/Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/d1c03f73ecaf/LFM2.5-24B-A2B-QAD-Q4_0.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 0.00.044.729 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.044.785 I srv llama_server: initializing ... 0.00.044.790 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.044.858 I srv init_listene: The UI is disabled 0.00.044.859 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.044.892 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) 0.00.046.088 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/d1c03f73ecaf/LFM2.5-24B-A2B-QAD-Q4_0.gguf' 0.00.990.027 I cmn init: llama threadpool init, n_threads = 8 0.01.049.671 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.01.052.508 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.052.523 I srv llama_server: model loaded 0.01.052.526 I srv llama_server: listening on http://127.0.0.1:8091 0.30.051.080 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.30.051.104 I slot launch_slot_: id 0 | task 1 | processing task, is_child = 0 0.30.051.109 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.30.051.121 I slot launch_slot_: id 1 | task 2 | processing task, is_child = 0 0.30.051.121 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.30.051.130 I slot launch_slot_: id 2 | task 0 | processing task, is_child = 0 0.30.051.131 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.30.051.139 I slot launch_slot_: id 3 | task 3 | processing task, is_child = 0 0.31.119.229 I slot print_timing: id 0 | task 1 | prompt eval time = 1021.45 ms / 123 tokens ( 8.30 ms per token, 120.42 tokens per second) 0.31.119.232 I slot print_timing: id 0 | task 1 | eval time = 46.63 ms / 2 tokens ( 46.63 ms per token, 21.45 tokens per second) 0.31.119.233 I slot print_timing: id 0 | task 1 | total time = 1068.08 ms / 125 tokens 0.31.119.233 I slot print_timing: id 0 | task 1 | graphs reused = 1 0.31.119.234 I slot print_timing: id 0 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.119.304 I slot release: id 0 | task 1 | stop processing: n_tokens = 124, truncated = 0 0.31.119.678 I slot print_timing: id 1 | task 2 | prompt eval time = 1021.93 ms / 112 tokens ( 9.12 ms per token, 109.60 tokens per second) 0.31.119.680 I slot print_timing: id 1 | task 2 | eval time = 46.60 ms / 2 tokens ( 46.60 ms per token, 21.46 tokens per second) 0.31.119.680 I slot print_timing: id 1 | task 2 | total time = 1068.52 ms / 114 tokens 0.31.119.680 I slot print_timing: id 1 | task 2 | graphs reused = 1 0.31.119.681 I slot print_timing: id 1 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.119.702 I slot release: id 1 | task 2 | stop processing: n_tokens = 113, truncated = 0 0.31.120.002 I slot print_timing: id 2 | task 0 | prompt eval time = 1022.36 ms / 131 tokens ( 7.80 ms per token, 128.14 tokens per second) 0.31.120.004 I slot print_timing: id 2 | task 0 | eval time = 46.48 ms / 2 tokens ( 46.48 ms per token, 21.51 tokens per second) 0.31.120.005 I slot print_timing: id 2 | task 0 | total time = 1068.84 ms / 133 tokens 0.31.120.005 I slot print_timing: id 2 | task 0 | graphs reused = 1 0.31.120.005 I slot print_timing: id 2 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.120.035 I slot release: id 2 | task 0 | stop processing: n_tokens = 132, truncated = 0 0.31.120.310 I slot print_timing: id 3 | task 3 | prompt eval time = 1022.78 ms / 117 tokens ( 8.74 ms per token, 114.39 tokens per second) 0.31.120.312 I slot print_timing: id 3 | task 3 | eval time = 46.37 ms / 2 tokens ( 46.37 ms per token, 21.57 tokens per second) 0.31.120.313 I slot print_timing: id 3 | task 3 | total time = 1069.15 ms / 119 tokens 0.31.120.313 I slot print_timing: id 3 | task 3 | graphs reused = 1 0.31.120.313 I slot print_timing: id 3 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.120.337 I slot release: id 3 | task 3 | stop processing: n_tokens = 118, truncated = 0 0.31.125.119 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 0.31.125.394 I slot launch_slot_: id 0 | task 7 | processing task, is_child = 0 0.31.126.351 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.227 0.31.126.382 I slot launch_slot_: id 2 | task 8 | processing task, is_child = 0 0.31.126.415 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.257 0.31.126.442 I slot launch_slot_: id 1 | task 9 | processing task, is_child = 0 0.31.126.459 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.246 0.31.126.486 I slot launch_slot_: id 3 | task 10 | processing task, is_child = 0 0.32.148.574 I slot print_timing: id 0 | task 7 | prompt eval time = 994.14 ms / 110 tokens ( 9.04 ms per token, 110.65 tokens per second) 0.32.148.578 I slot print_timing: id 0 | task 7 | eval time = 27.93 ms / 2 tokens ( 27.93 ms per token, 35.80 tokens per second) 0.32.148.579 I slot print_timing: id 0 | task 7 | total time = 1022.08 ms / 112 tokens 0.32.148.579 I slot print_timing: id 0 | task 7 | graphs reused = 1 0.32.148.579 I slot print_timing: id 0 | task 7 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.148.599 I slot release: id 0 | task 7 | stop processing: n_tokens = 111, truncated = 0 0.32.148.892 I slot print_timing: id 1 | task 9 | prompt eval time = 994.42 ms / 199 tokens ( 5.00 ms per token, 200.12 tokens per second) 0.32.148.895 I slot print_timing: id 1 | task 9 | eval time = 27.97 ms / 2 tokens ( 27.97 ms per token, 35.76 tokens per second) 0.32.148.895 I slot print_timing: id 1 | task 9 | total time = 1022.38 ms / 201 tokens 0.32.148.896 I slot print_timing: id 1 | task 9 | graphs reused = 1 0.32.148.896 I slot print_timing: id 1 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.148.932 I slot release: id 1 | task 9 | stop processing: n_tokens = 200, truncated = 0 0.32.149.229 I slot print_timing: id 2 | task 8 | prompt eval time = 994.71 ms / 161 tokens ( 6.18 ms per token, 161.86 tokens per second) 0.32.149.231 I slot print_timing: id 2 | task 8 | eval time = 28.00 ms / 2 tokens ( 28.00 ms per token, 35.71 tokens per second) 0.32.149.232 I slot print_timing: id 2 | task 8 | total time = 1022.71 ms / 163 tokens 0.32.149.232 I slot print_timing: id 2 | task 8 | graphs reused = 1 0.32.149.232 I slot print_timing: id 2 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.149.253 I slot release: id 2 | task 8 | stop processing: n_tokens = 162, truncated = 0 0.32.149.551 I slot print_timing: id 3 | task 10 | prompt eval time = 995.02 ms / 161 tokens ( 6.18 ms per token, 161.81 tokens per second) 0.32.149.554 I slot print_timing: id 3 | task 10 | eval time = 28.00 ms / 2 tokens ( 28.00 ms per token, 35.71 tokens per second) 0.32.149.554 I slot print_timing: id 3 | task 10 | total time = 1023.02 ms / 163 tokens 0.32.149.554 I slot print_timing: id 3 | task 10 | graphs reused = 1 0.32.149.554 I slot print_timing: id 3 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.149.600 I slot release: id 3 | task 10 | stop processing: n_tokens = 162, truncated = 0 0.32.154.070 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.261 0.32.154.509 I slot launch_slot_: id 0 | task 14 | processing task, is_child = 0 0.32.155.608 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.145 0.32.155.645 I slot launch_slot_: id 1 | task 15 | processing task, is_child = 0 0.32.155.679 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.185 0.32.155.706 I slot launch_slot_: id 2 | task 16 | processing task, is_child = 0 0.32.155.724 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.179 0.32.155.751 I slot launch_slot_: id 3 | task 17 | processing task, is_child = 0 0.33.019.513 I slot print_timing: id 0 | task 14 | prompt eval time = 836.13 ms / 116 tokens ( 7.21 ms per token, 138.73 tokens per second) 0.33.019.515 I slot print_timing: id 0 | task 14 | eval time = 27.63 ms / 2 tokens ( 27.63 ms per token, 36.20 tokens per second) 0.33.019.516 I slot print_timing: id 0 | task 14 | total time = 863.75 ms / 118 tokens 0.33.019.516 I slot print_timing: id 0 | task 14 | graphs reused = 1 0.33.019.517 I slot print_timing: id 0 | task 14 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.019.549 I slot release: id 0 | task 14 | stop processing: n_tokens = 117, truncated = 0 0.33.019.826 I slot print_timing: id 1 | task 15 | prompt eval time = 836.40 ms / 127 tokens ( 6.59 ms per token, 151.84 tokens per second) 0.33.019.830 I slot print_timing: id 1 | task 15 | eval time = 27.65 ms / 2 tokens ( 27.65 ms per token, 36.16 tokens per second) 0.33.019.831 I slot print_timing: id 1 | task 15 | total time = 864.06 ms / 129 tokens 0.33.019.831 I slot print_timing: id 1 | task 15 | graphs reused = 1 0.33.019.831 I slot print_timing: id 1 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.019.856 I slot release: id 1 | task 15 | stop processing: n_tokens = 128, truncated = 0 0.33.020.150 I slot print_timing: id 2 | task 16 | prompt eval time = 836.68 ms / 119 tokens ( 7.03 ms per token, 142.23 tokens per second) 0.33.020.152 I slot print_timing: id 2 | task 16 | eval time = 27.68 ms / 2 tokens ( 27.68 ms per token, 36.13 tokens per second) 0.33.020.152 I slot print_timing: id 2 | task 16 | total time = 864.36 ms / 121 tokens 0.33.020.152 I slot print_timing: id 2 | task 16 | graphs reused = 1 0.33.020.153 I slot print_timing: id 2 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.020.175 I slot release: id 2 | task 16 | stop processing: n_tokens = 120, truncated = 0 0.33.020.490 I slot print_timing: id 3 | task 17 | prompt eval time = 836.99 ms / 151 tokens ( 5.54 ms per token, 180.41 tokens per second) 0.33.020.492 I slot print_timing: id 3 | task 17 | eval time = 27.70 ms / 2 tokens ( 27.70 ms per token, 36.10 tokens per second) 0.33.020.493 I slot print_timing: id 3 | task 17 | total time = 864.69 ms / 153 tokens 0.33.020.493 I slot print_timing: id 3 | task 17 | graphs reused = 1 0.33.020.493 I slot print_timing: id 3 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.020.520 I slot release: id 3 | task 17 | stop processing: n_tokens = 152, truncated = 0 0.33.025.031 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.248 0.33.025.381 I slot launch_slot_: id 0 | task 21 | processing task, is_child = 0 0.33.026.346 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.227 0.33.026.376 I slot launch_slot_: id 1 | task 22 | processing task, is_child = 0 0.33.026.408 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.242 0.33.026.435 I slot launch_slot_: id 2 | task 23 | processing task, is_child = 0 0.33.026.452 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.191 0.33.026.480 I slot launch_slot_: id 3 | task 24 | processing task, is_child = 0 0.34.024.426 I slot print_timing: id 0 | task 21 | prompt eval time = 969.79 ms / 143 tokens ( 6.78 ms per token, 147.45 tokens per second) 0.34.024.429 I slot print_timing: id 0 | task 21 | eval time = 28.15 ms / 2 tokens ( 28.15 ms per token, 35.53 tokens per second) 0.34.024.429 I slot print_timing: id 0 | task 21 | total time = 997.94 ms / 145 tokens 0.34.024.430 I slot print_timing: id 0 | task 21 | graphs reused = 1 0.34.024.430 I slot print_timing: id 0 | task 21 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.024.466 I slot release: id 0 | task 21 | stop processing: n_tokens = 144, truncated = 0 0.34.024.737 I slot print_timing: id 1 | task 22 | prompt eval time = 970.05 ms / 135 tokens ( 7.19 ms per token, 139.17 tokens per second) 0.34.024.739 I slot print_timing: id 1 | task 22 | eval time = 28.19 ms / 2 tokens ( 28.19 ms per token, 35.47 tokens per second) 0.34.024.740 I slot print_timing: id 1 | task 22 | total time = 998.24 ms / 137 tokens 0.34.024.740 I slot print_timing: id 1 | task 22 | graphs reused = 1 0.34.024.740 I slot print_timing: id 1 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.024.757 I slot release: id 1 | task 22 | stop processing: n_tokens = 136, truncated = 0 0.34.025.027 I slot print_timing: id 2 | task 23 | prompt eval time = 970.34 ms / 184 tokens ( 5.27 ms per token, 189.62 tokens per second) 0.34.025.028 I slot print_timing: id 2 | task 23 | eval time = 28.18 ms / 2 tokens ( 28.18 ms per token, 35.49 tokens per second) 0.34.025.029 I slot print_timing: id 2 | task 23 | total time = 998.52 ms / 186 tokens 0.34.025.029 I slot print_timing: id 2 | task 23 | graphs reused = 1 0.34.025.029 I slot print_timing: id 2 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.025.046 I slot release: id 2 | task 23 | stop processing: n_tokens = 185, truncated = 0 0.34.025.364 I slot print_timing: id 3 | task 24 | prompt eval time = 970.71 ms / 120 tokens ( 8.09 ms per token, 123.62 tokens per second) 0.34.025.371 I slot print_timing: id 3 | task 24 | eval time = 28.13 ms / 2 tokens ( 28.13 ms per token, 35.55 tokens per second) 0.34.025.371 I slot print_timing: id 3 | task 24 | total time = 998.84 ms / 122 tokens 0.34.025.372 I slot print_timing: id 3 | task 24 | graphs reused = 1 0.34.025.372 I slot print_timing: id 3 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.025.391 I slot release: id 3 | task 24 | stop processing: n_tokens = 121, truncated = 0 0.34.029.601 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.201 0.34.030.062 I slot launch_slot_: id 0 | task 28 | processing task, is_child = 0 0.34.031.198 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.213 0.34.031.229 I slot launch_slot_: id 1 | task 29 | processing task, is_child = 0 0.34.031.263 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.157 0.34.031.411 I slot launch_slot_: id 2 | task 30 | processing task, is_child = 0 0.34.031.429 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.240 0.34.031.560 I slot launch_slot_: id 3 | task 31 | processing task, is_child = 0 0.34.993.038 I slot print_timing: id 0 | task 28 | prompt eval time = 933.87 ms / 141 tokens ( 6.62 ms per token, 150.98 tokens per second) 0.34.993.040 I slot print_timing: id 0 | task 28 | eval time = 27.60 ms / 2 tokens ( 27.60 ms per token, 36.23 tokens per second) 0.34.993.041 I slot print_timing: id 0 | task 28 | total time = 961.47 ms / 143 tokens 0.34.993.041 I slot print_timing: id 0 | task 28 | graphs reused = 1 0.34.993.042 I slot print_timing: id 0 | task 28 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.993.078 I slot release: id 0 | task 28 | stop processing: n_tokens = 142, truncated = 0 0.34.993.371 I slot print_timing: id 1 | task 29 | prompt eval time = 934.15 ms / 179 tokens ( 5.22 ms per token, 191.62 tokens per second) 0.34.993.374 I slot print_timing: id 1 | task 29 | eval time = 27.65 ms / 2 tokens ( 27.65 ms per token, 36.17 tokens per second) 0.34.993.375 I slot print_timing: id 1 | task 29 | total time = 961.79 ms / 181 tokens 0.34.993.375 I slot print_timing: id 1 | task 29 | graphs reused = 1 0.34.993.375 I slot print_timing: id 1 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.993.400 I slot release: id 1 | task 29 | stop processing: n_tokens = 180, truncated = 0 0.34.993.688 I slot print_timing: id 2 | task 30 | prompt eval time = 934.43 ms / 131 tokens ( 7.13 ms per token, 140.19 tokens per second) 0.34.993.690 I slot print_timing: id 2 | task 30 | eval time = 27.67 ms / 2 tokens ( 27.67 ms per token, 36.14 tokens per second) 0.34.993.690 I slot print_timing: id 2 | task 30 | total time = 962.10 ms / 133 tokens 0.34.993.690 I slot print_timing: id 2 | task 30 | graphs reused = 1 0.34.993.691 I slot print_timing: id 2 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.993.722 I slot release: id 2 | task 30 | stop processing: n_tokens = 132, truncated = 0 0.34.994.035 I slot print_timing: id 3 | task 31 | prompt eval time = 934.71 ms / 125 tokens ( 7.48 ms per token, 133.73 tokens per second) 0.34.994.039 I slot print_timing: id 3 | task 31 | eval time = 27.73 ms / 2 tokens ( 27.73 ms per token, 36.07 tokens per second) 0.34.994.039 I slot print_timing: id 3 | task 31 | total time = 962.44 ms / 127 tokens 0.34.994.039 I slot print_timing: id 3 | task 31 | graphs reused = 1 0.34.994.040 I slot print_timing: id 3 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.994.073 I slot release: id 3 | task 31 | stop processing: n_tokens = 126, truncated = 0 0.34.998.492 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.204 0.34.998.959 I slot launch_slot_: id 0 | task 35 | processing task, is_child = 0 0.35.000.108 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.161 0.35.000.140 I slot launch_slot_: id 1 | task 37 | processing task, is_child = 0 0.35.000.173 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.227 0.35.000.200 I slot launch_slot_: id 2 | task 36 | processing task, is_child = 0 0.35.000.219 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.230 0.35.000.246 I slot launch_slot_: id 3 | task 38 | processing task, is_child = 0 0.35.878.717 I slot print_timing: id 0 | task 35 | prompt eval time = 850.55 ms / 113 tokens ( 7.53 ms per token, 132.86 tokens per second) 0.35.878.719 I slot print_timing: id 0 | task 35 | eval time = 27.91 ms / 2 tokens ( 27.91 ms per token, 35.82 tokens per second) 0.35.878.719 I slot print_timing: id 0 | task 35 | total time = 878.46 ms / 115 tokens 0.35.878.720 I slot print_timing: id 0 | task 35 | graphs reused = 1 0.35.878.720 I slot print_timing: id 0 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.878.745 I slot release: id 0 | task 35 | stop processing: n_tokens = 114, truncated = 0 0.35.879.021 I slot print_timing: id 1 | task 37 | prompt eval time = 850.81 ms / 143 tokens ( 5.95 ms per token, 168.08 tokens per second) 0.35.879.025 I slot print_timing: id 1 | task 37 | eval time = 27.95 ms / 2 tokens ( 27.95 ms per token, 35.78 tokens per second) 0.35.879.026 I slot print_timing: id 1 | task 37 | total time = 878.76 ms / 145 tokens 0.35.879.026 I slot print_timing: id 1 | task 37 | graphs reused = 1 0.35.879.026 I slot print_timing: id 1 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.879.047 I slot release: id 1 | task 37 | stop processing: n_tokens = 144, truncated = 0 0.35.879.339 I slot print_timing: id 2 | task 36 | prompt eval time = 851.08 ms / 122 tokens ( 6.98 ms per token, 143.35 tokens per second) 0.35.879.341 I slot print_timing: id 2 | task 36 | eval time = 27.98 ms / 2 tokens ( 27.98 ms per token, 35.74 tokens per second) 0.35.879.341 I slot print_timing: id 2 | task 36 | total time = 879.06 ms / 124 tokens 0.35.879.342 I slot print_timing: id 2 | task 36 | graphs reused = 1 0.35.879.342 I slot print_timing: id 2 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.879.362 I slot release: id 2 | task 36 | stop processing: n_tokens = 123, truncated = 0 0.35.879.674 I slot print_timing: id 3 | task 38 | prompt eval time = 851.37 ms / 145 tokens ( 5.87 ms per token, 170.31 tokens per second) 0.35.879.676 I slot print_timing: id 3 | task 38 | eval time = 28.01 ms / 2 tokens ( 28.01 ms per token, 35.70 tokens per second) 0.35.879.677 I slot print_timing: id 3 | task 38 | total time = 879.38 ms / 147 tokens 0.35.879.677 I slot print_timing: id 3 | task 38 | graphs reused = 1 0.35.879.677 I slot print_timing: id 3 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.879.690 I slot release: id 3 | task 38 | stop processing: n_tokens = 146, truncated = 0 0.35.883.782 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.254 0.35.883.998 I slot launch_slot_: id 0 | task 43 | processing task, is_child = 0 0.35.885.068 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.244 0.35.885.101 I slot launch_slot_: id 2 | task 42 | processing task, is_child = 0 0.35.885.134 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.201 0.35.885.170 I slot launch_slot_: id 1 | task 44 | processing task, is_child = 0 0.35.885.187 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.199 0.35.885.214 I slot launch_slot_: id 3 | task 45 | processing task, is_child = 0 0.36.683.402 I slot print_timing: id 0 | task 43 | prompt eval time = 770.12 ms / 123 tokens ( 6.26 ms per token, 159.72 tokens per second) 0.36.683.405 I slot print_timing: id 0 | task 43 | eval time = 28.05 ms / 2 tokens ( 28.05 ms per token, 35.64 tokens per second) 0.36.683.405 I slot print_timing: id 0 | task 43 | total time = 798.17 ms / 125 tokens 0.36.683.406 I slot print_timing: id 0 | task 43 | graphs reused = 1 0.36.683.406 I slot print_timing: id 0 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.683.428 I slot release: id 0 | task 43 | stop processing: n_tokens = 124, truncated = 0 0.36.683.699 I slot print_timing: id 1 | task 44 | prompt eval time = 770.37 ms / 110 tokens ( 7.00 ms per token, 142.79 tokens per second) 0.36.683.701 I slot print_timing: id 1 | task 44 | eval time = 28.09 ms / 2 tokens ( 28.09 ms per token, 35.60 tokens per second) 0.36.683.701 I slot print_timing: id 1 | task 44 | total time = 798.46 ms / 112 tokens 0.36.683.702 I slot print_timing: id 1 | task 44 | graphs reused = 1 0.36.683.702 I slot print_timing: id 1 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.683.718 I slot release: id 1 | task 44 | stop processing: n_tokens = 111, truncated = 0 0.36.683.989 I slot print_timing: id 2 | task 42 | prompt eval time = 770.64 ms / 115 tokens ( 6.70 ms per token, 149.23 tokens per second) 0.36.683.992 I slot print_timing: id 2 | task 42 | eval time = 28.10 ms / 2 tokens ( 28.10 ms per token, 35.58 tokens per second) 0.36.683.993 I slot print_timing: id 2 | task 42 | total time = 798.74 ms / 117 tokens 0.36.683.993 I slot print_timing: id 2 | task 42 | graphs reused = 1 0.36.683.993 I slot print_timing: id 2 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.684.010 I slot release: id 2 | task 42 | stop processing: n_tokens = 116, truncated = 0 0.36.684.399 I slot print_timing: id 3 | task 45 | prompt eval time = 771.15 ms / 146 tokens ( 5.28 ms per token, 189.33 tokens per second) 0.36.684.401 I slot print_timing: id 3 | task 45 | eval time = 27.97 ms / 2 tokens ( 27.97 ms per token, 35.75 tokens per second) 0.36.684.401 I slot print_timing: id 3 | task 45 | total time = 799.12 ms / 148 tokens 0.36.684.401 I slot print_timing: id 3 | task 45 | graphs reused = 1 0.36.684.402 I slot print_timing: id 3 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.684.426 I slot release: id 3 | task 45 | stop processing: n_tokens = 147, truncated = 0 0.36.687.831 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.234 0.36.688.227 I slot launch_slot_: id 0 | task 49 | processing task, is_child = 0 0.36.689.023 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.261 0.36.689.054 I slot launch_slot_: id 1 | task 50 | processing task, is_child = 0 0.36.689.087 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.284 0.36.689.114 I slot launch_slot_: id 2 | task 51 | processing task, is_child = 0 0.36.689.132 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.197 0.36.689.268 I slot launch_slot_: id 3 | task 52 | processing task, is_child = 0 0.37.597.856 I slot print_timing: id 0 | task 49 | prompt eval time = 880.67 ms / 103 tokens ( 8.55 ms per token, 116.96 tokens per second) 0.37.597.861 I slot print_timing: id 0 | task 49 | eval time = 27.91 ms / 2 tokens ( 27.91 ms per token, 35.83 tokens per second) 0.37.597.862 I slot print_timing: id 0 | task 49 | total time = 908.58 ms / 105 tokens 0.37.597.862 I slot print_timing: id 0 | task 49 | graphs reused = 1 0.37.597.863 I slot print_timing: id 0 | task 49 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.597.885 I slot release: id 0 | task 49 | stop processing: n_tokens = 104, truncated = 0 0.37.598.154 I slot print_timing: id 1 | task 50 | prompt eval time = 880.93 ms / 137 tokens ( 6.43 ms per token, 155.52 tokens per second) 0.37.598.156 I slot print_timing: id 1 | task 50 | eval time = 27.94 ms / 2 tokens ( 27.94 ms per token, 35.79 tokens per second) 0.37.598.156 I slot print_timing: id 1 | task 50 | total time = 908.87 ms / 139 tokens 0.37.598.156 I slot print_timing: id 1 | task 50 | graphs reused = 1 0.37.598.157 I slot print_timing: id 1 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.598.174 I slot release: id 1 | task 50 | stop processing: n_tokens = 138, truncated = 0 0.37.598.463 I slot print_timing: id 2 | task 51 | prompt eval time = 881.20 ms / 131 tokens ( 6.73 ms per token, 148.66 tokens per second) 0.37.598.465 I slot print_timing: id 2 | task 51 | eval time = 27.97 ms / 2 tokens ( 27.97 ms per token, 35.75 tokens per second) 0.37.598.465 I slot print_timing: id 2 | task 51 | total time = 909.17 ms / 133 tokens 0.37.598.465 I slot print_timing: id 2 | task 51 | graphs reused = 1 0.37.598.466 I slot print_timing: id 2 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.598.490 I slot release: id 2 | task 51 | stop processing: n_tokens = 132, truncated = 0 0.37.598.798 I slot print_timing: id 3 | task 52 | prompt eval time = 881.49 ms / 114 tokens ( 7.73 ms per token, 129.33 tokens per second) 0.37.598.804 I slot print_timing: id 3 | task 52 | eval time = 28.00 ms / 2 tokens ( 28.00 ms per token, 35.71 tokens per second) 0.37.598.805 I slot print_timing: id 3 | task 52 | total time = 909.50 ms / 116 tokens 0.37.598.805 I slot print_timing: id 3 | task 52 | graphs reused = 1 0.37.598.805 I slot print_timing: id 3 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.598.820 I slot release: id 3 | task 52 | stop processing: n_tokens = 115, truncated = 0 0.37.603.277 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 0.37.603.522 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.37.604.574 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.210 0.37.604.607 I slot launch_slot_: id 1 | task 57 | processing task, is_child = 0 0.37.604.640 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.220 0.37.604.668 I slot launch_slot_: id 2 | task 58 | processing task, is_child = 0 0.37.604.686 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.252 0.37.604.831 I slot launch_slot_: id 3 | task 59 | processing task, is_child = 0 0.38.621.528 I slot print_timing: id 0 | task 56 | prompt eval time = 988.69 ms / 132 tokens ( 7.49 ms per token, 133.51 tokens per second) 0.38.621.533 I slot print_timing: id 0 | task 56 | eval time = 28.00 ms / 2 tokens ( 28.00 ms per token, 35.72 tokens per second) 0.38.621.534 I slot print_timing: id 0 | task 56 | total time = 1016.69 ms / 134 tokens 0.38.621.534 I slot print_timing: id 0 | task 56 | graphs reused = 1 0.38.621.535 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.621.555 I slot release: id 0 | task 56 | stop processing: n_tokens = 133, truncated = 0 0.38.621.840 I slot print_timing: id 1 | task 57 | prompt eval time = 988.97 ms / 168 tokens ( 5.89 ms per token, 169.87 tokens per second) 0.38.621.842 I slot print_timing: id 1 | task 57 | eval time = 28.02 ms / 2 tokens ( 28.02 ms per token, 35.68 tokens per second) 0.38.621.842 I slot print_timing: id 1 | task 57 | total time = 1016.99 ms / 170 tokens 0.38.621.843 I slot print_timing: id 1 | task 57 | graphs reused = 1 0.38.621.843 I slot print_timing: id 1 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.621.864 I slot release: id 1 | task 57 | stop processing: n_tokens = 169, truncated = 0 0.38.622.168 I slot print_timing: id 2 | task 58 | prompt eval time = 989.27 ms / 178 tokens ( 5.56 ms per token, 179.93 tokens per second) 0.38.622.169 I slot print_timing: id 2 | task 58 | eval time = 28.04 ms / 2 tokens ( 28.04 ms per token, 35.66 tokens per second) 0.38.622.170 I slot print_timing: id 2 | task 58 | total time = 1017.31 ms / 180 tokens 0.38.622.170 I slot print_timing: id 2 | task 58 | graphs reused = 1 0.38.622.170 I slot print_timing: id 2 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.622.185 I slot release: id 2 | task 58 | stop processing: n_tokens = 179, truncated = 0 0.38.622.487 I slot print_timing: id 3 | task 59 | prompt eval time = 989.56 ms / 186 tokens ( 5.32 ms per token, 187.96 tokens per second) 0.38.622.489 I slot print_timing: id 3 | task 59 | eval time = 28.06 ms / 2 tokens ( 28.06 ms per token, 35.64 tokens per second) 0.38.622.489 I slot print_timing: id 3 | task 59 | total time = 1017.62 ms / 188 tokens 0.38.622.490 I slot print_timing: id 3 | task 59 | graphs reused = 1 0.38.622.490 I slot print_timing: id 3 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.622.507 I slot release: id 3 | task 59 | stop processing: n_tokens = 187, truncated = 0 0.38.626.769 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 0.38.627.307 I slot launch_slot_: id 0 | task 64 | processing task, is_child = 0 0.38.628.519 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.172 0.38.628.551 I slot launch_slot_: id 1 | task 65 | processing task, is_child = 0 0.38.628.587 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.162 0.38.628.617 I slot launch_slot_: id 2 | task 63 | processing task, is_child = 0 0.38.628.636 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.155 0.38.628.667 I slot launch_slot_: id 3 | task 66 | processing task, is_child = 0 0.39.601.286 I slot print_timing: id 0 | task 64 | prompt eval time = 944.50 ms / 141 tokens ( 6.70 ms per token, 149.29 tokens per second) 0.39.601.288 I slot print_timing: id 0 | task 64 | eval time = 28.11 ms / 2 tokens ( 28.11 ms per token, 35.57 tokens per second) 0.39.601.289 I slot print_timing: id 0 | task 64 | total time = 972.61 ms / 143 tokens 0.39.601.289 I slot print_timing: id 0 | task 64 | graphs reused = 1 0.39.601.289 I slot print_timing: id 0 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.601.312 I slot release: id 0 | task 64 | stop processing: n_tokens = 142, truncated = 0 0.39.601.583 I slot print_timing: id 1 | task 65 | prompt eval time = 944.76 ms / 168 tokens ( 5.62 ms per token, 177.82 tokens per second) 0.39.601.585 I slot print_timing: id 1 | task 65 | eval time = 28.14 ms / 2 tokens ( 28.14 ms per token, 35.54 tokens per second) 0.39.601.585 I slot print_timing: id 1 | task 65 | total time = 972.90 ms / 170 tokens 0.39.601.586 I slot print_timing: id 1 | task 65 | graphs reused = 1 0.39.601.586 I slot print_timing: id 1 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.601.603 I slot release: id 1 | task 65 | stop processing: n_tokens = 169, truncated = 0 0.39.601.907 I slot print_timing: id 2 | task 63 | prompt eval time = 945.04 ms / 124 tokens ( 7.62 ms per token, 131.21 tokens per second) 0.39.601.909 I slot print_timing: id 2 | task 63 | eval time = 28.16 ms / 2 tokens ( 28.16 ms per token, 35.51 tokens per second) 0.39.601.909 I slot print_timing: id 2 | task 63 | total time = 973.21 ms / 126 tokens 0.39.601.910 I slot print_timing: id 2 | task 63 | graphs reused = 1 0.39.601.910 I slot print_timing: id 2 | task 63 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.601.921 I slot release: id 2 | task 63 | stop processing: n_tokens = 125, truncated = 0 0.39.602.228 I slot print_timing: id 3 | task 66 | prompt eval time = 945.33 ms / 150 tokens ( 6.30 ms per token, 158.68 tokens per second) 0.39.602.233 I slot print_timing: id 3 | task 66 | eval time = 28.19 ms / 2 tokens ( 28.19 ms per token, 35.48 tokens per second) 0.39.602.233 I slot print_timing: id 3 | task 66 | total time = 973.51 ms / 152 tokens 0.39.602.234 I slot print_timing: id 3 | task 66 | graphs reused = 1 0.39.602.234 I slot print_timing: id 3 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.602.246 I slot release: id 3 | task 66 | stop processing: n_tokens = 151, truncated = 0 0.39.606.590 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.240 0.39.606.996 I slot launch_slot_: id 2 | task 70 | processing task, is_child = 0 0.39.608.161 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.204 0.39.608.197 I slot launch_slot_: id 0 | task 71 | processing task, is_child = 0 0.39.608.231 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.172 0.39.608.261 I slot launch_slot_: id 1 | task 72 | processing task, is_child = 0 0.39.608.279 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.192 0.39.608.445 I slot launch_slot_: id 3 | task 73 | processing task, is_child = 0 0.40.620.842 I slot print_timing: id 0 | task 71 | prompt eval time = 984.11 ms / 160 tokens ( 6.15 ms per token, 162.58 tokens per second) 0.40.620.844 I slot print_timing: id 0 | task 71 | eval time = 28.27 ms / 2 tokens ( 28.27 ms per token, 35.37 tokens per second) 0.40.620.845 I slot print_timing: id 0 | task 71 | total time = 1012.39 ms / 162 tokens 0.40.620.845 I slot print_timing: id 0 | task 71 | graphs reused = 1 0.40.620.846 I slot print_timing: id 0 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.620.881 I slot release: id 0 | task 71 | stop processing: n_tokens = 161, truncated = 0 0.40.621.233 I slot print_timing: id 1 | task 72 | prompt eval time = 984.44 ms / 131 tokens ( 7.51 ms per token, 133.07 tokens per second) 0.40.621.235 I slot print_timing: id 1 | task 72 | eval time = 28.32 ms / 2 tokens ( 28.32 ms per token, 35.31 tokens per second) 0.40.621.235 I slot print_timing: id 1 | task 72 | total time = 1012.77 ms / 133 tokens 0.40.621.235 I slot print_timing: id 1 | task 72 | graphs reused = 1 0.40.621.236 I slot print_timing: id 1 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.621.249 I slot release: id 1 | task 72 | stop processing: n_tokens = 132, truncated = 0 0.40.621.533 I slot print_timing: id 2 | task 70 | prompt eval time = 984.80 ms / 164 tokens ( 6.00 ms per token, 166.53 tokens per second) 0.40.621.535 I slot print_timing: id 2 | task 70 | eval time = 28.25 ms / 2 tokens ( 28.25 ms per token, 35.40 tokens per second) 0.40.621.536 I slot print_timing: id 2 | task 70 | total time = 1013.05 ms / 166 tokens 0.40.621.536 I slot print_timing: id 2 | task 70 | graphs reused = 1 0.40.621.536 I slot print_timing: id 2 | task 70 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.621.550 I slot release: id 2 | task 70 | stop processing: n_tokens = 165, truncated = 0 0.40.621.854 I slot print_timing: id 3 | task 73 | prompt eval time = 985.31 ms / 111 tokens ( 8.88 ms per token, 112.65 tokens per second) 0.40.621.858 I slot print_timing: id 3 | task 73 | eval time = 28.05 ms / 2 tokens ( 28.05 ms per token, 35.66 tokens per second) 0.40.621.858 I slot print_timing: id 3 | task 73 | total time = 1013.36 ms / 113 tokens 0.40.621.859 I slot print_timing: id 3 | task 73 | graphs reused = 1 0.40.621.859 I slot print_timing: id 3 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.621.871 I slot release: id 3 | task 73 | stop processing: n_tokens = 112, truncated = 0 0.40.626.117 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.270 (> 0.100 thold), f_keep = 0.186 0.40.626.587 I slot launch_slot_: id 0 | task 77 | processing task, is_child = 0 0.40.627.483 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.182 0.40.627.531 I slot launch_slot_: id 2 | task 78 | processing task, is_child = 0 0.40.627.563 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 0.40.627.591 I slot launch_slot_: id 1 | task 79 | processing task, is_child = 0 0.40.627.619 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.259 0.40.627.646 I slot launch_slot_: id 3 | task 80 | processing task, is_child = 0 0.41.476.731 I slot print_timing: id 0 | task 77 | prompt eval time = 821.19 ms / 111 tokens ( 7.40 ms per token, 135.17 tokens per second) 0.41.476.734 I slot print_timing: id 0 | task 77 | eval time = 27.89 ms / 2 tokens ( 27.89 ms per token, 35.86 tokens per second) 0.41.476.734 I slot print_timing: id 0 | task 77 | total time = 849.08 ms / 113 tokens 0.41.476.735 I slot print_timing: id 0 | task 77 | graphs reused = 1 0.41.476.735 I slot print_timing: id 0 | task 77 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.476.757 I slot release: id 0 | task 77 | stop processing: n_tokens = 112, truncated = 0 0.41.477.048 I slot print_timing: id 1 | task 79 | prompt eval time = 821.45 ms / 166 tokens ( 4.95 ms per token, 202.08 tokens per second) 0.41.477.050 I slot print_timing: id 1 | task 79 | eval time = 27.93 ms / 2 tokens ( 27.93 ms per token, 35.81 tokens per second) 0.41.477.050 I slot print_timing: id 1 | task 79 | total time = 849.38 ms / 168 tokens 0.41.477.050 I slot print_timing: id 1 | task 79 | graphs reused = 1 0.41.477.051 I slot print_timing: id 1 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.477.069 I slot release: id 1 | task 79 | stop processing: n_tokens = 167, truncated = 0 0.41.477.359 I slot print_timing: id 2 | task 78 | prompt eval time = 821.75 ms / 166 tokens ( 4.95 ms per token, 202.01 tokens per second) 0.41.477.361 I slot print_timing: id 2 | task 78 | eval time = 27.93 ms / 2 tokens ( 27.93 ms per token, 35.81 tokens per second) 0.41.477.361 I slot print_timing: id 2 | task 78 | total time = 849.68 ms / 168 tokens 0.41.477.362 I slot print_timing: id 2 | task 78 | graphs reused = 1 0.41.477.362 I slot print_timing: id 2 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.477.391 I slot release: id 2 | task 78 | stop processing: n_tokens = 167, truncated = 0 0.41.477.704 I slot print_timing: id 3 | task 80 | prompt eval time = 822.05 ms / 112 tokens ( 7.34 ms per token, 136.24 tokens per second) 0.41.477.709 I slot print_timing: id 3 | task 80 | eval time = 27.96 ms / 2 tokens ( 27.96 ms per token, 35.77 tokens per second) 0.41.477.709 I slot print_timing: id 3 | task 80 | total time = 850.01 ms / 114 tokens 0.41.477.709 I slot print_timing: id 3 | task 80 | graphs reused = 1 0.41.477.710 I slot print_timing: id 3 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.477.726 I slot release: id 3 | task 80 | stop processing: n_tokens = 113, truncated = 0 0.41.482.065 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.259 0.41.482.330 I slot launch_slot_: id 0 | task 84 | processing task, is_child = 0 0.41.483.539 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 0.41.483.574 I slot launch_slot_: id 1 | task 86 | processing task, is_child = 0 0.41.483.607 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.174 0.41.483.637 I slot launch_slot_: id 2 | task 85 | processing task, is_child = 0 0.41.483.655 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.257 0.41.483.799 I slot launch_slot_: id 3 | task 87 | processing task, is_child = 0 0.42.266.106 I slot print_timing: id 0 | task 84 | prompt eval time = 754.32 ms / 122 tokens ( 6.18 ms per token, 161.74 tokens per second) 0.42.266.109 I slot print_timing: id 0 | task 84 | eval time = 27.98 ms / 2 tokens ( 27.98 ms per token, 35.74 tokens per second) 0.42.266.109 I slot print_timing: id 0 | task 84 | total time = 782.30 ms / 124 tokens 0.42.266.110 I slot print_timing: id 0 | task 84 | graphs reused = 1 0.42.266.110 I slot print_timing: id 0 | task 84 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.266.128 I slot release: id 0 | task 84 | stop processing: n_tokens = 123, truncated = 0 0.42.266.393 I slot print_timing: id 1 | task 86 | prompt eval time = 754.58 ms / 145 tokens ( 5.20 ms per token, 192.16 tokens per second) 0.42.266.394 I slot print_timing: id 1 | task 86 | eval time = 27.99 ms / 2 tokens ( 27.99 ms per token, 35.73 tokens per second) 0.42.266.395 I slot print_timing: id 1 | task 86 | total time = 782.57 ms / 147 tokens 0.42.266.395 I slot print_timing: id 1 | task 86 | graphs reused = 1 0.42.266.395 I slot print_timing: id 1 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.266.407 I slot release: id 1 | task 86 | stop processing: n_tokens = 146, truncated = 0 0.42.266.691 I slot print_timing: id 2 | task 85 | prompt eval time = 754.86 ms / 133 tokens ( 5.68 ms per token, 176.19 tokens per second) 0.42.266.693 I slot print_timing: id 2 | task 85 | eval time = 28.00 ms / 2 tokens ( 28.00 ms per token, 35.71 tokens per second) 0.42.266.693 I slot print_timing: id 2 | task 85 | total time = 782.86 ms / 135 tokens 0.42.266.693 I slot print_timing: id 2 | task 85 | graphs reused = 1 0.42.266.694 I slot print_timing: id 2 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.266.709 I slot release: id 2 | task 85 | stop processing: n_tokens = 134, truncated = 0 0.42.267.008 I slot print_timing: id 3 | task 87 | prompt eval time = 755.16 ms / 127 tokens ( 5.95 ms per token, 168.18 tokens per second) 0.42.267.010 I slot print_timing: id 3 | task 87 | eval time = 28.01 ms / 2 tokens ( 28.01 ms per token, 35.71 tokens per second) 0.42.267.011 I slot print_timing: id 3 | task 87 | total time = 783.16 ms / 129 tokens 0.42.267.011 I slot print_timing: id 3 | task 87 | graphs reused = 1 0.42.267.011 I slot print_timing: id 3 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.267.026 I slot release: id 3 | task 87 | stop processing: n_tokens = 128, truncated = 0 0.42.270.988 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 0.42.271.436 I slot launch_slot_: id 3 | task 92 | processing task, is_child = 0 0.42.272.488 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.236 0.42.272.654 I slot launch_slot_: id 0 | task 91 | processing task, is_child = 0 0.42.272.691 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 0.42.272.720 I slot launch_slot_: id 1 | task 93 | processing task, is_child = 0 0.42.272.742 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.216 0.42.272.880 I slot launch_slot_: id 2 | task 94 | processing task, is_child = 0 0.43.074.065 I slot print_timing: id 0 | task 91 | prompt eval time = 773.48 ms / 133 tokens ( 5.82 ms per token, 171.95 tokens per second) 0.43.074.068 I slot print_timing: id 0 | task 91 | eval time = 27.70 ms / 2 tokens ( 27.70 ms per token, 36.10 tokens per second) 0.43.074.068 I slot print_timing: id 0 | task 91 | total time = 801.18 ms / 135 tokens 0.43.074.069 I slot print_timing: id 0 | task 91 | graphs reused = 1 0.43.074.069 I slot print_timing: id 0 | task 91 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.074.089 I slot release: id 0 | task 91 | stop processing: n_tokens = 134, truncated = 0 0.43.074.360 I slot print_timing: id 1 | task 93 | prompt eval time = 773.75 ms / 126 tokens ( 6.14 ms per token, 162.84 tokens per second) 0.43.074.362 I slot print_timing: id 1 | task 93 | eval time = 27.71 ms / 2 tokens ( 27.71 ms per token, 36.09 tokens per second) 0.43.074.363 I slot print_timing: id 1 | task 93 | total time = 801.46 ms / 128 tokens 0.43.074.363 I slot print_timing: id 1 | task 93 | graphs reused = 1 0.43.074.363 I slot print_timing: id 1 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.074.379 I slot release: id 1 | task 93 | stop processing: n_tokens = 127, truncated = 0 0.43.074.651 I slot print_timing: id 2 | task 94 | prompt eval time = 774.02 ms / 140 tokens ( 5.53 ms per token, 180.87 tokens per second) 0.43.074.653 I slot print_timing: id 2 | task 94 | eval time = 27.72 ms / 2 tokens ( 27.72 ms per token, 36.08 tokens per second) 0.43.074.653 I slot print_timing: id 2 | task 94 | total time = 801.74 ms / 142 tokens 0.43.074.653 I slot print_timing: id 2 | task 94 | graphs reused = 1 0.43.074.654 I slot print_timing: id 2 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.074.667 I slot release: id 2 | task 94 | stop processing: n_tokens = 141, truncated = 0 0.43.074.965 I slot print_timing: id 3 | task 92 | prompt eval time = 774.39 ms / 146 tokens ( 5.30 ms per token, 188.53 tokens per second) 0.43.074.968 I slot print_timing: id 3 | task 92 | eval time = 27.65 ms / 2 tokens ( 27.65 ms per token, 36.17 tokens per second) 0.43.074.968 I slot print_timing: id 3 | task 92 | total time = 802.04 ms / 148 tokens 0.43.074.969 I slot print_timing: id 3 | task 92 | graphs reused = 1 0.43.074.969 I slot print_timing: id 3 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.074.988 I slot release: id 3 | task 92 | stop processing: n_tokens = 147, truncated = 0 0.43.079.229 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.216 0.43.079.608 I slot launch_slot_: id 0 | task 98 | processing task, is_child = 0 0.43.080.504 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.204 0.43.080.535 I slot launch_slot_: id 3 | task 100 | processing task, is_child = 0 0.43.080.569 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.228 0.43.080.714 I slot launch_slot_: id 1 | task 99 | processing task, is_child = 0 0.43.080.732 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.213 0.43.080.761 I slot launch_slot_: id 2 | task 101 | processing task, is_child = 0 0.43.969.832 I slot print_timing: id 0 | task 98 | prompt eval time = 860.90 ms / 123 tokens ( 7.00 ms per token, 142.87 tokens per second) 0.43.969.834 I slot print_timing: id 0 | task 98 | eval time = 28.17 ms / 2 tokens ( 28.17 ms per token, 35.50 tokens per second) 0.43.969.835 I slot print_timing: id 0 | task 98 | total time = 889.06 ms / 125 tokens 0.43.969.835 I slot print_timing: id 0 | task 98 | graphs reused = 1 0.43.969.835 I slot print_timing: id 0 | task 98 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.969.854 I slot release: id 0 | task 98 | stop processing: n_tokens = 124, truncated = 0 0.43.970.125 I slot print_timing: id 1 | task 99 | prompt eval time = 861.15 ms / 120 tokens ( 7.18 ms per token, 139.35 tokens per second) 0.43.970.131 I slot print_timing: id 1 | task 99 | eval time = 28.20 ms / 2 tokens ( 28.20 ms per token, 35.47 tokens per second) 0.43.970.131 I slot print_timing: id 1 | task 99 | total time = 889.35 ms / 122 tokens 0.43.970.132 I slot print_timing: id 1 | task 99 | graphs reused = 1 0.43.970.132 I slot print_timing: id 1 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.970.147 I slot release: id 1 | task 99 | stop processing: n_tokens = 121, truncated = 0 0.43.970.443 I slot print_timing: id 2 | task 101 | prompt eval time = 861.45 ms / 171 tokens ( 5.04 ms per token, 198.50 tokens per second) 0.43.970.450 I slot print_timing: id 2 | task 101 | eval time = 28.20 ms / 2 tokens ( 28.20 ms per token, 35.46 tokens per second) 0.43.970.451 I slot print_timing: id 2 | task 101 | total time = 889.66 ms / 173 tokens 0.43.970.451 I slot print_timing: id 2 | task 101 | graphs reused = 1 0.43.970.451 I slot print_timing: id 2 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.970.469 I slot release: id 2 | task 101 | stop processing: n_tokens = 172, truncated = 0 0.43.970.761 I slot print_timing: id 3 | task 100 | prompt eval time = 861.77 ms / 110 tokens ( 7.83 ms per token, 127.64 tokens per second) 0.43.970.763 I slot print_timing: id 3 | task 100 | eval time = 28.19 ms / 2 tokens ( 28.19 ms per token, 35.47 tokens per second) 0.43.970.763 I slot print_timing: id 3 | task 100 | total time = 889.96 ms / 112 tokens 0.43.970.764 I slot print_timing: id 3 | task 100 | graphs reused = 1 0.43.970.764 I slot print_timing: id 3 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.970.773 I slot release: id 3 | task 100 | stop processing: n_tokens = 111, truncated = 0 0.43.974.664 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.248 0.43.975.062 I slot launch_slot_: id 1 | task 105 | processing task, is_child = 0 0.43.975.944 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.125 (> 0.100 thold), f_keep = 0.234 0.43.975.978 I slot launch_slot_: id 0 | task 106 | processing task, is_child = 0 0.43.976.011 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.256 (> 0.100 thold), f_keep = 0.270 0.43.976.040 I slot launch_slot_: id 3 | task 107 | processing task, is_child = 0 0.43.976.059 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.169 0.43.976.088 I slot launch_slot_: id 2 | task 108 | processing task, is_child = 0 0.45.109.490 I slot print_timing: id 0 | task 106 | prompt eval time = 1105.65 ms / 232 tokens ( 4.77 ms per token, 209.83 tokens per second) 0.45.109.492 I slot print_timing: id 0 | task 106 | eval time = 27.75 ms / 2 tokens ( 27.75 ms per token, 36.04 tokens per second) 0.45.109.493 I slot print_timing: id 0 | task 106 | total time = 1133.39 ms / 234 tokens 0.45.109.494 I slot print_timing: id 0 | task 106 | graphs reused = 1 0.45.109.494 I slot print_timing: id 0 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.109.524 I slot release: id 0 | task 106 | stop processing: n_tokens = 233, truncated = 0 0.45.109.795 I slot print_timing: id 1 | task 105 | prompt eval time = 1105.92 ms / 138 tokens ( 8.01 ms per token, 124.78 tokens per second) 0.45.109.797 I slot print_timing: id 1 | task 105 | eval time = 27.77 ms / 2 tokens ( 27.77 ms per token, 36.01 tokens per second) 0.45.109.797 I slot print_timing: id 1 | task 105 | total time = 1133.69 ms / 140 tokens 0.45.109.797 I slot print_timing: id 1 | task 105 | graphs reused = 1 0.45.109.798 I slot print_timing: id 1 | task 105 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.109.818 I slot release: id 1 | task 105 | stop processing: n_tokens = 139, truncated = 0 0.45.110.100 I slot print_timing: id 2 | task 108 | prompt eval time = 1106.20 ms / 176 tokens ( 6.29 ms per token, 159.10 tokens per second) 0.45.110.102 I slot print_timing: id 2 | task 108 | eval time = 27.78 ms / 2 tokens ( 27.78 ms per token, 36.00 tokens per second) 0.45.110.102 I slot print_timing: id 2 | task 108 | total time = 1133.98 ms / 178 tokens 0.45.110.102 I slot print_timing: id 2 | task 108 | graphs reused = 1 0.45.110.103 I slot print_timing: id 2 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.110.125 I slot release: id 2 | task 108 | stop processing: n_tokens = 177, truncated = 0 0.45.110.411 I slot print_timing: id 3 | task 107 | prompt eval time = 1106.51 ms / 117 tokens ( 9.46 ms per token, 105.74 tokens per second) 0.45.110.415 I slot print_timing: id 3 | task 107 | eval time = 27.77 ms / 2 tokens ( 27.77 ms per token, 36.01 tokens per second) 0.45.110.415 I slot print_timing: id 3 | task 107 | total time = 1134.28 ms / 119 tokens 0.45.110.415 I slot print_timing: id 3 | task 107 | graphs reused = 1 0.45.110.416 I slot print_timing: id 3 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.110.427 I slot release: id 3 | task 107 | stop processing: n_tokens = 118, truncated = 0 0.45.114.150 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.124 0.45.114.676 I slot launch_slot_: id 0 | task 114 | processing task, is_child = 0 0.45.115.693 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.271 0.45.115.736 I slot launch_slot_: id 3 | task 112 | processing task, is_child = 0 0.45.115.772 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.216 0.45.115.906 I slot launch_slot_: id 1 | task 113 | processing task, is_child = 0 0.45.115.930 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.164 0.45.115.960 I slot launch_slot_: id 2 | task 115 | processing task, is_child = 0 0.46.303.993 I slot print_timing: id 0 | task 114 | prompt eval time = 1159.99 ms / 158 tokens ( 7.34 ms per token, 136.21 tokens per second) 0.46.303.997 I slot print_timing: id 0 | task 114 | eval time = 28.03 ms / 2 tokens ( 28.03 ms per token, 35.67 tokens per second) 0.46.303.998 I slot print_timing: id 0 | task 114 | total time = 1188.02 ms / 160 tokens 0.46.303.999 I slot print_timing: id 0 | task 114 | graphs reused = 1 0.46.303.999 I slot print_timing: id 0 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.304.021 I slot release: id 0 | task 114 | stop processing: n_tokens = 159, truncated = 0 0.46.304.381 I slot print_timing: id 1 | task 113 | prompt eval time = 1160.33 ms / 156 tokens ( 7.44 ms per token, 134.44 tokens per second) 0.46.304.383 I slot print_timing: id 1 | task 113 | eval time = 28.07 ms / 2 tokens ( 28.07 ms per token, 35.62 tokens per second) 0.46.304.383 I slot print_timing: id 1 | task 113 | total time = 1188.40 ms / 158 tokens 0.46.304.384 I slot print_timing: id 1 | task 113 | graphs reused = 1 0.46.304.384 I slot print_timing: id 1 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.304.399 I slot release: id 1 | task 113 | stop processing: n_tokens = 157, truncated = 0 0.46.304.683 I slot print_timing: id 2 | task 115 | prompt eval time = 1160.62 ms / 227 tokens ( 5.11 ms per token, 195.58 tokens per second) 0.46.304.686 I slot print_timing: id 2 | task 115 | eval time = 28.07 ms / 2 tokens ( 28.07 ms per token, 35.63 tokens per second) 0.46.304.686 I slot print_timing: id 2 | task 115 | total time = 1188.69 ms / 229 tokens 0.46.304.687 I slot print_timing: id 2 | task 115 | graphs reused = 1 0.46.304.687 I slot print_timing: id 2 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.304.707 I slot release: id 2 | task 115 | stop processing: n_tokens = 228, truncated = 0 0.46.305.029 I slot print_timing: id 3 | task 112 | prompt eval time = 1160.93 ms / 143 tokens ( 8.12 ms per token, 123.18 tokens per second) 0.46.305.031 I slot print_timing: id 3 | task 112 | eval time = 28.09 ms / 2 tokens ( 28.09 ms per token, 35.59 tokens per second) 0.46.305.032 I slot print_timing: id 3 | task 112 | total time = 1189.02 ms / 145 tokens 0.46.305.032 I slot print_timing: id 3 | task 112 | graphs reused = 1 0.46.305.032 I slot print_timing: id 3 | task 112 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.305.044 I slot release: id 3 | task 112 | stop processing: n_tokens = 144, truncated = 0 0.46.309.188 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.299 (> 0.100 thold), f_keep = 0.222 0.46.309.655 I slot launch_slot_: id 3 | task 119 | processing task, is_child = 0 0.46.310.987 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.182 0.46.311.026 I slot launch_slot_: id 0 | task 120 | processing task, is_child = 0 0.46.311.063 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.256 (> 0.100 thold), f_keep = 0.191 0.46.311.094 I slot launch_slot_: id 1 | task 121 | processing task, is_child = 0 0.46.311.116 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.153 (> 0.100 thold), f_keep = 0.127 0.46.311.267 I slot launch_slot_: id 2 | task 122 | processing task, is_child = 0 0.47.294.081 I slot print_timing: id 0 | task 120 | prompt eval time = 954.62 ms / 143 tokens ( 6.68 ms per token, 149.80 tokens per second) 0.47.294.083 I slot print_timing: id 0 | task 120 | eval time = 28.18 ms / 2 tokens ( 28.18 ms per token, 35.48 tokens per second) 0.47.294.084 I slot print_timing: id 0 | task 120 | total time = 982.80 ms / 145 tokens 0.47.294.085 I slot print_timing: id 0 | task 120 | graphs reused = 1 0.47.294.085 I slot print_timing: id 0 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.294.114 I slot release: id 0 | task 120 | stop processing: n_tokens = 144, truncated = 0 0.47.294.404 I slot print_timing: id 1 | task 121 | prompt eval time = 954.90 ms / 117 tokens ( 8.16 ms per token, 122.53 tokens per second) 0.47.294.408 I slot print_timing: id 1 | task 121 | eval time = 28.22 ms / 2 tokens ( 28.22 ms per token, 35.43 tokens per second) 0.47.294.408 I slot print_timing: id 1 | task 121 | total time = 983.12 ms / 119 tokens 0.47.294.408 I slot print_timing: id 1 | task 121 | graphs reused = 1 0.47.294.409 I slot print_timing: id 1 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.294.425 I slot release: id 1 | task 121 | stop processing: n_tokens = 118, truncated = 0 0.47.294.711 I slot print_timing: id 2 | task 122 | prompt eval time = 955.18 ms / 189 tokens ( 5.05 ms per token, 197.87 tokens per second) 0.47.294.713 I slot print_timing: id 2 | task 122 | eval time = 28.23 ms / 2 tokens ( 28.23 ms per token, 35.42 tokens per second) 0.47.294.714 I slot print_timing: id 2 | task 122 | total time = 983.41 ms / 191 tokens 0.47.294.714 I slot print_timing: id 2 | task 122 | graphs reused = 1 0.47.294.714 I slot print_timing: id 2 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.294.738 I slot release: id 2 | task 122 | stop processing: n_tokens = 190, truncated = 0 0.47.295.078 I slot print_timing: id 3 | task 119 | prompt eval time = 955.46 ms / 107 tokens ( 8.93 ms per token, 111.99 tokens per second) 0.47.295.080 I slot print_timing: id 3 | task 119 | eval time = 28.31 ms / 2 tokens ( 28.31 ms per token, 35.32 tokens per second) 0.47.295.081 I slot print_timing: id 3 | task 119 | total time = 983.77 ms / 109 tokens 0.47.295.081 I slot print_timing: id 3 | task 119 | graphs reused = 1 0.47.295.081 I slot print_timing: id 3 | task 119 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.295.093 I slot release: id 3 | task 119 | stop processing: n_tokens = 108, truncated = 0 0.47.299.394 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.254 0.47.299.697 I slot launch_slot_: id 1 | task 127 | processing task, is_child = 0 0.47.300.748 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.201 0.47.300.783 I slot launch_slot_: id 0 | task 126 | processing task, is_child = 0 0.47.300.817 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.153 0.47.300.848 I slot launch_slot_: id 2 | task 128 | processing task, is_child = 0 0.47.300.865 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.244 (> 0.100 thold), f_keep = 0.278 0.47.300.893 I slot launch_slot_: id 3 | task 129 | processing task, is_child = 0 0.48.217.789 I slot print_timing: id 0 | task 126 | prompt eval time = 888.96 ms / 173 tokens ( 5.14 ms per token, 194.61 tokens per second) 0.48.217.792 I slot print_timing: id 0 | task 126 | eval time = 27.93 ms / 2 tokens ( 27.93 ms per token, 35.80 tokens per second) 0.48.217.792 I slot print_timing: id 0 | task 126 | total time = 916.89 ms / 175 tokens 0.48.217.792 I slot print_timing: id 0 | task 126 | graphs reused = 1 0.48.217.793 I slot print_timing: id 0 | task 126 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.217.815 I slot release: id 0 | task 126 | stop processing: n_tokens = 174, truncated = 0 0.48.218.084 I slot print_timing: id 1 | task 127 | prompt eval time = 889.21 ms / 110 tokens ( 8.08 ms per token, 123.71 tokens per second) 0.48.218.086 I slot print_timing: id 1 | task 127 | eval time = 27.96 ms / 2 tokens ( 27.96 ms per token, 35.76 tokens per second) 0.48.218.087 I slot print_timing: id 1 | task 127 | total time = 917.17 ms / 112 tokens 0.48.218.087 I slot print_timing: id 1 | task 127 | graphs reused = 1 0.48.218.087 I slot print_timing: id 1 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.218.101 I slot release: id 1 | task 127 | stop processing: n_tokens = 111, truncated = 0 0.48.218.374 I slot print_timing: id 2 | task 128 | prompt eval time = 889.48 ms / 138 tokens ( 6.45 ms per token, 155.15 tokens per second) 0.48.218.376 I slot print_timing: id 2 | task 128 | eval time = 27.98 ms / 2 tokens ( 27.98 ms per token, 35.74 tokens per second) 0.48.218.377 I slot print_timing: id 2 | task 128 | total time = 917.45 ms / 140 tokens 0.48.218.377 I slot print_timing: id 2 | task 128 | graphs reused = 1 0.48.218.377 I slot print_timing: id 2 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.218.396 I slot release: id 2 | task 128 | stop processing: n_tokens = 139, truncated = 0 0.48.218.679 I slot print_timing: id 3 | task 129 | prompt eval time = 889.77 ms / 123 tokens ( 7.23 ms per token, 138.24 tokens per second) 0.48.218.682 I slot print_timing: id 3 | task 129 | eval time = 27.97 ms / 2 tokens ( 27.97 ms per token, 35.75 tokens per second) 0.48.218.683 I slot print_timing: id 3 | task 129 | total time = 917.74 ms / 125 tokens 0.48.218.683 I slot print_timing: id 3 | task 129 | graphs reused = 1 0.48.218.683 I slot print_timing: id 3 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.218.701 I slot release: id 3 | task 129 | stop processing: n_tokens = 124, truncated = 0 0.48.222.602 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 0.48.223.111 I slot launch_slot_: id 0 | task 133 | processing task, is_child = 0 0.48.224.019 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.270 0.48.224.160 I slot launch_slot_: id 1 | task 134 | processing task, is_child = 0 0.48.224.197 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.209 0.48.224.226 I slot launch_slot_: id 2 | task 136 | processing task, is_child = 0 0.48.224.245 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.234 0.48.224.273 I slot launch_slot_: id 3 | task 135 | processing task, is_child = 0 0.49.105.411 I slot print_timing: id 0 | task 133 | prompt eval time = 852.42 ms / 161 tokens ( 5.29 ms per token, 188.87 tokens per second) 0.49.105.415 I slot print_timing: id 0 | task 133 | eval time = 28.71 ms / 2 tokens ( 28.71 ms per token, 34.83 tokens per second) 0.49.105.416 I slot print_timing: id 0 | task 133 | total time = 881.13 ms / 163 tokens 0.49.105.416 I slot print_timing: id 0 | task 133 | graphs reused = 1 0.49.105.417 I slot print_timing: id 0 | task 133 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.105.440 I slot release: id 0 | task 133 | stop processing: n_tokens = 162, truncated = 0 0.49.105.735 I slot print_timing: id 1 | task 134 | prompt eval time = 852.80 ms / 122 tokens ( 6.99 ms per token, 143.06 tokens per second) 0.49.105.739 I slot print_timing: id 1 | task 134 | eval time = 28.64 ms / 2 tokens ( 28.64 ms per token, 34.91 tokens per second) 0.49.105.739 I slot print_timing: id 1 | task 134 | total time = 881.44 ms / 124 tokens 0.49.105.739 I slot print_timing: id 1 | task 134 | graphs reused = 1 0.49.105.740 I slot print_timing: id 1 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.105.756 I slot release: id 1 | task 134 | stop processing: n_tokens = 123, truncated = 0 0.49.106.064 I slot print_timing: id 2 | task 136 | prompt eval time = 853.38 ms / 134 tokens ( 6.37 ms per token, 157.02 tokens per second) 0.49.106.066 I slot print_timing: id 2 | task 136 | eval time = 28.38 ms / 2 tokens ( 28.38 ms per token, 35.23 tokens per second) 0.49.106.066 I slot print_timing: id 2 | task 136 | total time = 881.76 ms / 136 tokens 0.49.106.066 I slot print_timing: id 2 | task 136 | graphs reused = 1 0.49.106.066 I slot print_timing: id 2 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.106.081 I slot release: id 2 | task 136 | stop processing: n_tokens = 135, truncated = 0 0.49.106.409 I slot print_timing: id 3 | task 135 | prompt eval time = 853.95 ms / 136 tokens ( 6.28 ms per token, 159.26 tokens per second) 0.49.106.411 I slot print_timing: id 3 | task 135 | eval time = 28.14 ms / 2 tokens ( 28.14 ms per token, 35.53 tokens per second) 0.49.106.412 I slot print_timing: id 3 | task 135 | total time = 882.10 ms / 138 tokens 0.49.106.413 I slot print_timing: id 3 | task 135 | graphs reused = 1 0.49.106.413 I slot print_timing: id 3 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.106.429 I slot release: id 3 | task 135 | stop processing: n_tokens = 137, truncated = 0 0.49.110.578 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.179 0.49.111.050 I slot launch_slot_: id 0 | task 140 | processing task, is_child = 0 0.49.112.174 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.236 0.49.112.209 I slot launch_slot_: id 1 | task 141 | processing task, is_child = 0 0.49.112.246 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.215 0.49.112.275 I slot launch_slot_: id 2 | task 142 | processing task, is_child = 0 0.49.112.293 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.170 (> 0.100 thold), f_keep = 0.212 0.49.112.325 I slot launch_slot_: id 3 | task 143 | processing task, is_child = 0 0.50.135.331 I slot print_timing: id 0 | task 140 | prompt eval time = 994.30 ms / 181 tokens ( 5.49 ms per token, 182.04 tokens per second) 0.50.135.335 I slot print_timing: id 0 | task 140 | eval time = 28.70 ms / 2 tokens ( 28.70 ms per token, 34.85 tokens per second) 0.50.135.335 I slot print_timing: id 0 | task 140 | total time = 1023.00 ms / 183 tokens 0.50.135.336 I slot print_timing: id 0 | task 140 | graphs reused = 1 0.50.135.336 I slot print_timing: id 0 | task 140 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.135.367 I slot release: id 0 | task 140 | stop processing: n_tokens = 182, truncated = 0 0.50.135.653 I slot print_timing: id 1 | task 141 | prompt eval time = 994.65 ms / 131 tokens ( 7.59 ms per token, 131.70 tokens per second) 0.50.135.655 I slot print_timing: id 1 | task 141 | eval time = 28.66 ms / 2 tokens ( 28.66 ms per token, 34.89 tokens per second) 0.50.135.655 I slot print_timing: id 1 | task 141 | total time = 1023.31 ms / 133 tokens 0.50.135.656 I slot print_timing: id 1 | task 141 | graphs reused = 1 0.50.135.656 I slot print_timing: id 1 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.135.670 I slot release: id 1 | task 141 | stop processing: n_tokens = 132, truncated = 0 0.50.135.973 I slot print_timing: id 2 | task 142 | prompt eval time = 995.07 ms / 175 tokens ( 5.69 ms per token, 175.87 tokens per second) 0.50.135.975 I slot print_timing: id 2 | task 142 | eval time = 28.54 ms / 2 tokens ( 28.54 ms per token, 35.04 tokens per second) 0.50.135.976 I slot print_timing: id 2 | task 142 | total time = 1023.62 ms / 177 tokens 0.50.135.976 I slot print_timing: id 2 | task 142 | graphs reused = 1 0.50.135.976 I slot print_timing: id 2 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.135.991 I slot release: id 2 | task 142 | stop processing: n_tokens = 176, truncated = 0 0.50.136.310 I slot print_timing: id 3 | task 143 | prompt eval time = 995.65 ms / 171 tokens ( 5.82 ms per token, 171.75 tokens per second) 0.50.136.313 I slot print_timing: id 3 | task 143 | eval time = 28.29 ms / 2 tokens ( 28.29 ms per token, 35.35 tokens per second) 0.50.136.314 I slot print_timing: id 3 | task 143 | total time = 1023.94 ms / 173 tokens 0.50.136.314 I slot print_timing: id 3 | task 143 | graphs reused = 1 0.50.136.314 I slot print_timing: id 3 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.136.329 I slot release: id 3 | task 143 | stop processing: n_tokens = 172, truncated = 0 0.50.141.086 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.159 0.50.141.600 I slot launch_slot_: id 0 | task 147 | processing task, is_child = 0 0.50.142.855 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.220 0.50.143.018 I slot launch_slot_: id 1 | task 148 | processing task, is_child = 0 0.50.143.055 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.165 0.50.143.087 I slot launch_slot_: id 2 | task 149 | processing task, is_child = 0 0.50.143.109 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.169 0.50.143.283 I slot launch_slot_: id 3 | task 150 | processing task, is_child = 0 0.50.836.154 I slot print_timing: id 0 | task 147 | prompt eval time = 664.86 ms / 115 tokens ( 5.78 ms per token, 172.97 tokens per second) 0.50.836.157 I slot print_timing: id 0 | task 147 | eval time = 28.00 ms / 2 tokens ( 28.00 ms per token, 35.71 tokens per second) 0.50.836.157 I slot print_timing: id 0 | task 147 | total time = 692.86 ms / 117 tokens 0.50.836.158 I slot print_timing: id 0 | task 147 | graphs reused = 1 0.50.836.158 I slot print_timing: id 0 | task 147 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.836.180 I slot release: id 0 | task 147 | stop processing: n_tokens = 116, truncated = 0 0.50.836.474 I slot print_timing: id 1 | task 148 | prompt eval time = 665.12 ms / 123 tokens ( 5.41 ms per token, 184.93 tokens per second) 0.50.836.476 I slot print_timing: id 1 | task 148 | eval time = 28.05 ms / 2 tokens ( 28.05 ms per token, 35.65 tokens per second) 0.50.836.476 I slot print_timing: id 1 | task 148 | total time = 693.17 ms / 125 tokens 0.50.836.476 I slot print_timing: id 1 | task 148 | graphs reused = 1 0.50.836.477 I slot print_timing: id 1 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.836.490 I slot release: id 1 | task 148 | stop processing: n_tokens = 124, truncated = 0 0.50.836.769 I slot print_timing: id 2 | task 149 | prompt eval time = 665.37 ms / 125 tokens ( 5.32 ms per token, 187.87 tokens per second) 0.50.836.771 I slot print_timing: id 2 | task 149 | eval time = 28.09 ms / 2 tokens ( 28.09 ms per token, 35.60 tokens per second) 0.50.836.772 I slot print_timing: id 2 | task 149 | total time = 693.45 ms / 127 tokens 0.50.836.772 I slot print_timing: id 2 | task 149 | graphs reused = 1 0.50.836.772 I slot print_timing: id 2 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.836.789 I slot release: id 2 | task 149 | stop processing: n_tokens = 126, truncated = 0 0.50.837.170 I slot print_timing: id 3 | task 150 | prompt eval time = 665.86 ms / 116 tokens ( 5.74 ms per token, 174.21 tokens per second) 0.50.837.171 I slot print_timing: id 3 | task 150 | eval time = 27.98 ms / 2 tokens ( 27.98 ms per token, 35.74 tokens per second) 0.50.837.171 I slot print_timing: id 3 | task 150 | total time = 693.84 ms / 118 tokens 0.50.837.172 I slot print_timing: id 3 | task 150 | graphs reused = 1 0.50.837.172 I slot print_timing: id 3 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.837.181 I slot release: id 3 | task 150 | stop processing: n_tokens = 117, truncated = 0 0.50.841.316 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.223 (> 0.100 thold), f_keep = 0.250 0.50.841.686 I slot launch_slot_: id 0 | task 154 | processing task, is_child = 0 0.50.842.620 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.234 0.50.842.660 I slot launch_slot_: id 1 | task 155 | processing task, is_child = 0 0.50.842.696 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.223 (> 0.100 thold), f_keep = 0.230 0.50.842.724 I slot launch_slot_: id 2 | task 156 | processing task, is_child = 0 0.50.842.741 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.256 (> 0.100 thold), f_keep = 0.282 0.50.842.772 I slot launch_slot_: id 3 | task 157 | processing task, is_child = 0 0.51.560.077 I slot print_timing: id 0 | task 154 | prompt eval time = 689.22 ms / 130 tokens ( 5.30 ms per token, 188.62 tokens per second) 0.51.560.079 I slot print_timing: id 0 | task 154 | eval time = 28.08 ms / 2 tokens ( 28.08 ms per token, 35.61 tokens per second) 0.51.560.080 I slot print_timing: id 0 | task 154 | total time = 717.30 ms / 132 tokens 0.51.560.080 I slot print_timing: id 0 | task 154 | graphs reused = 1 0.51.560.081 I slot print_timing: id 0 | task 154 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.560.101 I slot release: id 0 | task 154 | stop processing: n_tokens = 131, truncated = 0 0.51.560.374 I slot print_timing: id 1 | task 155 | prompt eval time = 689.48 ms / 143 tokens ( 4.82 ms per token, 207.40 tokens per second) 0.51.560.376 I slot print_timing: id 1 | task 155 | eval time = 28.10 ms / 2 tokens ( 28.10 ms per token, 35.58 tokens per second) 0.51.560.377 I slot print_timing: id 1 | task 155 | total time = 717.58 ms / 145 tokens 0.51.560.377 I slot print_timing: id 1 | task 155 | graphs reused = 1 0.51.560.378 I slot print_timing: id 1 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.560.391 I slot release: id 1 | task 155 | stop processing: n_tokens = 144, truncated = 0 0.51.560.679 I slot print_timing: id 2 | task 156 | prompt eval time = 689.78 ms / 130 tokens ( 5.31 ms per token, 188.47 tokens per second) 0.51.560.681 I slot print_timing: id 2 | task 156 | eval time = 28.10 ms / 2 tokens ( 28.10 ms per token, 35.59 tokens per second) 0.51.560.681 I slot print_timing: id 2 | task 156 | total time = 717.88 ms / 132 tokens 0.51.560.682 I slot print_timing: id 2 | task 156 | graphs reused = 1 0.51.560.682 I slot print_timing: id 2 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.560.694 I slot release: id 2 | task 156 | stop processing: n_tokens = 131, truncated = 0 0.51.561.061 I slot print_timing: id 3 | task 157 | prompt eval time = 690.27 ms / 129 tokens ( 5.35 ms per token, 186.88 tokens per second) 0.51.561.065 I slot print_timing: id 3 | task 157 | eval time = 27.98 ms / 2 tokens ( 27.98 ms per token, 35.74 tokens per second) 0.51.561.065 I slot print_timing: id 3 | task 157 | total time = 718.25 ms / 131 tokens 0.51.561.065 I slot print_timing: id 3 | task 157 | graphs reused = 1 0.51.561.066 I slot print_timing: id 3 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.561.077 I slot release: id 3 | task 157 | stop processing: n_tokens = 130, truncated = 0 0.51.565.122 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.221 0.51.565.561 I slot launch_slot_: id 0 | task 163 | processing task, is_child = 0 0.51.566.526 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.225 (> 0.100 thold), f_keep = 0.201 0.51.566.561 I slot launch_slot_: id 1 | task 161 | processing task, is_child = 0 0.51.566.594 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.286 (> 0.100 thold), f_keep = 0.231 0.51.566.625 I slot launch_slot_: id 3 | task 162 | processing task, is_child = 0 0.51.566.643 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.221 0.51.566.672 I slot launch_slot_: id 2 | task 164 | processing task, is_child = 0 0.52.487.135 I slot print_timing: id 0 | task 163 | prompt eval time = 892.58 ms / 124 tokens ( 7.20 ms per token, 138.92 tokens per second) 0.52.487.137 I slot print_timing: id 0 | task 163 | eval time = 27.88 ms / 2 tokens ( 27.88 ms per token, 35.87 tokens per second) 0.52.487.138 I slot print_timing: id 0 | task 163 | total time = 920.46 ms / 126 tokens 0.52.487.139 I slot print_timing: id 0 | task 163 | graphs reused = 1 0.52.487.139 I slot print_timing: id 0 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.487.166 I slot release: id 0 | task 163 | stop processing: n_tokens = 125, truncated = 0 0.52.487.428 I slot print_timing: id 1 | task 161 | prompt eval time = 892.86 ms / 129 tokens ( 6.92 ms per token, 144.48 tokens per second) 0.52.487.431 I slot print_timing: id 1 | task 161 | eval time = 27.87 ms / 2 tokens ( 27.87 ms per token, 35.88 tokens per second) 0.52.487.432 I slot print_timing: id 1 | task 161 | total time = 920.74 ms / 131 tokens 0.52.487.432 I slot print_timing: id 1 | task 161 | graphs reused = 1 0.52.487.433 I slot print_timing: id 1 | task 161 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.487.445 I slot release: id 1 | task 161 | stop processing: n_tokens = 130, truncated = 0 0.52.487.736 I slot print_timing: id 2 | task 164 | prompt eval time = 893.18 ms / 161 tokens ( 5.55 ms per token, 180.25 tokens per second) 0.52.487.738 I slot print_timing: id 2 | task 164 | eval time = 27.85 ms / 2 tokens ( 27.85 ms per token, 35.91 tokens per second) 0.52.487.738 I slot print_timing: id 2 | task 164 | total time = 921.03 ms / 163 tokens 0.52.487.738 I slot print_timing: id 2 | task 164 | graphs reused = 1 0.52.487.738 I slot print_timing: id 2 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.487.757 I slot release: id 2 | task 164 | stop processing: n_tokens = 162, truncated = 0 0.52.488.038 I slot print_timing: id 3 | task 162 | prompt eval time = 893.51 ms / 105 tokens ( 8.51 ms per token, 117.51 tokens per second) 0.52.488.040 I slot print_timing: id 3 | task 162 | eval time = 27.81 ms / 2 tokens ( 27.81 ms per token, 35.95 tokens per second) 0.52.488.040 I slot print_timing: id 3 | task 162 | total time = 921.32 ms / 107 tokens 0.52.488.040 I slot print_timing: id 3 | task 162 | graphs reused = 1 0.52.488.041 I slot print_timing: id 3 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.488.050 I slot release: id 3 | task 162 | stop processing: n_tokens = 106, truncated = 0 0.52.491.503 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.283 0.52.491.718 I slot launch_slot_: id 3 | task 170 | processing task, is_child = 0 0.52.492.906 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.232 0.52.492.942 I slot launch_slot_: id 0 | task 169 | processing task, is_child = 0 0.52.492.976 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.223 0.52.493.139 I slot launch_slot_: id 1 | task 168 | processing task, is_child = 0 0.52.493.158 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.179 0.52.493.191 I slot launch_slot_: id 2 | task 171 | processing task, is_child = 0 0.53.431.482 I slot print_timing: id 0 | task 169 | prompt eval time = 910.12 ms / 155 tokens ( 5.87 ms per token, 170.31 tokens per second) 0.53.431.484 I slot print_timing: id 0 | task 169 | eval time = 28.16 ms / 2 tokens ( 28.16 ms per token, 35.51 tokens per second) 0.53.431.485 I slot print_timing: id 0 | task 169 | total time = 938.28 ms / 157 tokens 0.53.431.485 I slot print_timing: id 0 | task 169 | graphs reused = 1 0.53.431.486 I slot print_timing: id 0 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.431.508 I slot release: id 0 | task 169 | stop processing: n_tokens = 156, truncated = 0 0.53.431.785 I slot print_timing: id 1 | task 168 | prompt eval time = 910.42 ms / 143 tokens ( 6.37 ms per token, 157.07 tokens per second) 0.53.431.787 I slot print_timing: id 1 | task 168 | eval time = 28.16 ms / 2 tokens ( 28.16 ms per token, 35.52 tokens per second) 0.53.431.788 I slot print_timing: id 1 | task 168 | total time = 938.58 ms / 145 tokens 0.53.431.788 I slot print_timing: id 1 | task 168 | graphs reused = 1 0.53.431.788 I slot print_timing: id 1 | task 168 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.431.802 I slot release: id 1 | task 168 | stop processing: n_tokens = 144, truncated = 0 0.53.432.085 I slot print_timing: id 2 | task 171 | prompt eval time = 910.73 ms / 169 tokens ( 5.39 ms per token, 185.57 tokens per second) 0.53.432.087 I slot print_timing: id 2 | task 171 | eval time = 28.13 ms / 2 tokens ( 28.13 ms per token, 35.54 tokens per second) 0.53.432.087 I slot print_timing: id 2 | task 171 | total time = 938.87 ms / 171 tokens 0.53.432.088 I slot print_timing: id 2 | task 171 | graphs reused = 1 0.53.432.088 I slot print_timing: id 2 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.432.102 I slot release: id 2 | task 171 | stop processing: n_tokens = 170, truncated = 0 0.53.432.381 I slot print_timing: id 3 | task 170 | prompt eval time = 911.14 ms / 113 tokens ( 8.06 ms per token, 124.02 tokens per second) 0.53.432.385 I slot print_timing: id 3 | task 170 | eval time = 28.00 ms / 2 tokens ( 28.00 ms per token, 35.71 tokens per second) 0.53.432.385 I slot print_timing: id 3 | task 170 | total time = 939.15 ms / 115 tokens 0.53.432.385 I slot print_timing: id 3 | task 170 | graphs reused = 1 0.53.432.386 I slot print_timing: id 3 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.432.403 I slot release: id 3 | task 170 | stop processing: n_tokens = 114, truncated = 0 0.53.436.786 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.186 0.53.437.221 I slot launch_slot_: id 0 | task 176 | processing task, is_child = 0 0.53.438.221 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.201 0.53.438.262 I slot launch_slot_: id 1 | task 175 | processing task, is_child = 0 0.53.438.297 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.171 0.53.438.331 I slot launch_slot_: id 2 | task 177 | processing task, is_child = 0 0.53.438.348 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.263 0.53.438.377 I slot launch_slot_: id 3 | task 178 | processing task, is_child = 0 0.54.300.905 I slot print_timing: id 0 | task 176 | prompt eval time = 834.41 ms / 138 tokens ( 6.05 ms per token, 165.39 tokens per second) 0.54.300.906 I slot print_timing: id 0 | task 176 | eval time = 28.10 ms / 2 tokens ( 28.10 ms per token, 35.58 tokens per second) 0.54.300.907 I slot print_timing: id 0 | task 176 | total time = 862.52 ms / 140 tokens 0.54.300.907 I slot print_timing: id 0 | task 176 | graphs reused = 1 0.54.300.907 I slot print_timing: id 0 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.300.927 I slot release: id 0 | task 176 | stop processing: n_tokens = 139, truncated = 0 0.54.301.194 I slot print_timing: id 1 | task 175 | prompt eval time = 834.70 ms / 111 tokens ( 7.52 ms per token, 132.98 tokens per second) 0.54.301.196 I slot print_timing: id 1 | task 175 | eval time = 28.10 ms / 2 tokens ( 28.10 ms per token, 35.59 tokens per second) 0.54.301.196 I slot print_timing: id 1 | task 175 | total time = 862.80 ms / 113 tokens 0.54.301.196 I slot print_timing: id 1 | task 175 | graphs reused = 1 0.54.301.197 I slot print_timing: id 1 | task 175 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.301.209 I slot release: id 1 | task 175 | stop processing: n_tokens = 112, truncated = 0 0.54.301.477 I slot print_timing: id 2 | task 177 | prompt eval time = 835.00 ms / 150 tokens ( 5.57 ms per token, 179.64 tokens per second) 0.54.301.479 I slot print_timing: id 2 | task 177 | eval time = 28.07 ms / 2 tokens ( 28.07 ms per token, 35.63 tokens per second) 0.54.301.479 I slot print_timing: id 2 | task 177 | total time = 863.07 ms / 152 tokens 0.54.301.480 I slot print_timing: id 2 | task 177 | graphs reused = 1 0.54.301.480 I slot print_timing: id 2 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.301.503 I slot release: id 2 | task 177 | stop processing: n_tokens = 151, truncated = 0 0.54.301.774 I slot print_timing: id 3 | task 178 | prompt eval time = 835.44 ms / 113 tokens ( 7.39 ms per token, 135.26 tokens per second) 0.54.301.779 I slot print_timing: id 3 | task 178 | eval time = 27.91 ms / 2 tokens ( 27.91 ms per token, 35.84 tokens per second) 0.54.301.779 I slot print_timing: id 3 | task 178 | total time = 863.35 ms / 115 tokens 0.54.301.779 I slot print_timing: id 3 | task 178 | graphs reused = 1 0.54.301.780 I slot print_timing: id 3 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.301.797 I slot release: id 3 | task 178 | stop processing: n_tokens = 114, truncated = 0 0.54.305.992 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.209 0.54.306.477 I slot launch_slot_: id 0 | task 184 | processing task, is_child = 0 0.54.307.237 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.263 (> 0.100 thold), f_keep = 0.263 0.54.307.271 I slot launch_slot_: id 3 | task 183 | processing task, is_child = 0 0.54.307.305 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.259 0.54.307.335 I slot launch_slot_: id 1 | task 182 | processing task, is_child = 0 0.54.307.354 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.192 0.54.307.498 I slot launch_slot_: id 2 | task 185 | processing task, is_child = 0 0.55.178.344 I slot print_timing: id 0 | task 184 | prompt eval time = 843.07 ms / 126 tokens ( 6.69 ms per token, 149.45 tokens per second) 0.55.178.346 I slot print_timing: id 0 | task 184 | eval time = 27.76 ms / 2 tokens ( 27.76 ms per token, 36.02 tokens per second) 0.55.178.347 I slot print_timing: id 0 | task 184 | total time = 870.84 ms / 128 tokens 0.55.178.347 I slot print_timing: id 0 | task 184 | graphs reused = 1 0.55.178.347 I slot print_timing: id 0 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.178.367 I slot release: id 0 | task 184 | stop processing: n_tokens = 127, truncated = 0 0.55.178.658 I slot print_timing: id 1 | task 182 | prompt eval time = 843.40 ms / 153 tokens ( 5.51 ms per token, 181.41 tokens per second) 0.55.178.662 I slot print_timing: id 1 | task 182 | eval time = 27.74 ms / 2 tokens ( 27.74 ms per token, 36.05 tokens per second) 0.55.178.662 I slot print_timing: id 1 | task 182 | total time = 871.14 ms / 155 tokens 0.55.178.663 I slot print_timing: id 1 | task 182 | graphs reused = 1 0.55.178.663 I slot print_timing: id 1 | task 182 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.178.680 I slot release: id 1 | task 182 | stop processing: n_tokens = 154, truncated = 0 0.55.178.963 I slot print_timing: id 2 | task 185 | prompt eval time = 843.68 ms / 131 tokens ( 6.44 ms per token, 155.27 tokens per second) 0.55.178.965 I slot print_timing: id 2 | task 185 | eval time = 27.75 ms / 2 tokens ( 27.75 ms per token, 36.03 tokens per second) 0.55.178.965 I slot print_timing: id 2 | task 185 | total time = 871.44 ms / 133 tokens 0.55.178.965 I slot print_timing: id 2 | task 185 | graphs reused = 1 0.55.178.965 I slot print_timing: id 2 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.178.979 I slot release: id 2 | task 185 | stop processing: n_tokens = 132, truncated = 0 0.55.179.285 I slot print_timing: id 3 | task 183 | prompt eval time = 844.01 ms / 114 tokens ( 7.40 ms per token, 135.07 tokens per second) 0.55.179.287 I slot print_timing: id 3 | task 183 | eval time = 27.73 ms / 2 tokens ( 27.73 ms per token, 36.06 tokens per second) 0.55.179.287 I slot print_timing: id 3 | task 183 | total time = 871.75 ms / 116 tokens 0.55.179.288 I slot print_timing: id 3 | task 183 | graphs reused = 1 0.55.179.288 I slot print_timing: id 3 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.179.298 I slot release: id 3 | task 183 | stop processing: n_tokens = 115, truncated = 0 0.55.183.362 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.261 0.55.183.569 I slot launch_slot_: id 3 | task 189 | processing task, is_child = 0 0.55.184.647 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.228 0.55.184.681 I slot launch_slot_: id 0 | task 190 | processing task, is_child = 0 0.55.184.716 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.227 0.55.184.746 I slot launch_slot_: id 2 | task 191 | processing task, is_child = 0 0.55.184.766 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.185 (> 0.100 thold), f_keep = 0.188 0.55.184.796 I slot launch_slot_: id 1 | task 192 | processing task, is_child = 0 0.56.161.229 I slot print_timing: id 0 | task 190 | prompt eval time = 948.49 ms / 170 tokens ( 5.58 ms per token, 179.23 tokens per second) 0.56.161.231 I slot print_timing: id 0 | task 190 | eval time = 27.94 ms / 2 tokens ( 27.94 ms per token, 35.79 tokens per second) 0.56.161.232 I slot print_timing: id 0 | task 190 | total time = 976.42 ms / 172 tokens 0.56.161.233 I slot print_timing: id 0 | task 190 | graphs reused = 1 0.56.161.233 I slot print_timing: id 0 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.161.257 I slot release: id 0 | task 190 | stop processing: n_tokens = 171, truncated = 0 0.56.161.530 I slot print_timing: id 1 | task 192 | prompt eval time = 948.77 ms / 157 tokens ( 6.04 ms per token, 165.48 tokens per second) 0.56.161.533 I slot print_timing: id 1 | task 192 | eval time = 27.95 ms / 2 tokens ( 27.95 ms per token, 35.78 tokens per second) 0.56.161.533 I slot print_timing: id 1 | task 192 | total time = 976.72 ms / 159 tokens 0.56.161.534 I slot print_timing: id 1 | task 192 | graphs reused = 1 0.56.161.534 I slot print_timing: id 1 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.161.549 I slot release: id 1 | task 192 | stop processing: n_tokens = 158, truncated = 0 0.56.161.823 I slot print_timing: id 2 | task 191 | prompt eval time = 949.06 ms / 130 tokens ( 7.30 ms per token, 136.98 tokens per second) 0.56.161.825 I slot print_timing: id 2 | task 191 | eval time = 27.93 ms / 2 tokens ( 27.93 ms per token, 35.80 tokens per second) 0.56.161.825 I slot print_timing: id 2 | task 191 | total time = 976.99 ms / 132 tokens 0.56.161.825 I slot print_timing: id 2 | task 191 | graphs reused = 1 0.56.161.826 I slot print_timing: id 2 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.161.840 I slot release: id 2 | task 191 | stop processing: n_tokens = 131, truncated = 0 0.56.162.131 I slot print_timing: id 3 | task 189 | prompt eval time = 949.38 ms / 119 tokens ( 7.98 ms per token, 125.34 tokens per second) 0.56.162.135 I slot print_timing: id 3 | task 189 | eval time = 27.91 ms / 2 tokens ( 27.91 ms per token, 35.84 tokens per second) 0.56.162.135 I slot print_timing: id 3 | task 189 | total time = 977.29 ms / 121 tokens 0.56.162.135 I slot print_timing: id 3 | task 189 | graphs reused = 1 0.56.162.136 I slot print_timing: id 3 | task 189 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.162.152 I slot release: id 3 | task 189 | stop processing: n_tokens = 120, truncated = 0 0.56.166.463 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.170 0.56.166.929 I slot launch_slot_: id 0 | task 196 | processing task, is_child = 0 0.56.168.011 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.190 0.56.168.047 I slot launch_slot_: id 1 | task 197 | processing task, is_child = 0 0.56.168.082 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.221 0.56.168.229 I slot launch_slot_: id 2 | task 198 | processing task, is_child = 0 0.56.168.247 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.159 (> 0.100 thold), f_keep = 0.242 0.56.168.278 I slot launch_slot_: id 3 | task 199 | processing task, is_child = 0 0.57.191.589 I slot print_timing: id 0 | task 196 | prompt eval time = 995.13 ms / 110 tokens ( 9.05 ms per token, 110.54 tokens per second) 0.57.191.591 I slot print_timing: id 0 | task 196 | eval time = 28.17 ms / 2 tokens ( 28.17 ms per token, 35.50 tokens per second) 0.57.191.591 I slot print_timing: id 0 | task 196 | total time = 1023.30 ms / 112 tokens 0.57.191.592 I slot print_timing: id 0 | task 196 | graphs reused = 1 0.57.191.592 I slot print_timing: id 0 | task 196 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.191.614 I slot release: id 0 | task 196 | stop processing: n_tokens = 111, truncated = 0 0.57.191.899 I slot print_timing: id 1 | task 197 | prompt eval time = 995.43 ms / 155 tokens ( 6.42 ms per token, 155.71 tokens per second) 0.57.191.901 I slot print_timing: id 1 | task 197 | eval time = 28.17 ms / 2 tokens ( 28.17 ms per token, 35.50 tokens per second) 0.57.191.902 I slot print_timing: id 1 | task 197 | total time = 1023.60 ms / 157 tokens 0.57.191.902 I slot print_timing: id 1 | task 197 | graphs reused = 1 0.57.191.902 I slot print_timing: id 1 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.191.917 I slot release: id 1 | task 197 | stop processing: n_tokens = 156, truncated = 0 0.57.192.184 I slot print_timing: id 2 | task 198 | prompt eval time = 995.72 ms / 135 tokens ( 7.38 ms per token, 135.58 tokens per second) 0.57.192.187 I slot print_timing: id 2 | task 198 | eval time = 28.16 ms / 2 tokens ( 28.16 ms per token, 35.52 tokens per second) 0.57.192.188 I slot print_timing: id 2 | task 198 | total time = 1023.88 ms / 137 tokens 0.57.192.188 I slot print_timing: id 2 | task 198 | graphs reused = 1 0.57.192.188 I slot print_timing: id 2 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.192.206 I slot release: id 2 | task 198 | stop processing: n_tokens = 136, truncated = 0 0.57.192.522 I slot print_timing: id 3 | task 199 | prompt eval time = 996.13 ms / 182 tokens ( 5.47 ms per token, 182.71 tokens per second) 0.57.192.524 I slot print_timing: id 3 | task 199 | eval time = 28.07 ms / 2 tokens ( 28.07 ms per token, 35.62 tokens per second) 0.57.192.524 I slot print_timing: id 3 | task 199 | total time = 1024.20 ms / 184 tokens 0.57.192.524 I slot print_timing: id 3 | task 199 | graphs reused = 1 0.57.192.525 I slot print_timing: id 3 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.192.541 I slot release: id 3 | task 199 | stop processing: n_tokens = 183, truncated = 0 0.57.196.368 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.261 0.57.196.606 I slot launch_slot_: id 0 | task 203 | processing task, is_child = 0 0.57.197.769 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.186 0.57.197.920 I slot launch_slot_: id 1 | task 204 | processing task, is_child = 0 0.57.197.955 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.213 0.57.197.986 I slot launch_slot_: id 2 | task 205 | processing task, is_child = 0 0.57.198.005 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.158 0.57.198.036 I slot launch_slot_: id 3 | task 206 | processing task, is_child = 0 0.58.130.457 I slot print_timing: id 0 | task 203 | prompt eval time = 904.11 ms / 136 tokens ( 6.65 ms per token, 150.42 tokens per second) 0.58.130.459 I slot print_timing: id 0 | task 203 | eval time = 28.30 ms / 2 tokens ( 28.30 ms per token, 35.33 tokens per second) 0.58.130.459 I slot print_timing: id 0 | task 203 | total time = 932.41 ms / 138 tokens 0.58.130.460 I slot print_timing: id 0 | task 203 | graphs reused = 1 0.58.130.460 I slot print_timing: id 0 | task 203 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.130.481 I slot release: id 0 | task 203 | stop processing: n_tokens = 137, truncated = 0 0.58.130.792 I slot print_timing: id 1 | task 204 | prompt eval time = 904.42 ms / 117 tokens ( 7.73 ms per token, 129.36 tokens per second) 0.58.130.796 I slot print_timing: id 1 | task 204 | eval time = 28.32 ms / 2 tokens ( 28.32 ms per token, 35.31 tokens per second) 0.58.130.797 I slot print_timing: id 1 | task 204 | total time = 932.74 ms / 119 tokens 0.58.130.797 I slot print_timing: id 1 | task 204 | graphs reused = 1 0.58.130.797 I slot print_timing: id 1 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.130.813 I slot release: id 1 | task 204 | stop processing: n_tokens = 118, truncated = 0 0.58.131.109 I slot print_timing: id 2 | task 205 | prompt eval time = 904.74 ms / 160 tokens ( 5.65 ms per token, 176.85 tokens per second) 0.58.131.113 I slot print_timing: id 2 | task 205 | eval time = 28.31 ms / 2 tokens ( 28.31 ms per token, 35.33 tokens per second) 0.58.131.114 I slot print_timing: id 2 | task 205 | total time = 933.05 ms / 162 tokens 0.58.131.114 I slot print_timing: id 2 | task 205 | graphs reused = 1 0.58.131.114 I slot print_timing: id 2 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.131.137 I slot release: id 2 | task 205 | stop processing: n_tokens = 161, truncated = 0 0.58.131.506 I slot print_timing: id 3 | task 206 | prompt eval time = 905.20 ms / 134 tokens ( 6.76 ms per token, 148.03 tokens per second) 0.58.131.508 I slot print_timing: id 3 | task 206 | eval time = 28.24 ms / 2 tokens ( 28.24 ms per token, 35.41 tokens per second) 0.58.131.509 I slot print_timing: id 3 | task 206 | total time = 933.43 ms / 136 tokens 0.58.131.509 I slot print_timing: id 3 | task 206 | graphs reused = 1 0.58.131.509 I slot print_timing: id 3 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.131.520 I slot release: id 3 | task 206 | stop processing: n_tokens = 135, truncated = 0 0.58.135.462 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.212 0.58.135.907 I slot launch_slot_: id 0 | task 210 | processing task, is_child = 0 0.58.136.943 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.254 0.58.137.109 I slot launch_slot_: id 1 | task 211 | processing task, is_child = 0 0.58.137.147 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.180 0.58.137.293 I slot launch_slot_: id 2 | task 212 | processing task, is_child = 0 0.58.137.312 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.215 0.58.137.344 I slot launch_slot_: id 3 | task 213 | processing task, is_child = 0 0.59.070.509 I slot print_timing: id 0 | task 210 | prompt eval time = 904.72 ms / 151 tokens ( 5.99 ms per token, 166.90 tokens per second) 0.59.070.516 I slot print_timing: id 0 | task 210 | eval time = 28.44 ms / 2 tokens ( 28.44 ms per token, 35.16 tokens per second) 0.59.070.516 I slot print_timing: id 0 | task 210 | total time = 933.16 ms / 153 tokens 0.59.070.516 I slot print_timing: id 0 | task 210 | graphs reused = 1 0.59.070.517 I slot print_timing: id 0 | task 210 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.070.539 I slot release: id 0 | task 210 | stop processing: n_tokens = 152, truncated = 0 0.59.070.824 I slot print_timing: id 1 | task 211 | prompt eval time = 905.01 ms / 118 tokens ( 7.67 ms per token, 130.39 tokens per second) 0.59.070.826 I slot print_timing: id 1 | task 211 | eval time = 28.45 ms / 2 tokens ( 28.45 ms per token, 35.15 tokens per second) 0.59.070.827 I slot print_timing: id 1 | task 211 | total time = 933.46 ms / 120 tokens 0.59.070.827 I slot print_timing: id 1 | task 211 | graphs reused = 1 0.59.070.827 I slot print_timing: id 1 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.070.840 I slot release: id 1 | task 211 | stop processing: n_tokens = 119, truncated = 0 0.59.071.109 I slot print_timing: id 2 | task 212 | prompt eval time = 905.31 ms / 124 tokens ( 7.30 ms per token, 136.97 tokens per second) 0.59.071.111 I slot print_timing: id 2 | task 212 | eval time = 28.42 ms / 2 tokens ( 28.42 ms per token, 35.18 tokens per second) 0.59.071.111 I slot print_timing: id 2 | task 212 | total time = 933.73 ms / 126 tokens 0.59.071.111 I slot print_timing: id 2 | task 212 | graphs reused = 1 0.59.071.112 I slot print_timing: id 2 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.071.131 I slot release: id 2 | task 212 | stop processing: n_tokens = 125, truncated = 0 0.59.071.412 I slot print_timing: id 3 | task 213 | prompt eval time = 905.64 ms / 156 tokens ( 5.81 ms per token, 172.25 tokens per second) 0.59.071.414 I slot print_timing: id 3 | task 213 | eval time = 28.39 ms / 2 tokens ( 28.39 ms per token, 35.22 tokens per second) 0.59.071.414 I slot print_timing: id 3 | task 213 | total time = 934.03 ms / 158 tokens 0.59.071.415 I slot print_timing: id 3 | task 213 | graphs reused = 1 0.59.071.415 I slot print_timing: id 3 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.071.432 I slot release: id 3 | task 213 | stop processing: n_tokens = 157, truncated = 0 0.59.075.524 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.191 0.59.076.041 I slot launch_slot_: id 0 | task 219 | processing task, is_child = 0 0.59.076.996 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.244 0.59.077.030 I slot launch_slot_: id 1 | task 218 | processing task, is_child = 0 0.59.077.065 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.232 0.59.077.096 I slot launch_slot_: id 2 | task 217 | processing task, is_child = 0 0.59.077.116 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.185 0.59.077.155 I slot launch_slot_: id 3 | task 220 | processing task, is_child = 0 1.00.022.069 I slot print_timing: id 0 | task 219 | prompt eval time = 916.99 ms / 149 tokens ( 6.15 ms per token, 162.49 tokens per second) 1.00.022.072 I slot print_timing: id 0 | task 219 | eval time = 27.91 ms / 2 tokens ( 27.91 ms per token, 35.82 tokens per second) 1.00.022.072 I slot print_timing: id 0 | task 219 | total time = 944.90 ms / 151 tokens 1.00.022.073 I slot print_timing: id 0 | task 219 | graphs reused = 1 1.00.022.073 I slot print_timing: id 0 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.022.094 I slot release: id 0 | task 219 | stop processing: n_tokens = 150, truncated = 0 1.00.022.371 I slot print_timing: id 1 | task 218 | prompt eval time = 917.28 ms / 154 tokens ( 5.96 ms per token, 167.89 tokens per second) 1.00.022.373 I slot print_timing: id 1 | task 218 | eval time = 27.91 ms / 2 tokens ( 27.91 ms per token, 35.83 tokens per second) 1.00.022.373 I slot print_timing: id 1 | task 218 | total time = 945.19 ms / 156 tokens 1.00.022.373 I slot print_timing: id 1 | task 218 | graphs reused = 1 1.00.022.374 I slot print_timing: id 1 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.022.390 I slot release: id 1 | task 218 | stop processing: n_tokens = 155, truncated = 0 1.00.022.661 I slot print_timing: id 2 | task 217 | prompt eval time = 917.59 ms / 162 tokens ( 5.66 ms per token, 176.55 tokens per second) 1.00.022.663 I slot print_timing: id 2 | task 217 | eval time = 27.89 ms / 2 tokens ( 27.89 ms per token, 35.86 tokens per second) 1.00.022.664 I slot print_timing: id 2 | task 217 | total time = 945.47 ms / 164 tokens 1.00.022.664 I slot print_timing: id 2 | task 217 | graphs reused = 1 1.00.022.665 I slot print_timing: id 2 | task 217 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.022.688 I slot release: id 2 | task 217 | stop processing: n_tokens = 163, truncated = 0 1.00.022.980 I slot print_timing: id 3 | task 220 | prompt eval time = 917.96 ms / 156 tokens ( 5.88 ms per token, 169.94 tokens per second) 1.00.022.982 I slot print_timing: id 3 | task 220 | eval time = 27.82 ms / 2 tokens ( 27.82 ms per token, 35.94 tokens per second) 1.00.022.982 I slot print_timing: id 3 | task 220 | total time = 945.78 ms / 158 tokens 1.00.022.982 I slot print_timing: id 3 | task 220 | graphs reused = 1 1.00.022.983 I slot print_timing: id 3 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.022.994 I slot release: id 3 | task 220 | stop processing: n_tokens = 157, truncated = 0 1.00.026.540 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.193 1.00.027.076 I slot launch_slot_: id 0 | task 224 | processing task, is_child = 0 1.00.028.210 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.187 1.00.028.252 I slot launch_slot_: id 1 | task 225 | processing task, is_child = 0 1.00.028.288 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.178 1.00.028.319 I slot launch_slot_: id 2 | task 226 | processing task, is_child = 0 1.00.028.339 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.185 1.00.028.369 I slot launch_slot_: id 3 | task 227 | processing task, is_child = 0 1.00.877.050 I slot print_timing: id 0 | task 224 | prompt eval time = 820.43 ms / 103 tokens ( 7.97 ms per token, 125.54 tokens per second) 1.00.877.052 I slot print_timing: id 0 | task 224 | eval time = 28.25 ms / 2 tokens ( 28.25 ms per token, 35.40 tokens per second) 1.00.877.053 I slot print_timing: id 0 | task 224 | total time = 848.67 ms / 105 tokens 1.00.877.053 I slot print_timing: id 0 | task 224 | graphs reused = 1 1.00.877.053 I slot print_timing: id 0 | task 224 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.877.071 I slot release: id 0 | task 224 | stop processing: n_tokens = 104, truncated = 0 1.00.877.432 I slot print_timing: id 1 | task 225 | prompt eval time = 820.78 ms / 186 tokens ( 4.41 ms per token, 226.61 tokens per second) 1.00.877.434 I slot print_timing: id 1 | task 225 | eval time = 28.27 ms / 2 tokens ( 28.27 ms per token, 35.38 tokens per second) 1.00.877.435 I slot print_timing: id 1 | task 225 | total time = 849.05 ms / 188 tokens 1.00.877.435 I slot print_timing: id 1 | task 225 | graphs reused = 1 1.00.877.435 I slot print_timing: id 1 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.877.451 I slot release: id 1 | task 225 | stop processing: n_tokens = 187, truncated = 0 1.00.877.829 I slot print_timing: id 2 | task 226 | prompt eval time = 821.16 ms / 108 tokens ( 7.60 ms per token, 131.52 tokens per second) 1.00.877.830 I slot print_timing: id 2 | task 226 | eval time = 28.27 ms / 2 tokens ( 28.27 ms per token, 35.38 tokens per second) 1.00.877.830 I slot print_timing: id 2 | task 226 | total time = 849.43 ms / 110 tokens 1.00.877.831 I slot print_timing: id 2 | task 226 | graphs reused = 1 1.00.877.831 I slot print_timing: id 2 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.877.845 I slot release: id 2 | task 226 | stop processing: n_tokens = 109, truncated = 0 1.00.878.172 I slot print_timing: id 3 | task 227 | prompt eval time = 821.56 ms / 115 tokens ( 7.14 ms per token, 139.98 tokens per second) 1.00.878.174 I slot print_timing: id 3 | task 227 | eval time = 28.20 ms / 2 tokens ( 28.20 ms per token, 35.46 tokens per second) 1.00.878.174 I slot print_timing: id 3 | task 227 | total time = 849.76 ms / 117 tokens 1.00.878.175 I slot print_timing: id 3 | task 227 | graphs reused = 1 1.00.878.175 I slot print_timing: id 3 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.878.193 I slot release: id 3 | task 227 | stop processing: n_tokens = 116, truncated = 0 1.00.881.862 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.288 1.00.882.081 I slot launch_slot_: id 0 | task 231 | processing task, is_child = 0 1.00.882.874 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.155 1.00.882.932 I slot launch_slot_: id 1 | task 232 | processing task, is_child = 0 1.00.882.968 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.266 1.00.883.000 I slot launch_slot_: id 2 | task 233 | processing task, is_child = 0 1.00.883.018 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.250 1.00.883.047 I slot launch_slot_: id 3 | task 234 | processing task, is_child = 0 1.01.780.310 I slot print_timing: id 0 | task 231 | prompt eval time = 869.12 ms / 113 tokens ( 7.69 ms per token, 130.02 tokens per second) 1.01.780.313 I slot print_timing: id 0 | task 231 | eval time = 28.14 ms / 2 tokens ( 28.14 ms per token, 35.54 tokens per second) 1.01.780.313 I slot print_timing: id 0 | task 231 | total time = 897.26 ms / 115 tokens 1.01.780.314 I slot print_timing: id 0 | task 231 | graphs reused = 1 1.01.780.314 I slot print_timing: id 0 | task 231 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.780.337 I slot release: id 0 | task 231 | stop processing: n_tokens = 114, truncated = 0 1.01.780.612 I slot print_timing: id 1 | task 232 | prompt eval time = 869.40 ms / 122 tokens ( 7.13 ms per token, 140.33 tokens per second) 1.01.780.614 I slot print_timing: id 1 | task 232 | eval time = 28.15 ms / 2 tokens ( 28.15 ms per token, 35.53 tokens per second) 1.01.780.614 I slot print_timing: id 1 | task 232 | total time = 897.54 ms / 124 tokens 1.01.780.615 I slot print_timing: id 1 | task 232 | graphs reused = 1 1.01.780.615 I slot print_timing: id 1 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.780.630 I slot release: id 1 | task 232 | stop processing: n_tokens = 123, truncated = 0 1.01.780.900 I slot print_timing: id 2 | task 233 | prompt eval time = 869.69 ms / 128 tokens ( 6.79 ms per token, 147.18 tokens per second) 1.01.780.902 I slot print_timing: id 2 | task 233 | eval time = 28.12 ms / 2 tokens ( 28.12 ms per token, 35.56 tokens per second) 1.01.780.903 I slot print_timing: id 2 | task 233 | total time = 897.81 ms / 130 tokens 1.01.780.903 I slot print_timing: id 2 | task 233 | graphs reused = 1 1.01.780.903 I slot print_timing: id 2 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.780.914 I slot release: id 2 | task 233 | stop processing: n_tokens = 129, truncated = 0 1.01.781.207 I slot print_timing: id 3 | task 234 | prompt eval time = 870.15 ms / 163 tokens ( 5.34 ms per token, 187.32 tokens per second) 1.01.781.209 I slot print_timing: id 3 | task 234 | eval time = 27.96 ms / 2 tokens ( 27.96 ms per token, 35.77 tokens per second) 1.01.781.210 I slot print_timing: id 3 | task 234 | total time = 898.11 ms / 165 tokens 1.01.781.210 I slot print_timing: id 3 | task 234 | graphs reused = 1 1.01.781.210 I slot print_timing: id 3 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.781.222 I slot release: id 3 | task 234 | stop processing: n_tokens = 164, truncated = 0 1.01.785.583 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.263 1.01.786.091 I slot launch_slot_: id 0 | task 238 | processing task, is_child = 0 1.01.787.243 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.236 1.01.787.277 I slot launch_slot_: id 1 | task 240 | processing task, is_child = 0 1.01.787.312 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.240 (> 0.100 thold), f_keep = 0.225 1.01.787.344 I slot launch_slot_: id 2 | task 239 | processing task, is_child = 0 1.01.787.364 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.177 1.01.787.518 I slot launch_slot_: id 3 | task 241 | processing task, is_child = 0 1.02.575.363 I slot print_timing: id 0 | task 238 | prompt eval time = 759.82 ms / 136 tokens ( 5.59 ms per token, 178.99 tokens per second) 1.02.575.365 I slot print_timing: id 0 | task 238 | eval time = 28.02 ms / 2 tokens ( 28.02 ms per token, 35.69 tokens per second) 1.02.575.366 I slot print_timing: id 0 | task 238 | total time = 787.84 ms / 138 tokens 1.02.575.366 I slot print_timing: id 0 | task 238 | graphs reused = 1 1.02.575.367 I slot print_timing: id 0 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.575.386 I slot release: id 0 | task 238 | stop processing: n_tokens = 137, truncated = 0 1.02.575.670 I slot print_timing: id 1 | task 240 | prompt eval time = 760.11 ms / 127 tokens ( 5.99 ms per token, 167.08 tokens per second) 1.02.575.672 I slot print_timing: id 1 | task 240 | eval time = 28.02 ms / 2 tokens ( 28.02 ms per token, 35.68 tokens per second) 1.02.575.672 I slot print_timing: id 1 | task 240 | total time = 788.14 ms / 129 tokens 1.02.575.672 I slot print_timing: id 1 | task 240 | graphs reused = 1 1.02.575.673 I slot print_timing: id 1 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.575.685 I slot release: id 1 | task 240 | stop processing: n_tokens = 128, truncated = 0 1.02.575.958 I slot print_timing: id 2 | task 239 | prompt eval time = 760.38 ms / 121 tokens ( 6.28 ms per token, 159.13 tokens per second) 1.02.575.960 I slot print_timing: id 2 | task 239 | eval time = 28.03 ms / 2 tokens ( 28.03 ms per token, 35.67 tokens per second) 1.02.575.960 I slot print_timing: id 2 | task 239 | total time = 788.41 ms / 123 tokens 1.02.575.960 I slot print_timing: id 2 | task 239 | graphs reused = 1 1.02.575.961 I slot print_timing: id 2 | task 239 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.575.971 I slot release: id 2 | task 239 | stop processing: n_tokens = 122, truncated = 0 1.02.576.276 I slot print_timing: id 3 | task 241 | prompt eval time = 760.70 ms / 139 tokens ( 5.47 ms per token, 182.73 tokens per second) 1.02.576.279 I slot print_timing: id 3 | task 241 | eval time = 28.03 ms / 2 tokens ( 28.03 ms per token, 35.68 tokens per second) 1.02.576.279 I slot print_timing: id 3 | task 241 | total time = 788.72 ms / 141 tokens 1.02.576.279 I slot print_timing: id 3 | task 241 | graphs reused = 1 1.02.576.279 I slot print_timing: id 3 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.576.289 I slot release: id 3 | task 241 | stop processing: n_tokens = 140, truncated = 0 1.02.580.185 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.212 1.02.580.642 I slot launch_slot_: id 0 | task 245 | processing task, is_child = 0 1.02.581.749 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.227 1.02.581.784 I slot launch_slot_: id 1 | task 246 | processing task, is_child = 0 1.02.581.819 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.238 1.02.581.850 I slot launch_slot_: id 2 | task 248 | processing task, is_child = 0 1.02.581.870 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.207 1.02.582.017 I slot launch_slot_: id 3 | task 247 | processing task, is_child = 0 1.03.559.265 I slot print_timing: id 0 | task 245 | prompt eval time = 949.14 ms / 120 tokens ( 7.91 ms per token, 126.43 tokens per second) 1.03.559.268 I slot print_timing: id 0 | task 245 | eval time = 28.10 ms / 2 tokens ( 28.10 ms per token, 35.59 tokens per second) 1.03.559.268 I slot print_timing: id 0 | task 245 | total time = 977.24 ms / 122 tokens 1.03.559.268 I slot print_timing: id 0 | task 245 | graphs reused = 1 1.03.559.269 I slot print_timing: id 0 | task 245 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.559.289 I slot release: id 0 | task 245 | stop processing: n_tokens = 121, truncated = 0 1.03.559.562 I slot print_timing: id 1 | task 246 | prompt eval time = 949.45 ms / 170 tokens ( 5.58 ms per token, 179.05 tokens per second) 1.03.559.564 I slot print_timing: id 1 | task 246 | eval time = 28.08 ms / 2 tokens ( 28.08 ms per token, 35.61 tokens per second) 1.03.559.565 I slot print_timing: id 1 | task 246 | total time = 977.53 ms / 172 tokens 1.03.559.565 I slot print_timing: id 1 | task 246 | graphs reused = 1 1.03.559.565 I slot print_timing: id 1 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.559.581 I slot release: id 1 | task 246 | stop processing: n_tokens = 171, truncated = 0 1.03.559.845 I slot print_timing: id 2 | task 248 | prompt eval time = 949.74 ms / 142 tokens ( 6.69 ms per token, 149.52 tokens per second) 1.03.559.847 I slot print_timing: id 2 | task 248 | eval time = 28.06 ms / 2 tokens ( 28.06 ms per token, 35.63 tokens per second) 1.03.559.848 I slot print_timing: id 2 | task 248 | total time = 977.80 ms / 144 tokens 1.03.559.848 I slot print_timing: id 2 | task 248 | graphs reused = 1 1.03.559.848 I slot print_timing: id 2 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.559.860 I slot release: id 2 | task 248 | stop processing: n_tokens = 143, truncated = 0 1.03.560.173 I slot print_timing: id 3 | task 247 | prompt eval time = 950.10 ms / 159 tokens ( 5.98 ms per token, 167.35 tokens per second) 1.03.560.175 I slot print_timing: id 3 | task 247 | eval time = 28.02 ms / 2 tokens ( 28.02 ms per token, 35.69 tokens per second) 1.03.560.175 I slot print_timing: id 3 | task 247 | total time = 978.12 ms / 161 tokens 1.03.560.175 I slot print_timing: id 3 | task 247 | graphs reused = 1 1.03.560.176 I slot print_timing: id 3 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.560.188 I slot release: id 3 | task 247 | stop processing: n_tokens = 160, truncated = 0 1.03.564.019 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.256 1.03.564.446 I slot launch_slot_: id 0 | task 252 | processing task, is_child = 0 1.03.565.575 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.170 1.03.565.914 I slot launch_slot_: id 1 | task 253 | processing task, is_child = 0 1.03.565.954 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.203 1.03.565.985 I slot launch_slot_: id 2 | task 254 | processing task, is_child = 0 1.03.566.004 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.181 1.03.566.037 I slot launch_slot_: id 3 | task 255 | processing task, is_child = 0 1.04.642.001 I slot print_timing: id 0 | task 252 | prompt eval time = 1047.73 ms / 184 tokens ( 5.69 ms per token, 175.62 tokens per second) 1.04.642.003 I slot print_timing: id 0 | task 252 | eval time = 28.23 ms / 2 tokens ( 28.23 ms per token, 35.43 tokens per second) 1.04.642.004 I slot print_timing: id 0 | task 252 | total time = 1075.96 ms / 186 tokens 1.04.642.005 I slot print_timing: id 0 | task 252 | graphs reused = 1 1.04.642.005 I slot print_timing: id 0 | task 252 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.642.027 I slot release: id 0 | task 252 | stop processing: n_tokens = 185, truncated = 0 1.04.642.311 I slot print_timing: id 1 | task 253 | prompt eval time = 1048.02 ms / 134 tokens ( 7.82 ms per token, 127.86 tokens per second) 1.04.642.315 I slot print_timing: id 1 | task 253 | eval time = 28.23 ms / 2 tokens ( 28.23 ms per token, 35.42 tokens per second) 1.04.642.316 I slot print_timing: id 1 | task 253 | total time = 1076.25 ms / 136 tokens 1.04.642.316 I slot print_timing: id 1 | task 253 | graphs reused = 1 1.04.642.316 I slot print_timing: id 1 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.642.329 I slot release: id 1 | task 253 | stop processing: n_tokens = 135, truncated = 0 1.04.642.599 I slot print_timing: id 2 | task 254 | prompt eval time = 1048.31 ms / 103 tokens ( 10.18 ms per token, 98.25 tokens per second) 1.04.642.602 I slot print_timing: id 2 | task 254 | eval time = 28.22 ms / 2 tokens ( 28.22 ms per token, 35.44 tokens per second) 1.04.642.603 I slot print_timing: id 2 | task 254 | total time = 1076.53 ms / 105 tokens 1.04.642.603 I slot print_timing: id 2 | task 254 | graphs reused = 1 1.04.642.603 I slot print_timing: id 2 | task 254 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.642.614 I slot release: id 2 | task 254 | stop processing: n_tokens = 104, truncated = 0 1.04.642.901 I slot print_timing: id 3 | task 255 | prompt eval time = 1048.80 ms / 158 tokens ( 6.64 ms per token, 150.65 tokens per second) 1.04.642.903 I slot print_timing: id 3 | task 255 | eval time = 28.02 ms / 2 tokens ( 28.02 ms per token, 35.69 tokens per second) 1.04.642.904 I slot print_timing: id 3 | task 255 | total time = 1076.82 ms / 160 tokens 1.04.642.904 I slot print_timing: id 3 | task 255 | graphs reused = 1 1.04.642.904 I slot print_timing: id 3 | task 255 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.642.922 I slot release: id 3 | task 255 | stop processing: n_tokens = 159, truncated = 0 1.04.646.334 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.157 1.04.646.835 I slot launch_slot_: id 0 | task 260 | processing task, is_child = 0 1.04.647.785 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.215 1.04.647.826 I slot launch_slot_: id 1 | task 259 | processing task, is_child = 0 1.05.125.475 I slot print_timing: id 0 | task 260 | prompt eval time = 438.61 ms / 145 tokens ( 3.02 ms per token, 330.59 tokens per second) 1.05.125.477 I slot print_timing: id 0 | task 260 | eval time = 38.99 ms / 2 tokens ( 38.99 ms per token, 25.64 tokens per second) 1.05.125.477 I slot print_timing: id 0 | task 260 | total time = 477.61 ms / 147 tokens 1.05.125.478 I slot print_timing: id 0 | task 260 | graphs reused = 1 1.05.125.478 I slot print_timing: id 0 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.125.496 I slot release: id 0 | task 260 | stop processing: n_tokens = 146, truncated = 0 1.05.125.811 I slot print_timing: id 1 | task 259 | prompt eval time = 438.92 ms / 125 tokens ( 3.51 ms per token, 284.79 tokens per second) 1.05.125.814 I slot print_timing: id 1 | task 259 | eval time = 39.01 ms / 2 tokens ( 39.01 ms per token, 25.63 tokens per second) 1.05.125.814 I slot print_timing: id 1 | task 259 | total time = 477.93 ms / 127 tokens 1.05.125.814 I slot print_timing: id 1 | task 259 | graphs reused = 1 1.05.125.815 I slot print_timing: id 1 | task 259 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.125.830 I slot release: id 1 | task 259 | stop processing: n_tokens = 126, truncated = 0 1.05.139.370 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 104, t_last = 347000024583 1.05.139.414 I slot launch_slot_: id 2 | task 265 | processing task, is_child = 0 1.05.140.138 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 159, t_last = 347000024891 1.05.140.190 I slot launch_slot_: id 3 | task 264 | processing task, is_child = 0 1.06.558.061 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 146, t_last = 347000507465 1.06.558.129 I slot launch_slot_: id 0 | task 267 | processing task, is_child = 0 1.06.558.152 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 126, t_last = 347000507799 1.06.558.184 I slot launch_slot_: id 1 | task 268 | processing task, is_child = 0 1.09.094.097 I slot print_timing: id 2 | task 265 | prompt processing, n_tokens = 1149, progress = 1.00, t = 3.91 s / 293.93 tokens per second 1.09.094.296 I slot print_timing: id 3 | task 264 | prompt processing, n_tokens = 878, progress = 0.77, t = 3.91 s / 224.60 tokens per second 1.10.615.973 I slot print_timing: id 0 | task 267 | prompt processing, n_tokens = 1155, progress = 1.00, t = 4.06 s / 284.66 tokens per second 1.10.616.172 I slot print_timing: id 1 | task 268 | prompt processing, n_tokens = 1144, progress = 1.00, t = 4.06 s / 281.95 tokens per second 1.10.616.347 I slot print_timing: id 3 | task 264 | prompt processing, n_tokens = 1129, progress = 1.00, t = 5.48 s / 206.20 tokens per second 1.13.633.152 I slot print_timing: id 2 | task 265 | n_gen = 102, tg = 33.47 t/s, tg_3s = 33.81 t/s 1.13.719.372 I slot print_timing: id 0 | task 267 | n_gen = 104, tg = 34.05 t/s, tg_3s = 34.38 t/s 1.13.719.814 I slot print_timing: id 1 | task 268 | n_gen = 104, tg = 34.05 t/s, tg_3s = 34.38 t/s 1.13.720.794 I slot print_timing: id 3 | task 264 | n_gen = 104, tg = 34.05 t/s, tg_3s = 34.38 t/s 1.16.658.168 I slot print_timing: id 2 | task 265 | n_gen = 203, tg = 33.43 t/s, tg_3s = 33.39 t/s 1.16.744.699 I slot print_timing: id 0 | task 267 | n_gen = 205, tg = 33.72 t/s, tg_3s = 33.38 t/s 1.16.745.151 I slot print_timing: id 1 | task 268 | n_gen = 205, tg = 33.72 t/s, tg_3s = 33.38 t/s 1.16.745.996 I slot print_timing: id 3 | task 264 | n_gen = 205, tg = 33.72 t/s, tg_3s = 33.39 t/s 1.19.671.349 I slot print_timing: id 2 | task 265 | n_gen = 304, tg = 33.46 t/s, tg_3s = 33.52 t/s 1.19.758.015 I slot print_timing: id 0 | task 267 | n_gen = 306, tg = 33.65 t/s, tg_3s = 33.52 t/s 1.19.758.410 I slot print_timing: id 1 | task 268 | n_gen = 306, tg = 33.65 t/s, tg_3s = 33.52 t/s 1.19.759.300 I slot print_timing: id 3 | task 264 | n_gen = 306, tg = 33.65 t/s, tg_3s = 33.52 t/s 1.21.938.794 I slot print_timing: id 1 | task 268 | prompt eval time = 4136.91 ms / 1148 tokens ( 3.60 ms per token, 277.50 tokens per second) 1.21.938.799 I slot print_timing: id 1 | task 268 | eval time = 11243.65 ms / 379 tokens ( 29.75 ms per token, 33.62 tokens per second) 1.21.938.800 I slot print_timing: id 1 | task 268 | total time = 15380.56 ms / 1527 tokens 1.21.938.801 I slot print_timing: id 1 | task 268 | graphs reused = 376 1.21.938.801 I slot print_timing: id 1 | task 268 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.938.896 I slot release: id 1 | task 268 | stop processing: n_tokens = 1526, truncated = 0 1.21.973.857 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.700 1.21.973.889 I slot launch_slot_: id 1 | task 651 | processing task, is_child = 0 1.22.703.985 I slot print_timing: id 2 | task 265 | n_gen = 383, tg = 31.60 t/s, tg_3s = 26.05 t/s 1.22.762.438 I slot print_timing: id 0 | task 267 | n_gen = 383, tg = 31.65 t/s, tg_3s = 25.63 t/s 1.22.763.341 I slot print_timing: id 3 | task 264 | n_gen = 383, tg = 31.66 t/s, tg_3s = 25.63 t/s 1.25.728.166 I slot print_timing: id 2 | task 265 | n_gen = 483, tg = 31.89 t/s, tg_3s = 33.07 t/s 1.25.786.532 I slot print_timing: id 0 | task 267 | n_gen = 484, tg = 32.00 t/s, tg_3s = 33.40 t/s 1.25.786.939 I slot print_timing: id 1 | task 651 | n_gen = 102, tg = 33.40 t/s, tg_3s = 33.73 t/s 1.25.787.965 I slot print_timing: id 3 | task 264 | n_gen = 484, tg = 32.00 t/s, tg_3s = 33.39 t/s 1.26.812.102 I slot print_timing: id 3 | task 264 | prompt eval time = 5555.77 ms / 1133 tokens ( 4.90 ms per token, 203.93 tokens per second) 1.26.812.110 I slot print_timing: id 3 | task 264 | eval time = 16116.08 ms / 518 tokens ( 31.17 ms per token, 32.08 tokens per second) 1.26.812.111 I slot print_timing: id 3 | task 264 | total time = 21671.85 ms / 1651 tokens 1.26.812.111 I slot print_timing: id 3 | task 264 | graphs reused = 510 1.26.812.112 I slot print_timing: id 3 | task 264 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.812.193 I slot release: id 3 | task 264 | stop processing: n_tokens = 1650, truncated = 0 1.26.838.891 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.647 1.26.838.916 I slot launch_slot_: id 3 | task 791 | processing task, is_child = 0 1.28.753.320 I slot print_timing: id 2 | task 265 | n_gen = 571, tg = 31.43 t/s, tg_3s = 29.09 t/s 1.28.811.191 I slot print_timing: id 0 | task 267 | n_gen = 572, tg = 31.52 t/s, tg_3s = 29.09 t/s 1.28.811.626 I slot print_timing: id 1 | task 651 | n_gen = 190, tg = 31.25 t/s, tg_3s = 29.09 t/s 1.29.351.529 I slot print_timing: id 2 | task 265 | prompt eval time = 5475.73 ms / 1153 tokens ( 4.75 ms per token, 210.57 tokens per second) 1.29.351.537 I slot print_timing: id 2 | task 265 | eval time = 18735.56 ms / 591 tokens ( 31.76 ms per token, 31.49 tokens per second) 1.29.351.538 I slot print_timing: id 2 | task 265 | total time = 24211.28 ms / 1744 tokens 1.29.351.538 I slot print_timing: id 2 | task 265 | graphs reused = 578 1.29.351.539 I slot print_timing: id 2 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.351.629 I slot release: id 2 | task 265 | stop processing: n_tokens = 1743, truncated = 0 1.29.386.232 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.613 1.29.386.264 I slot launch_slot_: id 2 | task 864 | processing task, is_child = 0 1.30.979.295 I slot print_timing: id 3 | task 791 | n_gen = 100, tg = 26.91 t/s, tg_3s = 27.18 t/s 1.31.824.738 I slot print_timing: id 0 | task 267 | n_gen = 648, tg = 30.62 t/s, tg_3s = 25.22 t/s 1.31.825.156 I slot print_timing: id 1 | task 651 | n_gen = 266, tg = 29.24 t/s, tg_3s = 25.22 t/s 1.33.205.817 I slot print_timing: id 2 | task 864 | n_gen = 101, tg = 33.17 t/s, tg_3s = 33.50 t/s 1.34.001.325 I slot print_timing: id 3 | task 791 | n_gen = 200, tg = 29.70 t/s, tg_3s = 33.09 t/s 1.34.833.000 I slot print_timing: id 0 | task 267 | n_gen = 748, tg = 30.95 t/s, tg_3s = 33.24 t/s 1.34.833.443 I slot print_timing: id 1 | task 651 | n_gen = 366, tg = 30.24 t/s, tg_3s = 33.24 t/s 1.35.400.340 I slot print_timing: id 0 | task 267 | prompt eval time = 4136.52 ms / 1159 tokens ( 3.57 ms per token, 280.19 tokens per second) 1.35.400.347 I slot print_timing: id 0 | task 267 | eval time = 24705.62 ms / 767 tokens ( 32.25 ms per token, 31.01 tokens per second) 1.35.400.348 I slot print_timing: id 0 | task 267 | total time = 28842.14 ms / 1926 tokens 1.35.400.349 I slot print_timing: id 0 | task 267 | graphs reused = 749 1.35.400.349 I slot print_timing: id 0 | task 267 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.400.437 I slot release: id 0 | task 267 | stop processing: n_tokens = 1925, truncated = 0 1.35.429.021 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.555 1.35.429.053 I slot launch_slot_: id 0 | task 1042 | processing task, is_child = 0 1.36.216.540 I slot print_timing: id 2 | task 864 | n_gen = 182, tg = 30.04 t/s, tg_3s = 26.90 t/s 1.37.019.117 I slot print_timing: id 3 | task 791 | n_gen = 282, tg = 28.91 t/s, tg_3s = 27.17 t/s 1.37.863.161 I slot print_timing: id 1 | task 651 | n_gen = 448, tg = 29.60 t/s, tg_3s = 27.07 t/s 1.39.094.392 I slot print_timing: id 0 | task 1042 | n_gen = 102, tg = 33.36 t/s, tg_3s = 33.69 t/s 1.39.242.861 I slot print_timing: id 2 | task 864 | n_gen = 283, tg = 31.15 t/s, tg_3s = 33.37 t/s 1.40.028.287 I slot print_timing: id 3 | task 791 | n_gen = 382, tg = 29.93 t/s, tg_3s = 33.23 t/s 1.40.875.601 I slot print_timing: id 1 | task 651 | n_gen = 548, tg = 30.20 t/s, tg_3s = 33.20 t/s 1.42.110.055 I slot print_timing: id 0 | task 1042 | n_gen = 202, tg = 33.26 t/s, tg_3s = 33.16 t/s 1.42.263.747 I slot print_timing: id 2 | task 864 | n_gen = 383, tg = 31.64 t/s, tg_3s = 33.10 t/s 1.42.687.773 I slot print_timing: id 1 | task 651 | prompt eval time = 788.87 ms / 539 tokens ( 1.46 ms per token, 683.26 tokens per second) 1.42.687.779 I slot print_timing: id 1 | task 651 | eval time = 19925.01 ms / 608 tokens ( 32.83 ms per token, 30.46 tokens per second) 1.42.687.780 I slot print_timing: id 1 | task 651 | total time = 20713.88 ms / 1147 tokens 1.42.687.780 I slot print_timing: id 1 | task 651 | graphs reused = 969 1.42.687.781 I slot print_timing: id 1 | task 651 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.687.864 I slot release: id 1 | task 651 | stop processing: n_tokens = 1778, truncated = 0 1.42.722.384 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.601 1.42.722.418 I slot launch_slot_: id 1 | task 1266 | processing task, is_child = 0 1.43.420.565 I slot print_timing: id 3 | task 791 | n_gen = 473, tg = 29.28 t/s, tg_3s = 26.83 t/s 1.45.137.012 I slot print_timing: id 0 | task 1042 | n_gen = 280, tg = 30.76 t/s, tg_3s = 25.77 t/s 1.45.290.319 I slot print_timing: id 2 | task 864 | n_gen = 461, tg = 30.47 t/s, tg_3s = 25.77 t/s 1.45.380.281 I slot print_timing: id 2 | task 864 | prompt eval time = 804.82 ms / 544 tokens ( 1.48 ms per token, 675.93 tokens per second) 1.45.380.287 I slot print_timing: id 2 | task 864 | eval time = 15189.19 ms / 464 tokens ( 32.81 ms per token, 30.48 tokens per second) 1.45.380.288 I slot print_timing: id 2 | task 864 | total time = 15994.01 ms / 1008 tokens 1.45.380.289 I slot print_timing: id 2 | task 864 | graphs reused = 1031 1.45.380.294 I slot print_timing: id 2 | task 864 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.380.391 I slot release: id 2 | task 864 | stop processing: n_tokens = 1644, truncated = 0 1.45.414.698 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.650 1.45.414.737 I slot launch_slot_: id 2 | task 1334 | processing task, is_child = 0 1.46.437.770 I slot print_timing: id 3 | task 791 | n_gen = 548, tg = 28.58 t/s, tg_3s = 24.86 t/s 1.47.187.427 I slot print_timing: id 1 | task 1266 | n_gen = 100, tg = 26.70 t/s, tg_3s = 26.97 t/s 1.47.935.802 I slot print_timing: id 0 | task 1042 | prompt eval time = 637.96 ms / 512 tokens ( 1.25 ms per token, 802.56 tokens per second) 1.47.935.807 I slot print_timing: id 0 | task 1042 | eval time = 11868.78 ms / 349 tokens ( 34.11 ms per token, 29.32 tokens per second) 1.47.935.808 I slot print_timing: id 0 | task 1042 | total time = 12506.74 ms / 861 tokens 1.47.935.809 I slot print_timing: id 0 | task 1042 | graphs reused = 1087 1.47.935.809 I slot print_timing: id 0 | task 1042 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.935.888 I slot release: id 0 | task 1042 | stop processing: n_tokens = 1503, truncated = 0 1.47.963.752 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.711 1.47.963.780 I slot launch_slot_: id 0 | task 1396 | processing task, is_child = 0 1.49.452.603 I slot print_timing: id 3 | task 791 | n_gen = 628, tg = 28.30 t/s, tg_3s = 26.54 t/s 1.49.808.037 I slot print_timing: id 2 | task 1334 | n_gen = 100, tg = 27.63 t/s, tg_3s = 27.91 t/s 1.50.200.810 I slot print_timing: id 1 | task 1266 | n_gen = 180, tg = 26.63 t/s, tg_3s = 26.55 t/s 1.51.682.107 I slot print_timing: id 0 | task 1396 | n_gen = 101, tg = 33.20 t/s, tg_3s = 33.53 t/s 1.52.469.197 I slot print_timing: id 3 | task 791 | n_gen = 728, tg = 28.88 t/s, tg_3s = 33.15 t/s 1.52.833.135 I slot print_timing: id 2 | task 1334 | n_gen = 200, tg = 30.12 t/s, tg_3s = 33.06 t/s 1.53.222.695 I slot print_timing: id 1 | task 1266 | n_gen = 280, tg = 28.64 t/s, tg_3s = 33.09 t/s 1.54.707.607 I slot print_timing: id 0 | task 1396 | n_gen = 202, tg = 33.29 t/s, tg_3s = 33.38 t/s 1.55.471.985 I slot print_timing: id 3 | task 791 | n_gen = 829, tg = 29.39 t/s, tg_3s = 33.64 t/s 1.55.854.184 I slot print_timing: id 2 | task 1334 | n_gen = 302, tg = 31.26 t/s, tg_3s = 33.76 t/s 1.56.248.287 I slot print_timing: id 1 | task 1266 | n_gen = 382, tg = 29.84 t/s, tg_3s = 33.71 t/s 1.57.609.048 I slot print_timing: id 1 | task 1266 | prompt eval time = 757.43 ms / 531 tokens ( 1.43 ms per token, 701.05 tokens per second) 1.57.609.052 I slot print_timing: id 1 | task 1266 | eval time = 14129.19 ms / 427 tokens ( 33.17 ms per token, 30.15 tokens per second) 1.57.609.053 I slot print_timing: id 1 | task 1266 | total time = 14886.62 ms / 958 tokens 1.57.609.053 I slot print_timing: id 1 | task 1266 | graphs reused = 1383 1.57.609.054 I slot print_timing: id 1 | task 1266 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.609.146 I slot release: id 1 | task 1266 | stop processing: n_tokens = 1612, truncated = 0 1.57.644.228 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.663 1.57.644.261 I slot launch_slot_: id 1 | task 1699 | processing task, is_child = 0 1.58.213.719 I slot print_timing: id 0 | task 1396 | n_gen = 301, tg = 31.43 t/s, tg_3s = 28.24 t/s 1.58.487.665 I slot print_timing: id 3 | task 791 | n_gen = 910, tg = 29.15 t/s, tg_3s = 26.86 t/s 1.58.878.239 I slot print_timing: id 2 | task 1334 | n_gen = 383, tg = 30.19 t/s, tg_3s = 26.79 t/s 2.01.214.521 I slot print_timing: id 0 | task 1396 | n_gen = 400, tg = 31.81 t/s, tg_3s = 32.99 t/s 2.01.274.910 I slot print_timing: id 1 | task 1699 | n_gen = 101, tg = 33.32 t/s, tg_3s = 33.65 t/s 2.01.488.266 I slot print_timing: id 3 | task 791 | n_gen = 1010, tg = 29.51 t/s, tg_3s = 33.33 t/s 2.01.879.788 I slot print_timing: id 2 | task 1334 | n_gen = 483, tg = 30.79 t/s, tg_3s = 33.32 t/s 2.01.910.098 I slot print_timing: id 3 | task 791 | prompt eval time = 461.38 ms / 302 tokens ( 1.53 ms per token, 654.56 tokens per second) 2.01.910.106 I slot print_timing: id 3 | task 791 | eval time = 34609.80 ms / 1024 tokens ( 33.83 ms per token, 29.56 tokens per second) 2.01.910.106 I slot print_timing: id 3 | task 791 | total time = 35071.18 ms / 1326 tokens 2.01.910.107 I slot print_timing: id 3 | task 791 | graphs reused = 1503 2.01.910.108 I slot print_timing: id 3 | task 791 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.910.200 I slot release: id 3 | task 791 | stop processing: n_tokens = 2203, truncated = 0 2.01.937.233 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.485 2.01.943.195 I slot launch_slot_: id 3 | task 1824 | processing task, is_child = 0 2.04.243.005 I slot print_timing: id 0 | task 1396 | n_gen = 488, tg = 31.27 t/s, tg_3s = 29.06 t/s 2.04.302.659 I slot print_timing: id 1 | task 1699 | n_gen = 189, tg = 31.18 t/s, tg_3s = 29.06 t/s 2.04.890.284 I slot print_timing: id 2 | task 1334 | n_gen = 571, tg = 30.54 t/s, tg_3s = 29.23 t/s 2.05.375.650 I slot print_timing: id 3 | task 1824 | n_gen = 101, tg = 33.30 t/s, tg_3s = 33.63 t/s 2.07.248.765 I slot print_timing: id 0 | task 1396 | n_gen = 588, tg = 31.60 t/s, tg_3s = 33.27 t/s 2.07.308.952 I slot print_timing: id 1 | task 1699 | n_gen = 289, tg = 31.87 t/s, tg_3s = 33.26 t/s 2.07.905.614 I slot print_timing: id 2 | task 1334 | n_gen = 671, tg = 30.90 t/s, tg_3s = 33.16 t/s 2.08.382.800 I slot print_timing: id 3 | task 1824 | n_gen = 201, tg = 33.28 t/s, tg_3s = 33.25 t/s 2.09.050.776 I slot print_timing: id 1 | task 1699 | prompt eval time = 629.36 ms / 475 tokens ( 1.32 ms per token, 754.74 tokens per second) 2.09.050.780 I slot print_timing: id 1 | task 1699 | eval time = 10777.15 ms / 348 tokens ( 31.06 ms per token, 32.20 tokens per second) 2.09.050.781 I slot print_timing: id 1 | task 1699 | total time = 11406.51 ms / 823 tokens 2.09.050.782 I slot print_timing: id 1 | task 1699 | graphs reused = 1724 2.09.050.782 I slot print_timing: id 1 | task 1699 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.050.866 I slot release: id 1 | task 1699 | stop processing: n_tokens = 1492, truncated = 0 2.09.085.275 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.716 2.09.085.314 I slot launch_slot_: id 1 | task 2051 | processing task, is_child = 0 2.09.770.375 I slot print_timing: id 2 | task 1334 | prompt eval time = 810.66 ms / 546 tokens ( 1.48 ms per token, 673.52 tokens per second) 2.09.770.379 I slot print_timing: id 2 | task 1334 | eval time = 23544.97 ms / 715 tokens ( 32.98 ms per token, 30.32 tokens per second) 2.09.770.379 I slot print_timing: id 2 | task 1334 | total time = 24355.63 ms / 1261 tokens 2.09.770.380 I slot print_timing: id 2 | task 1334 | graphs reused = 1725 2.09.770.380 I slot print_timing: id 2 | task 1334 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.770.452 I slot release: id 2 | task 1334 | stop processing: n_tokens = 1925, truncated = 0 2.09.803.621 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.555 2.09.803.651 I slot launch_slot_: id 2 | task 2057 | processing task, is_child = 0 2.10.370.870 I slot print_timing: id 0 | task 1396 | n_gen = 656, tg = 30.18 t/s, tg_3s = 21.78 t/s 2.11.390.450 I slot print_timing: id 3 | task 1824 | n_gen = 264, tg = 29.16 t/s, tg_3s = 20.95 t/s 2.12.964.899 I slot print_timing: id 0 | task 1396 | prompt eval time = 706.09 ms / 525 tokens ( 1.34 ms per token, 743.53 tokens per second) 2.12.964.903 I slot print_timing: id 0 | task 1396 | eval time = 24295.02 ms / 742 tokens ( 32.79 ms per token, 30.50 tokens per second) 2.12.964.904 I slot print_timing: id 0 | task 1396 | total time = 25001.11 ms / 1267 tokens 2.12.964.905 I slot print_timing: id 0 | task 1396 | graphs reused = 1809 2.12.964.905 I slot print_timing: id 0 | task 1396 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.964.998 I slot release: id 0 | task 1396 | stop processing: n_tokens = 1909, truncated = 0 2.12.993.024 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.559 2.12.993.051 I slot launch_slot_: id 0 | task 2146 | processing task, is_child = 0 2.13.920.495 I slot print_timing: id 1 | task 2051 | n_gen = 100, tg = 23.51 t/s, tg_3s = 23.75 t/s 2.14.072.415 I slot print_timing: id 2 | task 2057 | n_gen = 100, tg = 27.23 t/s, tg_3s = 27.51 t/s 2.14.405.281 I slot print_timing: id 3 | task 1824 | n_gen = 342, tg = 28.34 t/s, tg_3s = 25.87 t/s 2.16.787.716 I slot print_timing: id 0 | task 2146 | n_gen = 101, tg = 33.04 t/s, tg_3s = 33.37 t/s 2.16.934.880 I slot print_timing: id 1 | task 2051 | n_gen = 200, tg = 27.54 t/s, tg_3s = 33.17 t/s 2.17.085.563 I slot print_timing: id 2 | task 2057 | n_gen = 200, tg = 29.93 t/s, tg_3s = 33.19 t/s 2.17.411.471 I slot print_timing: id 3 | task 1824 | n_gen = 442, tg = 29.32 t/s, tg_3s = 33.26 t/s 2.19.798.705 I slot print_timing: id 0 | task 2146 | n_gen = 201, tg = 33.13 t/s, tg_3s = 33.21 t/s 2.19.946.840 I slot print_timing: id 1 | task 2051 | n_gen = 300, tg = 29.21 t/s, tg_3s = 33.20 t/s 2.20.098.350 I slot print_timing: id 2 | task 2057 | n_gen = 300, tg = 30.95 t/s, tg_3s = 33.19 t/s 2.20.428.235 I slot print_timing: id 3 | task 1824 | n_gen = 542, tg = 29.96 t/s, tg_3s = 33.15 t/s 2.22.820.801 I slot print_timing: id 0 | task 2146 | n_gen = 302, tg = 33.22 t/s, tg_3s = 33.42 t/s 2.22.972.369 I slot print_timing: id 1 | task 2051 | n_gen = 401, tg = 30.16 t/s, tg_3s = 33.38 t/s 2.23.124.283 I slot print_timing: id 2 | task 2057 | n_gen = 401, tg = 31.53 t/s, tg_3s = 33.38 t/s 2.23.454.081 I slot print_timing: id 3 | task 1824 | n_gen = 643, tg = 30.45 t/s, tg_3s = 33.38 t/s 2.23.603.974 I slot print_timing: id 2 | task 2057 | prompt eval time = 633.70 ms / 471 tokens ( 1.35 ms per token, 743.26 tokens per second) 2.23.603.978 I slot print_timing: id 2 | task 2057 | eval time = 13166.62 ms / 417 tokens ( 31.65 ms per token, 31.60 tokens per second) 2.23.603.979 I slot print_timing: id 2 | task 2057 | total time = 13800.31 ms / 888 tokens 2.23.603.980 I slot print_timing: id 2 | task 2057 | graphs reused = 2135 2.23.603.980 I slot print_timing: id 2 | task 2057 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.604.076 I slot release: id 2 | task 2057 | stop processing: n_tokens = 1582, truncated = 0 2.23.637.674 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.675 2.23.637.703 I slot launch_slot_: id 2 | task 2478 | processing task, is_child = 0 2.24.983.074 I slot print_timing: id 1 | task 2051 | prompt eval time = 624.38 ms / 467 tokens ( 1.34 ms per token, 747.94 tokens per second) 2.24.983.080 I slot print_timing: id 1 | task 2051 | eval time = 15273.37 ms / 450 tokens ( 34.02 ms per token, 29.40 tokens per second) 2.24.983.081 I slot print_timing: id 1 | task 2051 | total time = 15897.75 ms / 917 tokens 2.24.983.082 I slot print_timing: id 1 | task 2051 | graphs reused = 2159 2.24.983.082 I slot print_timing: id 1 | task 2051 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.983.174 I slot release: id 1 | task 2051 | stop processing: n_tokens = 1586, truncated = 0 2.25.018.143 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.673 2.25.018.179 I slot launch_slot_: id 1 | task 2507 | processing task, is_child = 0 2.25.851.091 I slot print_timing: id 0 | task 2146 | n_gen = 365, tg = 30.11 t/s, tg_3s = 20.79 t/s 2.26.455.588 I slot print_timing: id 3 | task 1824 | n_gen = 705, tg = 29.23 t/s, tg_3s = 20.66 t/s 2.27.786.307 I slot print_timing: id 2 | task 2478 | n_gen = 100, tg = 27.81 t/s, tg_3s = 28.09 t/s 2.28.683.137 I slot print_timing: id 1 | task 2507 | n_gen = 102, tg = 33.54 t/s, tg_3s = 33.87 t/s 2.28.862.155 I slot print_timing: id 0 | task 2146 | n_gen = 466, tg = 30.79 t/s, tg_3s = 33.54 t/s 2.29.460.934 I slot print_timing: id 3 | task 1824 | n_gen = 806, tg = 29.72 t/s, tg_3s = 33.61 t/s 2.30.805.369 I slot print_timing: id 2 | task 2478 | n_gen = 201, tg = 30.40 t/s, tg_3s = 33.45 t/s 2.31.707.128 I slot print_timing: id 1 | task 2507 | n_gen = 203, tg = 33.47 t/s, tg_3s = 33.40 t/s 2.31.887.185 I slot print_timing: id 0 | task 2146 | n_gen = 567, tg = 31.23 t/s, tg_3s = 33.39 t/s 2.32.488.090 I slot print_timing: id 3 | task 1824 | n_gen = 907, tg = 30.08 t/s, tg_3s = 33.36 t/s 2.33.832.145 I slot print_timing: id 2 | task 2478 | n_gen = 302, tg = 31.34 t/s, tg_3s = 33.37 t/s 2.34.734.092 I slot print_timing: id 1 | task 2507 | n_gen = 304, tg = 33.44 t/s, tg_3s = 33.37 t/s 2.34.917.565 I slot print_timing: id 0 | task 2146 | n_gen = 668, tg = 31.53 t/s, tg_3s = 33.33 t/s 2.35.497.650 I slot print_timing: id 3 | task 1824 | n_gen = 1007, tg = 30.37 t/s, tg_3s = 33.23 t/s 2.36.011.956 I slot print_timing: id 3 | task 1824 | prompt eval time = 429.31 ms / 265 tokens ( 1.62 ms per token, 617.27 tokens per second) 2.36.011.963 I slot print_timing: id 3 | task 1824 | eval time = 33639.44 ms / 1024 tokens ( 32.88 ms per token, 30.41 tokens per second) 2.36.011.964 I slot print_timing: id 3 | task 1824 | total time = 34068.75 ms / 1289 tokens 2.36.011.965 I slot print_timing: id 3 | task 1824 | graphs reused = 2502 2.36.011.965 I slot print_timing: id 3 | task 1824 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.012.050 I slot release: id 3 | task 1824 | stop processing: n_tokens = 2166, truncated = 0 2.36.038.263 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.493 2.36.043.617 I slot launch_slot_: id 3 | task 2856 | processing task, is_child = 0 2.36.859.681 I slot print_timing: id 2 | task 2478 | n_gen = 390, tg = 30.79 t/s, tg_3s = 29.07 t/s 2.37.734.379 I slot print_timing: id 1 | task 2507 | n_gen = 391, tg = 32.33 t/s, tg_3s = 29.00 t/s 2.37.948.108 I slot print_timing: id 0 | task 2146 | n_gen = 756, tg = 31.22 t/s, tg_3s = 29.04 t/s 2.38.994.338 I slot print_timing: id 0 | task 2146 | prompt eval time = 768.26 ms / 539 tokens ( 1.43 ms per token, 701.58 tokens per second) 2.38.994.343 I slot print_timing: id 0 | task 2146 | eval time = 25233.02 ms / 791 tokens ( 31.94 ms per token, 31.31 tokens per second) 2.38.994.344 I slot print_timing: id 0 | task 2146 | total time = 26001.28 ms / 1330 tokens 2.38.994.345 I slot print_timing: id 0 | task 2146 | graphs reused = 2585 2.38.994.345 I slot print_timing: id 0 | task 2146 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.994.425 I slot release: id 0 | task 2146 | stop processing: n_tokens = 1981, truncated = 0 2.39.022.413 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.539 2.39.022.444 I slot launch_slot_: id 0 | task 2944 | processing task, is_child = 0 2.39.889.317 I slot print_timing: id 2 | task 2478 | n_gen = 473, tg = 30.14 t/s, tg_3s = 27.40 t/s 2.39.979.833 I slot print_timing: id 3 | task 2856 | n_gen = 100, tg = 28.21 t/s, tg_3s = 28.50 t/s 2.40.758.435 I slot print_timing: id 1 | task 2507 | n_gen = 474, tg = 31.35 t/s, tg_3s = 27.45 t/s 2.42.634.812 I slot print_timing: id 0 | task 2944 | n_gen = 102, tg = 33.44 t/s, tg_3s = 33.77 t/s 2.42.907.141 I slot print_timing: id 2 | task 2478 | n_gen = 574, tg = 30.67 t/s, tg_3s = 33.47 t/s 2.42.998.580 I slot print_timing: id 3 | task 2856 | n_gen = 201, tg = 30.64 t/s, tg_3s = 33.46 t/s 2.43.773.461 I slot print_timing: id 1 | task 2507 | n_gen = 575, tg = 31.71 t/s, tg_3s = 33.50 t/s 2.45.658.003 I slot print_timing: id 0 | task 2944 | n_gen = 203, tg = 33.42 t/s, tg_3s = 33.41 t/s 2.45.926.670 I slot print_timing: id 2 | task 2478 | n_gen = 675, tg = 31.06 t/s, tg_3s = 33.45 t/s 2.46.017.561 I slot print_timing: id 3 | task 2856 | n_gen = 302, tg = 31.53 t/s, tg_3s = 33.45 t/s 2.46.047.193 I slot print_timing: id 1 | task 2507 | prompt eval time = 653.56 ms / 500 tokens ( 1.31 ms per token, 765.04 tokens per second) 2.46.047.200 I slot print_timing: id 1 | task 2507 | eval time = 20375.44 ms / 651 tokens ( 31.35 ms per token, 31.90 tokens per second) 2.46.047.201 I slot print_timing: id 1 | task 2507 | total time = 21029.01 ms / 1151 tokens 2.46.047.201 I slot print_timing: id 1 | task 2507 | graphs reused = 2799 2.46.047.202 I slot print_timing: id 1 | task 2507 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.047.290 I slot release: id 1 | task 2507 | stop processing: n_tokens = 1820, truncated = 0 2.46.082.271 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.587 2.46.082.310 I slot launch_slot_: id 1 | task 3163 | processing task, is_child = 0 2.47.519.423 I slot print_timing: id 0 | task 2944 | prompt eval time = 592.03 ms / 453 tokens ( 1.31 ms per token, 765.16 tokens per second) 2.47.519.426 I slot print_timing: id 0 | task 2944 | eval time = 7904.94 ms / 246 tokens ( 32.27 ms per token, 30.99 tokens per second) 2.47.519.427 I slot print_timing: id 0 | task 2944 | total time = 8496.97 ms / 699 tokens 2.47.519.427 I slot print_timing: id 0 | task 2944 | graphs reused = 2825 2.47.519.428 I slot print_timing: id 0 | task 2944 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.519.509 I slot release: id 0 | task 2944 | stop processing: n_tokens = 1373, truncated = 0 2.47.547.704 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.778 2.47.547.737 I slot launch_slot_: id 0 | task 3194 | processing task, is_child = 0 2.48.938.713 I slot print_timing: id 2 | task 2478 | n_gen = 738, tg = 29.82 t/s, tg_3s = 20.92 t/s 2.49.027.505 I slot print_timing: id 3 | task 2856 | n_gen = 365, tg = 28.99 t/s, tg_3s = 20.93 t/s 2.50.231.555 I slot print_timing: id 1 | task 3163 | n_gen = 100, tg = 28.11 t/s, tg_3s = 28.40 t/s 2.51.154.242 I slot print_timing: id 0 | task 3194 | n_gen = 101, tg = 33.25 t/s, tg_3s = 33.59 t/s 2.51.963.690 I slot print_timing: id 2 | task 2478 | n_gen = 839, tg = 30.21 t/s, tg_3s = 33.39 t/s 2.52.053.572 I slot print_timing: id 3 | task 2856 | n_gen = 466, tg = 29.84 t/s, tg_3s = 33.38 t/s 2.53.260.131 I slot print_timing: id 1 | task 3163 | n_gen = 201, tg = 30.53 t/s, tg_3s = 33.35 t/s 2.54.155.035 I slot print_timing: id 0 | task 3194 | n_gen = 201, tg = 33.29 t/s, tg_3s = 33.32 t/s 2.54.397.295 I slot print_timing: id 2 | task 2478 | prompt eval time = 588.78 ms / 433 tokens ( 1.36 ms per token, 735.42 tokens per second) 2.54.397.301 I slot print_timing: id 2 | task 2478 | eval time = 30170.81 ms / 920 tokens ( 32.83 ms per token, 30.46 tokens per second) 2.54.397.302 I slot print_timing: id 2 | task 2478 | total time = 30759.58 ms / 1353 tokens 2.54.397.303 I slot print_timing: id 2 | task 2478 | graphs reused = 3033 2.54.397.303 I slot print_timing: id 2 | task 2478 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.397.392 I slot release: id 2 | task 2478 | stop processing: n_tokens = 2047, truncated = 0 2.54.431.616 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.522 2.54.431.653 I slot launch_slot_: id 2 | task 3406 | processing task, is_child = 0 2.55.064.505 I slot print_timing: id 3 | task 2856 | n_gen = 547, tg = 29.36 t/s, tg_3s = 26.90 t/s 2.56.276.328 I slot print_timing: id 1 | task 3163 | n_gen = 282, tg = 29.37 t/s, tg_3s = 26.86 t/s 2.57.176.178 I slot print_timing: id 0 | task 3194 | n_gen = 282, tg = 31.12 t/s, tg_3s = 26.81 t/s 2.58.084.285 I slot print_timing: id 2 | task 3406 | n_gen = 101, tg = 33.11 t/s, tg_3s = 33.44 t/s 2.58.084.743 I slot print_timing: id 3 | task 2856 | n_gen = 647, tg = 29.89 t/s, tg_3s = 33.11 t/s 2.59.288.026 I slot print_timing: id 1 | task 3163 | n_gen = 382, tg = 30.29 t/s, tg_3s = 33.20 t/s 3.00.192.329 I slot print_timing: id 0 | task 3194 | n_gen = 382, tg = 31.63 t/s, tg_3s = 33.15 t/s 3.01.105.314 I slot print_timing: id 2 | task 3406 | n_gen = 201, tg = 33.11 t/s, tg_3s = 33.10 t/s 3.01.105.771 I slot print_timing: id 3 | task 2856 | n_gen = 747, tg = 30.28 t/s, tg_3s = 33.10 t/s 3.02.315.525 I slot print_timing: id 1 | task 3163 | n_gen = 482, tg = 30.82 t/s, tg_3s = 33.03 t/s 3.03.215.315 I slot print_timing: id 0 | task 3194 | n_gen = 482, tg = 31.92 t/s, tg_3s = 33.08 t/s 3.04.121.176 I slot print_timing: id 2 | task 3406 | n_gen = 301, tg = 33.12 t/s, tg_3s = 33.16 t/s 3.04.121.657 I slot print_timing: id 3 | task 2856 | n_gen = 847, tg = 30.60 t/s, tg_3s = 33.16 t/s 3.05.323.292 I slot print_timing: id 1 | task 3163 | n_gen = 582, tg = 31.21 t/s, tg_3s = 33.25 t/s 3.06.234.436 I slot print_timing: id 0 | task 3194 | n_gen = 582, tg = 32.12 t/s, tg_3s = 33.12 t/s 3.07.140.277 I slot print_timing: id 2 | task 3406 | n_gen = 401, tg = 33.12 t/s, tg_3s = 33.12 t/s 3.07.140.779 I slot print_timing: id 3 | task 2856 | n_gen = 947, tg = 30.84 t/s, tg_3s = 33.12 t/s 3.08.335.808 I slot print_timing: id 1 | task 3163 | n_gen = 682, tg = 31.49 t/s, tg_3s = 33.19 t/s 3.09.234.808 I slot print_timing: id 0 | task 3194 | n_gen = 682, tg = 32.29 t/s, tg_3s = 33.33 t/s 3.09.446.776 I slot print_timing: id 3 | task 2856 | prompt eval time = 427.06 ms / 264 tokens ( 1.62 ms per token, 618.17 tokens per second) 3.09.446.781 I slot print_timing: id 3 | task 2856 | eval time = 32976.08 ms / 1024 tokens ( 32.23 ms per token, 31.02 tokens per second) 3.09.446.782 I slot print_timing: id 3 | task 2856 | total time = 33403.15 ms / 1288 tokens 3.09.446.782 I slot print_timing: id 3 | task 2856 | graphs reused = 3507 3.09.446.783 I slot print_timing: id 3 | task 2856 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.446.874 I slot release: id 3 | task 2856 | stop processing: n_tokens = 2165, truncated = 0 3.09.472.764 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.493 3.09.478.206 I slot launch_slot_: id 3 | task 3887 | processing task, is_child = 0 3.10.164.224 I slot print_timing: id 2 | task 3406 | n_gen = 490, tg = 32.38 t/s, tg_3s = 29.43 t/s 3.11.338.811 I slot print_timing: id 1 | task 3163 | n_gen = 770, tg = 31.22 t/s, tg_3s = 29.30 t/s 3.12.260.669 I slot print_timing: id 0 | task 3194 | n_gen = 771, tg = 31.93 t/s, tg_3s = 29.41 t/s 3.12.895.735 I slot print_timing: id 3 | task 3887 | n_gen = 101, tg = 33.28 t/s, tg_3s = 33.61 t/s 3.13.165.030 I slot print_timing: id 2 | task 3406 | n_gen = 590, tg = 32.54 t/s, tg_3s = 33.32 t/s 3.14.340.998 I slot print_timing: id 1 | task 3163 | n_gen = 870, tg = 31.45 t/s, tg_3s = 33.31 t/s 3.15.277.737 I slot print_timing: id 0 | task 3194 | n_gen = 871, tg = 32.07 t/s, tg_3s = 33.14 t/s 3.15.913.976 I slot print_timing: id 3 | task 3887 | n_gen = 201, tg = 33.21 t/s, tg_3s = 33.13 t/s 3.16.187.103 I slot print_timing: id 2 | task 3406 | n_gen = 690, tg = 32.62 t/s, tg_3s = 33.09 t/s 3.17.346.146 I slot print_timing: id 1 | task 3163 | n_gen = 969, tg = 31.60 t/s, tg_3s = 32.94 t/s 3.18.294.370 I slot print_timing: id 0 | task 3194 | n_gen = 970, tg = 32.14 t/s, tg_3s = 32.82 t/s 3.18.837.035 I slot print_timing: id 3 | task 3887 | prompt eval time = 412.81 ms / 255 tokens ( 1.62 ms per token, 617.72 tokens per second) 3.18.837.042 I slot print_timing: id 3 | task 3887 | eval time = 8946.00 ms / 297 tokens ( 30.22 ms per token, 33.09 tokens per second) 3.18.837.043 I slot print_timing: id 3 | task 3887 | total time = 9358.82 ms / 552 tokens 3.18.837.043 I slot print_timing: id 3 | task 3887 | graphs reused = 3801 3.18.837.044 I slot print_timing: id 3 | task 3887 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.837.133 I slot release: id 3 | task 3887 | stop processing: n_tokens = 1429, truncated = 0 3.18.864.352 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.747 3.18.864.395 I slot launch_slot_: id 3 | task 4187 | processing task, is_child = 0 3.19.227.649 I slot print_timing: id 2 | task 3406 | n_gen = 779, tg = 32.20 t/s, tg_3s = 29.27 t/s 3.19.369.949 I slot print_timing: id 1 | task 3163 | prompt eval time = 627.72 ms / 475 tokens ( 1.32 ms per token, 756.71 tokens per second) 3.19.369.954 I slot print_timing: id 1 | task 3163 | eval time = 32659.91 ms / 1024 tokens ( 31.93 ms per token, 31.32 tokens per second) 3.19.369.955 I slot print_timing: id 1 | task 3163 | total time = 33287.63 ms / 1499 tokens 3.19.369.956 I slot print_timing: id 1 | task 3163 | graphs reused = 3803 3.19.369.956 I slot print_timing: id 1 | task 3163 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.370.042 I slot release: id 1 | task 3163 | stop processing: n_tokens = 2168, truncated = 0 3.19.404.023 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.493 3.19.410.968 I slot launch_slot_: id 1 | task 4194 | processing task, is_child = 0 3.20.849.702 I slot print_timing: id 0 | task 3194 | prompt eval time = 599.41 ms / 463 tokens ( 1.29 ms per token, 772.43 tokens per second) 3.20.849.705 I slot print_timing: id 0 | task 3194 | eval time = 32702.55 ms / 1024 tokens ( 31.97 ms per token, 31.28 tokens per second) 3.20.849.707 I slot print_timing: id 0 | task 3194 | total time = 33301.96 ms / 1487 tokens 3.20.849.707 I slot print_timing: id 0 | task 3194 | graphs reused = 3829 3.20.849.708 I slot print_timing: id 0 | task 3194 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.849.795 I slot release: id 0 | task 3194 | stop processing: n_tokens = 2161, truncated = 0 3.20.878.094 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.494 3.20.884.673 I slot launch_slot_: id 0 | task 4225 | processing task, is_child = 0 3.22.235.456 I slot print_timing: id 2 | task 3406 | n_gen = 840, tg = 30.88 t/s, tg_3s = 20.28 t/s 3.23.392.363 I slot print_timing: id 3 | task 4187 | n_gen = 100, tg = 24.07 t/s, tg_3s = 24.32 t/s 3.23.570.942 I slot print_timing: id 1 | task 4194 | n_gen = 100, tg = 27.96 t/s, tg_3s = 28.24 t/s 3.24.539.712 I slot print_timing: id 0 | task 4225 | n_gen = 102, tg = 33.38 t/s, tg_3s = 33.72 t/s 3.25.263.899 I slot print_timing: id 2 | task 3406 | n_gen = 941, tg = 31.13 t/s, tg_3s = 33.35 t/s 3.26.326.920 I slot print_timing: id 2 | task 3406 | prompt eval time = 632.51 ms / 485 tokens ( 1.30 ms per token, 766.78 tokens per second) 3.26.326.928 I slot print_timing: id 2 | task 3406 | eval time = 31262.74 ms / 976 tokens ( 32.06 ms per token, 31.19 tokens per second) 3.26.326.928 I slot print_timing: id 2 | task 3406 | total time = 31895.26 ms / 1461 tokens 3.26.326.929 I slot print_timing: id 2 | task 3406 | graphs reused = 3988 3.26.326.930 I slot print_timing: id 2 | task 3406 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.327.022 I slot release: id 2 | task 3406 | stop processing: n_tokens = 2155, truncated = 0 3.26.360.938 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.496 3.26.366.971 I slot launch_slot_: id 2 | task 4389 | processing task, is_child = 0 3.26.938.531 I slot print_timing: id 1 | task 4194 | n_gen = 193, tg = 27.79 t/s, tg_3s = 27.62 t/s 3.26.938.836 I slot print_timing: id 3 | task 4187 | n_gen = 199, tg = 25.85 t/s, tg_3s = 27.92 t/s 3.27.569.287 I slot print_timing: id 0 | task 4225 | n_gen = 183, tg = 30.06 t/s, tg_3s = 26.74 t/s 3.29.967.481 I slot print_timing: id 1 | task 4194 | n_gen = 293, tg = 29.38 t/s, tg_3s = 33.01 t/s 3.29.968.433 I slot print_timing: id 3 | task 4187 | n_gen = 299, tg = 27.88 t/s, tg_3s = 33.01 t/s 3.29.997.715 I slot print_timing: id 2 | task 4389 | n_gen = 101, tg = 33.31 t/s, tg_3s = 33.65 t/s 3.30.415.823 I slot print_timing: id 3 | task 4187 | prompt eval time = 415.47 ms / 259 tokens ( 1.60 ms per token, 623.39 tokens per second) 3.30.415.827 I slot print_timing: id 3 | task 4187 | eval time = 11135.95 ms / 314 tokens ( 35.58 ms per token, 28.11 tokens per second) 3.30.415.828 I slot print_timing: id 3 | task 4187 | total time = 11551.42 ms / 573 tokens 3.30.415.829 I slot print_timing: id 3 | task 4187 | graphs reused = 4101 3.30.415.829 I slot print_timing: id 3 | task 4187 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.415.938 I slot release: id 3 | task 4187 | stop processing: n_tokens = 1450, truncated = 0 3.30.442.200 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.737 3.30.442.228 I slot launch_slot_: id 3 | task 4507 | processing task, is_child = 0 3.30.853.854 I slot print_timing: id 0 | task 4225 | n_gen = 280, tg = 29.87 t/s, tg_3s = 29.53 t/s 3.32.970.592 I slot print_timing: id 1 | task 4194 | n_gen = 380, tg = 29.29 t/s, tg_3s = 28.97 t/s 3.33.001.531 I slot print_timing: id 2 | task 4389 | n_gen = 188, tg = 31.14 t/s, tg_3s = 28.96 t/s 3.33.180.318 I slot print_timing: id 1 | task 4194 | prompt eval time = 619.02 ms / 460 tokens ( 1.35 ms per token, 743.11 tokens per second) 3.33.180.327 I slot print_timing: id 1 | task 4194 | eval time = 13150.32 ms / 387 tokens ( 34.07 ms per token, 29.35 tokens per second) 3.33.180.328 I slot print_timing: id 1 | task 4194 | total time = 13769.33 ms / 847 tokens 3.33.180.329 I slot print_timing: id 1 | task 4194 | graphs reused = 4176 3.33.180.329 I slot print_timing: id 1 | task 4194 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.180.414 I slot release: id 1 | task 4194 | stop processing: n_tokens = 1516, truncated = 0 3.33.214.944 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.704 3.33.214.986 I slot launch_slot_: id 1 | task 4587 | processing task, is_child = 0 3.33.869.480 I slot print_timing: id 0 | task 4225 | n_gen = 361, tg = 29.14 t/s, tg_3s = 26.86 t/s 3.34.440.087 I slot print_timing: id 3 | task 4507 | n_gen = 100, tg = 28.02 t/s, tg_3s = 28.30 t/s 3.36.004.365 I slot print_timing: id 2 | task 4389 | n_gen = 270, tg = 29.86 t/s, tg_3s = 27.31 t/s 3.36.864.055 I slot print_timing: id 1 | task 4587 | n_gen = 103, tg = 33.72 t/s, tg_3s = 34.05 t/s 3.36.893.756 I slot print_timing: id 0 | task 4225 | n_gen = 463, tg = 30.04 t/s, tg_3s = 33.73 t/s 3.37.465.558 I slot print_timing: id 3 | task 4507 | n_gen = 202, tg = 30.65 t/s, tg_3s = 33.71 t/s 3.39.028.794 I slot print_timing: id 2 | task 4389 | n_gen = 371, tg = 30.75 t/s, tg_3s = 33.39 t/s 3.39.867.933 I slot print_timing: id 1 | task 4587 | n_gen = 203, tg = 33.50 t/s, tg_3s = 33.29 t/s 3.39.897.830 I slot print_timing: id 0 | task 4225 | n_gen = 563, tg = 30.57 t/s, tg_3s = 33.29 t/s 3.40.493.801 I slot print_timing: id 3 | task 4507 | n_gen = 303, tg = 31.50 t/s, tg_3s = 33.35 t/s 3.42.053.434 I slot print_timing: id 2 | task 4389 | n_gen = 472, tg = 31.28 t/s, tg_3s = 33.39 t/s 3.42.870.105 I slot print_timing: id 1 | task 4587 | n_gen = 303, tg = 33.44 t/s, tg_3s = 33.31 t/s 3.42.899.901 I slot print_timing: id 0 | task 4225 | n_gen = 663, tg = 30.96 t/s, tg_3s = 33.31 t/s 3.43.500.327 I slot print_timing: id 3 | task 4507 | n_gen = 403, tg = 31.92 t/s, tg_3s = 33.26 t/s 3.45.067.289 I slot print_timing: id 2 | task 4389 | n_gen = 572, tg = 31.60 t/s, tg_3s = 33.18 t/s 3.45.890.668 I slot print_timing: id 1 | task 4587 | n_gen = 403, tg = 33.36 t/s, tg_3s = 33.11 t/s 3.45.921.098 I slot print_timing: id 0 | task 4225 | n_gen = 763, tg = 31.22 t/s, tg_3s = 33.10 t/s 3.46.521.228 I slot print_timing: id 3 | task 4507 | n_gen = 503, tg = 32.15 t/s, tg_3s = 33.10 t/s 3.48.085.005 I slot print_timing: id 2 | task 4389 | n_gen = 672, tg = 31.82 t/s, tg_3s = 33.14 t/s 3.48.897.574 I slot print_timing: id 1 | task 4587 | n_gen = 503, tg = 33.34 t/s, tg_3s = 33.26 t/s 3.48.927.587 I slot print_timing: id 0 | task 4225 | n_gen = 863, tg = 31.44 t/s, tg_3s = 33.26 t/s 3.49.380.024 I slot print_timing: id 1 | task 4587 | prompt eval time = 623.98 ms / 467 tokens ( 1.34 ms per token, 748.43 tokens per second) 3.49.380.031 I slot print_timing: id 1 | task 4587 | eval time = 15541.05 ms / 519 tokens ( 30.00 ms per token, 33.33 tokens per second) 3.49.380.031 I slot print_timing: id 1 | task 4587 | total time = 16165.03 ms / 986 tokens 3.49.380.032 I slot print_timing: id 1 | task 4587 | graphs reused = 4690 3.49.380.033 I slot print_timing: id 1 | task 4587 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.380.122 I slot release: id 1 | task 4587 | stop processing: n_tokens = 1655, truncated = 0 3.49.414.832 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.645 3.49.414.867 I slot launch_slot_: id 1 | task 5109 | processing task, is_child = 0 3.49.975.186 I slot print_timing: id 3 | task 4507 | n_gen = 600, tg = 31.41 t/s, tg_3s = 28.08 t/s 3.51.089.666 I slot print_timing: id 2 | task 4389 | n_gen = 753, tg = 31.21 t/s, tg_3s = 26.96 t/s 3.51.932.937 I slot print_timing: id 0 | task 4225 | n_gen = 944, tg = 31.00 t/s, tg_3s = 26.95 t/s 3.52.997.035 I slot print_timing: id 3 | task 4507 | n_gen = 699, tg = 31.60 t/s, tg_3s = 32.76 t/s 3.53.057.386 I slot print_timing: id 1 | task 5109 | n_gen = 101, tg = 33.08 t/s, tg_3s = 33.41 t/s 3.54.113.357 I slot print_timing: id 2 | task 4389 | n_gen = 853, tg = 31.42 t/s, tg_3s = 33.07 t/s 3.54.356.635 I slot print_timing: id 0 | task 4225 | prompt eval time = 629.68 ms / 498 tokens ( 1.26 ms per token, 790.88 tokens per second) 3.54.356.641 I slot print_timing: id 0 | task 4225 | eval time = 32842.27 ms / 1024 tokens ( 32.10 ms per token, 31.15 tokens per second) 3.54.356.642 I slot print_timing: id 0 | task 4225 | total time = 33471.95 ms / 1522 tokens 3.54.356.643 I slot print_timing: id 0 | task 4225 | graphs reused = 4832 3.54.356.643 I slot print_timing: id 0 | task 4225 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.356.730 I slot release: id 0 | task 4225 | stop processing: n_tokens = 2196, truncated = 0 3.54.385.093 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.486 3.54.390.890 I slot launch_slot_: id 0 | task 5256 | processing task, is_child = 0 3.56.008.929 I slot print_timing: id 3 | task 4507 | n_gen = 781, tg = 31.07 t/s, tg_3s = 27.23 t/s 3.56.068.191 I slot print_timing: id 1 | task 5109 | n_gen = 183, tg = 30.16 t/s, tg_3s = 27.24 t/s 3.57.121.572 I slot print_timing: id 2 | task 4389 | n_gen = 935, tg = 31.00 t/s, tg_3s = 27.26 t/s 3.57.993.352 I slot print_timing: id 0 | task 5256 | n_gen = 101, tg = 33.33 t/s, tg_3s = 33.66 t/s 3.59.035.521 I slot print_timing: id 3 | task 4507 | n_gen = 881, tg = 31.28 t/s, tg_3s = 33.04 t/s 3.59.093.114 I slot print_timing: id 1 | task 5109 | n_gen = 283, tg = 31.13 t/s, tg_3s = 33.06 t/s 3.59.824.575 I slot print_timing: id 2 | task 4389 | prompt eval time = 628.87 ms / 481 tokens ( 1.31 ms per token, 764.86 tokens per second) 3.59.824.582 I slot print_timing: id 2 | task 4389 | eval time = 32828.72 ms / 1024 tokens ( 32.09 ms per token, 31.16 tokens per second) 3.59.824.583 I slot print_timing: id 2 | task 4389 | total time = 33457.59 ms / 1505 tokens 3.59.824.584 I slot print_timing: id 2 | task 4389 | graphs reused = 4991 3.59.824.584 I slot print_timing: id 2 | task 4389 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.824.686 I slot release: id 2 | task 4389 | stop processing: n_tokens = 2199, truncated = 0 3.59.859.722 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 3.59.866.055 I slot launch_slot_: id 2 | task 5420 | processing task, is_child = 0 4.01.014.689 I slot print_timing: id 0 | task 5256 | n_gen = 182, tg = 30.06 t/s, tg_3s = 26.81 t/s 4.01.314.968 I slot print_timing: id 1 | task 5109 | prompt eval time = 619.53 ms / 461 tokens ( 1.34 ms per token, 744.11 tokens per second) 4.01.314.974 I slot print_timing: id 1 | task 5109 | eval time = 11280.56 ms / 338 tokens ( 33.47 ms per token, 29.87 tokens per second) 4.01.314.974 I slot print_timing: id 1 | task 5109 | total time = 11900.09 ms / 799 tokens 4.01.314.975 I slot print_timing: id 1 | task 5109 | graphs reused = 5018 4.01.314.976 I slot print_timing: id 1 | task 5109 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.315.072 I slot release: id 1 | task 5109 | stop processing: n_tokens = 1468, truncated = 0 4.01.349.321 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.728 4.01.349.354 I slot launch_slot_: id 1 | task 5452 | processing task, is_child = 0 4.02.044.204 I slot print_timing: id 3 | task 4507 | n_gen = 943, tg = 30.25 t/s, tg_3s = 20.61 t/s 4.04.043.165 I slot print_timing: id 0 | task 5256 | n_gen = 263, tg = 28.95 t/s, tg_3s = 26.75 t/s 4.04.044.141 I slot print_timing: id 2 | task 5420 | n_gen = 100, tg = 27.68 t/s, tg_3s = 27.96 t/s 4.04.503.431 I slot print_timing: id 3 | task 4507 | prompt eval time = 464.37 ms / 311 tokens ( 1.49 ms per token, 669.73 tokens per second) 4.04.503.438 I slot print_timing: id 3 | task 4507 | eval time = 33596.83 ms / 1024 tokens ( 32.84 ms per token, 30.45 tokens per second) 4.04.503.439 I slot print_timing: id 3 | task 4507 | total time = 34061.20 ms / 1335 tokens 4.04.503.439 I slot print_timing: id 3 | task 4507 | graphs reused = 5100 4.04.503.440 I slot print_timing: id 3 | task 4507 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.503.535 I slot release: id 3 | task 4507 | stop processing: n_tokens = 2212, truncated = 0 4.04.531.079 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.483 4.04.536.787 I slot launch_slot_: id 3 | task 5539 | processing task, is_child = 0 4.05.377.640 I slot print_timing: id 1 | task 5452 | n_gen = 100, tg = 29.17 t/s, tg_3s = 29.46 t/s 4.07.064.535 I slot print_timing: id 0 | task 5256 | n_gen = 350, tg = 28.91 t/s, tg_3s = 28.79 t/s 4.07.065.411 I slot print_timing: id 2 | task 5420 | n_gen = 187, tg = 28.19 t/s, tg_3s = 28.80 t/s 4.07.984.937 I slot print_timing: id 3 | task 5539 | n_gen = 101, tg = 33.30 t/s, tg_3s = 33.63 t/s 4.08.403.245 I slot print_timing: id 1 | task 5452 | n_gen = 201, tg = 31.15 t/s, tg_3s = 33.38 t/s 4.10.087.184 I slot print_timing: id 0 | task 5256 | n_gen = 451, tg = 29.81 t/s, tg_3s = 33.41 t/s 4.10.088.231 I slot print_timing: id 2 | task 5420 | n_gen = 288, tg = 29.83 t/s, tg_3s = 33.41 t/s 4.10.989.905 I slot print_timing: id 3 | task 5539 | n_gen = 201, tg = 33.29 t/s, tg_3s = 33.28 t/s 4.11.414.066 I slot print_timing: id 1 | task 5452 | n_gen = 301, tg = 31.81 t/s, tg_3s = 33.21 t/s 4.13.097.737 I slot print_timing: id 0 | task 5256 | n_gen = 551, tg = 30.38 t/s, tg_3s = 33.22 t/s 4.13.098.595 I slot print_timing: id 2 | task 5420 | n_gen = 388, tg = 30.64 t/s, tg_3s = 33.22 t/s 4.14.001.839 I slot print_timing: id 3 | task 5539 | n_gen = 301, tg = 33.26 t/s, tg_3s = 33.20 t/s 4.14.423.623 I slot print_timing: id 1 | task 5452 | n_gen = 401, tg = 32.15 t/s, tg_3s = 33.23 t/s 4.16.121.939 I slot print_timing: id 0 | task 5256 | n_gen = 652, tg = 30.81 t/s, tg_3s = 33.40 t/s 4.16.122.815 I slot print_timing: id 2 | task 5420 | n_gen = 489, tg = 31.17 t/s, tg_3s = 33.40 t/s 4.16.784.517 I slot print_timing: id 3 | task 5539 | prompt eval time = 445.12 ms / 288 tokens ( 1.55 ms per token, 647.01 tokens per second) 4.16.784.520 I slot print_timing: id 3 | task 5539 | eval time = 11802.59 ms / 394 tokens ( 30.03 ms per token, 33.30 tokens per second) 4.16.784.521 I slot print_timing: id 3 | task 5539 | total time = 12247.71 ms / 682 tokens 4.16.784.522 I slot print_timing: id 3 | task 5539 | graphs reused = 5490 4.16.784.523 I slot print_timing: id 3 | task 5539 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.784.612 I slot release: id 3 | task 5539 | stop processing: n_tokens = 1559, truncated = 0 4.16.812.066 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.685 4.16.812.108 I slot launch_slot_: id 3 | task 5936 | processing task, is_child = 0 4.17.441.018 I slot print_timing: id 1 | task 5452 | n_gen = 490, tg = 31.63 t/s, tg_3s = 29.50 t/s 4.17.500.371 I slot print_timing: id 1 | task 5452 | prompt eval time = 634.06 ms / 483 tokens ( 1.31 ms per token, 761.76 tokens per second) 4.17.500.377 I slot print_timing: id 1 | task 5452 | eval time = 15516.95 ms / 492 tokens ( 31.60 ms per token, 31.64 tokens per second) 4.17.500.378 I slot print_timing: id 1 | task 5452 | total time = 16151.01 ms / 975 tokens 4.17.500.378 I slot print_timing: id 1 | task 5452 | graphs reused = 5498 4.17.500.379 I slot print_timing: id 1 | task 5452 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.500.474 I slot release: id 1 | task 5452 | stop processing: n_tokens = 1644, truncated = 0 4.17.535.475 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.650 4.17.535.511 I slot launch_slot_: id 1 | task 5949 | processing task, is_child = 0 4.19.134.162 I slot print_timing: id 0 | task 5256 | n_gen = 721, tg = 29.82 t/s, tg_3s = 22.91 t/s 4.19.135.164 I slot print_timing: id 2 | task 5420 | n_gen = 558, tg = 29.84 t/s, tg_3s = 22.91 t/s 4.20.786.979 I slot print_timing: id 3 | task 5936 | n_gen = 100, tg = 27.82 t/s, tg_3s = 28.10 t/s 4.21.174.332 I slot print_timing: id 1 | task 5949 | n_gen = 101, tg = 33.26 t/s, tg_3s = 33.59 t/s 4.22.141.689 I slot print_timing: id 0 | task 5256 | n_gen = 821, tg = 30.20 t/s, tg_3s = 33.25 t/s 4.22.142.569 I slot print_timing: id 2 | task 5420 | n_gen = 658, tg = 30.31 t/s, tg_3s = 33.25 t/s 4.23.560.660 I slot print_timing: id 2 | task 5420 | prompt eval time = 601.19 ms / 453 tokens ( 1.33 ms per token, 753.50 tokens per second) 4.23.560.663 I slot print_timing: id 2 | task 5420 | eval time = 23093.40 ms / 705 tokens ( 32.80 ms per token, 30.48 tokens per second) 4.23.560.664 I slot print_timing: id 2 | task 5420 | total time = 23694.59 ms / 1158 tokens 4.23.560.664 I slot print_timing: id 2 | task 5420 | graphs reused = 5676 4.23.560.665 I slot print_timing: id 2 | task 5420 | graph reallocs = 0 / 0 (same size) / (changed size) 4.23.560.745 I slot release: id 2 | task 5420 | stop processing: n_tokens = 1852, truncated = 0 4.23.594.616 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.577 4.23.594.646 I slot launch_slot_: id 2 | task 6132 | processing task, is_child = 0 4.24.184.237 I slot print_timing: id 1 | task 5949 | n_gen = 182, tg = 30.08 t/s, tg_3s = 26.91 t/s 4.24.184.558 I slot print_timing: id 3 | task 5936 | n_gen = 194, tg = 27.75 t/s, tg_3s = 27.67 t/s 4.25.144.085 I slot print_timing: id 0 | task 5256 | n_gen = 901, tg = 29.85 t/s, tg_3s = 26.65 t/s 4.25.232.587 I slot print_timing: id 0 | task 5256 | prompt eval time = 601.99 ms / 468 tokens ( 1.29 ms per token, 777.43 tokens per second) 4.25.232.593 I slot print_timing: id 0 | task 5256 | eval time = 30239.70 ms / 904 tokens ( 33.49 ms per token, 29.86 tokens per second) 4.25.232.594 I slot print_timing: id 0 | task 5256 | total time = 30841.69 ms / 1372 tokens 4.25.232.595 I slot print_timing: id 0 | task 5256 | graphs reused = 5708 4.25.232.596 I slot print_timing: id 0 | task 5256 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.232.683 I slot release: id 0 | task 5256 | stop processing: n_tokens = 2046, truncated = 0 4.25.260.056 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.522 4.25.260.089 I slot launch_slot_: id 0 | task 6169 | processing task, is_child = 0 4.27.206.419 I slot print_timing: id 1 | task 5949 | n_gen = 263, tg = 28.99 t/s, tg_3s = 26.80 t/s 4.27.207.285 I slot print_timing: id 3 | task 5936 | n_gen = 275, tg = 27.46 t/s, tg_3s = 26.80 t/s 4.27.771.307 I slot print_timing: id 2 | task 6132 | n_gen = 100, tg = 28.06 t/s, tg_3s = 28.34 t/s 4.28.893.371 I slot print_timing: id 0 | task 6169 | n_gen = 102, tg = 33.63 t/s, tg_3s = 33.96 t/s 4.30.211.503 I slot print_timing: id 1 | task 5949 | n_gen = 364, tg = 30.14 t/s, tg_3s = 33.61 t/s 4.30.212.457 I slot print_timing: id 3 | task 5936 | n_gen = 376, tg = 28.88 t/s, tg_3s = 33.61 t/s 4.30.776.997 I slot print_timing: id 2 | task 6132 | n_gen = 201, tg = 30.61 t/s, tg_3s = 33.60 t/s 4.31.909.981 I slot print_timing: id 0 | task 6169 | n_gen = 203, tg = 33.55 t/s, tg_3s = 33.48 t/s 4.33.225.244 I slot print_timing: id 1 | task 5949 | n_gen = 465, tg = 30.82 t/s, tg_3s = 33.51 t/s 4.33.226.261 I slot print_timing: id 3 | task 5936 | n_gen = 477, tg = 29.75 t/s, tg_3s = 33.51 t/s 4.33.789.895 I slot print_timing: id 2 | task 6132 | n_gen = 302, tg = 31.53 t/s, tg_3s = 33.52 t/s 4.34.930.941 I slot print_timing: id 0 | task 6169 | n_gen = 304, tg = 33.51 t/s, tg_3s = 33.43 t/s 4.36.253.723 I slot print_timing: id 1 | task 5949 | n_gen = 566, tg = 31.24 t/s, tg_3s = 33.35 t/s 4.36.254.732 I slot print_timing: id 3 | task 5936 | n_gen = 578, tg = 30.33 t/s, tg_3s = 33.35 t/s 4.36.817.031 I slot print_timing: id 2 | task 6132 | n_gen = 403, tg = 31.97 t/s, tg_3s = 33.36 t/s 4.37.683.185 I slot print_timing: id 1 | task 5949 | prompt eval time = 632.21 ms / 485 tokens ( 1.30 ms per token, 767.15 tokens per second) 4.37.683.192 I slot print_timing: id 1 | task 5949 | eval time = 19515.46 ms / 614 tokens ( 31.84 ms per token, 31.41 tokens per second) 4.37.683.193 I slot print_timing: id 1 | task 5949 | total time = 20147.67 ms / 1099 tokens 4.37.683.193 I slot print_timing: id 1 | task 5949 | graphs reused = 6102 4.37.683.194 I slot print_timing: id 1 | task 5949 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.683.281 I slot release: id 1 | task 5949 | stop processing: n_tokens = 1768, truncated = 0 4.37.718.548 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.604 4.37.718.585 I slot launch_slot_: id 1 | task 6568 | processing task, is_child = 0 4.38.305.281 I slot print_timing: id 0 | task 6169 | n_gen = 398, tg = 31.98 t/s, tg_3s = 27.86 t/s 4.39.274.668 I slot print_timing: id 3 | task 5936 | n_gen = 659, tg = 29.85 t/s, tg_3s = 26.82 t/s 4.39.839.718 I slot print_timing: id 2 | task 6132 | n_gen = 484, tg = 30.97 t/s, tg_3s = 26.80 t/s 4.41.328.388 I slot print_timing: id 0 | task 6169 | n_gen = 498, tg = 32.19 t/s, tg_3s = 33.08 t/s 4.41.388.211 I slot print_timing: id 1 | task 6568 | n_gen = 102, tg = 33.41 t/s, tg_3s = 33.74 t/s 4.42.286.405 I slot print_timing: id 3 | task 5936 | n_gen = 760, tg = 30.29 t/s, tg_3s = 33.54 t/s 4.42.849.817 I slot print_timing: id 2 | task 6132 | n_gen = 585, tg = 31.39 t/s, tg_3s = 33.55 t/s 4.44.353.467 I slot print_timing: id 0 | task 6169 | n_gen = 599, tg = 32.39 t/s, tg_3s = 33.39 t/s 4.44.414.561 I slot print_timing: id 1 | task 6568 | n_gen = 203, tg = 33.39 t/s, tg_3s = 33.37 t/s 4.45.313.272 I slot print_timing: id 3 | task 5936 | n_gen = 861, tg = 30.62 t/s, tg_3s = 33.37 t/s 4.45.850.407 I slot print_timing: id 2 | task 6132 | n_gen = 685, tg = 31.66 t/s, tg_3s = 33.33 t/s 4.47.382.964 I slot print_timing: id 0 | task 6169 | n_gen = 700, tg = 32.52 t/s, tg_3s = 33.34 t/s 4.47.444.437 I slot print_timing: id 1 | task 6568 | n_gen = 304, tg = 33.37 t/s, tg_3s = 33.33 t/s 4.48.325.848 I slot print_timing: id 3 | task 5936 | n_gen = 961, tg = 30.87 t/s, tg_3s = 33.19 t/s 4.48.869.878 I slot print_timing: id 2 | task 6132 | n_gen = 785, tg = 31.83 t/s, tg_3s = 33.12 t/s 4.50.237.799 I slot print_timing: id 3 | task 5936 | prompt eval time = 416.65 ms / 259 tokens ( 1.61 ms per token, 621.63 tokens per second) 4.50.237.804 I slot print_timing: id 3 | task 5936 | eval time = 33009.04 ms / 1024 tokens ( 32.27 ms per token, 30.99 tokens per second) 4.50.237.805 I slot print_timing: id 3 | task 5936 | total time = 33425.68 ms / 1283 tokens 4.50.237.806 I slot print_timing: id 3 | task 5936 | graphs reused = 6494 4.50.237.806 I slot print_timing: id 3 | task 5936 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.237.898 I slot release: id 3 | task 5936 | stop processing: n_tokens = 2160, truncated = 0 4.50.265.654 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.494 4.50.271.315 I slot launch_slot_: id 3 | task 6967 | processing task, is_child = 0 4.50.663.445 I slot print_timing: id 0 | task 6169 | n_gen = 796, tg = 32.09 t/s, tg_3s = 29.26 t/s 4.50.663.772 I slot print_timing: id 1 | task 6568 | n_gen = 398, tg = 32.28 t/s, tg_3s = 29.20 t/s 4.51.892.657 I slot print_timing: id 2 | task 6132 | n_gen = 872, tg = 31.50 t/s, tg_3s = 28.78 t/s 4.52.619.920 I slot print_timing: id 0 | task 6169 | prompt eval time = 629.83 ms / 498 tokens ( 1.26 ms per token, 790.68 tokens per second) 4.52.619.927 I slot print_timing: id 0 | task 6169 | eval time = 26729.99 ms / 860 tokens ( 31.12 ms per token, 32.14 tokens per second) 4.52.619.928 I slot print_timing: id 0 | task 6169 | total time = 27359.82 ms / 1358 tokens 4.52.619.928 I slot print_timing: id 0 | task 6169 | graphs reused = 6555 4.52.619.929 I slot print_timing: id 0 | task 6169 | graph reallocs = 0 / 0 (same size) / (changed size) 4.52.620.017 I slot release: id 0 | task 6169 | stop processing: n_tokens = 2032, truncated = 0 4.52.648.080 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.526 4.52.648.114 I slot launch_slot_: id 0 | task 7034 | processing task, is_child = 0 4.53.682.257 I slot print_timing: id 1 | task 6568 | n_gen = 478, tg = 31.14 t/s, tg_3s = 26.50 t/s 4.54.283.453 I slot print_timing: id 3 | task 6967 | n_gen = 100, tg = 27.75 t/s, tg_3s = 28.03 t/s 4.54.913.822 I slot print_timing: id 2 | task 6132 | n_gen = 953, tg = 31.04 t/s, tg_3s = 26.81 t/s 4.55.094.950 I slot print_timing: id 2 | task 6132 | prompt eval time = 647.95 ms / 494 tokens ( 1.31 ms per token, 762.40 tokens per second) 4.55.094.957 I slot print_timing: id 2 | task 6132 | eval time = 30852.34 ms / 959 tokens ( 32.20 ms per token, 31.05 tokens per second) 4.55.094.958 I slot print_timing: id 2 | task 6132 | total time = 31500.29 ms / 1453 tokens 4.55.094.959 I slot print_timing: id 2 | task 6132 | graphs reused = 6615 4.55.094.959 I slot print_timing: id 2 | task 6132 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.095.062 I slot release: id 2 | task 6132 | stop processing: n_tokens = 2147, truncated = 0 4.55.128.491 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.497 4.55.134.271 I slot launch_slot_: id 2 | task 7098 | processing task, is_child = 0 4.56.682.412 I slot print_timing: id 1 | task 6568 | n_gen = 560, tg = 30.52 t/s, tg_3s = 27.33 t/s 4.56.801.326 I slot print_timing: id 0 | task 7034 | n_gen = 100, tg = 28.12 t/s, tg_3s = 28.41 t/s 4.57.310.044 I slot print_timing: id 3 | task 6967 | n_gen = 183, tg = 27.60 t/s, tg_3s = 27.42 t/s 4.57.488.641 I slot print_timing: id 1 | task 6568 | prompt eval time = 646.31 ms / 489 tokens ( 1.32 ms per token, 756.61 tokens per second) 4.57.488.647 I slot print_timing: id 1 | task 6568 | eval time = 19123.74 ms / 587 tokens ( 32.63 ms per token, 30.64 tokens per second) 4.57.488.648 I slot print_timing: id 1 | task 6568 | total time = 19770.05 ms / 1076 tokens 4.57.488.649 I slot print_timing: id 1 | task 6568 | graphs reused = 6673 4.57.488.649 I slot print_timing: id 1 | task 6568 | graph reallocs = 0 / 0 (same size) / (changed size) 4.57.488.742 I slot release: id 1 | task 6568 | stop processing: n_tokens = 1745, truncated = 0 4.57.523.159 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.612 4.57.523.194 I slot launch_slot_: id 1 | task 7161 | processing task, is_child = 0 4.59.244.829 I slot print_timing: id 2 | task 7098 | n_gen = 100, tg = 28.17 t/s, tg_3s = 28.45 t/s 4.59.817.827 I slot print_timing: id 0 | task 7034 | n_gen = 182, tg = 27.69 t/s, tg_3s = 27.18 t/s 5.00.326.056 I slot print_timing: id 3 | task 6967 | n_gen = 265, tg = 27.47 t/s, tg_3s = 27.19 t/s 5.01.168.260 I slot print_timing: id 1 | task 7161 | n_gen = 102, tg = 33.49 t/s, tg_3s = 33.82 t/s 5.02.264.441 I slot print_timing: id 2 | task 7098 | n_gen = 201, tg = 30.61 t/s, tg_3s = 33.45 t/s 5.02.832.839 I slot print_timing: id 0 | task 7034 | n_gen = 283, tg = 29.52 t/s, tg_3s = 33.50 t/s 5.03.345.778 I slot print_timing: id 3 | task 6967 | n_gen = 366, tg = 28.90 t/s, tg_3s = 33.45 t/s 5.04.185.698 I slot print_timing: id 1 | task 7161 | n_gen = 203, tg = 33.48 t/s, tg_3s = 33.47 t/s 5.05.268.310 I slot print_timing: id 2 | task 7098 | n_gen = 301, tg = 31.45 t/s, tg_3s = 33.29 t/s 5.05.833.288 I slot print_timing: id 0 | task 7034 | n_gen = 383, tg = 30.43 t/s, tg_3s = 33.33 t/s 5.06.351.441 I slot print_timing: id 3 | task 6967 | n_gen = 466, tg = 29.74 t/s, tg_3s = 33.27 t/s 5.07.198.178 I slot print_timing: id 1 | task 7161 | n_gen = 303, tg = 33.39 t/s, tg_3s = 33.20 t/s 5.08.281.053 I slot print_timing: id 2 | task 7098 | n_gen = 401, tg = 31.87 t/s, tg_3s = 33.19 t/s 5.08.859.037 I slot print_timing: id 0 | task 7034 | n_gen = 483, tg = 30.94 t/s, tg_3s = 33.05 t/s 5.09.377.864 I slot print_timing: id 3 | task 6967 | n_gen = 566, tg = 30.28 t/s, tg_3s = 33.04 t/s 5.10.214.981 I slot print_timing: id 1 | task 7161 | n_gen = 403, tg = 33.33 t/s, tg_3s = 33.15 t/s 5.11.292.818 I slot print_timing: id 2 | task 7098 | n_gen = 501, tg = 32.13 t/s, tg_3s = 33.20 t/s 5.11.865.981 I slot print_timing: id 0 | task 7034 | n_gen = 583, tg = 31.32 t/s, tg_3s = 33.26 t/s 5.12.382.738 I slot print_timing: id 2 | task 7098 | prompt eval time = 595.81 ms / 444 tokens ( 1.34 ms per token, 745.20 tokens per second) 5.12.382.746 I slot print_timing: id 2 | task 7098 | eval time = 16652.63 ms / 537 tokens ( 31.07 ms per token, 32.19 tokens per second) 5.12.382.747 I slot print_timing: id 2 | task 7098 | total time = 17248.45 ms / 981 tokens 5.12.382.748 I slot print_timing: id 2 | task 7098 | graphs reused = 7144 5.12.382.748 I slot print_timing: id 2 | task 7098 | graph reallocs = 0 / 0 (same size) / (changed size) 5.12.382.848 I slot release: id 2 | task 7098 | stop processing: n_tokens = 1675, truncated = 0 5.12.383.316 I slot print_timing: id 3 | task 6967 | n_gen = 666, tg = 30.69 t/s, tg_3s = 33.27 t/s 5.12.418.015 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.638 5.12.418.055 I slot launch_slot_: id 2 | task 7639 | processing task, is_child = 0 5.13.231.756 I slot print_timing: id 1 | task 7161 | n_gen = 485, tg = 32.10 t/s, tg_3s = 27.18 t/s 5.14.872.189 I slot print_timing: id 0 | task 7034 | n_gen = 665, tg = 30.75 t/s, tg_3s = 27.28 t/s 5.15.408.215 I slot print_timing: id 3 | task 6967 | n_gen = 749, tg = 30.29 t/s, tg_3s = 27.44 t/s 5.16.024.784 I slot print_timing: id 2 | task 7639 | n_gen = 102, tg = 33.59 t/s, tg_3s = 33.92 t/s 5.16.085.164 I slot print_timing: id 1 | task 7161 | prompt eval time = 629.32 ms / 478 tokens ( 1.32 ms per token, 759.55 tokens per second) 5.16.085.167 I slot print_timing: id 1 | task 7161 | eval time = 17932.64 ms / 581 tokens ( 30.92 ms per token, 32.34 tokens per second) 5.16.085.168 I slot print_timing: id 1 | task 7161 | total time = 18561.96 ms / 1059 tokens 5.16.085.168 I slot print_timing: id 1 | task 7161 | graphs reused = 7246 5.16.085.169 I slot print_timing: id 1 | task 7161 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.085.261 I slot release: id 1 | task 7161 | stop processing: n_tokens = 1728, truncated = 0 5.16.120.060 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.618 5.16.120.094 I slot launch_slot_: id 1 | task 7746 | processing task, is_child = 0 5.17.886.877 I slot print_timing: id 0 | task 7034 | n_gen = 747, tg = 30.32 t/s, tg_3s = 27.20 t/s 5.18.423.491 I slot print_timing: id 3 | task 6967 | n_gen = 831, tg = 29.96 t/s, tg_3s = 27.19 t/s 5.18.868.984 I slot print_timing: id 0 | task 7034 | prompt eval time = 632.83 ms / 505 tokens ( 1.25 ms per token, 798.01 tokens per second) 5.18.868.990 I slot print_timing: id 0 | task 7034 | eval time = 25588.04 ms / 780 tokens ( 32.85 ms per token, 30.44 tokens per second) 5.18.868.990 I slot print_timing: id 0 | task 7034 | total time = 26220.86 ms / 1285 tokens 5.18.868.991 I slot print_timing: id 0 | task 7034 | graphs reused = 7316 5.18.868.992 I slot print_timing: id 0 | task 7034 | graph reallocs = 0 / 0 (same size) / (changed size) 5.18.869.081 I slot release: id 0 | task 7034 | stop processing: n_tokens = 1959, truncated = 0 5.18.898.045 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.545 5.18.898.078 I slot launch_slot_: id 0 | task 7821 | processing task, is_child = 0 5.19.454.240 I slot print_timing: id 2 | task 7639 | n_gen = 180, tg = 27.81 t/s, tg_3s = 22.74 t/s 5.20.265.871 I slot print_timing: id 1 | task 7746 | n_gen = 100, tg = 28.13 t/s, tg_3s = 28.42 t/s 5.21.440.163 I slot print_timing: id 3 | task 6967 | n_gen = 913, tg = 29.68 t/s, tg_3s = 27.18 t/s 5.22.483.862 I slot print_timing: id 2 | task 7639 | n_gen = 280, tg = 29.47 t/s, tg_3s = 33.01 t/s 5.22.512.890 I slot print_timing: id 0 | task 7821 | n_gen = 101, tg = 33.23 t/s, tg_3s = 33.57 t/s 5.23.270.811 I slot print_timing: id 1 | task 7746 | n_gen = 200, tg = 30.50 t/s, tg_3s = 33.28 t/s 5.24.451.121 I slot print_timing: id 3 | task 6967 | n_gen = 1013, tg = 30.00 t/s, tg_3s = 33.21 t/s 5.24.782.189 I slot print_timing: id 3 | task 6967 | prompt eval time = 444.75 ms / 293 tokens ( 1.52 ms per token, 658.80 tokens per second) 5.24.782.193 I slot print_timing: id 3 | task 6967 | eval time = 34066.12 ms / 1024 tokens ( 33.30 ms per token, 30.03 tokens per second) 5.24.782.195 I slot print_timing: id 3 | task 6967 | total time = 34510.87 ms / 1317 tokens 5.24.782.195 I slot print_timing: id 3 | task 6967 | graphs reused = 7490 5.24.782.196 I slot print_timing: id 3 | task 6967 | graph reallocs = 0 / 0 (same size) / (changed size) 5.24.782.288 I slot release: id 3 | task 6967 | stop processing: n_tokens = 2194, truncated = 0 5.24.807.684 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.487 5.24.813.369 I slot launch_slot_: id 3 | task 8000 | processing task, is_child = 0 5.25.494.178 I slot print_timing: id 2 | task 7639 | n_gen = 367, tg = 29.34 t/s, tg_3s = 28.90 t/s 5.25.523.192 I slot print_timing: id 0 | task 7821 | n_gen = 188, tg = 31.07 t/s, tg_3s = 28.90 t/s 5.26.294.737 I slot print_timing: id 1 | task 7746 | n_gen = 288, tg = 30.06 t/s, tg_3s = 29.10 t/s 5.27.670.802 I slot print_timing: id 2 | task 7639 | prompt eval time = 599.77 ms / 447 tokens ( 1.34 ms per token, 745.28 tokens per second) 5.27.670.809 I slot print_timing: id 2 | task 7639 | eval time = 14652.97 ms / 440 tokens ( 33.38 ms per token, 29.96 tokens per second) 5.27.670.809 I slot print_timing: id 2 | task 7639 | total time = 15252.74 ms / 887 tokens 5.27.670.810 I slot print_timing: id 2 | task 7639 | graphs reused = 7569 5.27.670.811 I slot print_timing: id 2 | task 7639 | graph reallocs = 0 / 0 (same size) / (changed size) 5.27.670.903 I slot release: id 2 | task 7639 | stop processing: n_tokens = 1581, truncated = 0 5.27.705.455 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.676 5.27.705.498 I slot launch_slot_: id 2 | task 8085 | processing task, is_child = 0 5.28.542.579 I slot print_timing: id 0 | task 7821 | n_gen = 270, tg = 29.76 t/s, tg_3s = 27.16 t/s 5.28.753.951 I slot print_timing: id 1 | task 7746 | prompt eval time = 626.92 ms / 473 tokens ( 1.33 ms per token, 754.48 tokens per second) 5.28.753.957 I slot print_timing: id 1 | task 7746 | eval time = 12006.93 ms / 351 tokens ( 34.31 ms per token, 29.15 tokens per second) 5.28.753.957 I slot print_timing: id 1 | task 7746 | total time = 12633.85 ms / 824 tokens 5.28.753.958 I slot print_timing: id 1 | task 7746 | graphs reused = 7582 5.28.753.959 I slot print_timing: id 1 | task 7746 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.754.048 I slot release: id 1 | task 7746 | stop processing: n_tokens = 1493, truncated = 0 5.28.788.886 I slot print_timing: id 3 | task 8000 | n_gen = 100, tg = 28.02 t/s, tg_3s = 28.30 t/s 5.28.788.895 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.715 5.28.788.927 I slot launch_slot_: id 1 | task 8103 | processing task, is_child = 0 5.31.568.856 I slot print_timing: id 0 | task 7821 | n_gen = 352, tg = 29.09 t/s, tg_3s = 27.10 t/s 5.31.815.393 I slot print_timing: id 3 | task 8000 | n_gen = 182, tg = 27.59 t/s, tg_3s = 27.09 t/s 5.31.876.662 I slot print_timing: id 2 | task 8085 | n_gen = 100, tg = 27.93 t/s, tg_3s = 28.21 t/s 5.32.448.448 I slot print_timing: id 1 | task 8103 | n_gen = 102, tg = 33.36 t/s, tg_3s = 33.69 t/s 5.34.595.827 I slot print_timing: id 0 | task 7821 | n_gen = 453, tg = 29.95 t/s, tg_3s = 33.37 t/s 5.34.834.062 I slot print_timing: id 3 | task 8000 | n_gen = 283, tg = 29.44 t/s, tg_3s = 33.46 t/s 5.34.893.734 I slot print_timing: id 2 | task 8085 | n_gen = 201, tg = 30.48 t/s, tg_3s = 33.48 t/s 5.34.981.633 I slot print_timing: id 0 | task 7821 | prompt eval time = 605.87 ms / 476 tokens ( 1.27 ms per token, 785.65 tokens per second) 5.34.981.636 I slot print_timing: id 0 | task 7821 | eval time = 15477.68 ms / 466 tokens ( 33.29 ms per token, 30.04 tokens per second) 5.34.981.637 I slot print_timing: id 0 | task 7821 | total time = 16083.55 ms / 942 tokens 5.34.981.638 I slot print_timing: id 0 | task 7821 | graphs reused = 7766 5.34.981.638 I slot print_timing: id 0 | task 7821 | graph reallocs = 0 / 0 (same size) / (changed size) 5.34.981.742 I slot release: id 0 | task 7821 | stop processing: n_tokens = 1616, truncated = 0 5.35.010.096 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.661 5.35.010.132 I slot launch_slot_: id 0 | task 8293 | processing task, is_child = 0 5.35.553.404 I slot print_timing: id 1 | task 8103 | n_gen = 189, tg = 30.66 t/s, tg_3s = 28.02 t/s 5.37.856.712 I slot print_timing: id 3 | task 8000 | n_gen = 366, tg = 28.96 t/s, tg_3s = 27.46 t/s 5.37.916.758 I slot print_timing: id 2 | task 8085 | n_gen = 284, tg = 29.53 t/s, tg_3s = 27.46 t/s 5.38.578.194 I slot print_timing: id 1 | task 8103 | n_gen = 289, tg = 31.45 t/s, tg_3s = 33.06 t/s 5.38.607.757 I slot print_timing: id 0 | task 8293 | n_gen = 101, tg = 33.28 t/s, tg_3s = 33.62 t/s 5.40.870.904 I slot print_timing: id 3 | task 8000 | n_gen = 466, tg = 29.78 t/s, tg_3s = 33.18 t/s 5.40.929.440 I slot print_timing: id 2 | task 8085 | n_gen = 384, tg = 30.40 t/s, tg_3s = 33.19 t/s 5.41.593.656 I slot print_timing: id 1 | task 8103 | n_gen = 389, tg = 31.87 t/s, tg_3s = 33.16 t/s 5.41.623.364 I slot print_timing: id 0 | task 8293 | n_gen = 201, tg = 33.22 t/s, tg_3s = 33.16 t/s 5.42.012.411 I slot print_timing: id 3 | task 8000 | prompt eval time = 441.74 ms / 288 tokens ( 1.53 ms per token, 651.96 tokens per second) 5.42.012.417 I slot print_timing: id 3 | task 8000 | eval time = 16757.29 ms / 504 tokens ( 33.31 ms per token, 30.02 tokens per second) 5.42.012.418 I slot print_timing: id 3 | task 8000 | total time = 17199.03 ms / 792 tokens 5.42.012.419 I slot print_timing: id 3 | task 8000 | graphs reused = 7978 5.42.012.419 I slot print_timing: id 3 | task 8000 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.012.508 I slot release: id 3 | task 8000 | stop processing: n_tokens = 1669, truncated = 0 5.42.039.269 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.640 5.42.039.298 I slot launch_slot_: id 3 | task 8510 | processing task, is_child = 0 5.42.927.647 I slot print_timing: id 1 | task 8103 | prompt eval time = 632.12 ms / 479 tokens ( 1.32 ms per token, 757.77 tokens per second) 5.42.927.653 I slot print_timing: id 1 | task 8103 | eval time = 13506.59 ms / 421 tokens ( 32.16 ms per token, 31.10 tokens per second) 5.42.927.653 I slot print_timing: id 1 | task 8103 | total time = 14138.71 ms / 900 tokens 5.42.927.654 I slot print_timing: id 1 | task 8103 | graphs reused = 7992 5.42.927.655 I slot print_timing: id 1 | task 8103 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.927.739 I slot release: id 1 | task 8103 | stop processing: n_tokens = 1569, truncated = 0 5.42.962.608 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.681 5.42.962.641 I slot launch_slot_: id 1 | task 8529 | processing task, is_child = 0 5.43.951.322 I slot print_timing: id 2 | task 8085 | n_gen = 453, tg = 28.94 t/s, tg_3s = 22.83 t/s 5.44.638.702 I slot print_timing: id 0 | task 8293 | n_gen = 270, tg = 29.77 t/s, tg_3s = 22.88 t/s 5.46.024.280 I slot print_timing: id 3 | task 8510 | n_gen = 100, tg = 27.88 t/s, tg_3s = 28.16 t/s 5.46.601.556 I slot print_timing: id 1 | task 8529 | n_gen = 101, tg = 33.18 t/s, tg_3s = 33.51 t/s 5.46.960.171 I slot print_timing: id 2 | task 8085 | n_gen = 553, tg = 29.63 t/s, tg_3s = 33.24 t/s 5.47.644.420 I slot print_timing: id 0 | task 8293 | n_gen = 370, tg = 30.65 t/s, tg_3s = 33.27 t/s 5.49.041.528 I slot print_timing: id 3 | task 8510 | n_gen = 200, tg = 30.30 t/s, tg_3s = 33.14 t/s 5.49.614.436 I slot print_timing: id 1 | task 8529 | n_gen = 201, tg = 33.19 t/s, tg_3s = 33.19 t/s 5.49.974.826 I slot print_timing: id 2 | task 8085 | n_gen = 653, tg = 30.13 t/s, tg_3s = 33.17 t/s 5.50.661.739 I slot print_timing: id 0 | task 8293 | n_gen = 470, tg = 31.15 t/s, tg_3s = 33.14 t/s 5.52.054.951 I slot print_timing: id 3 | task 8510 | n_gen = 300, tg = 31.20 t/s, tg_3s = 33.18 t/s 5.52.627.226 I slot print_timing: id 1 | task 8529 | n_gen = 301, tg = 33.19 t/s, tg_3s = 33.19 t/s 5.52.993.459 I slot print_timing: id 2 | task 8085 | n_gen = 753, tg = 30.49 t/s, tg_3s = 33.13 t/s 5.53.677.163 I slot print_timing: id 0 | task 8293 | n_gen = 570, tg = 31.48 t/s, tg_3s = 33.16 t/s 5.55.059.464 I slot print_timing: id 3 | task 8510 | n_gen = 400, tg = 31.70 t/s, tg_3s = 33.28 t/s 5.55.629.405 I slot print_timing: id 1 | task 8529 | n_gen = 401, tg = 33.22 t/s, tg_3s = 33.31 t/s 5.56.019.014 I slot print_timing: id 2 | task 8085 | n_gen = 854, tg = 30.81 t/s, tg_3s = 33.38 t/s 5.56.706.273 I slot print_timing: id 0 | task 8293 | n_gen = 671, tg = 31.75 t/s, tg_3s = 33.34 t/s 5.57.372.393 I slot print_timing: id 1 | task 8529 | prompt eval time = 625.00 ms / 469 tokens ( 1.33 ms per token, 750.39 tokens per second) 5.57.372.400 I slot print_timing: id 1 | task 8529 | eval time = 13784.74 ms / 459 tokens ( 30.10 ms per token, 33.23 tokens per second) 5.57.372.401 I slot print_timing: id 1 | task 8529 | total time = 14409.74 ms / 928 tokens 5.57.372.402 I slot print_timing: id 1 | task 8529 | graphs reused = 8447 5.57.372.402 I slot print_timing: id 1 | task 8529 | graph reallocs = 0 / 0 (same size) / (changed size) 5.57.372.500 I slot release: id 1 | task 8529 | stop processing: n_tokens = 1597, truncated = 0 5.57.407.608 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.669 5.57.407.643 I slot launch_slot_: id 1 | task 8991 | processing task, is_child = 0 5.58.060.791 I slot print_timing: id 3 | task 8510 | n_gen = 481, tg = 30.79 t/s, tg_3s = 26.99 t/s 5.59.023.837 I slot print_timing: id 2 | task 8085 | n_gen = 935, tg = 30.43 t/s, tg_3s = 26.96 t/s 5.59.722.895 I slot print_timing: id 0 | task 8293 | n_gen = 752, tg = 31.14 t/s, tg_3s = 26.85 t/s 6.01.030.667 I slot print_timing: id 1 | task 8991 | n_gen = 100, tg = 32.99 t/s, tg_3s = 33.32 t/s 6.01.062.404 I slot print_timing: id 3 | task 8510 | n_gen = 580, tg = 31.15 t/s, tg_3s = 32.98 t/s 6.01.728.348 I slot print_timing: id 2 | task 8085 | prompt eval time = 626.91 ms / 471 tokens ( 1.33 ms per token, 751.31 tokens per second) 6.01.728.355 I slot print_timing: id 2 | task 8085 | eval time = 33395.93 ms / 1024 tokens ( 32.65 ms per token, 30.63 tokens per second) 6.01.728.357 I slot print_timing: id 2 | task 8085 | total time = 34022.83 ms / 1495 tokens 6.01.728.358 I slot print_timing: id 2 | task 8085 | graphs reused = 8568 6.01.728.358 I slot print_timing: id 2 | task 8085 | graph reallocs = 0 / 0 (same size) / (changed size) 6.01.728.468 I slot release: id 2 | task 8085 | stop processing: n_tokens = 2189, truncated = 0 6.01.763.444 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.488 6.01.769.310 I slot launch_slot_: id 2 | task 9117 | processing task, is_child = 0 6.02.727.434 I slot print_timing: id 0 | task 8293 | n_gen = 832, tg = 30.64 t/s, tg_3s = 26.63 t/s 6.04.039.951 I slot print_timing: id 1 | task 8991 | n_gen = 181, tg = 29.95 t/s, tg_3s = 26.92 t/s 6.04.070.983 I slot print_timing: id 3 | task 8510 | n_gen = 661, tg = 30.56 t/s, tg_3s = 26.92 t/s 6.05.401.766 I slot print_timing: id 2 | task 9117 | n_gen = 101, tg = 33.25 t/s, tg_3s = 33.58 t/s 6.05.735.189 I slot print_timing: id 0 | task 8293 | n_gen = 932, tg = 30.90 t/s, tg_3s = 33.25 t/s 6.07.069.273 I slot print_timing: id 1 | task 8991 | n_gen = 281, tg = 30.97 t/s, tg_3s = 33.01 t/s 6.07.100.572 I slot print_timing: id 3 | task 8510 | n_gen = 761, tg = 30.86 t/s, tg_3s = 33.01 t/s 6.08.405.650 I slot print_timing: id 2 | task 9117 | n_gen = 200, tg = 33.10 t/s, tg_3s = 32.96 t/s 6.08.526.690 I slot print_timing: id 0 | task 8293 | prompt eval time = 593.25 ms / 455 tokens ( 1.30 ms per token, 766.97 tokens per second) 6.08.526.696 I slot print_timing: id 0 | task 8293 | eval time = 32923.30 ms / 1024 tokens ( 32.18 ms per token, 31.07 tokens per second) 6.08.526.697 I slot print_timing: id 0 | task 8293 | total time = 33516.55 ms / 1479 tokens 6.08.526.698 I slot print_timing: id 0 | task 8293 | graphs reused = 8769 6.08.526.698 I slot print_timing: id 0 | task 8293 | graph reallocs = 0 / 0 (same size) / (changed size) 6.08.526.798 I slot release: id 0 | task 8293 | stop processing: n_tokens = 2153, truncated = 0 6.08.555.228 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.496 6.08.561.059 I slot launch_slot_: id 0 | task 9324 | processing task, is_child = 0 6.10.070.154 I slot print_timing: id 1 | task 8991 | n_gen = 362, tg = 29.98 t/s, tg_3s = 26.99 t/s 6.10.101.094 I slot print_timing: id 3 | task 8510 | n_gen = 842, tg = 30.44 t/s, tg_3s = 27.00 t/s 6.11.427.926 I slot print_timing: id 2 | task 9117 | n_gen = 282, tg = 31.11 t/s, tg_3s = 27.13 t/s 6.12.179.163 I slot print_timing: id 0 | task 9324 | n_gen = 101, tg = 33.17 t/s, tg_3s = 33.51 t/s 6.13.089.639 I slot print_timing: id 1 | task 8991 | n_gen = 463, tg = 30.68 t/s, tg_3s = 33.45 t/s 6.13.121.696 I slot print_timing: id 3 | task 8510 | n_gen = 943, tg = 30.74 t/s, tg_3s = 33.44 t/s 6.13.305.025 I slot print_timing: id 2 | task 9117 | prompt eval time = 624.87 ms / 472 tokens ( 1.32 ms per token, 755.36 tokens per second) 6.13.305.032 I slot print_timing: id 2 | task 9117 | eval time = 10910.83 ms / 345 tokens ( 31.72 ms per token, 31.53 tokens per second) 6.13.305.033 I slot print_timing: id 2 | task 9117 | total time = 11535.70 ms / 817 tokens 6.13.305.033 I slot print_timing: id 2 | task 9117 | graphs reused = 8906 6.13.305.034 I slot print_timing: id 2 | task 9117 | graph reallocs = 0 / 0 (same size) / (changed size) 6.13.305.131 I slot release: id 2 | task 9117 | stop processing: n_tokens = 1511, truncated = 0 6.13.339.677 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.707 6.13.339.710 I slot launch_slot_: id 2 | task 9466 | processing task, is_child = 0 6.14.750.630 I slot print_timing: id 3 | task 8510 | prompt eval time = 433.66 ms / 273 tokens ( 1.59 ms per token, 629.52 tokens per second) 6.14.750.637 I slot print_timing: id 3 | task 8510 | eval time = 32277.65 ms / 979 tokens ( 33.00 ms per token, 30.30 tokens per second) 6.14.750.638 I slot print_timing: id 3 | task 8510 | total time = 32711.32 ms / 1252 tokens 6.14.750.638 I slot print_timing: id 3 | task 8510 | graphs reused = 8932 6.14.750.639 I slot print_timing: id 3 | task 8510 | graph reallocs = 0 / 0 (same size) / (changed size) 6.14.750.734 I slot release: id 3 | task 8510 | stop processing: n_tokens = 2129, truncated = 0 6.14.777.594 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.502 6.14.777.620 I slot launch_slot_: id 3 | task 9497 | processing task, is_child = 0 6.15.188.504 I slot print_timing: id 0 | task 9324 | n_gen = 171, tg = 28.22 t/s, tg_3s = 23.26 t/s 6.15.422.576 I slot print_timing: id 1 | task 8991 | prompt eval time = 621.69 ms / 464 tokens ( 1.34 ms per token, 746.35 tokens per second) 6.15.422.583 I slot print_timing: id 1 | task 8991 | eval time = 17393.23 ms / 509 tokens ( 34.24 ms per token, 29.21 tokens per second) 6.15.422.586 I slot print_timing: id 1 | task 8991 | total time = 18014.92 ms / 973 tokens 6.15.422.586 I slot print_timing: id 1 | task 8991 | graphs reused = 8937 6.15.422.587 I slot print_timing: id 1 | task 8991 | graph reallocs = 0 / 0 (same size) / (changed size) 6.15.422.711 I slot release: id 1 | task 8991 | stop processing: n_tokens = 1642, truncated = 0 6.15.458.412 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.650 6.15.458.449 I slot launch_slot_: id 1 | task 9507 | processing task, is_child = 0 6.17.901.571 I slot print_timing: id 2 | task 9466 | n_gen = 100, tg = 24.96 t/s, tg_3s = 25.21 t/s 6.18.201.386 I slot print_timing: id 0 | task 9324 | n_gen = 251, tg = 27.67 t/s, tg_3s = 26.55 t/s 6.18.804.387 I slot print_timing: id 3 | task 9497 | n_gen = 100, tg = 27.78 t/s, tg_3s = 28.06 t/s 6.19.133.852 I slot print_timing: id 1 | task 9507 | n_gen = 102, tg = 33.34 t/s, tg_3s = 33.67 t/s 6.20.912.631 I slot print_timing: id 2 | task 9466 | n_gen = 200, tg = 28.52 t/s, tg_3s = 33.21 t/s 6.21.209.131 I slot print_timing: id 0 | task 9324 | n_gen = 351, tg = 29.06 t/s, tg_3s = 33.25 t/s 6.21.818.176 I slot print_timing: id 3 | task 9497 | n_gen = 200, tg = 30.26 t/s, tg_3s = 33.18 t/s 6.22.150.872 I slot print_timing: id 1 | task 9507 | n_gen = 202, tg = 33.24 t/s, tg_3s = 33.15 t/s 6.23.929.953 I slot print_timing: id 2 | task 9466 | n_gen = 300, tg = 29.92 t/s, tg_3s = 33.14 t/s 6.24.233.744 I slot print_timing: id 0 | task 9324 | n_gen = 451, tg = 29.86 t/s, tg_3s = 33.06 t/s 6.24.836.981 I slot print_timing: id 3 | task 9497 | n_gen = 300, tg = 31.16 t/s, tg_3s = 33.13 t/s 6.25.135.552 I slot print_timing: id 0 | task 9324 | prompt eval time = 603.69 ms / 474 tokens ( 1.27 ms per token, 785.17 tokens per second) 6.25.135.558 I slot print_timing: id 0 | task 9324 | eval time = 15970.79 ms / 481 tokens ( 33.27 ms per token, 30.05 tokens per second) 6.25.135.559 I slot print_timing: id 0 | task 9324 | total time = 16574.48 ms / 955 tokens 6.25.135.559 I slot print_timing: id 0 | task 9324 | graphs reused = 9235 6.25.135.560 I slot print_timing: id 0 | task 9324 | graph reallocs = 0 / 0 (same size) / (changed size) 6.25.135.647 I slot release: id 0 | task 9324 | stop processing: n_tokens = 1629, truncated = 0 6.25.162.246 I slot print_timing: id 1 | task 9507 | n_gen = 302, tg = 33.23 t/s, tg_3s = 33.21 t/s 6.25.163.132 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.656 6.25.163.159 I slot launch_slot_: id 0 | task 9811 | processing task, is_child = 0 6.26.936.046 I slot print_timing: id 2 | task 9466 | n_gen = 379, tg = 29.07 t/s, tg_3s = 26.28 t/s 6.27.845.817 I slot print_timing: id 3 | task 9497 | n_gen = 379, tg = 29.99 t/s, tg_3s = 26.26 t/s 6.28.176.628 I slot print_timing: id 1 | task 9507 | n_gen = 381, tg = 31.48 t/s, tg_3s = 26.21 t/s 6.28.896.508 I slot print_timing: id 0 | task 9811 | n_gen = 101, tg = 33.14 t/s, tg_3s = 33.47 t/s 6.29.950.018 I slot print_timing: id 2 | task 9466 | n_gen = 479, tg = 29.85 t/s, tg_3s = 33.18 t/s 6.30.847.712 I slot print_timing: id 3 | task 9497 | n_gen = 479, tg = 30.63 t/s, tg_3s = 33.31 t/s 6.31.203.733 I slot print_timing: id 1 | task 9507 | n_gen = 482, tg = 31.86 t/s, tg_3s = 33.37 t/s 6.31.925.128 I slot print_timing: id 0 | task 9811 | n_gen = 202, tg = 33.24 t/s, tg_3s = 33.35 t/s 6.32.973.365 I slot print_timing: id 2 | task 9466 | n_gen = 580, tg = 30.41 t/s, tg_3s = 33.41 t/s 6.33.003.731 I slot print_timing: id 2 | task 9466 | prompt eval time = 595.46 ms / 440 tokens ( 1.35 ms per token, 738.92 tokens per second) 6.33.003.736 I slot print_timing: id 2 | task 9466 | eval time = 19068.55 ms / 581 tokens ( 32.88 ms per token, 30.42 tokens per second) 6.33.003.737 I slot print_timing: id 2 | task 9466 | total time = 19664.01 ms / 1021 tokens 6.33.003.738 I slot print_timing: id 2 | task 9466 | graphs reused = 9471 6.33.003.738 I slot print_timing: id 2 | task 9466 | graph reallocs = 0 / 0 (same size) / (changed size) 6.33.003.828 I slot release: id 2 | task 9466 | stop processing: n_tokens = 1715, truncated = 0 6.33.038.638 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.623 6.33.038.671 I slot launch_slot_: id 2 | task 10053 | processing task, is_child = 0 6.33.875.157 I slot print_timing: id 3 | task 9497 | n_gen = 561, tg = 30.05 t/s, tg_3s = 27.09 t/s 6.34.204.456 I slot print_timing: id 1 | task 9507 | n_gen = 563, tg = 31.05 t/s, tg_3s = 26.99 t/s 6.34.948.960 I slot print_timing: id 0 | task 9811 | n_gen = 284, tg = 31.20 t/s, tg_3s = 27.12 t/s 6.36.481.001 I slot print_timing: id 1 | task 9507 | prompt eval time = 645.82 ms / 486 tokens ( 1.33 ms per token, 752.53 tokens per second) 6.36.481.007 I slot print_timing: id 1 | task 9507 | eval time = 20376.72 ms / 640 tokens ( 31.89 ms per token, 31.36 tokens per second) 6.36.481.008 I slot print_timing: id 1 | task 9507 | total time = 21022.54 ms / 1126 tokens 6.36.481.008 I slot print_timing: id 1 | task 9507 | graphs reused = 9564 6.36.481.009 I slot print_timing: id 1 | task 9507 | graph reallocs = 0 / 0 (same size) / (changed size) 6.36.481.096 I slot release: id 1 | task 9507 | stop processing: n_tokens = 1795, truncated = 0 6.36.515.120 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.595 6.36.515.153 I slot launch_slot_: id 1 | task 10152 | processing task, is_child = 0 6.37.106.846 I slot print_timing: id 3 | task 9497 | n_gen = 651, tg = 29.73 t/s, tg_3s = 27.85 t/s 6.37.196.139 I slot print_timing: id 2 | task 10053 | n_gen = 100, tg = 28.00 t/s, tg_3s = 28.29 t/s 6.37.968.160 I slot print_timing: id 0 | task 9811 | n_gen = 366, tg = 30.19 t/s, tg_3s = 27.16 t/s 6.40.130.840 I slot print_timing: id 3 | task 9497 | n_gen = 752, tg = 30.17 t/s, tg_3s = 33.40 t/s 6.40.189.721 I slot print_timing: id 1 | task 10152 | n_gen = 103, tg = 33.73 t/s, tg_3s = 34.06 t/s 6.40.220.329 I slot print_timing: id 2 | task 10053 | n_gen = 202, tg = 30.64 t/s, tg_3s = 33.73 t/s 6.40.992.643 I slot print_timing: id 0 | task 9811 | n_gen = 468, tg = 30.90 t/s, tg_3s = 33.72 t/s 6.43.131.363 I slot print_timing: id 3 | task 9497 | n_gen = 852, tg = 30.51 t/s, tg_3s = 33.33 t/s 6.43.190.255 I slot print_timing: id 1 | task 10152 | n_gen = 203, tg = 33.53 t/s, tg_3s = 33.33 t/s 6.43.250.302 I slot print_timing: id 2 | task 10053 | n_gen = 303, tg = 31.49 t/s, tg_3s = 33.33 t/s 6.44.003.257 I slot print_timing: id 0 | task 9811 | n_gen = 568, tg = 31.28 t/s, tg_3s = 33.22 t/s 6.46.149.773 I slot print_timing: id 3 | task 9497 | n_gen = 952, tg = 30.77 t/s, tg_3s = 33.13 t/s 6.46.207.591 I slot print_timing: id 1 | task 10152 | n_gen = 303, tg = 33.40 t/s, tg_3s = 33.14 t/s 6.46.268.057 I slot print_timing: id 2 | task 10053 | n_gen = 403, tg = 31.89 t/s, tg_3s = 33.14 t/s 6.47.019.971 I slot print_timing: id 0 | task 9811 | n_gen = 668, tg = 31.55 t/s, tg_3s = 33.15 t/s 6.48.316.354 I slot print_timing: id 3 | task 9497 | prompt eval time = 463.46 ms / 306 tokens ( 1.51 ms per token, 660.25 tokens per second) 6.48.316.361 I slot print_timing: id 3 | task 9497 | eval time = 33075.26 ms / 1024 tokens ( 32.33 ms per token, 30.93 tokens per second) 6.48.316.362 I slot print_timing: id 3 | task 9497 | total time = 33538.73 ms / 1330 tokens 6.48.316.363 I slot print_timing: id 3 | task 9497 | graphs reused = 9934 6.48.316.363 I slot print_timing: id 3 | task 9497 | graph reallocs = 0 / 0 (same size) / (changed size) 6.48.316.455 I slot release: id 3 | task 9497 | stop processing: n_tokens = 2207, truncated = 0 6.48.343.608 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.484 6.48.349.394 I slot launch_slot_: id 3 | task 10528 | processing task, is_child = 0 6.48.906.851 I slot print_timing: id 2 | task 10053 | prompt eval time = 622.07 ms / 468 tokens ( 1.33 ms per token, 752.32 tokens per second) 6.48.906.857 I slot print_timing: id 2 | task 10053 | eval time = 15246.10 ms / 479 tokens ( 31.90 ms per token, 31.35 tokens per second) 6.48.906.858 I slot print_timing: id 2 | task 10053 | total time = 15868.17 ms / 947 tokens 6.48.906.859 I slot print_timing: id 2 | task 10053 | graphs reused = 9938 6.48.906.860 I slot print_timing: id 2 | task 10053 | graph reallocs = 0 / 0 (same size) / (changed size) 6.48.906.946 I slot release: id 2 | task 10053 | stop processing: n_tokens = 1641, truncated = 0 6.48.941.567 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.651 6.48.941.604 I slot launch_slot_: id 2 | task 10537 | processing task, is_child = 0 6.49.489.558 I slot print_timing: id 1 | task 10152 | n_gen = 383, tg = 31.00 t/s, tg_3s = 24.38 t/s 6.50.030.993 I slot print_timing: id 0 | task 9811 | n_gen = 738, tg = 30.51 t/s, tg_3s = 23.25 t/s 6.52.277.375 I slot print_timing: id 3 | task 10528 | n_gen = 100, tg = 28.13 t/s, tg_3s = 28.41 t/s 6.52.517.746 I slot print_timing: id 1 | task 10152 | n_gen = 483, tg = 31.40 t/s, tg_3s = 33.02 t/s 6.52.548.792 I slot print_timing: id 2 | task 10537 | n_gen = 101, tg = 33.32 t/s, tg_3s = 33.66 t/s 6.53.031.592 I slot print_timing: id 0 | task 9811 | n_gen = 838, tg = 30.83 t/s, tg_3s = 33.33 t/s 6.55.283.864 I slot print_timing: id 3 | task 10528 | n_gen = 200, tg = 30.49 t/s, tg_3s = 33.26 t/s 6.55.522.682 I slot print_timing: id 1 | task 10152 | n_gen = 583, tg = 31.70 t/s, tg_3s = 33.28 t/s 6.55.553.424 I slot print_timing: id 2 | task 10537 | n_gen = 201, tg = 33.30 t/s, tg_3s = 33.28 t/s 6.56.060.654 I slot print_timing: id 0 | task 9811 | n_gen = 939, tg = 31.08 t/s, tg_3s = 33.34 t/s 6.58.302.635 I slot print_timing: id 3 | task 10528 | n_gen = 301, tg = 31.43 t/s, tg_3s = 33.46 t/s 6.58.541.369 I slot print_timing: id 1 | task 10152 | n_gen = 684, tg = 31.95 t/s, tg_3s = 33.46 t/s 6.58.571.478 I slot print_timing: id 2 | task 10537 | n_gen = 302, tg = 33.36 t/s, tg_3s = 33.47 t/s 6.58.599.620 I slot print_timing: id 0 | task 9811 | prompt eval time = 715.41 ms / 528 tokens ( 1.35 ms per token, 738.04 tokens per second) 6.58.599.622 I slot print_timing: id 0 | task 9811 | eval time = 32721.04 ms / 1024 tokens ( 31.99 ms per token, 31.26 tokens per second) 6.58.599.623 I slot print_timing: id 0 | task 9811 | total time = 33436.46 ms / 1552 tokens 6.58.599.624 I slot print_timing: id 0 | task 9811 | graphs reused = 10238 6.58.599.625 I slot print_timing: id 0 | task 9811 | graph reallocs = 0 / 0 (same size) / (changed size) 6.58.599.716 I slot release: id 0 | task 9811 | stop processing: n_tokens = 2226, truncated = 0 6.58.627.510 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.480 6.58.633.684 I slot launch_slot_: id 0 | task 10843 | processing task, is_child = 0 7.01.332.568 I slot print_timing: id 3 | task 10528 | n_gen = 383, tg = 30.38 t/s, tg_3s = 27.06 t/s 7.01.541.694 I slot print_timing: id 1 | task 10152 | n_gen = 765, tg = 31.34 t/s, tg_3s = 27.00 t/s 7.01.572.208 I slot print_timing: id 2 | task 10537 | n_gen = 383, tg = 31.77 t/s, tg_3s = 26.99 t/s 7.01.755.057 I slot print_timing: id 2 | task 10537 | prompt eval time = 606.41 ms / 452 tokens ( 1.34 ms per token, 745.37 tokens per second) 7.01.755.063 I slot print_timing: id 2 | task 10537 | eval time = 12207.03 ms / 389 tokens ( 31.46 ms per token, 31.78 tokens per second) 7.01.755.064 I slot print_timing: id 2 | task 10537 | total time = 12813.45 ms / 841 tokens 7.01.755.064 I slot print_timing: id 2 | task 10537 | graphs reused = 10321 7.01.755.065 I slot print_timing: id 2 | task 10537 | graph reallocs = 0 / 0 (same size) / (changed size) 7.01.755.153 I slot release: id 2 | task 10537 | stop processing: n_tokens = 1535, truncated = 0 7.01.789.692 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.696 7.01.789.722 I slot launch_slot_: id 2 | task 10930 | processing task, is_child = 0 7.02.781.769 I slot print_timing: id 0 | task 10843 | n_gen = 100, tg = 27.98 t/s, tg_3s = 28.26 t/s 7.04.348.558 I slot print_timing: id 3 | task 10528 | n_gen = 466, tg = 29.82 t/s, tg_3s = 27.52 t/s 7.04.557.594 I slot print_timing: id 1 | task 10152 | n_gen = 848, tg = 30.92 t/s, tg_3s = 27.52 t/s 7.05.397.315 I slot print_timing: id 2 | task 10930 | n_gen = 102, tg = 33.58 t/s, tg_3s = 33.91 t/s 7.05.786.491 I slot print_timing: id 0 | task 10843 | n_gen = 201, tg = 30.57 t/s, tg_3s = 33.61 t/s 7.07.145.819 I slot print_timing: id 3 | task 10528 | prompt eval time = 408.14 ms / 246 tokens ( 1.66 ms per token, 602.74 tokens per second) 7.07.145.823 I slot print_timing: id 3 | task 10528 | eval time = 18388.27 ms / 559 tokens ( 32.95 ms per token, 30.35 tokens per second) 7.07.145.824 I slot print_timing: id 3 | task 10528 | total time = 18796.41 ms / 805 tokens 7.07.145.824 I slot print_timing: id 3 | task 10528 | graphs reused = 10478 7.07.145.825 I slot print_timing: id 3 | task 10528 | graph reallocs = 0 / 0 (same size) / (changed size) 7.07.145.911 I slot release: id 3 | task 10528 | stop processing: n_tokens = 1682, truncated = 0 7.07.171.969 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.635 7.07.171.998 I slot launch_slot_: id 3 | task 11093 | processing task, is_child = 0 7.07.562.631 I slot print_timing: id 1 | task 10152 | n_gen = 936, tg = 30.76 t/s, tg_3s = 29.28 t/s 7.08.402.803 I slot print_timing: id 2 | task 10930 | n_gen = 189, tg = 31.27 t/s, tg_3s = 28.95 t/s 7.08.796.849 I slot print_timing: id 0 | task 10843 | n_gen = 288, tg = 30.04 t/s, tg_3s = 28.90 t/s 7.10.242.795 I slot print_timing: id 1 | task 10152 | prompt eval time = 650.66 ms / 496 tokens ( 1.31 ms per token, 762.30 tokens per second) 7.10.242.800 I slot print_timing: id 1 | task 10152 | eval time = 33076.97 ms / 1024 tokens ( 32.33 ms per token, 30.93 tokens per second) 7.10.242.800 I slot print_timing: id 1 | task 10152 | total time = 33727.63 ms / 1520 tokens 7.10.242.801 I slot print_timing: id 1 | task 10152 | graphs reused = 10564 7.10.242.801 I slot print_timing: id 1 | task 10152 | graph reallocs = 0 / 0 (same size) / (changed size) 7.10.242.889 I slot release: id 1 | task 10152 | stop processing: n_tokens = 2189, truncated = 0 7.10.277.541 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.488 7.10.283.931 I slot launch_slot_: id 1 | task 11184 | processing task, is_child = 0 7.11.209.482 I slot print_timing: id 3 | task 11093 | n_gen = 100, tg = 27.54 t/s, tg_3s = 27.82 t/s 7.11.415.237 I slot print_timing: id 2 | task 10930 | n_gen = 269, tg = 29.69 t/s, tg_3s = 26.56 t/s 7.11.798.043 I slot print_timing: id 0 | task 10843 | n_gen = 368, tg = 29.23 t/s, tg_3s = 26.66 t/s 7.13.957.561 I slot print_timing: id 1 | task 11184 | n_gen = 102, tg = 33.39 t/s, tg_3s = 33.73 t/s 7.14.230.831 I slot print_timing: id 3 | task 11093 | n_gen = 201, tg = 30.23 t/s, tg_3s = 33.43 t/s 7.14.441.399 I slot print_timing: id 2 | task 10930 | n_gen = 370, tg = 30.62 t/s, tg_3s = 33.38 t/s 7.14.802.543 I slot print_timing: id 0 | task 10843 | n_gen = 468, tg = 30.01 t/s, tg_3s = 33.28 t/s 7.16.879.189 I slot print_timing: id 0 | task 10843 | prompt eval time = 609.40 ms / 479 tokens ( 1.27 ms per token, 786.02 tokens per second) 7.16.879.194 I slot print_timing: id 0 | task 10843 | eval time = 17636.10 ms / 538 tokens ( 32.84 ms per token, 30.45 tokens per second) 7.16.879.194 I slot print_timing: id 0 | task 10843 | total time = 18245.50 ms / 1017 tokens 7.16.879.195 I slot print_timing: id 0 | task 10843 | graphs reused = 10761 7.16.879.195 I slot print_timing: id 0 | task 10843 | graph reallocs = 0 / 0 (same size) / (changed size) 7.16.879.274 I slot release: id 0 | task 10843 | stop processing: n_tokens = 1703, truncated = 0 7.16.907.519 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.627 7.16.907.559 I slot launch_slot_: id 0 | task 11387 | processing task, is_child = 0 7.17.456.663 I slot print_timing: id 1 | task 11184 | n_gen = 202, tg = 30.81 t/s, tg_3s = 28.58 t/s 7.17.456.964 I slot print_timing: id 2 | task 10930 | n_gen = 454, tg = 30.07 t/s, tg_3s = 27.86 t/s 7.17.457.251 I slot print_timing: id 3 | task 11093 | n_gen = 292, tg = 29.57 t/s, tg_3s = 28.20 t/s 7.19.937.872 I slot print_timing: id 3 | task 11093 | prompt eval time = 442.79 ms / 287 tokens ( 1.54 ms per token, 648.16 tokens per second) 7.19.937.878 I slot print_timing: id 3 | task 11093 | eval time = 12323.07 ms / 375 tokens ( 32.95 ms per token, 30.35 tokens per second) 7.19.937.879 I slot print_timing: id 3 | task 11093 | total time = 12765.87 ms / 662 tokens 7.19.937.879 I slot print_timing: id 3 | task 11093 | graphs reused = 10843 7.19.937.880 I slot print_timing: id 3 | task 11093 | graph reallocs = 0 / 0 (same size) / (changed size) 7.19.937.972 I slot release: id 3 | task 11093 | stop processing: n_tokens = 1539, truncated = 0 7.19.965.074 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.694 7.19.965.102 I slot launch_slot_: id 3 | task 11473 | processing task, is_child = 0 7.20.480.616 I slot print_timing: id 1 | task 11184 | n_gen = 291, tg = 30.37 t/s, tg_3s = 29.43 t/s 7.20.480.949 I slot print_timing: id 2 | task 10930 | n_gen = 543, tg = 29.96 t/s, tg_3s = 29.43 t/s 7.20.808.177 I slot print_timing: id 0 | task 11387 | n_gen = 100, tg = 29.99 t/s, tg_3s = 30.29 t/s 7.23.399.442 I slot print_timing: id 3 | task 11473 | n_gen = 102, tg = 33.58 t/s, tg_3s = 33.92 t/s 7.23.488.762 I slot print_timing: id 1 | task 11184 | n_gen = 392, tg = 31.14 t/s, tg_3s = 33.58 t/s 7.23.489.226 I slot print_timing: id 2 | task 10930 | n_gen = 644, tg = 30.47 t/s, tg_3s = 33.57 t/s 7.23.817.964 I slot print_timing: id 0 | task 11387 | n_gen = 201, tg = 31.69 t/s, tg_3s = 33.56 t/s 7.26.423.534 I slot print_timing: id 3 | task 11473 | n_gen = 203, tg = 33.49 t/s, tg_3s = 33.40 t/s 7.26.512.229 I slot print_timing: id 1 | task 11184 | n_gen = 493, tg = 31.58 t/s, tg_3s = 33.41 t/s 7.26.512.740 I slot print_timing: id 2 | task 10930 | n_gen = 745, tg = 30.84 t/s, tg_3s = 33.40 t/s 7.26.845.254 I slot print_timing: id 0 | task 11387 | n_gen = 302, tg = 32.23 t/s, tg_3s = 33.36 t/s 7.29.431.396 I slot print_timing: id 3 | task 11473 | n_gen = 303, tg = 33.41 t/s, tg_3s = 33.25 t/s 7.29.520.418 I slot print_timing: id 1 | task 11184 | n_gen = 593, tg = 31.85 t/s, tg_3s = 33.24 t/s 7.29.520.870 I slot print_timing: id 2 | task 10930 | n_gen = 845, tg = 31.11 t/s, tg_3s = 33.24 t/s 7.29.848.678 I slot print_timing: id 0 | task 11387 | n_gen = 402, tg = 32.49 t/s, tg_3s = 33.30 t/s 7.30.149.316 I slot print_timing: id 3 | task 11473 | prompt eval time = 426.97 ms / 262 tokens ( 1.63 ms per token, 613.62 tokens per second) 7.30.149.323 I slot print_timing: id 3 | task 11473 | eval time = 9757.23 ms / 327 tokens ( 29.93 ms per token, 33.41 tokens per second) 7.30.149.325 I slot print_timing: id 3 | task 11473 | total time = 10184.20 ms / 589 tokens 7.30.149.326 I slot print_timing: id 3 | task 11473 | graphs reused = 11167 7.30.149.326 I slot print_timing: id 3 | task 11473 | graph reallocs = 0 / 0 (same size) / (changed size) 7.30.149.426 I slot release: id 3 | task 11473 | stop processing: n_tokens = 1466, truncated = 0 7.30.176.878 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.881 (> 0.100 thold), f_keep = 0.729 7.30.176.907 I slot launch_slot_: id 3 | task 11803 | processing task, is_child = 0 7.32.547.203 I slot print_timing: id 1 | task 11184 | n_gen = 680, tg = 31.41 t/s, tg_3s = 28.74 t/s 7.32.547.754 I slot print_timing: id 2 | task 10930 | n_gen = 932, tg = 30.87 t/s, tg_3s = 28.74 t/s 7.32.872.925 I slot print_timing: id 0 | task 11387 | n_gen = 489, tg = 31.76 t/s, tg_3s = 28.77 t/s 7.33.682.145 I slot print_timing: id 1 | task 11184 | prompt eval time = 649.20 ms / 494 tokens ( 1.31 ms per token, 760.94 tokens per second) 7.33.682.152 I slot print_timing: id 1 | task 11184 | eval time = 22749.01 ms / 718 tokens ( 31.73 ms per token, 31.52 tokens per second) 7.33.682.153 I slot print_timing: id 1 | task 11184 | total time = 23398.20 ms / 1212 tokens 7.33.682.154 I slot print_timing: id 1 | task 11184 | graphs reused = 11266 7.33.682.154 I slot print_timing: id 1 | task 11184 | graph reallocs = 0 / 0 (same size) / (changed size) 7.33.682.249 I slot release: id 1 | task 11184 | stop processing: n_tokens = 1881, truncated = 0 7.33.683.321 I slot print_timing: id 3 | task 11803 | n_gen = 102, tg = 33.46 t/s, tg_3s = 33.79 t/s 7.33.717.100 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.568 7.33.717.131 I slot launch_slot_: id 1 | task 11908 | processing task, is_child = 0 7.34.427.052 I slot print_timing: id 0 | task 11387 | prompt eval time = 599.45 ms / 465 tokens ( 1.29 ms per token, 775.71 tokens per second) 7.34.427.059 I slot print_timing: id 0 | task 11387 | eval time = 16920.03 ms / 522 tokens ( 32.48 ms per token, 30.79 tokens per second) 7.34.427.059 I slot print_timing: id 0 | task 11387 | total time = 17519.49 ms / 987 tokens 7.34.427.060 I slot print_timing: id 0 | task 11387 | graphs reused = 11268 7.34.427.061 I slot print_timing: id 0 | task 11387 | graph reallocs = 0 / 0 (same size) / (changed size) 7.34.427.146 I slot release: id 0 | task 11387 | stop processing: n_tokens = 1673, truncated = 0 7.34.456.142 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.638 7.34.456.180 I slot launch_slot_: id 0 | task 11915 | processing task, is_child = 0 7.35.555.762 I slot print_timing: id 2 | task 10930 | n_gen = 996, tg = 30.00 t/s, tg_3s = 21.28 t/s 7.36.387.207 I slot print_timing: id 2 | task 10930 | prompt eval time = 600.01 ms / 449 tokens ( 1.34 ms per token, 748.32 tokens per second) 7.36.387.214 I slot print_timing: id 2 | task 10930 | eval time = 33997.46 ms / 1024 tokens ( 33.23 ms per token, 30.09 tokens per second) 7.36.387.214 I slot print_timing: id 2 | task 10930 | total time = 34597.47 ms / 1473 tokens 7.36.387.215 I slot print_timing: id 2 | task 10930 | graphs reused = 11313 7.36.387.216 I slot print_timing: id 2 | task 10930 | graph reallocs = 0 / 0 (same size) / (changed size) 7.36.387.318 I slot release: id 2 | task 10930 | stop processing: n_tokens = 2167, truncated = 0 7.36.421.705 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.493 7.36.427.545 I slot launch_slot_: id 2 | task 11964 | processing task, is_child = 0 7.36.987.211 I slot print_timing: id 3 | task 11803 | n_gen = 158, tg = 24.83 t/s, tg_3s = 16.95 t/s 7.38.392.768 I slot print_timing: id 1 | task 11908 | n_gen = 100, tg = 24.42 t/s, tg_3s = 24.66 t/s 7.38.570.728 I slot print_timing: id 0 | task 11915 | n_gen = 100, tg = 28.02 t/s, tg_3s = 28.30 t/s 7.40.003.705 I slot print_timing: id 3 | task 11803 | n_gen = 258, tg = 27.52 t/s, tg_3s = 33.15 t/s 7.40.059.509 I slot print_timing: id 2 | task 11964 | n_gen = 102, tg = 33.50 t/s, tg_3s = 33.83 t/s 7.41.394.942 I slot print_timing: id 1 | task 11908 | n_gen = 201, tg = 28.34 t/s, tg_3s = 33.64 t/s 7.41.572.385 I slot print_timing: id 0 | task 11915 | n_gen = 201, tg = 30.60 t/s, tg_3s = 33.65 t/s 7.43.014.230 I slot print_timing: id 3 | task 11803 | n_gen = 359, tg = 28.99 t/s, tg_3s = 33.55 t/s 7.43.073.940 I slot print_timing: id 2 | task 11964 | n_gen = 203, tg = 33.50 t/s, tg_3s = 33.51 t/s 7.44.401.867 I slot print_timing: id 1 | task 11908 | n_gen = 301, tg = 29.81 t/s, tg_3s = 33.26 t/s 7.44.578.135 I slot print_timing: id 0 | task 11915 | n_gen = 301, tg = 31.44 t/s, tg_3s = 33.27 t/s 7.46.020.931 I slot print_timing: id 3 | task 11803 | n_gen = 459, tg = 29.83 t/s, tg_3s = 33.26 t/s 7.46.081.456 I slot print_timing: id 2 | task 11964 | n_gen = 303, tg = 33.42 t/s, tg_3s = 33.25 t/s 7.46.772.307 I slot print_timing: id 0 | task 11915 | prompt eval time = 580.97 ms / 437 tokens ( 1.33 ms per token, 752.20 tokens per second) 7.46.772.314 I slot print_timing: id 0 | task 11915 | eval time = 11735.15 ms / 374 tokens ( 31.46 ms per token, 31.78 tokens per second) 7.46.772.315 I slot print_timing: id 0 | task 11915 | total time = 12316.12 ms / 811 tokens 7.46.772.316 I slot print_timing: id 0 | task 11915 | graphs reused = 11636 7.46.772.316 I slot print_timing: id 0 | task 11915 | graph reallocs = 0 / 0 (same size) / (changed size) 7.46.772.403 I slot release: id 0 | task 11915 | stop processing: n_tokens = 1497, truncated = 0 7.46.801.619 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.713 7.46.801.650 I slot launch_slot_: id 0 | task 12293 | processing task, is_child = 0 7.47.425.193 I slot print_timing: id 1 | task 11908 | n_gen = 384, tg = 29.27 t/s, tg_3s = 27.45 t/s 7.49.021.036 I slot print_timing: id 3 | task 11803 | n_gen = 541, tg = 29.42 t/s, tg_3s = 27.33 t/s 7.49.111.237 I slot print_timing: id 2 | task 11964 | n_gen = 386, tg = 31.91 t/s, tg_3s = 27.39 t/s 7.50.406.840 I slot print_timing: id 0 | task 12293 | n_gen = 101, tg = 33.19 t/s, tg_3s = 33.52 t/s 7.50.437.667 I slot print_timing: id 1 | task 11908 | n_gen = 484, tg = 30.00 t/s, tg_3s = 33.20 t/s 7.51.996.816 I slot print_timing: id 3 | task 11803 | prompt eval time = 487.93 ms / 334 tokens ( 1.46 ms per token, 684.53 tokens per second) 7.51.996.822 I slot print_timing: id 3 | task 11803 | eval time = 21331.97 ms / 640 tokens ( 33.38 ms per token, 29.96 tokens per second) 7.51.996.823 I slot print_timing: id 3 | task 11803 | total time = 21819.90 ms / 974 tokens 7.51.996.824 I slot print_timing: id 3 | task 11803 | graphs reused = 11788 7.51.996.825 I slot print_timing: id 3 | task 11803 | graph reallocs = 0 / 0 (same size) / (changed size) 7.51.996.921 I slot release: id 3 | task 11803 | stop processing: n_tokens = 1851, truncated = 0 7.52.024.142 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.577 7.52.024.169 I slot launch_slot_: id 3 | task 12450 | processing task, is_child = 0 7.52.404.972 I slot print_timing: id 2 | task 11964 | n_gen = 484, tg = 31.44 t/s, tg_3s = 29.75 t/s 7.53.422.795 I slot print_timing: id 0 | task 12293 | n_gen = 189, tg = 31.18 t/s, tg_3s = 29.18 t/s 7.53.454.426 I slot print_timing: id 1 | task 11908 | n_gen = 572, tg = 29.87 t/s, tg_3s = 29.17 t/s 7.55.009.878 I slot print_timing: id 1 | task 11908 | prompt eval time = 620.96 ms / 465 tokens ( 1.34 ms per token, 748.84 tokens per second) 7.55.009.885 I slot print_timing: id 1 | task 11908 | eval time = 20671.78 ms / 624 tokens ( 33.18 ms per token, 30.14 tokens per second) 7.55.009.885 I slot print_timing: id 1 | task 11908 | total time = 21292.74 ms / 1089 tokens 7.55.009.886 I slot print_timing: id 1 | task 11908 | graphs reused = 11872 7.55.009.887 I slot print_timing: id 1 | task 11908 | graph reallocs = 0 / 0 (same size) / (changed size) 7.55.009.978 I slot release: id 1 | task 11908 | stop processing: n_tokens = 1758, truncated = 0 7.55.045.356 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.608 7.55.045.389 I slot launch_slot_: id 1 | task 12539 | processing task, is_child = 0 7.55.610.898 I slot print_timing: id 2 | task 11964 | n_gen = 572, tg = 30.75 t/s, tg_3s = 27.45 t/s 7.56.009.706 I slot print_timing: id 3 | task 12450 | n_gen = 100, tg = 27.86 t/s, tg_3s = 28.14 t/s 7.56.433.935 I slot print_timing: id 0 | task 12293 | n_gen = 270, tg = 29.76 t/s, tg_3s = 26.90 t/s 7.58.637.080 I slot print_timing: id 2 | task 11964 | n_gen = 671, tg = 31.03 t/s, tg_3s = 32.71 t/s 7.58.696.837 I slot print_timing: id 1 | task 12539 | n_gen = 101, tg = 33.05 t/s, tg_3s = 33.38 t/s 7.59.029.216 I slot print_timing: id 3 | task 12450 | n_gen = 200, tg = 30.28 t/s, tg_3s = 33.12 t/s 7.59.451.510 I slot print_timing: id 0 | task 12293 | n_gen = 370, tg = 30.60 t/s, tg_3s = 33.14 t/s 8.01.648.240 I slot print_timing: id 2 | task 11964 | n_gen = 772, tg = 31.34 t/s, tg_3s = 33.54 t/s 8.01.708.874 I slot print_timing: id 1 | task 12539 | n_gen = 202, tg = 33.29 t/s, tg_3s = 33.53 t/s 8.02.039.938 I slot print_timing: id 3 | task 12450 | n_gen = 301, tg = 31.30 t/s, tg_3s = 33.55 t/s 8.02.217.298 I slot print_timing: id 0 | task 12293 | prompt eval time = 592.05 ms / 455 tokens ( 1.30 ms per token, 768.52 tokens per second) 8.02.217.304 I slot print_timing: id 0 | task 12293 | eval time = 14823.59 ms / 463 tokens ( 32.09 ms per token, 31.17 tokens per second) 8.02.217.305 I slot print_timing: id 0 | task 12293 | total time = 15415.64 ms / 918 tokens 8.02.217.305 I slot print_timing: id 0 | task 12293 | graphs reused = 12088 8.02.217.306 I slot print_timing: id 0 | task 12293 | graph reallocs = 0 / 0 (same size) / (changed size) 8.02.217.396 I slot release: id 0 | task 12293 | stop processing: n_tokens = 1604, truncated = 0 8.02.244.967 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.666 8.02.244.998 I slot launch_slot_: id 0 | task 12761 | processing task, is_child = 0 8.04.652.549 I slot print_timing: id 2 | task 11964 | n_gen = 854, tg = 30.90 t/s, tg_3s = 27.29 t/s 8.04.713.650 I slot print_timing: id 1 | task 12539 | n_gen = 284, tg = 31.30 t/s, tg_3s = 27.29 t/s 8.05.044.051 I slot print_timing: id 3 | task 12450 | n_gen = 383, tg = 30.35 t/s, tg_3s = 27.30 t/s 8.05.859.253 I slot print_timing: id 0 | task 12761 | n_gen = 101, tg = 33.19 t/s, tg_3s = 33.53 t/s 8.07.668.818 I slot print_timing: id 2 | task 11964 | n_gen = 954, tg = 31.12 t/s, tg_3s = 33.15 t/s 8.07.728.757 I slot print_timing: id 1 | task 12539 | n_gen = 384, tg = 31.76 t/s, tg_3s = 33.17 t/s 8.08.064.660 I slot print_timing: id 3 | task 12450 | n_gen = 483, tg = 30.88 t/s, tg_3s = 33.11 t/s 8.08.486.199 I slot print_timing: id 2 | task 11964 | prompt eval time = 616.79 ms / 461 tokens ( 1.34 ms per token, 747.41 tokens per second) 8.08.486.207 I slot print_timing: id 2 | task 11964 | eval time = 31441.85 ms / 981 tokens ( 32.08 ms per token, 31.17 tokens per second) 8.08.486.208 I slot print_timing: id 2 | task 11964 | total time = 32058.65 ms / 1442 tokens 8.08.486.209 I slot print_timing: id 2 | task 11964 | graphs reused = 12274 8.08.486.210 I slot print_timing: id 2 | task 11964 | graph reallocs = 0 / 0 (same size) / (changed size) 8.08.486.315 I slot release: id 2 | task 11964 | stop processing: n_tokens = 2136, truncated = 0 8.08.521.069 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.500 8.08.521.103 I slot launch_slot_: id 2 | task 12952 | processing task, is_child = 0 8.09.081.974 I slot print_timing: id 0 | task 12761 | n_gen = 190, tg = 30.31 t/s, tg_3s = 27.62 t/s 8.10.734.362 I slot print_timing: id 1 | task 12539 | n_gen = 465, tg = 30.80 t/s, tg_3s = 26.95 t/s 8.11.069.517 I slot print_timing: id 3 | task 12450 | n_gen = 564, tg = 30.25 t/s, tg_3s = 26.96 t/s 8.12.088.619 I slot print_timing: id 0 | task 12761 | n_gen = 289, tg = 31.16 t/s, tg_3s = 32.93 t/s 8.12.149.149 I slot print_timing: id 2 | task 12952 | n_gen = 101, tg = 33.24 t/s, tg_3s = 33.57 t/s 8.13.752.065 I slot print_timing: id 1 | task 12539 | n_gen = 566, tg = 31.25 t/s, tg_3s = 33.47 t/s 8.14.081.229 I slot print_timing: id 3 | task 12450 | n_gen = 665, tg = 30.71 t/s, tg_3s = 33.54 t/s 8.15.118.236 I slot print_timing: id 0 | task 12761 | n_gen = 391, tg = 31.78 t/s, tg_3s = 33.67 t/s 8.15.149.588 I slot print_timing: id 2 | task 12952 | n_gen = 202, tg = 33.45 t/s, tg_3s = 33.66 t/s 8.16.553.722 I slot print_timing: id 1 | task 12539 | prompt eval time = 625.32 ms / 471 tokens ( 1.33 ms per token, 753.22 tokens per second) 8.16.553.729 I slot print_timing: id 1 | task 12539 | eval time = 20883.01 ms / 660 tokens ( 31.69 ms per token, 31.56 tokens per second) 8.16.553.731 I slot print_timing: id 1 | task 12539 | total time = 21508.32 ms / 1131 tokens 8.16.553.732 I slot print_timing: id 1 | task 12539 | graphs reused = 12520 8.16.553.733 I slot print_timing: id 1 | task 12539 | graph reallocs = 0 / 0 (same size) / (changed size) 8.16.553.849 I slot release: id 1 | task 12539 | stop processing: n_tokens = 1800, truncated = 0 8.16.589.212 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.593 8.16.589.249 I slot launch_slot_: id 1 | task 13204 | processing task, is_child = 0 8.17.187.142 I slot print_timing: id 3 | task 12450 | n_gen = 750, tg = 30.29 t/s, tg_3s = 27.37 t/s 8.18.146.992 I slot print_timing: id 0 | task 12761 | n_gen = 472, tg = 30.78 t/s, tg_3s = 26.74 t/s 8.18.178.083 I slot print_timing: id 2 | task 12952 | n_gen = 283, tg = 31.20 t/s, tg_3s = 26.75 t/s 8.20.204.247 I slot print_timing: id 3 | task 12450 | n_gen = 849, tg = 30.56 t/s, tg_3s = 32.81 t/s 8.20.262.856 I slot print_timing: id 1 | task 13204 | n_gen = 101, tg = 33.15 t/s, tg_3s = 33.49 t/s 8.21.172.868 I slot print_timing: id 0 | task 12761 | n_gen = 572, tg = 31.16 t/s, tg_3s = 33.05 t/s 8.21.204.519 I slot print_timing: id 2 | task 12952 | n_gen = 383, tg = 31.66 t/s, tg_3s = 33.04 t/s 8.23.210.345 I slot print_timing: id 3 | task 12450 | n_gen = 948, tg = 30.79 t/s, tg_3s = 32.93 t/s 8.23.270.194 I slot print_timing: id 1 | task 13204 | n_gen = 200, tg = 33.04 t/s, tg_3s = 32.92 t/s 8.24.189.168 I slot print_timing: id 0 | task 12761 | n_gen = 671, tg = 31.39 t/s, tg_3s = 32.82 t/s 8.24.219.498 I slot print_timing: id 2 | task 12952 | n_gen = 482, tg = 31.90 t/s, tg_3s = 32.84 t/s 8.25.332.111 I slot print_timing: id 2 | task 12952 | prompt eval time = 619.58 ms / 463 tokens ( 1.34 ms per token, 747.28 tokens per second) 8.25.332.115 I slot print_timing: id 2 | task 12952 | eval time = 16191.42 ms / 519 tokens ( 31.26 ms per token, 31.99 tokens per second) 8.25.332.116 I slot print_timing: id 2 | task 12952 | total time = 16811.00 ms / 982 tokens 8.25.332.117 I slot print_timing: id 2 | task 12952 | graphs reused = 12785 8.25.332.117 I slot print_timing: id 2 | task 12952 | graph reallocs = 0 / 0 (same size) / (changed size) 8.25.332.207 I slot release: id 2 | task 12952 | stop processing: n_tokens = 1676, truncated = 0 8.25.366.745 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.637 8.25.366.776 I slot launch_slot_: id 2 | task 13475 | processing task, is_child = 0 8.26.076.562 I slot print_timing: id 3 | task 12450 | prompt eval time = 432.06 ms / 271 tokens ( 1.59 ms per token, 627.23 tokens per second) 8.26.076.566 I slot print_timing: id 3 | task 12450 | eval time = 33620.33 ms / 1024 tokens ( 32.86 ms per token, 30.43 tokens per second) 8.26.076.567 I slot print_timing: id 3 | task 12450 | total time = 34052.39 ms / 1295 tokens 8.26.076.567 I slot print_timing: id 3 | task 12450 | graphs reused = 12787 8.26.076.568 I slot print_timing: id 3 | task 12450 | graph reallocs = 0 / 0 (same size) / (changed size) 8.26.076.653 I slot release: id 3 | task 12450 | stop processing: n_tokens = 2172, truncated = 0 8.26.103.768 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.492 8.26.110.697 I slot launch_slot_: id 3 | task 13482 | processing task, is_child = 0 8.26.494.707 I slot print_timing: id 1 | task 13204 | n_gen = 276, tg = 29.74 t/s, tg_3s = 23.57 t/s 8.27.202.633 I slot print_timing: id 0 | task 12761 | n_gen = 740, tg = 30.34 t/s, tg_3s = 22.90 t/s 8.29.319.180 I slot print_timing: id 2 | task 13475 | n_gen = 100, tg = 29.70 t/s, tg_3s = 30.00 t/s 8.29.407.806 I slot print_timing: id 0 | task 12761 | prompt eval time = 601.73 ms / 468 tokens ( 1.29 ms per token, 777.75 tokens per second) 8.29.407.813 I slot print_timing: id 0 | task 12761 | eval time = 26561.07 ms / 814 tokens ( 32.67 ms per token, 30.61 tokens per second) 8.29.407.814 I slot print_timing: id 0 | task 12761 | total time = 27162.80 ms / 1282 tokens 8.29.407.814 I slot print_timing: id 0 | task 12761 | graphs reused = 12882 8.29.407.815 I slot print_timing: id 0 | task 12761 | graph reallocs = 0 / 0 (same size) / (changed size) 8.29.407.895 I slot release: id 0 | task 12761 | stop processing: n_tokens = 1968, truncated = 0 8.29.436.036 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.543 8.29.436.065 I slot launch_slot_: id 0 | task 13582 | processing task, is_child = 0 8.29.979.821 I slot print_timing: id 1 | task 13204 | n_gen = 375, tg = 29.37 t/s, tg_3s = 28.41 t/s 8.30.031.097 I slot print_timing: id 3 | task 13482 | n_gen = 100, tg = 28.42 t/s, tg_3s = 28.70 t/s 8.32.344.178 I slot print_timing: id 2 | task 13475 | n_gen = 183, tg = 28.62 t/s, tg_3s = 27.44 t/s 8.33.009.121 I slot print_timing: id 1 | task 13204 | n_gen = 475, tg = 30.07 t/s, tg_3s = 33.01 t/s 8.33.038.313 I slot print_timing: id 0 | task 13582 | n_gen = 101, tg = 33.24 t/s, tg_3s = 33.58 t/s 8.33.039.685 I slot print_timing: id 3 | task 13482 | n_gen = 200, tg = 30.65 t/s, tg_3s = 33.24 t/s 8.35.354.855 I slot print_timing: id 2 | task 13475 | n_gen = 283, tg = 30.10 t/s, tg_3s = 33.22 t/s 8.35.900.036 I slot print_timing: id 1 | task 13204 | prompt eval time = 657.34 ms / 508 tokens ( 1.29 ms per token, 772.81 tokens per second) 8.35.900.039 I slot print_timing: id 1 | task 13204 | eval time = 18653.44 ms / 571 tokens ( 32.73 ms per token, 30.56 tokens per second) 8.35.900.040 I slot print_timing: id 1 | task 13204 | total time = 19310.78 ms / 1079 tokens 8.35.900.040 I slot print_timing: id 1 | task 13204 | graphs reused = 13077 8.35.900.041 I slot print_timing: id 1 | task 13204 | graph reallocs = 0 / 0 (same size) / (changed size) 8.35.900.137 I slot release: id 1 | task 13204 | stop processing: n_tokens = 1748, truncated = 0 8.35.935.355 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.611 8.35.935.390 I slot launch_slot_: id 1 | task 13781 | processing task, is_child = 0 8.36.499.929 I slot print_timing: id 0 | task 13582 | n_gen = 198, tg = 30.45 t/s, tg_3s = 28.02 t/s 8.36.500.572 I slot print_timing: id 3 | task 13482 | n_gen = 297, tg = 29.74 t/s, tg_3s = 28.03 t/s 8.38.372.175 I slot print_timing: id 2 | task 13475 | n_gen = 364, tg = 29.31 t/s, tg_3s = 26.84 t/s 8.39.512.619 I slot print_timing: id 0 | task 13582 | n_gen = 297, tg = 31.22 t/s, tg_3s = 32.86 t/s 8.39.513.980 I slot print_timing: id 3 | task 13482 | n_gen = 396, tg = 30.46 t/s, tg_3s = 32.85 t/s 8.39.573.256 I slot print_timing: id 1 | task 13781 | n_gen = 101, tg = 33.18 t/s, tg_3s = 33.51 t/s 8.40.505.956 I slot print_timing: id 3 | task 13482 | prompt eval time = 436.48 ms / 274 tokens ( 1.59 ms per token, 627.74 tokens per second) 8.40.505.962 I slot print_timing: id 3 | task 13482 | eval time = 13958.76 ms / 429 tokens ( 32.61 ms per token, 30.66 tokens per second) 8.40.505.963 I slot print_timing: id 3 | task 13482 | total time = 14395.24 ms / 703 tokens 8.40.505.963 I slot print_timing: id 3 | task 13482 | graphs reused = 13206 8.40.505.964 I slot print_timing: id 3 | task 13482 | graph reallocs = 0 / 0 (same size) / (changed size) 8.40.506.055 I slot release: id 3 | task 13482 | stop processing: n_tokens = 1580, truncated = 0 8.40.533.010 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.676 8.40.533.040 I slot launch_slot_: id 3 | task 13916 | processing task, is_child = 0 8.41.401.835 I slot print_timing: id 2 | task 13475 | n_gen = 452, tg = 29.25 t/s, tg_3s = 29.05 t/s 8.42.539.233 I slot print_timing: id 0 | task 13582 | n_gen = 385, tg = 30.70 t/s, tg_3s = 29.08 t/s 8.42.598.572 I slot print_timing: id 1 | task 13781 | n_gen = 189, tg = 31.13 t/s, tg_3s = 29.09 t/s 8.43.982.092 I slot print_timing: id 3 | task 13916 | n_gen = 101, tg = 33.27 t/s, tg_3s = 33.60 t/s 8.44.431.618 I slot print_timing: id 2 | task 13475 | n_gen = 553, tg = 29.92 t/s, tg_3s = 33.34 t/s 8.45.564.123 I slot print_timing: id 0 | task 13582 | n_gen = 486, tg = 31.22 t/s, tg_3s = 33.39 t/s 8.45.624.859 I slot print_timing: id 1 | task 13781 | n_gen = 290, tg = 31.88 t/s, tg_3s = 33.37 t/s 8.46.884.555 I slot print_timing: id 0 | task 13582 | prompt eval time = 594.24 ms / 455 tokens ( 1.31 ms per token, 765.68 tokens per second) 8.46.884.562 I slot print_timing: id 0 | task 13582 | eval time = 16854.24 ms / 530 tokens ( 31.86 ms per token, 31.39 tokens per second) 8.46.884.563 I slot print_timing: id 0 | task 13582 | total time = 17448.48 ms / 985 tokens 8.46.884.563 I slot print_timing: id 0 | task 13582 | graphs reused = 13402 8.46.884.564 I slot print_timing: id 0 | task 13582 | graph reallocs = 0 / 0 (same size) / (changed size) 8.46.884.655 I slot release: id 0 | task 13582 | stop processing: n_tokens = 1671, truncated = 0 8.46.912.553 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.639 8.46.912.594 I slot launch_slot_: id 0 | task 14117 | processing task, is_child = 0 8.47.557.442 I slot print_timing: id 2 | task 13475 | n_gen = 638, tg = 29.53 t/s, tg_3s = 27.19 t/s 8.47.557.713 I slot print_timing: id 3 | task 13916 | n_gen = 201, tg = 30.39 t/s, tg_3s = 27.97 t/s 8.48.652.904 I slot print_timing: id 1 | task 13781 | n_gen = 371, tg = 30.59 t/s, tg_3s = 26.75 t/s 8.50.558.782 I slot print_timing: id 2 | task 13475 | n_gen = 738, tg = 29.99 t/s, tg_3s = 33.32 t/s 8.50.559.172 I slot print_timing: id 3 | task 13916 | n_gen = 301, tg = 31.30 t/s, tg_3s = 33.32 t/s 8.50.619.436 I slot print_timing: id 0 | task 14117 | n_gen = 102, tg = 33.54 t/s, tg_3s = 33.87 t/s 8.51.666.493 I slot print_timing: id 1 | task 13781 | n_gen = 472, tg = 31.18 t/s, tg_3s = 33.51 t/s 8.51.759.326 I slot print_timing: id 2 | task 13475 | prompt eval time = 618.55 ms / 463 tokens ( 1.34 ms per token, 748.52 tokens per second) 8.51.759.333 I slot print_timing: id 2 | task 13475 | eval time = 25773.99 ms / 778 tokens ( 33.17 ms per token, 30.15 tokens per second) 8.51.759.334 I slot print_timing: id 2 | task 13475 | total time = 26392.54 ms / 1241 tokens 8.51.759.336 I slot print_timing: id 2 | task 13475 | graphs reused = 13541 8.51.759.336 I slot print_timing: id 2 | task 13475 | graph reallocs = 0 / 0 (same size) / (changed size) 8.51.759.466 I slot release: id 2 | task 13475 | stop processing: n_tokens = 1935, truncated = 0 8.51.793.667 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.552 8.51.793.701 I slot launch_slot_: id 2 | task 14261 | processing task, is_child = 0 8.53.581.365 I slot print_timing: id 3 | task 13916 | n_gen = 383, tg = 30.30 t/s, tg_3s = 27.13 t/s 8.53.639.470 I slot print_timing: id 0 | task 14117 | n_gen = 184, tg = 30.34 t/s, tg_3s = 27.15 t/s 8.54.685.498 I slot print_timing: id 1 | task 13781 | n_gen = 554, tg = 30.51 t/s, tg_3s = 27.16 t/s 8.55.433.764 I slot print_timing: id 2 | task 14261 | n_gen = 102, tg = 33.43 t/s, tg_3s = 33.76 t/s 8.56.603.880 I slot print_timing: id 3 | task 13916 | n_gen = 484, tg = 30.91 t/s, tg_3s = 33.42 t/s 8.56.661.257 I slot print_timing: id 0 | task 14117 | n_gen = 285, tg = 31.37 t/s, tg_3s = 33.42 t/s 8.57.708.206 I slot print_timing: id 1 | task 13781 | n_gen = 655, tg = 30.92 t/s, tg_3s = 33.41 t/s 8.58.438.262 I slot print_timing: id 2 | task 14261 | n_gen = 202, tg = 33.36 t/s, tg_3s = 33.28 t/s 8.59.614.067 I slot print_timing: id 3 | task 13916 | n_gen = 584, tg = 31.28 t/s, tg_3s = 33.22 t/s 8.59.671.399 I slot print_timing: id 0 | task 14117 | n_gen = 385, tg = 31.83 t/s, tg_3s = 33.22 t/s 9.00.727.297 I slot print_timing: id 1 | task 13781 | n_gen = 755, tg = 31.20 t/s, tg_3s = 33.12 t/s 9.01.461.058 I slot print_timing: id 2 | task 14261 | n_gen = 302, tg = 33.27 t/s, tg_3s = 33.08 t/s 9.02.633.926 I slot print_timing: id 3 | task 13916 | n_gen = 684, tg = 31.54 t/s, tg_3s = 33.11 t/s 9.02.691.759 I slot print_timing: id 0 | task 14117 | n_gen = 485, tg = 32.09 t/s, tg_3s = 33.11 t/s 9.03.747.564 I slot print_timing: id 1 | task 13781 | n_gen = 855, tg = 31.41 t/s, tg_3s = 33.11 t/s 9.04.465.474 I slot print_timing: id 2 | task 14261 | n_gen = 402, tg = 33.27 t/s, tg_3s = 33.28 t/s 9.05.651.592 I slot print_timing: id 3 | task 13916 | n_gen = 784, tg = 31.73 t/s, tg_3s = 33.14 t/s 9.05.712.098 I slot print_timing: id 0 | task 14117 | n_gen = 585, tg = 32.26 t/s, tg_3s = 33.11 t/s 9.06.773.193 I slot print_timing: id 1 | task 13781 | n_gen = 955, tg = 31.58 t/s, tg_3s = 33.05 t/s 9.07.473.501 I slot print_timing: id 2 | task 14261 | n_gen = 501, tg = 33.20 t/s, tg_3s = 32.91 t/s 9.08.680.660 I slot print_timing: id 3 | task 13916 | n_gen = 884, tg = 31.87 t/s, tg_3s = 33.01 t/s 9.08.740.865 I slot print_timing: id 0 | task 14117 | n_gen = 685, tg = 32.37 t/s, tg_3s = 33.02 t/s 9.08.861.540 I slot print_timing: id 1 | task 13781 | prompt eval time = 624.02 ms / 468 tokens ( 1.33 ms per token, 749.97 tokens per second) 9.08.861.547 I slot print_timing: id 1 | task 13781 | eval time = 32302.12 ms / 1024 tokens ( 31.58 ms per token, 31.67 tokens per second) 9.08.861.547 I slot print_timing: id 1 | task 13781 | total time = 32926.14 ms / 1492 tokens 9.08.861.548 I slot print_timing: id 1 | task 13781 | graphs reused = 14084 9.08.861.549 I slot print_timing: id 1 | task 13781 | graph reallocs = 0 / 0 (same size) / (changed size) 9.08.861.639 I slot release: id 1 | task 13781 | stop processing: n_tokens = 2161, truncated = 0 9.08.896.699 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.494 9.08.902.638 I slot launch_slot_: id 1 | task 14811 | processing task, is_child = 0 9.10.482.852 I slot print_timing: id 2 | task 14261 | n_gen = 581, tg = 32.10 t/s, tg_3s = 26.58 t/s 9.11.682.585 I slot print_timing: id 3 | task 13916 | n_gen = 964, tg = 31.36 t/s, tg_3s = 26.65 t/s 9.11.741.772 I slot print_timing: id 0 | task 14117 | n_gen = 765, tg = 31.66 t/s, tg_3s = 26.66 t/s 9.12.559.989 I slot print_timing: id 1 | task 14811 | n_gen = 101, tg = 33.02 t/s, tg_3s = 33.35 t/s 9.12.925.784 I slot print_timing: id 3 | task 13916 | prompt eval time = 442.96 ms / 289 tokens ( 1.53 ms per token, 652.43 tokens per second) 9.12.925.791 I slot print_timing: id 3 | task 13916 | eval time = 31949.78 ms / 1005 tokens ( 31.82 ms per token, 31.42 tokens per second) 9.12.925.791 I slot print_timing: id 3 | task 13916 | total time = 32392.74 ms / 1294 tokens 9.12.925.792 I slot print_timing: id 3 | task 13916 | graphs reused = 14195 9.12.925.792 I slot print_timing: id 3 | task 13916 | graph reallocs = 0 / 0 (same size) / (changed size) 9.12.925.892 I slot release: id 3 | task 13916 | stop processing: n_tokens = 2171, truncated = 0 9.12.953.658 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.492 9.12.959.742 I slot launch_slot_: id 3 | task 14927 | processing task, is_child = 0 9.13.483.214 I slot print_timing: id 2 | task 14261 | n_gen = 668, tg = 31.66 t/s, tg_3s = 29.00 t/s 9.14.750.160 I slot print_timing: id 0 | task 14117 | n_gen = 852, tg = 31.35 t/s, tg_3s = 28.92 t/s 9.15.569.124 I slot print_timing: id 1 | task 14811 | n_gen = 188, tg = 30.97 t/s, tg_3s = 28.91 t/s 9.16.408.411 I slot print_timing: id 3 | task 14927 | n_gen = 101, tg = 33.15 t/s, tg_3s = 33.48 t/s 9.16.499.266 I slot print_timing: id 2 | task 14261 | n_gen = 768, tg = 31.84 t/s, tg_3s = 33.16 t/s 9.17.770.979 I slot print_timing: id 0 | task 14117 | n_gen = 952, tg = 31.53 t/s, tg_3s = 33.10 t/s 9.18.573.561 I slot print_timing: id 1 | task 14811 | n_gen = 288, tg = 31.74 t/s, tg_3s = 33.28 t/s 9.19.414.271 I slot print_timing: id 3 | task 14927 | n_gen = 201, tg = 33.21 t/s, tg_3s = 33.27 t/s 9.19.503.776 I slot print_timing: id 2 | task 14261 | n_gen = 868, tg = 32.00 t/s, tg_3s = 33.28 t/s 9.19.923.056 I slot print_timing: id 0 | task 14117 | prompt eval time = 695.37 ms / 522 tokens ( 1.33 ms per token, 750.68 tokens per second) 9.19.923.063 I slot print_timing: id 0 | task 14117 | eval time = 32315.09 ms / 1024 tokens ( 31.59 ms per token, 31.66 tokens per second) 9.19.923.065 I slot print_timing: id 0 | task 14117 | total time = 33010.46 ms / 1546 tokens 9.19.923.066 I slot print_timing: id 0 | task 14117 | graphs reused = 14410 9.19.923.067 I slot print_timing: id 0 | task 14117 | graph reallocs = 0 / 0 (same size) / (changed size) 9.19.923.159 I slot release: id 0 | task 14117 | stop processing: n_tokens = 2232, truncated = 0 9.19.951.363 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.478 9.19.957.850 I slot launch_slot_: id 0 | task 15148 | processing task, is_child = 0 9.21.388.569 I slot print_timing: id 2 | task 14261 | prompt eval time = 619.05 ms / 463 tokens ( 1.34 ms per token, 747.92 tokens per second) 9.21.388.573 I slot print_timing: id 2 | task 14261 | eval time = 28975.81 ms / 912 tokens ( 31.81 ms per token, 31.44 tokens per second) 9.21.388.574 I slot print_timing: id 2 | task 14261 | total time = 29594.86 ms / 1375 tokens 9.21.388.574 I slot print_timing: id 2 | task 14261 | graphs reused = 14436 9.21.388.575 I slot print_timing: id 2 | task 14261 | graph reallocs = 0 / 0 (same size) / (changed size) 9.21.388.681 I slot release: id 2 | task 14261 | stop processing: n_tokens = 2069, truncated = 0 9.21.423.426 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.516 9.21.423.462 I slot launch_slot_: id 2 | task 15179 | processing task, is_child = 0 9.21.979.495 I slot print_timing: id 1 | task 14811 | n_gen = 365, tg = 29.24 t/s, tg_3s = 22.61 t/s 9.22.426.971 I slot print_timing: id 3 | task 14927 | n_gen = 264, tg = 29.11 t/s, tg_3s = 20.91 t/s 9.24.013.787 I slot print_timing: id 1 | task 14811 | prompt eval time = 628.98 ms / 474 tokens ( 1.33 ms per token, 753.60 tokens per second) 9.24.013.791 I slot print_timing: id 1 | task 14811 | eval time = 14482.16 ms / 433 tokens ( 33.52 ms per token, 29.83 tokens per second) 9.24.013.792 I slot print_timing: id 1 | task 14811 | total time = 15111.13 ms / 907 tokens 9.24.013.792 I slot print_timing: id 1 | task 14811 | graphs reused = 14501 9.24.013.793 I slot print_timing: id 1 | task 14811 | graph reallocs = 0 / 0 (same size) / (changed size) 9.24.013.880 I slot release: id 1 | task 14811 | stop processing: n_tokens = 1576, truncated = 0 9.24.048.023 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.678 9.24.048.057 I slot launch_slot_: id 1 | task 15250 | processing task, is_child = 0 9.24.634.505 I slot print_timing: id 0 | task 15148 | n_gen = 100, tg = 24.40 t/s, tg_3s = 24.65 t/s 9.25.444.462 I slot print_timing: id 3 | task 14927 | n_gen = 346, tg = 28.62 t/s, tg_3s = 27.17 t/s 9.25.563.255 I slot print_timing: id 2 | task 15179 | n_gen = 100, tg = 28.08 t/s, tg_3s = 28.37 t/s 9.27.642.121 I slot print_timing: id 0 | task 15148 | n_gen = 199, tg = 28.02 t/s, tg_3s = 32.92 t/s 9.27.703.239 I slot print_timing: id 1 | task 15250 | n_gen = 101, tg = 33.23 t/s, tg_3s = 33.56 t/s 9.28.454.602 I slot print_timing: id 3 | task 14927 | n_gen = 446, tg = 29.54 t/s, tg_3s = 33.22 t/s 9.28.574.417 I slot print_timing: id 2 | task 15179 | n_gen = 200, tg = 30.45 t/s, tg_3s = 33.21 t/s 9.30.669.905 I slot print_timing: id 0 | task 15148 | n_gen = 300, tg = 29.62 t/s, tg_3s = 33.36 t/s 9.30.731.022 I slot print_timing: id 1 | task 15250 | n_gen = 202, tg = 33.29 t/s, tg_3s = 33.36 t/s 9.31.482.441 I slot print_timing: id 3 | task 14927 | n_gen = 547, tg = 30.18 t/s, tg_3s = 33.36 t/s 9.31.601.917 I slot print_timing: id 2 | task 15179 | n_gen = 301, tg = 31.37 t/s, tg_3s = 33.36 t/s 9.32.571.175 I slot print_timing: id 2 | task 15179 | prompt eval time = 614.77 ms / 455 tokens ( 1.35 ms per token, 740.12 tokens per second) 9.32.571.181 I slot print_timing: id 2 | task 15179 | eval time = 10532.94 ms / 333 tokens ( 31.73 ms per token, 31.52 tokens per second) 9.32.571.183 I slot print_timing: id 2 | task 15179 | total time = 11147.70 ms / 788 tokens 9.32.571.183 I slot print_timing: id 2 | task 15179 | graphs reused = 14761 9.32.571.184 I slot print_timing: id 2 | task 15179 | graph reallocs = 0 / 0 (same size) / (changed size) 9.32.571.277 I slot release: id 2 | task 15179 | stop processing: n_tokens = 1482, truncated = 0 9.32.606.079 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.721 9.32.606.109 I slot launch_slot_: id 2 | task 15516 | processing task, is_child = 0 9.33.687.240 I slot print_timing: id 0 | task 15148 | n_gen = 381, tg = 28.98 t/s, tg_3s = 26.84 t/s 9.33.748.353 I slot print_timing: id 1 | task 15250 | n_gen = 283, tg = 31.14 t/s, tg_3s = 26.84 t/s 9.34.493.613 I slot print_timing: id 3 | task 14927 | n_gen = 628, tg = 29.71 t/s, tg_3s = 26.90 t/s 9.35.556.039 I slot print_timing: id 3 | task 14927 | prompt eval time = 432.09 ms / 272 tokens ( 1.59 ms per token, 629.49 tokens per second) 9.35.556.046 I slot print_timing: id 3 | task 14927 | eval time = 22164.19 ms / 663 tokens ( 33.48 ms per token, 29.87 tokens per second) 9.35.556.047 I slot print_timing: id 3 | task 14927 | total time = 22596.28 ms / 935 tokens 9.35.556.048 I slot print_timing: id 3 | task 14927 | graphs reused = 14836 9.35.556.049 I slot print_timing: id 3 | task 14927 | graph reallocs = 0 / 0 (same size) / (changed size) 9.35.556.151 I slot release: id 3 | task 14927 | stop processing: n_tokens = 1812, truncated = 0 9.35.583.858 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.589 9.35.583.886 I slot launch_slot_: id 3 | task 15597 | processing task, is_child = 0 9.36.588.085 I slot print_timing: id 2 | task 15516 | n_gen = 100, tg = 29.47 t/s, tg_3s = 29.77 t/s 9.36.707.959 I slot print_timing: id 0 | task 15148 | n_gen = 469, tg = 29.01 t/s, tg_3s = 29.13 t/s 9.36.769.570 I slot print_timing: id 1 | task 15250 | n_gen = 371, tg = 30.64 t/s, tg_3s = 29.13 t/s 9.39.035.167 I slot print_timing: id 3 | task 15597 | n_gen = 102, tg = 33.53 t/s, tg_3s = 33.87 t/s 9.39.609.323 I slot print_timing: id 2 | task 15516 | n_gen = 201, tg = 31.34 t/s, tg_3s = 33.43 t/s 9.39.730.440 I slot print_timing: id 0 | task 15148 | n_gen = 570, tg = 29.71 t/s, tg_3s = 33.42 t/s 9.39.792.026 I slot print_timing: id 1 | task 15250 | n_gen = 472, tg = 31.20 t/s, tg_3s = 33.42 t/s 9.42.043.670 I slot print_timing: id 3 | task 15597 | n_gen = 202, tg = 33.39 t/s, tg_3s = 33.24 t/s 9.42.618.385 I slot print_timing: id 2 | task 15516 | n_gen = 301, tg = 31.95 t/s, tg_3s = 33.23 t/s 9.42.737.101 I slot print_timing: id 0 | task 15148 | n_gen = 670, tg = 30.19 t/s, tg_3s = 33.26 t/s 9.42.797.470 I slot print_timing: id 1 | task 15250 | n_gen = 572, tg = 31.54 t/s, tg_3s = 33.27 t/s 9.44.088.364 I slot print_timing: id 1 | task 15250 | prompt eval time = 645.81 ms / 490 tokens ( 1.32 ms per token, 758.74 tokens per second) 9.44.088.370 I slot print_timing: id 1 | task 15250 | eval time = 19394.49 ms / 615 tokens ( 31.59 ms per token, 31.66 tokens per second) 9.44.088.371 I slot print_timing: id 1 | task 15250 | total time = 20040.30 ms / 1105 tokens 9.44.088.372 I slot print_timing: id 1 | task 15250 | graphs reused = 15103 9.44.088.373 I slot print_timing: id 1 | task 15250 | graph reallocs = 0 / 0 (same size) / (changed size) 9.44.088.467 I slot release: id 1 | task 15250 | stop processing: n_tokens = 1774, truncated = 0 9.44.123.672 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.602 9.44.123.703 I slot launch_slot_: id 1 | task 15870 | processing task, is_child = 0 9.45.055.740 I slot print_timing: id 3 | task 15597 | n_gen = 283, tg = 31.22 t/s, tg_3s = 26.89 t/s 9.45.621.166 I slot print_timing: id 2 | task 15516 | n_gen = 382, tg = 30.74 t/s, tg_3s = 26.97 t/s 9.45.740.554 I slot print_timing: id 0 | task 15148 | n_gen = 751, tg = 29.80 t/s, tg_3s = 26.97 t/s 9.47.752.470 I slot print_timing: id 1 | task 15870 | n_gen = 101, tg = 33.32 t/s, tg_3s = 33.66 t/s 9.48.083.632 I slot print_timing: id 3 | task 15597 | n_gen = 384, tg = 31.76 t/s, tg_3s = 33.36 t/s 9.48.621.953 I slot print_timing: id 2 | task 15516 | n_gen = 482, tg = 31.25 t/s, tg_3s = 33.32 t/s 9.48.743.151 I slot print_timing: id 0 | task 15148 | n_gen = 851, tg = 30.18 t/s, tg_3s = 33.30 t/s 9.50.780.571 I slot print_timing: id 1 | task 15870 | n_gen = 201, tg = 33.17 t/s, tg_3s = 33.02 t/s 9.51.110.281 I slot print_timing: id 3 | task 15597 | n_gen = 484, tg = 32.01 t/s, tg_3s = 33.04 t/s 9.51.623.796 I slot print_timing: id 2 | task 15516 | n_gen = 581, tg = 31.53 t/s, tg_3s = 32.98 t/s 9.51.745.390 I slot print_timing: id 0 | task 15148 | n_gen = 950, tg = 30.45 t/s, tg_3s = 32.98 t/s 9.52.193.039 I slot print_timing: id 2 | task 15516 | prompt eval time = 622.42 ms / 467 tokens ( 1.33 ms per token, 750.29 tokens per second) 9.52.193.047 I slot print_timing: id 2 | task 15516 | eval time = 18964.50 ms / 600 tokens ( 31.66 ms per token, 31.59 tokens per second) 9.52.193.048 I slot print_timing: id 2 | task 15516 | total time = 19586.92 ms / 1067 tokens 9.52.193.048 I slot print_timing: id 2 | task 15516 | graphs reused = 15348 9.52.193.049 I slot print_timing: id 2 | task 15516 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.193.135 I slot release: id 2 | task 15516 | stop processing: n_tokens = 1761, truncated = 0 9.52.227.249 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.606 9.52.227.285 I slot launch_slot_: id 2 | task 16121 | processing task, is_child = 0 9.53.797.768 I slot print_timing: id 1 | task 15870 | n_gen = 282, tg = 31.06 t/s, tg_3s = 26.85 t/s 9.54.129.676 I slot print_timing: id 3 | task 15597 | n_gen = 565, tg = 31.15 t/s, tg_3s = 26.83 t/s 9.54.549.357 I slot print_timing: id 0 | task 15148 | prompt eval time = 619.12 ms / 486 tokens ( 1.27 ms per token, 784.99 tokens per second) 9.54.549.363 I slot print_timing: id 0 | task 15148 | eval time = 33972.38 ms / 1024 tokens ( 33.21 ms per token, 30.11 tokens per second) 9.54.549.364 I slot print_timing: id 0 | task 15148 | total time = 34591.50 ms / 1510 tokens 9.54.549.364 I slot print_timing: id 0 | task 15148 | graphs reused = 15403 9.54.549.365 I slot print_timing: id 0 | task 15148 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.549.457 I slot release: id 0 | task 15148 | stop processing: n_tokens = 2202, truncated = 0 9.54.577.715 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.485 9.54.583.576 I slot launch_slot_: id 0 | task 16181 | processing task, is_child = 0 9.56.380.535 I slot print_timing: id 2 | task 16121 | n_gen = 100, tg = 28.05 t/s, tg_3s = 28.33 t/s 9.56.799.914 I slot print_timing: id 1 | task 15870 | n_gen = 364, tg = 30.13 t/s, tg_3s = 27.31 t/s 9.57.131.949 I slot print_timing: id 3 | task 15597 | n_gen = 647, tg = 30.60 t/s, tg_3s = 27.31 t/s 9.58.201.517 I slot print_timing: id 0 | task 16181 | n_gen = 102, tg = 33.41 t/s, tg_3s = 33.75 t/s 9.59.395.202 I slot print_timing: id 2 | task 16121 | n_gen = 201, tg = 30.56 t/s, tg_3s = 33.50 t/s 9.59.814.750 I slot print_timing: id 1 | task 15870 | n_gen = 465, tg = 30.80 t/s, tg_3s = 33.50 t/s 10.00.143.735 I slot print_timing: id 3 | task 15597 | n_gen = 748, tg = 30.97 t/s, tg_3s = 33.53 t/s 10.00.173.851 I slot print_timing: id 3 | task 15597 | prompt eval time = 439.46 ms / 284 tokens ( 1.55 ms per token, 646.25 tokens per second) 10.00.173.857 I slot print_timing: id 3 | task 15597 | eval time = 24150.50 ms / 749 tokens ( 32.29 ms per token, 30.97 tokens per second) 10.00.173.858 I slot print_timing: id 3 | task 15597 | total time = 24589.96 ms / 1033 tokens 10.00.173.859 I slot print_timing: id 3 | task 15597 | graphs reused = 15569 10.00.173.859 I slot print_timing: id 3 | task 15597 | graph reallocs = 0 / 0 (same size) / (changed size) 10.00.173.958 I slot release: id 3 | task 15597 | stop processing: n_tokens = 1910, truncated = 0 10.00.200.618 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.559 10.00.200.647 I slot launch_slot_: id 3 | task 16352 | processing task, is_child = 0 10.01.201.973 I slot print_timing: id 0 | task 16181 | n_gen = 190, tg = 31.38 t/s, tg_3s = 29.33 t/s 10.02.398.334 I slot print_timing: id 2 | task 16121 | n_gen = 289, tg = 30.16 t/s, tg_3s = 29.30 t/s 10.02.842.629 I slot print_timing: id 1 | task 15870 | n_gen = 554, tg = 30.57 t/s, tg_3s = 29.39 t/s 10.03.651.664 I slot print_timing: id 3 | task 16352 | n_gen = 102, tg = 33.41 t/s, tg_3s = 33.74 t/s 10.04.216.895 I slot print_timing: id 0 | task 16181 | n_gen = 291, tg = 32.09 t/s, tg_3s = 33.50 t/s 10.05.416.454 I slot print_timing: id 2 | task 16121 | n_gen = 390, tg = 30.96 t/s, tg_3s = 33.46 t/s 10.05.863.654 I slot print_timing: id 1 | task 15870 | n_gen = 655, tg = 30.98 t/s, tg_3s = 33.43 t/s 10.06.676.503 I slot print_timing: id 3 | task 16352 | n_gen = 203, tg = 33.40 t/s, tg_3s = 33.39 t/s 10.07.243.454 I slot print_timing: id 0 | task 16181 | n_gen = 392, tg = 32.41 t/s, tg_3s = 33.37 t/s 10.07.571.179 I slot print_timing: id 0 | task 16181 | prompt eval time = 595.26 ms / 459 tokens ( 1.30 ms per token, 771.09 tokens per second) 10.07.571.185 I slot print_timing: id 0 | task 16181 | eval time = 12392.33 ms / 403 tokens ( 30.83 ms per token, 32.44 tokens per second) 10.07.571.186 I slot print_timing: id 0 | task 16181 | total time = 12987.59 ms / 862 tokens 10.07.571.187 I slot print_timing: id 0 | task 16181 | graphs reused = 15799 10.07.571.187 I slot print_timing: id 0 | task 16181 | graph reallocs = 0 / 0 (same size) / (changed size) 10.07.571.275 I slot release: id 0 | task 16181 | stop processing: n_tokens = 1554, truncated = 0 10.07.600.103 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.687 10.07.600.138 I slot launch_slot_: id 0 | task 16588 | processing task, is_child = 0 10.08.422.718 I slot print_timing: id 2 | task 16121 | n_gen = 473, tg = 30.31 t/s, tg_3s = 27.61 t/s 10.08.781.145 I slot print_timing: id 3 | task 16352 | prompt eval time = 428.01 ms / 264 tokens ( 1.62 ms per token, 616.80 tokens per second) 10.08.781.151 I slot print_timing: id 3 | task 16352 | eval time = 8152.47 ms / 256 tokens ( 31.97 ms per token, 31.28 tokens per second) 10.08.781.152 I slot print_timing: id 3 | task 16352 | total time = 8580.49 ms / 520 tokens 10.08.781.153 I slot print_timing: id 3 | task 16352 | graphs reused = 15819 10.08.781.153 I slot print_timing: id 3 | task 16352 | graph reallocs = 0 / 0 (same size) / (changed size) 10.08.781.247 I slot release: id 3 | task 16352 | stop processing: n_tokens = 1397, truncated = 0 10.08.808.071 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.764 10.08.808.099 I slot launch_slot_: id 3 | task 16612 | processing task, is_child = 0 10.09.240.368 I slot print_timing: id 1 | task 15870 | n_gen = 737, tg = 30.05 t/s, tg_3s = 24.28 t/s 10.09.688.023 I slot print_timing: id 2 | task 16121 | prompt eval time = 623.23 ms / 467 tokens ( 1.33 ms per token, 749.32 tokens per second) 10.09.688.029 I slot print_timing: id 2 | task 16121 | eval time = 16837.50 ms / 501 tokens ( 33.67 ms per token, 29.70 tokens per second) 10.09.688.030 I slot print_timing: id 2 | task 16121 | total time = 17460.73 ms / 968 tokens 10.09.688.030 I slot print_timing: id 2 | task 16121 | graphs reused = 15831 10.09.688.031 I slot print_timing: id 2 | task 16121 | graph reallocs = 0 / 0 (same size) / (changed size) 10.09.688.121 I slot release: id 2 | task 16121 | stop processing: n_tokens = 1662, truncated = 0 10.09.722.451 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.643 10.09.722.484 I slot launch_slot_: id 2 | task 16629 | processing task, is_child = 0 10.12.138.119 I slot print_timing: id 0 | task 16588 | n_gen = 100, tg = 25.00 t/s, tg_3s = 25.25 t/s 10.12.258.003 I slot print_timing: id 1 | task 15870 | n_gen = 818, tg = 29.70 t/s, tg_3s = 26.84 t/s 10.12.819.958 I slot print_timing: id 3 | task 16612 | n_gen = 100, tg = 28.06 t/s, tg_3s = 28.35 t/s 10.13.353.268 I slot print_timing: id 2 | task 16629 | n_gen = 102, tg = 33.54 t/s, tg_3s = 33.87 t/s 10.15.163.672 I slot print_timing: id 0 | task 16588 | n_gen = 201, tg = 28.63 t/s, tg_3s = 33.38 t/s 10.15.285.733 I slot print_timing: id 1 | task 15870 | n_gen = 919, tg = 30.06 t/s, tg_3s = 33.36 t/s 10.15.830.870 I slot print_timing: id 3 | task 16612 | n_gen = 200, tg = 30.43 t/s, tg_3s = 33.21 t/s 10.16.372.850 I slot print_timing: id 2 | task 16629 | n_gen = 202, tg = 33.33 t/s, tg_3s = 33.12 t/s 10.18.181.974 I slot print_timing: id 0 | task 16588 | n_gen = 301, tg = 29.99 t/s, tg_3s = 33.13 t/s 10.18.301.029 I slot print_timing: id 1 | task 15870 | n_gen = 1019, tg = 30.34 t/s, tg_3s = 33.16 t/s 10.18.450.834 I slot print_timing: id 1 | task 15870 | prompt eval time = 627.97 ms / 475 tokens ( 1.32 ms per token, 756.41 tokens per second) 10.18.450.840 I slot print_timing: id 1 | task 15870 | eval time = 33699.16 ms / 1024 tokens ( 32.94 ms per token, 30.36 tokens per second) 10.18.450.841 I slot print_timing: id 1 | task 15870 | total time = 34327.12 ms / 1499 tokens 10.18.450.842 I slot print_timing: id 1 | task 15870 | graphs reused = 16099 10.18.450.842 I slot print_timing: id 1 | task 15870 | graph reallocs = 0 / 0 (same size) / (changed size) 10.18.450.928 I slot release: id 1 | task 15870 | stop processing: n_tokens = 2168, truncated = 0 10.18.485.609 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.493 10.18.491.399 I slot launch_slot_: id 1 | task 16903 | processing task, is_child = 0 10.19.079.064 I slot print_timing: id 3 | task 16612 | n_gen = 289, tg = 29.43 t/s, tg_3s = 27.40 t/s 10.19.381.688 I slot print_timing: id 2 | task 16629 | n_gen = 282, tg = 31.09 t/s, tg_3s = 26.59 t/s 10.19.738.955 I slot print_timing: id 0 | task 16588 | prompt eval time = 578.02 ms / 446 tokens ( 1.30 ms per token, 771.60 tokens per second) 10.19.738.961 I slot print_timing: id 0 | task 16588 | eval time = 11560.79 ms / 333 tokens ( 34.82 ms per token, 28.72 tokens per second) 10.19.738.962 I slot print_timing: id 0 | task 16588 | total time = 12138.81 ms / 779 tokens 10.19.738.963 I slot print_timing: id 0 | task 16588 | graphs reused = 16118 10.19.738.963 I slot print_timing: id 0 | task 16588 | graph reallocs = 0 / 0 (same size) / (changed size) 10.19.739.046 I slot release: id 0 | task 16588 | stop processing: n_tokens = 1471, truncated = 0 10.19.767.325 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.726 10.19.767.358 I slot launch_slot_: id 0 | task 16927 | processing task, is_child = 0 10.22.081.316 I slot print_timing: id 3 | task 16612 | n_gen = 371, tg = 28.93 t/s, tg_3s = 27.31 t/s 10.22.406.868 I slot print_timing: id 2 | task 16629 | n_gen = 366, tg = 30.25 t/s, tg_3s = 27.77 t/s 10.22.611.234 I slot print_timing: id 1 | task 16903 | n_gen = 100, tg = 28.51 t/s, tg_3s = 28.79 t/s 10.23.377.326 I slot print_timing: id 0 | task 16927 | n_gen = 103, tg = 33.81 t/s, tg_3s = 34.14 t/s 10.25.096.930 I slot print_timing: id 3 | task 16612 | n_gen = 472, tg = 29.80 t/s, tg_3s = 33.49 t/s 10.25.428.328 I slot print_timing: id 2 | task 16629 | n_gen = 467, tg = 30.89 t/s, tg_3s = 33.43 t/s 10.25.635.604 I slot print_timing: id 1 | task 16903 | n_gen = 201, tg = 30.78 t/s, tg_3s = 33.40 t/s 10.26.382.082 I slot print_timing: id 0 | task 16927 | n_gen = 203, tg = 33.54 t/s, tg_3s = 33.28 t/s 10.28.100.779 I slot print_timing: id 3 | task 16612 | n_gen = 572, tg = 30.36 t/s, tg_3s = 33.29 t/s 10.28.433.542 I slot print_timing: id 2 | task 16629 | n_gen = 567, tg = 31.29 t/s, tg_3s = 33.28 t/s 10.28.645.603 I slot print_timing: id 1 | task 16903 | n_gen = 301, tg = 31.55 t/s, tg_3s = 33.22 t/s 10.29.399.704 I slot print_timing: id 0 | task 16927 | n_gen = 303, tg = 33.41 t/s, tg_3s = 33.14 t/s 10.31.109.612 I slot print_timing: id 3 | task 16612 | n_gen = 672, tg = 30.76 t/s, tg_3s = 33.24 t/s 10.31.441.670 I slot print_timing: id 2 | task 16629 | n_gen = 667, tg = 31.56 t/s, tg_3s = 33.24 t/s 10.31.653.779 I slot print_timing: id 1 | task 16903 | n_gen = 401, tg = 31.96 t/s, tg_3s = 33.24 t/s 10.32.350.610 I slot print_timing: id 1 | task 16903 | prompt eval time = 646.91 ms / 489 tokens ( 1.32 ms per token, 755.90 tokens per second) 10.32.350.617 I slot print_timing: id 1 | task 16903 | eval time = 13212.28 ms / 424 tokens ( 31.23 ms per token, 32.02 tokens per second) 10.32.350.617 I slot print_timing: id 1 | task 16903 | total time = 13859.19 ms / 913 tokens 10.32.350.618 I slot print_timing: id 1 | task 16903 | graphs reused = 16516 10.32.350.619 I slot print_timing: id 1 | task 16903 | graph reallocs = 0 / 0 (same size) / (changed size) 10.32.350.708 I slot release: id 1 | task 16903 | stop processing: n_tokens = 1582, truncated = 0 10.32.385.401 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.675 10.32.385.434 I slot launch_slot_: id 1 | task 17331 | processing task, is_child = 0 10.32.972.369 I slot print_timing: id 0 | task 16927 | n_gen = 403, tg = 31.87 t/s, tg_3s = 27.99 t/s 10.34.109.785 I slot print_timing: id 3 | task 16612 | n_gen = 752, tg = 30.26 t/s, tg_3s = 26.67 t/s 10.34.469.481 I slot print_timing: id 0 | task 16927 | prompt eval time = 592.80 ms / 454 tokens ( 1.31 ms per token, 765.85 tokens per second) 10.34.469.487 I slot print_timing: id 0 | task 16927 | eval time = 14109.31 ms / 452 tokens ( 31.28 ms per token, 31.96 tokens per second) 10.34.469.489 I slot print_timing: id 0 | task 16927 | total time = 14702.11 ms / 906 tokens 10.34.469.490 I slot print_timing: id 0 | task 16927 | graphs reused = 16563 10.34.469.490 I slot print_timing: id 0 | task 16927 | graph reallocs = 0 / 0 (same size) / (changed size) 10.34.469.577 I slot release: id 0 | task 16927 | stop processing: n_tokens = 1598, truncated = 0 10.34.470.571 I slot print_timing: id 2 | task 16629 | n_gen = 748, tg = 30.96 t/s, tg_3s = 26.74 t/s 10.34.498.098 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.668 10.34.498.131 I slot launch_slot_: id 0 | task 17383 | processing task, is_child = 0 10.36.513.407 I slot print_timing: id 1 | task 17331 | n_gen = 100, tg = 28.43 t/s, tg_3s = 28.72 t/s 10.37.121.187 I slot print_timing: id 3 | task 16612 | n_gen = 835, tg = 29.97 t/s, tg_3s = 27.56 t/s 10.37.482.406 I slot print_timing: id 2 | task 16629 | n_gen = 831, tg = 30.58 t/s, tg_3s = 27.56 t/s 10.38.084.904 I slot print_timing: id 0 | task 17383 | n_gen = 101, tg = 33.15 t/s, tg_3s = 33.49 t/s 10.39.520.565 I slot print_timing: id 1 | task 17331 | n_gen = 200, tg = 30.66 t/s, tg_3s = 33.25 t/s 10.40.133.137 I slot print_timing: id 3 | task 16612 | n_gen = 935, tg = 30.28 t/s, tg_3s = 33.20 t/s 10.40.495.346 I slot print_timing: id 2 | task 16629 | n_gen = 931, tg = 30.84 t/s, tg_3s = 33.19 t/s 10.41.099.526 I slot print_timing: id 0 | task 17383 | n_gen = 201, tg = 33.16 t/s, tg_3s = 33.17 t/s 10.42.550.508 I slot print_timing: id 1 | task 17331 | n_gen = 300, tg = 31.41 t/s, tg_3s = 33.00 t/s 10.42.824.055 I slot print_timing: id 3 | task 16612 | prompt eval time = 483.92 ms / 326 tokens ( 1.48 ms per token, 673.67 tokens per second) 10.42.824.061 I slot print_timing: id 3 | task 16612 | eval time = 33532.03 ms / 1024 tokens ( 32.78 ms per token, 30.51 tokens per second) 10.42.824.062 I slot print_timing: id 3 | task 16612 | total time = 34015.95 ms / 1350 tokens 10.42.824.063 I slot print_timing: id 3 | task 16612 | graphs reused = 16819 10.42.824.063 I slot print_timing: id 3 | task 16612 | graph reallocs = 0 / 0 (same size) / (changed size) 10.42.824.159 I slot release: id 3 | task 16612 | stop processing: n_tokens = 2227, truncated = 0 10.42.851.247 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.480 10.42.859.531 I slot launch_slot_: id 3 | task 17644 | processing task, is_child = 0 10.43.516.240 I slot print_timing: id 2 | task 16629 | n_gen = 1018, tg = 30.66 t/s, tg_3s = 28.80 t/s 10.43.700.180 I slot print_timing: id 2 | task 16629 | prompt eval time = 619.53 ms / 463 tokens ( 1.34 ms per token, 747.34 tokens per second) 10.43.700.183 I slot print_timing: id 2 | task 16629 | eval time = 33358.16 ms / 1024 tokens ( 32.61 ms per token, 30.67 tokens per second) 10.43.700.185 I slot print_timing: id 2 | task 16629 | total time = 33977.68 ms / 1487 tokens 10.43.700.186 I slot print_timing: id 2 | task 16629 | graphs reused = 16831 10.43.700.187 I slot print_timing: id 2 | task 16629 | graph reallocs = 0 / 0 (same size) / (changed size) 10.43.700.275 I slot release: id 2 | task 16629 | stop processing: n_tokens = 2181, truncated = 0 10.43.735.101 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.490 10.43.741.207 I slot launch_slot_: id 2 | task 17661 | processing task, is_child = 0 10.44.274.107 I slot print_timing: id 0 | task 17383 | n_gen = 276, tg = 29.87 t/s, tg_3s = 23.63 t/s 10.45.372.725 I slot print_timing: id 1 | task 17331 | prompt eval time = 645.55 ms / 490 tokens ( 1.32 ms per token, 759.05 tokens per second) 10.45.372.729 I slot print_timing: id 1 | task 17331 | eval time = 12341.74 ms / 363 tokens ( 34.09 ms per token, 29.33 tokens per second) 10.45.372.730 I slot print_timing: id 1 | task 17331 | total time = 12987.28 ms / 853 tokens 10.45.372.730 I slot print_timing: id 1 | task 17331 | graphs reused = 16865 10.45.372.731 I slot print_timing: id 1 | task 17331 | graph reallocs = 0 / 0 (same size) / (changed size) 10.45.372.816 I slot release: id 1 | task 17331 | stop processing: n_tokens = 1522, truncated = 0 10.45.407.718 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.891 (> 0.100 thold), f_keep = 0.702 10.45.407.750 I slot launch_slot_: id 1 | task 17700 | processing task, is_child = 0 10.47.274.984 I slot print_timing: id 0 | task 17383 | n_gen = 353, tg = 28.84 t/s, tg_3s = 25.66 t/s 10.47.487.203 I slot print_timing: id 3 | task 17644 | n_gen = 100, tg = 23.67 t/s, tg_3s = 23.91 t/s 10.47.968.894 I slot print_timing: id 2 | task 17661 | n_gen = 100, tg = 27.23 t/s, tg_3s = 27.50 t/s 10.48.968.006 I slot print_timing: id 0 | task 17383 | prompt eval time = 570.55 ms / 436 tokens ( 1.31 ms per token, 764.17 tokens per second) 10.48.968.012 I slot print_timing: id 0 | task 17383 | eval time = 13899.32 ms / 409 tokens ( 34.07 ms per token, 29.35 tokens per second) 10.48.968.013 I slot print_timing: id 0 | task 17383 | total time = 14469.87 ms / 845 tokens 10.48.968.013 I slot print_timing: id 0 | task 17383 | graphs reused = 16956 10.48.968.014 I slot print_timing: id 0 | task 17383 | graph reallocs = 0 / 0 (same size) / (changed size) 10.48.968.098 I slot release: id 0 | task 17383 | stop processing: n_tokens = 1537, truncated = 0 10.48.996.705 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.695 10.48.996.732 I slot launch_slot_: id 0 | task 17798 | processing task, is_child = 0 10.49.690.104 I slot print_timing: id 1 | task 17700 | n_gen = 100, tg = 28.01 t/s, tg_3s = 28.29 t/s 10.50.497.122 I slot print_timing: id 3 | task 17644 | n_gen = 182, tg = 25.17 t/s, tg_3s = 27.24 t/s 10.50.979.811 I slot print_timing: id 2 | task 17661 | n_gen = 182, tg = 27.23 t/s, tg_3s = 27.23 t/s 10.52.625.663 I slot print_timing: id 0 | task 17798 | n_gen = 102, tg = 33.37 t/s, tg_3s = 33.70 t/s 10.52.717.110 I slot print_timing: id 1 | task 17700 | n_gen = 201, tg = 30.48 t/s, tg_3s = 33.37 t/s 10.53.498.566 I slot print_timing: id 3 | task 17644 | n_gen = 282, tg = 27.57 t/s, tg_3s = 33.32 t/s 10.54.000.433 I slot print_timing: id 2 | task 17661 | n_gen = 283, tg = 29.17 t/s, tg_3s = 33.44 t/s 10.55.652.002 I slot print_timing: id 0 | task 17798 | n_gen = 203, tg = 33.37 t/s, tg_3s = 33.37 t/s 10.55.740.312 I slot print_timing: id 1 | task 17700 | n_gen = 302, tg = 31.40 t/s, tg_3s = 33.41 t/s 10.56.523.062 I slot print_timing: id 3 | task 17644 | n_gen = 383, tg = 28.90 t/s, tg_3s = 33.39 t/s 10.57.005.435 I slot print_timing: id 2 | task 17661 | n_gen = 383, tg = 30.14 t/s, tg_3s = 33.28 t/s 10.58.669.618 I slot print_timing: id 0 | task 17798 | n_gen = 303, tg = 33.29 t/s, tg_3s = 33.14 t/s 10.58.758.322 I slot print_timing: id 1 | task 17700 | n_gen = 402, tg = 31.82 t/s, tg_3s = 33.13 t/s 10.59.543.588 I slot print_timing: id 3 | task 17644 | n_gen = 483, tg = 29.68 t/s, tg_3s = 33.11 t/s 10.59.572.362 I slot print_timing: id 1 | task 17700 | prompt eval time = 747.40 ms / 528 tokens ( 1.42 ms per token, 706.45 tokens per second) 10.59.572.368 I slot print_timing: id 1 | task 17700 | eval time = 13417.21 ms / 429 tokens ( 31.35 ms per token, 31.90 tokens per second) 10.59.572.368 I slot print_timing: id 1 | task 17700 | total time = 14164.61 ms / 957 tokens 10.59.572.369 I slot print_timing: id 1 | task 17700 | graphs reused = 17287 10.59.572.369 I slot print_timing: id 1 | task 17700 | graph reallocs = 0 / 0 (same size) / (changed size) 10.59.572.452 I slot release: id 1 | task 17700 | stop processing: n_tokens = 1626, truncated = 0 10.59.607.056 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.657 10.59.607.091 I slot launch_slot_: id 1 | task 18134 | processing task, is_child = 0 11.00.173.584 I slot print_timing: id 2 | task 17661 | n_gen = 470, tg = 29.61 t/s, tg_3s = 27.46 t/s 11.01.674.414 I slot print_timing: id 0 | task 17798 | n_gen = 384, tg = 31.72 t/s, tg_3s = 26.96 t/s 11.02.552.462 I slot print_timing: id 3 | task 17644 | n_gen = 564, tg = 29.25 t/s, tg_3s = 26.92 t/s 11.02.582.701 I slot print_timing: id 2 | task 17661 | prompt eval time = 591.54 ms / 436 tokens ( 1.36 ms per token, 737.06 tokens per second) 11.02.582.704 I slot print_timing: id 2 | task 17661 | eval time = 18249.94 ms / 549 tokens ( 33.30 ms per token, 30.03 tokens per second) 11.02.582.705 I slot print_timing: id 2 | task 17661 | total time = 18841.48 ms / 985 tokens 11.02.582.706 I slot print_timing: id 2 | task 17661 | graphs reused = 17364 11.02.582.706 I slot print_timing: id 2 | task 17661 | graph reallocs = 0 / 0 (same size) / (changed size) 11.02.582.805 I slot release: id 2 | task 17661 | stop processing: n_tokens = 1679, truncated = 0 11.02.617.131 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.636 11.02.617.164 I slot launch_slot_: id 2 | task 18216 | processing task, is_child = 0 11.03.785.379 I slot print_timing: id 1 | task 18134 | n_gen = 100, tg = 27.87 t/s, tg_3s = 28.15 t/s 11.04.689.279 I slot print_timing: id 0 | task 17798 | n_gen = 465, tg = 30.75 t/s, tg_3s = 26.87 t/s 11.05.562.375 I slot print_timing: id 3 | task 17644 | n_gen = 645, tg = 28.93 t/s, tg_3s = 26.91 t/s 11.06.256.965 I slot print_timing: id 2 | task 18216 | n_gen = 101, tg = 33.25 t/s, tg_3s = 33.58 t/s 11.06.802.988 I slot print_timing: id 1 | task 18134 | n_gen = 200, tg = 30.29 t/s, tg_3s = 33.14 t/s 11.07.713.768 I slot print_timing: id 0 | task 17798 | n_gen = 565, tg = 31.13 t/s, tg_3s = 33.06 t/s 11.08.585.352 I slot print_timing: id 3 | task 17644 | n_gen = 745, tg = 29.43 t/s, tg_3s = 33.08 t/s 11.09.275.991 I slot print_timing: id 2 | task 18216 | n_gen = 201, tg = 33.18 t/s, tg_3s = 33.12 t/s 11.09.818.959 I slot print_timing: id 1 | task 18134 | n_gen = 300, tg = 31.19 t/s, tg_3s = 33.16 t/s 11.10.726.065 I slot print_timing: id 0 | task 17798 | n_gen = 665, tg = 31.43 t/s, tg_3s = 33.20 t/s 11.11.146.751 I slot print_timing: id 0 | task 17798 | prompt eval time = 601.88 ms / 467 tokens ( 1.29 ms per token, 775.91 tokens per second) 11.11.146.757 I slot print_timing: id 0 | task 17798 | eval time = 21548.14 ms / 679 tokens ( 31.78 ms per token, 31.46 tokens per second) 11.11.146.757 I slot print_timing: id 0 | task 17798 | total time = 22150.01 ms / 1146 tokens 11.11.146.758 I slot print_timing: id 0 | task 17798 | graphs reused = 17624 11.11.146.759 I slot print_timing: id 0 | task 17798 | graph reallocs = 0 / 0 (same size) / (changed size) 11.11.146.838 I slot release: id 0 | task 17798 | stop processing: n_tokens = 1838, truncated = 0 11.11.175.294 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.581 11.11.175.328 I slot launch_slot_: id 0 | task 18482 | processing task, is_child = 0 11.11.698.459 I slot print_timing: id 3 | task 17644 | n_gen = 832, tg = 29.27 t/s, tg_3s = 27.95 t/s 11.12.289.404 I slot print_timing: id 2 | task 18216 | n_gen = 284, tg = 31.30 t/s, tg_3s = 27.54 t/s 11.12.819.921 I slot print_timing: id 1 | task 18134 | n_gen = 383, tg = 30.35 t/s, tg_3s = 27.66 t/s 11.14.716.298 I slot print_timing: id 3 | task 17644 | n_gen = 932, tg = 29.64 t/s, tg_3s = 33.14 t/s 11.14.774.526 I slot print_timing: id 0 | task 18482 | n_gen = 102, tg = 33.37 t/s, tg_3s = 33.70 t/s 11.15.319.445 I slot print_timing: id 2 | task 18216 | n_gen = 385, tg = 31.81 t/s, tg_3s = 33.33 t/s 11.15.830.045 I slot print_timing: id 1 | task 18134 | n_gen = 483, tg = 30.90 t/s, tg_3s = 33.22 t/s 11.17.497.318 I slot print_timing: id 3 | task 17644 | prompt eval time = 445.90 ms / 293 tokens ( 1.52 ms per token, 657.09 tokens per second) 11.17.497.325 I slot print_timing: id 3 | task 17644 | eval time = 34191.87 ms / 1024 tokens ( 33.42 ms per token, 29.92 tokens per second) 11.17.497.326 I slot print_timing: id 3 | task 17644 | total time = 34637.77 ms / 1317 tokens 11.17.497.326 I slot print_timing: id 3 | task 17644 | graphs reused = 17814 11.17.497.327 I slot print_timing: id 3 | task 17644 | graph reallocs = 0 / 0 (same size) / (changed size) 11.17.497.422 I slot release: id 3 | task 17644 | stop processing: n_tokens = 2194, truncated = 0 11.17.524.337 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.487 11.17.532.091 I slot launch_slot_: id 3 | task 18677 | processing task, is_child = 0 11.17.921.340 I slot print_timing: id 0 | task 18482 | n_gen = 194, tg = 31.26 t/s, tg_3s = 29.24 t/s 11.18.332.392 I slot print_timing: id 2 | task 18216 | n_gen = 472, tg = 31.23 t/s, tg_3s = 28.88 t/s 11.18.842.211 I slot print_timing: id 1 | task 18134 | n_gen = 570, tg = 30.58 t/s, tg_3s = 28.88 t/s 11.20.947.419 I slot print_timing: id 0 | task 18482 | n_gen = 295, tg = 31.96 t/s, tg_3s = 33.38 t/s 11.20.980.962 I slot print_timing: id 3 | task 18677 | n_gen = 102, tg = 33.59 t/s, tg_3s = 33.92 t/s 11.21.340.474 I slot print_timing: id 2 | task 18216 | n_gen = 573, tg = 31.62 t/s, tg_3s = 33.58 t/s 11.21.849.912 I slot print_timing: id 1 | task 18134 | n_gen = 671, tg = 30.99 t/s, tg_3s = 33.58 t/s 11.23.947.546 I slot print_timing: id 0 | task 18482 | n_gen = 394, tg = 32.21 t/s, tg_3s = 33.00 t/s 11.24.008.037 I slot print_timing: id 3 | task 18677 | n_gen = 202, tg = 33.31 t/s, tg_3s = 33.04 t/s 11.24.370.145 I slot print_timing: id 2 | task 18216 | n_gen = 673, tg = 31.82 t/s, tg_3s = 33.01 t/s 11.24.874.680 I slot print_timing: id 1 | task 18134 | n_gen = 771, tg = 31.25 t/s, tg_3s = 33.06 t/s 11.25.319.778 I slot print_timing: id 1 | task 18134 | prompt eval time = 626.12 ms / 470 tokens ( 1.33 ms per token, 750.65 tokens per second) 11.25.319.785 I slot print_timing: id 1 | task 18134 | eval time = 25086.56 ms / 786 tokens ( 31.96 ms per token, 31.29 tokens per second) 11.25.319.785 I slot print_timing: id 1 | task 18134 | total time = 25712.68 ms / 1256 tokens 11.25.319.786 I slot print_timing: id 1 | task 18134 | graphs reused = 18057 11.25.319.787 I slot print_timing: id 1 | task 18134 | graph reallocs = 0 / 0 (same size) / (changed size) 11.25.319.891 I slot release: id 1 | task 18134 | stop processing: n_tokens = 1937, truncated = 0 11.25.354.459 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.551 11.25.354.490 I slot launch_slot_: id 1 | task 18926 | processing task, is_child = 0 11.26.962.054 I slot print_timing: id 0 | task 18482 | n_gen = 475, tg = 31.16 t/s, tg_3s = 26.87 t/s 11.27.024.414 I slot print_timing: id 3 | task 18677 | n_gen = 283, tg = 31.16 t/s, tg_3s = 26.85 t/s 11.27.384.193 I slot print_timing: id 2 | task 18216 | n_gen = 754, tg = 31.20 t/s, tg_3s = 26.87 t/s 11.29.007.279 I slot print_timing: id 1 | task 18926 | n_gen = 101, tg = 33.27 t/s, tg_3s = 33.61 t/s 11.29.974.076 I slot print_timing: id 0 | task 18482 | n_gen = 575, tg = 31.49 t/s, tg_3s = 33.20 t/s 11.30.036.829 I slot print_timing: id 3 | task 18677 | n_gen = 383, tg = 31.67 t/s, tg_3s = 33.20 t/s 11.30.402.903 I slot print_timing: id 2 | task 18216 | n_gen = 854, tg = 31.41 t/s, tg_3s = 33.13 t/s 11.30.433.910 I slot print_timing: id 3 | task 18677 | prompt eval time = 441.76 ms / 287 tokens ( 1.54 ms per token, 649.67 tokens per second) 11.30.433.917 I slot print_timing: id 3 | task 18677 | eval time = 12460.04 ms / 396 tokens ( 31.54 ms per token, 31.70 tokens per second) 11.30.433.918 I slot print_timing: id 3 | task 18677 | total time = 12901.81 ms / 683 tokens 11.30.433.919 I slot print_timing: id 3 | task 18677 | graphs reused = 18203 11.30.433.919 I slot print_timing: id 3 | task 18677 | graph reallocs = 0 / 0 (same size) / (changed size) 11.30.434.007 I slot release: id 3 | task 18677 | stop processing: n_tokens = 1560, truncated = 0 11.30.461.810 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.685 11.30.461.843 I slot launch_slot_: id 3 | task 19077 | processing task, is_child = 0 11.32.023.343 I slot print_timing: id 1 | task 18926 | n_gen = 189, tg = 31.22 t/s, tg_3s = 29.18 t/s 11.32.985.308 I slot print_timing: id 0 | task 18482 | n_gen = 663, tg = 31.17 t/s, tg_3s = 29.22 t/s 11.33.406.298 I slot print_timing: id 2 | task 18216 | n_gen = 942, tg = 31.20 t/s, tg_3s = 29.30 t/s 11.33.894.445 I slot print_timing: id 3 | task 19077 | n_gen = 101, tg = 33.16 t/s, tg_3s = 33.49 t/s 11.34.629.154 I slot print_timing: id 2 | task 18216 | prompt eval time = 631.91 ms / 483 tokens ( 1.31 ms per token, 764.35 tokens per second) 11.34.629.161 I slot print_timing: id 2 | task 18216 | eval time = 31380.07 ms / 983 tokens ( 31.96 ms per token, 31.29 tokens per second) 11.34.629.162 I slot print_timing: id 2 | task 18216 | total time = 32011.98 ms / 1466 tokens 11.34.629.163 I slot print_timing: id 2 | task 18216 | graphs reused = 18326 11.34.629.164 I slot print_timing: id 2 | task 18216 | graph reallocs = 0 / 0 (same size) / (changed size) 11.34.629.257 I slot release: id 2 | task 18216 | stop processing: n_tokens = 2160, truncated = 0 11.34.663.676 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.494 11.34.665.843 I slot launch_slot_: id 2 | task 19206 | processing task, is_child = 0 11.35.204.623 I slot print_timing: id 1 | task 18926 | n_gen = 278, tg = 30.10 t/s, tg_3s = 27.98 t/s 11.36.006.725 I slot print_timing: id 0 | task 18482 | n_gen = 746, tg = 30.71 t/s, tg_3s = 27.47 t/s 11.36.770.312 I slot print_timing: id 0 | task 18482 | prompt eval time = 572.68 ms / 441 tokens ( 1.30 ms per token, 770.06 tokens per second) 11.36.770.318 I slot print_timing: id 0 | task 18482 | eval time = 25022.30 ms / 772 tokens ( 32.45 ms per token, 30.81 tokens per second) 11.36.770.319 I slot print_timing: id 0 | task 18482 | total time = 25594.98 ms / 1213 tokens 11.36.770.320 I slot print_timing: id 0 | task 18482 | graphs reused = 18376 11.36.770.321 I slot print_timing: id 0 | task 18482 | graph reallocs = 0 / 0 (same size) / (changed size) 11.36.770.406 I slot release: id 0 | task 18482 | stop processing: n_tokens = 1905, truncated = 0 11.36.797.286 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.561 11.36.797.312 I slot launch_slot_: id 0 | task 19261 | processing task, is_child = 0 11.37.349.077 I slot print_timing: id 3 | task 19077 | n_gen = 182, tg = 27.97 t/s, tg_3s = 23.45 t/s 11.38.205.609 I slot print_timing: id 1 | task 18926 | n_gen = 360, tg = 29.42 t/s, tg_3s = 27.32 t/s 11.38.753.618 I slot print_timing: id 2 | task 19206 | n_gen = 100, tg = 28.36 t/s, tg_3s = 28.65 t/s 11.40.373.191 I slot print_timing: id 3 | task 19077 | n_gen = 282, tg = 29.60 t/s, tg_3s = 33.07 t/s 11.40.401.556 I slot print_timing: id 0 | task 19261 | n_gen = 101, tg = 33.30 t/s, tg_3s = 33.64 t/s 11.41.213.387 I slot print_timing: id 1 | task 18926 | n_gen = 460, tg = 30.17 t/s, tg_3s = 33.25 t/s 11.41.755.506 I slot print_timing: id 2 | task 19206 | n_gen = 200, tg = 30.65 t/s, tg_3s = 33.31 t/s 11.43.398.868 I slot print_timing: id 3 | task 19077 | n_gen = 383, tg = 30.51 t/s, tg_3s = 33.38 t/s 11.43.427.432 I slot print_timing: id 0 | task 19261 | n_gen = 202, tg = 33.34 t/s, tg_3s = 33.38 t/s 11.44.233.851 I slot print_timing: id 1 | task 18926 | n_gen = 561, tg = 30.72 t/s, tg_3s = 33.44 t/s 11.44.764.726 I slot print_timing: id 2 | task 19206 | n_gen = 301, tg = 31.57 t/s, tg_3s = 33.56 t/s 11.46.260.935 I slot print_timing: id 3 | task 19077 | prompt eval time = 416.86 ms / 258 tokens ( 1.62 ms per token, 618.92 tokens per second) 11.46.260.942 I slot print_timing: id 3 | task 19077 | eval time = 15382.23 ms / 478 tokens ( 32.25 ms per token, 31.01 tokens per second) 11.46.260.943 I slot print_timing: id 3 | task 19077 | total time = 15799.09 ms / 736 tokens 11.46.260.943 I slot print_timing: id 3 | task 19077 | graphs reused = 18669 11.46.260.944 I slot print_timing: id 3 | task 19077 | graph reallocs = 0 / 0 (same size) / (changed size) 11.46.261.035 I slot release: id 3 | task 19077 | stop processing: n_tokens = 1613, truncated = 0 11.46.288.281 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.662 11.46.288.311 I slot launch_slot_: id 3 | task 19560 | processing task, is_child = 0 11.46.680.986 I slot print_timing: id 0 | task 19261 | n_gen = 298, tg = 32.00 t/s, tg_3s = 29.51 t/s 11.47.247.791 I slot print_timing: id 1 | task 18926 | n_gen = 648, tg = 30.45 t/s, tg_3s = 28.87 t/s 11.47.767.846 I slot print_timing: id 2 | task 19206 | n_gen = 387, tg = 30.87 t/s, tg_3s = 28.64 t/s 11.49.690.930 I slot print_timing: id 0 | task 19261 | n_gen = 397, tg = 32.22 t/s, tg_3s = 32.89 t/s 11.49.752.843 I slot print_timing: id 3 | task 19560 | n_gen = 101, tg = 33.13 t/s, tg_3s = 33.46 t/s 11.50.027.802 I slot print_timing: id 2 | task 19206 | prompt eval time = 597.22 ms / 444 tokens ( 1.35 ms per token, 743.45 tokens per second) 11.50.027.806 I slot print_timing: id 2 | task 19206 | eval time = 14764.73 ms / 462 tokens ( 32.03 ms per token, 31.22 tokens per second) 11.50.027.807 I slot print_timing: id 2 | task 19206 | total time = 15361.94 ms / 906 tokens 11.50.027.808 I slot print_timing: id 2 | task 19206 | graphs reused = 18777 11.50.027.808 I slot print_timing: id 2 | task 19206 | graph reallocs = 0 / 0 (same size) / (changed size) 11.50.027.911 I slot release: id 2 | task 19206 | stop processing: n_tokens = 1600, truncated = 0 11.50.062.933 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.668 11.50.062.969 I slot launch_slot_: id 2 | task 19673 | processing task, is_child = 0 11.50.605.398 I slot print_timing: id 1 | task 18926 | n_gen = 742, tg = 30.12 t/s, tg_3s = 28.00 t/s 11.52.693.039 I slot print_timing: id 0 | task 19261 | n_gen = 479, tg = 31.25 t/s, tg_3s = 27.31 t/s 11.52.753.959 I slot print_timing: id 3 | task 19560 | n_gen = 183, tg = 30.23 t/s, tg_3s = 27.32 t/s 11.53.617.271 I slot print_timing: id 1 | task 18926 | n_gen = 842, tg = 30.45 t/s, tg_3s = 33.20 t/s 11.53.678.085 I slot print_timing: id 2 | task 19673 | n_gen = 102, tg = 33.50 t/s, tg_3s = 33.83 t/s 11.55.716.784 I slot print_timing: id 0 | task 19261 | n_gen = 580, tg = 31.61 t/s, tg_3s = 33.40 t/s 11.55.780.490 I slot print_timing: id 3 | task 19560 | n_gen = 284, tg = 31.28 t/s, tg_3s = 33.37 t/s 11.56.625.876 I slot print_timing: id 1 | task 18926 | n_gen = 942, tg = 30.73 t/s, tg_3s = 33.24 t/s 11.56.687.392 I slot print_timing: id 2 | task 19673 | n_gen = 202, tg = 33.37 t/s, tg_3s = 33.23 t/s 11.58.740.424 I slot print_timing: id 0 | task 19261 | n_gen = 680, tg = 31.82 t/s, tg_3s = 33.07 t/s 11.58.801.582 I slot print_timing: id 3 | task 19560 | n_gen = 384, tg = 31.74 t/s, tg_3s = 33.10 t/s 11.59.100.868 I slot print_timing: id 1 | task 18926 | prompt eval time = 647.39 ms / 493 tokens ( 1.31 ms per token, 761.52 tokens per second) 11.59.100.874 I slot print_timing: id 1 | task 18926 | eval time = 33098.98 ms / 1024 tokens ( 32.35 ms per token, 30.91 tokens per second) 11.59.100.875 I slot print_timing: id 1 | task 18926 | total time = 33746.37 ms / 1517 tokens 11.59.100.876 I slot print_timing: id 1 | task 18926 | graphs reused = 19056 11.59.100.882 I slot print_timing: id 1 | task 18926 | graph reallocs = 0 / 0 (same size) / (changed size) 11.59.100.979 I slot release: id 1 | task 18926 | stop processing: n_tokens = 2198, truncated = 0 11.59.134.620 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 11.59.140.505 I slot launch_slot_: id 1 | task 19958 | processing task, is_child = 0 11.59.713.217 I slot print_timing: id 2 | task 19673 | n_gen = 284, tg = 31.27 t/s, tg_3s = 27.10 t/s 12.01.743.588 I slot print_timing: id 0 | task 19261 | n_gen = 760, tg = 31.18 t/s, tg_3s = 26.64 t/s 12.01.805.389 I slot print_timing: id 3 | task 19560 | n_gen = 464, tg = 30.72 t/s, tg_3s = 26.63 t/s 12.02.731.878 I slot print_timing: id 2 | task 19673 | n_gen = 383, tg = 31.65 t/s, tg_3s = 32.80 t/s 12.02.790.884 I slot print_timing: id 1 | task 19958 | n_gen = 101, tg = 33.13 t/s, tg_3s = 33.46 t/s 12.04.766.221 I slot print_timing: id 0 | task 19261 | n_gen = 861, tg = 31.42 t/s, tg_3s = 33.41 t/s 12.04.828.288 I slot print_timing: id 3 | task 19560 | n_gen = 565, tg = 31.17 t/s, tg_3s = 33.41 t/s 12.05.735.004 I slot print_timing: id 2 | task 19673 | n_gen = 483, tg = 31.98 t/s, tg_3s = 33.30 t/s 12.05.795.347 I slot print_timing: id 1 | task 19958 | n_gen = 201, tg = 33.20 t/s, tg_3s = 33.28 t/s 12.07.776.279 I slot print_timing: id 0 | task 19261 | n_gen = 960, tg = 31.57 t/s, tg_3s = 32.89 t/s 12.07.837.573 I slot print_timing: id 3 | task 19560 | n_gen = 664, tg = 31.42 t/s, tg_3s = 32.90 t/s 12.08.744.531 I slot print_timing: id 2 | task 19673 | n_gen = 582, tg = 32.13 t/s, tg_3s = 32.90 t/s 12.08.805.523 I slot print_timing: id 1 | task 19958 | n_gen = 300, tg = 33.10 t/s, tg_3s = 32.89 t/s 12.09.709.665 I slot print_timing: id 0 | task 19261 | prompt eval time = 601.55 ms / 467 tokens ( 1.29 ms per token, 776.33 tokens per second) 12.09.709.671 I slot print_timing: id 0 | task 19261 | eval time = 32310.79 ms / 1024 tokens ( 31.58 ms per token, 31.66 tokens per second) 12.09.709.672 I slot print_timing: id 0 | task 19261 | total time = 32912.34 ms / 1491 tokens 12.09.709.673 I slot print_timing: id 0 | task 19261 | graphs reused = 19383 12.09.709.673 I slot print_timing: id 0 | task 19261 | graph reallocs = 0 / 0 (same size) / (changed size) 12.09.709.758 I slot release: id 0 | task 19261 | stop processing: n_tokens = 2183, truncated = 0 12.09.738.167 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.489 12.09.744.161 I slot launch_slot_: id 0 | task 20291 | processing task, is_child = 0 12.10.841.112 I slot print_timing: id 3 | task 19560 | n_gen = 745, tg = 30.86 t/s, tg_3s = 26.97 t/s 12.10.900.238 I slot print_timing: id 2 | task 19673 | prompt eval time = 600.40 ms / 449 tokens ( 1.34 ms per token, 747.83 tokens per second) 12.10.900.245 I slot print_timing: id 2 | task 19673 | eval time = 20236.86 ms / 635 tokens ( 31.92 ms per token, 31.33 tokens per second) 12.10.900.246 I slot print_timing: id 2 | task 19673 | total time = 20837.26 ms / 1084 tokens 12.10.900.246 I slot print_timing: id 2 | task 19673 | graphs reused = 19401 12.10.900.247 I slot print_timing: id 2 | task 19673 | graph reallocs = 0 / 0 (same size) / (changed size) 12.10.900.339 I slot release: id 2 | task 19673 | stop processing: n_tokens = 1778, truncated = 0 12.10.934.730 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.601 12.10.934.762 I slot launch_slot_: id 2 | task 20313 | processing task, is_child = 0 12.11.829.903 I slot print_timing: id 1 | task 19958 | n_gen = 363, tg = 30.02 t/s, tg_3s = 20.83 t/s 12.12.497.202 I slot print_timing: id 3 | task 19560 | prompt eval time = 445.94 ms / 291 tokens ( 1.53 ms per token, 652.55 tokens per second) 12.12.497.209 I slot print_timing: id 3 | task 19560 | eval time = 25762.94 ms / 781 tokens ( 33.03 ms per token, 30.28 tokens per second) 12.12.497.209 I slot print_timing: id 3 | task 19560 | total time = 26208.88 ms / 1072 tokens 12.12.497.210 I slot print_timing: id 3 | task 19560 | graphs reused = 19431 12.12.497.211 I slot print_timing: id 3 | task 19560 | graph reallocs = 0 / 0 (same size) / (changed size) 12.12.497.300 I slot release: id 3 | task 19560 | stop processing: n_tokens = 1949, truncated = 0 12.12.524.680 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.548 12.12.524.713 I slot launch_slot_: id 3 | task 20348 | processing task, is_child = 0 12.14.290.445 I slot print_timing: id 0 | task 20291 | n_gen = 100, tg = 25.16 t/s, tg_3s = 25.42 t/s 12.14.859.902 I slot print_timing: id 1 | task 19958 | n_gen = 451, tg = 29.83 t/s, tg_3s = 29.04 t/s 12.14.920.330 I slot print_timing: id 2 | task 20313 | n_gen = 100, tg = 29.45 t/s, tg_3s = 29.74 t/s 12.15.987.178 I slot print_timing: id 3 | task 20348 | n_gen = 102, tg = 33.41 t/s, tg_3s = 33.74 t/s 12.17.302.341 I slot print_timing: id 0 | task 20291 | n_gen = 201, tg = 28.79 t/s, tg_3s = 33.53 t/s 12.17.870.739 I slot print_timing: id 1 | task 19958 | n_gen = 552, tg = 30.44 t/s, tg_3s = 33.55 t/s 12.17.930.570 I slot print_timing: id 2 | task 20313 | n_gen = 201, tg = 31.39 t/s, tg_3s = 33.55 t/s 12.19.002.341 I slot print_timing: id 3 | task 20348 | n_gen = 203, tg = 33.45 t/s, tg_3s = 33.50 t/s 12.20.326.173 I slot print_timing: id 0 | task 20291 | n_gen = 302, tg = 30.19 t/s, tg_3s = 33.40 t/s 12.20.889.623 I slot print_timing: id 1 | task 19958 | n_gen = 653, tg = 30.87 t/s, tg_3s = 33.46 t/s 12.20.949.086 I slot print_timing: id 2 | task 20313 | n_gen = 302, tg = 32.05 t/s, tg_3s = 33.46 t/s 12.22.022.149 I slot print_timing: id 3 | task 20348 | n_gen = 304, tg = 33.45 t/s, tg_3s = 33.45 t/s 12.23.353.894 I slot print_timing: id 0 | task 20291 | n_gen = 403, tg = 30.93 t/s, tg_3s = 33.36 t/s 12.23.900.095 I slot print_timing: id 1 | task 19958 | n_gen = 753, tg = 31.17 t/s, tg_3s = 33.22 t/s 12.23.961.045 I slot print_timing: id 2 | task 20313 | n_gen = 402, tg = 32.33 t/s, tg_3s = 33.20 t/s 12.24.110.420 I slot print_timing: id 1 | task 19958 | prompt eval time = 631.63 ms / 479 tokens ( 1.32 ms per token, 758.36 tokens per second) 12.24.110.427 I slot print_timing: id 1 | task 19958 | eval time = 24338.28 ms / 760 tokens ( 32.07 ms per token, 31.19 tokens per second) 12.24.110.428 I slot print_timing: id 1 | task 19958 | total time = 24969.91 ms / 1239 tokens 12.24.110.428 I slot print_timing: id 1 | task 19958 | graphs reused = 19801 12.24.110.429 I slot print_timing: id 1 | task 19958 | graph reallocs = 0 / 0 (same size) / (changed size) 12.24.110.525 I slot release: id 1 | task 19958 | stop processing: n_tokens = 1920, truncated = 0 12.24.145.575 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.556 12.24.145.607 I slot launch_slot_: id 1 | task 20724 | processing task, is_child = 0 12.25.041.446 I slot print_timing: id 3 | task 20348 | n_gen = 385, tg = 31.79 t/s, tg_3s = 26.83 t/s 12.26.379.630 I slot print_timing: id 0 | task 20291 | n_gen = 485, tg = 30.21 t/s, tg_3s = 27.10 t/s 12.26.985.905 I slot print_timing: id 2 | task 20313 | n_gen = 484, tg = 31.31 t/s, tg_3s = 27.11 t/s 12.27.766.902 I slot print_timing: id 1 | task 20724 | n_gen = 101, tg = 33.33 t/s, tg_3s = 33.66 t/s 12.28.069.235 I slot print_timing: id 3 | task 20348 | n_gen = 486, tg = 32.11 t/s, tg_3s = 33.36 t/s 12.29.399.841 I slot print_timing: id 0 | task 20291 | n_gen = 585, tg = 30.67 t/s, tg_3s = 33.11 t/s 12.29.999.837 I slot print_timing: id 2 | task 20313 | n_gen = 584, tg = 31.61 t/s, tg_3s = 33.18 t/s 12.30.779.459 I slot print_timing: id 1 | task 20724 | n_gen = 201, tg = 33.26 t/s, tg_3s = 33.19 t/s 12.31.082.677 I slot print_timing: id 3 | task 20348 | n_gen = 586, tg = 32.29 t/s, tg_3s = 33.18 t/s 12.31.143.292 I slot print_timing: id 2 | task 20313 | prompt eval time = 623.65 ms / 472 tokens ( 1.32 ms per token, 756.84 tokens per second) 12.31.143.295 I slot print_timing: id 2 | task 20313 | eval time = 19584.88 ms / 622 tokens ( 31.54 ms per token, 31.71 tokens per second) 12.31.143.296 I slot print_timing: id 2 | task 20313 | total time = 20208.52 ms / 1094 tokens 12.31.143.297 I slot print_timing: id 2 | task 20313 | graphs reused = 20011 12.31.143.297 I slot print_timing: id 2 | task 20313 | graph reallocs = 0 / 0 (same size) / (changed size) 12.31.143.391 I slot release: id 2 | task 20313 | stop processing: n_tokens = 1788, truncated = 0 12.31.178.084 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.597 12.31.178.121 I slot launch_slot_: id 2 | task 20940 | processing task, is_child = 0 12.32.403.837 I slot print_timing: id 0 | task 20291 | n_gen = 667, tg = 30.21 t/s, tg_3s = 27.30 t/s 12.33.799.028 I slot print_timing: id 1 | task 20724 | n_gen = 284, tg = 31.33 t/s, tg_3s = 27.49 t/s 12.34.098.467 I slot print_timing: id 3 | task 20348 | prompt eval time = 439.09 ms / 281 tokens ( 1.56 ms per token, 639.96 tokens per second) 12.34.098.474 I slot print_timing: id 3 | task 20348 | eval time = 21134.65 ms / 669 tokens ( 31.64 ms per token, 31.61 tokens per second) 12.34.098.475 I slot print_timing: id 3 | task 20348 | total time = 21573.75 ms / 950 tokens 12.34.098.476 I slot print_timing: id 3 | task 20348 | graphs reused = 20088 12.34.098.476 I slot print_timing: id 3 | task 20348 | graph reallocs = 0 / 0 (same size) / (changed size) 12.34.098.575 I slot release: id 3 | task 20348 | stop processing: n_tokens = 1827, truncated = 0 12.34.125.961 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.585 12.34.125.988 I slot launch_slot_: id 3 | task 21022 | processing task, is_child = 0 12.35.070.193 I slot print_timing: id 1 | task 20724 | prompt eval time = 620.66 ms / 462 tokens ( 1.34 ms per token, 744.37 tokens per second) 12.35.070.196 I slot print_timing: id 1 | task 20724 | eval time = 10303.92 ms / 313 tokens ( 33.03 ms per token, 30.28 tokens per second) 12.35.070.197 I slot print_timing: id 1 | task 20724 | total time = 10924.58 ms / 775 tokens 12.35.070.198 I slot print_timing: id 1 | task 20724 | graphs reused = 20103 12.35.070.204 I slot print_timing: id 1 | task 20724 | graph reallocs = 0 / 0 (same size) / (changed size) 12.35.070.300 I slot release: id 1 | task 20724 | stop processing: n_tokens = 1456, truncated = 0 12.35.105.498 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.734 12.35.105.548 I slot launch_slot_: id 1 | task 21042 | processing task, is_child = 0 12.35.646.288 I slot print_timing: id 0 | task 20291 | n_gen = 745, tg = 29.42 t/s, tg_3s = 24.06 t/s 12.35.646.604 I slot print_timing: id 2 | task 20940 | n_gen = 100, tg = 25.57 t/s, tg_3s = 25.83 t/s 12.38.085.419 I slot print_timing: id 3 | task 21022 | n_gen = 100, tg = 28.37 t/s, tg_3s = 28.65 t/s 12.38.647.626 I slot print_timing: id 0 | task 20291 | n_gen = 845, tg = 29.83 t/s, tg_3s = 33.32 t/s 12.38.648.618 I slot print_timing: id 2 | task 20940 | n_gen = 200, tg = 28.95 t/s, tg_3s = 33.31 t/s 12.38.708.032 I slot print_timing: id 1 | task 21042 | n_gen = 102, tg = 33.65 t/s, tg_3s = 33.98 t/s 12.41.092.809 I slot print_timing: id 3 | task 21022 | n_gen = 200, tg = 30.63 t/s, tg_3s = 33.25 t/s 12.41.663.732 I slot print_timing: id 0 | task 20291 | n_gen = 945, tg = 30.15 t/s, tg_3s = 33.16 t/s 12.41.664.681 I slot print_timing: id 2 | task 20940 | n_gen = 300, tg = 30.23 t/s, tg_3s = 33.16 t/s 12.41.724.629 I slot print_timing: id 1 | task 21042 | n_gen = 202, tg = 33.40 t/s, tg_3s = 33.15 t/s 12.44.036.954 I slot print_timing: id 0 | task 20291 | prompt eval time = 612.06 ms / 482 tokens ( 1.27 ms per token, 787.50 tokens per second) 12.44.036.960 I slot print_timing: id 0 | task 20291 | eval time = 33680.72 ms / 1024 tokens ( 32.92 ms per token, 30.37 tokens per second) 12.44.036.961 I slot print_timing: id 0 | task 20291 | total time = 34292.78 ms / 1506 tokens 12.44.036.961 I slot print_timing: id 0 | task 20291 | graphs reused = 20379 12.44.036.962 I slot print_timing: id 0 | task 20291 | graph reallocs = 0 / 0 (same size) / (changed size) 12.44.037.044 I slot release: id 0 | task 20291 | stop processing: n_tokens = 2198, truncated = 0 12.44.063.963 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.486 12.44.069.734 I slot launch_slot_: id 0 | task 21324 | processing task, is_child = 0 12.44.600.390 I slot print_timing: id 3 | task 21022 | n_gen = 300, tg = 29.88 t/s, tg_3s = 28.51 t/s 12.44.681.185 I slot print_timing: id 2 | task 20940 | n_gen = 383, tg = 29.60 t/s, tg_3s = 27.52 t/s 12.44.738.010 I slot print_timing: id 1 | task 21042 | n_gen = 285, tg = 31.44 t/s, tg_3s = 27.54 t/s 12.47.620.558 I slot print_timing: id 3 | task 21022 | n_gen = 400, tg = 30.63 t/s, tg_3s = 33.11 t/s 12.47.678.455 I slot print_timing: id 0 | task 21324 | n_gen = 102, tg = 33.35 t/s, tg_3s = 33.68 t/s 12.47.709.343 I slot print_timing: id 2 | task 20940 | n_gen = 484, tg = 30.31 t/s, tg_3s = 33.35 t/s 12.47.739.099 I slot print_timing: id 1 | task 21042 | n_gen = 385, tg = 31.91 t/s, tg_3s = 33.32 t/s 12.50.611.916 I slot print_timing: id 1 | task 21042 | prompt eval time = 600.76 ms / 448 tokens ( 1.34 ms per token, 745.72 tokens per second) 12.50.611.920 I slot print_timing: id 1 | task 21042 | eval time = 14905.59 ms / 481 tokens ( 31.05 ms per token, 32.20 tokens per second) 12.50.611.921 I slot print_timing: id 1 | task 21042 | total time = 15506.36 ms / 929 tokens 12.50.611.921 I slot print_timing: id 1 | task 21042 | graphs reused = 20577 12.50.611.922 I slot print_timing: id 1 | task 21042 | graph reallocs = 0 / 0 (same size) / (changed size) 12.50.612.019 I slot release: id 1 | task 21042 | stop processing: n_tokens = 1610, truncated = 0 12.50.647.103 I slot print_timing: id 3 | task 21022 | n_gen = 501, tg = 31.15 t/s, tg_3s = 33.37 t/s 12.50.647.109 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.663 12.50.647.151 I slot launch_slot_: id 1 | task 21527 | processing task, is_child = 0 12.51.202.925 I slot print_timing: id 0 | task 21324 | n_gen = 202, tg = 30.67 t/s, tg_3s = 28.37 t/s 12.51.203.257 I slot print_timing: id 2 | task 20940 | n_gen = 583, tg = 29.96 t/s, tg_3s = 28.33 t/s 12.53.668.906 I slot print_timing: id 3 | task 21022 | n_gen = 583, tg = 30.51 t/s, tg_3s = 27.14 t/s 12.54.206.685 I slot print_timing: id 0 | task 21324 | n_gen = 301, tg = 31.39 t/s, tg_3s = 32.96 t/s 12.54.207.625 I slot print_timing: id 2 | task 20940 | n_gen = 682, tg = 30.36 t/s, tg_3s = 32.95 t/s 12.54.268.522 I slot print_timing: id 1 | task 21527 | n_gen = 101, tg = 33.27 t/s, tg_3s = 33.60 t/s 12.56.673.347 I slot print_timing: id 3 | task 21022 | n_gen = 683, tg = 30.89 t/s, tg_3s = 33.28 t/s 12.57.212.571 I slot print_timing: id 0 | task 21324 | n_gen = 401, tg = 31.84 t/s, tg_3s = 33.27 t/s 12.57.213.423 I slot print_timing: id 2 | task 20940 | n_gen = 782, tg = 30.70 t/s, tg_3s = 33.27 t/s 12.57.273.723 I slot print_timing: id 1 | task 21527 | n_gen = 201, tg = 33.27 t/s, tg_3s = 33.28 t/s 12.57.393.993 I slot print_timing: id 2 | task 20940 | prompt eval time = 596.61 ms / 443 tokens ( 1.35 ms per token, 742.52 tokens per second) 12.57.393.999 I slot print_timing: id 2 | task 20940 | eval time = 25619.25 ms / 788 tokens ( 32.55 ms per token, 30.72 tokens per second) 12.57.394.001 I slot print_timing: id 2 | task 20940 | total time = 26215.87 ms / 1231 tokens 12.57.394.004 I slot print_timing: id 2 | task 20940 | graphs reused = 20779 12.57.394.004 I slot print_timing: id 2 | task 20940 | graph reallocs = 0 / 0 (same size) / (changed size) 12.57.394.098 I slot release: id 2 | task 20940 | stop processing: n_tokens = 1925, truncated = 0 12.57.428.600 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.555 12.57.428.637 I slot launch_slot_: id 2 | task 21735 | processing task, is_child = 0 12.59.676.253 I slot print_timing: id 3 | task 21022 | n_gen = 764, tg = 30.42 t/s, tg_3s = 26.97 t/s 13.00.218.776 I slot print_timing: id 0 | task 21324 | n_gen = 482, tg = 30.90 t/s, tg_3s = 26.94 t/s 13.00.281.063 I slot print_timing: id 1 | task 21527 | n_gen = 282, tg = 31.16 t/s, tg_3s = 26.93 t/s 13.01.066.127 I slot print_timing: id 2 | task 21735 | n_gen = 101, tg = 33.13 t/s, tg_3s = 33.46 t/s 13.02.699.720 I slot print_timing: id 3 | task 21022 | n_gen = 864, tg = 30.71 t/s, tg_3s = 33.07 t/s 13.03.241.806 I slot print_timing: id 0 | task 21324 | n_gen = 582, tg = 31.25 t/s, tg_3s = 33.08 t/s 13.03.303.680 I slot print_timing: id 1 | task 21527 | n_gen = 382, tg = 31.64 t/s, tg_3s = 33.08 t/s 13.04.091.590 I slot print_timing: id 2 | task 21735 | n_gen = 201, tg = 33.09 t/s, tg_3s = 33.05 t/s 13.04.907.600 I slot print_timing: id 1 | task 21527 | prompt eval time = 615.36 ms / 456 tokens ( 1.35 ms per token, 741.03 tokens per second) 13.04.907.603 I slot print_timing: id 1 | task 21527 | eval time = 13645.07 ms / 435 tokens ( 31.44 ms per token, 31.81 tokens per second) 13.04.907.604 I slot print_timing: id 1 | task 21527 | total time = 14260.43 ms / 891 tokens 13.04.907.604 I slot print_timing: id 1 | task 21527 | graphs reused = 21004 13.04.907.605 I slot print_timing: id 1 | task 21527 | graph reallocs = 0 / 0 (same size) / (changed size) 13.04.907.703 I slot release: id 1 | task 21527 | stop processing: n_tokens = 1572, truncated = 0 13.04.943.137 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.679 13.04.943.169 I slot launch_slot_: id 1 | task 21966 | processing task, is_child = 0 13.05.727.268 I slot print_timing: id 3 | task 21022 | n_gen = 945, tg = 30.32 t/s, tg_3s = 26.75 t/s 13.06.248.697 I slot print_timing: id 0 | task 21324 | n_gen = 662, tg = 30.60 t/s, tg_3s = 26.61 t/s 13.07.098.883 I slot print_timing: id 2 | task 21735 | n_gen = 281, tg = 30.94 t/s, tg_3s = 26.60 t/s 13.08.138.274 I slot print_timing: id 3 | task 21022 | prompt eval time = 469.31 ms / 314 tokens ( 1.49 ms per token, 669.06 tokens per second) 13.08.138.280 I slot print_timing: id 3 | task 21022 | eval time = 33542.96 ms / 1024 tokens ( 32.79 ms per token, 30.50 tokens per second) 13.08.138.281 I slot print_timing: id 3 | task 21022 | total time = 34012.27 ms / 1338 tokens 13.08.138.282 I slot print_timing: id 3 | task 21022 | graphs reused = 21087 13.08.138.282 I slot print_timing: id 3 | task 21022 | graph reallocs = 0 / 0 (same size) / (changed size) 13.08.138.367 I slot release: id 3 | task 21022 | stop processing: n_tokens = 2215, truncated = 0 13.08.165.654 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.482 13.08.171.327 I slot launch_slot_: id 3 | task 22054 | processing task, is_child = 0 13.08.951.529 I slot print_timing: id 1 | task 21966 | n_gen = 100, tg = 29.33 t/s, tg_3s = 29.63 t/s 13.09.250.001 I slot print_timing: id 0 | task 21324 | n_gen = 749, tg = 30.41 t/s, tg_3s = 28.99 t/s 13.10.117.890 I slot print_timing: id 2 | task 21735 | n_gen = 369, tg = 30.49 t/s, tg_3s = 29.15 t/s 13.11.596.979 I slot print_timing: id 3 | task 22054 | n_gen = 102, tg = 33.55 t/s, tg_3s = 33.88 t/s 13.11.954.745 I slot print_timing: id 1 | task 21966 | n_gen = 201, tg = 31.36 t/s, tg_3s = 33.63 t/s 13.12.255.902 I slot print_timing: id 0 | task 21324 | n_gen = 850, tg = 30.75 t/s, tg_3s = 33.60 t/s 13.12.639.819 I slot print_timing: id 0 | task 21324 | prompt eval time = 580.22 ms / 450 tokens ( 1.29 ms per token, 775.56 tokens per second) 13.12.639.825 I slot print_timing: id 0 | task 21324 | eval time = 27989.85 ms / 863 tokens ( 32.47 ms per token, 30.80 tokens per second) 13.12.639.826 I slot print_timing: id 0 | task 21324 | total time = 28570.08 ms / 1313 tokens 13.12.639.826 I slot print_timing: id 0 | task 21324 | graphs reused = 21222 13.12.639.827 I slot print_timing: id 0 | task 21324 | graph reallocs = 0 / 0 (same size) / (changed size) 13.12.639.915 I slot release: id 0 | task 21324 | stop processing: n_tokens = 2005, truncated = 0 13.12.668.435 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.533 13.12.668.464 I slot launch_slot_: id 0 | task 22194 | processing task, is_child = 0 13.13.312.384 I slot print_timing: id 2 | task 21735 | n_gen = 457, tg = 29.87 t/s, tg_3s = 27.55 t/s 13.13.545.828 I slot print_timing: id 2 | task 21735 | prompt eval time = 619.31 ms / 462 tokens ( 1.34 ms per token, 745.99 tokens per second) 13.13.545.833 I slot print_timing: id 2 | task 21735 | eval time = 15497.87 ms / 464 tokens ( 33.47 ms per token, 29.88 tokens per second) 13.13.545.834 I slot print_timing: id 2 | task 21735 | total time = 16117.18 ms / 926 tokens 13.13.545.834 I slot print_timing: id 2 | task 21735 | graphs reused = 21228 13.13.545.835 I slot print_timing: id 2 | task 21735 | graph reallocs = 0 / 0 (same size) / (changed size) 13.13.545.949 I slot release: id 2 | task 21735 | stop processing: n_tokens = 1620, truncated = 0 13.13.581.597 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.659 13.13.581.635 I slot launch_slot_: id 2 | task 22205 | processing task, is_child = 0 13.14.621.269 I slot print_timing: id 3 | task 22054 | n_gen = 164, tg = 27.01 t/s, tg_3s = 20.50 t/s 13.14.980.439 I slot print_timing: id 1 | task 21966 | n_gen = 263, tg = 27.86 t/s, tg_3s = 20.49 t/s 13.16.888.078 I slot print_timing: id 0 | task 22194 | n_gen = 100, tg = 28.08 t/s, tg_3s = 28.36 t/s 13.17.219.669 I slot print_timing: id 2 | task 22205 | n_gen = 102, tg = 33.41 t/s, tg_3s = 33.74 t/s 13.17.643.465 I slot print_timing: id 3 | task 22054 | n_gen = 265, tg = 29.15 t/s, tg_3s = 33.42 t/s 13.18.009.028 I slot print_timing: id 1 | task 21966 | n_gen = 364, tg = 29.20 t/s, tg_3s = 33.35 t/s 13.19.899.208 I slot print_timing: id 0 | task 22194 | n_gen = 200, tg = 30.44 t/s, tg_3s = 33.21 t/s 13.20.231.293 I slot print_timing: id 2 | task 22205 | n_gen = 202, tg = 33.31 t/s, tg_3s = 33.20 t/s 13.20.646.444 I slot print_timing: id 3 | task 22054 | n_gen = 365, tg = 30.18 t/s, tg_3s = 33.30 t/s 13.21.038.029 I slot print_timing: id 1 | task 21966 | n_gen = 465, tg = 30.01 t/s, tg_3s = 33.34 t/s 13.22.918.517 I slot print_timing: id 0 | task 22194 | n_gen = 301, tg = 31.39 t/s, tg_3s = 33.45 t/s 13.23.246.277 I slot print_timing: id 2 | task 22205 | n_gen = 303, tg = 33.37 t/s, tg_3s = 33.50 t/s 13.23.664.725 I slot print_timing: id 3 | task 22054 | n_gen = 466, tg = 30.84 t/s, tg_3s = 33.46 t/s 13.24.056.975 I slot print_timing: id 1 | task 21966 | n_gen = 566, tg = 30.57 t/s, tg_3s = 33.46 t/s 13.25.933.848 I slot print_timing: id 0 | task 22194 | n_gen = 401, tg = 31.82 t/s, tg_3s = 33.16 t/s 13.26.270.500 I slot print_timing: id 2 | task 22205 | n_gen = 403, tg = 33.30 t/s, tg_3s = 33.07 t/s 13.26.691.970 I slot print_timing: id 3 | task 22054 | n_gen = 566, tg = 31.21 t/s, tg_3s = 33.03 t/s 13.27.083.807 I slot print_timing: id 1 | task 21966 | n_gen = 666, tg = 30.92 t/s, tg_3s = 33.04 t/s 13.28.935.544 I slot print_timing: id 0 | task 22194 | n_gen = 500, tg = 32.04 t/s, tg_3s = 32.98 t/s 13.29.294.830 I slot print_timing: id 2 | task 22205 | n_gen = 503, tg = 33.25 t/s, tg_3s = 33.07 t/s 13.29.716.208 I slot print_timing: id 3 | task 22054 | n_gen = 666, tg = 31.47 t/s, tg_3s = 33.07 t/s 13.30.084.229 I slot print_timing: id 1 | task 21966 | n_gen = 765, tg = 31.17 t/s, tg_3s = 33.00 t/s 13.31.958.966 I slot print_timing: id 0 | task 22194 | n_gen = 600, tg = 32.21 t/s, tg_3s = 33.08 t/s 13.32.323.153 I slot print_timing: id 2 | task 22205 | n_gen = 603, tg = 33.21 t/s, tg_3s = 33.02 t/s 13.32.722.833 I slot print_timing: id 3 | task 22054 | n_gen = 765, tg = 31.65 t/s, tg_3s = 32.93 t/s 13.33.112.476 I slot print_timing: id 1 | task 21966 | n_gen = 865, tg = 31.38 t/s, tg_3s = 33.02 t/s 13.34.959.325 I slot print_timing: id 0 | task 22194 | n_gen = 699, tg = 32.32 t/s, tg_3s = 33.00 t/s 13.35.323.354 I slot print_timing: id 2 | task 22205 | n_gen = 702, tg = 33.18 t/s, tg_3s = 33.00 t/s 13.35.744.563 I slot print_timing: id 3 | task 22054 | n_gen = 865, tg = 31.81 t/s, tg_3s = 33.09 t/s 13.36.137.793 I slot print_timing: id 1 | task 21966 | n_gen = 965, tg = 31.54 t/s, tg_3s = 33.05 t/s 13.37.912.126 I slot print_timing: id 1 | task 21966 | prompt eval time = 633.46 ms / 483 tokens ( 1.31 ms per token, 762.49 tokens per second) 13.37.912.136 I slot print_timing: id 1 | task 21966 | eval time = 32335.49 ms / 1024 tokens ( 31.61 ms per token, 31.64 tokens per second) 13.37.912.137 I slot print_timing: id 1 | task 21966 | total time = 32968.95 ms / 1507 tokens 13.37.912.137 I slot print_timing: id 1 | task 21966 | graphs reused = 22011 13.37.912.138 I slot print_timing: id 1 | task 21966 | graph reallocs = 0 / 0 (same size) / (changed size) 13.37.912.220 I slot release: id 1 | task 21966 | stop processing: n_tokens = 2188, truncated = 0 13.37.947.742 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.488 13.37.953.776 I slot launch_slot_: id 1 | task 22996 | processing task, is_child = 0 13.38.553.333 I slot print_timing: id 0 | task 22194 | n_gen = 799, tg = 31.68 t/s, tg_3s = 27.82 t/s 13.38.553.621 I slot print_timing: id 2 | task 22205 | n_gen = 790, tg = 32.39 t/s, tg_3s = 27.24 t/s 13.38.767.258 I slot print_timing: id 3 | task 22054 | n_gen = 945, tg = 31.28 t/s, tg_3s = 26.47 t/s 13.41.153.216 I slot print_timing: id 3 | task 22054 | prompt eval time = 415.07 ms / 256 tokens ( 1.62 ms per token, 616.76 tokens per second) 13.41.153.220 I slot print_timing: id 3 | task 22054 | eval time = 32566.81 ms / 1024 tokens ( 31.83 ms per token, 31.41 tokens per second) 13.41.153.221 I slot print_timing: id 3 | task 22054 | total time = 32981.88 ms / 1280 tokens 13.41.153.222 I slot print_timing: id 3 | task 22054 | graphs reused = 22094 13.41.153.222 I slot print_timing: id 3 | task 22054 | graph reallocs = 0 / 0 (same size) / (changed size) 13.41.153.312 I slot release: id 3 | task 22054 | stop processing: n_tokens = 2157, truncated = 0 13.41.179.778 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.495 13.41.181.793 I slot launch_slot_: id 3 | task 23084 | processing task, is_child = 0 13.41.564.163 I slot print_timing: id 0 | task 22194 | n_gen = 886, tg = 31.38 t/s, tg_3s = 28.90 t/s 13.41.564.777 I slot print_timing: id 2 | task 22205 | n_gen = 877, tg = 32.01 t/s, tg_3s = 28.89 t/s 13.41.979.612 I slot print_timing: id 1 | task 22996 | n_gen = 100, tg = 29.41 t/s, tg_3s = 29.71 t/s 13.44.587.593 I slot print_timing: id 0 | task 22194 | n_gen = 985, tg = 31.51 t/s, tg_3s = 32.74 t/s 13.44.588.581 I slot print_timing: id 2 | task 22205 | n_gen = 976, tg = 32.08 t/s, tg_3s = 32.74 t/s 13.44.619.304 I slot print_timing: id 3 | task 23084 | n_gen = 100, tg = 32.97 t/s, tg_3s = 33.30 t/s 13.44.983.762 I slot print_timing: id 1 | task 22996 | n_gen = 199, tg = 31.08 t/s, tg_3s = 32.95 t/s 13.45.773.953 I slot print_timing: id 0 | task 22194 | prompt eval time = 693.65 ms / 521 tokens ( 1.33 ms per token, 751.10 tokens per second) 13.45.773.958 I slot print_timing: id 0 | task 22194 | eval time = 32411.83 ms / 1024 tokens ( 31.68 ms per token, 31.56 tokens per second) 13.45.773.959 I slot print_timing: id 0 | task 22194 | total time = 33105.48 ms / 1545 tokens 13.45.773.960 I slot print_timing: id 0 | task 22194 | graphs reused = 22230 13.45.773.960 I slot print_timing: id 0 | task 22194 | graph reallocs = 0 / 0 (same size) / (changed size) 13.45.774.051 I slot release: id 0 | task 22194 | stop processing: n_tokens = 2237, truncated = 0 13.45.801.607 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 13.45.807.463 I slot launch_slot_: id 0 | task 23225 | processing task, is_child = 0 13.46.600.698 I slot print_timing: id 2 | task 22205 | prompt eval time = 615.32 ms / 456 tokens ( 1.35 ms per token, 741.08 tokens per second) 13.46.600.707 I slot print_timing: id 2 | task 22205 | eval time = 32403.73 ms / 1024 tokens ( 31.68 ms per token, 31.57 tokens per second) 13.46.600.710 I slot print_timing: id 2 | task 22205 | total time = 33019.04 ms / 1480 tokens 13.46.600.711 I slot print_timing: id 2 | task 22205 | graphs reused = 22236 13.46.600.712 I slot print_timing: id 2 | task 22205 | graph reallocs = 0 / 0 (same size) / (changed size) 13.46.600.850 I slot release: id 2 | task 22205 | stop processing: n_tokens = 2174, truncated = 0 13.46.637.815 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.491 13.46.645.168 I slot launch_slot_: id 2 | task 23235 | processing task, is_child = 0 13.47.620.780 I slot print_timing: id 3 | task 23084 | n_gen = 162, tg = 26.81 t/s, tg_3s = 20.66 t/s 13.48.013.374 I slot print_timing: id 1 | task 22996 | n_gen = 262, tg = 27.77 t/s, tg_3s = 20.79 t/s 13.49.956.816 I slot print_timing: id 0 | task 23225 | n_gen = 100, tg = 27.98 t/s, tg_3s = 28.26 t/s 13.50.263.322 I slot print_timing: id 2 | task 23235 | n_gen = 101, tg = 33.31 t/s, tg_3s = 33.64 t/s 13.50.627.539 I slot print_timing: id 3 | task 23084 | n_gen = 262, tg = 28.96 t/s, tg_3s = 33.26 t/s 13.51.019.241 I slot print_timing: id 1 | task 22996 | n_gen = 362, tg = 29.10 t/s, tg_3s = 33.27 t/s 13.52.983.293 I slot print_timing: id 0 | task 23225 | n_gen = 201, tg = 30.46 t/s, tg_3s = 33.37 t/s 13.53.283.593 I slot print_timing: id 2 | task 23235 | n_gen = 202, tg = 33.38 t/s, tg_3s = 33.44 t/s 13.53.283.976 I slot print_timing: id 3 | task 23084 | prompt eval time = 434.73 ms / 274 tokens ( 1.59 ms per token, 630.27 tokens per second) 13.53.283.978 I slot print_timing: id 3 | task 23084 | eval time = 11667.44 ms / 351 tokens ( 33.34 ms per token, 30.00 tokens per second) 13.53.283.979 I slot print_timing: id 3 | task 23084 | total time = 12102.17 ms / 625 tokens 13.53.283.980 I slot print_timing: id 3 | task 23084 | graphs reused = 22435 13.53.283.980 I slot print_timing: id 3 | task 23084 | graph reallocs = 0 / 0 (same size) / (changed size) 13.53.284.062 I slot release: id 3 | task 23084 | stop processing: n_tokens = 1502, truncated = 0 13.53.310.362 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.711 13.53.310.397 I slot launch_slot_: id 3 | task 23440 | processing task, is_child = 0 13.54.038.205 I slot print_timing: id 1 | task 22996 | n_gen = 450, tg = 29.11 t/s, tg_3s = 29.15 t/s 13.56.010.725 I slot print_timing: id 0 | task 23225 | n_gen = 289, tg = 30.02 t/s, tg_3s = 29.07 t/s 13.56.307.493 I slot print_timing: id 2 | task 23235 | n_gen = 290, tg = 31.95 t/s, tg_3s = 29.10 t/s 13.56.781.937 I slot print_timing: id 3 | task 23440 | n_gen = 102, tg = 33.48 t/s, tg_3s = 33.81 t/s 13.57.046.962 I slot print_timing: id 1 | task 22996 | n_gen = 551, tg = 29.84 t/s, tg_3s = 33.57 t/s 13.59.026.831 I slot print_timing: id 0 | task 23225 | n_gen = 391, tg = 30.93 t/s, tg_3s = 33.82 t/s 13.59.325.587 I slot print_timing: id 2 | task 23235 | n_gen = 392, tg = 32.41 t/s, tg_3s = 33.80 t/s 13.59.806.697 I slot print_timing: id 3 | task 23440 | n_gen = 204, tg = 33.60 t/s, tg_3s = 33.72 t/s 14.00.076.777 I slot print_timing: id 1 | task 22996 | n_gen = 653, tg = 30.38 t/s, tg_3s = 33.67 t/s 14.02.038.145 I slot print_timing: id 0 | task 23225 | n_gen = 491, tg = 31.37 t/s, tg_3s = 33.21 t/s 14.02.341.360 I slot print_timing: id 2 | task 23235 | n_gen = 492, tg = 32.56 t/s, tg_3s = 33.16 t/s 14.02.828.118 I slot print_timing: id 3 | task 23440 | n_gen = 304, tg = 33.43 t/s, tg_3s = 33.10 t/s 14.03.102.175 I slot print_timing: id 1 | task 22996 | n_gen = 753, tg = 30.71 t/s, tg_3s = 33.05 t/s 14.05.055.294 I slot print_timing: id 0 | task 23225 | n_gen = 591, tg = 31.66 t/s, tg_3s = 33.14 t/s 14.05.353.119 I slot print_timing: id 2 | task 23235 | n_gen = 592, tg = 32.67 t/s, tg_3s = 33.20 t/s 14.05.854.531 I slot print_timing: id 3 | task 23440 | n_gen = 405, tg = 33.42 t/s, tg_3s = 33.37 t/s 14.06.123.756 I slot print_timing: id 1 | task 22996 | n_gen = 854, tg = 31.01 t/s, tg_3s = 33.43 t/s 14.08.075.775 I slot print_timing: id 0 | task 23225 | n_gen = 692, tg = 31.91 t/s, tg_3s = 33.44 t/s 14.08.374.367 I slot print_timing: id 2 | task 23235 | n_gen = 693, tg = 32.78 t/s, tg_3s = 33.43 t/s 14.08.857.043 I slot print_timing: id 3 | task 23440 | n_gen = 505, tg = 33.39 t/s, tg_3s = 33.31 t/s 14.09.152.913 I slot print_timing: id 1 | task 22996 | n_gen = 955, tg = 31.24 t/s, tg_3s = 33.34 t/s 14.11.081.431 I slot print_timing: id 0 | task 23225 | n_gen = 792, tg = 32.07 t/s, tg_3s = 33.27 t/s 14.11.232.390 I slot print_timing: id 1 | task 22996 | prompt eval time = 659.39 ms / 510 tokens ( 1.29 ms per token, 773.44 tokens per second) 14.11.232.396 I slot print_timing: id 1 | task 22996 | eval time = 32619.21 ms / 1024 tokens ( 31.89 ms per token, 31.36 tokens per second) 14.11.232.397 I slot print_timing: id 1 | task 22996 | total time = 33278.60 ms / 1534 tokens 14.11.232.398 I slot print_timing: id 1 | task 22996 | graphs reused = 23015 14.11.232.399 I slot print_timing: id 1 | task 22996 | graph reallocs = 0 / 0 (same size) / (changed size) 14.11.232.495 I slot release: id 1 | task 22996 | stop processing: n_tokens = 2215, truncated = 0 14.11.267.590 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.482 14.11.276.362 I slot launch_slot_: id 1 | task 24027 | processing task, is_child = 0 14.11.863.435 I slot print_timing: id 2 | task 23235 | n_gen = 790, tg = 32.07 t/s, tg_3s = 27.80 t/s 14.11.863.777 I slot print_timing: id 3 | task 23440 | n_gen = 586, tg = 32.32 t/s, tg_3s = 26.94 t/s 14.14.082.093 I slot print_timing: id 0 | task 23225 | n_gen = 871, tg = 31.45 t/s, tg_3s = 26.33 t/s 14.14.870.477 I slot print_timing: id 2 | task 23235 | n_gen = 888, tg = 32.13 t/s, tg_3s = 32.59 t/s 14.14.870.992 I slot print_timing: id 3 | task 23440 | n_gen = 684, tg = 32.36 t/s, tg_3s = 32.59 t/s 14.14.931.373 I slot print_timing: id 1 | task 24027 | n_gen = 100, tg = 32.90 t/s, tg_3s = 33.24 t/s 14.15.084.355 I slot print_timing: id 0 | task 23225 | prompt eval time = 610.83 ms / 484 tokens ( 1.26 ms per token, 792.36 tokens per second) 14.15.084.358 I slot print_timing: id 0 | task 23225 | eval time = 28666.05 ms / 904 tokens ( 31.75 ms per token, 31.50 tokens per second) 14.15.084.359 I slot print_timing: id 0 | task 23225 | total time = 29276.88 ms / 1388 tokens 14.15.084.359 I slot print_timing: id 0 | task 23225 | graphs reused = 23117 14.15.084.360 I slot print_timing: id 0 | task 23225 | graph reallocs = 0 / 0 (same size) / (changed size) 14.15.084.454 I slot release: id 0 | task 23225 | stop processing: n_tokens = 2085, truncated = 0 14.15.112.686 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.512 14.15.112.714 I slot launch_slot_: id 0 | task 24135 | processing task, is_child = 0 14.17.898.957 I slot print_timing: id 2 | task 23235 | n_gen = 971, tg = 31.66 t/s, tg_3s = 27.41 t/s 14.17.899.473 I slot print_timing: id 3 | task 23440 | n_gen = 767, tg = 31.74 t/s, tg_3s = 27.41 t/s 14.17.958.077 I slot print_timing: id 1 | task 24027 | n_gen = 183, tg = 30.15 t/s, tg_3s = 27.42 t/s 14.18.259.189 I slot print_timing: id 3 | task 23440 | prompt eval time = 454.46 ms / 296 tokens ( 1.54 ms per token, 651.33 tokens per second) 14.18.259.196 I slot print_timing: id 3 | task 23440 | eval time = 24494.32 ms / 779 tokens ( 31.48 ms per token, 31.76 tokens per second) 14.18.259.196 I slot print_timing: id 3 | task 23440 | total time = 24948.78 ms / 1075 tokens 14.18.259.197 I slot print_timing: id 3 | task 23440 | graphs reused = 23202 14.18.259.198 I slot print_timing: id 3 | task 23440 | graph reallocs = 0 / 0 (same size) / (changed size) 14.18.259.307 I slot release: id 3 | task 23440 | stop processing: n_tokens = 1952, truncated = 0 14.18.286.403 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.547 14.18.286.430 I slot launch_slot_: id 3 | task 24224 | processing task, is_child = 0 14.19.054.153 I slot print_timing: id 0 | task 24135 | n_gen = 100, tg = 29.40 t/s, tg_3s = 29.70 t/s 14.19.855.779 I slot print_timing: id 2 | task 23235 | prompt eval time = 616.12 ms / 457 tokens ( 1.35 ms per token, 741.74 tokens per second) 14.19.855.783 I slot print_timing: id 2 | task 23235 | eval time = 32594.48 ms / 1024 tokens ( 31.86 ms per token, 31.39 tokens per second) 14.19.855.783 I slot print_timing: id 2 | task 23235 | total time = 33210.60 ms / 1481 tokens 14.19.855.784 I slot print_timing: id 2 | task 23235 | graphs reused = 23239 14.19.855.785 I slot print_timing: id 2 | task 23235 | graph reallocs = 0 / 0 (same size) / (changed size) 14.19.855.881 I slot release: id 2 | task 23235 | stop processing: n_tokens = 2175, truncated = 0 14.19.889.241 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.491 14.19.893.887 I slot launch_slot_: id 2 | task 24266 | processing task, is_child = 0 14.20.963.146 I slot print_timing: id 1 | task 24027 | n_gen = 252, tg = 27.76 t/s, tg_3s = 22.96 t/s 14.22.055.829 I slot print_timing: id 0 | task 24135 | n_gen = 182, tg = 28.42 t/s, tg_3s = 27.32 t/s 14.22.237.885 I slot print_timing: id 3 | task 24224 | n_gen = 100, tg = 28.17 t/s, tg_3s = 28.46 t/s 14.23.521.012 I slot print_timing: id 2 | task 24266 | n_gen = 102, tg = 33.62 t/s, tg_3s = 33.95 t/s 14.23.971.321 I slot print_timing: id 1 | task 24027 | n_gen = 353, tg = 29.21 t/s, tg_3s = 33.58 t/s 14.25.067.385 I slot print_timing: id 0 | task 24135 | n_gen = 283, tg = 30.06 t/s, tg_3s = 33.54 t/s 14.25.249.271 I slot print_timing: id 3 | task 24224 | n_gen = 201, tg = 30.65 t/s, tg_3s = 33.54 t/s 14.26.535.259 I slot print_timing: id 2 | task 24266 | n_gen = 203, tg = 33.56 t/s, tg_3s = 33.51 t/s 14.26.983.829 I slot print_timing: id 1 | task 24027 | n_gen = 454, tg = 30.08 t/s, tg_3s = 33.53 t/s 14.28.095.091 I slot print_timing: id 0 | task 24135 | n_gen = 384, tg = 30.87 t/s, tg_3s = 33.36 t/s 14.28.276.805 I slot print_timing: id 3 | task 24224 | n_gen = 302, tg = 31.51 t/s, tg_3s = 33.36 t/s 14.29.551.965 I slot print_timing: id 2 | task 24266 | n_gen = 304, tg = 33.53 t/s, tg_3s = 33.48 t/s 14.29.994.697 I slot print_timing: id 1 | task 24027 | n_gen = 555, tg = 30.65 t/s, tg_3s = 33.55 t/s 14.31.111.095 I slot print_timing: id 0 | task 24135 | n_gen = 485, tg = 31.38 t/s, tg_3s = 33.49 t/s 14.31.292.310 I slot print_timing: id 3 | task 24224 | n_gen = 403, tg = 31.98 t/s, tg_3s = 33.49 t/s 14.32.554.338 I slot print_timing: id 2 | task 24266 | n_gen = 404, tg = 33.48 t/s, tg_3s = 33.31 t/s 14.33.004.690 I slot print_timing: id 1 | task 24027 | n_gen = 655, tg = 31.02 t/s, tg_3s = 33.22 t/s 14.34.120.375 I slot print_timing: id 0 | task 24135 | n_gen = 585, tg = 31.68 t/s, tg_3s = 33.23 t/s 14.34.301.760 I slot print_timing: id 3 | task 24224 | n_gen = 503, tg = 32.22 t/s, tg_3s = 33.23 t/s 14.35.558.034 I slot print_timing: id 2 | task 24266 | n_gen = 504, tg = 33.44 t/s, tg_3s = 33.29 t/s 14.36.010.958 I slot print_timing: id 1 | task 24027 | n_gen = 755, tg = 31.30 t/s, tg_3s = 33.26 t/s 14.36.186.929 I slot print_timing: id 1 | task 24027 | prompt eval time = 646.20 ms / 489 tokens ( 1.32 ms per token, 756.73 tokens per second) 14.36.186.934 I slot print_timing: id 1 | task 24027 | eval time = 24264.35 ms / 761 tokens ( 31.93 ms per token, 31.32 tokens per second) 14.36.186.935 I slot print_timing: id 1 | task 24027 | total time = 24910.56 ms / 1250 tokens 14.36.186.936 I slot print_timing: id 1 | task 24027 | graphs reused = 23760 14.36.186.936 I slot print_timing: id 1 | task 24027 | graph reallocs = 0 / 0 (same size) / (changed size) 14.36.187.032 I slot release: id 1 | task 24027 | stop processing: n_tokens = 1919, truncated = 0 14.36.221.995 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.557 14.36.222.031 I slot launch_slot_: id 1 | task 24794 | processing task, is_child = 0 14.37.126.731 I slot print_timing: id 0 | task 24135 | n_gen = 666, tg = 31.02 t/s, tg_3s = 26.94 t/s 14.37.309.952 I slot print_timing: id 3 | task 24224 | n_gen = 584, tg = 31.37 t/s, tg_3s = 26.93 t/s 14.38.585.920 I slot print_timing: id 2 | task 24266 | n_gen = 585, tg = 32.32 t/s, tg_3s = 26.75 t/s 14.39.872.077 I slot print_timing: id 1 | task 24794 | n_gen = 101, tg = 33.14 t/s, tg_3s = 33.47 t/s 14.40.139.574 I slot print_timing: id 0 | task 24135 | n_gen = 766, tg = 31.28 t/s, tg_3s = 33.19 t/s 14.40.317.416 I slot print_timing: id 3 | task 24224 | n_gen = 684, tg = 31.63 t/s, tg_3s = 33.25 t/s 14.40.760.248 I slot print_timing: id 2 | task 24266 | prompt eval time = 622.51 ms / 473 tokens ( 1.32 ms per token, 759.82 tokens per second) 14.40.760.255 I slot print_timing: id 2 | task 24266 | eval time = 20243.84 ms / 658 tokens ( 30.81 ms per token, 32.45 tokens per second) 14.40.760.256 I slot print_timing: id 2 | task 24266 | total time = 20866.35 ms / 1131 tokens 14.40.760.257 I slot print_timing: id 2 | task 24266 | graphs reused = 23889 14.40.760.258 I slot print_timing: id 2 | task 24266 | graph reallocs = 0 / 0 (same size) / (changed size) 14.40.760.354 I slot release: id 2 | task 24266 | stop processing: n_tokens = 1800, truncated = 0 14.40.794.804 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.593 14.40.794.838 I slot launch_slot_: id 2 | task 24928 | processing task, is_child = 0 14.42.878.338 I slot print_timing: id 1 | task 24794 | n_gen = 178, tg = 29.38 t/s, tg_3s = 25.61 t/s 14.43.141.530 I slot print_timing: id 0 | task 24135 | n_gen = 843, tg = 30.67 t/s, tg_3s = 25.65 t/s 14.43.320.798 I slot print_timing: id 3 | task 24224 | n_gen = 761, tg = 30.90 t/s, tg_3s = 25.64 t/s 14.44.578.192 I slot print_timing: id 0 | task 24135 | prompt eval time = 574.01 ms / 441 tokens ( 1.30 ms per token, 768.28 tokens per second) 14.44.578.198 I slot print_timing: id 0 | task 24135 | eval time = 28891.46 ms / 891 tokens ( 32.46 ms per token, 30.80 tokens per second) 14.44.578.199 I slot print_timing: id 0 | task 24135 | total time = 29465.47 ms / 1332 tokens 14.44.578.200 I slot print_timing: id 0 | task 24135 | graphs reused = 23988 14.44.578.200 I slot print_timing: id 0 | task 24135 | graph reallocs = 0 / 0 (same size) / (changed size) 14.44.578.287 I slot release: id 0 | task 24135 | stop processing: n_tokens = 2029, truncated = 0 14.44.606.236 I slot print_timing: id 2 | task 24928 | n_gen = 102, tg = 33.50 t/s, tg_3s = 33.83 t/s 14.44.606.719 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.526 14.44.606.752 I slot launch_slot_: id 0 | task 25033 | processing task, is_child = 0 14.45.890.719 I slot print_timing: id 1 | task 24794 | n_gen = 261, tg = 28.77 t/s, tg_3s = 27.55 t/s 14.46.342.594 I slot print_timing: id 3 | task 24224 | n_gen = 844, tg = 30.52 t/s, tg_3s = 27.47 t/s 14.47.635.128 I slot print_timing: id 2 | task 24928 | n_gen = 185, tg = 30.44 t/s, tg_3s = 27.40 t/s 14.48.213.736 I slot print_timing: id 0 | task 25033 | n_gen = 101, tg = 33.19 t/s, tg_3s = 33.52 t/s 14.48.910.084 I slot print_timing: id 1 | task 24794 | n_gen = 361, tg = 29.86 t/s, tg_3s = 33.12 t/s 14.49.364.095 I slot print_timing: id 3 | task 24224 | n_gen = 944, tg = 30.78 t/s, tg_3s = 33.10 t/s 14.50.657.415 I slot print_timing: id 2 | task 24928 | n_gen = 285, tg = 31.33 t/s, tg_3s = 33.09 t/s 14.51.228.571 I slot print_timing: id 0 | task 25033 | n_gen = 201, tg = 33.18 t/s, tg_3s = 33.17 t/s 14.51.774.541 I slot print_timing: id 3 | task 24224 | prompt eval time = 437.17 ms / 276 tokens ( 1.58 ms per token, 631.33 tokens per second) 14.51.774.547 I slot print_timing: id 3 | task 24224 | eval time = 33050.93 ms / 1024 tokens ( 32.31 ms per token, 30.95 tokens per second) 14.51.774.548 I slot print_timing: id 3 | task 24224 | total time = 33488.10 ms / 1300 tokens 14.51.774.549 I slot print_timing: id 3 | task 24224 | graphs reused = 24205 14.51.774.550 I slot print_timing: id 3 | task 24224 | graph reallocs = 0 / 0 (same size) / (changed size) 14.51.774.639 I slot release: id 3 | task 24224 | stop processing: n_tokens = 2177, truncated = 0 14.51.801.534 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.491 14.51.807.348 I slot launch_slot_: id 3 | task 25255 | processing task, is_child = 0 14.52.200.399 I slot print_timing: id 1 | task 24794 | n_gen = 458, tg = 29.78 t/s, tg_3s = 29.48 t/s 14.53.663.105 I slot print_timing: id 2 | task 24928 | n_gen = 372, tg = 30.73 t/s, tg_3s = 28.95 t/s 14.54.236.136 I slot print_timing: id 0 | task 25033 | n_gen = 288, tg = 31.76 t/s, tg_3s = 28.93 t/s 14.55.226.393 I slot print_timing: id 1 | task 24794 | n_gen = 558, tg = 30.32 t/s, tg_3s = 33.05 t/s 14.55.258.386 I slot print_timing: id 3 | task 25255 | n_gen = 101, tg = 33.27 t/s, tg_3s = 33.61 t/s 14.56.687.573 I slot print_timing: id 2 | task 24928 | n_gen = 473, tg = 31.27 t/s, tg_3s = 33.39 t/s 14.57.254.908 I slot print_timing: id 0 | task 25033 | n_gen = 389, tg = 32.19 t/s, tg_3s = 33.46 t/s 14.58.253.111 I slot print_timing: id 1 | task 24794 | n_gen = 659, tg = 30.75 t/s, tg_3s = 33.37 t/s 14.58.283.497 I slot print_timing: id 3 | task 25255 | n_gen = 202, tg = 33.33 t/s, tg_3s = 33.39 t/s 14.59.691.855 I slot print_timing: id 2 | task 24928 | n_gen = 573, tg = 31.60 t/s, tg_3s = 33.29 t/s 15.00.258.673 I slot print_timing: id 0 | task 25033 | n_gen = 489, tg = 32.41 t/s, tg_3s = 33.29 t/s 15.01.253.187 I slot print_timing: id 1 | task 24794 | n_gen = 759, tg = 31.07 t/s, tg_3s = 33.33 t/s 15.01.284.033 I slot print_timing: id 3 | task 25255 | n_gen = 302, tg = 33.33 t/s, tg_3s = 33.33 t/s 15.02.705.811 I slot print_timing: id 2 | task 24928 | n_gen = 673, tg = 31.83 t/s, tg_3s = 33.18 t/s 15.03.277.377 I slot print_timing: id 0 | task 25033 | n_gen = 589, tg = 32.53 t/s, tg_3s = 33.13 t/s 15.04.273.641 I slot print_timing: id 1 | task 24794 | n_gen = 859, tg = 31.29 t/s, tg_3s = 33.11 t/s 15.04.303.436 I slot print_timing: id 3 | task 25255 | n_gen = 402, tg = 33.28 t/s, tg_3s = 33.12 t/s 15.05.725.647 I slot print_timing: id 2 | task 24928 | n_gen = 774, tg = 32.03 t/s, tg_3s = 33.45 t/s 15.05.997.006 I slot print_timing: id 1 | task 24794 | prompt eval time = 632.67 ms / 480 tokens ( 1.32 ms per token, 758.69 tokens per second) 15.05.997.013 I slot print_timing: id 1 | task 24794 | eval time = 29142.30 ms / 917 tokens ( 31.81 ms per token, 31.43 tokens per second) 15.05.997.014 I slot print_timing: id 1 | task 24794 | total time = 29774.97 ms / 1397 tokens 15.05.997.014 I slot print_timing: id 1 | task 24794 | graphs reused = 24660 15.05.997.015 I slot print_timing: id 1 | task 24794 | graph reallocs = 0 / 0 (same size) / (changed size) 15.05.997.104 I slot release: id 1 | task 24794 | stop processing: n_tokens = 2066, truncated = 0 15.06.032.140 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.517 15.06.032.171 I slot launch_slot_: id 1 | task 25717 | processing task, is_child = 0 15.06.596.971 I slot print_timing: id 0 | task 25033 | n_gen = 682, tg = 31.83 t/s, tg_3s = 28.02 t/s 15.07.327.948 I slot print_timing: id 3 | task 25255 | n_gen = 484, tg = 32.04 t/s, tg_3s = 27.11 t/s 15.07.688.976 I slot print_timing: id 0 | task 25033 | prompt eval time = 594.20 ms / 457 tokens ( 1.30 ms per token, 769.10 tokens per second) 15.07.688.982 I slot print_timing: id 0 | task 25033 | eval time = 22488.01 ms / 717 tokens ( 31.41 ms per token, 31.84 tokens per second) 15.07.688.983 I slot print_timing: id 0 | task 25033 | total time = 23082.22 ms / 1174 tokens 15.07.688.984 I slot print_timing: id 0 | task 25033 | graphs reused = 24693 15.07.688.985 I slot print_timing: id 0 | task 25033 | graph reallocs = 0 / 0 (same size) / (changed size) 15.07.689.072 I slot release: id 0 | task 25033 | stop processing: n_tokens = 1871, truncated = 0 15.07.717.503 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.571 15.07.717.540 I slot launch_slot_: id 0 | task 25755 | processing task, is_child = 0 15.08.736.467 I slot print_timing: id 2 | task 24928 | n_gen = 836, tg = 30.76 t/s, tg_3s = 20.59 t/s 15.10.214.920 I slot print_timing: id 1 | task 25717 | n_gen = 100, tg = 27.82 t/s, tg_3s = 28.10 t/s 15.10.333.581 I slot print_timing: id 3 | task 25255 | n_gen = 565, tg = 31.19 t/s, tg_3s = 26.95 t/s 15.11.358.976 I slot print_timing: id 0 | task 25755 | n_gen = 101, tg = 33.14 t/s, tg_3s = 33.48 t/s 15.11.755.862 I slot print_timing: id 2 | task 24928 | n_gen = 936, tg = 31.00 t/s, tg_3s = 33.12 t/s 15.13.225.747 I slot print_timing: id 1 | task 25717 | n_gen = 200, tg = 30.29 t/s, tg_3s = 33.21 t/s 15.13.345.170 I slot print_timing: id 3 | task 25255 | n_gen = 665, tg = 31.48 t/s, tg_3s = 33.21 t/s 15.13.375.601 I slot print_timing: id 3 | task 25255 | prompt eval time = 445.54 ms / 290 tokens ( 1.54 ms per token, 650.90 tokens per second) 15.13.375.609 I slot print_timing: id 3 | task 25255 | eval time = 21122.71 ms / 666 tokens ( 31.76 ms per token, 31.48 tokens per second) 15.13.375.609 I slot print_timing: id 3 | task 25255 | total time = 21568.24 ms / 956 tokens 15.13.375.610 I slot print_timing: id 3 | task 25255 | graphs reused = 24859 15.13.375.611 I slot print_timing: id 3 | task 25255 | graph reallocs = 0 / 0 (same size) / (changed size) 15.13.375.731 I slot release: id 3 | task 25255 | stop processing: n_tokens = 1833, truncated = 0 15.13.402.438 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.583 15.13.402.477 I slot launch_slot_: id 3 | task 25926 | processing task, is_child = 0 15.14.365.578 I slot print_timing: id 0 | task 25755 | n_gen = 189, tg = 31.21 t/s, tg_3s = 29.27 t/s 15.14.766.043 I slot print_timing: id 2 | task 24928 | prompt eval time = 796.33 ms / 541 tokens ( 1.47 ms per token, 679.36 tokens per second) 15.14.766.047 I slot print_timing: id 2 | task 24928 | eval time = 33174.86 ms / 1024 tokens ( 32.43 ms per token, 30.84 tokens per second) 15.14.766.048 I slot print_timing: id 2 | task 24928 | total time = 33971.20 ms / 1565 tokens 15.14.766.048 I slot print_timing: id 2 | task 24928 | graphs reused = 24889 15.14.766.053 I slot print_timing: id 2 | task 24928 | graph reallocs = 0 / 0 (same size) / (changed size) 15.14.766.151 I slot release: id 2 | task 24928 | stop processing: n_tokens = 2234, truncated = 0 15.16.261.109 I slot print_timing: id 1 | task 25717 | n_gen = 281, tg = 29.15 t/s, tg_3s = 26.69 t/s 15.17.189.132 I slot print_timing: id 3 | task 25926 | n_gen = 100, tg = 29.38 t/s, tg_3s = 29.68 t/s 15.17.366.461 I slot print_timing: id 0 | task 25755 | n_gen = 275, tg = 30.36 t/s, tg_3s = 28.66 t/s 15.19.294.985 I slot print_timing: id 1 | task 25717 | n_gen = 366, tg = 28.88 t/s, tg_3s = 28.02 t/s 15.20.193.678 I slot print_timing: id 3 | task 25926 | n_gen = 184, tg = 28.71 t/s, tg_3s = 27.96 t/s 15.20.372.474 I slot print_timing: id 0 | task 25755 | n_gen = 359, tg = 29.76 t/s, tg_3s = 27.94 t/s 15.22.310.341 I slot print_timing: id 1 | task 25717 | n_gen = 450, tg = 28.68 t/s, tg_3s = 27.86 t/s 15.23.208.822 I slot print_timing: id 3 | task 25926 | n_gen = 268, tg = 28.44 t/s, tg_3s = 27.86 t/s 15.23.388.175 I slot print_timing: id 0 | task 25755 | n_gen = 443, tg = 29.38 t/s, tg_3s = 27.85 t/s 15.25.331.293 I slot print_timing: id 1 | task 25717 | n_gen = 534, tg = 28.54 t/s, tg_3s = 27.81 t/s 15.25.724.232 I slot print_timing: id 3 | task 25926 | prompt eval time = 416.86 ms / 261 tokens ( 1.60 ms per token, 626.11 tokens per second) 15.25.724.240 I slot print_timing: id 3 | task 25926 | eval time = 11904.88 ms / 338 tokens ( 35.33 ms per token, 28.31 tokens per second) 15.25.724.241 I slot print_timing: id 3 | task 25926 | total time = 12321.74 ms / 599 tokens 15.25.724.242 I slot print_timing: id 3 | task 25926 | graphs reused = 24889 15.25.724.243 I slot print_timing: id 3 | task 25926 | graph reallocs = 0 / 0 (same size) / (changed size) 15.25.724.366 I slot release: id 3 | task 25926 | stop processing: n_tokens = 1476, truncated = 0 15.26.269.205 I slot print_timing: id 0 | task 25755 | prompt eval time = 624.26 ms / 489 tokens ( 1.28 ms per token, 783.32 tokens per second) 15.26.269.208 I slot print_timing: id 0 | task 25755 | eval time = 17927.39 ms / 536 tokens ( 33.51 ms per token, 29.84 tokens per second) 15.26.269.210 I slot print_timing: id 0 | task 25755 | total time = 18551.65 ms / 1025 tokens 15.26.269.210 I slot print_timing: id 0 | task 25755 | graphs reused = 24916 15.26.269.211 I slot print_timing: id 0 | task 25755 | graph reallocs = 0 / 0 (same size) / (changed size) 15.26.269.284 I slot release: id 0 | task 25755 | stop processing: n_tokens = 1722, truncated = 0 15.28.334.579 I slot print_timing: id 1 | task 25717 | n_gen = 748, tg = 34.46 t/s, tg_3s = 71.26 t/s 15.30.923.543 I slot print_timing: id 1 | task 25717 | prompt eval time = 623.92 ms / 468 tokens ( 1.33 ms per token, 750.10 tokens per second) 15.30.923.548 I slot print_timing: id 1 | task 25717 | eval time = 24267.45 ms / 967 tokens ( 25.12 ms per token, 39.81 tokens per second) 15.30.923.550 I slot print_timing: id 1 | task 25717 | total time = 24891.37 ms / 1435 tokens 15.30.923.550 I slot print_timing: id 1 | task 25717 | graphs reused = 25307 15.30.923.551 I slot print_timing: id 1 | task 25717 | graph reallocs = 0 / 0 (same size) / (changed size) 15.30.923.616 I slot release: id 1 | task 25717 | stop processing: n_tokens = 2104, truncated = 0 15.30.938.371 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2234, t_last = 347850148120 15.30.943.168 I slot launch_slot_: id 2 | task 26688 | processing task, is_child = 0 15.30.951.803 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 347861106335 15.30.951.914 I slot launch_slot_: id 3 | task 26689 | processing task, is_child = 0 15.30.952.106 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1722, t_last = 347861651253 15.30.952.222 I slot launch_slot_: id 0 | task 26690 | processing task, is_child = 0 15.30.952.333 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2104, t_last = 347866305585 15.30.952.458 I slot launch_slot_: id 1 | task 26691 | processing task, is_child = 0 15.34.304.451 I slot print_timing: id 0 | task 26690 | prompt processing, n_tokens = 760, progress = 0.99, t = 3.35 s / 226.73 tokens per second 15.34.868.453 I slot print_timing: id 1 | task 26691 | prompt processing, n_tokens = 940, progress = 1.00, t = 3.35 s / 280.44 tokens per second 15.34.868.624 I slot print_timing: id 2 | task 26688 | prompt processing, n_tokens = 754, progress = 0.99, t = 3.35 s / 224.96 tokens per second 15.34.868.771 I slot print_timing: id 3 | task 26689 | prompt processing, n_tokens = 942, progress = 1.00, t = 3.35 s / 281.07 tokens per second 15.34.969.032 I slot print_timing: id 0 | task 26690 | prompt eval time = 3988.06 ms / 764 tokens ( 5.22 ms per token, 191.57 tokens per second) 15.34.969.034 I slot print_timing: id 0 | task 26690 | eval time = 28.51 ms / 2 tokens ( 28.51 ms per token, 35.08 tokens per second) 15.34.969.034 I slot print_timing: id 0 | task 26690 | total time = 4016.56 ms / 766 tokens 15.34.969.035 I slot print_timing: id 0 | task 26690 | graphs reused = 25309 15.34.969.035 I slot print_timing: id 0 | task 26690 | graph reallocs = 0 / 0 (same size) / (changed size) 15.34.969.085 I slot release: id 0 | task 26690 | stop processing: n_tokens = 765, truncated = 0 15.34.969.351 I slot print_timing: id 1 | task 26691 | prompt eval time = 3988.22 ms / 944 tokens ( 4.22 ms per token, 236.70 tokens per second) 15.34.969.353 I slot print_timing: id 1 | task 26691 | eval time = 28.52 ms / 2 tokens ( 28.52 ms per token, 35.07 tokens per second) 15.34.969.354 I slot print_timing: id 1 | task 26691 | total time = 4016.74 ms / 946 tokens 15.34.969.354 I slot print_timing: id 1 | task 26691 | graphs reused = 25309 15.34.969.354 I slot print_timing: id 1 | task 26691 | graph reallocs = 0 / 0 (same size) / (changed size) 15.34.969.406 I slot release: id 1 | task 26691 | stop processing: n_tokens = 945, truncated = 0 15.34.969.689 I slot print_timing: id 2 | task 26688 | prompt eval time = 3988.35 ms / 758 tokens ( 5.26 ms per token, 190.05 tokens per second) 15.34.969.697 I slot print_timing: id 2 | task 26688 | eval time = 28.55 ms / 2 tokens ( 28.55 ms per token, 35.03 tokens per second) 15.34.969.697 I slot print_timing: id 2 | task 26688 | total time = 4016.90 ms / 760 tokens 15.34.969.698 I slot print_timing: id 2 | task 26688 | graphs reused = 25309 15.34.969.698 I slot print_timing: id 2 | task 26688 | graph reallocs = 0 / 0 (same size) / (changed size) 15.34.969.733 I slot release: id 2 | task 26688 | stop processing: n_tokens = 759, truncated = 0 15.34.970.032 I slot print_timing: id 3 | task 26689 | prompt eval time = 3988.53 ms / 946 tokens ( 4.22 ms per token, 237.18 tokens per second) 15.34.970.033 I slot print_timing: id 3 | task 26689 | eval time = 28.55 ms / 2 tokens ( 28.55 ms per token, 35.03 tokens per second) 15.34.970.034 I slot print_timing: id 3 | task 26689 | total time = 4017.09 ms / 948 tokens 15.34.970.034 I slot print_timing: id 3 | task 26689 | graphs reused = 25309 15.34.970.035 I slot print_timing: id 3 | task 26689 | graph reallocs = 0 / 0 (same size) / (changed size) 15.34.970.090 I slot release: id 3 | task 26689 | stop processing: n_tokens = 947, truncated = 0 15.34.976.468 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 765, t_last = 347870351054 15.34.978.015 I slot launch_slot_: id 0 | task 26696 | processing task, is_child = 0 15.34.983.056 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 945, t_last = 347870351375 15.34.983.123 I slot launch_slot_: id 1 | task 26697 | processing task, is_child = 0 15.34.983.207 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 759, t_last = 347870351702 15.34.983.262 I slot launch_slot_: id 2 | task 26699 | processing task, is_child = 0 15.34.983.307 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 947, t_last = 347870352060 15.34.983.369 I slot launch_slot_: id 3 | task 26698 | processing task, is_child = 0 15.38.628.382 I slot print_timing: id 0 | task 26696 | prompt eval time = 3616.45 ms / 776 tokens ( 4.66 ms per token, 214.58 tokens per second) 15.38.628.385 I slot print_timing: id 0 | task 26696 | eval time = 28.56 ms / 2 tokens ( 28.56 ms per token, 35.02 tokens per second) 15.38.628.386 I slot print_timing: id 0 | task 26696 | total time = 3645.01 ms / 778 tokens 15.38.628.386 I slot print_timing: id 0 | task 26696 | graphs reused = 25310 15.38.628.387 I slot print_timing: id 0 | task 26696 | graph reallocs = 0 / 0 (same size) / (changed size) 15.38.628.434 I slot release: id 0 | task 26696 | stop processing: n_tokens = 777, truncated = 0 15.38.628.695 I slot print_timing: id 1 | task 26697 | prompt eval time = 3616.70 ms / 772 tokens ( 4.68 ms per token, 213.45 tokens per second) 15.38.628.697 I slot print_timing: id 1 | task 26697 | eval time = 28.57 ms / 2 tokens ( 28.57 ms per token, 35.00 tokens per second) 15.38.628.697 I slot print_timing: id 1 | task 26697 | total time = 3645.27 ms / 774 tokens 15.38.628.698 I slot print_timing: id 1 | task 26697 | graphs reused = 25310 15.38.628.698 I slot print_timing: id 1 | task 26697 | graph reallocs = 0 / 0 (same size) / (changed size) 15.38.628.731 I slot release: id 1 | task 26697 | stop processing: n_tokens = 773, truncated = 0 15.38.629.006 I slot print_timing: id 2 | task 26699 | prompt eval time = 3616.98 ms / 825 tokens ( 4.38 ms per token, 228.09 tokens per second) 15.38.629.009 I slot print_timing: id 2 | task 26699 | eval time = 28.54 ms / 2 tokens ( 28.54 ms per token, 35.04 tokens per second) 15.38.629.009 I slot print_timing: id 2 | task 26699 | total time = 3645.52 ms / 827 tokens 15.38.629.010 I slot print_timing: id 2 | task 26699 | graphs reused = 25310 15.38.629.010 I slot print_timing: id 2 | task 26699 | graph reallocs = 0 / 0 (same size) / (changed size) 15.38.629.047 I slot release: id 2 | task 26699 | stop processing: n_tokens = 826, truncated = 0 15.38.629.327 I slot print_timing: id 3 | task 26698 | prompt eval time = 3617.28 ms / 820 tokens ( 4.41 ms per token, 226.69 tokens per second) 15.38.629.329 I slot print_timing: id 3 | task 26698 | eval time = 28.51 ms / 2 tokens ( 28.51 ms per token, 35.07 tokens per second) 15.38.629.329 I slot print_timing: id 3 | task 26698 | total time = 3645.79 ms / 822 tokens 15.38.629.330 I slot print_timing: id 3 | task 26698 | graphs reused = 25310 15.38.629.330 I slot print_timing: id 3 | task 26698 | graph reallocs = 0 / 0 (same size) / (changed size) 15.38.629.359 I slot release: id 3 | task 26698 | stop processing: n_tokens = 821, truncated = 0 15.38.635.536 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 15.38.635.560 I slot launch_slot_: id 0 | task 26705 | processing task, is_child = 0 15.38.639.911 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 347874010700 15.38.639.972 I slot launch_slot_: id 1 | task 26704 | processing task, is_child = 0 15.38.640.052 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 347874011016 15.38.640.109 I slot launch_slot_: id 2 | task 26706 | processing task, is_child = 0 15.38.640.154 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 821, t_last = 347874011328 15.38.640.214 I slot launch_slot_: id 3 | task 26707 | processing task, is_child = 0 15.41.797.689 I slot print_timing: id 0 | task 26705 | prompt processing, n_tokens = 533, progress = 0.99, t = 3.16 s / 168.81 tokens per second 15.42.360.382 I slot print_timing: id 1 | task 26704 | prompt processing, n_tokens = 927, progress = 1.00, t = 3.16 s / 293.60 tokens per second 15.42.360.565 I slot print_timing: id 2 | task 26706 | prompt processing, n_tokens = 852, progress = 1.00, t = 3.16 s / 269.85 tokens per second 15.42.360.726 I slot print_timing: id 3 | task 26707 | prompt processing, n_tokens = 845, progress = 1.00, t = 3.16 s / 267.64 tokens per second 15.42.461.304 I slot print_timing: id 0 | task 26705 | prompt eval time = 3792.63 ms / 537 tokens ( 7.06 ms per token, 141.59 tokens per second) 15.42.461.306 I slot print_timing: id 0 | task 26705 | eval time = 28.45 ms / 2 tokens ( 28.45 ms per token, 35.15 tokens per second) 15.42.461.306 I slot print_timing: id 0 | task 26705 | total time = 3821.08 ms / 539 tokens 15.42.461.307 I slot print_timing: id 0 | task 26705 | graphs reused = 25312 15.42.461.307 I slot print_timing: id 0 | task 26705 | graph reallocs = 0 / 0 (same size) / (changed size) 15.42.461.359 I slot release: id 0 | task 26705 | stop processing: n_tokens = 798, truncated = 0 15.42.461.627 I slot print_timing: id 1 | task 26704 | prompt eval time = 3792.87 ms / 931 tokens ( 4.07 ms per token, 245.46 tokens per second) 15.42.461.629 I slot print_timing: id 1 | task 26704 | eval time = 28.46 ms / 2 tokens ( 28.46 ms per token, 35.13 tokens per second) 15.42.461.630 I slot print_timing: id 1 | task 26704 | total time = 3821.33 ms / 933 tokens 15.42.461.630 I slot print_timing: id 1 | task 26704 | graphs reused = 25312 15.42.461.630 I slot print_timing: id 1 | task 26704 | graph reallocs = 0 / 0 (same size) / (changed size) 15.42.461.671 I slot release: id 1 | task 26704 | stop processing: n_tokens = 932, truncated = 0 15.42.461.943 I slot print_timing: id 2 | task 26706 | prompt eval time = 3793.15 ms / 856 tokens ( 4.43 ms per token, 225.67 tokens per second) 15.42.461.947 I slot print_timing: id 2 | task 26706 | eval time = 28.45 ms / 2 tokens ( 28.45 ms per token, 35.15 tokens per second) 15.42.461.947 I slot print_timing: id 2 | task 26706 | total time = 3821.60 ms / 858 tokens 15.42.461.948 I slot print_timing: id 2 | task 26706 | graphs reused = 25312 15.42.461.948 I slot print_timing: id 2 | task 26706 | graph reallocs = 0 / 0 (same size) / (changed size) 15.42.462.002 I slot release: id 2 | task 26706 | stop processing: n_tokens = 857, truncated = 0 15.42.462.309 I slot print_timing: id 3 | task 26707 | prompt eval time = 3793.45 ms / 849 tokens ( 4.47 ms per token, 223.81 tokens per second) 15.42.462.312 I slot print_timing: id 3 | task 26707 | eval time = 28.47 ms / 2 tokens ( 28.47 ms per token, 35.13 tokens per second) 15.42.462.313 I slot print_timing: id 3 | task 26707 | total time = 3821.91 ms / 851 tokens 15.42.462.313 I slot print_timing: id 3 | task 26707 | graphs reused = 25312 15.42.462.313 I slot print_timing: id 3 | task 26707 | graph reallocs = 0 / 0 (same size) / (changed size) 15.42.462.354 I slot release: id 3 | task 26707 | stop processing: n_tokens = 850, truncated = 0 15.42.469.365 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 798, t_last = 347877843330 15.42.471.024 I slot launch_slot_: id 0 | task 26712 | processing task, is_child = 0 15.42.475.866 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 347877843640 15.42.475.932 I slot launch_slot_: id 1 | task 26713 | processing task, is_child = 0 15.42.476.017 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 857, t_last = 347877843973 15.42.476.079 I slot launch_slot_: id 2 | task 26714 | processing task, is_child = 0 15.42.476.125 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 850, t_last = 347877844323 15.42.476.193 I slot launch_slot_: id 3 | task 26715 | processing task, is_child = 0 15.46.991.079 I slot print_timing: id 0 | task 26712 | prompt processing, n_tokens = 950, progress = 1.00, t = 4.51 s / 210.42 tokens per second 15.47.234.146 I slot print_timing: id 1 | task 26713 | prompt processing, n_tokens = 985, progress = 1.00, t = 4.51 s / 218.17 tokens per second 15.47.234.325 I slot print_timing: id 2 | task 26714 | prompt processing, n_tokens = 887, progress = 1.00, t = 4.51 s / 196.47 tokens per second 15.47.234.489 I slot print_timing: id 3 | task 26715 | prompt processing, n_tokens = 1226, progress = 0.70, t = 4.51 s / 271.56 tokens per second 15.47.879.830 I slot print_timing: id 3 | task 26715 | prompt processing, n_tokens = 1738, progress = 1.00, t = 5.40 s / 321.72 tokens per second 15.47.929.460 I slot print_timing: id 0 | task 26712 | prompt eval time = 5402.83 ms / 954 tokens ( 5.66 ms per token, 176.57 tokens per second) 15.47.929.463 I slot print_timing: id 0 | task 26712 | eval time = 50.43 ms / 2 tokens ( 50.43 ms per token, 19.83 tokens per second) 15.47.929.463 I slot print_timing: id 0 | task 26712 | total time = 5453.26 ms / 956 tokens 15.47.929.464 I slot print_timing: id 0 | task 26712 | graphs reused = 25313 15.47.929.464 I slot print_timing: id 0 | task 26712 | graph reallocs = 0 / 0 (same size) / (changed size) 15.47.929.521 I slot release: id 0 | task 26712 | stop processing: n_tokens = 955, truncated = 0 15.47.929.871 I slot print_timing: id 1 | task 26713 | prompt eval time = 5403.16 ms / 989 tokens ( 5.46 ms per token, 183.04 tokens per second) 15.47.929.876 I slot print_timing: id 1 | task 26713 | eval time = 50.45 ms / 2 tokens ( 50.45 ms per token, 19.82 tokens per second) 15.47.929.876 I slot print_timing: id 1 | task 26713 | total time = 5453.61 ms / 991 tokens 15.47.929.877 I slot print_timing: id 1 | task 26713 | graphs reused = 25313 15.47.929.877 I slot print_timing: id 1 | task 26713 | graph reallocs = 0 / 0 (same size) / (changed size) 15.47.929.920 I slot release: id 1 | task 26713 | stop processing: n_tokens = 990, truncated = 0 15.47.930.221 I slot print_timing: id 2 | task 26714 | prompt eval time = 5403.48 ms / 891 tokens ( 6.06 ms per token, 164.89 tokens per second) 15.47.930.224 I slot print_timing: id 2 | task 26714 | eval time = 50.41 ms / 2 tokens ( 50.41 ms per token, 19.84 tokens per second) 15.47.930.225 I slot print_timing: id 2 | task 26714 | total time = 5453.88 ms / 893 tokens 15.47.930.225 I slot print_timing: id 2 | task 26714 | graphs reused = 25313 15.47.930.226 I slot print_timing: id 2 | task 26714 | graph reallocs = 0 / 0 (same size) / (changed size) 15.47.930.273 I slot release: id 2 | task 26714 | stop processing: n_tokens = 892, truncated = 0 15.47.944.178 I slot print_timing: id 3 | task 26715 | prompt eval time = 5454.25 ms / 1742 tokens ( 3.13 ms per token, 319.38 tokens per second) 15.47.944.181 I slot print_timing: id 3 | task 26715 | eval time = 13.53 ms / 2 tokens ( 13.53 ms per token, 73.91 tokens per second) 15.47.944.182 I slot print_timing: id 3 | task 26715 | total time = 5467.78 ms / 1744 tokens 15.47.944.182 I slot print_timing: id 3 | task 26715 | graphs reused = 25313 15.47.944.182 I slot print_timing: id 3 | task 26715 | graph reallocs = 0 / 0 (same size) / (changed size) 15.47.944.273 I slot release: id 3 | task 26715 | stop processing: n_tokens = 1743, truncated = 0 15.47.944.281 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 15.47.944.304 I slot launch_slot_: id 2 | task 26721 | processing task, is_child = 0 15.47.951.558 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 955, t_last = 347883311491 15.47.951.629 I slot launch_slot_: id 0 | task 26722 | processing task, is_child = 0 15.47.951.744 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 990, t_last = 347883311889 15.47.951.810 I slot launch_slot_: id 1 | task 26723 | processing task, is_child = 0 15.47.951.879 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1743, t_last = 347883326243 15.47.951.968 I slot launch_slot_: id 3 | task 26724 | processing task, is_child = 0 15.51.421.731 I slot print_timing: id 0 | task 26722 | prompt eval time = 3441.02 ms / 727 tokens ( 4.73 ms per token, 211.27 tokens per second) 15.51.421.736 I slot print_timing: id 0 | task 26722 | eval time = 28.74 ms / 2 tokens ( 28.74 ms per token, 34.80 tokens per second) 15.51.421.738 I slot print_timing: id 0 | task 26722 | total time = 3469.75 ms / 729 tokens 15.51.421.738 I slot print_timing: id 0 | task 26722 | graphs reused = 25315 15.51.421.739 I slot print_timing: id 0 | task 26722 | graph reallocs = 0 / 0 (same size) / (changed size) 15.51.421.788 I slot release: id 0 | task 26722 | stop processing: n_tokens = 728, truncated = 0 15.51.422.044 I slot print_timing: id 1 | task 26723 | prompt eval time = 3441.21 ms / 862 tokens ( 3.99 ms per token, 250.49 tokens per second) 15.51.422.045 I slot print_timing: id 1 | task 26723 | eval time = 28.78 ms / 2 tokens ( 28.78 ms per token, 34.74 tokens per second) 15.51.422.046 I slot print_timing: id 1 | task 26723 | total time = 3469.99 ms / 864 tokens 15.51.422.046 I slot print_timing: id 1 | task 26723 | graphs reused = 25315 15.51.422.046 I slot print_timing: id 1 | task 26723 | graph reallocs = 0 / 0 (same size) / (changed size) 15.51.422.090 I slot release: id 1 | task 26723 | stop processing: n_tokens = 863, truncated = 0 15.51.422.361 I slot print_timing: id 2 | task 26721 | prompt eval time = 3441.55 ms / 533 tokens ( 6.46 ms per token, 154.87 tokens per second) 15.51.422.362 I slot print_timing: id 2 | task 26721 | eval time = 28.69 ms / 2 tokens ( 28.69 ms per token, 34.85 tokens per second) 15.51.422.363 I slot print_timing: id 2 | task 26721 | total time = 3470.25 ms / 535 tokens 15.51.422.363 I slot print_timing: id 2 | task 26721 | graphs reused = 25315 15.51.422.363 I slot print_timing: id 2 | task 26721 | graph reallocs = 0 / 0 (same size) / (changed size) 15.51.422.409 I slot release: id 2 | task 26721 | stop processing: n_tokens = 909, truncated = 0 15.51.422.704 I slot print_timing: id 3 | task 26724 | prompt eval time = 3441.88 ms / 700 tokens ( 4.92 ms per token, 203.38 tokens per second) 15.51.422.707 I slot print_timing: id 3 | task 26724 | eval time = 28.62 ms / 2 tokens ( 28.62 ms per token, 34.95 tokens per second) 15.51.422.708 I slot print_timing: id 3 | task 26724 | total time = 3470.50 ms / 702 tokens 15.51.422.708 I slot print_timing: id 3 | task 26724 | graphs reused = 25315 15.51.422.708 I slot print_timing: id 3 | task 26724 | graph reallocs = 0 / 0 (same size) / (changed size) 15.51.422.740 I slot release: id 3 | task 26724 | stop processing: n_tokens = 701, truncated = 0 15.51.429.176 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 15.51.429.204 I slot launch_slot_: id 0 | task 26731 | processing task, is_child = 0 15.51.434.180 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 347886804059 15.51.434.248 I slot launch_slot_: id 1 | task 26732 | processing task, is_child = 0 15.51.434.328 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 15.51.434.342 I slot launch_slot_: id 3 | task 26729 | processing task, is_child = 0 15.51.434.386 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 909, t_last = 347886804378 15.51.435.015 I slot launch_slot_: id 2 | task 26730 | processing task, is_child = 0 15.54.441.827 I slot print_timing: id 0 | task 26731 | prompt eval time = 2934.62 ms / 493 tokens ( 5.95 ms per token, 167.99 tokens per second) 15.54.441.830 I slot print_timing: id 0 | task 26731 | eval time = 72.19 ms / 2 tokens ( 72.19 ms per token, 13.85 tokens per second) 15.54.441.831 I slot print_timing: id 0 | task 26731 | total time = 3006.80 ms / 495 tokens 15.54.441.831 I slot print_timing: id 0 | task 26731 | graphs reused = 25315 15.54.441.832 I slot print_timing: id 0 | task 26731 | graph reallocs = 0 / 0 (same size) / (changed size) 15.54.441.883 I slot release: id 0 | task 26731 | stop processing: n_tokens = 705, truncated = 0 15.54.465.956 I slot print_timing: id 1 | task 26732 | prompt eval time = 3007.06 ms / 828 tokens ( 3.63 ms per token, 275.35 tokens per second) 15.54.465.959 I slot print_timing: id 1 | task 26732 | eval time = 23.75 ms / 2 tokens ( 23.75 ms per token, 42.10 tokens per second) 15.54.465.959 I slot print_timing: id 1 | task 26732 | total time = 3030.81 ms / 830 tokens 15.54.465.960 I slot print_timing: id 1 | task 26732 | graphs reused = 25315 15.54.465.960 I slot print_timing: id 1 | task 26732 | graph reallocs = 0 / 0 (same size) / (changed size) 15.54.466.000 I slot release: id 1 | task 26732 | stop processing: n_tokens = 829, truncated = 0 15.54.466.259 I slot print_timing: id 2 | task 26730 | prompt eval time = 3007.32 ms / 524 tokens ( 5.74 ms per token, 174.24 tokens per second) 15.54.466.266 I slot print_timing: id 2 | task 26730 | eval time = 23.74 ms / 2 tokens ( 23.74 ms per token, 42.12 tokens per second) 15.54.466.266 I slot print_timing: id 2 | task 26730 | total time = 3031.06 ms / 526 tokens 15.54.466.266 I slot print_timing: id 2 | task 26730 | graphs reused = 25315 15.54.466.267 I slot print_timing: id 2 | task 26730 | graph reallocs = 0 / 0 (same size) / (changed size) 15.54.466.297 I slot release: id 2 | task 26730 | stop processing: n_tokens = 709, truncated = 0 15.54.466.586 I slot print_timing: id 3 | task 26729 | prompt eval time = 3007.64 ms / 522 tokens ( 5.76 ms per token, 173.56 tokens per second) 15.54.466.588 I slot print_timing: id 3 | task 26729 | eval time = 23.68 ms / 2 tokens ( 23.68 ms per token, 42.23 tokens per second) 15.54.466.588 I slot print_timing: id 3 | task 26729 | total time = 3031.32 ms / 524 tokens 15.54.466.588 I slot print_timing: id 3 | task 26729 | graphs reused = 25315 15.54.466.589 I slot print_timing: id 3 | task 26729 | graph reallocs = 0 / 0 (same size) / (changed size) 15.54.466.622 I slot release: id 3 | task 26729 | stop processing: n_tokens = 707, truncated = 0 15.54.466.626 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 705, t_last = 347889823852 15.54.468.195 I slot launch_slot_: id 0 | task 26737 | processing task, is_child = 0 15.54.472.609 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 829, t_last = 347889847969 15.54.472.675 I slot launch_slot_: id 1 | task 26738 | processing task, is_child = 0 15.54.472.748 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 709, t_last = 347889848266 15.54.472.800 I slot launch_slot_: id 2 | task 26739 | processing task, is_child = 0 15.54.472.837 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 347889848591 15.54.472.892 I slot launch_slot_: id 3 | task 26740 | processing task, is_child = 0 15.58.198.299 I slot print_timing: id 0 | task 26737 | prompt processing, n_tokens = 913, progress = 1.00, t = 3.73 s / 245.08 tokens per second 15.58.762.784 I slot print_timing: id 1 | task 26738 | prompt processing, n_tokens = 932, progress = 1.00, t = 3.73 s / 250.18 tokens per second 15.58.762.948 I slot print_timing: id 2 | task 26739 | prompt processing, n_tokens = 922, progress = 1.00, t = 3.73 s / 247.50 tokens per second 15.58.763.100 I slot print_timing: id 3 | task 26740 | prompt processing, n_tokens = 958, progress = 1.00, t = 3.73 s / 257.17 tokens per second 15.58.863.834 I slot print_timing: id 0 | task 26737 | prompt eval time = 4362.30 ms / 917 tokens ( 4.76 ms per token, 210.21 tokens per second) 15.58.863.836 I slot print_timing: id 0 | task 26737 | eval time = 28.63 ms / 2 tokens ( 28.63 ms per token, 34.93 tokens per second) 15.58.863.836 I slot print_timing: id 0 | task 26737 | total time = 4390.93 ms / 919 tokens 15.58.863.836 I slot print_timing: id 0 | task 26737 | graphs reused = 25317 15.58.863.837 I slot print_timing: id 0 | task 26737 | graph reallocs = 0 / 0 (same size) / (changed size) 15.58.863.885 I slot release: id 0 | task 26737 | stop processing: n_tokens = 918, truncated = 0 15.58.864.161 I slot print_timing: id 1 | task 26738 | prompt eval time = 4362.54 ms / 936 tokens ( 4.66 ms per token, 214.55 tokens per second) 15.58.864.163 I slot print_timing: id 1 | task 26738 | eval time = 28.66 ms / 2 tokens ( 28.66 ms per token, 34.89 tokens per second) 15.58.864.164 I slot print_timing: id 1 | task 26738 | total time = 4391.20 ms / 938 tokens 15.58.864.164 I slot print_timing: id 1 | task 26738 | graphs reused = 25317 15.58.864.164 I slot print_timing: id 1 | task 26738 | graph reallocs = 0 / 0 (same size) / (changed size) 15.58.864.203 I slot release: id 1 | task 26738 | stop processing: n_tokens = 937, truncated = 0 15.58.864.495 I slot print_timing: id 2 | task 26739 | prompt eval time = 4362.90 ms / 926 tokens ( 4.71 ms per token, 212.24 tokens per second) 15.58.864.498 I slot print_timing: id 2 | task 26739 | eval time = 28.57 ms / 2 tokens ( 28.57 ms per token, 35.00 tokens per second) 15.58.864.498 I slot print_timing: id 2 | task 26739 | total time = 4391.47 ms / 928 tokens 15.58.864.499 I slot print_timing: id 2 | task 26739 | graphs reused = 25317 15.58.864.499 I slot print_timing: id 2 | task 26739 | graph reallocs = 0 / 0 (same size) / (changed size) 15.58.864.538 I slot release: id 2 | task 26739 | stop processing: n_tokens = 927, truncated = 0 15.58.864.889 I slot print_timing: id 3 | task 26740 | prompt eval time = 4363.30 ms / 962 tokens ( 4.54 ms per token, 220.48 tokens per second) 15.58.864.891 I slot print_timing: id 3 | task 26740 | eval time = 28.52 ms / 2 tokens ( 28.52 ms per token, 35.07 tokens per second) 15.58.864.891 I slot print_timing: id 3 | task 26740 | total time = 4391.81 ms / 964 tokens 15.58.864.892 I slot print_timing: id 3 | task 26740 | graphs reused = 25317 15.58.864.892 I slot print_timing: id 3 | task 26740 | graph reallocs = 0 / 0 (same size) / (changed size) 15.58.864.933 I slot release: id 3 | task 26740 | stop processing: n_tokens = 963, truncated = 0 15.58.871.744 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.898 15.58.871.766 I slot launch_slot_: id 0 | task 26745 | processing task, is_child = 0 15.58.877.028 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 937, t_last = 347894246172 15.58.877.101 I slot launch_slot_: id 1 | task 26746 | processing task, is_child = 0 15.58.877.196 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 927, t_last = 347894246507 15.58.877.258 I slot launch_slot_: id 2 | task 26747 | processing task, is_child = 0 15.58.877.305 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 963, t_last = 347894246902 15.58.877.368 I slot launch_slot_: id 3 | task 26748 | processing task, is_child = 0 16.02.149.688 I slot print_timing: id 0 | task 26745 | prompt processing, n_tokens = 519, progress = 1.00, t = 3.27 s / 158.60 tokens per second 16.02.713.426 I slot print_timing: id 1 | task 26746 | prompt processing, n_tokens = 817, progress = 1.00, t = 3.27 s / 249.68 tokens per second 16.02.713.576 I slot print_timing: id 2 | task 26747 | prompt processing, n_tokens = 996, progress = 1.00, t = 3.27 s / 304.39 tokens per second 16.02.713.734 I slot print_timing: id 3 | task 26748 | prompt processing, n_tokens = 882, progress = 1.00, t = 3.27 s / 269.55 tokens per second 16.02.814.038 I slot print_timing: id 0 | task 26745 | prompt eval time = 3908.18 ms / 523 tokens ( 7.47 ms per token, 133.82 tokens per second) 16.02.814.040 I slot print_timing: id 0 | task 26745 | eval time = 28.48 ms / 2 tokens ( 28.48 ms per token, 35.12 tokens per second) 16.02.814.041 I slot print_timing: id 0 | task 26745 | total time = 3936.66 ms / 525 tokens 16.02.814.041 I slot print_timing: id 0 | task 26745 | graphs reused = 25319 16.02.814.042 I slot print_timing: id 0 | task 26745 | graph reallocs = 0 / 0 (same size) / (changed size) 16.02.814.094 I slot release: id 0 | task 26745 | stop processing: n_tokens = 925, truncated = 0 16.02.814.367 I slot print_timing: id 1 | task 26746 | prompt eval time = 3908.38 ms / 821 tokens ( 4.76 ms per token, 210.06 tokens per second) 16.02.814.369 I slot print_timing: id 1 | task 26746 | eval time = 28.52 ms / 2 tokens ( 28.52 ms per token, 35.06 tokens per second) 16.02.814.370 I slot print_timing: id 1 | task 26746 | total time = 3936.90 ms / 823 tokens 16.02.814.370 I slot print_timing: id 1 | task 26746 | graphs reused = 25319 16.02.814.370 I slot print_timing: id 1 | task 26746 | graph reallocs = 0 / 0 (same size) / (changed size) 16.02.814.405 I slot release: id 1 | task 26746 | stop processing: n_tokens = 822, truncated = 0 16.02.814.680 I slot print_timing: id 2 | task 26747 | prompt eval time = 3908.63 ms / 1000 tokens ( 3.91 ms per token, 255.84 tokens per second) 16.02.814.683 I slot print_timing: id 2 | task 26747 | eval time = 28.52 ms / 2 tokens ( 28.52 ms per token, 35.07 tokens per second) 16.02.814.684 I slot print_timing: id 2 | task 26747 | total time = 3937.14 ms / 1002 tokens 16.02.814.684 I slot print_timing: id 2 | task 26747 | graphs reused = 25319 16.02.814.684 I slot print_timing: id 2 | task 26747 | graph reallocs = 0 / 0 (same size) / (changed size) 16.02.814.731 I slot release: id 2 | task 26747 | stop processing: n_tokens = 1001, truncated = 0 16.02.815.006 I slot print_timing: id 3 | task 26748 | prompt eval time = 3908.99 ms / 886 tokens ( 4.41 ms per token, 226.66 tokens per second) 16.02.815.011 I slot print_timing: id 3 | task 26748 | eval time = 28.42 ms / 2 tokens ( 28.42 ms per token, 35.18 tokens per second) 16.02.815.012 I slot print_timing: id 3 | task 26748 | total time = 3937.41 ms / 888 tokens 16.02.815.012 I slot print_timing: id 3 | task 26748 | graphs reused = 25319 16.02.815.012 I slot print_timing: id 3 | task 26748 | graph reallocs = 0 / 0 (same size) / (changed size) 16.02.815.050 I slot release: id 3 | task 26748 | stop processing: n_tokens = 887, truncated = 0 16.02.822.446 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.791 16.02.822.475 I slot launch_slot_: id 2 | task 26753 | processing task, is_child = 0 16.02.827.503 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.891 (> 0.100 thold), f_keep = 0.892 16.02.827.525 I slot launch_slot_: id 3 | task 26754 | processing task, is_child = 0 16.02.827.613 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 925, t_last = 347898196063 16.02.828.354 I slot launch_slot_: id 0 | task 26755 | processing task, is_child = 0 16.02.828.397 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 822, t_last = 347898196374 16.02.828.460 I slot launch_slot_: id 1 | task 26756 | processing task, is_child = 0 16.05.896.464 I slot print_timing: id 0 | task 26755 | prompt processing, n_tokens = 587, progress = 1.00, t = 3.07 s / 191.36 tokens per second 16.05.896.674 I slot print_timing: id 1 | task 26756 | prompt processing, n_tokens = 986, progress = 1.00, t = 3.07 s / 321.43 tokens per second 16.05.896.870 I slot print_timing: id 3 | task 26754 | prompt processing, n_tokens = 514, progress = 1.00, t = 3.07 s / 167.57 tokens per second 16.05.976.363 I slot print_timing: id 2 | task 26753 | prompt eval time = 3067.84 ms / 388 tokens ( 7.91 ms per token, 126.47 tokens per second) 16.05.976.366 I slot print_timing: id 2 | task 26753 | eval time = 79.91 ms / 2 tokens ( 79.91 ms per token, 12.51 tokens per second) 16.05.976.366 I slot print_timing: id 2 | task 26753 | total time = 3147.75 ms / 390 tokens 16.05.976.367 I slot print_timing: id 2 | task 26753 | graphs reused = 25319 16.05.976.367 I slot print_timing: id 2 | task 26753 | graph reallocs = 0 / 0 (same size) / (changed size) 16.05.976.450 I slot release: id 2 | task 26753 | stop processing: n_tokens = 873, truncated = 0 16.06.007.297 I slot print_timing: id 0 | task 26755 | prompt eval time = 3147.14 ms / 591 tokens ( 5.33 ms per token, 187.79 tokens per second) 16.06.007.299 I slot print_timing: id 0 | task 26755 | eval time = 31.69 ms / 2 tokens ( 31.69 ms per token, 31.56 tokens per second) 16.06.007.299 I slot print_timing: id 0 | task 26755 | total time = 3178.83 ms / 593 tokens 16.06.007.300 I slot print_timing: id 0 | task 26755 | graphs reused = 25319 16.06.007.300 I slot print_timing: id 0 | task 26755 | graph reallocs = 0 / 0 (same size) / (changed size) 16.06.007.349 I slot release: id 0 | task 26755 | stop processing: n_tokens = 962, truncated = 0 16.06.007.632 I slot print_timing: id 1 | task 26756 | prompt eval time = 3147.47 ms / 990 tokens ( 3.18 ms per token, 314.54 tokens per second) 16.06.007.635 I slot print_timing: id 1 | task 26756 | eval time = 31.62 ms / 2 tokens ( 31.62 ms per token, 31.62 tokens per second) 16.06.007.635 I slot print_timing: id 1 | task 26756 | total time = 3179.09 ms / 992 tokens 16.06.007.636 I slot print_timing: id 1 | task 26756 | graphs reused = 25319 16.06.007.636 I slot print_timing: id 1 | task 26756 | graph reallocs = 0 / 0 (same size) / (changed size) 16.06.007.680 I slot release: id 1 | task 26756 | stop processing: n_tokens = 991, truncated = 0 16.06.007.962 I slot print_timing: id 3 | task 26754 | prompt eval time = 3148.30 ms / 518 tokens ( 6.08 ms per token, 164.53 tokens per second) 16.06.007.964 I slot print_timing: id 3 | task 26754 | eval time = 30.95 ms / 2 tokens ( 30.95 ms per token, 32.31 tokens per second) 16.06.007.964 I slot print_timing: id 3 | task 26754 | total time = 3179.25 ms / 520 tokens 16.06.007.964 I slot print_timing: id 3 | task 26754 | graphs reused = 25319 16.06.007.965 I slot print_timing: id 3 | task 26754 | graph reallocs = 0 / 0 (same size) / (changed size) 16.06.008.000 I slot release: id 3 | task 26754 | stop processing: n_tokens = 889, truncated = 0 16.06.008.004 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 347901358419 16.06.009.786 I slot launch_slot_: id 2 | task 26761 | processing task, is_child = 0 16.06.016.001 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 347901389318 16.06.016.080 I slot launch_slot_: id 0 | task 26762 | processing task, is_child = 0 16.06.016.170 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 347901389650 16.06.016.233 I slot launch_slot_: id 1 | task 26763 | processing task, is_child = 0 16.06.016.277 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 889, t_last = 347901389969 16.06.016.335 I slot launch_slot_: id 3 | task 26764 | processing task, is_child = 0 16.10.007.083 I slot print_timing: id 0 | task 26762 | prompt processing, n_tokens = 865, progress = 1.00, t = 3.99 s / 216.75 tokens per second 16.10.573.397 I slot print_timing: id 1 | task 26763 | prompt processing, n_tokens = 899, progress = 1.00, t = 3.99 s / 225.28 tokens per second 16.10.573.564 I slot print_timing: id 2 | task 26761 | prompt processing, n_tokens = 906, progress = 1.00, t = 3.99 s / 227.03 tokens per second 16.10.573.712 I slot print_timing: id 3 | task 26764 | prompt processing, n_tokens = 1276, progress = 1.00, t = 3.99 s / 319.76 tokens per second 16.10.674.084 I slot print_timing: id 0 | task 26762 | prompt eval time = 4629.44 ms / 869 tokens ( 5.33 ms per token, 187.71 tokens per second) 16.10.674.087 I slot print_timing: id 0 | task 26762 | eval time = 28.31 ms / 2 tokens ( 28.31 ms per token, 35.33 tokens per second) 16.10.674.087 I slot print_timing: id 0 | task 26762 | total time = 4657.74 ms / 871 tokens 16.10.674.088 I slot print_timing: id 0 | task 26762 | graphs reused = 25321 16.10.674.088 I slot print_timing: id 0 | task 26762 | graph reallocs = 0 / 0 (same size) / (changed size) 16.10.674.138 I slot release: id 0 | task 26762 | stop processing: n_tokens = 870, truncated = 0 16.10.674.432 I slot print_timing: id 1 | task 26763 | prompt eval time = 4629.73 ms / 903 tokens ( 5.13 ms per token, 195.04 tokens per second) 16.10.674.435 I slot print_timing: id 1 | task 26763 | eval time = 28.29 ms / 2 tokens ( 28.29 ms per token, 35.35 tokens per second) 16.10.674.435 I slot print_timing: id 1 | task 26763 | total time = 4658.02 ms / 905 tokens 16.10.674.435 I slot print_timing: id 1 | task 26763 | graphs reused = 25321 16.10.674.436 I slot print_timing: id 1 | task 26763 | graph reallocs = 0 / 0 (same size) / (changed size) 16.10.674.479 I slot release: id 1 | task 26763 | stop processing: n_tokens = 904, truncated = 0 16.10.674.742 I slot print_timing: id 2 | task 26761 | prompt eval time = 4629.97 ms / 910 tokens ( 5.09 ms per token, 196.55 tokens per second) 16.10.674.744 I slot print_timing: id 2 | task 26761 | eval time = 28.29 ms / 2 tokens ( 28.29 ms per token, 35.35 tokens per second) 16.10.674.745 I slot print_timing: id 2 | task 26761 | total time = 4658.26 ms / 912 tokens 16.10.674.745 I slot print_timing: id 2 | task 26761 | graphs reused = 25321 16.10.674.745 I slot print_timing: id 2 | task 26761 | graph reallocs = 0 / 0 (same size) / (changed size) 16.10.674.781 I slot release: id 2 | task 26761 | stop processing: n_tokens = 911, truncated = 0 16.10.675.076 I slot print_timing: id 3 | task 26764 | prompt eval time = 4630.24 ms / 1280 tokens ( 3.62 ms per token, 276.44 tokens per second) 16.10.675.078 I slot print_timing: id 3 | task 26764 | eval time = 28.29 ms / 2 tokens ( 28.29 ms per token, 35.35 tokens per second) 16.10.675.078 I slot print_timing: id 3 | task 26764 | total time = 4658.53 ms / 1282 tokens 16.10.675.078 I slot print_timing: id 3 | task 26764 | graphs reused = 25321 16.10.675.079 I slot print_timing: id 3 | task 26764 | graph reallocs = 0 / 0 (same size) / (changed size) 16.10.675.144 I slot release: id 3 | task 26764 | stop processing: n_tokens = 1281, truncated = 0 16.10.681.458 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 870, t_last = 347906056107 16.10.683.332 I slot launch_slot_: id 0 | task 26769 | processing task, is_child = 0 16.10.689.222 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.877 16.10.689.246 I slot launch_slot_: id 3 | task 26770 | processing task, is_child = 0 16.10.689.333 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 347906056448 16.10.690.240 I slot launch_slot_: id 1 | task 26771 | processing task, is_child = 0 16.10.690.287 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 911, t_last = 347906056750 16.10.690.347 I slot launch_slot_: id 2 | task 26772 | processing task, is_child = 0 16.14.315.630 I slot print_timing: id 0 | task 26769 | prompt processing, n_tokens = 763, progress = 0.99, t = 3.62 s / 210.51 tokens per second 16.14.315.791 I slot print_timing: id 2 | task 26772 | prompt processing, n_tokens = 1283, progress = 1.00, t = 3.62 s / 353.99 tokens per second 16.14.391.555 I slot print_timing: id 1 | task 26771 | prompt eval time = 3624.89 ms / 476 tokens ( 7.62 ms per token, 131.31 tokens per second) 16.14.391.558 I slot print_timing: id 1 | task 26771 | eval time = 76.25 ms / 2 tokens ( 76.25 ms per token, 13.11 tokens per second) 16.14.391.558 I slot print_timing: id 1 | task 26771 | total time = 3701.14 ms / 478 tokens 16.14.391.559 I slot print_timing: id 1 | task 26771 | graphs reused = 25321 16.14.391.559 I slot print_timing: id 1 | task 26771 | graph reallocs = 0 / 0 (same size) / (changed size) 16.14.391.631 I slot release: id 1 | task 26771 | stop processing: n_tokens = 1241, truncated = 0 16.14.392.405 I slot print_timing: id 3 | task 26770 | prompt eval time = 3625.03 ms / 439 tokens ( 8.26 ms per token, 121.10 tokens per second) 16.14.392.408 I slot print_timing: id 3 | task 26770 | eval time = 76.78 ms / 2 tokens ( 76.78 ms per token, 13.02 tokens per second) 16.14.392.408 I slot print_timing: id 3 | task 26770 | total time = 3701.81 ms / 441 tokens 16.14.392.409 I slot print_timing: id 3 | task 26770 | graphs reused = 25321 16.14.392.409 I slot print_timing: id 3 | task 26770 | graph reallocs = 0 / 0 (same size) / (changed size) 16.14.392.458 I slot release: id 3 | task 26770 | stop processing: n_tokens = 1204, truncated = 0 16.14.418.313 I slot print_timing: id 0 | task 26769 | prompt eval time = 3700.82 ms / 767 tokens ( 4.83 ms per token, 207.25 tokens per second) 16.14.418.320 I slot print_timing: id 0 | task 26769 | eval time = 27.13 ms / 2 tokens ( 27.13 ms per token, 36.86 tokens per second) 16.14.418.320 I slot print_timing: id 0 | task 26769 | total time = 3727.95 ms / 769 tokens 16.14.418.321 I slot print_timing: id 0 | task 26769 | graphs reused = 25321 16.14.418.322 I slot print_timing: id 0 | task 26769 | graph reallocs = 0 / 0 (same size) / (changed size) 16.14.418.383 I slot release: id 0 | task 26769 | stop processing: n_tokens = 768, truncated = 0 16.14.418.868 I slot print_timing: id 2 | task 26772 | prompt eval time = 3701.50 ms / 1287 tokens ( 2.88 ms per token, 347.70 tokens per second) 16.14.418.871 I slot print_timing: id 2 | task 26772 | eval time = 26.84 ms / 2 tokens ( 26.84 ms per token, 37.26 tokens per second) 16.14.418.872 I slot print_timing: id 2 | task 26772 | total time = 3728.33 ms / 1289 tokens 16.14.418.872 I slot print_timing: id 2 | task 26772 | graphs reused = 25321 16.14.418.873 I slot print_timing: id 2 | task 26772 | graph reallocs = 0 / 0 (same size) / (changed size) 16.14.418.955 I slot release: id 2 | task 26772 | stop processing: n_tokens = 1288, truncated = 0 16.14.418.963 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.872 (> 0.100 thold), f_keep = 0.889 16.14.419.000 I slot launch_slot_: id 0 | task 26777 | processing task, is_child = 0 16.14.428.973 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1241, t_last = 347909773600 16.14.429.114 I slot launch_slot_: id 1 | task 26778 | processing task, is_child = 0 16.14.429.310 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1204, t_last = 347909774427 16.14.429.429 I slot launch_slot_: id 3 | task 26779 | processing task, is_child = 0 16.14.429.525 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1288, t_last = 347909800926 16.14.429.653 I slot launch_slot_: id 2 | task 26780 | processing task, is_child = 0 16.17.531.818 I slot print_timing: id 0 | task 26777 | prompt processing, n_tokens = 528, progress = 0.99, t = 3.10 s / 170.20 tokens per second 16.18.095.948 I slot print_timing: id 1 | task 26778 | prompt processing, n_tokens = 870, progress = 1.00, t = 3.10 s / 280.46 tokens per second 16.18.096.100 I slot print_timing: id 2 | task 26780 | prompt processing, n_tokens = 766, progress = 0.99, t = 3.10 s / 246.95 tokens per second 16.18.096.260 I slot print_timing: id 3 | task 26779 | prompt processing, n_tokens = 840, progress = 1.00, t = 3.10 s / 270.82 tokens per second 16.18.196.645 I slot print_timing: id 0 | task 26777 | prompt eval time = 3738.48 ms / 532 tokens ( 7.03 ms per token, 142.30 tokens per second) 16.18.196.651 I slot print_timing: id 0 | task 26777 | eval time = 28.50 ms / 2 tokens ( 28.50 ms per token, 35.08 tokens per second) 16.18.196.651 I slot print_timing: id 0 | task 26777 | total time = 3766.98 ms / 534 tokens 16.18.196.652 I slot print_timing: id 0 | task 26777 | graphs reused = 25322 16.18.196.652 I slot print_timing: id 0 | task 26777 | graph reallocs = 0 / 0 (same size) / (changed size) 16.18.196.697 I slot release: id 0 | task 26777 | stop processing: n_tokens = 784, truncated = 0 16.18.197.026 I slot print_timing: id 1 | task 26778 | prompt eval time = 3738.74 ms / 874 tokens ( 4.28 ms per token, 233.77 tokens per second) 16.18.197.029 I slot print_timing: id 1 | task 26778 | eval time = 28.49 ms / 2 tokens ( 28.49 ms per token, 35.10 tokens per second) 16.18.197.029 I slot print_timing: id 1 | task 26778 | total time = 3767.23 ms / 876 tokens 16.18.197.030 I slot print_timing: id 1 | task 26778 | graphs reused = 25322 16.18.197.030 I slot print_timing: id 1 | task 26778 | graph reallocs = 0 / 0 (same size) / (changed size) 16.18.197.080 I slot release: id 1 | task 26778 | stop processing: n_tokens = 875, truncated = 0 16.18.197.370 I slot print_timing: id 2 | task 26780 | prompt eval time = 3738.98 ms / 770 tokens ( 4.86 ms per token, 205.94 tokens per second) 16.18.197.373 I slot print_timing: id 2 | task 26780 | eval time = 28.44 ms / 2 tokens ( 28.44 ms per token, 35.16 tokens per second) 16.18.197.373 I slot print_timing: id 2 | task 26780 | total time = 3767.42 ms / 772 tokens 16.18.197.373 I slot print_timing: id 2 | task 26780 | graphs reused = 25322 16.18.197.374 I slot print_timing: id 2 | task 26780 | graph reallocs = 0 / 0 (same size) / (changed size) 16.18.197.422 I slot release: id 2 | task 26780 | stop processing: n_tokens = 771, truncated = 0 16.18.197.716 I slot print_timing: id 3 | task 26779 | prompt eval time = 3739.27 ms / 844 tokens ( 4.43 ms per token, 225.71 tokens per second) 16.18.197.719 I slot print_timing: id 3 | task 26779 | eval time = 28.35 ms / 2 tokens ( 28.35 ms per token, 35.27 tokens per second) 16.18.197.719 I slot print_timing: id 3 | task 26779 | total time = 3767.62 ms / 846 tokens 16.18.197.719 I slot print_timing: id 3 | task 26779 | graphs reused = 25322 16.18.197.720 I slot print_timing: id 3 | task 26779 | graph reallocs = 0 / 0 (same size) / (changed size) 16.18.197.758 I slot release: id 3 | task 26779 | stop processing: n_tokens = 845, truncated = 0 16.18.203.909 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.861 16.18.203.930 I slot launch_slot_: id 2 | task 26785 | processing task, is_child = 0 16.18.208.823 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 784, t_last = 347913578666 16.18.208.893 I slot launch_slot_: id 0 | task 26786 | processing task, is_child = 0 16.18.208.985 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 875, t_last = 347913579049 16.18.209.047 I slot launch_slot_: id 1 | task 26787 | processing task, is_child = 0 16.18.209.092 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 845, t_last = 347913579727 16.18.209.152 I slot launch_slot_: id 3 | task 26788 | processing task, is_child = 0 16.21.644.576 I slot print_timing: id 0 | task 26786 | prompt processing, n_tokens = 814, progress = 1.00, t = 3.44 s / 236.97 tokens per second 16.21.644.731 I slot print_timing: id 1 | task 26787 | prompt processing, n_tokens = 775, progress = 0.99, t = 3.43 s / 225.62 tokens per second 16.21.644.868 I slot print_timing: id 3 | task 26788 | prompt processing, n_tokens = 746, progress = 0.99, t = 3.43 s / 217.19 tokens per second 16.21.723.755 I slot print_timing: id 2 | task 26785 | prompt eval time = 3435.27 ms / 502 tokens ( 6.84 ms per token, 146.13 tokens per second) 16.21.723.758 I slot print_timing: id 2 | task 26785 | eval time = 79.19 ms / 2 tokens ( 79.19 ms per token, 12.63 tokens per second) 16.21.723.759 I slot print_timing: id 2 | task 26785 | total time = 3514.46 ms / 504 tokens 16.21.723.759 I slot print_timing: id 2 | task 26785 | graphs reused = 25322 16.21.723.760 I slot print_timing: id 2 | task 26785 | graph reallocs = 0 / 0 (same size) / (changed size) 16.21.723.829 I slot release: id 2 | task 26785 | stop processing: n_tokens = 757, truncated = 0 16.21.754.310 I slot print_timing: id 0 | task 26786 | prompt eval time = 3513.95 ms / 818 tokens ( 4.30 ms per token, 232.79 tokens per second) 16.21.754.312 I slot print_timing: id 0 | task 26786 | eval time = 31.20 ms / 2 tokens ( 31.20 ms per token, 32.05 tokens per second) 16.21.754.312 I slot print_timing: id 0 | task 26786 | total time = 3545.15 ms / 820 tokens 16.21.754.312 I slot print_timing: id 0 | task 26786 | graphs reused = 25322 16.21.754.313 I slot print_timing: id 0 | task 26786 | graph reallocs = 0 / 0 (same size) / (changed size) 16.21.754.363 I slot release: id 0 | task 26786 | stop processing: n_tokens = 819, truncated = 0 16.21.754.680 I slot print_timing: id 1 | task 26787 | prompt eval time = 3514.23 ms / 779 tokens ( 4.51 ms per token, 221.67 tokens per second) 16.21.754.682 I slot print_timing: id 1 | task 26787 | eval time = 31.22 ms / 2 tokens ( 31.22 ms per token, 32.03 tokens per second) 16.21.754.683 I slot print_timing: id 1 | task 26787 | total time = 3545.46 ms / 781 tokens 16.21.754.684 I slot print_timing: id 1 | task 26787 | graphs reused = 25322 16.21.754.684 I slot print_timing: id 1 | task 26787 | graph reallocs = 0 / 0 (same size) / (changed size) 16.21.754.722 I slot release: id 1 | task 26787 | stop processing: n_tokens = 780, truncated = 0 16.21.755.057 I slot print_timing: id 3 | task 26788 | prompt eval time = 3514.88 ms / 750 tokens ( 4.69 ms per token, 213.38 tokens per second) 16.21.755.060 I slot print_timing: id 3 | task 26788 | eval time = 30.77 ms / 2 tokens ( 30.77 ms per token, 32.50 tokens per second) 16.21.755.060 I slot print_timing: id 3 | task 26788 | total time = 3545.65 ms / 752 tokens 16.21.755.061 I slot print_timing: id 3 | task 26788 | graphs reused = 25322 16.21.755.061 I slot print_timing: id 3 | task 26788 | graph reallocs = 0 / 0 (same size) / (changed size) 16.21.755.111 I slot release: id 3 | task 26788 | stop processing: n_tokens = 751, truncated = 0 16.21.755.117 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 757, t_last = 347917105799 16.21.756.731 I slot launch_slot_: id 2 | task 26793 | processing task, is_child = 0 16.21.760.948 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 819, t_last = 347917136332 16.21.761.023 I slot launch_slot_: id 0 | task 26794 | processing task, is_child = 0 16.21.761.101 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 347917136691 16.21.761.158 I slot launch_slot_: id 1 | task 26795 | processing task, is_child = 0 16.21.761.198 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 347917137080 16.21.761.253 I slot launch_slot_: id 3 | task 26796 | processing task, is_child = 0 16.25.167.531 I slot print_timing: id 0 | task 26794 | prompt processing, n_tokens = 877, progress = 1.00, t = 3.41 s / 257.47 tokens per second 16.25.731.389 I slot print_timing: id 1 | task 26795 | prompt processing, n_tokens = 881, progress = 1.00, t = 3.41 s / 258.65 tokens per second 16.25.731.566 I slot print_timing: id 2 | task 26793 | prompt processing, n_tokens = 893, progress = 1.00, t = 3.41 s / 262.17 tokens per second 16.25.731.722 I slot print_timing: id 3 | task 26796 | prompt processing, n_tokens = 899, progress = 1.00, t = 3.41 s / 263.94 tokens per second 16.25.832.474 I slot print_timing: id 0 | task 26794 | prompt eval time = 4042.44 ms / 881 tokens ( 4.59 ms per token, 217.94 tokens per second) 16.25.832.476 I slot print_timing: id 0 | task 26794 | eval time = 28.78 ms / 2 tokens ( 28.78 ms per token, 34.75 tokens per second) 16.25.832.480 I slot print_timing: id 0 | task 26794 | total time = 4071.21 ms / 883 tokens 16.25.832.481 I slot print_timing: id 0 | task 26794 | graphs reused = 25324 16.25.832.482 I slot print_timing: id 0 | task 26794 | graph reallocs = 0 / 0 (same size) / (changed size) 16.25.832.533 I slot release: id 0 | task 26794 | stop processing: n_tokens = 882, truncated = 0 16.25.832.800 I slot print_timing: id 1 | task 26795 | prompt eval time = 4042.69 ms / 885 tokens ( 4.57 ms per token, 218.91 tokens per second) 16.25.832.801 I slot print_timing: id 1 | task 26795 | eval time = 28.79 ms / 2 tokens ( 28.79 ms per token, 34.74 tokens per second) 16.25.832.802 I slot print_timing: id 1 | task 26795 | total time = 4071.48 ms / 887 tokens 16.25.832.802 I slot print_timing: id 1 | task 26795 | graphs reused = 25324 16.25.832.803 I slot print_timing: id 1 | task 26795 | graph reallocs = 0 / 0 (same size) / (changed size) 16.25.832.840 I slot release: id 1 | task 26795 | stop processing: n_tokens = 886, truncated = 0 16.25.833.101 I slot print_timing: id 2 | task 26793 | prompt eval time = 4042.94 ms / 897 tokens ( 4.51 ms per token, 221.87 tokens per second) 16.25.833.104 I slot print_timing: id 2 | task 26793 | eval time = 28.79 ms / 2 tokens ( 28.79 ms per token, 34.73 tokens per second) 16.25.833.104 I slot print_timing: id 2 | task 26793 | total time = 4071.73 ms / 899 tokens 16.25.833.108 I slot print_timing: id 2 | task 26793 | graphs reused = 25324 16.25.833.109 I slot print_timing: id 2 | task 26793 | graph reallocs = 0 / 0 (same size) / (changed size) 16.25.833.145 I slot release: id 2 | task 26793 | stop processing: n_tokens = 898, truncated = 0 16.25.833.443 I slot print_timing: id 3 | task 26796 | prompt eval time = 4043.24 ms / 903 tokens ( 4.48 ms per token, 223.34 tokens per second) 16.25.833.445 I slot print_timing: id 3 | task 26796 | eval time = 28.78 ms / 2 tokens ( 28.78 ms per token, 34.75 tokens per second) 16.25.833.445 I slot print_timing: id 3 | task 26796 | total time = 4072.02 ms / 905 tokens 16.25.833.445 I slot print_timing: id 3 | task 26796 | graphs reused = 25324 16.25.833.446 I slot print_timing: id 3 | task 26796 | graph reallocs = 0 / 0 (same size) / (changed size) 16.25.833.487 I slot release: id 3 | task 26796 | stop processing: n_tokens = 904, truncated = 0 16.25.840.268 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 347921214502 16.25.842.127 I slot launch_slot_: id 0 | task 26801 | processing task, is_child = 0 16.25.847.640 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 886, t_last = 347921214809 16.25.847.714 I slot launch_slot_: id 1 | task 26802 | processing task, is_child = 0 16.25.847.804 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 898, t_last = 347921215114 16.25.847.867 I slot launch_slot_: id 2 | task 26803 | processing task, is_child = 0 16.25.847.914 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.889 16.25.847.931 I slot launch_slot_: id 3 | task 26804 | processing task, is_child = 0 16.29.420.917 I slot print_timing: id 0 | task 26801 | prompt processing, n_tokens = 941, progress = 1.00, t = 3.57 s / 263.39 tokens per second 16.29.421.097 I slot print_timing: id 1 | task 26802 | prompt processing, n_tokens = 773, progress = 0.99, t = 3.57 s / 216.37 tokens per second 16.29.421.241 I slot print_timing: id 2 | task 26803 | prompt processing, n_tokens = 773, progress = 0.99, t = 3.57 s / 216.37 tokens per second 16.29.491.072 I slot print_timing: id 3 | task 26804 | prompt eval time = 3572.76 ms / 511 tokens ( 6.99 ms per token, 143.03 tokens per second) 16.29.491.075 I slot print_timing: id 3 | task 26804 | eval time = 70.17 ms / 2 tokens ( 70.17 ms per token, 14.25 tokens per second) 16.29.491.075 I slot print_timing: id 3 | task 26804 | total time = 3642.93 ms / 513 tokens 16.29.491.076 I slot print_timing: id 3 | task 26804 | graphs reused = 25324 16.29.491.076 I slot print_timing: id 3 | task 26804 | graph reallocs = 0 / 0 (same size) / (changed size) 16.29.491.161 I slot release: id 3 | task 26804 | stop processing: n_tokens = 899, truncated = 0 16.29.513.927 I slot print_timing: id 0 | task 26801 | prompt eval time = 3642.14 ms / 945 tokens ( 3.85 ms per token, 259.46 tokens per second) 16.29.513.930 I slot print_timing: id 0 | task 26801 | eval time = 23.85 ms / 2 tokens ( 23.85 ms per token, 41.93 tokens per second) 16.29.513.930 I slot print_timing: id 0 | task 26801 | total time = 3665.99 ms / 947 tokens 16.29.513.931 I slot print_timing: id 0 | task 26801 | graphs reused = 25324 16.29.513.931 I slot print_timing: id 0 | task 26801 | graph reallocs = 0 / 0 (same size) / (changed size) 16.29.513.978 I slot release: id 0 | task 26801 | stop processing: n_tokens = 946, truncated = 0 16.29.514.263 I slot print_timing: id 1 | task 26802 | prompt eval time = 3642.36 ms / 777 tokens ( 4.69 ms per token, 213.32 tokens per second) 16.29.514.269 I slot print_timing: id 1 | task 26802 | eval time = 23.89 ms / 2 tokens ( 23.89 ms per token, 41.86 tokens per second) 16.29.514.270 I slot print_timing: id 1 | task 26802 | total time = 3666.25 ms / 779 tokens 16.29.514.270 I slot print_timing: id 1 | task 26802 | graphs reused = 25324 16.29.514.270 I slot print_timing: id 1 | task 26802 | graph reallocs = 0 / 0 (same size) / (changed size) 16.29.514.317 I slot release: id 1 | task 26802 | stop processing: n_tokens = 778, truncated = 0 16.29.514.599 I slot print_timing: id 2 | task 26803 | prompt eval time = 3642.69 ms / 777 tokens ( 4.69 ms per token, 213.30 tokens per second) 16.29.514.602 I slot print_timing: id 2 | task 26803 | eval time = 23.84 ms / 2 tokens ( 23.84 ms per token, 41.95 tokens per second) 16.29.514.602 I slot print_timing: id 2 | task 26803 | total time = 3666.53 ms / 779 tokens 16.29.514.602 I slot print_timing: id 2 | task 26803 | graphs reused = 25324 16.29.514.603 I slot print_timing: id 2 | task 26803 | graph reallocs = 0 / 0 (same size) / (changed size) 16.29.514.642 I slot release: id 2 | task 26803 | stop processing: n_tokens = 778, truncated = 0 16.29.514.646 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.871 16.29.514.669 I slot launch_slot_: id 0 | task 26809 | processing task, is_child = 0 16.29.519.978 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 347924873131 16.29.520.054 I slot launch_slot_: id 3 | task 26810 | processing task, is_child = 0 16.30.070.707 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 347924896286 16.30.070.808 I slot launch_slot_: id 1 | task 26812 | processing task, is_child = 0 16.30.070.853 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 347924896611 16.30.070.915 I slot launch_slot_: id 2 | task 26813 | processing task, is_child = 0 16.33.533.491 I slot print_timing: id 0 | task 26809 | prompt eval time = 2820.38 ms / 494 tokens ( 5.71 ms per token, 175.15 tokens per second) 16.33.533.494 I slot print_timing: id 0 | task 26809 | eval time = 1192.96 ms / 2 tokens ( 1192.96 ms per token, 0.84 tokens per second) 16.33.533.495 I slot print_timing: id 0 | task 26809 | total time = 4013.34 ms / 496 tokens 16.33.533.495 I slot print_timing: id 0 | task 26809 | graphs reused = 25325 16.33.533.496 I slot print_timing: id 0 | task 26809 | graph reallocs = 0 / 0 (same size) / (changed size) 16.33.533.550 I slot release: id 0 | task 26809 | stop processing: n_tokens = 924, truncated = 0 16.33.533.928 I slot print_timing: id 1 | task 26812 | prompt processing, n_tokens = 876, progress = 1.00, t = 3.01 s / 291.29 tokens per second 16.33.534.121 I slot print_timing: id 2 | task 26813 | prompt processing, n_tokens = 925, progress = 1.00, t = 3.01 s / 307.59 tokens per second 16.33.587.331 I slot print_timing: id 3 | task 26810 | prompt eval time = 4013.67 ms / 912 tokens ( 4.40 ms per token, 227.22 tokens per second) 16.33.587.335 I slot print_timing: id 3 | task 26810 | eval time = 53.41 ms / 2 tokens ( 53.41 ms per token, 18.72 tokens per second) 16.33.587.336 I slot print_timing: id 3 | task 26810 | total time = 4067.08 ms / 914 tokens 16.33.587.336 I slot print_timing: id 3 | task 26810 | graphs reused = 25325 16.33.587.336 I slot print_timing: id 3 | task 26810 | graph reallocs = 0 / 0 (same size) / (changed size) 16.33.587.396 I slot release: id 3 | task 26810 | stop processing: n_tokens = 913, truncated = 0 16.33.587.402 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.891 (> 0.100 thold), f_keep = 0.863 16.33.587.432 I slot launch_slot_: id 3 | task 26817 | processing task, is_child = 0 16.34.157.417 I slot print_timing: id 1 | task 26812 | prompt eval time = 3060.78 ms / 880 tokens ( 3.48 ms per token, 287.51 tokens per second) 16.34.157.420 I slot print_timing: id 1 | task 26812 | eval time = 570.82 ms / 2 tokens ( 570.82 ms per token, 1.75 tokens per second) 16.34.157.421 I slot print_timing: id 1 | task 26812 | total time = 3631.59 ms / 882 tokens 16.34.157.421 I slot print_timing: id 1 | task 26812 | graphs reused = 25325 16.34.157.422 I slot print_timing: id 1 | task 26812 | graph reallocs = 0 / 0 (same size) / (changed size) 16.34.157.474 I slot release: id 1 | task 26812 | stop processing: n_tokens = 881, truncated = 0 16.34.157.844 I slot print_timing: id 2 | task 26813 | prompt eval time = 3061.14 ms / 929 tokens ( 3.30 ms per token, 303.48 tokens per second) 16.34.157.847 I slot print_timing: id 2 | task 26813 | eval time = 570.82 ms / 2 tokens ( 570.82 ms per token, 1.75 tokens per second) 16.34.157.847 I slot print_timing: id 2 | task 26813 | total time = 3631.97 ms / 931 tokens 16.34.157.847 I slot print_timing: id 2 | task 26813 | graphs reused = 25325 16.34.157.848 I slot print_timing: id 2 | task 26813 | graph reallocs = 0 / 0 (same size) / (changed size) 16.34.157.888 I slot release: id 2 | task 26813 | stop processing: n_tokens = 930, truncated = 0 16.34.157.893 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.894 16.34.157.920 I slot launch_slot_: id 1 | task 26819 | processing task, is_child = 0 16.34.203.132 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 924, t_last = 347928915520 16.34.203.218 I slot launch_slot_: id 0 | task 26821 | processing task, is_child = 0 16.34.203.267 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 930, t_last = 347929539857 16.34.203.331 I slot launch_slot_: id 2 | task 26822 | processing task, is_child = 0 16.36.142.124 I slot print_timing: id 3 | task 26817 | prompt eval time = 613.70 ms / 488 tokens ( 1.26 ms per token, 795.17 tokens per second) 16.36.142.130 I slot print_timing: id 3 | task 26817 | eval time = 1938.99 ms / 2 tokens ( 1938.99 ms per token, 0.52 tokens per second) 16.36.142.130 I slot print_timing: id 3 | task 26817 | total time = 2552.69 ms / 490 tokens 16.36.142.131 I slot print_timing: id 3 | task 26817 | graphs reused = 25325 16.36.142.131 I slot print_timing: id 3 | task 26817 | graph reallocs = 0 / 0 (same size) / (changed size) 16.36.142.193 I slot release: id 3 | task 26817 | stop processing: n_tokens = 885, truncated = 0 16.37.319.941 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 885, t_last = 347931524163 16.37.322.669 I slot launch_slot_: id 3 | task 26825 | processing task, is_child = 0 16.37.322.695 I slot print_timing: id 0 | task 26821 | prompt processing, n_tokens = 1168, progress = 1.00, t = 3.12 s / 374.81 tokens per second 16.37.322.921 I slot print_timing: id 2 | task 26822 | prompt processing, n_tokens = 866, progress = 1.00, t = 3.12 s / 277.91 tokens per second 16.38.200.155 I slot print_timing: id 1 | task 26819 | prompt eval time = 3158.44 ms / 518 tokens ( 6.10 ms per token, 164.01 tokens per second) 16.38.200.159 I slot print_timing: id 1 | task 26819 | eval time = 880.22 ms / 2 tokens ( 880.22 ms per token, 1.14 tokens per second) 16.38.200.159 I slot print_timing: id 1 | task 26819 | total time = 4038.65 ms / 520 tokens 16.38.200.160 I slot print_timing: id 1 | task 26819 | graphs reused = 25325 16.38.200.160 I slot print_timing: id 1 | task 26819 | graph reallocs = 0 / 0 (same size) / (changed size) 16.38.200.213 I slot release: id 1 | task 26819 | stop processing: n_tokens = 883, truncated = 0 16.38.798.303 I slot print_timing: id 0 | task 26821 | prompt eval time = 3996.51 ms / 1172 tokens ( 3.41 ms per token, 293.26 tokens per second) 16.38.798.308 I slot print_timing: id 0 | task 26821 | eval time = 598.45 ms / 2 tokens ( 598.45 ms per token, 1.67 tokens per second) 16.38.798.310 I slot print_timing: id 0 | task 26821 | total time = 4594.97 ms / 1174 tokens 16.38.798.310 I slot print_timing: id 0 | task 26821 | graphs reused = 25325 16.38.798.310 I slot print_timing: id 0 | task 26821 | graph reallocs = 0 / 0 (same size) / (changed size) 16.38.798.371 I slot release: id 0 | task 26821 | stop processing: n_tokens = 1173, truncated = 0 16.38.798.681 I slot print_timing: id 2 | task 26822 | prompt eval time = 3997.25 ms / 870 tokens ( 4.59 ms per token, 217.65 tokens per second) 16.38.798.684 I slot print_timing: id 2 | task 26822 | eval time = 597.99 ms / 2 tokens ( 597.99 ms per token, 1.67 tokens per second) 16.38.798.684 I slot print_timing: id 2 | task 26822 | total time = 4595.24 ms / 872 tokens 16.38.798.685 I slot print_timing: id 2 | task 26822 | graphs reused = 25325 16.38.798.685 I slot print_timing: id 2 | task 26822 | graph reallocs = 0 / 0 (same size) / (changed size) 16.38.798.727 I slot release: id 2 | task 26822 | stop processing: n_tokens = 871, truncated = 0 16.38.798.732 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.835 (> 0.100 thold), f_keep = 0.883 16.38.798.760 I slot launch_slot_: id 0 | task 26828 | processing task, is_child = 0 16.39.009.420 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 347933582182 16.39.009.511 I slot launch_slot_: id 1 | task 26830 | processing task, is_child = 0 16.39.009.558 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 347934180696 16.39.009.628 I slot launch_slot_: id 2 | task 26831 | processing task, is_child = 0 16.41.282.830 I slot print_timing: id 3 | task 26825 | prompt eval time = 1686.30 ms / 1179 tokens ( 1.43 ms per token, 699.16 tokens per second) 16.41.282.834 I slot print_timing: id 3 | task 26825 | eval time = 2273.41 ms / 2 tokens ( 2273.41 ms per token, 0.44 tokens per second) 16.41.282.834 I slot print_timing: id 3 | task 26825 | total time = 3959.71 ms / 1181 tokens 16.41.282.835 I slot print_timing: id 3 | task 26825 | graphs reused = 25325 16.41.282.835 I slot print_timing: id 3 | task 26825 | graph reallocs = 0 / 0 (same size) / (changed size) 16.41.282.900 I slot release: id 3 | task 26825 | stop processing: n_tokens = 1180, truncated = 0 16.43.717.521 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1180, t_last = 347936664870 16.43.721.308 I slot launch_slot_: id 3 | task 26834 | processing task, is_child = 0 16.43.721.342 I slot print_timing: id 1 | task 26830 | prompt processing, n_tokens = 1983, progress = 0.79, t = 4.71 s / 421.25 tokens per second 16.46.282.103 I slot print_timing: id 0 | task 26828 | prompt eval time = 4913.62 ms / 584 tokens ( 8.41 ms per token, 118.85 tokens per second) 16.46.282.106 I slot print_timing: id 0 | task 26828 | eval time = 2564.58 ms / 2 tokens ( 2564.58 ms per token, 0.39 tokens per second) 16.46.282.106 I slot print_timing: id 0 | task 26828 | total time = 7478.20 ms / 586 tokens 16.46.282.107 I slot print_timing: id 0 | task 26828 | graphs reused = 25325 16.46.282.107 I slot print_timing: id 0 | task 26828 | graph reallocs = 0 / 0 (same size) / (changed size) 16.46.282.176 I slot release: id 0 | task 26828 | stop processing: n_tokens = 1241, truncated = 0 16.46.282.192 I slot print_timing: id 1 | task 26830 | prompt processing, n_tokens = 2495, progress = 1.00, t = 7.27 s / 343.09 tokens per second 16.46.282.578 I slot print_timing: id 2 | task 26831 | prompt processing, n_tokens = 2076, progress = 0.80, t = 5.00 s / 415.31 tokens per second 16.48.326.706 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1241, t_last = 347941664146 16.48.330.814 I slot launch_slot_: id 0 | task 26837 | processing task, is_child = 0 16.50.617.184 I slot print_timing: id 1 | task 26830 | prompt eval time = 9317.02 ms / 2499 tokens ( 3.73 ms per token, 268.22 tokens per second) 16.50.617.188 I slot print_timing: id 1 | task 26830 | eval time = 2290.48 ms / 2 tokens ( 2290.48 ms per token, 0.44 tokens per second) 16.50.617.188 I slot print_timing: id 1 | task 26830 | total time = 11607.50 ms / 2501 tokens 16.50.617.189 I slot print_timing: id 1 | task 26830 | graphs reused = 25325 16.50.617.189 I slot print_timing: id 1 | task 26830 | graph reallocs = 0 / 0 (same size) / (changed size) 16.50.617.327 I slot release: id 1 | task 26830 | stop processing: n_tokens = 2500, truncated = 0 16.50.617.351 I slot print_timing: id 2 | task 26831 | prompt processing, n_tokens = 2588, progress = 1.00, t = 7.04 s / 367.45 tokens per second 16.50.617.754 I slot print_timing: id 3 | task 26834 | prompt processing, n_tokens = 2230, progress = 0.81, t = 4.60 s / 484.27 tokens per second 16.51.420.073 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2500, t_last = 347945999296 16.51.427.611 I slot launch_slot_: id 1 | task 26840 | processing task, is_child = 0 16.51.427.622 I slot print_timing: id 0 | task 26837 | prompt processing, n_tokens = 2126, progress = 0.80, t = 3.09 s / 688.27 tokens per second 16.51.427.860 I slot print_timing: id 3 | task 26834 | prompt processing, n_tokens = 2742, progress = 1.00, t = 7.70 s / 356.18 tokens per second 16.53.482.603 I slot print_timing: id 2 | task 26831 | prompt eval time = 10136.92 ms / 2592 tokens ( 3.91 ms per token, 255.70 tokens per second) 16.53.482.606 I slot print_timing: id 2 | task 26831 | eval time = 2062.54 ms / 2 tokens ( 2062.54 ms per token, 0.48 tokens per second) 16.53.482.607 I slot print_timing: id 2 | task 26831 | total time = 12199.47 ms / 2594 tokens 16.53.482.607 I slot print_timing: id 2 | task 26831 | graphs reused = 25325 16.53.482.607 I slot print_timing: id 2 | task 26831 | graph reallocs = 0 / 0 (same size) / (changed size) 16.53.482.741 I slot release: id 2 | task 26831 | stop processing: n_tokens = 2593, truncated = 0 16.53.483.102 I slot print_timing: id 0 | task 26837 | prompt processing, n_tokens = 2638, progress = 1.00, t = 5.15 s / 512.09 tokens per second 16.54.109.246 I slot print_timing: id 3 | task 26834 | prompt eval time = 9761.64 ms / 2746 tokens ( 3.55 ms per token, 281.31 tokens per second) 16.54.109.248 I slot print_timing: id 3 | task 26834 | eval time = 626.15 ms / 2 tokens ( 626.15 ms per token, 1.60 tokens per second) 16.54.109.249 I slot print_timing: id 3 | task 26834 | total time = 10387.79 ms / 2748 tokens 16.54.109.249 I slot print_timing: id 3 | task 26834 | graphs reused = 25325 16.54.109.250 I slot print_timing: id 3 | task 26834 | graph reallocs = 0 / 0 (same size) / (changed size) 16.54.109.383 I slot release: id 3 | task 26834 | stop processing: n_tokens = 2747, truncated = 0 16.54.109.389 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2593, t_last = 347948864710 16.54.116.558 I slot launch_slot_: id 2 | task 26843 | processing task, is_child = 0 16.54.122.189 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2747, t_last = 347949491353 16.54.122.323 I slot launch_slot_: id 3 | task 26844 | processing task, is_child = 0 16.56.522.096 I slot print_timing: id 0 | task 26837 | prompt eval time = 5778.08 ms / 2642 tokens ( 2.19 ms per token, 457.25 tokens per second) 16.56.522.098 I slot print_timing: id 0 | task 26837 | eval time = 2413.15 ms / 2 tokens ( 2413.15 ms per token, 0.41 tokens per second) 16.56.522.103 I slot print_timing: id 0 | task 26837 | total time = 8191.24 ms / 2644 tokens 16.56.522.111 I slot print_timing: id 0 | task 26837 | graphs reused = 25325 16.56.522.112 I slot print_timing: id 0 | task 26837 | graph reallocs = 0 / 0 (same size) / (changed size) 16.56.522.242 I slot release: id 0 | task 26837 | stop processing: n_tokens = 2643, truncated = 0 16.58.012.963 I slot print_timing: id 1 | task 26840 | prompt eval time = 5094.93 ms / 1759 tokens ( 2.90 ms per token, 345.25 tokens per second) 16.58.012.965 I slot print_timing: id 1 | task 26840 | eval time = 1490.36 ms / 2 tokens ( 1490.36 ms per token, 0.67 tokens per second) 16.58.012.966 I slot print_timing: id 1 | task 26840 | total time = 6585.29 ms / 1761 tokens 16.58.012.966 I slot print_timing: id 1 | task 26840 | graphs reused = 25325 16.58.012.967 I slot print_timing: id 1 | task 26840 | graph reallocs = 0 / 0 (same size) / (changed size) 16.58.013.067 I slot release: id 1 | task 26840 | stop processing: n_tokens = 1760, truncated = 0 16.58.013.077 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.798 (> 0.100 thold), f_keep = 0.830 16.58.013.114 I slot launch_slot_: id 1 | task 26847 | processing task, is_child = 0 16.58.019.971 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2643, t_last = 347951904211 16.58.020.123 I slot launch_slot_: id 0 | task 26848 | processing task, is_child = 0 16.58.020.432 I slot print_timing: id 2 | task 26843 | prompt processing, n_tokens = 1807, progress = 1.00, t = 3.89 s / 464.52 tokens per second 16.58.020.719 I slot print_timing: id 3 | task 26844 | prompt processing, n_tokens = 1489, progress = 0.74, t = 3.89 s / 382.79 tokens per second 17.00.409.299 I slot print_timing: id 3 | task 26844 | prompt processing, n_tokens = 2001, progress = 1.00, t = 6.29 s / 318.32 tokens per second 17.01.603.069 I slot print_timing: id 2 | task 26843 | prompt eval time = 6286.60 ms / 1811 tokens ( 3.47 ms per token, 288.07 tokens per second) 17.01.603.072 I slot print_timing: id 2 | task 26843 | eval time = 1193.86 ms / 2 tokens ( 1193.86 ms per token, 0.84 tokens per second) 17.01.603.073 I slot print_timing: id 2 | task 26843 | total time = 7480.46 ms / 1813 tokens 17.01.603.073 I slot print_timing: id 2 | task 26843 | graphs reused = 25325 17.01.603.074 I slot print_timing: id 2 | task 26843 | graph reallocs = 0 / 0 (same size) / (changed size) 17.01.603.176 I slot release: id 2 | task 26843 | stop processing: n_tokens = 1812, truncated = 0 17.01.603.581 I slot print_timing: id 0 | task 26848 | prompt processing, n_tokens = 1904, progress = 1.00, t = 3.58 s / 531.46 tokens per second 17.01.603.971 I slot print_timing: id 1 | task 26847 | prompt processing, n_tokens = 582, progress = 1.00, t = 3.58 s / 162.46 tokens per second 17.01.658.421 I slot print_timing: id 3 | task 26844 | prompt eval time = 7480.78 ms / 2005 tokens ( 3.73 ms per token, 268.02 tokens per second) 17.01.658.424 I slot print_timing: id 3 | task 26844 | eval time = 54.84 ms / 2 tokens ( 54.84 ms per token, 18.23 tokens per second) 17.01.658.424 I slot print_timing: id 3 | task 26844 | total time = 7535.63 ms / 2007 tokens 17.01.658.424 I slot print_timing: id 3 | task 26844 | graphs reused = 25325 17.01.658.425 I slot print_timing: id 3 | task 26844 | graph reallocs = 0 / 0 (same size) / (changed size) 17.01.658.547 I slot release: id 3 | task 26844 | stop processing: n_tokens = 2006, truncated = 0 17.01.658.555 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.836 (> 0.100 thold), f_keep = 0.806 17.01.658.596 I slot launch_slot_: id 2 | task 26852 | processing task, is_child = 0 17.02.198.293 I slot print_timing: id 0 | task 26848 | prompt eval time = 3637.57 ms / 1908 tokens ( 1.91 ms per token, 524.53 tokens per second) 17.02.198.295 I slot print_timing: id 0 | task 26848 | eval time = 540.58 ms / 2 tokens ( 540.58 ms per token, 1.85 tokens per second) 17.02.198.296 I slot print_timing: id 0 | task 26848 | total time = 4178.15 ms / 1910 tokens 17.02.198.296 I slot print_timing: id 0 | task 26848 | graphs reused = 25325 17.02.198.296 I slot print_timing: id 0 | task 26848 | graph reallocs = 0 / 0 (same size) / (changed size) 17.02.198.404 I slot release: id 0 | task 26848 | stop processing: n_tokens = 1909, truncated = 0 17.02.198.825 I slot print_timing: id 1 | task 26847 | prompt eval time = 3637.76 ms / 586 tokens ( 6.21 ms per token, 161.09 tokens per second) 17.02.198.828 I slot print_timing: id 1 | task 26847 | eval time = 540.73 ms / 2 tokens ( 540.73 ms per token, 1.85 tokens per second) 17.02.198.828 I slot print_timing: id 1 | task 26847 | total time = 4178.49 ms / 588 tokens 17.02.198.828 I slot print_timing: id 1 | task 26847 | graphs reused = 25325 17.02.198.829 I slot print_timing: id 1 | task 26847 | graph reallocs = 0 / 0 (same size) / (changed size) 17.02.198.912 I slot release: id 1 | task 26847 | stop processing: n_tokens = 1830, truncated = 0 17.02.198.920 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2006, t_last = 347957040516 17.02.199.092 I slot launch_slot_: id 3 | task 26854 | processing task, is_child = 0 17.02.208.601 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1909, t_last = 347957580374 17.02.208.734 I slot launch_slot_: id 0 | task 26855 | processing task, is_child = 0 17.02.208.817 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1830, t_last = 347957580882 17.02.208.912 I slot launch_slot_: id 1 | task 26856 | processing task, is_child = 0 17.04.770.142 I slot print_timing: id 2 | task 26852 | prompt eval time = 1416.44 ms / 452 tokens ( 3.13 ms per token, 319.11 tokens per second) 17.04.770.147 I slot print_timing: id 2 | task 26852 | eval time = 1690.78 ms / 2 tokens ( 1690.78 ms per token, 0.59 tokens per second) 17.04.770.147 I slot print_timing: id 2 | task 26852 | total time = 3107.22 ms / 454 tokens 17.04.770.148 I slot print_timing: id 2 | task 26852 | graphs reused = 25325 17.04.770.148 I slot print_timing: id 2 | task 26852 | graph reallocs = 0 / 0 (same size) / (changed size) 17.04.770.265 I slot release: id 2 | task 26852 | stop processing: n_tokens = 1748, truncated = 0 17.04.834.953 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1748, t_last = 347960152235 17.04.838.720 I slot launch_slot_: id 2 | task 26860 | processing task, is_child = 0 17.05.158.362 I slot print_timing: id 0 | task 26855 | prompt eval time = 2625.23 ms / 733 tokens ( 3.58 ms per token, 279.21 tokens per second) 17.05.158.365 I slot print_timing: id 0 | task 26855 | eval time = 324.21 ms / 2 tokens ( 324.21 ms per token, 3.08 tokens per second) 17.05.158.365 I slot print_timing: id 0 | task 26855 | total time = 2949.44 ms / 735 tokens 17.05.158.366 I slot print_timing: id 0 | task 26855 | graphs reused = 25325 17.05.158.366 I slot print_timing: id 0 | task 26855 | graph reallocs = 0 / 0 (same size) / (changed size) 17.05.158.414 I slot release: id 0 | task 26855 | stop processing: n_tokens = 734, truncated = 0 17.05.158.744 I slot print_timing: id 1 | task 26856 | prompt eval time = 2625.46 ms / 744 tokens ( 3.53 ms per token, 283.38 tokens per second) 17.05.158.746 I slot print_timing: id 1 | task 26856 | eval time = 324.22 ms / 2 tokens ( 324.22 ms per token, 3.08 tokens per second) 17.05.158.747 I slot print_timing: id 1 | task 26856 | total time = 2949.68 ms / 746 tokens 17.05.158.747 I slot print_timing: id 1 | task 26856 | graphs reused = 25325 17.05.158.747 I slot print_timing: id 1 | task 26856 | graph reallocs = 0 / 0 (same size) / (changed size) 17.05.158.789 I slot release: id 1 | task 26856 | stop processing: n_tokens = 745, truncated = 0 17.05.159.127 I slot print_timing: id 3 | task 26854 | prompt eval time = 2625.51 ms / 711 tokens ( 3.69 ms per token, 270.80 tokens per second) 17.05.159.131 I slot print_timing: id 3 | task 26854 | eval time = 324.18 ms / 2 tokens ( 324.18 ms per token, 3.08 tokens per second) 17.05.159.132 I slot print_timing: id 3 | task 26854 | total time = 2949.68 ms / 713 tokens 17.05.159.132 I slot print_timing: id 3 | task 26854 | graphs reused = 25325 17.05.159.133 I slot print_timing: id 3 | task 26854 | graph reallocs = 0 / 0 (same size) / (changed size) 17.05.159.170 I slot release: id 3 | task 26854 | stop processing: n_tokens = 712, truncated = 0 17.05.745.175 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 734, t_last = 347960540383 17.05.747.441 I slot launch_slot_: id 0 | task 26864 | processing task, is_child = 0 17.05.751.111 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 745, t_last = 347960540758 17.05.751.177 I slot launch_slot_: id 1 | task 26865 | processing task, is_child = 0 17.05.751.220 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.864 (> 0.100 thold), f_keep = 0.881 17.05.751.235 I slot launch_slot_: id 3 | task 26866 | processing task, is_child = 0 17.06.857.066 I slot print_timing: id 2 | task 26860 | prompt eval time = 906.44 ms / 710 tokens ( 1.28 ms per token, 783.28 tokens per second) 17.06.857.070 I slot print_timing: id 2 | task 26860 | eval time = 1111.89 ms / 2 tokens ( 1111.89 ms per token, 0.90 tokens per second) 17.06.857.070 I slot print_timing: id 2 | task 26860 | total time = 2018.33 ms / 712 tokens 17.06.857.071 I slot print_timing: id 2 | task 26860 | graphs reused = 25325 17.06.857.071 I slot print_timing: id 2 | task 26860 | graph reallocs = 0 / 0 (same size) / (changed size) 17.06.857.116 I slot release: id 2 | task 26860 | stop processing: n_tokens = 711, truncated = 0 17.07.984.910 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 347962239085 17.08.542.375 I slot launch_slot_: id 2 | task 26869 | processing task, is_child = 0 17.09.551.589 I slot print_timing: id 0 | task 26864 | prompt eval time = 3204.42 ms / 789 tokens ( 4.06 ms per token, 246.22 tokens per second) 17.09.551.592 I slot print_timing: id 0 | task 26864 | eval time = 595.93 ms / 2 tokens ( 595.93 ms per token, 1.68 tokens per second) 17.09.551.593 I slot print_timing: id 0 | task 26864 | total time = 3800.35 ms / 791 tokens 17.09.551.593 I slot print_timing: id 0 | task 26864 | graphs reused = 25325 17.09.551.594 I slot print_timing: id 0 | task 26864 | graph reallocs = 0 / 0 (same size) / (changed size) 17.09.551.644 I slot release: id 0 | task 26864 | stop processing: n_tokens = 790, truncated = 0 17.09.551.954 I slot print_timing: id 1 | task 26865 | prompt eval time = 3204.69 ms / 1040 tokens ( 3.08 ms per token, 324.52 tokens per second) 17.09.551.956 I slot print_timing: id 1 | task 26865 | eval time = 595.97 ms / 2 tokens ( 595.97 ms per token, 1.68 tokens per second) 17.09.551.957 I slot print_timing: id 1 | task 26865 | total time = 3800.66 ms / 1042 tokens 17.09.551.962 I slot print_timing: id 1 | task 26865 | graphs reused = 25325 17.09.551.962 I slot print_timing: id 1 | task 26865 | graph reallocs = 0 / 0 (same size) / (changed size) 17.09.552.026 I slot release: id 1 | task 26865 | stop processing: n_tokens = 1041, truncated = 0 17.09.552.328 I slot print_timing: id 3 | task 26866 | prompt eval time = 3204.95 ms / 531 tokens ( 6.04 ms per token, 165.68 tokens per second) 17.09.552.330 I slot print_timing: id 3 | task 26866 | eval time = 596.03 ms / 2 tokens ( 596.03 ms per token, 1.68 tokens per second) 17.09.552.331 I slot print_timing: id 3 | task 26866 | total time = 3800.98 ms / 533 tokens 17.09.552.331 I slot print_timing: id 3 | task 26866 | graphs reused = 25325 17.09.552.331 I slot print_timing: id 3 | task 26866 | graph reallocs = 0 / 0 (same size) / (changed size) 17.09.552.366 I slot release: id 3 | task 26866 | stop processing: n_tokens = 727, truncated = 0 17.09.578.685 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 347964933613 17.09.580.368 I slot launch_slot_: id 0 | task 26873 | processing task, is_child = 0 17.09.584.013 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1041, t_last = 347964933997 17.09.584.102 I slot launch_slot_: id 1 | task 26874 | processing task, is_child = 0 17.09.584.145 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 347964934335 17.09.584.209 I slot launch_slot_: id 3 | task 26875 | processing task, is_child = 0 17.10.714.922 I slot print_timing: id 2 | task 26869 | prompt eval time = 1035.97 ms / 784 tokens ( 1.32 ms per token, 756.78 tokens per second) 17.10.714.924 I slot print_timing: id 2 | task 26869 | eval time = 1136.24 ms / 2 tokens ( 1136.24 ms per token, 0.88 tokens per second) 17.10.714.924 I slot print_timing: id 2 | task 26869 | total time = 2172.21 ms / 786 tokens 17.10.714.925 I slot print_timing: id 2 | task 26869 | graphs reused = 25325 17.10.714.926 I slot print_timing: id 2 | task 26869 | graph reallocs = 0 / 0 (same size) / (changed size) 17.10.714.973 I slot release: id 2 | task 26869 | stop processing: n_tokens = 785, truncated = 0 17.11.831.859 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 785, t_last = 347966096942 17.12.388.037 I slot launch_slot_: id 2 | task 26878 | processing task, is_child = 0 17.13.485.132 I slot print_timing: id 0 | task 26873 | prompt eval time = 3305.79 ms / 831 tokens ( 3.98 ms per token, 251.38 tokens per second) 17.13.485.135 I slot print_timing: id 0 | task 26873 | eval time = 595.12 ms / 2 tokens ( 595.12 ms per token, 1.68 tokens per second) 17.13.485.135 I slot print_timing: id 0 | task 26873 | total time = 3900.91 ms / 833 tokens 17.13.485.136 I slot print_timing: id 0 | task 26873 | graphs reused = 25325 17.13.485.136 I slot print_timing: id 0 | task 26873 | graph reallocs = 0 / 0 (same size) / (changed size) 17.13.485.189 I slot release: id 0 | task 26873 | stop processing: n_tokens = 832, truncated = 0 17.13.485.477 I slot print_timing: id 1 | task 26874 | prompt eval time = 3306.03 ms / 825 tokens ( 4.01 ms per token, 249.54 tokens per second) 17.13.485.484 I slot print_timing: id 1 | task 26874 | eval time = 595.17 ms / 2 tokens ( 595.17 ms per token, 1.68 tokens per second) 17.13.485.485 I slot print_timing: id 1 | task 26874 | total time = 3901.19 ms / 827 tokens 17.13.485.485 I slot print_timing: id 1 | task 26874 | graphs reused = 25325 17.13.485.486 I slot print_timing: id 1 | task 26874 | graph reallocs = 0 / 0 (same size) / (changed size) 17.13.485.523 I slot release: id 1 | task 26874 | stop processing: n_tokens = 826, truncated = 0 17.13.485.824 I slot print_timing: id 3 | task 26875 | prompt eval time = 3306.27 ms / 776 tokens ( 4.26 ms per token, 234.71 tokens per second) 17.13.485.827 I slot print_timing: id 3 | task 26875 | eval time = 595.20 ms / 2 tokens ( 595.20 ms per token, 1.68 tokens per second) 17.13.485.828 I slot print_timing: id 3 | task 26875 | total time = 3901.47 ms / 778 tokens 17.13.485.828 I slot print_timing: id 3 | task 26875 | graphs reused = 25325 17.13.485.828 I slot print_timing: id 3 | task 26875 | graph reallocs = 0 / 0 (same size) / (changed size) 17.13.485.875 I slot release: id 3 | task 26875 | stop processing: n_tokens = 777, truncated = 0 17.13.511.794 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.892 17.13.511.820 I slot launch_slot_: id 1 | task 26882 | processing task, is_child = 0 17.13.515.073 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.885 17.13.515.097 I slot launch_slot_: id 0 | task 26883 | processing task, is_child = 0 17.13.515.139 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 777, t_last = 347968867844 17.13.515.208 I slot launch_slot_: id 3 | task 26884 | processing task, is_child = 0 17.14.068.516 I slot print_timing: id 2 | task 26878 | prompt eval time = 1123.41 ms / 885 tokens ( 1.27 ms per token, 787.78 tokens per second) 17.14.068.518 I slot print_timing: id 2 | task 26878 | eval time = 556.72 ms / 2 tokens ( 556.72 ms per token, 1.80 tokens per second) 17.14.068.519 I slot print_timing: id 2 | task 26878 | total time = 1680.14 ms / 887 tokens 17.14.068.520 I slot print_timing: id 2 | task 26878 | graphs reused = 25325 17.14.068.520 I slot print_timing: id 2 | task 26878 | graph reallocs = 0 / 0 (same size) / (changed size) 17.14.068.572 I slot release: id 2 | task 26878 | stop processing: n_tokens = 886, truncated = 0 17.15.190.728 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 886, t_last = 347969450541 17.15.746.459 I slot launch_slot_: id 2 | task 26887 | processing task, is_child = 0 17.16.760.295 I slot print_timing: id 0 | task 26883 | prompt eval time = 2649.26 ms / 533 tokens ( 4.97 ms per token, 201.19 tokens per second) 17.16.760.298 I slot print_timing: id 0 | task 26883 | eval time = 595.82 ms / 2 tokens ( 595.82 ms per token, 1.68 tokens per second) 17.16.760.299 I slot print_timing: id 0 | task 26883 | total time = 3245.08 ms / 535 tokens 17.16.760.300 I slot print_timing: id 0 | task 26883 | graphs reused = 25325 17.16.760.300 I slot print_timing: id 0 | task 26883 | graph reallocs = 0 / 0 (same size) / (changed size) 17.16.760.359 I slot release: id 0 | task 26883 | stop processing: n_tokens = 849, truncated = 0 17.16.760.685 I slot print_timing: id 1 | task 26882 | prompt eval time = 2649.57 ms / 583 tokens ( 4.54 ms per token, 220.04 tokens per second) 17.16.760.688 I slot print_timing: id 1 | task 26882 | eval time = 595.81 ms / 2 tokens ( 595.81 ms per token, 1.68 tokens per second) 17.16.760.688 I slot print_timing: id 1 | task 26882 | total time = 3245.37 ms / 585 tokens 17.16.760.688 I slot print_timing: id 1 | task 26882 | graphs reused = 25325 17.16.760.689 I slot print_timing: id 1 | task 26882 | graph reallocs = 0 / 0 (same size) / (changed size) 17.16.760.728 I slot release: id 1 | task 26882 | stop processing: n_tokens = 893, truncated = 0 17.16.761.025 I slot print_timing: id 3 | task 26884 | prompt eval time = 2649.79 ms / 677 tokens ( 3.91 ms per token, 255.49 tokens per second) 17.16.761.028 I slot print_timing: id 3 | task 26884 | eval time = 595.85 ms / 2 tokens ( 595.85 ms per token, 1.68 tokens per second) 17.16.761.029 I slot print_timing: id 3 | task 26884 | total time = 3245.64 ms / 679 tokens 17.16.761.029 I slot print_timing: id 3 | task 26884 | graphs reused = 25325 17.16.761.029 I slot print_timing: id 3 | task 26884 | graph reallocs = 0 / 0 (same size) / (changed size) 17.16.761.085 I slot release: id 3 | task 26884 | stop processing: n_tokens = 678, truncated = 0 17.16.786.928 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 849, t_last = 347972142328 17.16.788.803 I slot launch_slot_: id 0 | task 26891 | processing task, is_child = 0 17.16.791.824 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 893, t_last = 347972142697 17.16.791.900 I slot launch_slot_: id 1 | task 26892 | processing task, is_child = 0 17.16.791.944 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 347972143054 17.16.792.006 I slot launch_slot_: id 3 | task 26893 | processing task, is_child = 0 17.17.777.266 I slot print_timing: id 2 | task 26887 | prompt eval time = 1040.14 ms / 792 tokens ( 1.31 ms per token, 761.43 tokens per second) 17.17.777.271 I slot print_timing: id 2 | task 26887 | eval time = 990.34 ms / 2 tokens ( 990.34 ms per token, 1.01 tokens per second) 17.17.777.272 I slot print_timing: id 2 | task 26887 | total time = 2030.48 ms / 794 tokens 17.17.777.272 I slot print_timing: id 2 | task 26887 | graphs reused = 25325 17.17.777.273 I slot print_timing: id 2 | task 26887 | graph reallocs = 0 / 0 (same size) / (changed size) 17.17.777.363 I slot release: id 2 | task 26887 | stop processing: n_tokens = 793, truncated = 0 17.18.903.660 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 793, t_last = 347973159339 17.19.460.833 I slot launch_slot_: id 2 | task 26896 | processing task, is_child = 0 17.20.391.163 I slot print_timing: id 0 | task 26891 | prompt eval time = 3006.80 ms / 719 tokens ( 4.18 ms per token, 239.12 tokens per second) 17.20.391.165 I slot print_timing: id 0 | task 26891 | eval time = 592.34 ms / 2 tokens ( 592.34 ms per token, 1.69 tokens per second) 17.20.391.166 I slot print_timing: id 0 | task 26891 | total time = 3599.14 ms / 721 tokens 17.20.391.167 I slot print_timing: id 0 | task 26891 | graphs reused = 25325 17.20.391.167 I slot print_timing: id 0 | task 26891 | graph reallocs = 0 / 0 (same size) / (changed size) 17.20.391.208 I slot release: id 0 | task 26891 | stop processing: n_tokens = 720, truncated = 0 17.20.391.556 I slot print_timing: id 1 | task 26892 | prompt eval time = 3007.02 ms / 813 tokens ( 3.70 ms per token, 270.37 tokens per second) 17.20.391.559 I slot print_timing: id 1 | task 26892 | eval time = 592.43 ms / 2 tokens ( 592.43 ms per token, 1.69 tokens per second) 17.20.391.559 I slot print_timing: id 1 | task 26892 | total time = 3599.45 ms / 815 tokens 17.20.391.560 I slot print_timing: id 1 | task 26892 | graphs reused = 25325 17.20.391.560 I slot print_timing: id 1 | task 26892 | graph reallocs = 0 / 0 (same size) / (changed size) 17.20.391.603 I slot release: id 1 | task 26892 | stop processing: n_tokens = 814, truncated = 0 17.20.391.911 I slot print_timing: id 3 | task 26893 | prompt eval time = 3007.28 ms / 740 tokens ( 4.06 ms per token, 246.07 tokens per second) 17.20.391.917 I slot print_timing: id 3 | task 26893 | eval time = 592.47 ms / 2 tokens ( 592.47 ms per token, 1.69 tokens per second) 17.20.391.917 I slot print_timing: id 3 | task 26893 | total time = 3599.75 ms / 742 tokens 17.20.391.917 I slot print_timing: id 3 | task 26893 | graphs reused = 25325 17.20.391.918 I slot print_timing: id 3 | task 26893 | graph reallocs = 0 / 0 (same size) / (changed size) 17.20.391.963 I slot release: id 3 | task 26893 | stop processing: n_tokens = 741, truncated = 0 17.20.417.850 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 347975773177 17.20.419.665 I slot launch_slot_: id 0 | task 26900 | processing task, is_child = 0 17.20.422.977 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 814, t_last = 347975773572 17.20.423.048 I slot launch_slot_: id 1 | task 26901 | processing task, is_child = 0 17.20.423.090 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 347975773932 17.20.423.153 I slot launch_slot_: id 3 | task 26902 | processing task, is_child = 0 17.21.218.844 I slot print_timing: id 2 | task 26896 | prompt eval time = 956.71 ms / 694 tokens ( 1.38 ms per token, 725.40 tokens per second) 17.21.218.850 I slot print_timing: id 2 | task 26896 | eval time = 800.99 ms / 2 tokens ( 800.99 ms per token, 1.25 tokens per second) 17.21.218.850 I slot print_timing: id 2 | task 26896 | total time = 1757.71 ms / 696 tokens 17.21.218.851 I slot print_timing: id 2 | task 26896 | graphs reused = 25325 17.21.218.851 I slot print_timing: id 2 | task 26896 | graph reallocs = 0 / 0 (same size) / (changed size) 17.21.218.892 I slot release: id 2 | task 26896 | stop processing: n_tokens = 695, truncated = 0 17.22.336.797 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.881 17.22.336.839 I slot launch_slot_: id 2 | task 26905 | processing task, is_child = 0 17.23.573.599 I slot print_timing: id 0 | task 26900 | prompt eval time = 2555.93 ms / 694 tokens ( 3.68 ms per token, 271.53 tokens per second) 17.23.573.602 I slot print_timing: id 0 | task 26900 | eval time = 594.50 ms / 2 tokens ( 594.50 ms per token, 1.68 tokens per second) 17.23.573.602 I slot print_timing: id 0 | task 26900 | total time = 3150.44 ms / 696 tokens 17.23.573.603 I slot print_timing: id 0 | task 26900 | graphs reused = 25325 17.23.573.603 I slot print_timing: id 0 | task 26900 | graph reallocs = 0 / 0 (same size) / (changed size) 17.23.573.649 I slot release: id 0 | task 26900 | stop processing: n_tokens = 695, truncated = 0 17.23.573.928 I slot print_timing: id 1 | task 26901 | prompt eval time = 2556.23 ms / 718 tokens ( 3.56 ms per token, 280.88 tokens per second) 17.23.573.930 I slot print_timing: id 1 | task 26901 | eval time = 594.48 ms / 2 tokens ( 594.48 ms per token, 1.68 tokens per second) 17.23.573.930 I slot print_timing: id 1 | task 26901 | total time = 3150.71 ms / 720 tokens 17.23.573.931 I slot print_timing: id 1 | task 26901 | graphs reused = 25325 17.23.573.931 I slot print_timing: id 1 | task 26901 | graph reallocs = 0 / 0 (same size) / (changed size) 17.23.573.969 I slot release: id 1 | task 26901 | stop processing: n_tokens = 719, truncated = 0 17.23.574.258 I slot print_timing: id 3 | task 26902 | prompt eval time = 2556.59 ms / 693 tokens ( 3.69 ms per token, 271.06 tokens per second) 17.23.574.261 I slot print_timing: id 3 | task 26902 | eval time = 594.39 ms / 2 tokens ( 594.39 ms per token, 1.68 tokens per second) 17.23.574.261 I slot print_timing: id 3 | task 26902 | total time = 3150.98 ms / 695 tokens 17.23.574.261 I slot print_timing: id 3 | task 26902 | graphs reused = 25325 17.23.574.261 I slot print_timing: id 3 | task 26902 | graph reallocs = 0 / 0 (same size) / (changed size) 17.23.574.303 I slot release: id 3 | task 26902 | stop processing: n_tokens = 694, truncated = 0 17.23.600.914 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.885 17.23.600.946 I slot launch_slot_: id 3 | task 26909 | processing task, is_child = 0 17.23.604.006 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 17.23.604.030 I slot launch_slot_: id 0 | task 26910 | processing task, is_child = 0 17.23.604.069 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.851 17.23.604.085 I slot launch_slot_: id 1 | task 26911 | processing task, is_child = 0 17.25.316.597 I slot print_timing: id 2 | task 26905 | prompt eval time = 707.24 ms / 518 tokens ( 1.37 ms per token, 732.42 tokens per second) 17.25.316.602 I slot print_timing: id 2 | task 26905 | eval time = 1715.68 ms / 2 tokens ( 1715.68 ms per token, 0.58 tokens per second) 17.25.316.603 I slot print_timing: id 2 | task 26905 | total time = 2422.93 ms / 520 tokens 17.25.316.607 I slot print_timing: id 2 | task 26905 | graphs reused = 25325 17.25.316.607 I slot print_timing: id 2 | task 26905 | graph reallocs = 0 / 0 (same size) / (changed size) 17.25.316.659 I slot release: id 2 | task 26905 | stop processing: n_tokens = 697, truncated = 0 17.25.382.043 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 17.25.382.087 I slot launch_slot_: id 2 | task 26914 | processing task, is_child = 0 17.25.426.790 I slot print_timing: id 0 | task 26910 | prompt eval time = 1777.29 ms / 510 tokens ( 3.48 ms per token, 286.95 tokens per second) 17.25.426.794 I slot print_timing: id 0 | task 26910 | eval time = 45.41 ms / 2 tokens ( 45.41 ms per token, 22.02 tokens per second) 17.25.426.794 I slot print_timing: id 0 | task 26910 | total time = 1822.70 ms / 512 tokens 17.25.426.795 I slot print_timing: id 0 | task 26910 | graphs reused = 25325 17.25.426.795 I slot print_timing: id 0 | task 26910 | graph reallocs = 0 / 0 (same size) / (changed size) 17.25.426.844 I slot release: id 0 | task 26910 | stop processing: n_tokens = 689, truncated = 0 17.25.427.140 I slot print_timing: id 1 | task 26911 | prompt eval time = 1777.44 ms / 499 tokens ( 3.56 ms per token, 280.74 tokens per second) 17.25.427.143 I slot print_timing: id 1 | task 26911 | eval time = 45.48 ms / 2 tokens ( 45.48 ms per token, 21.99 tokens per second) 17.25.427.143 I slot print_timing: id 1 | task 26911 | total time = 1822.93 ms / 501 tokens 17.25.427.144 I slot print_timing: id 1 | task 26911 | graphs reused = 25325 17.25.427.144 I slot print_timing: id 1 | task 26911 | graph reallocs = 0 / 0 (same size) / (changed size) 17.25.427.178 I slot release: id 1 | task 26911 | stop processing: n_tokens = 702, truncated = 0 17.25.427.461 I slot print_timing: id 3 | task 26909 | prompt eval time = 1777.70 ms / 513 tokens ( 3.47 ms per token, 288.57 tokens per second) 17.25.427.465 I slot print_timing: id 3 | task 26909 | eval time = 45.42 ms / 2 tokens ( 45.42 ms per token, 22.02 tokens per second) 17.25.427.465 I slot print_timing: id 3 | task 26909 | total time = 1823.13 ms / 515 tokens 17.25.427.466 I slot print_timing: id 3 | task 26909 | graphs reused = 25325 17.25.427.466 I slot print_timing: id 3 | task 26909 | graph reallocs = 0 / 0 (same size) / (changed size) 17.25.427.501 I slot release: id 3 | task 26909 | stop processing: n_tokens = 691, truncated = 0 17.25.434.936 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.888 17.25.434.969 I slot launch_slot_: id 0 | task 26917 | processing task, is_child = 0 17.25.990.231 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.837 (> 0.100 thold), f_keep = 0.872 17.25.990.285 I slot launch_slot_: id 1 | task 26918 | processing task, is_child = 0 17.25.990.327 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 691, t_last = 347980809470 17.25.990.391 I slot launch_slot_: id 3 | task 26919 | processing task, is_child = 0 17.28.281.783 I slot print_timing: id 2 | task 26914 | prompt eval time = 1725.90 ms / 518 tokens ( 3.33 ms per token, 300.13 tokens per second) 17.28.281.785 I slot print_timing: id 2 | task 26914 | eval time = 1173.79 ms / 2 tokens ( 1173.79 ms per token, 0.85 tokens per second) 17.28.281.786 I slot print_timing: id 2 | task 26914 | total time = 2899.69 ms / 520 tokens 17.28.281.786 I slot print_timing: id 2 | task 26914 | graphs reused = 25325 17.28.281.787 I slot print_timing: id 2 | task 26914 | graph reallocs = 0 / 0 (same size) / (changed size) 17.28.281.829 I slot release: id 2 | task 26914 | stop processing: n_tokens = 699, truncated = 0 17.28.345.606 I slot print_timing: id 0 | task 26917 | prompt eval time = 2291.06 ms / 513 tokens ( 4.47 ms per token, 223.91 tokens per second) 17.28.345.609 I slot print_timing: id 0 | task 26917 | eval time = 64.14 ms / 2 tokens ( 64.14 ms per token, 15.59 tokens per second) 17.28.345.610 I slot print_timing: id 0 | task 26917 | total time = 2355.20 ms / 515 tokens 17.28.345.610 I slot print_timing: id 0 | task 26917 | graphs reused = 25325 17.28.345.611 I slot print_timing: id 0 | task 26917 | graph reallocs = 0 / 0 (same size) / (changed size) 17.28.345.657 I slot release: id 0 | task 26917 | stop processing: n_tokens = 692, truncated = 0 17.28.346.507 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 699, t_last = 347983663798 17.28.348.301 I slot launch_slot_: id 2 | task 26923 | processing task, is_child = 0 17.28.786.817 I slot print_timing: id 1 | task 26918 | prompt eval time = 2355.49 ms / 529 tokens ( 4.45 ms per token, 224.58 tokens per second) 17.28.786.820 I slot print_timing: id 1 | task 26918 | eval time = 440.74 ms / 2 tokens ( 440.74 ms per token, 2.27 tokens per second) 17.28.786.820 I slot print_timing: id 1 | task 26918 | total time = 2796.23 ms / 531 tokens 17.28.786.821 I slot print_timing: id 1 | task 26918 | graphs reused = 25325 17.28.786.821 I slot print_timing: id 1 | task 26918 | graph reallocs = 0 / 0 (same size) / (changed size) 17.28.786.862 I slot release: id 1 | task 26918 | stop processing: n_tokens = 732, truncated = 0 17.28.787.246 I slot print_timing: id 3 | task 26919 | prompt eval time = 2355.67 ms / 874 tokens ( 2.70 ms per token, 371.02 tokens per second) 17.28.787.249 I slot print_timing: id 3 | task 26919 | eval time = 440.74 ms / 2 tokens ( 440.74 ms per token, 2.27 tokens per second) 17.28.787.249 I slot print_timing: id 3 | task 26919 | total time = 2796.41 ms / 876 tokens 17.28.787.249 I slot print_timing: id 3 | task 26919 | graphs reused = 25325 17.28.787.250 I slot print_timing: id 3 | task 26919 | graph reallocs = 0 / 0 (same size) / (changed size) 17.28.787.301 I slot release: id 3 | task 26919 | stop processing: n_tokens = 875, truncated = 0 17.28.787.305 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 692, t_last = 347983727626 17.28.787.421 I slot launch_slot_: id 0 | task 26925 | processing task, is_child = 0 17.29.535.296 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 347984168831 17.29.535.413 I slot launch_slot_: id 1 | task 26927 | processing task, is_child = 0 17.29.535.461 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 875, t_last = 347984169270 17.29.535.527 I slot launch_slot_: id 3 | task 26928 | processing task, is_child = 0 17.32.187.191 I slot print_timing: id 0 | task 26925 | prompt processing, n_tokens = 1101, progress = 1.00, t = 3.39 s / 324.30 tokens per second 17.33.370.226 I slot print_timing: id 2 | task 26923 | prompt eval time = 3837.46 ms / 861 tokens ( 4.46 ms per token, 224.37 tokens per second) 17.33.370.229 I slot print_timing: id 2 | task 26923 | eval time = 1183.05 ms / 2 tokens ( 1183.05 ms per token, 0.85 tokens per second) 17.33.370.229 I slot print_timing: id 2 | task 26923 | total time = 5020.51 ms / 863 tokens 17.33.370.230 I slot print_timing: id 2 | task 26923 | graphs reused = 25325 17.33.370.230 I slot print_timing: id 2 | task 26923 | graph reallocs = 0 / 0 (same size) / (changed size) 17.33.370.286 I slot release: id 2 | task 26923 | stop processing: n_tokens = 862, truncated = 0 17.33.370.300 I slot print_timing: id 1 | task 26927 | prompt processing, n_tokens = 1094, progress = 1.00, t = 3.28 s / 334.00 tokens per second 17.33.370.495 I slot print_timing: id 3 | task 26928 | prompt processing, n_tokens = 1092, progress = 1.00, t = 3.28 s / 333.41 tokens per second 17.33.434.540 I slot print_timing: id 0 | task 26925 | prompt eval time = 4578.14 ms / 1105 tokens ( 4.14 ms per token, 241.36 tokens per second) 17.33.434.545 I slot print_timing: id 0 | task 26925 | eval time = 64.60 ms / 2 tokens ( 64.60 ms per token, 15.48 tokens per second) 17.33.434.546 I slot print_timing: id 0 | task 26925 | total time = 4642.74 ms / 1107 tokens 17.33.434.547 I slot print_timing: id 0 | task 26925 | graphs reused = 25325 17.33.434.547 I slot print_timing: id 0 | task 26925 | graph reallocs = 0 / 0 (same size) / (changed size) 17.33.434.598 I slot release: id 0 | task 26925 | stop processing: n_tokens = 1106, truncated = 0 17.33.435.296 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.892 17.33.435.335 I slot launch_slot_: id 0 | task 26932 | processing task, is_child = 0 17.34.015.923 I slot print_timing: id 1 | task 26927 | prompt eval time = 3340.71 ms / 1098 tokens ( 3.04 ms per token, 328.67 tokens per second) 17.34.015.927 I slot print_timing: id 1 | task 26927 | eval time = 581.04 ms / 2 tokens ( 581.04 ms per token, 1.72 tokens per second) 17.34.015.928 I slot print_timing: id 1 | task 26927 | total time = 3921.75 ms / 1100 tokens 17.34.015.928 I slot print_timing: id 1 | task 26927 | graphs reused = 25325 17.34.015.929 I slot print_timing: id 1 | task 26927 | graph reallocs = 0 / 0 (same size) / (changed size) 17.34.015.996 I slot release: id 1 | task 26927 | stop processing: n_tokens = 1099, truncated = 0 17.34.016.310 I slot print_timing: id 3 | task 26928 | prompt eval time = 3340.91 ms / 1096 tokens ( 3.05 ms per token, 328.05 tokens per second) 17.34.016.312 I slot print_timing: id 3 | task 26928 | eval time = 581.02 ms / 2 tokens ( 581.02 ms per token, 1.72 tokens per second) 17.34.016.313 I slot print_timing: id 3 | task 26928 | total time = 3921.93 ms / 1098 tokens 17.34.016.313 I slot print_timing: id 3 | task 26928 | graphs reused = 25325 17.34.016.313 I slot print_timing: id 3 | task 26928 | graph reallocs = 0 / 0 (same size) / (changed size) 17.34.016.360 I slot release: id 3 | task 26928 | stop processing: n_tokens = 1097, truncated = 0 17.34.016.367 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 17.34.016.397 I slot launch_slot_: id 1 | task 26934 | processing task, is_child = 0 17.34.619.147 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.898 17.34.619.177 I slot launch_slot_: id 3 | task 26936 | processing task, is_child = 0 17.34.619.241 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 862, t_last = 347988752255 17.34.620.558 I slot launch_slot_: id 2 | task 26937 | processing task, is_child = 0 17.35.838.866 I slot print_timing: id 0 | task 26932 | prompt eval time = 1181.94 ms / 497 tokens ( 2.38 ms per token, 420.49 tokens per second) 17.35.838.868 I slot print_timing: id 0 | task 26932 | eval time = 1219.72 ms / 2 tokens ( 1219.72 ms per token, 0.82 tokens per second) 17.35.838.869 I slot print_timing: id 0 | task 26932 | total time = 2401.66 ms / 499 tokens 17.35.838.869 I slot print_timing: id 0 | task 26932 | graphs reused = 25325 17.35.838.870 I slot print_timing: id 0 | task 26932 | graph reallocs = 0 / 0 (same size) / (changed size) 17.35.838.924 I slot release: id 0 | task 26932 | stop processing: n_tokens = 1087, truncated = 0 17.35.894.095 I slot print_timing: id 1 | task 26934 | prompt eval time = 1819.71 ms / 512 tokens ( 3.55 ms per token, 281.36 tokens per second) 17.35.894.101 I slot print_timing: id 1 | task 26934 | eval time = 54.80 ms / 2 tokens ( 54.80 ms per token, 18.25 tokens per second) 17.35.894.102 I slot print_timing: id 1 | task 26934 | total time = 1874.51 ms / 514 tokens 17.35.894.102 I slot print_timing: id 1 | task 26934 | graphs reused = 25325 17.35.894.103 I slot print_timing: id 1 | task 26934 | graph reallocs = 0 / 0 (same size) / (changed size) 17.35.894.159 I slot release: id 1 | task 26934 | stop processing: n_tokens = 1095, truncated = 0 17.35.894.899 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 17.35.894.935 I slot launch_slot_: id 0 | task 26940 | processing task, is_child = 0 17.36.474.631 I slot print_timing: id 2 | task 26937 | prompt eval time = 1273.66 ms / 506 tokens ( 2.52 ms per token, 397.28 tokens per second) 17.36.474.633 I slot print_timing: id 2 | task 26937 | eval time = 580.19 ms / 2 tokens ( 580.19 ms per token, 1.72 tokens per second) 17.36.474.634 I slot print_timing: id 2 | task 26937 | total time = 1853.85 ms / 508 tokens 17.36.474.634 I slot print_timing: id 2 | task 26937 | graphs reused = 25325 17.36.474.635 I slot print_timing: id 2 | task 26937 | graph reallocs = 0 / 0 (same size) / (changed size) 17.36.474.686 I slot release: id 2 | task 26937 | stop processing: n_tokens = 1087, truncated = 0 17.36.474.999 I slot print_timing: id 3 | task 26936 | prompt eval time = 1273.95 ms / 515 tokens ( 2.47 ms per token, 404.26 tokens per second) 17.36.475.006 I slot print_timing: id 3 | task 26936 | eval time = 580.11 ms / 2 tokens ( 580.11 ms per token, 1.72 tokens per second) 17.36.475.007 I slot print_timing: id 3 | task 26936 | total time = 1854.05 ms / 517 tokens 17.36.475.007 I slot print_timing: id 3 | task 26936 | graphs reused = 25325 17.36.475.007 I slot print_timing: id 3 | task 26936 | graph reallocs = 0 / 0 (same size) / (changed size) 17.36.475.045 I slot release: id 3 | task 26936 | stop processing: n_tokens = 1096, truncated = 0 17.36.475.050 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.894 (> 0.100 thold), f_keep = 0.900 17.36.475.076 I slot launch_slot_: id 1 | task 26942 | processing task, is_child = 0 17.36.480.503 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.907 17.36.480.530 I slot launch_slot_: id 2 | task 26943 | processing task, is_child = 0 17.37.112.515 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.900 17.37.112.550 I slot launch_slot_: id 3 | task 26945 | processing task, is_child = 0 17.38.303.536 I slot print_timing: id 0 | task 26940 | prompt eval time = 1216.30 ms / 506 tokens ( 2.40 ms per token, 416.02 tokens per second) 17.38.303.539 I slot print_timing: id 0 | task 26940 | eval time = 1191.02 ms / 2 tokens ( 1191.02 ms per token, 0.84 tokens per second) 17.38.303.539 I slot print_timing: id 0 | task 26940 | total time = 2407.32 ms / 508 tokens 17.38.303.540 I slot print_timing: id 0 | task 26940 | graphs reused = 25325 17.38.303.540 I slot print_timing: id 0 | task 26940 | graph reallocs = 0 / 0 (same size) / (changed size) 17.38.303.598 I slot release: id 0 | task 26940 | stop processing: n_tokens = 1096, truncated = 0 17.38.367.875 I slot print_timing: id 2 | task 26943 | prompt eval time = 1823.06 ms / 516 tokens ( 3.53 ms per token, 283.04 tokens per second) 17.38.367.880 I slot print_timing: id 2 | task 26943 | eval time = 63.95 ms / 2 tokens ( 63.95 ms per token, 15.64 tokens per second) 17.38.367.880 I slot print_timing: id 2 | task 26943 | total time = 1887.00 ms / 518 tokens 17.38.367.880 I slot print_timing: id 2 | task 26943 | graphs reused = 25325 17.38.367.881 I slot print_timing: id 2 | task 26943 | graph reallocs = 0 / 0 (same size) / (changed size) 17.38.367.938 I slot release: id 2 | task 26943 | stop processing: n_tokens = 1097, truncated = 0 17.38.368.315 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.900 17.38.368.362 I slot launch_slot_: id 0 | task 26948 | processing task, is_child = 0 17.38.950.233 I slot print_timing: id 1 | task 26942 | prompt eval time = 1886.84 ms / 521 tokens ( 3.62 ms per token, 276.12 tokens per second) 17.38.950.236 I slot print_timing: id 1 | task 26942 | eval time = 582.62 ms / 2 tokens ( 582.62 ms per token, 1.72 tokens per second) 17.38.950.236 I slot print_timing: id 1 | task 26942 | total time = 2469.46 ms / 523 tokens 17.38.950.237 I slot print_timing: id 1 | task 26942 | graphs reused = 25325 17.38.950.237 I slot print_timing: id 1 | task 26942 | graph reallocs = 0 / 0 (same size) / (changed size) 17.38.950.296 I slot release: id 1 | task 26942 | stop processing: n_tokens = 1104, truncated = 0 17.38.950.611 I slot print_timing: id 3 | task 26945 | prompt eval time = 1255.53 ms / 508 tokens ( 2.47 ms per token, 404.61 tokens per second) 17.38.950.620 I slot print_timing: id 3 | task 26945 | eval time = 582.30 ms / 2 tokens ( 582.30 ms per token, 1.72 tokens per second) 17.38.950.620 I slot print_timing: id 3 | task 26945 | total time = 1837.83 ms / 510 tokens 17.38.950.620 I slot print_timing: id 3 | task 26945 | graphs reused = 25325 17.38.950.621 I slot print_timing: id 3 | task 26945 | graph reallocs = 0 / 0 (same size) / (changed size) 17.38.950.662 I slot release: id 3 | task 26945 | stop processing: n_tokens = 1089, truncated = 0 17.38.950.673 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.893 17.38.950.707 I slot launch_slot_: id 1 | task 26950 | processing task, is_child = 0 17.39.550.550 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.899 17.39.550.579 I slot launch_slot_: id 2 | task 26952 | processing task, is_child = 0 17.39.550.645 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.905 17.39.550.666 I slot launch_slot_: id 3 | task 26953 | processing task, is_child = 0 17.40.748.576 I slot print_timing: id 0 | task 26948 | prompt eval time = 1179.81 ms / 500 tokens ( 2.36 ms per token, 423.80 tokens per second) 17.40.748.579 I slot print_timing: id 0 | task 26948 | eval time = 1198.03 ms / 2 tokens ( 1198.03 ms per token, 0.83 tokens per second) 17.40.748.580 I slot print_timing: id 0 | task 26948 | total time = 2377.84 ms / 502 tokens 17.40.748.580 I slot print_timing: id 0 | task 26948 | graphs reused = 25325 17.40.748.581 I slot print_timing: id 0 | task 26948 | graph reallocs = 0 / 0 (same size) / (changed size) 17.40.748.632 I slot release: id 0 | task 26948 | stop processing: n_tokens = 1090, truncated = 0 17.40.804.074 I slot print_timing: id 1 | task 26950 | prompt eval time = 1794.85 ms / 506 tokens ( 3.55 ms per token, 281.92 tokens per second) 17.40.804.076 I slot print_timing: id 1 | task 26950 | eval time = 55.06 ms / 2 tokens ( 55.06 ms per token, 18.16 tokens per second) 17.40.804.077 I slot print_timing: id 1 | task 26950 | total time = 1849.91 ms / 508 tokens 17.40.804.077 I slot print_timing: id 1 | task 26950 | graphs reused = 25325 17.40.804.078 I slot print_timing: id 1 | task 26950 | graph reallocs = 0 / 0 (same size) / (changed size) 17.40.804.150 I slot release: id 1 | task 26950 | stop processing: n_tokens = 1094, truncated = 0 17.40.804.885 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1090, t_last = 347996130601 17.40.807.329 I slot launch_slot_: id 0 | task 26956 | processing task, is_child = 0 17.40.809.698 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1094, t_last = 347996186121 17.40.809.786 I slot launch_slot_: id 1 | task 26957 | processing task, is_child = 0 17.41.903.008 I slot print_timing: id 2 | task 26952 | prompt eval time = 1253.61 ms / 511 tokens ( 2.45 ms per token, 407.62 tokens per second) 17.41.903.010 I slot print_timing: id 2 | task 26952 | eval time = 1098.54 ms / 2 tokens ( 1098.54 ms per token, 0.91 tokens per second) 17.41.903.011 I slot print_timing: id 2 | task 26952 | total time = 2352.15 ms / 513 tokens 17.41.903.011 I slot print_timing: id 2 | task 26952 | graphs reused = 25325 17.41.903.011 I slot print_timing: id 2 | task 26952 | graph reallocs = 0 / 0 (same size) / (changed size) 17.41.903.071 I slot release: id 2 | task 26952 | stop processing: n_tokens = 1092, truncated = 0 17.41.903.388 I slot print_timing: id 3 | task 26953 | prompt eval time = 1253.90 ms / 512 tokens ( 2.45 ms per token, 408.33 tokens per second) 17.41.903.391 I slot print_timing: id 3 | task 26953 | eval time = 1098.51 ms / 2 tokens ( 1098.51 ms per token, 0.91 tokens per second) 17.41.903.391 I slot print_timing: id 3 | task 26953 | total time = 2352.41 ms / 514 tokens 17.41.903.391 I slot print_timing: id 3 | task 26953 | graphs reused = 25325 17.41.903.392 I slot print_timing: id 3 | task 26953 | graph reallocs = 0 / 0 (same size) / (changed size) 17.41.903.440 I slot release: id 3 | task 26953 | stop processing: n_tokens = 1093, truncated = 0 17.42.465.137 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1092, t_last = 347997285040 17.43.028.570 I slot launch_slot_: id 2 | task 26960 | processing task, is_child = 0 17.43.031.932 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1093, t_last = 347997285409 17.43.032.016 I slot launch_slot_: id 3 | task 26961 | processing task, is_child = 0 17.45.507.438 I slot print_timing: id 0 | task 26956 | prompt eval time = 3542.53 ms / 983 tokens ( 3.60 ms per token, 277.48 tokens per second) 17.45.507.440 I slot print_timing: id 0 | task 26956 | eval time = 1155.10 ms / 2 tokens ( 1155.10 ms per token, 0.87 tokens per second) 17.45.507.440 I slot print_timing: id 0 | task 26956 | total time = 4697.64 ms / 985 tokens 17.45.507.441 I slot print_timing: id 0 | task 26956 | graphs reused = 25325 17.45.507.441 I slot print_timing: id 0 | task 26956 | graph reallocs = 0 / 0 (same size) / (changed size) 17.45.507.498 I slot release: id 0 | task 26956 | stop processing: n_tokens = 984, truncated = 0 17.45.507.847 I slot print_timing: id 1 | task 26957 | prompt eval time = 3542.89 ms / 996 tokens ( 3.56 ms per token, 281.13 tokens per second) 17.45.507.854 I slot print_timing: id 1 | task 26957 | eval time = 1155.08 ms / 2 tokens ( 1155.08 ms per token, 0.87 tokens per second) 17.45.507.855 I slot print_timing: id 1 | task 26957 | total time = 4697.96 ms / 998 tokens 17.45.507.855 I slot print_timing: id 1 | task 26957 | graphs reused = 25325 17.45.507.855 I slot print_timing: id 1 | task 26957 | graph reallocs = 0 / 0 (same size) / (changed size) 17.45.507.904 I slot release: id 1 | task 26957 | stop processing: n_tokens = 997, truncated = 0 17.45.549.401 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.886 17.45.549.424 I slot launch_slot_: id 0 | task 26965 | processing task, is_child = 0 17.45.551.504 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.875 17.45.551.525 I slot launch_slot_: id 1 | task 26966 | processing task, is_child = 0 17.46.262.938 I slot print_timing: id 2 | task 26960 | prompt eval time = 2516.62 ms / 1037 tokens ( 2.43 ms per token, 412.06 tokens per second) 17.46.262.940 I slot print_timing: id 2 | task 26960 | eval time = 713.96 ms / 2 tokens ( 713.96 ms per token, 1.40 tokens per second) 17.46.262.941 I slot print_timing: id 2 | task 26960 | total time = 3230.59 ms / 1039 tokens 17.46.262.941 I slot print_timing: id 2 | task 26960 | graphs reused = 25325 17.46.262.942 I slot print_timing: id 2 | task 26960 | graph reallocs = 0 / 0 (same size) / (changed size) 17.46.263.004 I slot release: id 2 | task 26960 | stop processing: n_tokens = 1038, truncated = 0 17.46.263.415 I slot print_timing: id 3 | task 26961 | prompt eval time = 2516.96 ms / 1066 tokens ( 2.36 ms per token, 423.53 tokens per second) 17.46.263.418 I slot print_timing: id 3 | task 26961 | eval time = 714.02 ms / 2 tokens ( 714.02 ms per token, 1.40 tokens per second) 17.46.263.419 I slot print_timing: id 3 | task 26961 | total time = 3230.98 ms / 1068 tokens 17.46.263.419 I slot print_timing: id 3 | task 26961 | graphs reused = 25325 17.46.263.420 I slot print_timing: id 3 | task 26961 | graph reallocs = 0 / 0 (same size) / (changed size) 17.46.263.471 I slot release: id 3 | task 26961 | stop processing: n_tokens = 1067, truncated = 0 17.46.864.885 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1038, t_last = 348001644973 17.46.868.391 I slot launch_slot_: id 2 | task 26969 | processing task, is_child = 0 17.46.870.644 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1067, t_last = 348001645440 17.46.870.738 I slot launch_slot_: id 3 | task 26970 | processing task, is_child = 0 17.47.546.844 I slot print_timing: id 1 | task 26966 | prompt eval time = 1313.27 ms / 514 tokens ( 2.55 ms per token, 391.39 tokens per second) 17.47.546.847 I slot print_timing: id 1 | task 26966 | eval time = 681.96 ms / 2 tokens ( 681.96 ms per token, 1.47 tokens per second) 17.47.546.847 I slot print_timing: id 1 | task 26966 | total time = 1995.22 ms / 516 tokens 17.47.546.848 I slot print_timing: id 1 | task 26966 | graphs reused = 25325 17.47.546.848 I slot print_timing: id 1 | task 26966 | graph reallocs = 0 / 0 (same size) / (changed size) 17.47.546.909 I slot release: id 1 | task 26966 | stop processing: n_tokens = 995, truncated = 0 17.48.677.149 I slot print_timing: id 0 | task 26965 | prompt eval time = 1994.98 ms / 540 tokens ( 3.69 ms per token, 270.68 tokens per second) 17.48.677.151 I slot print_timing: id 0 | task 26965 | eval time = 1130.63 ms / 2 tokens ( 1130.63 ms per token, 0.88 tokens per second) 17.48.677.152 I slot print_timing: id 0 | task 26965 | total time = 3125.61 ms / 542 tokens 17.48.677.152 I slot print_timing: id 0 | task 26965 | graphs reused = 25325 17.48.677.153 I slot print_timing: id 0 | task 26965 | graph reallocs = 0 / 0 (same size) / (changed size) 17.48.677.219 I slot release: id 0 | task 26965 | stop processing: n_tokens = 1008, truncated = 0 17.48.677.227 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 995, t_last = 348002928879 17.48.679.814 I slot launch_slot_: id 1 | task 26973 | processing task, is_child = 0 17.49.007.360 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1008, t_last = 348004059189 17.49.007.489 I slot launch_slot_: id 0 | task 26975 | processing task, is_child = 0 17.49.877.855 I slot print_timing: id 2 | task 26969 | prompt eval time = 2136.01 ms / 731 tokens ( 2.92 ms per token, 342.23 tokens per second) 17.49.877.857 I slot print_timing: id 2 | task 26969 | eval time = 870.90 ms / 2 tokens ( 870.90 ms per token, 1.15 tokens per second) 17.49.877.857 I slot print_timing: id 2 | task 26969 | total time = 3006.91 ms / 733 tokens 17.49.877.858 I slot print_timing: id 2 | task 26969 | graphs reused = 25325 17.49.877.858 I slot print_timing: id 2 | task 26969 | graph reallocs = 0 / 0 (same size) / (changed size) 17.49.877.917 I slot release: id 2 | task 26969 | stop processing: n_tokens = 732, truncated = 0 17.49.878.265 I slot print_timing: id 3 | task 26970 | prompt eval time = 2136.35 ms / 774 tokens ( 2.76 ms per token, 362.30 tokens per second) 17.49.878.273 I slot print_timing: id 3 | task 26970 | eval time = 870.91 ms / 2 tokens ( 870.91 ms per token, 1.15 tokens per second) 17.49.878.273 I slot print_timing: id 3 | task 26970 | total time = 3007.26 ms / 776 tokens 17.49.878.273 I slot print_timing: id 3 | task 26970 | graphs reused = 25325 17.49.878.274 I slot print_timing: id 3 | task 26970 | graph reallocs = 0 / 0 (same size) / (changed size) 17.49.878.319 I slot release: id 3 | task 26970 | stop processing: n_tokens = 775, truncated = 0 17.50.474.278 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.862 17.50.474.307 I slot launch_slot_: id 2 | task 26978 | processing task, is_child = 0 17.50.476.639 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.814 17.50.476.670 I slot launch_slot_: id 3 | task 26979 | processing task, is_child = 0 17.51.703.094 I slot print_timing: id 1 | task 26973 | prompt eval time = 1792.38 ms / 706 tokens ( 2.54 ms per token, 393.89 tokens per second) 17.51.703.096 I slot print_timing: id 1 | task 26973 | eval time = 1228.82 ms / 2 tokens ( 1228.82 ms per token, 0.81 tokens per second) 17.51.703.097 I slot print_timing: id 1 | task 26973 | total time = 3021.20 ms / 708 tokens 17.51.703.097 I slot print_timing: id 1 | task 26973 | graphs reused = 25325 17.51.703.097 I slot print_timing: id 1 | task 26973 | graph reallocs = 0 / 0 (same size) / (changed size) 17.51.703.144 I slot release: id 1 | task 26973 | stop processing: n_tokens = 707, truncated = 0 17.51.755.742 I slot print_timing: id 0 | task 26975 | prompt eval time = 2695.28 ms / 721 tokens ( 3.74 ms per token, 267.50 tokens per second) 17.51.755.744 I slot print_timing: id 0 | task 26975 | eval time = 52.96 ms / 2 tokens ( 52.96 ms per token, 18.88 tokens per second) 17.51.755.744 I slot print_timing: id 0 | task 26975 | total time = 2748.24 ms / 723 tokens 17.51.755.745 I slot print_timing: id 0 | task 26975 | graphs reused = 25325 17.51.755.745 I slot print_timing: id 0 | task 26975 | graph reallocs = 0 / 0 (same size) / (changed size) 17.51.755.789 I slot release: id 0 | task 26975 | stop processing: n_tokens = 722, truncated = 0 17.51.756.560 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.874 17.51.756.589 I slot launch_slot_: id 0 | task 26982 | processing task, is_child = 0 17.52.325.237 I slot print_timing: id 2 | task 26978 | prompt eval time = 1279.20 ms / 508 tokens ( 2.52 ms per token, 397.12 tokens per second) 17.52.325.240 I slot print_timing: id 2 | task 26978 | eval time = 569.15 ms / 2 tokens ( 569.15 ms per token, 1.76 tokens per second) 17.52.325.240 I slot print_timing: id 2 | task 26978 | total time = 1848.35 ms / 510 tokens 17.52.325.241 I slot print_timing: id 2 | task 26978 | graphs reused = 25325 17.52.325.241 I slot print_timing: id 2 | task 26978 | graph reallocs = 0 / 0 (same size) / (changed size) 17.52.325.290 I slot release: id 2 | task 26978 | stop processing: n_tokens = 724, truncated = 0 17.52.325.664 I slot print_timing: id 3 | task 26979 | prompt eval time = 1279.48 ms / 457 tokens ( 2.80 ms per token, 357.18 tokens per second) 17.52.325.666 I slot print_timing: id 3 | task 26979 | eval time = 569.11 ms / 2 tokens ( 569.11 ms per token, 1.76 tokens per second) 17.52.325.666 I slot print_timing: id 3 | task 26979 | total time = 1848.59 ms / 459 tokens 17.52.325.667 I slot print_timing: id 3 | task 26979 | graphs reused = 25325 17.52.325.667 I slot print_timing: id 3 | task 26979 | graph reallocs = 0 / 0 (same size) / (changed size) 17.52.325.703 I slot release: id 3 | task 26979 | stop processing: n_tokens = 716, truncated = 0 17.52.325.710 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.893 17.52.325.741 I slot launch_slot_: id 1 | task 26984 | processing task, is_child = 0 17.52.453.537 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 724, t_last = 348007707259 17.52.453.620 I slot launch_slot_: id 2 | task 26986 | processing task, is_child = 0 17.52.453.667 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.881 17.52.453.690 I slot launch_slot_: id 3 | task 26987 | processing task, is_child = 0 17.54.288.892 I slot print_timing: id 0 | task 26982 | prompt eval time = 695.44 ms / 504 tokens ( 1.38 ms per token, 724.73 tokens per second) 17.54.288.895 I slot print_timing: id 0 | task 26982 | eval time = 1835.35 ms / 2 tokens ( 1835.35 ms per token, 0.54 tokens per second) 17.54.288.895 I slot print_timing: id 0 | task 26982 | total time = 2530.79 ms / 506 tokens 17.54.288.896 I slot print_timing: id 0 | task 26982 | graphs reused = 25325 17.54.288.896 I slot print_timing: id 0 | task 26982 | graph reallocs = 0 / 0 (same size) / (changed size) 17.54.288.948 I slot release: id 0 | task 26982 | stop processing: n_tokens = 710, truncated = 0 17.54.904.274 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 348009670917 17.54.905.865 I slot launch_slot_: id 0 | task 26990 | processing task, is_child = 0 17.55.424.102 I slot print_timing: id 1 | task 26984 | prompt eval time = 2573.84 ms / 541 tokens ( 4.76 ms per token, 210.19 tokens per second) 17.55.424.108 I slot print_timing: id 1 | task 26984 | eval time = 520.14 ms / 2 tokens ( 520.14 ms per token, 1.92 tokens per second) 17.55.424.108 I slot print_timing: id 1 | task 26984 | total time = 3093.98 ms / 543 tokens 17.55.424.109 I slot print_timing: id 1 | task 26984 | graphs reused = 25325 17.55.424.109 I slot print_timing: id 1 | task 26984 | graph reallocs = 0 / 0 (same size) / (changed size) 17.55.424.153 I slot release: id 1 | task 26984 | stop processing: n_tokens = 732, truncated = 0 17.55.424.747 I slot print_timing: id 3 | task 26987 | prompt eval time = 2450.47 ms / 465 tokens ( 5.27 ms per token, 189.76 tokens per second) 17.55.424.750 I slot print_timing: id 3 | task 26987 | eval time = 520.48 ms / 2 tokens ( 520.48 ms per token, 1.92 tokens per second) 17.55.424.750 I slot print_timing: id 3 | task 26987 | total time = 2970.95 ms / 467 tokens 17.55.424.750 I slot print_timing: id 3 | task 26987 | graphs reused = 25325 17.55.424.751 I slot print_timing: id 3 | task 26987 | graph reallocs = 0 / 0 (same size) / (changed size) 17.55.424.793 I slot release: id 3 | task 26987 | stop processing: n_tokens = 724, truncated = 0 17.55.997.596 I slot print_timing: id 2 | task 26986 | prompt eval time = 2970.74 ms / 944 tokens ( 3.15 ms per token, 317.77 tokens per second) 17.55.997.598 I slot print_timing: id 2 | task 26986 | eval time = 573.12 ms / 2 tokens ( 573.12 ms per token, 1.74 tokens per second) 17.55.997.598 I slot print_timing: id 2 | task 26986 | total time = 3543.85 ms / 946 tokens 17.55.997.599 I slot print_timing: id 2 | task 26986 | graphs reused = 25325 17.55.997.600 I slot print_timing: id 2 | task 26986 | graph reallocs = 0 / 0 (same size) / (changed size) 17.55.997.659 I slot release: id 2 | task 26986 | stop processing: n_tokens = 945, truncated = 0 17.55.997.667 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.881 (> 0.100 thold), f_keep = 0.852 17.55.997.695 I slot launch_slot_: id 2 | task 26993 | processing task, is_child = 0 17.56.001.291 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 348010806123 17.56.001.372 I slot launch_slot_: id 1 | task 26994 | processing task, is_child = 0 17.57.125.609 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 724, t_last = 348010806762 17.57.125.717 I slot launch_slot_: id 3 | task 26996 | processing task, is_child = 0 17.58.388.728 I slot print_timing: id 0 | task 26990 | prompt eval time = 2219.73 ms / 930 tokens ( 2.39 ms per token, 418.97 tokens per second) 17.58.388.732 I slot print_timing: id 0 | task 26990 | eval time = 1263.12 ms / 2 tokens ( 1263.12 ms per token, 0.79 tokens per second) 17.58.388.732 I slot print_timing: id 0 | task 26990 | total time = 3482.85 ms / 932 tokens 17.58.388.733 I slot print_timing: id 0 | task 26990 | graphs reused = 25325 17.58.388.733 I slot print_timing: id 0 | task 26990 | graph reallocs = 0 / 0 (same size) / (changed size) 17.58.388.792 I slot release: id 0 | task 26990 | stop processing: n_tokens = 931, truncated = 0 17.58.996.418 I slot print_timing: id 2 | task 26993 | prompt eval time = 2387.50 ms / 486 tokens ( 4.91 ms per token, 203.56 tokens per second) 17.58.996.420 I slot print_timing: id 2 | task 26993 | eval time = 607.28 ms / 2 tokens ( 607.28 ms per token, 1.65 tokens per second) 17.58.996.421 I slot print_timing: id 2 | task 26993 | total time = 2994.78 ms / 488 tokens 17.58.996.422 I slot print_timing: id 2 | task 26993 | graphs reused = 25325 17.58.996.422 I slot print_timing: id 2 | task 26993 | graph reallocs = 0 / 0 (same size) / (changed size) 17.58.996.474 I slot release: id 2 | task 26993 | stop processing: n_tokens = 915, truncated = 0 17.58.996.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 348013770761 17.58.999.836 I slot launch_slot_: id 0 | task 26999 | processing task, is_child = 0 17.59.690.827 I slot print_timing: id 1 | task 26994 | prompt eval time = 2994.53 ms / 999 tokens ( 3.00 ms per token, 333.61 tokens per second) 17.59.690.829 I slot print_timing: id 1 | task 26994 | eval time = 694.71 ms / 2 tokens ( 694.71 ms per token, 1.44 tokens per second) 17.59.690.830 I slot print_timing: id 1 | task 26994 | total time = 3689.24 ms / 1001 tokens 17.59.690.830 I slot print_timing: id 1 | task 26994 | graphs reused = 25325 17.59.690.831 I slot print_timing: id 1 | task 26994 | graph reallocs = 0 / 0 (same size) / (changed size) 17.59.690.891 I slot release: id 1 | task 26994 | stop processing: n_tokens = 1000, truncated = 0 17.59.691.173 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 915, t_last = 348014378443 17.59.691.286 I slot launch_slot_: id 2 | task 27001 | processing task, is_child = 0 18.01.956.646 I slot print_timing: id 3 | task 26996 | prompt eval time = 2565.23 ms / 1051 tokens ( 2.44 ms per token, 409.71 tokens per second) 18.01.956.649 I slot print_timing: id 3 | task 26996 | eval time = 2265.47 ms / 2 tokens ( 2265.47 ms per token, 0.44 tokens per second) 18.01.956.649 I slot print_timing: id 3 | task 26996 | total time = 4830.70 ms / 1053 tokens 18.01.956.650 I slot print_timing: id 3 | task 26996 | graphs reused = 25325 18.01.956.650 I slot print_timing: id 3 | task 26996 | graph reallocs = 0 / 0 (same size) / (changed size) 18.01.956.721 I slot release: id 3 | task 26996 | stop processing: n_tokens = 1052, truncated = 0 18.01.956.728 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1000, t_last = 348015072860 18.01.956.851 I slot launch_slot_: id 1 | task 27003 | processing task, is_child = 0 18.03.891.288 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1052, t_last = 348017338690 18.03.891.397 I slot launch_slot_: id 3 | task 27005 | processing task, is_child = 0 18.03.891.455 I slot print_timing: id 2 | task 27001 | prompt processing, n_tokens = 1555, progress = 0.75, t = 4.20 s / 370.56 tokens per second 18.06.263.457 I slot print_timing: id 0 | task 26999 | prompt eval time = 4889.56 ms / 1054 tokens ( 4.64 ms per token, 215.56 tokens per second) 18.06.263.460 I slot print_timing: id 0 | task 26999 | eval time = 2372.17 ms / 2 tokens ( 2372.17 ms per token, 0.42 tokens per second) 18.06.263.460 I slot print_timing: id 0 | task 26999 | total time = 7261.73 ms / 1056 tokens 18.06.263.461 I slot print_timing: id 0 | task 26999 | graphs reused = 25325 18.06.263.461 I slot print_timing: id 0 | task 26999 | graph reallocs = 0 / 0 (same size) / (changed size) 18.06.263.522 I slot release: id 0 | task 26999 | stop processing: n_tokens = 1055, truncated = 0 18.06.263.537 I slot print_timing: id 1 | task 27003 | prompt processing, n_tokens = 2081, progress = 1.00, t = 4.30 s / 483.71 tokens per second 18.06.263.870 I slot print_timing: id 2 | task 27001 | prompt processing, n_tokens = 2067, progress = 1.00, t = 6.57 s / 314.68 tokens per second 18.06.891.316 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1055, t_last = 348021645491 18.06.895.322 I slot launch_slot_: id 0 | task 27008 | processing task, is_child = 0 18.09.168.043 I slot print_timing: id 1 | task 27003 | prompt eval time = 4929.89 ms / 2085 tokens ( 2.36 ms per token, 422.93 tokens per second) 18.09.168.048 I slot print_timing: id 1 | task 27003 | eval time = 2277.18 ms / 2 tokens ( 2277.18 ms per token, 0.44 tokens per second) 18.09.168.049 I slot print_timing: id 1 | task 27003 | total time = 7207.07 ms / 2087 tokens 18.09.168.049 I slot print_timing: id 1 | task 27003 | graphs reused = 25325 18.09.168.049 I slot print_timing: id 1 | task 27003 | graph reallocs = 0 / 0 (same size) / (changed size) 18.09.168.165 I slot release: id 1 | task 27003 | stop processing: n_tokens = 2086, truncated = 0 18.09.168.547 I slot print_timing: id 2 | task 27001 | prompt eval time = 7196.69 ms / 2071 tokens ( 3.47 ms per token, 287.77 tokens per second) 18.09.168.550 I slot print_timing: id 2 | task 27001 | eval time = 2277.24 ms / 2 tokens ( 2277.24 ms per token, 0.44 tokens per second) 18.09.168.551 I slot print_timing: id 2 | task 27001 | total time = 9473.92 ms / 2073 tokens 18.09.168.551 I slot print_timing: id 2 | task 27001 | graphs reused = 25325 18.09.168.551 I slot print_timing: id 2 | task 27001 | graph reallocs = 0 / 0 (same size) / (changed size) 18.09.168.638 I slot release: id 2 | task 27001 | stop processing: n_tokens = 2072, truncated = 0 18.09.168.725 I slot print_timing: id 3 | task 27005 | prompt processing, n_tokens = 2045, progress = 1.00, t = 5.28 s / 387.59 tokens per second 18.09.774.512 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.842 (> 0.100 thold), f_keep = 0.850 18.09.774.551 I slot launch_slot_: id 1 | task 27011 | processing task, is_child = 0 18.09.780.385 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.838 (> 0.100 thold), f_keep = 0.856 18.09.780.418 I slot launch_slot_: id 2 | task 27012 | processing task, is_child = 0 18.10.071.065 I slot print_timing: id 3 | task 27005 | prompt eval time = 5883.00 ms / 2049 tokens ( 2.87 ms per token, 348.29 tokens per second) 18.10.071.067 I slot print_timing: id 3 | task 27005 | eval time = 296.56 ms / 2 tokens ( 296.56 ms per token, 3.37 tokens per second) 18.10.071.068 I slot print_timing: id 3 | task 27005 | total time = 6179.56 ms / 2051 tokens 18.10.071.068 I slot print_timing: id 3 | task 27005 | graphs reused = 25325 18.10.071.069 I slot print_timing: id 3 | task 27005 | graph reallocs = 0 / 0 (same size) / (changed size) 18.10.071.186 I slot release: id 3 | task 27005 | stop processing: n_tokens = 2050, truncated = 0 18.11.255.298 I slot print_timing: id 0 | task 27008 | prompt eval time = 3175.39 ms / 2026 tokens ( 1.57 ms per token, 638.03 tokens per second) 18.11.255.303 I slot print_timing: id 0 | task 27008 | eval time = 1184.56 ms / 2 tokens ( 1184.56 ms per token, 0.84 tokens per second) 18.11.255.304 I slot print_timing: id 0 | task 27008 | total time = 4359.95 ms / 2028 tokens 18.11.255.305 I slot print_timing: id 0 | task 27008 | graphs reused = 25325 18.11.255.305 I slot print_timing: id 0 | task 27008 | graph reallocs = 0 / 0 (same size) / (changed size) 18.11.255.413 I slot release: id 0 | task 27008 | stop processing: n_tokens = 2027, truncated = 0 18.11.255.424 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 18.11.255.464 I slot launch_slot_: id 0 | task 27015 | processing task, is_child = 0 18.11.393.132 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.834 (> 0.100 thold), f_keep = 0.865 18.11.393.174 I slot launch_slot_: id 3 | task 27017 | processing task, is_child = 0 18.12.170.758 I slot print_timing: id 1 | task 27011 | prompt eval time = 1611.98 ms / 537 tokens ( 3.00 ms per token, 333.13 tokens per second) 18.12.170.763 I slot print_timing: id 1 | task 27011 | eval time = 778.04 ms / 2 tokens ( 778.04 ms per token, 1.29 tokens per second) 18.12.170.764 I slot print_timing: id 1 | task 27011 | total time = 2390.03 ms / 539 tokens 18.12.170.764 I slot print_timing: id 1 | task 27011 | graphs reused = 25325 18.12.170.765 I slot print_timing: id 1 | task 27011 | graph reallocs = 0 / 0 (same size) / (changed size) 18.12.170.883 I slot release: id 1 | task 27011 | stop processing: n_tokens = 2107, truncated = 0 18.12.171.203 I slot print_timing: id 2 | task 27012 | prompt eval time = 1612.29 ms / 561 tokens ( 2.87 ms per token, 347.95 tokens per second) 18.12.171.205 I slot print_timing: id 2 | task 27012 | eval time = 778.08 ms / 2 tokens ( 778.08 ms per token, 1.29 tokens per second) 18.12.171.206 I slot print_timing: id 2 | task 27012 | total time = 2390.37 ms / 563 tokens 18.12.171.206 I slot print_timing: id 2 | task 27012 | graphs reused = 25325 18.12.171.206 I slot print_timing: id 2 | task 27012 | graph reallocs = 0 / 0 (same size) / (changed size) 18.12.171.303 I slot release: id 2 | task 27012 | stop processing: n_tokens = 2117, truncated = 0 18.12.776.847 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.842 18.12.776.882 I slot launch_slot_: id 1 | task 27020 | processing task, is_child = 0 18.12.783.815 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.805 (> 0.100 thold), f_keep = 0.838 18.12.783.841 I slot launch_slot_: id 2 | task 27021 | processing task, is_child = 0 18.13.476.186 I slot print_timing: id 0 | task 27015 | prompt eval time = 1515.72 ms / 537 tokens ( 2.82 ms per token, 354.29 tokens per second) 18.13.476.188 I slot print_timing: id 0 | task 27015 | eval time = 699.34 ms / 2 tokens ( 699.34 ms per token, 1.43 tokens per second) 18.13.476.190 I slot print_timing: id 0 | task 27015 | total time = 2215.05 ms / 539 tokens 18.13.476.190 I slot print_timing: id 0 | task 27015 | graphs reused = 25325 18.13.476.190 I slot print_timing: id 0 | task 27015 | graph reallocs = 0 / 0 (same size) / (changed size) 18.13.476.304 I slot release: id 0 | task 27015 | stop processing: n_tokens = 2048, truncated = 0 18.14.109.497 I slot print_timing: id 3 | task 27017 | prompt eval time = 2083.50 ms / 593 tokens ( 3.51 ms per token, 284.62 tokens per second) 18.14.109.500 I slot print_timing: id 3 | task 27017 | eval time = 632.76 ms / 2 tokens ( 632.76 ms per token, 1.58 tokens per second) 18.14.109.500 I slot print_timing: id 3 | task 27017 | total time = 2716.26 ms / 595 tokens 18.14.109.501 I slot print_timing: id 3 | task 27017 | graphs reused = 25325 18.14.109.501 I slot print_timing: id 3 | task 27017 | graph reallocs = 0 / 0 (same size) / (changed size) 18.14.109.614 I slot release: id 3 | task 27017 | stop processing: n_tokens = 2127, truncated = 0 18.14.109.623 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.834 18.14.109.653 I slot launch_slot_: id 3 | task 27024 | processing task, is_child = 0 18.14.630.727 I slot print_timing: id 1 | task 27020 | prompt eval time = 1325.33 ms / 365 tokens ( 3.63 ms per token, 275.40 tokens per second) 18.14.630.730 I slot print_timing: id 1 | task 27020 | eval time = 521.54 ms / 2 tokens ( 521.54 ms per token, 1.92 tokens per second) 18.14.630.730 I slot print_timing: id 1 | task 27020 | total time = 1846.88 ms / 367 tokens 18.14.630.731 I slot print_timing: id 1 | task 27020 | graphs reused = 25325 18.14.630.731 I slot print_timing: id 1 | task 27020 | graph reallocs = 0 / 0 (same size) / (changed size) 18.14.630.828 I slot release: id 1 | task 27020 | stop processing: n_tokens = 1956, truncated = 0 18.14.631.282 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.866 18.14.631.319 I slot launch_slot_: id 0 | task 27026 | processing task, is_child = 0 18.14.636.133 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.865 (> 0.100 thold), f_keep = 0.907 18.14.636.166 I slot launch_slot_: id 1 | task 27027 | processing task, is_child = 0 18.15.769.241 I slot print_timing: id 2 | task 27021 | prompt eval time = 1847.28 ms / 604 tokens ( 3.06 ms per token, 326.97 tokens per second) 18.15.769.244 I slot print_timing: id 2 | task 27021 | eval time = 1137.97 ms / 2 tokens ( 1137.97 ms per token, 0.88 tokens per second) 18.15.769.244 I slot print_timing: id 2 | task 27021 | total time = 2985.25 ms / 606 tokens 18.15.769.245 I slot print_timing: id 2 | task 27021 | graphs reused = 25325 18.15.769.245 I slot print_timing: id 2 | task 27021 | graph reallocs = 0 / 0 (same size) / (changed size) 18.15.769.365 I slot release: id 2 | task 27021 | stop processing: n_tokens = 2205, truncated = 0 18.15.824.191 I slot print_timing: id 3 | task 27024 | prompt eval time = 1654.74 ms / 390 tokens ( 4.24 ms per token, 235.69 tokens per second) 18.15.824.195 I slot print_timing: id 3 | task 27024 | eval time = 54.48 ms / 2 tokens ( 54.48 ms per token, 18.35 tokens per second) 18.15.824.195 I slot print_timing: id 3 | task 27024 | total time = 1709.22 ms / 392 tokens 18.15.824.196 I slot print_timing: id 3 | task 27024 | graphs reused = 25325 18.15.824.196 I slot print_timing: id 3 | task 27024 | graph reallocs = 0 / 0 (same size) / (changed size) 18.15.824.299 I slot release: id 3 | task 27024 | stop processing: n_tokens = 2001, truncated = 0 18.15.824.308 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.848 (> 0.100 thold), f_keep = 0.805 18.15.824.339 I slot launch_slot_: id 2 | task 27030 | processing task, is_child = 0 18.15.828.726 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.886 18.15.828.761 I slot launch_slot_: id 3 | task 27031 | processing task, is_child = 0 18.16.878.092 I slot print_timing: id 0 | task 27026 | prompt eval time = 1187.33 ms / 466 tokens ( 2.55 ms per token, 392.48 tokens per second) 18.16.878.095 I slot print_timing: id 0 | task 27026 | eval time = 1054.58 ms / 2 tokens ( 1054.58 ms per token, 0.95 tokens per second) 18.16.878.096 I slot print_timing: id 0 | task 27026 | total time = 2241.91 ms / 468 tokens 18.16.878.096 I slot print_timing: id 0 | task 27026 | graphs reused = 25325 18.16.878.097 I slot print_timing: id 0 | task 27026 | graph reallocs = 0 / 0 (same size) / (changed size) 18.16.878.210 I slot release: id 0 | task 27026 | stop processing: n_tokens = 1998, truncated = 0 18.16.878.512 I slot print_timing: id 1 | task 27027 | prompt eval time = 1187.58 ms / 461 tokens ( 2.58 ms per token, 388.18 tokens per second) 18.16.878.514 I slot print_timing: id 1 | task 27027 | eval time = 1054.60 ms / 2 tokens ( 1054.60 ms per token, 0.95 tokens per second) 18.16.878.515 I slot print_timing: id 1 | task 27027 | total time = 2242.18 ms / 463 tokens 18.16.878.515 I slot print_timing: id 1 | task 27027 | graphs reused = 25325 18.16.878.515 I slot print_timing: id 1 | task 27027 | graph reallocs = 0 / 0 (same size) / (changed size) 18.16.878.605 I slot release: id 1 | task 27027 | stop processing: n_tokens = 2052, truncated = 0 18.16.920.488 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.887 18.16.920.514 I slot launch_slot_: id 0 | task 27034 | processing task, is_child = 0 18.16.925.248 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.842 (> 0.100 thold), f_keep = 0.865 18.16.925.272 I slot launch_slot_: id 1 | task 27035 | processing task, is_child = 0 18.17.576.391 I slot print_timing: id 2 | task 27030 | prompt eval time = 1091.36 ms / 403 tokens ( 2.71 ms per token, 369.26 tokens per second) 18.17.576.393 I slot print_timing: id 2 | task 27030 | eval time = 656.26 ms / 2 tokens ( 656.26 ms per token, 1.52 tokens per second) 18.17.576.394 I slot print_timing: id 2 | task 27030 | total time = 1747.62 ms / 405 tokens 18.17.576.394 I slot print_timing: id 2 | task 27030 | graphs reused = 25325 18.17.576.395 I slot print_timing: id 2 | task 27030 | graph reallocs = 0 / 0 (same size) / (changed size) 18.17.576.510 I slot release: id 2 | task 27030 | stop processing: n_tokens = 2092, truncated = 0 18.17.576.862 I slot print_timing: id 3 | task 27031 | prompt eval time = 1091.58 ms / 348 tokens ( 3.14 ms per token, 318.80 tokens per second) 18.17.576.864 I slot print_timing: id 3 | task 27031 | eval time = 656.38 ms / 2 tokens ( 656.38 ms per token, 1.52 tokens per second) 18.17.576.865 I slot print_timing: id 3 | task 27031 | total time = 1747.96 ms / 350 tokens 18.17.576.865 I slot print_timing: id 3 | task 27031 | graphs reused = 25325 18.17.576.865 I slot print_timing: id 3 | task 27031 | graph reallocs = 0 / 0 (same size) / (changed size) 18.17.576.946 I slot release: id 3 | task 27031 | stop processing: n_tokens = 1959, truncated = 0 18.18.194.881 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.848 18.18.194.921 I slot launch_slot_: id 2 | task 27038 | processing task, is_child = 0 18.18.200.984 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.905 18.18.201.016 I slot launch_slot_: id 3 | task 27039 | processing task, is_child = 0 18.18.751.936 I slot print_timing: id 1 | task 27035 | prompt eval time = 1269.49 ms / 516 tokens ( 2.46 ms per token, 406.46 tokens per second) 18.18.751.939 I slot print_timing: id 1 | task 27035 | eval time = 557.06 ms / 2 tokens ( 557.06 ms per token, 1.80 tokens per second) 18.18.751.939 I slot print_timing: id 1 | task 27035 | total time = 1826.55 ms / 518 tokens 18.18.751.940 I slot print_timing: id 1 | task 27035 | graphs reused = 25325 18.18.751.940 I slot print_timing: id 1 | task 27035 | graph reallocs = 0 / 0 (same size) / (changed size) 18.18.752.053 I slot release: id 1 | task 27035 | stop processing: n_tokens = 2107, truncated = 0 18.19.383.727 I slot print_timing: id 0 | task 27034 | prompt eval time = 1826.35 ms / 523 tokens ( 3.49 ms per token, 286.36 tokens per second) 18.19.383.730 I slot print_timing: id 0 | task 27034 | eval time = 632.09 ms / 2 tokens ( 632.09 ms per token, 1.58 tokens per second) 18.19.383.730 I slot print_timing: id 0 | task 27034 | total time = 2458.45 ms / 525 tokens 18.19.383.731 I slot print_timing: id 0 | task 27034 | graphs reused = 25325 18.19.383.731 I slot print_timing: id 0 | task 27034 | graph reallocs = 0 / 0 (same size) / (changed size) 18.19.383.850 I slot release: id 0 | task 27034 | stop processing: n_tokens = 2055, truncated = 0 18.19.384.261 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.820 (> 0.100 thold), f_keep = 0.842 18.19.384.307 I slot launch_slot_: id 1 | task 27042 | processing task, is_child = 0 18.19.390.081 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.863 18.19.390.109 I slot launch_slot_: id 0 | task 27043 | processing task, is_child = 0 18.20.145.794 I slot print_timing: id 2 | task 27038 | prompt eval time = 1182.91 ms / 270 tokens ( 4.38 ms per token, 228.25 tokens per second) 18.20.145.796 I slot print_timing: id 2 | task 27038 | eval time = 761.54 ms / 2 tokens ( 761.54 ms per token, 1.31 tokens per second) 18.20.145.797 I slot print_timing: id 2 | task 27038 | total time = 1944.45 ms / 272 tokens 18.20.145.797 I slot print_timing: id 2 | task 27038 | graphs reused = 25325 18.20.145.798 I slot print_timing: id 2 | task 27038 | graph reallocs = 0 / 0 (same size) / (changed size) 18.20.145.913 I slot release: id 2 | task 27038 | stop processing: n_tokens = 1959, truncated = 0 18.20.779.437 I slot print_timing: id 3 | task 27039 | prompt eval time = 1944.77 ms / 545 tokens ( 3.57 ms per token, 280.24 tokens per second) 18.20.779.444 I slot print_timing: id 3 | task 27039 | eval time = 633.22 ms / 2 tokens ( 633.22 ms per token, 1.58 tokens per second) 18.20.779.444 I slot print_timing: id 3 | task 27039 | total time = 2577.98 ms / 547 tokens 18.20.779.445 I slot print_timing: id 3 | task 27039 | graphs reused = 25325 18.20.779.445 I slot print_timing: id 3 | task 27039 | graph reallocs = 0 / 0 (same size) / (changed size) 18.20.779.562 I slot release: id 3 | task 27039 | stop processing: n_tokens = 2156, truncated = 0 18.20.779.570 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.905 18.20.779.612 I slot launch_slot_: id 2 | task 27046 | processing task, is_child = 0 18.21.207.427 I slot print_timing: id 0 | task 27043 | prompt eval time = 1389.04 ms / 481 tokens ( 2.89 ms per token, 346.28 tokens per second) 18.21.207.430 I slot print_timing: id 0 | task 27043 | eval time = 428.26 ms / 2 tokens ( 428.26 ms per token, 2.34 tokens per second) 18.21.207.430 I slot print_timing: id 0 | task 27043 | total time = 1817.30 ms / 483 tokens 18.21.207.431 I slot print_timing: id 0 | task 27043 | graphs reused = 25325 18.21.207.431 I slot print_timing: id 0 | task 27043 | graph reallocs = 0 / 0 (same size) / (changed size) 18.21.207.553 I slot release: id 0 | task 27043 | stop processing: n_tokens = 2020, truncated = 0 18.21.207.969 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.878 18.21.208.003 I slot launch_slot_: id 0 | task 27048 | processing task, is_child = 0 18.21.786.818 I slot print_timing: id 1 | task 27042 | prompt eval time = 1817.71 ms / 573 tokens ( 3.17 ms per token, 315.23 tokens per second) 18.21.786.820 I slot print_timing: id 1 | task 27042 | eval time = 578.85 ms / 2 tokens ( 578.85 ms per token, 1.73 tokens per second) 18.21.786.821 I slot print_timing: id 1 | task 27042 | total time = 2396.56 ms / 575 tokens 18.21.786.822 I slot print_timing: id 1 | task 27042 | graphs reused = 25325 18.21.786.822 I slot print_timing: id 1 | task 27042 | graph reallocs = 0 / 0 (same size) / (changed size) 18.21.786.940 I slot release: id 1 | task 27042 | stop processing: n_tokens = 2164, truncated = 0 18.21.787.274 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.819 18.21.787.319 I slot launch_slot_: id 1 | task 27050 | processing task, is_child = 0 18.22.167.829 I slot print_timing: id 2 | task 27046 | prompt eval time = 1001.57 ms / 289 tokens ( 3.47 ms per token, 288.55 tokens per second) 18.22.167.832 I slot print_timing: id 2 | task 27046 | eval time = 380.56 ms / 2 tokens ( 380.56 ms per token, 2.63 tokens per second) 18.22.167.832 I slot print_timing: id 2 | task 27046 | total time = 1382.13 ms / 291 tokens 18.22.167.833 I slot print_timing: id 2 | task 27046 | graphs reused = 25325 18.22.167.833 I slot print_timing: id 2 | task 27046 | graph reallocs = 0 / 0 (same size) / (changed size) 18.22.167.944 I slot release: id 2 | task 27046 | stop processing: n_tokens = 1978, truncated = 0 18.22.167.954 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.896 18.22.167.984 I slot launch_slot_: id 2 | task 27052 | processing task, is_child = 0 18.22.592.553 I slot print_timing: id 0 | task 27048 | prompt eval time = 959.36 ms / 466 tokens ( 2.06 ms per token, 485.74 tokens per second) 18.22.592.555 I slot print_timing: id 0 | task 27048 | eval time = 425.06 ms / 2 tokens ( 425.06 ms per token, 2.35 tokens per second) 18.22.592.556 I slot print_timing: id 0 | task 27048 | total time = 1384.42 ms / 468 tokens 18.22.592.556 I slot print_timing: id 0 | task 27048 | graphs reused = 25325 18.22.592.556 I slot print_timing: id 0 | task 27048 | graph reallocs = 0 / 0 (same size) / (changed size) 18.22.592.669 I slot release: id 0 | task 27048 | stop processing: n_tokens = 2005, truncated = 0 18.22.593.057 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.884 18.22.593.088 I slot launch_slot_: id 0 | task 27054 | processing task, is_child = 0 18.23.109.157 I slot print_timing: id 1 | task 27050 | prompt eval time = 805.24 ms / 244 tokens ( 3.30 ms per token, 303.02 tokens per second) 18.23.109.160 I slot print_timing: id 1 | task 27050 | eval time = 516.10 ms / 2 tokens ( 516.10 ms per token, 1.94 tokens per second) 18.23.109.161 I slot print_timing: id 1 | task 27050 | total time = 1321.34 ms / 246 tokens 18.23.109.161 I slot print_timing: id 1 | task 27050 | graphs reused = 25325 18.23.109.162 I slot print_timing: id 1 | task 27050 | graph reallocs = 0 / 0 (same size) / (changed size) 18.23.109.263 I slot release: id 1 | task 27050 | stop processing: n_tokens = 1892, truncated = 0 18.23.109.593 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2156, t_last = 348036161532 18.23.109.758 I slot launch_slot_: id 3 | task 27056 | processing task, is_child = 0 18.24.178.877 I slot print_timing: id 2 | task 27052 | prompt eval time = 941.11 ms / 289 tokens ( 3.26 ms per token, 307.08 tokens per second) 18.24.178.879 I slot print_timing: id 2 | task 27052 | eval time = 1069.29 ms / 2 tokens ( 1069.29 ms per token, 0.94 tokens per second) 18.24.178.880 I slot print_timing: id 2 | task 27052 | total time = 2010.40 ms / 291 tokens 18.24.178.880 I slot print_timing: id 2 | task 27052 | graphs reused = 25325 18.24.178.880 I slot print_timing: id 2 | task 27052 | graph reallocs = 0 / 0 (same size) / (changed size) 18.24.178.991 I slot release: id 2 | task 27052 | stop processing: n_tokens = 1978, truncated = 0 18.24.178.999 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1892, t_last = 348038491234 18.24.179.177 I slot launch_slot_: id 1 | task 27058 | processing task, is_child = 0 18.26.086.921 I slot print_timing: id 0 | task 27054 | prompt eval time = 1585.30 ms / 398 tokens ( 3.98 ms per token, 251.06 tokens per second) 18.26.086.923 I slot print_timing: id 0 | task 27054 | eval time = 1908.38 ms / 2 tokens ( 1908.38 ms per token, 0.52 tokens per second) 18.26.086.924 I slot print_timing: id 0 | task 27054 | total time = 3493.68 ms / 400 tokens 18.26.086.924 I slot print_timing: id 0 | task 27054 | graphs reused = 25325 18.26.086.925 I slot print_timing: id 0 | task 27054 | graph reallocs = 0 / 0 (same size) / (changed size) 18.26.087.039 I slot release: id 0 | task 27054 | stop processing: n_tokens = 1937, truncated = 0 18.26.087.050 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1978, t_last = 348039560961 18.26.087.211 I slot launch_slot_: id 2 | task 27060 | processing task, is_child = 0 18.27.805.818 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1937, t_last = 348041469009 18.27.805.992 I slot launch_slot_: id 0 | task 27062 | processing task, is_child = 0 18.27.806.146 I slot print_timing: id 1 | task 27058 | prompt processing, n_tokens = 1623, progress = 1.00, t = 3.62 s / 448.21 tokens per second 18.28.957.121 I slot print_timing: id 3 | task 27056 | prompt eval time = 4690.27 ms / 1430 tokens ( 3.28 ms per token, 304.89 tokens per second) 18.28.957.124 I slot print_timing: id 3 | task 27056 | eval time = 1151.31 ms / 2 tokens ( 1151.31 ms per token, 0.87 tokens per second) 18.28.957.134 I slot print_timing: id 3 | task 27056 | total time = 5841.57 ms / 1432 tokens 18.28.957.135 I slot print_timing: id 3 | task 27056 | graphs reused = 25325 18.28.957.136 I slot print_timing: id 3 | task 27056 | graph reallocs = 0 / 0 (same size) / (changed size) 18.28.957.218 I slot release: id 3 | task 27056 | stop processing: n_tokens = 1431, truncated = 0 18.29.560.688 I slot print_timing: id 1 | task 27058 | prompt eval time = 4772.33 ms / 1627 tokens ( 2.93 ms per token, 340.92 tokens per second) 18.29.560.690 I slot print_timing: id 1 | task 27058 | eval time = 603.99 ms / 2 tokens ( 603.99 ms per token, 1.66 tokens per second) 18.29.560.691 I slot print_timing: id 1 | task 27058 | total time = 5376.32 ms / 1629 tokens 18.29.560.691 I slot print_timing: id 1 | task 27058 | graphs reused = 25325 18.29.560.692 I slot print_timing: id 1 | task 27058 | graph reallocs = 0 / 0 (same size) / (changed size) 18.29.560.776 I slot release: id 1 | task 27058 | stop processing: n_tokens = 1628, truncated = 0 18.29.561.160 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1431, t_last = 348044339188 18.29.565.267 I slot launch_slot_: id 3 | task 27065 | processing task, is_child = 0 18.29.568.602 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1628, t_last = 348044942746 18.29.568.715 I slot launch_slot_: id 1 | task 27066 | processing task, is_child = 0 18.30.627.925 I slot print_timing: id 2 | task 27060 | prompt eval time = 3469.31 ms / 1498 tokens ( 2.32 ms per token, 431.79 tokens per second) 18.30.627.930 I slot print_timing: id 2 | task 27060 | eval time = 1066.76 ms / 2 tokens ( 1066.76 ms per token, 0.94 tokens per second) 18.30.627.931 I slot print_timing: id 2 | task 27060 | total time = 4536.08 ms / 1500 tokens 18.30.627.931 I slot print_timing: id 2 | task 27060 | graphs reused = 25325 18.30.627.932 I slot print_timing: id 2 | task 27060 | graph reallocs = 0 / 0 (same size) / (changed size) 18.30.628.013 I slot release: id 2 | task 27060 | stop processing: n_tokens = 1499, truncated = 0 18.31.771.901 I slot print_timing: id 0 | task 27062 | prompt eval time = 2821.62 ms / 981 tokens ( 2.88 ms per token, 347.67 tokens per second) 18.31.771.904 I slot print_timing: id 0 | task 27062 | eval time = 1144.27 ms / 2 tokens ( 1144.27 ms per token, 0.87 tokens per second) 18.31.771.905 I slot print_timing: id 0 | task 27062 | total time = 3965.89 ms / 983 tokens 18.31.771.905 I slot print_timing: id 0 | task 27062 | graphs reused = 25325 18.31.771.906 I slot print_timing: id 0 | task 27062 | graph reallocs = 0 / 0 (same size) / (changed size) 18.31.771.979 I slot release: id 0 | task 27062 | stop processing: n_tokens = 982, truncated = 0 18.31.771.989 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.878 18.31.772.020 I slot launch_slot_: id 0 | task 27069 | processing task, is_child = 0 18.32.369.296 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1499, t_last = 348046009982 18.32.369.413 I slot launch_slot_: id 2 | task 27070 | processing task, is_child = 0 18.32.922.189 I slot print_timing: id 1 | task 27066 | prompt eval time = 2800.02 ms / 958 tokens ( 2.92 ms per token, 342.14 tokens per second) 18.32.922.193 I slot print_timing: id 1 | task 27066 | eval time = 553.28 ms / 2 tokens ( 553.28 ms per token, 1.81 tokens per second) 18.32.922.193 I slot print_timing: id 1 | task 27066 | total time = 3353.30 ms / 960 tokens 18.32.922.194 I slot print_timing: id 1 | task 27066 | graphs reused = 25325 18.32.922.194 I slot print_timing: id 1 | task 27066 | graph reallocs = 0 / 0 (same size) / (changed size) 18.32.922.255 I slot release: id 1 | task 27066 | stop processing: n_tokens = 959, truncated = 0 18.32.922.643 I slot print_timing: id 3 | task 27065 | prompt eval time = 2800.28 ms / 969 tokens ( 2.89 ms per token, 346.04 tokens per second) 18.32.922.646 I slot print_timing: id 3 | task 27065 | eval time = 553.35 ms / 2 tokens ( 553.35 ms per token, 1.81 tokens per second) 18.32.922.647 I slot print_timing: id 3 | task 27065 | total time = 3353.63 ms / 971 tokens 18.32.922.647 I slot print_timing: id 3 | task 27065 | graphs reused = 25325 18.32.922.647 I slot print_timing: id 3 | task 27065 | graph reallocs = 0 / 0 (same size) / (changed size) 18.32.922.700 I slot release: id 3 | task 27065 | stop processing: n_tokens = 970, truncated = 0 18.33.497.772 I slot print_timing: id 0 | task 27069 | prompt eval time = 1144.33 ms / 478 tokens ( 2.39 ms per token, 417.71 tokens per second) 18.33.497.777 I slot print_timing: id 0 | task 27069 | eval time = 576.01 ms / 2 tokens ( 576.01 ms per token, 1.74 tokens per second) 18.33.497.778 I slot print_timing: id 0 | task 27069 | total time = 1720.35 ms / 480 tokens 18.33.497.778 I slot print_timing: id 0 | task 27069 | graphs reused = 25325 18.33.497.779 I slot print_timing: id 0 | task 27069 | graph reallocs = 0 / 0 (same size) / (changed size) 18.33.497.839 I slot release: id 0 | task 27069 | stop processing: n_tokens = 944, truncated = 0 18.33.497.848 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.912 18.33.497.871 I slot launch_slot_: id 0 | task 27074 | processing task, is_child = 0 18.33.503.423 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.898 18.33.503.451 I slot launch_slot_: id 1 | task 27075 | processing task, is_child = 0 18.33.503.503 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 348048304669 18.33.503.574 I slot launch_slot_: id 3 | task 27076 | processing task, is_child = 0 18.35.700.572 I slot print_timing: id 2 | task 27070 | prompt eval time = 2711.38 ms / 964 tokens ( 2.81 ms per token, 355.54 tokens per second) 18.35.700.574 I slot print_timing: id 2 | task 27070 | eval time = 619.52 ms / 2 tokens ( 619.52 ms per token, 1.61 tokens per second) 18.35.700.574 I slot print_timing: id 2 | task 27070 | total time = 3330.90 ms / 966 tokens 18.35.700.575 I slot print_timing: id 2 | task 27070 | graphs reused = 25325 18.35.700.575 I slot print_timing: id 2 | task 27070 | graph reallocs = 0 / 0 (same size) / (changed size) 18.35.700.643 I slot release: id 2 | task 27070 | stop processing: n_tokens = 965, truncated = 0 18.35.743.103 I slot print_timing: id 0 | task 27074 | prompt eval time = 2196.37 ms / 492 tokens ( 4.46 ms per token, 224.01 tokens per second) 18.35.743.108 I slot print_timing: id 0 | task 27074 | eval time = 43.15 ms / 2 tokens ( 43.15 ms per token, 23.18 tokens per second) 18.35.743.108 I slot print_timing: id 0 | task 27074 | total time = 2239.52 ms / 494 tokens 18.35.743.108 I slot print_timing: id 0 | task 27074 | graphs reused = 25325 18.35.743.109 I slot print_timing: id 0 | task 27074 | graph reallocs = 0 / 0 (same size) / (changed size) 18.35.743.160 I slot release: id 0 | task 27074 | stop processing: n_tokens = 958, truncated = 0 18.35.743.487 I slot print_timing: id 1 | task 27075 | prompt eval time = 2196.57 ms / 511 tokens ( 4.30 ms per token, 232.64 tokens per second) 18.35.743.490 I slot print_timing: id 1 | task 27075 | eval time = 43.20 ms / 2 tokens ( 43.20 ms per token, 23.15 tokens per second) 18.35.743.490 I slot print_timing: id 1 | task 27075 | total time = 2239.77 ms / 513 tokens 18.35.743.491 I slot print_timing: id 1 | task 27075 | graphs reused = 25325 18.35.743.491 I slot print_timing: id 1 | task 27075 | graph reallocs = 0 / 0 (same size) / (changed size) 18.35.743.531 I slot release: id 1 | task 27075 | stop processing: n_tokens = 954, truncated = 0 18.35.743.937 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 965, t_last = 348051082612 18.35.746.166 I slot launch_slot_: id 2 | task 27080 | processing task, is_child = 0 18.37.072.744 I slot print_timing: id 3 | task 27076 | prompt eval time = 2239.92 ms / 789 tokens ( 2.84 ms per token, 352.24 tokens per second) 18.37.072.750 I slot print_timing: id 3 | task 27076 | eval time = 1328.81 ms / 2 tokens ( 1328.81 ms per token, 0.75 tokens per second) 18.37.072.751 I slot print_timing: id 3 | task 27076 | total time = 3568.73 ms / 791 tokens 18.37.072.751 I slot print_timing: id 3 | task 27076 | graphs reused = 25325 18.37.072.752 I slot print_timing: id 3 | task 27076 | graph reallocs = 0 / 0 (same size) / (changed size) 18.37.072.815 I slot release: id 3 | task 27076 | stop processing: n_tokens = 790, truncated = 0 18.37.072.823 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 958, t_last = 348051125129 18.37.072.932 I slot launch_slot_: id 0 | task 27082 | processing task, is_child = 0 18.37.075.570 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 348051125500 18.37.075.679 I slot launch_slot_: id 1 | task 27083 | processing task, is_child = 0 18.39.220.525 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 348052454784 18.39.220.655 I slot launch_slot_: id 3 | task 27085 | processing task, is_child = 0 18.41.332.805 I slot print_timing: id 0 | task 27082 | prompt processing, n_tokens = 1574, progress = 1.00, t = 4.26 s / 369.74 tokens per second 18.41.798.243 I slot print_timing: id 1 | task 27083 | prompt processing, n_tokens = 1094, progress = 0.68, t = 4.26 s / 256.99 tokens per second 18.41.798.294 I slot print_timing: id 2 | task 27080 | prompt processing, n_tokens = 1619, progress = 1.00, t = 5.58 s / 290.00 tokens per second 18.42.732.530 I slot print_timing: id 1 | task 27083 | prompt processing, n_tokens = 1606, progress = 1.00, t = 5.66 s / 283.94 tokens per second 18.42.732.790 I slot print_timing: id 3 | task 27085 | prompt processing, n_tokens = 1117, progress = 0.68, t = 3.33 s / 335.66 tokens per second 18.43.361.594 I slot print_timing: id 0 | task 27082 | prompt eval time = 5656.47 ms / 1578 tokens ( 3.58 ms per token, 278.97 tokens per second) 18.43.361.597 I slot print_timing: id 0 | task 27082 | eval time = 629.38 ms / 2 tokens ( 629.38 ms per token, 1.59 tokens per second) 18.43.361.598 I slot print_timing: id 0 | task 27082 | total time = 6285.85 ms / 1580 tokens 18.43.361.598 I slot print_timing: id 0 | task 27082 | graphs reused = 25325 18.43.361.599 I slot print_timing: id 0 | task 27082 | graph reallocs = 0 / 0 (same size) / (changed size) 18.43.361.697 I slot release: id 0 | task 27082 | stop processing: n_tokens = 1579, truncated = 0 18.43.362.376 I slot print_timing: id 2 | task 27080 | prompt eval time = 6982.56 ms / 1623 tokens ( 4.30 ms per token, 232.44 tokens per second) 18.43.362.381 I slot print_timing: id 2 | task 27080 | eval time = 629.85 ms / 2 tokens ( 629.85 ms per token, 1.59 tokens per second) 18.43.362.381 I slot print_timing: id 2 | task 27080 | total time = 7612.40 ms / 1625 tokens 18.43.362.382 I slot print_timing: id 2 | task 27080 | graphs reused = 25325 18.43.362.382 I slot print_timing: id 2 | task 27080 | graph reallocs = 0 / 0 (same size) / (changed size) 18.43.362.486 I slot release: id 2 | task 27080 | stop processing: n_tokens = 1624, truncated = 0 18.43.362.511 I slot print_timing: id 3 | task 27085 | prompt processing, n_tokens = 1629, progress = 1.00, t = 3.96 s / 411.66 tokens per second 18.43.401.139 I slot print_timing: id 1 | task 27083 | prompt eval time = 6286.21 ms / 1610 tokens ( 3.90 ms per token, 256.12 tokens per second) 18.43.401.143 I slot print_timing: id 1 | task 27083 | eval time = 39.09 ms / 2 tokens ( 39.09 ms per token, 25.58 tokens per second) 18.43.401.144 I slot print_timing: id 1 | task 27083 | total time = 6325.30 ms / 1612 tokens 18.43.401.144 I slot print_timing: id 1 | task 27083 | graphs reused = 25325 18.43.401.145 I slot print_timing: id 1 | task 27083 | graph reallocs = 0 / 0 (same size) / (changed size) 18.43.401.237 I slot release: id 1 | task 27083 | stop processing: n_tokens = 1611, truncated = 0 18.43.401.647 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.812 (> 0.100 thold), f_keep = 0.886 18.43.401.698 I slot launch_slot_: id 0 | task 27090 | processing task, is_child = 0 18.43.408.533 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1624, t_last = 348058744457 18.43.408.635 I slot launch_slot_: id 2 | task 27091 | processing task, is_child = 0 18.43.408.704 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1611, t_last = 348058783206 18.43.408.792 I slot launch_slot_: id 1 | task 27092 | processing task, is_child = 0 18.44.425.795 I slot print_timing: id 3 | task 27085 | prompt eval time = 3997.54 ms / 1633 tokens ( 2.45 ms per token, 408.50 tokens per second) 18.44.425.801 I slot print_timing: id 3 | task 27085 | eval time = 1024.15 ms / 2 tokens ( 1024.15 ms per token, 0.98 tokens per second) 18.44.425.801 I slot print_timing: id 3 | task 27085 | total time = 5021.69 ms / 1635 tokens 18.44.425.802 I slot print_timing: id 3 | task 27085 | graphs reused = 25325 18.44.425.802 I slot print_timing: id 3 | task 27085 | graph reallocs = 0 / 0 (same size) / (changed size) 18.44.425.900 I slot release: id 3 | task 27085 | stop processing: n_tokens = 1634, truncated = 0 18.46.170.338 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1634, t_last = 348059807870 18.46.202.446 I slot launch_slot_: id 3 | task 27095 | processing task, is_child = 0 18.47.239.351 I slot print_timing: id 0 | task 27090 | prompt eval time = 3242.70 ms / 661 tokens ( 4.91 ms per token, 203.84 tokens per second) 18.47.239.357 I slot print_timing: id 0 | task 27090 | eval time = 587.85 ms / 2 tokens ( 587.85 ms per token, 1.70 tokens per second) 18.47.239.357 I slot print_timing: id 0 | task 27090 | total time = 3830.55 ms / 663 tokens 18.47.239.358 I slot print_timing: id 0 | task 27090 | graphs reused = 25326 18.47.239.358 I slot print_timing: id 0 | task 27090 | graph reallocs = 0 / 0 (same size) / (changed size) 18.47.239.457 I slot release: id 0 | task 27090 | stop processing: n_tokens = 1724, truncated = 0 18.47.239.793 I slot print_timing: id 1 | task 27092 | prompt eval time = 3242.95 ms / 854 tokens ( 3.80 ms per token, 263.34 tokens per second) 18.47.239.795 I slot print_timing: id 1 | task 27092 | eval time = 587.95 ms / 2 tokens ( 587.95 ms per token, 1.70 tokens per second) 18.47.239.795 I slot print_timing: id 1 | task 27092 | total time = 3830.90 ms / 856 tokens 18.47.239.796 I slot print_timing: id 1 | task 27092 | graphs reused = 25326 18.47.239.796 I slot print_timing: id 1 | task 27092 | graph reallocs = 0 / 0 (same size) / (changed size) 18.47.239.838 I slot release: id 1 | task 27092 | stop processing: n_tokens = 855, truncated = 0 18.47.240.171 I slot print_timing: id 2 | task 27091 | prompt eval time = 3243.14 ms / 826 tokens ( 3.93 ms per token, 254.69 tokens per second) 18.47.240.174 I slot print_timing: id 2 | task 27091 | eval time = 588.04 ms / 2 tokens ( 588.04 ms per token, 1.70 tokens per second) 18.47.240.175 I slot print_timing: id 2 | task 27091 | total time = 3831.18 ms / 828 tokens 18.47.240.175 I slot print_timing: id 2 | task 27091 | graphs reused = 25326 18.47.240.175 I slot print_timing: id 2 | task 27091 | graph reallocs = 0 / 0 (same size) / (changed size) 18.47.240.229 I slot release: id 2 | task 27091 | stop processing: n_tokens = 827, truncated = 0 18.47.266.360 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1724, t_last = 348062621428 18.47.270.080 I slot launch_slot_: id 0 | task 27099 | processing task, is_child = 0 18.47.273.504 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 348062621807 18.47.273.579 I slot launch_slot_: id 1 | task 27100 | processing task, is_child = 0 18.47.273.627 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 827, t_last = 348062622198 18.47.273.692 I slot launch_slot_: id 2 | task 27101 | processing task, is_child = 0 18.48.565.101 I slot print_timing: id 3 | task 27095 | prompt eval time = 1063.26 ms / 828 tokens ( 1.28 ms per token, 778.74 tokens per second) 18.48.565.103 I slot print_timing: id 3 | task 27095 | eval time = 1298.74 ms / 2 tokens ( 1298.74 ms per token, 0.77 tokens per second) 18.48.565.103 I slot print_timing: id 3 | task 27095 | total time = 2362.00 ms / 830 tokens 18.48.565.104 I slot print_timing: id 3 | task 27095 | graphs reused = 25326 18.48.565.104 I slot print_timing: id 3 | task 27095 | graph reallocs = 0 / 0 (same size) / (changed size) 18.48.565.160 I slot release: id 3 | task 27095 | stop processing: n_tokens = 829, truncated = 0 18.50.287.525 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 829, t_last = 348063947129 18.50.318.761 I slot launch_slot_: id 3 | task 27104 | processing task, is_child = 0 18.50.318.772 I slot print_timing: id 0 | task 27099 | prompt processing, n_tokens = 843, progress = 1.00, t = 3.01 s / 279.71 tokens per second 18.50.318.943 I slot print_timing: id 1 | task 27100 | prompt processing, n_tokens = 755, progress = 0.99, t = 3.01 s / 250.52 tokens per second 18.50.319.081 I slot print_timing: id 2 | task 27101 | prompt processing, n_tokens = 863, progress = 1.00, t = 3.01 s / 286.37 tokens per second 18.51.269.190 I slot print_timing: id 0 | task 27099 | prompt eval time = 3408.88 ms / 847 tokens ( 4.02 ms per token, 248.47 tokens per second) 18.51.269.196 I slot print_timing: id 0 | task 27099 | eval time = 586.61 ms / 2 tokens ( 586.61 ms per token, 1.70 tokens per second) 18.51.269.196 I slot print_timing: id 0 | task 27099 | total time = 3995.49 ms / 849 tokens 18.51.269.197 I slot print_timing: id 0 | task 27099 | graphs reused = 25327 18.51.269.197 I slot print_timing: id 0 | task 27099 | graph reallocs = 0 / 0 (same size) / (changed size) 18.51.269.259 I slot release: id 0 | task 27099 | stop processing: n_tokens = 848, truncated = 0 18.51.269.561 I slot print_timing: id 1 | task 27100 | prompt eval time = 3409.06 ms / 759 tokens ( 4.49 ms per token, 222.64 tokens per second) 18.51.269.563 I slot print_timing: id 1 | task 27100 | eval time = 586.68 ms / 2 tokens ( 586.68 ms per token, 1.70 tokens per second) 18.51.269.564 I slot print_timing: id 1 | task 27100 | total time = 3995.74 ms / 761 tokens 18.51.269.564 I slot print_timing: id 1 | task 27100 | graphs reused = 25327 18.51.269.564 I slot print_timing: id 1 | task 27100 | graph reallocs = 0 / 0 (same size) / (changed size) 18.51.269.607 I slot release: id 1 | task 27100 | stop processing: n_tokens = 760, truncated = 0 18.51.269.916 I slot print_timing: id 2 | task 27101 | prompt eval time = 3409.33 ms / 867 tokens ( 3.93 ms per token, 254.30 tokens per second) 18.51.269.920 I slot print_timing: id 2 | task 27101 | eval time = 586.71 ms / 2 tokens ( 586.71 ms per token, 1.70 tokens per second) 18.51.269.920 I slot print_timing: id 2 | task 27101 | total time = 3996.03 ms / 869 tokens 18.51.269.920 I slot print_timing: id 2 | task 27101 | graphs reused = 25327 18.51.269.921 I slot print_timing: id 2 | task 27101 | graph reallocs = 0 / 0 (same size) / (changed size) 18.51.269.968 I slot release: id 2 | task 27101 | stop processing: n_tokens = 868, truncated = 0 18.51.295.744 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 848, t_last = 348066651228 18.51.297.619 I slot launch_slot_: id 0 | task 27108 | processing task, is_child = 0 18.51.300.962 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 760, t_last = 348066651576 18.51.301.031 I slot launch_slot_: id 1 | task 27109 | processing task, is_child = 0 18.51.301.079 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 868, t_last = 348066651937 18.51.301.146 I slot launch_slot_: id 2 | task 27110 | processing task, is_child = 0 18.51.987.018 I slot print_timing: id 3 | task 27104 | prompt eval time = 976.50 ms / 728 tokens ( 1.34 ms per token, 745.52 tokens per second) 18.51.987.021 I slot print_timing: id 3 | task 27104 | eval time = 691.26 ms / 2 tokens ( 691.26 ms per token, 1.45 tokens per second) 18.51.987.021 I slot print_timing: id 3 | task 27104 | total time = 1667.76 ms / 730 tokens 18.51.987.022 I slot print_timing: id 3 | task 27104 | graphs reused = 25327 18.51.987.022 I slot print_timing: id 3 | task 27104 | graph reallocs = 0 / 0 (same size) / (changed size) 18.51.987.066 I slot release: id 3 | task 27104 | stop processing: n_tokens = 729, truncated = 0 18.53.807.787 I slot print_timing: id 0 | task 27108 | prompt eval time = 2482.83 ms / 700 tokens ( 3.55 ms per token, 281.94 tokens per second) 18.53.807.793 I slot print_timing: id 0 | task 27108 | eval time = 23.80 ms / 2 tokens ( 23.80 ms per token, 42.02 tokens per second) 18.53.807.793 I slot print_timing: id 0 | task 27108 | total time = 2506.63 ms / 702 tokens 18.53.807.794 I slot print_timing: id 0 | task 27108 | graphs reused = 25328 18.53.807.794 I slot print_timing: id 0 | task 27108 | graph reallocs = 0 / 0 (same size) / (changed size) 18.53.807.848 I slot release: id 0 | task 27108 | stop processing: n_tokens = 701, truncated = 0 18.53.808.140 I slot print_timing: id 1 | task 27109 | prompt eval time = 2483.06 ms / 682 tokens ( 3.64 ms per token, 274.66 tokens per second) 18.53.808.142 I slot print_timing: id 1 | task 27109 | eval time = 23.86 ms / 2 tokens ( 23.86 ms per token, 41.91 tokens per second) 18.53.808.143 I slot print_timing: id 1 | task 27109 | total time = 2506.92 ms / 684 tokens 18.53.808.143 I slot print_timing: id 1 | task 27109 | graphs reused = 25328 18.53.808.143 I slot print_timing: id 1 | task 27109 | graph reallocs = 0 / 0 (same size) / (changed size) 18.53.808.179 I slot release: id 1 | task 27109 | stop processing: n_tokens = 683, truncated = 0 18.53.808.453 I slot print_timing: id 2 | task 27110 | prompt eval time = 2483.39 ms / 665 tokens ( 3.73 ms per token, 267.78 tokens per second) 18.53.808.455 I slot print_timing: id 2 | task 27110 | eval time = 23.79 ms / 2 tokens ( 23.79 ms per token, 42.03 tokens per second) 18.53.808.455 I slot print_timing: id 2 | task 27110 | total time = 2507.18 ms / 667 tokens 18.53.808.455 I slot print_timing: id 2 | task 27110 | graphs reused = 25328 18.53.808.456 I slot print_timing: id 2 | task 27110 | graph reallocs = 0 / 0 (same size) / (changed size) 18.53.808.483 I slot release: id 2 | task 27110 | stop processing: n_tokens = 666, truncated = 0 18.56.293.383 I srv operator(): operator(): cleaning up before exit...