.930 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.872 21.01.564.945 I slot launch_slot_: id 2 | task 25526 | processing task, is_child = 0 21.03.029.155 I slot print_timing: id 3 | task 25520 | prompt eval time = 717.01 ms / 518 tokens ( 1.38 ms per token, 722.44 tokens per second) 21.03.029.166 I slot print_timing: id 3 | task 25520 | eval time = 1468.21 ms / 2 tokens ( 1468.21 ms per token, 0.68 tokens per second) 21.03.029.166 I slot print_timing: id 3 | task 25520 | total time = 2185.22 ms / 520 tokens 21.03.029.167 I slot print_timing: id 3 | task 25520 | graphs reused = 23829 21.03.029.167 I slot print_timing: id 3 | task 25520 | graph reallocs = 0 / 0 (same size) / (changed size) 21.03.029.208 I slot release: id 3 | task 25520 | stop processing: n_tokens = 699, truncated = 0 21.04.374.614 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 699, t_last = 346111380414 21.04.377.447 I slot launch_slot_: id 3 | task 25529 | processing task, is_child = 0 21.04.919.758 I slot print_timing: id 2 | task 25526 | prompt eval time = 2809.52 ms / 489 tokens ( 5.75 ms per token, 174.05 tokens per second) 21.04.919.761 I slot print_timing: id 2 | task 25526 | eval time = 545.14 ms / 2 tokens ( 545.14 ms per token, 1.83 tokens per second) 21.04.919.761 I slot print_timing: id 2 | task 25526 | total time = 3354.66 ms / 491 tokens 21.04.919.762 I slot print_timing: id 2 | task 25526 | graphs reused = 23829 21.04.919.762 I slot print_timing: id 2 | task 25526 | graph reallocs = 0 / 0 (same size) / (changed size) 21.04.919.841 I slot release: id 2 | task 25526 | stop processing: n_tokens = 692, truncated = 0 21.05.576.832 I slot print_timing: id 0 | task 25524 | prompt eval time = 3354.16 ms / 553 tokens ( 6.07 ms per token, 164.87 tokens per second) 21.05.576.837 I slot print_timing: id 0 | task 25524 | eval time = 657.72 ms / 2 tokens ( 657.72 ms per token, 1.52 tokens per second) 21.05.576.838 I slot print_timing: id 0 | task 25524 | total time = 4011.88 ms / 555 tokens 21.05.576.838 I slot print_timing: id 0 | task 25524 | graphs reused = 23829 21.05.576.838 I slot print_timing: id 0 | task 25524 | graph reallocs = 0 / 0 (same size) / (changed size) 21.05.576.882 I slot release: id 0 | task 25524 | stop processing: n_tokens = 732, truncated = 0 21.05.577.185 I slot print_timing: id 1 | task 25525 | prompt eval time = 3354.44 ms / 874 tokens ( 3.84 ms per token, 260.55 tokens per second) 21.05.577.189 I slot print_timing: id 1 | task 25525 | eval time = 657.70 ms / 2 tokens ( 657.70 ms per token, 1.52 tokens per second) 21.05.577.190 I slot print_timing: id 1 | task 25525 | total time = 4012.14 ms / 876 tokens 21.05.577.190 I slot print_timing: id 1 | task 25525 | graphs reused = 23829 21.05.577.190 I slot print_timing: id 1 | task 25525 | graph reallocs = 0 / 0 (same size) / (changed size) 21.05.577.247 I slot release: id 1 | task 25525 | stop processing: n_tokens = 875, truncated = 0 21.05.577.253 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 692, t_last = 346113271047 21.05.579.580 I slot launch_slot_: id 2 | task 25532 | processing task, is_child = 0 21.06.489.721 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 346113928088 21.06.489.819 I slot launch_slot_: id 0 | task 25534 | processing task, is_child = 0 21.06.489.867 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 875, t_last = 346113928455 21.06.489.940 I slot launch_slot_: id 1 | task 25535 | processing task, is_child = 0 21.08.782.532 I slot print_timing: id 3 | task 25529 | prompt eval time = 2111.89 ms / 861 tokens ( 2.45 ms per token, 407.69 tokens per second) 21.08.782.534 I slot print_timing: id 3 | task 25529 | eval time = 2292.81 ms / 2 tokens ( 2292.81 ms per token, 0.44 tokens per second) 21.08.782.535 I slot print_timing: id 3 | task 25529 | total time = 4404.69 ms / 863 tokens 21.08.782.535 I slot print_timing: id 3 | task 25529 | graphs reused = 23829 21.08.782.536 I slot print_timing: id 3 | task 25529 | graph reallocs = 0 / 0 (same size) / (changed size) 21.08.782.585 I slot release: id 3 | task 25529 | stop processing: n_tokens = 862, truncated = 0 21.08.782.673 I slot print_timing: id 2 | task 25532 | prompt processing, n_tokens = 1101, progress = 1.00, t = 3.20 s / 344.26 tokens per second 21.10.131.250 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 862, t_last = 346117133791 21.10.134.852 I slot launch_slot_: id 3 | task 25538 | processing task, is_child = 0 21.10.134.879 I slot print_timing: id 0 | task 25534 | prompt processing, n_tokens = 1092, progress = 1.00, t = 3.64 s / 299.92 tokens per second 21.10.135.127 I slot print_timing: id 1 | task 25535 | prompt processing, n_tokens = 1094, progress = 1.00, t = 3.64 s / 300.47 tokens per second 21.11.043.086 I slot print_timing: id 2 | task 25532 | prompt eval time = 4547.14 ms / 1105 tokens ( 4.12 ms per token, 243.01 tokens per second) 21.11.043.090 I slot print_timing: id 2 | task 25532 | eval time = 911.84 ms / 2 tokens ( 911.84 ms per token, 1.10 tokens per second) 21.11.043.090 I slot print_timing: id 2 | task 25532 | total time = 5458.98 ms / 1107 tokens 21.11.043.101 I slot print_timing: id 2 | task 25532 | graphs reused = 23829 21.11.043.101 I slot print_timing: id 2 | task 25532 | graph reallocs = 0 / 0 (same size) / (changed size) 21.11.043.170 I slot release: id 2 | task 25532 | stop processing: n_tokens = 1106, truncated = 0 21.11.702.909 I slot print_timing: id 0 | task 25534 | prompt eval time = 4552.46 ms / 1096 tokens ( 4.15 ms per token, 240.75 tokens per second) 21.11.702.911 I slot print_timing: id 0 | task 25534 | eval time = 660.50 ms / 2 tokens ( 660.50 ms per token, 1.51 tokens per second) 21.11.702.912 I slot print_timing: id 0 | task 25534 | total time = 5212.96 ms / 1098 tokens 21.11.702.912 I slot print_timing: id 0 | task 25534 | graphs reused = 23829 21.11.702.912 I slot print_timing: id 0 | task 25534 | graph reallocs = 0 / 0 (same size) / (changed size) 21.11.702.967 I slot release: id 0 | task 25534 | stop processing: n_tokens = 1097, truncated = 0 21.11.703.237 I slot print_timing: id 1 | task 25535 | prompt eval time = 4552.80 ms / 1098 tokens ( 4.15 ms per token, 241.17 tokens per second) 21.11.703.239 I slot print_timing: id 1 | task 25535 | eval time = 660.44 ms / 2 tokens ( 660.44 ms per token, 1.51 tokens per second) 21.11.703.240 I slot print_timing: id 1 | task 25535 | total time = 5213.23 ms / 1100 tokens 21.11.703.241 I slot print_timing: id 1 | task 25535 | graphs reused = 23829 21.11.703.241 I slot print_timing: id 1 | task 25535 | graph reallocs = 0 / 0 (same size) / (changed size) 21.11.703.289 I slot release: id 1 | task 25535 | stop processing: n_tokens = 1099, truncated = 0 21.11.703.294 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.897 21.11.703.321 I slot launch_slot_: id 1 | task 25541 | processing task, is_child = 0 21.11.710.936 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.892 21.11.710.980 I slot launch_slot_: id 2 | task 25542 | processing task, is_child = 0 21.11.711.038 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.898 21.11.711.055 I slot launch_slot_: id 0 | task 25543 | processing task, is_child = 0 21.13.848.342 I slot print_timing: id 3 | task 25538 | prompt eval time = 3617.22 ms / 1086 tokens ( 3.33 ms per token, 300.23 tokens per second) 21.13.848.346 I slot print_timing: id 3 | task 25538 | eval time = 95.73 ms / 2 tokens ( 95.73 ms per token, 10.45 tokens per second) 21.13.848.347 I slot print_timing: id 3 | task 25538 | total time = 3712.96 ms / 1088 tokens 21.13.848.348 I slot print_timing: id 3 | task 25538 | graphs reused = 23829 21.13.848.348 I slot print_timing: id 3 | task 25538 | graph reallocs = 0 / 0 (same size) / (changed size) 21.13.848.414 I slot release: id 3 | task 25538 | stop processing: n_tokens = 1087, truncated = 0 21.13.878.728 I slot print_timing: id 0 | task 25543 | prompt eval time = 2136.24 ms / 506 tokens ( 4.22 ms per token, 236.86 tokens per second) 21.13.878.730 I slot print_timing: id 0 | task 25543 | eval time = 31.42 ms / 2 tokens ( 31.42 ms per token, 31.83 tokens per second) 21.13.878.730 I slot print_timing: id 0 | task 25543 | total time = 2167.66 ms / 508 tokens 21.13.878.731 I slot print_timing: id 0 | task 25543 | graphs reused = 23829 21.13.878.731 I slot print_timing: id 0 | task 25543 | graph reallocs = 0 / 0 (same size) / (changed size) 21.13.878.783 I slot release: id 0 | task 25543 | stop processing: n_tokens = 1087, truncated = 0 21.13.879.052 I slot print_timing: id 1 | task 25541 | prompt eval time = 2136.47 ms / 512 tokens ( 4.17 ms per token, 239.65 tokens per second) 21.13.879.055 I slot print_timing: id 1 | task 25541 | eval time = 31.39 ms / 2 tokens ( 31.39 ms per token, 31.86 tokens per second) 21.13.879.056 I slot print_timing: id 1 | task 25541 | total time = 2167.85 ms / 514 tokens 21.13.879.056 I slot print_timing: id 1 | task 25541 | graphs reused = 23829 21.13.879.056 I slot print_timing: id 1 | task 25541 | graph reallocs = 0 / 0 (same size) / (changed size) 21.13.879.094 I slot release: id 1 | task 25541 | stop processing: n_tokens = 1095, truncated = 0 21.13.879.367 I slot print_timing: id 2 | task 25542 | prompt eval time = 2136.72 ms / 506 tokens ( 4.22 ms per token, 236.81 tokens per second) 21.13.879.369 I slot print_timing: id 2 | task 25542 | eval time = 31.32 ms / 2 tokens ( 31.32 ms per token, 31.92 tokens per second) 21.13.879.370 I slot print_timing: id 2 | task 25542 | total time = 2168.05 ms / 508 tokens 21.13.879.370 I slot print_timing: id 2 | task 25542 | graphs reused = 23829 21.13.879.370 I slot print_timing: id 2 | task 25542 | graph reallocs = 0 / 0 (same size) / (changed size) 21.13.879.407 I slot release: id 2 | task 25542 | stop processing: n_tokens = 1096, truncated = 0 21.13.879.413 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 21.13.879.435 I slot launch_slot_: id 0 | task 25547 | processing task, is_child = 0 21.13.889.279 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 21.13.889.313 I slot launch_slot_: id 1 | task 25548 | processing task, is_child = 0 21.13.889.421 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.900 21.13.889.440 I slot launch_slot_: id 2 | task 25549 | processing task, is_child = 0 21.13.889.491 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.894 (> 0.100 thold), f_keep = 0.907 21.13.889.504 I slot launch_slot_: id 3 | task 25550 | processing task, is_child = 0 21.16.850.328 I slot print_timing: id 0 | task 25547 | prompt eval time = 2894.89 ms / 515 tokens ( 5.62 ms per token, 177.90 tokens per second) 21.16.850.330 I slot print_timing: id 0 | task 25547 | eval time = 65.93 ms / 2 tokens ( 65.93 ms per token, 15.17 tokens per second) 21.16.850.331 I slot print_timing: id 0 | task 25547 | total time = 2960.82 ms / 517 tokens 21.16.850.331 I slot print_timing: id 0 | task 25547 | graphs reused = 23830 21.16.850.332 I slot print_timing: id 0 | task 25547 | graph reallocs = 0 / 0 (same size) / (changed size) 21.16.850.393 I slot release: id 0 | task 25547 | stop processing: n_tokens = 1096, truncated = 0 21.16.850.650 I slot print_timing: id 1 | task 25548 | prompt eval time = 2895.11 ms / 506 tokens ( 5.72 ms per token, 174.78 tokens per second) 21.16.850.652 I slot print_timing: id 1 | task 25548 | eval time = 65.90 ms / 2 tokens ( 65.90 ms per token, 15.17 tokens per second) 21.16.850.652 I slot print_timing: id 1 | task 25548 | total time = 2961.01 ms / 508 tokens 21.16.850.652 I slot print_timing: id 1 | task 25548 | graphs reused = 23830 21.16.850.653 I slot print_timing: id 1 | task 25548 | graph reallocs = 0 / 0 (same size) / (changed size) 21.16.850.694 I slot release: id 1 | task 25548 | stop processing: n_tokens = 1089, truncated = 0 21.16.850.951 I slot print_timing: id 2 | task 25549 | prompt eval time = 2895.35 ms / 507 tokens ( 5.71 ms per token, 175.11 tokens per second) 21.16.850.952 I slot print_timing: id 2 | task 25549 | eval time = 65.85 ms / 2 tokens ( 65.85 ms per token, 15.19 tokens per second) 21.16.850.953 I slot print_timing: id 2 | task 25549 | total time = 2961.20 ms / 509 tokens 21.16.850.953 I slot print_timing: id 2 | task 25549 | graphs reused = 23830 21.16.850.953 I slot print_timing: id 2 | task 25549 | graph reallocs = 0 / 0 (same size) / (changed size) 21.16.850.991 I slot release: id 2 | task 25549 | stop processing: n_tokens = 1097, truncated = 0 21.16.866.581 I slot print_timing: id 3 | task 25550 | prompt eval time = 2961.66 ms / 533 tokens ( 5.56 ms per token, 179.97 tokens per second) 21.16.866.584 I slot print_timing: id 3 | task 25550 | eval time = 15.06 ms / 2 tokens ( 15.06 ms per token, 66.40 tokens per second) 21.16.866.584 I slot print_timing: id 3 | task 25550 | total time = 2976.72 ms / 535 tokens 21.16.866.585 I slot print_timing: id 3 | task 25550 | graphs reused = 23830 21.16.866.585 I slot print_timing: id 3 | task 25550 | graph reallocs = 0 / 0 (same size) / (changed size) 21.16.866.635 I slot release: id 3 | task 25550 | stop processing: n_tokens = 1104, truncated = 0 21.16.866.646 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.900 21.16.866.669 I slot launch_slot_: id 0 | task 25555 | processing task, is_child = 0 21.16.875.446 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.905 21.16.875.475 I slot launch_slot_: id 1 | task 25556 | processing task, is_child = 0 21.16.875.584 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.899 21.16.875.602 I slot launch_slot_: id 2 | task 25557 | processing task, is_child = 0 21.16.875.658 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 21.16.875.675 I slot launch_slot_: id 3 | task 25558 | processing task, is_child = 0 21.19.669.564 I slot print_timing: id 0 | task 25555 | prompt eval time = 2755.79 ms / 513 tokens ( 5.37 ms per token, 186.15 tokens per second) 21.19.669.566 I slot print_timing: id 0 | task 25555 | eval time = 38.09 ms / 2 tokens ( 38.09 ms per token, 26.25 tokens per second) 21.19.669.567 I slot print_timing: id 0 | task 25555 | total time = 2793.88 ms / 515 tokens 21.19.669.567 I slot print_timing: id 0 | task 25555 | graphs reused = 23831 21.19.669.568 I slot print_timing: id 0 | task 25555 | graph reallocs = 0 / 0 (same size) / (changed size) 21.19.669.624 I slot release: id 0 | task 25555 | stop processing: n_tokens = 1094, truncated = 0 21.19.669.885 I slot print_timing: id 1 | task 25556 | prompt eval time = 2755.96 ms / 510 tokens ( 5.40 ms per token, 185.05 tokens per second) 21.19.669.897 I slot print_timing: id 1 | task 25556 | eval time = 38.12 ms / 2 tokens ( 38.12 ms per token, 26.24 tokens per second) 21.19.669.898 I slot print_timing: id 1 | task 25556 | total time = 2794.07 ms / 512 tokens 21.19.669.898 I slot print_timing: id 1 | task 25556 | graphs reused = 23831 21.19.669.898 I slot print_timing: id 1 | task 25556 | graph reallocs = 0 / 0 (same size) / (changed size) 21.19.669.941 I slot release: id 1 | task 25556 | stop processing: n_tokens = 1093, truncated = 0 21.19.670.211 I slot print_timing: id 2 | task 25557 | prompt eval time = 2756.17 ms / 500 tokens ( 5.51 ms per token, 181.41 tokens per second) 21.19.670.214 I slot print_timing: id 2 | task 25557 | eval time = 38.13 ms / 2 tokens ( 38.13 ms per token, 26.23 tokens per second) 21.19.670.214 I slot print_timing: id 2 | task 25557 | total time = 2794.29 ms / 502 tokens 21.19.670.214 I slot print_timing: id 2 | task 25557 | graphs reused = 23831 21.19.670.214 I slot print_timing: id 2 | task 25557 | graph reallocs = 0 / 0 (same size) / (changed size) 21.19.670.255 I slot release: id 2 | task 25557 | stop processing: n_tokens = 1090, truncated = 0 21.19.670.535 I slot print_timing: id 3 | task 25558 | prompt eval time = 2756.64 ms / 504 tokens ( 5.47 ms per token, 182.83 tokens per second) 21.19.670.536 I slot print_timing: id 3 | task 25558 | eval time = 37.86 ms / 2 tokens ( 37.86 ms per token, 26.41 tokens per second) 21.19.670.537 I slot print_timing: id 3 | task 25558 | total time = 2794.50 ms / 506 tokens 21.19.670.537 I slot print_timing: id 3 | task 25558 | graphs reused = 23831 21.19.670.537 I slot print_timing: id 3 | task 25558 | graph reallocs = 0 / 0 (same size) / (changed size) 21.19.670.580 I slot release: id 3 | task 25558 | stop processing: n_tokens = 1092, truncated = 0 21.19.677.395 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1094, t_last = 346128020830 21.19.680.549 I slot launch_slot_: id 0 | task 25562 | processing task, is_child = 0 21.19.689.471 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1093, t_last = 346128021147 21.19.689.577 I slot launch_slot_: id 1 | task 25563 | processing task, is_child = 0 21.19.689.694 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1090, t_last = 346128021461 21.19.689.768 I slot launch_slot_: id 2 | task 25564 | processing task, is_child = 0 21.19.689.831 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1092, t_last = 346128021786 21.19.689.910 I slot launch_slot_: id 3 | task 25565 | processing task, is_child = 0 21.24.424.166 I slot print_timing: id 0 | task 25562 | prompt processing, n_tokens = 1062, progress = 1.00, t = 4.73 s / 224.32 tokens per second 21.25.063.723 I slot print_timing: id 1 | task 25563 | prompt processing, n_tokens = 979, progress = 1.00, t = 4.73 s / 206.80 tokens per second 21.25.063.889 I slot print_timing: id 2 | task 25564 | prompt processing, n_tokens = 992, progress = 1.00, t = 4.73 s / 209.55 tokens per second 21.25.064.047 I slot print_timing: id 3 | task 25565 | prompt processing, n_tokens = 1033, progress = 1.00, t = 4.73 s / 218.21 tokens per second 21.25.206.603 I slot print_timing: id 0 | task 25562 | prompt eval time = 5478.35 ms / 1066 tokens ( 5.14 ms per token, 194.58 tokens per second) 21.25.206.605 I slot print_timing: id 0 | task 25562 | eval time = 38.33 ms / 2 tokens ( 38.33 ms per token, 26.09 tokens per second) 21.25.206.606 I slot print_timing: id 0 | task 25562 | total time = 5516.68 ms / 1068 tokens 21.25.206.606 I slot print_timing: id 0 | task 25562 | graphs reused = 23832 21.25.206.607 I slot print_timing: id 0 | task 25562 | graph reallocs = 0 / 0 (same size) / (changed size) 21.25.206.669 I slot release: id 0 | task 25562 | stop processing: n_tokens = 1067, truncated = 0 21.25.206.942 I slot print_timing: id 1 | task 25563 | prompt eval time = 5478.53 ms / 983 tokens ( 5.57 ms per token, 179.43 tokens per second) 21.25.206.948 I slot print_timing: id 1 | task 25563 | eval time = 38.38 ms / 2 tokens ( 38.38 ms per token, 26.05 tokens per second) 21.25.206.949 I slot print_timing: id 1 | task 25563 | total time = 5516.92 ms / 985 tokens 21.25.206.949 I slot print_timing: id 1 | task 25563 | graphs reused = 23832 21.25.206.949 I slot print_timing: id 1 | task 25563 | graph reallocs = 0 / 0 (same size) / (changed size) 21.25.206.993 I slot release: id 1 | task 25563 | stop processing: n_tokens = 984, truncated = 0 21.25.207.281 I slot print_timing: id 2 | task 25564 | prompt eval time = 5478.79 ms / 996 tokens ( 5.50 ms per token, 181.79 tokens per second) 21.25.207.285 I slot print_timing: id 2 | task 25564 | eval time = 38.39 ms / 2 tokens ( 38.39 ms per token, 26.05 tokens per second) 21.25.207.285 I slot print_timing: id 2 | task 25564 | total time = 5517.18 ms / 998 tokens 21.25.207.294 I slot print_timing: id 2 | task 25564 | graphs reused = 23832 21.25.207.294 I slot print_timing: id 2 | task 25564 | graph reallocs = 0 / 0 (same size) / (changed size) 21.25.207.333 I slot release: id 2 | task 25564 | stop processing: n_tokens = 997, truncated = 0 21.25.207.630 I slot print_timing: id 3 | task 25565 | prompt eval time = 5479.29 ms / 1037 tokens ( 5.28 ms per token, 189.26 tokens per second) 21.25.207.633 I slot print_timing: id 3 | task 25565 | eval time = 38.16 ms / 2 tokens ( 38.16 ms per token, 26.21 tokens per second) 21.25.207.634 I slot print_timing: id 3 | task 25565 | total time = 5517.45 ms / 1039 tokens 21.25.207.634 I slot print_timing: id 3 | task 25565 | graphs reused = 23832 21.25.207.634 I slot print_timing: id 3 | task 25565 | graph reallocs = 0 / 0 (same size) / (changed size) 21.25.207.676 I slot release: id 3 | task 25565 | stop processing: n_tokens = 1038, truncated = 0 21.25.214.590 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.817 21.25.214.610 I slot launch_slot_: id 0 | task 25570 | processing task, is_child = 0 21.25.223.679 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.886 21.25.223.709 I slot launch_slot_: id 1 | task 25571 | processing task, is_child = 0 21.25.223.821 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 997, t_last = 346133558539 21.25.223.892 I slot launch_slot_: id 2 | task 25573 | processing task, is_child = 0 21.25.223.944 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1038, t_last = 346133558882 21.25.224.015 I slot launch_slot_: id 3 | task 25572 | processing task, is_child = 0 21.28.723.929 I slot print_timing: id 1 | task 25571 | prompt processing, n_tokens = 536, progress = 1.00, t = 3.50 s / 153.17 tokens per second 21.28.724.116 I slot print_timing: id 2 | task 25573 | prompt processing, n_tokens = 770, progress = 0.99, t = 3.50 s / 220.04 tokens per second 21.28.724.251 I slot print_timing: id 3 | task 25572 | prompt processing, n_tokens = 727, progress = 0.99, t = 3.50 s / 207.76 tokens per second 21.28.825.076 I slot print_timing: id 0 | task 25570 | prompt eval time = 3499.89 ms / 444 tokens ( 7.88 ms per token, 126.86 tokens per second) 21.28.825.078 I slot print_timing: id 0 | task 25570 | eval time = 101.16 ms / 2 tokens ( 101.16 ms per token, 9.89 tokens per second) 21.28.825.079 I slot print_timing: id 0 | task 25570 | total time = 3601.05 ms / 446 tokens 21.28.825.079 I slot print_timing: id 0 | task 25570 | graphs reused = 23832 21.28.825.080 I slot print_timing: id 0 | task 25570 | graph reallocs = 0 / 0 (same size) / (changed size) 21.28.825.136 I slot release: id 0 | task 25570 | stop processing: n_tokens = 995, truncated = 0 21.28.856.721 I slot print_timing: id 1 | task 25571 | prompt eval time = 3601.27 ms / 540 tokens ( 6.67 ms per token, 149.95 tokens per second) 21.28.856.723 I slot print_timing: id 1 | task 25571 | eval time = 31.28 ms / 2 tokens ( 31.28 ms per token, 31.97 tokens per second) 21.28.856.724 I slot print_timing: id 1 | task 25571 | total time = 3632.55 ms / 542 tokens 21.28.856.724 I slot print_timing: id 1 | task 25571 | graphs reused = 23832 21.28.856.725 I slot print_timing: id 1 | task 25571 | graph reallocs = 0 / 0 (same size) / (changed size) 21.28.856.780 I slot release: id 1 | task 25571 | stop processing: n_tokens = 1008, truncated = 0 21.28.857.061 I slot print_timing: id 2 | task 25573 | prompt eval time = 3601.62 ms / 774 tokens ( 4.65 ms per token, 214.90 tokens per second) 21.28.857.064 I slot print_timing: id 2 | task 25573 | eval time = 31.19 ms / 2 tokens ( 31.19 ms per token, 32.06 tokens per second) 21.28.857.064 I slot print_timing: id 2 | task 25573 | total time = 3632.81 ms / 776 tokens 21.28.857.064 I slot print_timing: id 2 | task 25573 | graphs reused = 23832 21.28.857.065 I slot print_timing: id 2 | task 25573 | graph reallocs = 0 / 0 (same size) / (changed size) 21.28.857.107 I slot release: id 2 | task 25573 | stop processing: n_tokens = 775, truncated = 0 21.28.857.390 I slot print_timing: id 3 | task 25572 | prompt eval time = 3602.16 ms / 731 tokens ( 4.93 ms per token, 202.93 tokens per second) 21.28.857.393 I slot print_timing: id 3 | task 25572 | eval time = 30.90 ms / 2 tokens ( 30.90 ms per token, 32.36 tokens per second) 21.28.857.393 I slot print_timing: id 3 | task 25572 | total time = 3633.06 ms / 733 tokens 21.28.857.393 I slot print_timing: id 3 | task 25572 | graphs reused = 23832 21.28.857.394 I slot print_timing: id 3 | task 25572 | graph reallocs = 0 / 0 (same size) / (changed size) 21.28.857.431 I slot release: id 3 | task 25572 | stop processing: n_tokens = 732, truncated = 0 21.28.857.440 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.894 (> 0.100 thold), f_keep = 0.814 21.28.857.465 I slot launch_slot_: id 2 | task 25578 | processing task, is_child = 0 21.28.864.729 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.865 21.28.864.753 I slot launch_slot_: id 3 | task 25579 | processing task, is_child = 0 21.28.864.858 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 995, t_last = 346137176343 21.28.865.518 I slot launch_slot_: id 0 | task 25580 | processing task, is_child = 0 21.28.865.576 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1008, t_last = 346137207986 21.28.865.643 I slot launch_slot_: id 1 | task 25581 | processing task, is_child = 0 21.31.906.132 I slot print_timing: id 1 | task 25581 | prompt processing, n_tokens = 711, progress = 0.99, t = 3.04 s / 233.93 tokens per second 21.31.978.056 I slot print_timing: id 0 | task 25580 | prompt eval time = 3039.81 ms / 508 tokens ( 5.98 ms per token, 167.12 tokens per second) 21.31.978.059 I slot print_timing: id 0 | task 25580 | eval time = 72.60 ms / 2 tokens ( 72.60 ms per token, 13.77 tokens per second) 21.31.978.060 I slot print_timing: id 0 | task 25580 | total time = 3112.40 ms / 510 tokens 21.31.978.060 I slot print_timing: id 0 | task 25580 | graphs reused = 23832 21.31.978.061 I slot print_timing: id 0 | task 25580 | graph reallocs = 0 / 0 (same size) / (changed size) 21.31.978.104 I slot release: id 0 | task 25580 | stop processing: n_tokens = 724, truncated = 0 21.31.978.790 I slot print_timing: id 2 | task 25578 | prompt eval time = 3039.93 ms / 448 tokens ( 6.79 ms per token, 147.37 tokens per second) 21.31.978.792 I slot print_timing: id 2 | task 25578 | eval time = 73.03 ms / 2 tokens ( 73.03 ms per token, 13.69 tokens per second) 21.31.978.792 I slot print_timing: id 2 | task 25578 | total time = 3112.97 ms / 450 tokens 21.31.978.793 I slot print_timing: id 2 | task 25578 | graphs reused = 23832 21.31.978.793 I slot print_timing: id 2 | task 25578 | graph reallocs = 0 / 0 (same size) / (changed size) 21.31.978.830 I slot release: id 2 | task 25578 | stop processing: n_tokens = 707, truncated = 0 21.31.979.119 I slot print_timing: id 3 | task 25579 | prompt eval time = 3040.19 ms / 506 tokens ( 6.01 ms per token, 166.44 tokens per second) 21.31.979.121 I slot print_timing: id 3 | task 25579 | eval time = 73.00 ms / 2 tokens ( 73.00 ms per token, 13.70 tokens per second) 21.31.979.122 I slot print_timing: id 3 | task 25579 | total time = 3113.19 ms / 508 tokens 21.31.979.122 I slot print_timing: id 3 | task 25579 | graphs reused = 23832 21.31.979.122 I slot print_timing: id 3 | task 25579 | graph reallocs = 0 / 0 (same size) / (changed size) 21.31.979.154 I slot release: id 3 | task 25579 | stop processing: n_tokens = 722, truncated = 0 21.31.994.029 I slot print_timing: id 1 | task 25581 | prompt eval time = 3112.74 ms / 715 tokens ( 4.35 ms per token, 229.70 tokens per second) 21.31.994.031 I slot print_timing: id 1 | task 25581 | eval time = 15.53 ms / 2 tokens ( 15.53 ms per token, 64.38 tokens per second) 21.31.994.031 I slot print_timing: id 1 | task 25581 | total time = 3128.27 ms / 717 tokens 21.31.994.031 I slot print_timing: id 1 | task 25581 | graphs reused = 23832 21.31.994.032 I slot print_timing: id 1 | task 25581 | graph reallocs = 0 / 0 (same size) / (changed size) 21.31.994.067 I slot release: id 1 | task 25581 | stop processing: n_tokens = 716, truncated = 0 21.31.994.074 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.872 21.31.994.097 I slot launch_slot_: id 0 | task 25586 | processing task, is_child = 0 21.31.999.220 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.881 21.31.999.249 I slot launch_slot_: id 1 | task 25587 | processing task, is_child = 0 21.31.999.339 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.893 21.31.999.359 I slot launch_slot_: id 2 | task 25588 | processing task, is_child = 0 21.31.999.405 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 722, t_last = 346140330360 21.31.999.468 I slot launch_slot_: id 3 | task 25589 | processing task, is_child = 0 21.35.494.731 I slot print_timing: id 3 | task 25589 | prompt processing, n_tokens = 940, progress = 1.00, t = 3.49 s / 269.04 tokens per second 21.35.559.234 I slot print_timing: id 0 | task 25586 | prompt eval time = 3494.56 ms / 516 tokens ( 6.77 ms per token, 147.66 tokens per second) 21.35.559.236 I slot print_timing: id 0 | task 25586 | eval time = 65.20 ms / 2 tokens ( 65.20 ms per token, 15.34 tokens per second) 21.35.559.236 I slot print_timing: id 0 | task 25586 | total time = 3559.76 ms / 518 tokens 21.35.559.237 I slot print_timing: id 0 | task 25586 | graphs reused = 23833 21.35.559.237 I slot print_timing: id 0 | task 25586 | graph reallocs = 0 / 0 (same size) / (changed size) 21.35.559.287 I slot release: id 0 | task 25586 | stop processing: n_tokens = 732, truncated = 0 21.35.559.567 I slot print_timing: id 1 | task 25587 | prompt eval time = 3494.75 ms / 510 tokens ( 6.85 ms per token, 145.93 tokens per second) 21.35.559.569 I slot print_timing: id 1 | task 25587 | eval time = 65.22 ms / 2 tokens ( 65.22 ms per token, 15.33 tokens per second) 21.35.559.569 I slot print_timing: id 1 | task 25587 | total time = 3559.97 ms / 512 tokens 21.35.559.570 I slot print_timing: id 1 | task 25587 | graphs reused = 23833 21.35.559.570 I slot print_timing: id 1 | task 25587 | graph reallocs = 0 / 0 (same size) / (changed size) 21.35.559.605 I slot release: id 1 | task 25587 | stop processing: n_tokens = 710, truncated = 0 21.35.559.887 I slot print_timing: id 2 | task 25588 | prompt eval time = 3495.01 ms / 465 tokens ( 7.52 ms per token, 133.05 tokens per second) 21.35.559.892 I slot print_timing: id 2 | task 25588 | eval time = 65.17 ms / 2 tokens ( 65.17 ms per token, 15.34 tokens per second) 21.35.559.892 I slot print_timing: id 2 | task 25588 | total time = 3560.18 ms / 467 tokens 21.35.559.893 I slot print_timing: id 2 | task 25588 | graphs reused = 23833 21.35.559.893 I slot print_timing: id 2 | task 25588 | graph reallocs = 0 / 0 (same size) / (changed size) 21.35.559.920 I slot release: id 2 | task 25588 | stop processing: n_tokens = 724, truncated = 0 21.35.575.042 I slot print_timing: id 3 | task 25589 | prompt eval time = 3560.53 ms / 944 tokens ( 3.77 ms per token, 265.13 tokens per second) 21.35.575.044 I slot print_timing: id 3 | task 25589 | eval time = 14.70 ms / 2 tokens ( 14.70 ms per token, 68.03 tokens per second) 21.35.575.044 I slot print_timing: id 3 | task 25589 | total time = 3575.23 ms / 946 tokens 21.35.575.045 I slot print_timing: id 3 | task 25589 | graphs reused = 23833 21.35.575.045 I slot print_timing: id 3 | task 25589 | graph reallocs = 0 / 0 (same size) / (changed size) 21.35.575.101 I slot release: id 3 | task 25589 | stop processing: n_tokens = 945, truncated = 0 21.35.575.107 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.852 21.35.575.129 I slot launch_slot_: id 3 | task 25594 | processing task, is_child = 0 21.35.581.358 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 346143910493 21.35.581.449 I slot launch_slot_: id 0 | task 25595 | processing task, is_child = 0 21.35.581.540 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 346143910811 21.35.581.602 I slot launch_slot_: id 1 | task 25596 | processing task, is_child = 0 21.35.581.648 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 724, t_last = 346143911126 21.35.581.726 I slot launch_slot_: id 2 | task 25597 | processing task, is_child = 0 21.40.481.361 I slot print_timing: id 0 | task 25595 | prompt processing, n_tokens = 995, progress = 1.00, t = 4.90 s / 203.09 tokens per second 21.40.481.548 I slot print_timing: id 1 | task 25596 | prompt processing, n_tokens = 910, progress = 1.00, t = 4.90 s / 185.74 tokens per second 21.40.481.704 I slot print_timing: id 2 | task 25597 | prompt processing, n_tokens = 1047, progress = 1.00, t = 4.90 s / 213.71 tokens per second 21.40.576.820 I slot print_timing: id 3 | task 25594 | prompt eval time = 4899.43 ms / 502 tokens ( 9.76 ms per token, 102.46 tokens per second) 21.40.576.825 I slot print_timing: id 3 | task 25594 | eval time = 95.47 ms / 2 tokens ( 95.47 ms per token, 10.47 tokens per second) 21.40.576.825 I slot print_timing: id 3 | task 25594 | total time = 4994.90 ms / 504 tokens 21.40.576.826 I slot print_timing: id 3 | task 25594 | graphs reused = 23833 21.40.576.827 I slot print_timing: id 3 | task 25594 | graph reallocs = 0 / 0 (same size) / (changed size) 21.40.576.900 I slot release: id 3 | task 25594 | stop processing: n_tokens = 931, truncated = 0 21.40.607.204 I slot print_timing: id 0 | task 25595 | prompt eval time = 4994.14 ms / 999 tokens ( 5.00 ms per token, 200.03 tokens per second) 21.40.607.209 I slot print_timing: id 0 | task 25595 | eval time = 31.33 ms / 2 tokens ( 31.33 ms per token, 31.92 tokens per second) 21.40.607.210 I slot print_timing: id 0 | task 25595 | total time = 5025.47 ms / 1001 tokens 21.40.607.211 I slot print_timing: id 0 | task 25595 | graphs reused = 23833 21.40.607.211 I slot print_timing: id 0 | task 25595 | graph reallocs = 0 / 0 (same size) / (changed size) 21.40.607.265 I slot release: id 0 | task 25595 | stop processing: n_tokens = 1000, truncated = 0 21.40.607.545 I slot print_timing: id 1 | task 25596 | prompt eval time = 4994.38 ms / 914 tokens ( 5.46 ms per token, 183.01 tokens per second) 21.40.607.548 I slot print_timing: id 1 | task 25596 | eval time = 31.36 ms / 2 tokens ( 31.36 ms per token, 31.88 tokens per second) 21.40.607.549 I slot print_timing: id 1 | task 25596 | total time = 5025.75 ms / 916 tokens 21.40.607.549 I slot print_timing: id 1 | task 25596 | graphs reused = 23833 21.40.607.549 I slot print_timing: id 1 | task 25596 | graph reallocs = 0 / 0 (same size) / (changed size) 21.40.607.590 I slot release: id 1 | task 25596 | stop processing: n_tokens = 915, truncated = 0 21.40.607.864 I slot print_timing: id 2 | task 25597 | prompt eval time = 4994.64 ms / 1051 tokens ( 4.75 ms per token, 210.43 tokens per second) 21.40.607.866 I slot print_timing: id 2 | task 25597 | eval time = 31.36 ms / 2 tokens ( 31.36 ms per token, 31.88 tokens per second) 21.40.607.867 I slot print_timing: id 2 | task 25597 | total time = 5026.01 ms / 1053 tokens 21.40.607.867 I slot print_timing: id 2 | task 25597 | graphs reused = 23833 21.40.607.867 I slot print_timing: id 2 | task 25597 | graph reallocs = 0 / 0 (same size) / (changed size) 21.40.607.923 I slot release: id 2 | task 25597 | stop processing: n_tokens = 1052, truncated = 0 21.40.607.928 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 21.40.607.953 I slot launch_slot_: id 2 | task 25602 | processing task, is_child = 0 21.40.616.627 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 346148928106 21.40.616.736 I slot launch_slot_: id 3 | task 25603 | processing task, is_child = 0 21.40.616.847 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1000, t_last = 346148958472 21.40.616.915 I slot launch_slot_: id 0 | task 25604 | processing task, is_child = 0 21.40.616.961 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 915, t_last = 346148958796 21.40.617.025 I slot launch_slot_: id 1 | task 25605 | processing task, is_child = 0 21.45.488.518 I slot print_timing: id 0 | task 25604 | prompt processing, n_tokens = 2081, progress = 1.00, t = 4.87 s / 427.18 tokens per second 21.46.070.672 I slot print_timing: id 1 | task 25605 | prompt processing, n_tokens = 1555, progress = 0.75, t = 4.87 s / 319.21 tokens per second 21.48.787.080 I slot print_timing: id 1 | task 25605 | prompt processing, n_tokens = 2067, progress = 1.00, t = 8.17 s / 253.01 tokens per second 21.48.787.401 I slot print_timing: id 2 | task 25602 | prompt processing, n_tokens = 515, progress = 1.00, t = 5.50 s / 93.61 tokens per second 21.48.787.575 I slot print_timing: id 3 | task 25603 | prompt processing, n_tokens = 1477, progress = 0.72, t = 5.50 s / 268.48 tokens per second 21.49.074.688 I slot print_timing: id 0 | task 25604 | prompt eval time = 8170.03 ms / 2085 tokens ( 3.92 ms per token, 255.20 tokens per second) 21.49.074.692 I slot print_timing: id 0 | task 25604 | eval time = 287.62 ms / 2 tokens ( 287.62 ms per token, 3.48 tokens per second) 21.49.074.693 I slot print_timing: id 0 | task 25604 | total time = 8457.66 ms / 2087 tokens 21.49.074.694 I slot print_timing: id 0 | task 25604 | graphs reused = 23833 21.49.074.694 I slot print_timing: id 0 | task 25604 | graph reallocs = 0 / 0 (same size) / (changed size) 21.49.074.809 I slot release: id 0 | task 25604 | stop processing: n_tokens = 2086, truncated = 0 21.49.075.521 I slot print_timing: id 3 | task 25603 | prompt processing, n_tokens = 1533, progress = 0.75, t = 5.79 s / 264.81 tokens per second 21.49.762.353 I slot print_timing: id 1 | task 25605 | prompt eval time = 8458.05 ms / 2071 tokens ( 4.08 ms per token, 244.86 tokens per second) 21.49.762.358 I slot print_timing: id 1 | task 25605 | eval time = 687.19 ms / 2 tokens ( 687.19 ms per token, 1.46 tokens per second) 21.49.762.358 I slot print_timing: id 1 | task 25605 | total time = 9145.24 ms / 2073 tokens 21.49.762.359 I slot print_timing: id 1 | task 25605 | graphs reused = 23833 21.49.762.359 I slot print_timing: id 1 | task 25605 | graph reallocs = 0 / 0 (same size) / (changed size) 21.49.762.466 I slot release: id 1 | task 25605 | stop processing: n_tokens = 2072, truncated = 0 21.49.762.788 I slot print_timing: id 2 | task 25602 | prompt eval time = 5790.24 ms / 519 tokens ( 11.16 ms per token, 89.63 tokens per second) 21.49.762.790 I slot print_timing: id 2 | task 25602 | eval time = 687.28 ms / 2 tokens ( 687.28 ms per token, 1.46 tokens per second) 21.49.762.791 I slot print_timing: id 2 | task 25602 | total time = 6477.52 ms / 521 tokens 21.49.762.791 I slot print_timing: id 2 | task 25602 | graphs reused = 23833 21.49.762.791 I slot print_timing: id 2 | task 25602 | graph reallocs = 0 / 0 (same size) / (changed size) 21.49.762.846 I slot release: id 2 | task 25602 | stop processing: n_tokens = 1055, truncated = 0 21.49.762.853 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.850 21.49.762.880 I slot launch_slot_: id 0 | task 25611 | processing task, is_child = 0 21.49.773.811 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.842 (> 0.100 thold), f_keep = 0.856 21.49.773.843 I slot launch_slot_: id 1 | task 25612 | processing task, is_child = 0 21.49.773.895 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1055, t_last = 346158114053 21.49.775.305 I slot launch_slot_: id 2 | task 25613 | processing task, is_child = 0 21.49.775.582 I slot print_timing: id 3 | task 25603 | prompt processing, n_tokens = 2045, progress = 1.00, t = 6.48 s / 315.75 tokens per second 21.52.100.755 I slot print_timing: id 3 | task 25603 | prompt eval time = 7416.41 ms / 2049 tokens ( 3.62 ms per token, 276.28 tokens per second) 21.52.100.758 I slot print_timing: id 3 | task 25603 | eval time = 1398.98 ms / 2 tokens ( 1398.98 ms per token, 0.71 tokens per second) 21.52.100.759 I slot print_timing: id 3 | task 25603 | total time = 8815.40 ms / 2051 tokens 21.52.100.759 I slot print_timing: id 3 | task 25603 | graphs reused = 23833 21.52.100.760 I slot print_timing: id 3 | task 25603 | graph reallocs = 0 / 0 (same size) / (changed size) 21.52.100.880 I slot release: id 3 | task 25603 | stop processing: n_tokens = 2050, truncated = 0 21.52.178.352 I slot print_timing: id 0 | task 25611 | prompt eval time = 2325.13 ms / 457 tokens ( 5.09 ms per token, 196.55 tokens per second) 21.52.178.354 I slot print_timing: id 0 | task 25611 | eval time = 77.91 ms / 2 tokens ( 77.91 ms per token, 12.84 tokens per second) 21.52.178.355 I slot print_timing: id 0 | task 25611 | total time = 2403.04 ms / 459 tokens 21.52.178.355 I slot print_timing: id 0 | task 25611 | graphs reused = 23833 21.52.178.355 I slot print_timing: id 0 | task 25611 | graph reallocs = 0 / 0 (same size) / (changed size) 21.52.178.466 I slot release: id 0 | task 25611 | stop processing: n_tokens = 2027, truncated = 0 21.52.179.300 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 21.52.179.347 I slot launch_slot_: id 0 | task 25617 | processing task, is_child = 0 21.52.822.882 I slot print_timing: id 1 | task 25612 | prompt eval time = 2403.42 ms / 551 tokens ( 4.36 ms per token, 229.26 tokens per second) 21.52.822.884 I slot print_timing: id 1 | task 25612 | eval time = 644.03 ms / 2 tokens ( 644.03 ms per token, 1.55 tokens per second) 21.52.822.884 I slot print_timing: id 1 | task 25612 | total time = 3047.44 ms / 553 tokens 21.52.822.884 I slot print_timing: id 1 | task 25612 | graphs reused = 23833 21.52.822.885 I slot print_timing: id 1 | task 25612 | graph reallocs = 0 / 0 (same size) / (changed size) 21.52.823.002 I slot release: id 1 | task 25612 | stop processing: n_tokens = 2107, truncated = 0 21.52.823.320 I slot print_timing: id 2 | task 25613 | prompt eval time = 2403.78 ms / 561 tokens ( 4.28 ms per token, 233.38 tokens per second) 21.52.823.322 I slot print_timing: id 2 | task 25613 | eval time = 644.02 ms / 2 tokens ( 644.02 ms per token, 1.55 tokens per second) 21.52.823.322 I slot print_timing: id 2 | task 25613 | total time = 3047.80 ms / 563 tokens 21.52.823.322 I slot print_timing: id 2 | task 25613 | graphs reused = 23833 21.52.823.323 I slot print_timing: id 2 | task 25613 | graph reallocs = 0 / 0 (same size) / (changed size) 21.52.823.424 I slot release: id 2 | task 25613 | stop processing: n_tokens = 2117, truncated = 0 21.52.823.432 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 21.52.823.464 I slot launch_slot_: id 1 | task 25619 | processing task, is_child = 0 21.52.980.610 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 21.52.980.651 I slot launch_slot_: id 2 | task 25621 | processing task, is_child = 0 21.52.980.752 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.805 (> 0.100 thold), f_keep = 0.865 21.52.980.770 I slot launch_slot_: id 3 | task 25622 | processing task, is_child = 0 21.54.485.460 I slot print_timing: id 0 | task 25617 | prompt eval time = 799.18 ms / 478 tokens ( 1.67 ms per token, 598.11 tokens per second) 21.54.485.463 I slot print_timing: id 0 | task 25617 | eval time = 1504.86 ms / 2 tokens ( 1504.86 ms per token, 0.66 tokens per second) 21.54.485.464 I slot print_timing: id 0 | task 25617 | total time = 2304.04 ms / 480 tokens 21.54.485.464 I slot print_timing: id 0 | task 25617 | graphs reused = 23833 21.54.485.465 I slot print_timing: id 0 | task 25617 | graph reallocs = 0 / 0 (same size) / (changed size) 21.54.485.581 I slot release: id 0 | task 25617 | stop processing: n_tokens = 2048, truncated = 0 21.55.222.460 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 21.55.222.500 I slot launch_slot_: id 0 | task 25625 | processing task, is_child = 0 21.55.853.180 I slot print_timing: id 1 | task 25619 | prompt eval time = 2389.05 ms / 536 tokens ( 4.46 ms per token, 224.36 tokens per second) 21.55.853.184 I slot print_timing: id 1 | task 25619 | eval time = 631.11 ms / 2 tokens ( 631.11 ms per token, 1.58 tokens per second) 21.55.853.185 I slot print_timing: id 1 | task 25619 | total time = 3020.16 ms / 538 tokens 21.55.853.185 I slot print_timing: id 1 | task 25619 | graphs reused = 23833 21.55.853.186 I slot print_timing: id 1 | task 25619 | graph reallocs = 0 / 0 (same size) / (changed size) 21.55.853.297 I slot release: id 1 | task 25619 | stop processing: n_tokens = 2127, truncated = 0 21.55.853.625 I slot print_timing: id 2 | task 25621 | prompt eval time = 2241.64 ms / 355 tokens ( 6.31 ms per token, 158.37 tokens per second) 21.55.853.627 I slot print_timing: id 2 | task 25621 | eval time = 631.17 ms / 2 tokens ( 631.17 ms per token, 1.58 tokens per second) 21.55.853.627 I slot print_timing: id 2 | task 25621 | total time = 2872.81 ms / 357 tokens 21.55.853.628 I slot print_timing: id 2 | task 25621 | graphs reused = 23833 21.55.853.628 I slot print_timing: id 2 | task 25621 | graph reallocs = 0 / 0 (same size) / (changed size) 21.55.853.739 I slot release: id 2 | task 25621 | stop processing: n_tokens = 1956, truncated = 0 21.55.902.560 I slot print_timing: id 3 | task 25622 | prompt eval time = 2873.20 ms / 671 tokens ( 4.28 ms per token, 233.54 tokens per second) 21.55.902.563 I slot print_timing: id 3 | task 25622 | eval time = 48.42 ms / 2 tokens ( 48.42 ms per token, 20.65 tokens per second) 21.55.902.564 I slot print_timing: id 3 | task 25622 | total time = 2921.61 ms / 673 tokens 21.55.902.564 I slot print_timing: id 3 | task 25622 | graphs reused = 23833 21.55.902.564 I slot print_timing: id 3 | task 25622 | graph reallocs = 0 / 0 (same size) / (changed size) 21.55.902.673 I slot release: id 3 | task 25622 | stop processing: n_tokens = 2205, truncated = 0 21.55.902.682 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 21.55.902.708 I slot launch_slot_: id 1 | task 25628 | processing task, is_child = 0 21.55.915.762 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 21.55.915.792 I slot launch_slot_: id 2 | task 25629 | processing task, is_child = 0 21.55.915.890 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 21.55.915.906 I slot launch_slot_: id 3 | task 25630 | processing task, is_child = 0 21.57.827.117 I slot print_timing: id 0 | task 25625 | prompt eval time = 679.77 ms / 431 tokens ( 1.58 ms per token, 634.04 tokens per second) 21.57.827.120 I slot print_timing: id 0 | task 25625 | eval time = 1924.84 ms / 2 tokens ( 1924.84 ms per token, 0.52 tokens per second) 21.57.827.120 I slot print_timing: id 0 | task 25625 | total time = 2604.61 ms / 433 tokens 21.57.827.121 I slot print_timing: id 0 | task 25625 | graphs reused = 23834 21.57.827.121 I slot print_timing: id 0 | task 25625 | graph reallocs = 0 / 0 (same size) / (changed size) 21.57.827.231 I slot release: id 0 | task 25625 | stop processing: n_tokens = 2001, truncated = 0 21.57.910.803 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 21.57.910.840 I slot launch_slot_: id 0 | task 25633 | processing task, is_child = 0 21.58.474.885 I slot print_timing: id 1 | task 25628 | prompt eval time = 1994.24 ms / 441 tokens ( 4.52 ms per token, 221.14 tokens per second) 21.58.474.887 I slot print_timing: id 1 | task 25628 | eval time = 564.73 ms / 2 tokens ( 564.73 ms per token, 1.77 tokens per second) 21.58.474.888 I slot print_timing: id 1 | task 25628 | total time = 2558.97 ms / 443 tokens 21.58.474.888 I slot print_timing: id 1 | task 25628 | graphs reused = 23834 21.58.474.889 I slot print_timing: id 1 | task 25628 | graph reallocs = 0 / 0 (same size) / (changed size) 21.58.474.994 I slot release: id 1 | task 25628 | stop processing: n_tokens = 2052, truncated = 0 21.58.475.276 I slot print_timing: id 2 | task 25629 | prompt eval time = 1994.38 ms / 397 tokens ( 5.02 ms per token, 199.06 tokens per second) 21.58.475.278 I slot print_timing: id 2 | task 25629 | eval time = 564.85 ms / 2 tokens ( 564.85 ms per token, 1.77 tokens per second) 21.58.475.278 I slot print_timing: id 2 | task 25629 | total time = 2559.22 ms / 399 tokens 21.58.475.279 I slot print_timing: id 2 | task 25629 | graphs reused = 23834 21.58.475.279 I slot print_timing: id 2 | task 25629 | graph reallocs = 0 / 0 (same size) / (changed size) 21.58.475.370 I slot release: id 2 | task 25629 | stop processing: n_tokens = 1998, truncated = 0 21.58.475.671 I slot print_timing: id 3 | task 25630 | prompt eval time = 1994.63 ms / 403 tokens ( 4.95 ms per token, 202.04 tokens per second) 21.58.475.674 I slot print_timing: id 3 | task 25630 | eval time = 564.88 ms / 2 tokens ( 564.88 ms per token, 1.77 tokens per second) 21.58.475.674 I slot print_timing: id 3 | task 25630 | total time = 2559.51 ms / 405 tokens 21.58.475.674 I slot print_timing: id 3 | task 25630 | graphs reused = 23834 21.58.475.675 I slot print_timing: id 3 | task 25630 | graph reallocs = 0 / 0 (same size) / (changed size) 21.58.475.768 I slot release: id 3 | task 25630 | stop processing: n_tokens = 2092, truncated = 0 21.58.510.730 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 21.58.510.752 I slot launch_slot_: id 1 | task 25636 | processing task, is_child = 0 21.58.523.007 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 21.58.523.029 I slot launch_slot_: id 2 | task 25637 | processing task, is_child = 0 21.58.523.119 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 21.58.523.134 I slot launch_slot_: id 3 | task 25638 | processing task, is_child = 0 21.59.895.340 I slot print_timing: id 0 | task 25633 | prompt eval time = 599.88 ms / 389 tokens ( 1.54 ms per token, 648.46 tokens per second) 21.59.895.343 I slot print_timing: id 0 | task 25633 | eval time = 1384.61 ms / 2 tokens ( 1384.61 ms per token, 0.72 tokens per second) 21.59.895.344 I slot print_timing: id 0 | task 25633 | total time = 1984.49 ms / 391 tokens 21.59.895.344 I slot print_timing: id 0 | task 25633 | graphs reused = 23834 21.59.895.345 I slot print_timing: id 0 | task 25633 | graph reallocs = 0 / 0 (same size) / (changed size) 21.59.895.460 I slot release: id 0 | task 25633 | stop processing: n_tokens = 1959, truncated = 0 22.00.632.442 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 22.00.632.486 I slot launch_slot_: id 0 | task 25641 | processing task, is_child = 0 22.01.229.370 I slot print_timing: id 1 | task 25636 | prompt eval time = 2108.98 ms / 444 tokens ( 4.75 ms per token, 210.53 tokens per second) 22.01.229.373 I slot print_timing: id 1 | task 25636 | eval time = 597.25 ms / 2 tokens ( 597.25 ms per token, 1.67 tokens per second) 22.01.229.373 I slot print_timing: id 1 | task 25636 | total time = 2706.23 ms / 446 tokens 22.01.229.374 I slot print_timing: id 1 | task 25636 | graphs reused = 23834 22.01.229.374 I slot print_timing: id 1 | task 25636 | graph reallocs = 0 / 0 (same size) / (changed size) 22.01.229.490 I slot release: id 1 | task 25636 | stop processing: n_tokens = 2055, truncated = 0 22.01.230.145 I slot print_timing: id 3 | task 25638 | prompt eval time = 2109.10 ms / 418 tokens ( 5.05 ms per token, 198.19 tokens per second) 22.01.230.148 I slot print_timing: id 3 | task 25638 | eval time = 597.70 ms / 2 tokens ( 597.70 ms per token, 1.67 tokens per second) 22.01.230.148 I slot print_timing: id 3 | task 25638 | total time = 2706.80 ms / 420 tokens 22.01.230.149 I slot print_timing: id 3 | task 25638 | graphs reused = 23834 22.01.230.149 I slot print_timing: id 3 | task 25638 | graph reallocs = 0 / 0 (same size) / (changed size) 22.01.230.287 I slot release: id 3 | task 25638 | stop processing: n_tokens = 2107, truncated = 0 22.01.278.672 I slot print_timing: id 2 | task 25637 | prompt eval time = 2706.52 ms / 555 tokens ( 4.88 ms per token, 205.06 tokens per second) 22.01.278.675 I slot print_timing: id 2 | task 25637 | eval time = 48.88 ms / 2 tokens ( 48.88 ms per token, 20.46 tokens per second) 22.01.278.676 I slot print_timing: id 2 | task 25637 | total time = 2755.40 ms / 557 tokens 22.01.278.676 I slot print_timing: id 2 | task 25637 | graphs reused = 23834 22.01.278.677 I slot print_timing: id 2 | task 25637 | graph reallocs = 0 / 0 (same size) / (changed size) 22.01.278.788 I slot release: id 2 | task 25637 | stop processing: n_tokens = 2156, truncated = 0 22.01.278.797 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 22.01.278.822 I slot launch_slot_: id 3 | task 25644 | processing task, is_child = 0 22.01.292.378 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 22.01.292.410 I slot launch_slot_: id 1 | task 25645 | processing task, is_child = 0 22.01.292.507 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 22.01.292.522 I slot launch_slot_: id 2 | task 25646 | processing task, is_child = 0 22.03.170.717 I slot print_timing: id 0 | task 25641 | prompt eval time = 645.91 ms / 389 tokens ( 1.66 ms per token, 602.25 tokens per second) 22.03.170.720 I slot print_timing: id 0 | task 25641 | eval time = 1892.31 ms / 2 tokens ( 1892.31 ms per token, 0.53 tokens per second) 22.03.170.720 I slot print_timing: id 0 | task 25641 | total time = 2538.22 ms / 391 tokens 22.03.170.721 I slot print_timing: id 0 | task 25641 | graphs reused = 23834 22.03.170.721 I slot print_timing: id 0 | task 25641 | graph reallocs = 0 / 0 (same size) / (changed size) 22.03.170.839 I slot release: id 0 | task 25641 | stop processing: n_tokens = 1959, truncated = 0 22.03.254.949 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 22.03.254.991 I slot launch_slot_: id 0 | task 25649 | processing task, is_child = 0 22.03.861.133 I slot print_timing: id 1 | task 25645 | prompt eval time = 1961.58 ms / 409 tokens ( 4.80 ms per token, 208.51 tokens per second) 22.03.861.136 I slot print_timing: id 1 | task 25645 | eval time = 607.02 ms / 2 tokens ( 607.02 ms per token, 1.65 tokens per second) 22.03.861.136 I slot print_timing: id 1 | task 25645 | total time = 2568.60 ms / 411 tokens 22.03.861.137 I slot print_timing: id 1 | task 25645 | graphs reused = 23834 22.03.861.137 I slot print_timing: id 1 | task 25645 | graph reallocs = 0 / 0 (same size) / (changed size) 22.03.861.250 I slot release: id 1 | task 25645 | stop processing: n_tokens = 2020, truncated = 0 22.03.861.687 I slot print_timing: id 2 | task 25646 | prompt eval time = 1961.81 ms / 338 tokens ( 5.80 ms per token, 172.29 tokens per second) 22.03.861.689 I slot print_timing: id 2 | task 25646 | eval time = 607.20 ms / 2 tokens ( 607.20 ms per token, 1.65 tokens per second) 22.03.861.690 I slot print_timing: id 2 | task 25646 | total time = 2569.01 ms / 340 tokens 22.03.861.691 I slot print_timing: id 2 | task 25646 | graphs reused = 23834 22.03.861.691 I slot print_timing: id 2 | task 25646 | graph reallocs = 0 / 0 (same size) / (changed size) 22.03.861.778 I slot release: id 2 | task 25646 | stop processing: n_tokens = 1978, truncated = 0 22.03.862.264 I slot print_timing: id 3 | task 25644 | prompt eval time = 1962.14 ms / 475 tokens ( 4.13 ms per token, 242.08 tokens per second) 22.03.862.270 I slot print_timing: id 3 | task 25644 | eval time = 607.33 ms / 2 tokens ( 607.33 ms per token, 1.65 tokens per second) 22.03.862.270 I slot print_timing: id 3 | task 25644 | total time = 2569.47 ms / 477 tokens 22.03.862.270 I slot print_timing: id 3 | task 25644 | graphs reused = 23834 22.03.862.271 I slot print_timing: id 3 | task 25644 | graph reallocs = 0 / 0 (same size) / (changed size) 22.03.862.373 I slot release: id 3 | task 25644 | stop processing: n_tokens = 2164, truncated = 0 22.03.897.418 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 22.03.897.444 I slot launch_slot_: id 3 | task 25652 | processing task, is_child = 0 22.03.908.413 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 22.03.908.439 I slot launch_slot_: id 1 | task 25653 | processing task, is_child = 0 22.03.908.528 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 22.03.908.545 I slot launch_slot_: id 2 | task 25654 | processing task, is_child = 0 22.05.224.624 I slot print_timing: id 0 | task 25649 | prompt eval time = 642.41 ms / 435 tokens ( 1.48 ms per token, 677.14 tokens per second) 22.05.224.628 I slot print_timing: id 0 | task 25649 | eval time = 1327.21 ms / 2 tokens ( 1327.21 ms per token, 0.75 tokens per second) 22.05.224.628 I slot print_timing: id 0 | task 25649 | total time = 1969.62 ms / 437 tokens 22.05.224.628 I slot print_timing: id 0 | task 25649 | graphs reused = 23834 22.05.224.629 I slot print_timing: id 0 | task 25649 | graph reallocs = 0 / 0 (same size) / (changed size) 22.05.224.737 I slot release: id 0 | task 25649 | stop processing: n_tokens = 2005, truncated = 0 22.05.307.434 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2005, t_last = 346173575944 22.05.314.640 I slot launch_slot_: id 0 | task 25657 | processing task, is_child = 0 22.06.503.427 I slot print_timing: id 1 | task 25653 | prompt eval time = 1398.17 ms / 281 tokens ( 4.98 ms per token, 200.98 tokens per second) 22.06.503.430 I slot print_timing: id 1 | task 25653 | eval time = 1196.70 ms / 2 tokens ( 1196.70 ms per token, 0.84 tokens per second) 22.06.503.430 I slot print_timing: id 1 | task 25653 | total time = 2594.87 ms / 283 tokens 22.06.503.431 I slot print_timing: id 1 | task 25653 | graphs reused = 23834 22.06.503.431 I slot print_timing: id 1 | task 25653 | graph reallocs = 0 / 0 (same size) / (changed size) 22.06.503.541 I slot release: id 1 | task 25653 | stop processing: n_tokens = 1892, truncated = 0 22.06.503.889 I slot print_timing: id 2 | task 25654 | prompt eval time = 1398.35 ms / 297 tokens ( 4.71 ms per token, 212.39 tokens per second) 22.06.503.891 I slot print_timing: id 2 | task 25654 | eval time = 1196.88 ms / 2 tokens ( 1196.88 ms per token, 0.84 tokens per second) 22.06.503.892 I slot print_timing: id 2 | task 25654 | total time = 2595.23 ms / 299 tokens 22.06.503.892 I slot print_timing: id 2 | task 25654 | graphs reused = 23834 22.06.503.892 I slot print_timing: id 2 | task 25654 | graph reallocs = 0 / 0 (same size) / (changed size) 22.06.503.974 I slot release: id 2 | task 25654 | stop processing: n_tokens = 1937, truncated = 0 22.06.504.549 I slot print_timing: id 3 | task 25652 | prompt eval time = 1398.66 ms / 289 tokens ( 4.84 ms per token, 206.63 tokens per second) 22.06.504.551 I slot print_timing: id 3 | task 25652 | eval time = 1197.12 ms / 2 tokens ( 1197.12 ms per token, 0.84 tokens per second) 22.06.504.551 I slot print_timing: id 3 | task 25652 | total time = 2595.78 ms / 291 tokens 22.06.504.552 I slot print_timing: id 3 | task 25652 | graphs reused = 23834 22.06.504.552 I slot print_timing: id 3 | task 25652 | graph reallocs = 0 / 0 (same size) / (changed size) 22.06.504.644 I slot release: id 3 | task 25652 | stop processing: n_tokens = 1978, truncated = 0 22.07.183.900 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1892, t_last = 346174854748 22.07.190.336 I slot launch_slot_: id 1 | task 25661 | processing task, is_child = 0 22.07.202.664 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1937, t_last = 346174855181 22.07.202.779 I slot launch_slot_: id 2 | task 25662 | processing task, is_child = 0 22.07.202.871 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1978, t_last = 346174855851 22.07.202.982 I slot launch_slot_: id 3 | task 25663 | processing task, is_child = 0 22.09.973.678 I slot print_timing: id 0 | task 25657 | prompt eval time = 1869.25 ms / 1430 tokens ( 1.31 ms per token, 765.01 tokens per second) 22.09.973.681 I slot print_timing: id 0 | task 25657 | eval time = 2789.78 ms / 2 tokens ( 2789.78 ms per token, 0.36 tokens per second) 22.09.973.681 I slot print_timing: id 0 | task 25657 | total time = 4659.03 ms / 1432 tokens 22.09.973.682 I slot print_timing: id 0 | task 25657 | graphs reused = 23834 22.09.973.682 I slot print_timing: id 0 | task 25657 | graph reallocs = 0 / 0 (same size) / (changed size) 22.09.973.767 I slot release: id 0 | task 25657 | stop processing: n_tokens = 1431, truncated = 0 22.11.970.016 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1431, t_last = 346178324973 22.11.990.323 I slot launch_slot_: id 0 | task 25666 | processing task, is_child = 0 22.11.990.456 I slot print_timing: id 1 | task 25661 | prompt processing, n_tokens = 1494, progress = 1.00, t = 4.77 s / 313.40 tokens per second 22.11.990.738 I slot print_timing: id 2 | task 25662 | prompt processing, n_tokens = 977, progress = 1.00, t = 4.77 s / 204.96 tokens per second 22.11.990.893 I slot print_timing: id 3 | task 25663 | prompt processing, n_tokens = 1111, progress = 0.68, t = 4.77 s / 233.07 tokens per second 22.13.316.664 I slot print_timing: id 3 | task 25663 | prompt processing, n_tokens = 1623, progress = 1.00, t = 6.11 s / 265.51 tokens per second 22.14.009.261 I slot print_timing: id 1 | task 25661 | prompt eval time = 6113.27 ms / 1498 tokens ( 4.08 ms per token, 245.04 tokens per second) 22.14.009.267 I slot print_timing: id 1 | task 25661 | eval time = 693.00 ms / 2 tokens ( 693.00 ms per token, 1.44 tokens per second) 22.14.009.267 I slot print_timing: id 1 | task 25661 | total time = 6806.27 ms / 1500 tokens 22.14.009.268 I slot print_timing: id 1 | task 25661 | graphs reused = 23835 22.14.009.268 I slot print_timing: id 1 | task 25661 | graph reallocs = 0 / 0 (same size) / (changed size) 22.14.009.355 I slot release: id 1 | task 25661 | stop processing: n_tokens = 1499, truncated = 0 22.14.009.682 I slot print_timing: id 2 | task 25662 | prompt eval time = 6113.47 ms / 981 tokens ( 6.23 ms per token, 160.47 tokens per second) 22.14.009.685 I slot print_timing: id 2 | task 25662 | eval time = 693.08 ms / 2 tokens ( 693.08 ms per token, 1.44 tokens per second) 22.14.009.686 I slot print_timing: id 2 | task 25662 | total time = 6806.55 ms / 983 tokens 22.14.009.686 I slot print_timing: id 2 | task 25662 | graphs reused = 23835 22.14.009.686 I slot print_timing: id 2 | task 25662 | graph reallocs = 0 / 0 (same size) / (changed size) 22.14.009.743 I slot release: id 2 | task 25662 | stop processing: n_tokens = 982, truncated = 0 22.14.057.907 I slot print_timing: id 3 | task 25663 | prompt eval time = 6806.79 ms / 1627 tokens ( 4.18 ms per token, 239.03 tokens per second) 22.14.057.910 I slot print_timing: id 3 | task 25663 | eval time = 47.85 ms / 2 tokens ( 47.85 ms per token, 20.90 tokens per second) 22.14.057.910 I slot print_timing: id 3 | task 25663 | total time = 6854.64 ms / 1629 tokens 22.14.057.910 I slot print_timing: id 3 | task 25663 | graphs reused = 23835 22.14.057.911 I slot print_timing: id 3 | task 25663 | graph reallocs = 0 / 0 (same size) / (changed size) 22.14.058.006 I slot release: id 3 | task 25663 | stop processing: n_tokens = 1628, truncated = 0 22.14.058.011 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.878 22.14.058.035 I slot launch_slot_: id 2 | task 25670 | processing task, is_child = 0 22.14.066.990 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1499, t_last = 346182360561 22.14.067.098 I slot launch_slot_: id 1 | task 25671 | processing task, is_child = 0 22.14.067.170 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1628, t_last = 346182409212 22.14.067.263 I slot launch_slot_: id 3 | task 25672 | processing task, is_child = 0 22.16.153.590 I slot print_timing: id 0 | task 25666 | prompt eval time = 2067.28 ms / 969 tokens ( 2.13 ms per token, 468.73 tokens per second) 22.16.153.596 I slot print_timing: id 0 | task 25666 | eval time = 2095.97 ms / 2 tokens ( 2095.97 ms per token, 0.48 tokens per second) 22.16.153.597 I slot print_timing: id 0 | task 25666 | total time = 4163.24 ms / 971 tokens 22.16.153.597 I slot print_timing: id 0 | task 25666 | graphs reused = 23835 22.16.153.598 I slot print_timing: id 0 | task 25666 | graph reallocs = 0 / 0 (same size) / (changed size) 22.16.153.666 I slot release: id 0 | task 25666 | stop processing: n_tokens = 970, truncated = 0 22.17.501.299 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 22.17.501.332 I slot launch_slot_: id 0 | task 25675 | processing task, is_child = 0 22.17.501.451 I slot print_timing: id 1 | task 25671 | prompt processing, n_tokens = 939, progress = 1.00, t = 3.43 s / 273.47 tokens per second 22.17.501.608 I slot print_timing: id 3 | task 25672 | prompt processing, n_tokens = 960, progress = 1.00, t = 3.43 s / 279.60 tokens per second 22.18.229.953 I slot print_timing: id 2 | task 25670 | prompt eval time = 3433.90 ms / 493 tokens ( 6.97 ms per token, 143.57 tokens per second) 22.18.229.956 I slot print_timing: id 2 | task 25670 | eval time = 728.66 ms / 2 tokens ( 728.66 ms per token, 1.37 tokens per second) 22.18.229.957 I slot print_timing: id 2 | task 25670 | total time = 4162.56 ms / 495 tokens 22.18.229.957 I slot print_timing: id 2 | task 25670 | graphs reused = 23835 22.18.229.957 I slot print_timing: id 2 | task 25670 | graph reallocs = 0 / 0 (same size) / (changed size) 22.18.230.011 I slot release: id 2 | task 25670 | stop processing: n_tokens = 959, truncated = 0 22.18.291.275 I slot print_timing: id 1 | task 25671 | prompt eval time = 4162.36 ms / 943 tokens ( 4.41 ms per token, 226.55 tokens per second) 22.18.291.280 I slot print_timing: id 1 | task 25671 | eval time = 61.64 ms / 2 tokens ( 61.64 ms per token, 16.22 tokens per second) 22.18.291.280 I slot print_timing: id 1 | task 25671 | total time = 4224.00 ms / 945 tokens 22.18.291.285 I slot print_timing: id 1 | task 25671 | graphs reused = 23835 22.18.291.285 I slot print_timing: id 1 | task 25671 | graph reallocs = 0 / 0 (same size) / (changed size) 22.18.291.334 I slot release: id 1 | task 25671 | stop processing: n_tokens = 944, truncated = 0 22.18.291.608 I slot print_timing: id 3 | task 25672 | prompt eval time = 4162.84 ms / 964 tokens ( 4.32 ms per token, 231.57 tokens per second) 22.18.291.610 I slot print_timing: id 3 | task 25672 | eval time = 61.27 ms / 2 tokens ( 61.27 ms per token, 16.32 tokens per second) 22.18.291.611 I slot print_timing: id 3 | task 25672 | total time = 4224.11 ms / 966 tokens 22.18.291.612 I slot print_timing: id 3 | task 25672 | graphs reused = 23835 22.18.291.612 I slot print_timing: id 3 | task 25672 | graph reallocs = 0 / 0 (same size) / (changed size) 22.18.291.658 I slot release: id 3 | task 25672 | stop processing: n_tokens = 965, truncated = 0 22.18.291.664 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 22.18.291.690 I slot launch_slot_: id 1 | task 25678 | processing task, is_child = 0 22.18.395.680 I slot print_timing: id 0 | task 25675 | prompt eval time = 789.64 ms / 500 tokens ( 1.58 ms per token, 633.20 tokens per second) 22.18.395.683 I slot print_timing: id 0 | task 25675 | eval time = 104.70 ms / 2 tokens ( 104.70 ms per token, 9.55 tokens per second) 22.18.395.683 I slot print_timing: id 0 | task 25675 | total time = 894.34 ms / 502 tokens 22.18.395.684 I slot print_timing: id 0 | task 25675 | graphs reused = 23835 22.18.395.684 I slot print_timing: id 0 | task 25675 | graph reallocs = 0 / 0 (same size) / (changed size) 22.18.395.737 I slot release: id 0 | task 25675 | stop processing: n_tokens = 954, truncated = 0 22.18.395.743 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 959, t_last = 346186581217 22.18.395.828 I slot launch_slot_: id 2 | task 25680 | processing task, is_child = 0 22.18.398.813 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 965, t_last = 346186642864 22.18.398.894 I slot launch_slot_: id 3 | task 25681 | processing task, is_child = 0 22.20.500.409 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 346186746943 22.20.500.550 I slot launch_slot_: id 0 | task 25683 | processing task, is_child = 0 22.23.877.298 I slot print_timing: id 0 | task 25683 | prompt processing, n_tokens = 1062, progress = 0.67, t = 3.38 s / 314.54 tokens per second 22.23.877.357 I slot print_timing: id 2 | task 25680 | prompt processing, n_tokens = 785, progress = 0.99, t = 5.48 s / 143.30 tokens per second 22.23.877.509 I slot print_timing: id 3 | task 25681 | prompt processing, n_tokens = 1577, progress = 0.97, t = 5.48 s / 287.89 tokens per second 22.24.774.431 I slot print_timing: id 1 | task 25678 | prompt eval time = 5580.14 ms / 530 tokens ( 10.53 ms per token, 94.98 tokens per second) 22.24.774.434 I slot print_timing: id 1 | task 25678 | eval time = 897.14 ms / 2 tokens ( 897.14 ms per token, 1.11 tokens per second) 22.24.774.435 I slot print_timing: id 1 | task 25678 | total time = 6477.29 ms / 532 tokens 22.24.774.435 I slot print_timing: id 1 | task 25678 | graphs reused = 23835 22.24.774.436 I slot print_timing: id 1 | task 25678 | graph reallocs = 0 / 0 (same size) / (changed size) 22.24.774.504 I slot release: id 1 | task 25678 | stop processing: n_tokens = 958, truncated = 0 22.24.774.830 I slot print_timing: id 0 | task 25683 | prompt processing, n_tokens = 1574, progress = 1.00, t = 4.27 s / 368.31 tokens per second 22.24.775.109 I slot print_timing: id 3 | task 25681 | prompt processing, n_tokens = 1619, progress = 1.00, t = 6.38 s / 253.96 tokens per second 22.24.858.406 I slot print_timing: id 2 | task 25680 | prompt eval time = 6375.82 ms / 789 tokens ( 8.08 ms per token, 123.75 tokens per second) 22.24.858.409 I slot print_timing: id 2 | task 25680 | eval time = 83.58 ms / 2 tokens ( 83.58 ms per token, 11.96 tokens per second) 22.24.858.409 I slot print_timing: id 2 | task 25680 | total time = 6459.41 ms / 791 tokens 22.24.858.410 I slot print_timing: id 2 | task 25680 | graphs reused = 23835 22.24.858.410 I slot print_timing: id 2 | task 25680 | graph reallocs = 0 / 0 (same size) / (changed size) 22.24.858.458 I slot release: id 2 | task 25680 | stop processing: n_tokens = 790, truncated = 0 22.24.858.904 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 958, t_last = 346193125710 22.24.861.927 I slot launch_slot_: id 1 | task 25687 | processing task, is_child = 0 22.24.863.905 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 346193209664 22.24.863.985 I slot launch_slot_: id 2 | task 25688 | processing task, is_child = 0 22.27.544.114 I slot print_timing: id 0 | task 25683 | prompt eval time = 4357.55 ms / 1578 tokens ( 2.76 ms per token, 362.13 tokens per second) 22.27.544.116 I slot print_timing: id 0 | task 25683 | eval time = 2686.00 ms / 2 tokens ( 2686.00 ms per token, 0.37 tokens per second) 22.27.544.117 I slot print_timing: id 0 | task 25683 | total time = 7043.55 ms / 1580 tokens 22.27.544.117 I slot print_timing: id 0 | task 25683 | graphs reused = 23835 22.27.544.118 I slot print_timing: id 0 | task 25683 | graph reallocs = 0 / 0 (same size) / (changed size) 22.27.544.215 I slot release: id 0 | task 25683 | stop processing: n_tokens = 1579, truncated = 0 22.27.544.582 I slot print_timing: id 3 | task 25681 | prompt eval time = 6459.84 ms / 1623 tokens ( 3.98 ms per token, 251.24 tokens per second) 22.27.544.585 I slot print_timing: id 3 | task 25681 | eval time = 2685.68 ms / 2 tokens ( 2685.68 ms per token, 0.37 tokens per second) 22.27.544.586 I slot print_timing: id 3 | task 25681 | total time = 9145.51 ms / 1625 tokens 22.27.544.586 I slot print_timing: id 3 | task 25681 | graphs reused = 23835 22.27.544.586 I slot print_timing: id 3 | task 25681 | graph reallocs = 0 / 0 (same size) / (changed size) 22.27.544.660 I slot release: id 3 | task 25681 | stop processing: n_tokens = 1624, truncated = 0 22.28.021.871 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1579, t_last = 346195895422 22.28.502.686 I slot launch_slot_: id 0 | task 25691 | processing task, is_child = 0 22.28.508.417 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.812 (> 0.100 thold), f_keep = 0.861 22.28.508.451 I slot launch_slot_: id 3 | task 25692 | processing task, is_child = 0 22.28.508.580 I slot print_timing: id 1 | task 25687 | prompt processing, n_tokens = 1606, progress = 1.00, t = 3.16 s / 508.57 tokens per second 22.28.508.843 I slot print_timing: id 2 | task 25688 | prompt processing, n_tokens = 1117, progress = 0.68, t = 3.16 s / 353.73 tokens per second 22.29.896.829 I slot print_timing: id 2 | task 25688 | prompt processing, n_tokens = 1629, progress = 1.00, t = 5.03 s / 323.71 tokens per second 22.31.251.573 I slot print_timing: id 1 | task 25687 | prompt eval time = 5032.78 ms / 1610 tokens ( 3.13 ms per token, 319.90 tokens per second) 22.31.251.579 I slot print_timing: id 1 | task 25687 | eval time = 1354.80 ms / 2 tokens ( 1354.80 ms per token, 0.74 tokens per second) 22.31.251.580 I slot print_timing: id 1 | task 25687 | total time = 6387.58 ms / 1612 tokens 22.31.251.580 I slot print_timing: id 1 | task 25687 | graphs reused = 23835 22.31.251.581 I slot print_timing: id 1 | task 25687 | graph reallocs = 0 / 0 (same size) / (changed size) 22.31.251.684 I slot release: id 1 | task 25687 | stop processing: n_tokens = 1611, truncated = 0 22.31.335.881 I slot print_timing: id 2 | task 25688 | prompt eval time = 6388.08 ms / 1633 tokens ( 3.91 ms per token, 255.63 tokens per second) 22.31.335.884 I slot print_timing: id 2 | task 25688 | eval time = 83.72 ms / 2 tokens ( 83.72 ms per token, 11.94 tokens per second) 22.31.335.884 I slot print_timing: id 2 | task 25688 | total time = 6471.80 ms / 1635 tokens 22.31.335.885 I slot print_timing: id 2 | task 25688 | graphs reused = 23835 22.31.335.885 I slot print_timing: id 2 | task 25688 | graph reallocs = 0 / 0 (same size) / (changed size) 22.31.335.991 I slot release: id 2 | task 25688 | stop processing: n_tokens = 1634, truncated = 0 22.31.336.445 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1611, t_last = 346199602891 22.31.341.992 I slot launch_slot_: id 1 | task 25696 | processing task, is_child = 0 22.31.346.973 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1634, t_last = 346199687197 22.31.347.081 I slot launch_slot_: id 2 | task 25697 | processing task, is_child = 0 22.32.417.868 I slot print_timing: id 0 | task 25691 | prompt eval time = 2827.06 ms / 826 tokens ( 3.42 ms per token, 292.18 tokens per second) 22.32.417.871 I slot print_timing: id 0 | task 25691 | eval time = 1082.35 ms / 2 tokens ( 1082.35 ms per token, 0.92 tokens per second) 22.32.417.872 I slot print_timing: id 0 | task 25691 | total time = 3909.41 ms / 828 tokens 22.32.417.872 I slot print_timing: id 0 | task 25691 | graphs reused = 23835 22.32.417.872 I slot print_timing: id 0 | task 25691 | graph reallocs = 0 / 0 (same size) / (changed size) 22.32.417.931 I slot release: id 0 | task 25691 | stop processing: n_tokens = 827, truncated = 0 22.32.418.382 I slot print_timing: id 3 | task 25692 | prompt eval time = 2827.56 ms / 616 tokens ( 4.59 ms per token, 217.86 tokens per second) 22.32.418.388 I slot print_timing: id 3 | task 25692 | eval time = 1081.94 ms / 2 tokens ( 1081.94 ms per token, 0.92 tokens per second) 22.32.418.389 I slot print_timing: id 3 | task 25692 | total time = 3909.50 ms / 618 tokens 22.32.418.389 I slot print_timing: id 3 | task 25692 | graphs reused = 23835 22.32.418.390 I slot print_timing: id 3 | task 25692 | graph reallocs = 0 / 0 (same size) / (changed size) 22.32.418.491 I slot release: id 3 | task 25692 | stop processing: n_tokens = 1724, truncated = 0 22.33.055.169 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 827, t_last = 346200769138 22.33.691.387 I slot launch_slot_: id 0 | task 25700 | processing task, is_child = 0 22.33.698.129 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1724, t_last = 346200769697 22.33.698.243 I slot launch_slot_: id 3 | task 25701 | processing task, is_child = 0 22.36.018.684 I slot print_timing: id 1 | task 25696 | prompt eval time = 3374.88 ms / 854 tokens ( 3.95 ms per token, 253.05 tokens per second) 22.36.018.687 I slot print_timing: id 1 | task 25696 | eval time = 1296.71 ms / 2 tokens ( 1296.71 ms per token, 0.77 tokens per second) 22.36.018.687 I slot print_timing: id 1 | task 25696 | total time = 4671.59 ms / 856 tokens 22.36.018.688 I slot print_timing: id 1 | task 25696 | graphs reused = 23835 22.36.018.688 I slot print_timing: id 1 | task 25696 | graph reallocs = 0 / 0 (same size) / (changed size) 22.36.018.746 I slot release: id 1 | task 25696 | stop processing: n_tokens = 855, truncated = 0 22.36.019.089 I slot print_timing: id 2 | task 25697 | prompt eval time = 3375.07 ms / 828 tokens ( 4.08 ms per token, 245.33 tokens per second) 22.36.019.092 I slot print_timing: id 2 | task 25697 | eval time = 1296.83 ms / 2 tokens ( 1296.83 ms per token, 0.77 tokens per second) 22.36.019.093 I slot print_timing: id 2 | task 25697 | total time = 4671.89 ms / 830 tokens 22.36.019.093 I slot print_timing: id 2 | task 25697 | graphs reused = 23835 22.36.019.093 I slot print_timing: id 2 | task 25697 | graph reallocs = 0 / 0 (same size) / (changed size) 22.36.019.143 I slot release: id 2 | task 25697 | stop processing: n_tokens = 829, truncated = 0 22.36.086.313 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 346204369953 22.36.089.055 I slot launch_slot_: id 1 | task 25705 | processing task, is_child = 0 22.36.091.189 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 829, t_last = 346204370350 22.36.091.262 I slot launch_slot_: id 2 | task 25706 | processing task, is_child = 0 22.36.841.446 I slot print_timing: id 0 | task 25700 | prompt eval time = 2387.67 ms / 847 tokens ( 2.82 ms per token, 354.74 tokens per second) 22.36.841.448 I slot print_timing: id 0 | task 25700 | eval time = 755.52 ms / 2 tokens ( 755.52 ms per token, 1.32 tokens per second) 22.36.841.448 I slot print_timing: id 0 | task 25700 | total time = 3143.19 ms / 849 tokens 22.36.841.449 I slot print_timing: id 0 | task 25700 | graphs reused = 23835 22.36.841.449 I slot print_timing: id 0 | task 25700 | graph reallocs = 0 / 0 (same size) / (changed size) 22.36.841.506 I slot release: id 0 | task 25700 | stop processing: n_tokens = 848, truncated = 0 22.36.841.921 I slot print_timing: id 3 | task 25701 | prompt eval time = 2387.71 ms / 867 tokens ( 2.75 ms per token, 363.11 tokens per second) 22.36.841.925 I slot print_timing: id 3 | task 25701 | eval time = 755.61 ms / 2 tokens ( 755.61 ms per token, 1.32 tokens per second) 22.36.841.925 I slot print_timing: id 3 | task 25701 | total time = 3143.32 ms / 869 tokens 22.36.841.925 I slot print_timing: id 3 | task 25701 | graphs reused = 23835 22.36.841.926 I slot print_timing: id 3 | task 25701 | graph reallocs = 0 / 0 (same size) / (changed size) 22.36.841.963 I slot release: id 3 | task 25701 | stop processing: n_tokens = 868, truncated = 0 22.37.472.299 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 848, t_last = 346205192712 22.38.105.313 I slot launch_slot_: id 0 | task 25709 | processing task, is_child = 0 22.38.108.870 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 868, t_last = 346205193170 22.38.108.956 I slot launch_slot_: id 3 | task 25710 | processing task, is_child = 0 22.40.123.558 I slot print_timing: id 1 | task 25705 | prompt eval time = 2740.70 ms / 759 tokens ( 3.61 ms per token, 276.94 tokens per second) 22.40.123.560 I slot print_timing: id 1 | task 25705 | eval time = 1291.59 ms / 2 tokens ( 1291.59 ms per token, 0.77 tokens per second) 22.40.123.561 I slot print_timing: id 1 | task 25705 | total time = 4032.29 ms / 761 tokens 22.40.123.561 I slot print_timing: id 1 | task 25705 | graphs reused = 23835 22.40.123.562 I slot print_timing: id 1 | task 25705 | graph reallocs = 0 / 0 (same size) / (changed size) 22.40.123.607 I slot release: id 1 | task 25705 | stop processing: n_tokens = 760, truncated = 0 22.40.123.944 I slot print_timing: id 2 | task 25706 | prompt eval time = 2740.96 ms / 728 tokens ( 3.77 ms per token, 265.60 tokens per second) 22.40.123.948 I slot print_timing: id 2 | task 25706 | eval time = 1291.65 ms / 2 tokens ( 1291.65 ms per token, 0.77 tokens per second) 22.40.123.948 I slot print_timing: id 2 | task 25706 | total time = 4032.61 ms / 730 tokens 22.40.123.948 I slot print_timing: id 2 | task 25706 | graphs reused = 23835 22.40.123.949 I slot print_timing: id 2 | task 25706 | graph reallocs = 0 / 0 (same size) / (changed size) 22.40.123.979 I slot release: id 2 | task 25706 | stop processing: n_tokens = 729, truncated = 0 22.40.191.134 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 760, t_last = 346208474813 22.40.193.453 I slot launch_slot_: id 1 | task 25714 | processing task, is_child = 0 22.40.517.117 I slot print_timing: id 0 | task 25709 | prompt eval time = 2081.81 ms / 682 tokens ( 3.05 ms per token, 327.60 tokens per second) 22.40.517.119 I slot print_timing: id 0 | task 25709 | eval time = 326.34 ms / 2 tokens ( 326.34 ms per token, 3.06 tokens per second) 22.40.517.121 I slot print_timing: id 0 | task 25709 | total time = 2408.15 ms / 684 tokens 22.40.517.121 I slot print_timing: id 0 | task 25709 | graphs reused = 23835 22.40.517.121 I slot print_timing: id 0 | task 25709 | graph reallocs = 0 / 0 (same size) / (changed size) 22.40.517.164 I slot release: id 0 | task 25709 | stop processing: n_tokens = 683, truncated = 0 22.40.517.553 I slot print_timing: id 3 | task 25710 | prompt eval time = 2081.85 ms / 700 tokens ( 2.97 ms per token, 336.24 tokens per second) 22.40.517.555 I slot print_timing: id 3 | task 25710 | eval time = 326.42 ms / 2 tokens ( 326.42 ms per token, 3.06 tokens per second) 22.40.517.555 I slot print_timing: id 3 | task 25710 | total time = 2408.27 ms / 702 tokens 22.40.517.556 I slot print_timing: id 3 | task 25710 | graphs reused = 23835 22.40.517.556 I slot print_timing: id 3 | task 25710 | graph reallocs = 0 / 0 (same size) / (changed size) 22.40.517.587 I slot release: id 3 | task 25710 | stop processing: n_tokens = 701, truncated = 0 22.41.200.215 I slot print_timing: id 1 | task 25714 | prompt eval time = 989.85 ms / 665 tokens ( 1.49 ms per token, 671.82 tokens per second) 22.41.200.217 I slot print_timing: id 1 | task 25714 | eval time = 15.02 ms / 2 tokens ( 15.02 ms per token, 66.56 tokens per second) 22.41.200.217 I slot print_timing: id 1 | task 25714 | total time = 1004.88 ms / 667 tokens 22.41.200.218 I slot print_timing: id 1 | task 25714 | graphs reused = 23835 22.41.200.218 I slot print_timing: id 1 | task 25714 | graph reallocs = 0 / 0 (same size) / (changed size) 22.41.200.252 I slot release: id 1 | task 25714 | stop processing: n_tokens = 666, truncated = 0 22.44.143.462 I srv operator(): operator(): cleaning up before exit...