/Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/ddff7a731322/Spark-X2.6-4B-IQ2_M.gguf --host 127.0.0.1 --port 8091 -c 16384 -np 4 -ngl 999 -fa on --jinja --seed 1234 --chat-template-kwargs "{\"enable_thinking\": false}" --no-webui -a quant 0.00.043.201 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.043.258 I srv llama_server: initializing ... 0.00.043.263 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.043.327 I srv init_listene: The UI is disabled 0.00.043.328 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.043.363 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) 0.00.045.033 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/ddff7a731322/Spark-X2.6-4B-IQ2_M.gguf' 0.00.414.841 I cmn init: llama threadpool init, n_threads = 8 0.00.513.912 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.00.523.233 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.523.246 I srv llama_server: model loaded 0.00.523.248 I srv llama_server: listening on http://127.0.0.1:8091 0.29.805.146 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.29.805.191 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.29.807.709 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.29.807.752 I slot launch_slot_: id 1 | task 2 | processing task, is_child = 0 0.29.807.753 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.29.807.784 I slot launch_slot_: id 2 | task 3 | processing task, is_child = 0 0.29.807.785 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.29.807.812 I slot launch_slot_: id 3 | task 4 | processing task, is_child = 0 0.31.089.495 I slot print_timing: id 0 | task 0 | prompt eval time = 1195.87 ms / 134 tokens ( 8.92 ms per token, 112.05 tokens per second) 0.31.089.498 I slot print_timing: id 0 | task 0 | eval time = 88.42 ms / 2 tokens ( 88.42 ms per token, 11.31 tokens per second) 0.31.089.498 I slot print_timing: id 0 | task 0 | total time = 1284.29 ms / 136 tokens 0.31.089.499 I slot print_timing: id 0 | task 0 | graphs reused = 1 0.31.089.499 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.089.528 I slot release: id 0 | task 0 | stop processing: n_tokens = 135, truncated = 0 0.31.128.261 I slot print_timing: id 1 | task 2 | prompt eval time = 1216.94 ms / 128 tokens ( 9.51 ms per token, 105.18 tokens per second) 0.31.128.263 I slot print_timing: id 1 | task 2 | eval time = 37.28 ms / 2 tokens ( 37.28 ms per token, 26.82 tokens per second) 0.31.128.264 I slot print_timing: id 1 | task 2 | total time = 1254.22 ms / 130 tokens 0.31.128.264 I slot print_timing: id 1 | task 2 | graphs reused = 1 0.31.128.265 I slot print_timing: id 1 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.128.283 I slot release: id 1 | task 2 | stop processing: n_tokens = 129, truncated = 0 0.31.129.438 I slot print_timing: id 2 | task 3 | prompt eval time = 1218.37 ms / 130 tokens ( 9.37 ms per token, 106.70 tokens per second) 0.31.129.440 I slot print_timing: id 2 | task 3 | eval time = 37.02 ms / 2 tokens ( 37.02 ms per token, 27.02 tokens per second) 0.31.129.440 I slot print_timing: id 2 | task 3 | total time = 1255.38 ms / 132 tokens 0.31.129.441 I slot print_timing: id 2 | task 3 | graphs reused = 1 0.31.129.441 I slot print_timing: id 2 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.129.456 I slot release: id 2 | task 3 | stop processing: n_tokens = 131, truncated = 0 0.31.130.558 I slot print_timing: id 3 | task 4 | prompt eval time = 1219.82 ms / 142 tokens ( 8.59 ms per token, 116.41 tokens per second) 0.31.130.560 I slot print_timing: id 3 | task 4 | eval time = 36.68 ms / 2 tokens ( 36.68 ms per token, 27.26 tokens per second) 0.31.130.560 I slot print_timing: id 3 | task 4 | total time = 1256.50 ms / 144 tokens 0.31.130.560 I slot print_timing: id 3 | task 4 | graphs reused = 1 0.31.130.561 I slot print_timing: id 3 | task 4 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.130.570 I slot release: id 3 | task 4 | stop processing: n_tokens = 143, truncated = 0 0.31.130.574 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.274 0.31.133.717 I slot launch_slot_: id 0 | task 9 | processing task, is_child = 0 0.31.141.838 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.295 0.31.141.907 I slot launch_slot_: id 1 | task 10 | processing task, is_child = 0 0.31.141.959 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.282 0.31.142.010 I slot launch_slot_: id 2 | task 11 | processing task, is_child = 0 0.31.142.034 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.319 (> 0.100 thold), f_keep = 0.266 0.31.142.087 I slot launch_slot_: id 3 | task 12 | processing task, is_child = 0 0.32.516.650 I slot print_timing: id 0 | task 9 | prompt eval time = 1335.44 ms / 164 tokens ( 8.14 ms per token, 122.81 tokens per second) 0.32.516.652 I slot print_timing: id 0 | task 9 | eval time = 39.11 ms / 2 tokens ( 39.11 ms per token, 25.57 tokens per second) 0.32.516.653 I slot print_timing: id 0 | task 9 | total time = 1374.55 ms / 166 tokens 0.32.516.653 I slot print_timing: id 0 | task 9 | graphs reused = 1 0.32.516.654 I slot print_timing: id 0 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.516.678 I slot release: id 0 | task 9 | stop processing: n_tokens = 174, truncated = 0 0.32.517.801 I slot print_timing: id 1 | task 10 | prompt eval time = 1336.54 ms / 159 tokens ( 8.41 ms per token, 118.96 tokens per second) 0.32.517.803 I slot print_timing: id 1 | task 10 | eval time = 39.03 ms / 2 tokens ( 39.03 ms per token, 25.62 tokens per second) 0.32.517.803 I slot print_timing: id 1 | task 10 | total time = 1375.57 ms / 161 tokens 0.32.517.803 I slot print_timing: id 1 | task 10 | graphs reused = 1 0.32.517.804 I slot print_timing: id 1 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.517.816 I slot release: id 1 | task 10 | stop processing: n_tokens = 169, truncated = 0 0.32.518.905 I slot print_timing: id 2 | task 11 | prompt eval time = 1337.65 ms / 204 tokens ( 6.56 ms per token, 152.51 tokens per second) 0.32.518.907 I slot print_timing: id 2 | task 11 | eval time = 38.91 ms / 2 tokens ( 38.91 ms per token, 25.70 tokens per second) 0.32.518.908 I slot print_timing: id 2 | task 11 | total time = 1376.56 ms / 206 tokens 0.32.518.908 I slot print_timing: id 2 | task 11 | graphs reused = 1 0.32.518.908 I slot print_timing: id 2 | task 11 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.518.920 I slot release: id 2 | task 11 | stop processing: n_tokens = 214, truncated = 0 0.32.520.035 I slot print_timing: id 3 | task 12 | prompt eval time = 1338.76 ms / 110 tokens ( 12.17 ms per token, 82.17 tokens per second) 0.32.520.036 I slot print_timing: id 3 | task 12 | eval time = 38.81 ms / 2 tokens ( 38.81 ms per token, 25.77 tokens per second) 0.32.520.036 I slot print_timing: id 3 | task 12 | total time = 1377.57 ms / 112 tokens 0.32.520.037 I slot print_timing: id 3 | task 12 | graphs reused = 1 0.32.520.037 I slot print_timing: id 3 | task 12 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.520.043 I slot release: id 3 | task 12 | stop processing: n_tokens = 120, truncated = 0 0.32.520.469 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.297 (> 0.100 thold), f_keep = 0.225 0.32.524.179 I slot launch_slot_: id 1 | task 17 | processing task, is_child = 0 0.32.533.616 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.213 0.32.533.690 I slot launch_slot_: id 0 | task 18 | processing task, is_child = 0 0.32.533.749 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.173 0.32.533.808 I slot launch_slot_: id 2 | task 19 | processing task, is_child = 0 0.32.533.833 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.287 (> 0.100 thold), f_keep = 0.308 0.32.533.889 I slot launch_slot_: id 3 | task 20 | processing task, is_child = 0 0.33.640.792 I slot print_timing: id 0 | task 18 | prompt eval time = 1068.33 ms / 127 tokens ( 8.41 ms per token, 118.88 tokens per second) 0.33.640.799 I slot print_timing: id 0 | task 18 | eval time = 38.56 ms / 2 tokens ( 38.56 ms per token, 25.94 tokens per second) 0.33.640.799 I slot print_timing: id 0 | task 18 | total time = 1106.89 ms / 129 tokens 0.33.640.800 I slot print_timing: id 0 | task 18 | graphs reused = 1 0.33.640.800 I slot print_timing: id 0 | task 18 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.640.820 I slot release: id 0 | task 18 | stop processing: n_tokens = 137, truncated = 0 0.33.642.961 I slot print_timing: id 2 | task 19 | prompt eval time = 1070.20 ms / 151 tokens ( 7.09 ms per token, 141.09 tokens per second) 0.33.642.963 I slot print_timing: id 2 | task 19 | eval time = 38.60 ms / 2 tokens ( 38.60 ms per token, 25.91 tokens per second) 0.33.642.964 I slot print_timing: id 2 | task 19 | total time = 1108.81 ms / 153 tokens 0.33.642.964 I slot print_timing: id 2 | task 19 | graphs reused = 1 0.33.642.964 I slot print_timing: id 2 | task 19 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.642.978 I slot release: id 2 | task 19 | stop processing: n_tokens = 161, truncated = 0 0.33.644.099 I slot print_timing: id 3 | task 20 | prompt eval time = 1071.23 ms / 120 tokens ( 8.93 ms per token, 112.02 tokens per second) 0.33.644.100 I slot print_timing: id 3 | task 20 | eval time = 38.60 ms / 2 tokens ( 38.60 ms per token, 25.90 tokens per second) 0.33.644.101 I slot print_timing: id 3 | task 20 | total time = 1109.83 ms / 122 tokens 0.33.644.101 I slot print_timing: id 3 | task 20 | graphs reused = 1 0.33.644.101 I slot print_timing: id 3 | task 20 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.644.110 I slot release: id 3 | task 20 | stop processing: n_tokens = 130, truncated = 0 0.33.667.530 I slot print_timing: id 1 | task 17 | prompt eval time = 1069.27 ms / 119 tokens ( 8.99 ms per token, 111.29 tokens per second) 0.33.667.532 I slot print_timing: id 1 | task 17 | eval time = 64.22 ms / 3 tokens ( 32.11 ms per token, 31.14 tokens per second) 0.33.667.532 I slot print_timing: id 1 | task 17 | total time = 1133.49 ms / 122 tokens 0.33.667.533 I slot print_timing: id 1 | task 17 | graphs reused = 1 0.33.667.533 I slot print_timing: id 1 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.667.549 I slot release: id 1 | task 17 | stop processing: n_tokens = 130, truncated = 0 0.33.667.553 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.270 0.33.668.735 I slot launch_slot_: id 0 | task 26 | processing task, is_child = 0 0.33.677.278 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.240 (> 0.100 thold), f_keep = 0.285 0.33.677.339 I slot launch_slot_: id 1 | task 27 | processing task, is_child = 0 0.33.677.386 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.230 0.33.677.437 I slot launch_slot_: id 2 | task 28 | processing task, is_child = 0 0.33.677.461 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.285 0.33.677.509 I slot launch_slot_: id 3 | task 29 | processing task, is_child = 0 0.34.965.759 I slot print_timing: id 0 | task 26 | prompt eval time = 1249.63 ms / 184 tokens ( 6.79 ms per token, 147.24 tokens per second) 0.34.965.762 I slot print_timing: id 0 | task 26 | eval time = 38.61 ms / 2 tokens ( 38.61 ms per token, 25.90 tokens per second) 0.34.965.764 I slot print_timing: id 0 | task 26 | total time = 1288.23 ms / 186 tokens 0.34.965.764 I slot print_timing: id 0 | task 26 | graphs reused = 1 0.34.965.764 I slot print_timing: id 0 | task 26 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.965.793 I slot release: id 0 | task 26 | stop processing: n_tokens = 194, truncated = 0 0.34.966.944 I slot print_timing: id 1 | task 27 | prompt eval time = 1250.71 ms / 145 tokens ( 8.63 ms per token, 115.93 tokens per second) 0.34.966.950 I slot print_timing: id 1 | task 27 | eval time = 38.59 ms / 2 tokens ( 38.59 ms per token, 25.91 tokens per second) 0.34.966.951 I slot print_timing: id 1 | task 27 | total time = 1289.30 ms / 147 tokens 0.34.966.951 I slot print_timing: id 1 | task 27 | graphs reused = 1 0.34.966.951 I slot print_timing: id 1 | task 27 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.966.968 I slot release: id 1 | task 27 | stop processing: n_tokens = 155, truncated = 0 0.34.968.100 I slot print_timing: id 2 | task 28 | prompt eval time = 1251.65 ms / 138 tokens ( 9.07 ms per token, 110.25 tokens per second) 0.34.968.102 I slot print_timing: id 2 | task 28 | eval time = 38.69 ms / 2 tokens ( 38.69 ms per token, 25.85 tokens per second) 0.34.968.102 I slot print_timing: id 2 | task 28 | total time = 1290.34 ms / 140 tokens 0.34.968.102 I slot print_timing: id 2 | task 28 | graphs reused = 1 0.34.968.103 I slot print_timing: id 2 | task 28 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.968.114 I slot release: id 2 | task 28 | stop processing: n_tokens = 148, truncated = 0 0.34.969.196 I slot print_timing: id 3 | task 29 | prompt eval time = 1252.70 ms / 122 tokens ( 10.27 ms per token, 97.39 tokens per second) 0.34.969.200 I slot print_timing: id 3 | task 29 | eval time = 38.62 ms / 2 tokens ( 38.62 ms per token, 25.89 tokens per second) 0.34.969.201 I slot print_timing: id 3 | task 29 | total time = 1291.33 ms / 124 tokens 0.34.969.201 I slot print_timing: id 3 | task 29 | graphs reused = 1 0.34.969.201 I slot print_timing: id 3 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.969.209 I slot release: id 3 | task 29 | stop processing: n_tokens = 132, truncated = 0 0.34.969.639 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.191 0.34.974.506 I slot launch_slot_: id 0 | task 34 | processing task, is_child = 0 0.34.980.893 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.239 0.34.980.961 I slot launch_slot_: id 1 | task 36 | processing task, is_child = 0 0.34.981.015 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.250 0.34.981.081 I slot launch_slot_: id 2 | task 35 | processing task, is_child = 0 0.34.981.105 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.280 0.34.981.620 I slot launch_slot_: id 3 | task 37 | processing task, is_child = 0 0.36.255.867 I slot print_timing: id 0 | task 34 | prompt eval time = 1235.65 ms / 133 tokens ( 9.29 ms per token, 107.64 tokens per second) 0.36.255.870 I slot print_timing: id 0 | task 34 | eval time = 38.58 ms / 2 tokens ( 38.58 ms per token, 25.92 tokens per second) 0.36.255.870 I slot print_timing: id 0 | task 34 | total time = 1274.24 ms / 135 tokens 0.36.255.871 I slot print_timing: id 0 | task 34 | graphs reused = 1 0.36.255.871 I slot print_timing: id 0 | task 34 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.255.892 I slot release: id 0 | task 34 | stop processing: n_tokens = 143, truncated = 0 0.36.257.013 I slot print_timing: id 1 | task 36 | prompt eval time = 1236.72 ms / 149 tokens ( 8.30 ms per token, 120.48 tokens per second) 0.36.257.014 I slot print_timing: id 1 | task 36 | eval time = 38.55 ms / 2 tokens ( 38.55 ms per token, 25.94 tokens per second) 0.36.257.014 I slot print_timing: id 1 | task 36 | total time = 1275.27 ms / 151 tokens 0.36.257.015 I slot print_timing: id 1 | task 36 | graphs reused = 1 0.36.257.015 I slot print_timing: id 1 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.257.026 I slot release: id 1 | task 36 | stop processing: n_tokens = 159, truncated = 0 0.36.258.125 I slot print_timing: id 2 | task 35 | prompt eval time = 1237.67 ms / 181 tokens ( 6.84 ms per token, 146.24 tokens per second) 0.36.258.130 I slot print_timing: id 2 | task 35 | eval time = 38.60 ms / 2 tokens ( 38.60 ms per token, 25.91 tokens per second) 0.36.258.130 I slot print_timing: id 2 | task 35 | total time = 1276.27 ms / 183 tokens 0.36.258.131 I slot print_timing: id 2 | task 35 | graphs reused = 1 0.36.258.131 I slot print_timing: id 2 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.258.144 I slot release: id 2 | task 35 | stop processing: n_tokens = 191, truncated = 0 0.36.259.251 I slot print_timing: id 3 | task 37 | prompt eval time = 1238.75 ms / 127 tokens ( 9.75 ms per token, 102.52 tokens per second) 0.36.259.253 I slot print_timing: id 3 | task 37 | eval time = 38.54 ms / 2 tokens ( 38.54 ms per token, 25.95 tokens per second) 0.36.259.254 I slot print_timing: id 3 | task 37 | total time = 1277.29 ms / 129 tokens 0.36.259.254 I slot print_timing: id 3 | task 37 | graphs reused = 1 0.36.259.254 I slot print_timing: id 3 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.259.261 I slot release: id 3 | task 37 | stop processing: n_tokens = 137, truncated = 0 0.36.259.670 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.298 (> 0.100 thold), f_keep = 0.259 0.36.262.448 I slot launch_slot_: id 0 | task 42 | processing task, is_child = 0 0.36.271.656 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.199 0.36.271.724 I slot launch_slot_: id 2 | task 43 | processing task, is_child = 0 0.36.271.772 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.233 0.36.271.825 I slot launch_slot_: id 1 | task 44 | processing task, is_child = 0 0.36.271.850 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.290 (> 0.100 thold), f_keep = 0.277 0.36.271.901 I slot launch_slot_: id 3 | task 45 | processing task, is_child = 0 0.37.436.390 I slot print_timing: id 0 | task 42 | prompt eval time = 1126.12 ms / 115 tokens ( 9.79 ms per token, 102.12 tokens per second) 0.37.436.392 I slot print_timing: id 0 | task 42 | eval time = 38.36 ms / 2 tokens ( 38.36 ms per token, 26.07 tokens per second) 0.37.436.393 I slot print_timing: id 0 | task 42 | total time = 1164.47 ms / 117 tokens 0.37.436.393 I slot print_timing: id 0 | task 42 | graphs reused = 1 0.37.436.394 I slot print_timing: id 0 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.436.411 I slot release: id 0 | task 42 | stop processing: n_tokens = 125, truncated = 0 0.37.437.663 I slot print_timing: id 1 | task 44 | prompt eval time = 1127.03 ms / 144 tokens ( 7.83 ms per token, 127.77 tokens per second) 0.37.437.665 I slot print_timing: id 1 | task 44 | eval time = 38.56 ms / 2 tokens ( 38.56 ms per token, 25.94 tokens per second) 0.37.437.665 I slot print_timing: id 1 | task 44 | total time = 1165.58 ms / 146 tokens 0.37.437.666 I slot print_timing: id 1 | task 44 | graphs reused = 1 0.37.437.666 I slot print_timing: id 1 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.437.680 I slot release: id 1 | task 44 | stop processing: n_tokens = 154, truncated = 0 0.37.438.856 I slot print_timing: id 2 | task 43 | prompt eval time = 1127.91 ms / 148 tokens ( 7.62 ms per token, 131.22 tokens per second) 0.37.438.858 I slot print_timing: id 2 | task 43 | eval time = 38.70 ms / 2 tokens ( 38.70 ms per token, 25.84 tokens per second) 0.37.438.858 I slot print_timing: id 2 | task 43 | total time = 1166.62 ms / 150 tokens 0.37.438.858 I slot print_timing: id 2 | task 43 | graphs reused = 1 0.37.438.858 I slot print_timing: id 2 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.438.869 I slot release: id 2 | task 43 | stop processing: n_tokens = 158, truncated = 0 0.37.439.974 I slot print_timing: id 3 | task 45 | prompt eval time = 1128.85 ms / 122 tokens ( 9.25 ms per token, 108.07 tokens per second) 0.37.439.976 I slot print_timing: id 3 | task 45 | eval time = 38.73 ms / 2 tokens ( 38.73 ms per token, 25.82 tokens per second) 0.37.439.976 I slot print_timing: id 3 | task 45 | total time = 1167.58 ms / 124 tokens 0.37.439.976 I slot print_timing: id 3 | task 45 | graphs reused = 1 0.37.439.977 I slot print_timing: id 3 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.439.987 I slot release: id 3 | task 45 | stop processing: n_tokens = 132, truncated = 0 0.37.440.266 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.309 (> 0.100 thold), f_keep = 0.288 0.37.441.864 I slot launch_slot_: id 3 | task 50 | processing task, is_child = 0 0.37.449.019 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.296 0.37.449.079 I slot launch_slot_: id 0 | task 51 | processing task, is_child = 0 0.37.449.128 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.240 0.37.449.180 I slot launch_slot_: id 1 | task 52 | processing task, is_child = 0 0.37.449.206 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.308 (> 0.100 thold), f_keep = 0.234 0.37.449.257 I slot launch_slot_: id 2 | task 53 | processing task, is_child = 0 0.38.560.927 I slot print_timing: id 0 | task 51 | prompt eval time = 1072.87 ms / 124 tokens ( 8.65 ms per token, 115.58 tokens per second) 0.38.560.929 I slot print_timing: id 0 | task 51 | eval time = 38.79 ms / 2 tokens ( 38.79 ms per token, 25.78 tokens per second) 0.38.560.930 I slot print_timing: id 0 | task 51 | total time = 1111.66 ms / 126 tokens 0.38.560.930 I slot print_timing: id 0 | task 51 | graphs reused = 1 0.38.560.931 I slot print_timing: id 0 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.560.949 I slot release: id 0 | task 51 | stop processing: n_tokens = 134, truncated = 0 0.38.562.079 I slot print_timing: id 1 | task 52 | prompt eval time = 1073.87 ms / 148 tokens ( 7.26 ms per token, 137.82 tokens per second) 0.38.562.083 I slot print_timing: id 1 | task 52 | eval time = 38.84 ms / 2 tokens ( 38.84 ms per token, 25.75 tokens per second) 0.38.562.084 I slot print_timing: id 1 | task 52 | total time = 1112.70 ms / 150 tokens 0.38.562.084 I slot print_timing: id 1 | task 52 | graphs reused = 1 0.38.562.084 I slot print_timing: id 1 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.562.096 I slot release: id 1 | task 52 | stop processing: n_tokens = 158, truncated = 0 0.38.563.203 I slot print_timing: id 2 | task 53 | prompt eval time = 1074.82 ms / 111 tokens ( 9.68 ms per token, 103.27 tokens per second) 0.38.563.205 I slot print_timing: id 2 | task 53 | eval time = 38.90 ms / 2 tokens ( 38.90 ms per token, 25.71 tokens per second) 0.38.563.205 I slot print_timing: id 2 | task 53 | total time = 1113.72 ms / 113 tokens 0.38.563.206 I slot print_timing: id 2 | task 53 | graphs reused = 1 0.38.563.206 I slot print_timing: id 2 | task 53 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.563.215 I slot release: id 2 | task 53 | stop processing: n_tokens = 121, truncated = 0 0.38.564.318 I slot print_timing: id 3 | task 50 | prompt eval time = 1075.80 ms / 114 tokens ( 9.44 ms per token, 105.97 tokens per second) 0.38.564.321 I slot print_timing: id 3 | task 50 | eval time = 38.93 ms / 2 tokens ( 38.93 ms per token, 25.69 tokens per second) 0.38.564.322 I slot print_timing: id 3 | task 50 | total time = 1114.73 ms / 116 tokens 0.38.564.322 I slot print_timing: id 3 | task 50 | graphs reused = 1 0.38.564.322 I slot print_timing: id 3 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.564.331 I slot release: id 3 | task 50 | stop processing: n_tokens = 124, truncated = 0 0.38.565.696 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.293 (> 0.100 thold), f_keep = 0.331 0.38.566.668 I slot launch_slot_: id 3 | task 58 | processing task, is_child = 0 0.38.574.750 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.276 0.38.574.820 I slot launch_slot_: id 0 | task 59 | processing task, is_child = 0 0.38.574.873 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.322 (> 0.100 thold), f_keep = 0.234 0.38.574.936 I slot launch_slot_: id 1 | task 60 | processing task, is_child = 0 0.38.574.962 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.306 0.38.575.482 I slot launch_slot_: id 2 | task 61 | processing task, is_child = 0 0.39.645.637 I slot print_timing: id 0 | task 59 | prompt eval time = 1031.20 ms / 138 tokens ( 7.47 ms per token, 133.82 tokens per second) 0.39.645.639 I slot print_timing: id 0 | task 59 | eval time = 38.94 ms / 2 tokens ( 38.94 ms per token, 25.68 tokens per second) 0.39.645.639 I slot print_timing: id 0 | task 59 | total time = 1070.14 ms / 140 tokens 0.39.645.640 I slot print_timing: id 0 | task 59 | graphs reused = 1 0.39.645.640 I slot print_timing: id 0 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.645.667 I slot release: id 0 | task 59 | stop processing: n_tokens = 148, truncated = 0 0.39.646.750 I slot print_timing: id 1 | task 60 | prompt eval time = 1032.22 ms / 106 tokens ( 9.74 ms per token, 102.69 tokens per second) 0.39.646.752 I slot print_timing: id 1 | task 60 | eval time = 38.91 ms / 2 tokens ( 38.91 ms per token, 25.70 tokens per second) 0.39.646.752 I slot print_timing: id 1 | task 60 | total time = 1071.13 ms / 108 tokens 0.39.646.753 I slot print_timing: id 1 | task 60 | graphs reused = 1 0.39.646.753 I slot print_timing: id 1 | task 60 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.646.764 I slot release: id 1 | task 60 | stop processing: n_tokens = 116, truncated = 0 0.39.647.852 I slot print_timing: id 2 | task 61 | prompt eval time = 1033.32 ms / 113 tokens ( 9.14 ms per token, 109.36 tokens per second) 0.39.647.854 I slot print_timing: id 2 | task 61 | eval time = 38.79 ms / 2 tokens ( 38.79 ms per token, 25.78 tokens per second) 0.39.647.854 I slot print_timing: id 2 | task 61 | total time = 1072.11 ms / 115 tokens 0.39.647.854 I slot print_timing: id 2 | task 61 | graphs reused = 1 0.39.647.855 I slot print_timing: id 2 | task 61 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.647.862 I slot release: id 2 | task 61 | stop processing: n_tokens = 123, truncated = 0 0.39.648.969 I slot print_timing: id 3 | task 58 | prompt eval time = 1034.48 ms / 131 tokens ( 7.90 ms per token, 126.63 tokens per second) 0.39.648.971 I slot print_timing: id 3 | task 58 | eval time = 38.65 ms / 2 tokens ( 38.65 ms per token, 25.88 tokens per second) 0.39.648.971 I slot print_timing: id 3 | task 58 | total time = 1073.12 ms / 133 tokens 0.39.648.971 I slot print_timing: id 3 | task 58 | graphs reused = 1 0.39.648.972 I slot print_timing: id 3 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.648.985 I slot release: id 3 | task 58 | stop processing: n_tokens = 141, truncated = 0 0.39.650.930 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.250 0.39.653.704 I slot launch_slot_: id 0 | task 66 | processing task, is_child = 0 0.39.659.201 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.319 0.39.659.262 I slot launch_slot_: id 1 | task 67 | processing task, is_child = 0 0.39.659.308 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.301 0.39.659.360 I slot launch_slot_: id 2 | task 68 | processing task, is_child = 0 0.39.659.388 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.262 0.39.659.439 I slot launch_slot_: id 3 | task 69 | processing task, is_child = 0 0.41.068.433 I slot print_timing: id 0 | task 66 | prompt eval time = 1370.22 ms / 194 tokens ( 7.06 ms per token, 141.58 tokens per second) 0.41.068.439 I slot print_timing: id 0 | task 66 | eval time = 38.77 ms / 2 tokens ( 38.77 ms per token, 25.79 tokens per second) 0.41.068.439 I slot print_timing: id 0 | task 66 | total time = 1408.99 ms / 196 tokens 0.41.068.440 I slot print_timing: id 0 | task 66 | graphs reused = 1 0.41.068.440 I slot print_timing: id 0 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.068.472 I slot release: id 0 | task 66 | stop processing: n_tokens = 204, truncated = 0 0.41.069.600 I slot print_timing: id 1 | task 67 | prompt eval time = 1371.19 ms / 181 tokens ( 7.58 ms per token, 132.00 tokens per second) 0.41.069.602 I slot print_timing: id 1 | task 67 | eval time = 38.84 ms / 2 tokens ( 38.84 ms per token, 25.75 tokens per second) 0.41.069.602 I slot print_timing: id 1 | task 67 | total time = 1410.03 ms / 183 tokens 0.41.069.603 I slot print_timing: id 1 | task 67 | graphs reused = 1 0.41.069.603 I slot print_timing: id 1 | task 67 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.069.615 I slot release: id 1 | task 67 | stop processing: n_tokens = 191, truncated = 0 0.41.070.705 I slot print_timing: id 2 | task 68 | prompt eval time = 1372.12 ms / 134 tokens ( 10.24 ms per token, 97.66 tokens per second) 0.41.070.707 I slot print_timing: id 2 | task 68 | eval time = 38.88 ms / 2 tokens ( 38.88 ms per token, 25.72 tokens per second) 0.41.070.707 I slot print_timing: id 2 | task 68 | total time = 1411.00 ms / 136 tokens 0.41.070.707 I slot print_timing: id 2 | task 68 | graphs reused = 1 0.41.070.708 I slot print_timing: id 2 | task 68 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.070.717 I slot release: id 2 | task 68 | stop processing: n_tokens = 144, truncated = 0 0.41.071.801 I slot print_timing: id 3 | task 69 | prompt eval time = 1373.16 ms / 168 tokens ( 8.17 ms per token, 122.35 tokens per second) 0.41.071.803 I slot print_timing: id 3 | task 69 | eval time = 38.83 ms / 2 tokens ( 38.83 ms per token, 25.76 tokens per second) 0.41.071.803 I slot print_timing: id 3 | task 69 | total time = 1411.99 ms / 170 tokens 0.41.071.804 I slot print_timing: id 3 | task 69 | graphs reused = 1 0.41.071.804 I slot print_timing: id 3 | task 69 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.071.813 I slot release: id 3 | task 69 | stop processing: n_tokens = 178, truncated = 0 0.41.072.281 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.181 0.41.076.232 I slot launch_slot_: id 0 | task 74 | processing task, is_child = 0 0.41.086.038 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.194 0.41.086.104 I slot launch_slot_: id 1 | task 75 | processing task, is_child = 0 0.41.086.157 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.257 0.41.086.736 I slot launch_slot_: id 2 | task 76 | processing task, is_child = 0 0.41.086.764 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.208 0.41.087.330 I slot launch_slot_: id 3 | task 77 | processing task, is_child = 0 0.42.350.215 I slot print_timing: id 0 | task 74 | prompt eval time = 1224.21 ms / 171 tokens ( 7.16 ms per token, 139.68 tokens per second) 0.42.350.218 I slot print_timing: id 0 | task 74 | eval time = 38.66 ms / 2 tokens ( 38.66 ms per token, 25.87 tokens per second) 0.42.350.218 I slot print_timing: id 0 | task 74 | total time = 1262.87 ms / 173 tokens 0.42.350.219 I slot print_timing: id 0 | task 74 | graphs reused = 1 0.42.350.219 I slot print_timing: id 0 | task 74 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.350.245 I slot release: id 0 | task 74 | stop processing: n_tokens = 181, truncated = 0 0.42.351.341 I slot print_timing: id 1 | task 75 | prompt eval time = 1225.09 ms / 152 tokens ( 8.06 ms per token, 124.07 tokens per second) 0.42.351.343 I slot print_timing: id 1 | task 75 | eval time = 38.74 ms / 2 tokens ( 38.74 ms per token, 25.81 tokens per second) 0.42.351.343 I slot print_timing: id 1 | task 75 | total time = 1263.83 ms / 154 tokens 0.42.351.343 I slot print_timing: id 1 | task 75 | graphs reused = 1 0.42.351.344 I slot print_timing: id 1 | task 75 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.351.356 I slot release: id 1 | task 75 | stop processing: n_tokens = 162, truncated = 0 0.42.352.475 I slot print_timing: id 2 | task 76 | prompt eval time = 1226.01 ms / 143 tokens ( 8.57 ms per token, 116.64 tokens per second) 0.42.352.480 I slot print_timing: id 2 | task 76 | eval time = 38.79 ms / 2 tokens ( 38.79 ms per token, 25.78 tokens per second) 0.42.352.480 I slot print_timing: id 2 | task 76 | total time = 1264.80 ms / 145 tokens 0.42.352.481 I slot print_timing: id 2 | task 76 | graphs reused = 1 0.42.352.481 I slot print_timing: id 2 | task 76 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.352.498 I slot release: id 2 | task 76 | stop processing: n_tokens = 153, truncated = 0 0.42.353.590 I slot print_timing: id 3 | task 77 | prompt eval time = 1226.99 ms / 125 tokens ( 9.82 ms per token, 101.87 tokens per second) 0.42.353.592 I slot print_timing: id 3 | task 77 | eval time = 38.77 ms / 2 tokens ( 38.77 ms per token, 25.79 tokens per second) 0.42.353.592 I slot print_timing: id 3 | task 77 | total time = 1265.76 ms / 127 tokens 0.42.353.592 I slot print_timing: id 3 | task 77 | graphs reused = 1 0.42.353.593 I slot print_timing: id 3 | task 77 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.353.601 I slot release: id 3 | task 77 | stop processing: n_tokens = 135, truncated = 0 0.42.355.290 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.204 0.42.358.123 I slot launch_slot_: id 0 | task 82 | processing task, is_child = 0 0.42.364.565 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.281 0.42.364.628 I slot launch_slot_: id 3 | task 83 | processing task, is_child = 0 0.42.364.683 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.322 (> 0.100 thold), f_keep = 0.248 0.42.364.741 I slot launch_slot_: id 2 | task 84 | processing task, is_child = 0 0.42.364.766 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.228 0.42.365.314 I slot launch_slot_: id 1 | task 85 | processing task, is_child = 0 0.43.559.135 I slot print_timing: id 0 | task 82 | prompt eval time = 1154.92 ms / 130 tokens ( 8.88 ms per token, 112.56 tokens per second) 0.43.559.137 I slot print_timing: id 0 | task 82 | eval time = 38.88 ms / 2 tokens ( 38.88 ms per token, 25.72 tokens per second) 0.43.559.137 I slot print_timing: id 0 | task 82 | total time = 1193.81 ms / 132 tokens 0.43.559.138 I slot print_timing: id 0 | task 82 | graphs reused = 1 0.43.559.138 I slot print_timing: id 0 | task 82 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.559.155 I slot release: id 0 | task 82 | stop processing: n_tokens = 140, truncated = 0 0.43.560.259 I slot print_timing: id 1 | task 85 | prompt eval time = 1155.88 ms / 160 tokens ( 7.22 ms per token, 138.42 tokens per second) 0.43.560.262 I slot print_timing: id 1 | task 85 | eval time = 38.93 ms / 2 tokens ( 38.93 ms per token, 25.69 tokens per second) 0.43.560.263 I slot print_timing: id 1 | task 85 | total time = 1194.80 ms / 162 tokens 0.43.560.263 I slot print_timing: id 1 | task 85 | graphs reused = 1 0.43.560.264 I slot print_timing: id 1 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.560.278 I slot release: id 1 | task 85 | stop processing: n_tokens = 170, truncated = 0 0.43.561.368 I slot print_timing: id 2 | task 84 | prompt eval time = 1156.82 ms / 109 tokens ( 10.61 ms per token, 94.22 tokens per second) 0.43.561.370 I slot print_timing: id 2 | task 84 | eval time = 38.98 ms / 2 tokens ( 38.98 ms per token, 25.65 tokens per second) 0.43.561.370 I slot print_timing: id 2 | task 84 | total time = 1195.80 ms / 111 tokens 0.43.561.371 I slot print_timing: id 2 | task 84 | graphs reused = 1 0.43.561.371 I slot print_timing: id 2 | task 84 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.561.382 I slot release: id 2 | task 84 | stop processing: n_tokens = 119, truncated = 0 0.43.562.462 I slot print_timing: id 3 | task 83 | prompt eval time = 1157.94 ms / 166 tokens ( 6.98 ms per token, 143.36 tokens per second) 0.43.562.464 I slot print_timing: id 3 | task 83 | eval time = 38.84 ms / 2 tokens ( 38.84 ms per token, 25.75 tokens per second) 0.43.562.464 I slot print_timing: id 3 | task 83 | total time = 1196.78 ms / 168 tokens 0.43.562.465 I slot print_timing: id 3 | task 83 | graphs reused = 1 0.43.562.465 I slot print_timing: id 3 | task 83 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.562.475 I slot release: id 3 | task 83 | stop processing: n_tokens = 176, truncated = 0 0.43.563.375 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.264 0.43.564.471 I slot launch_slot_: id 0 | task 90 | processing task, is_child = 0 0.43.572.892 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.224 0.43.572.963 I slot launch_slot_: id 1 | task 91 | processing task, is_child = 0 0.43.573.013 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.311 0.43.573.065 I slot launch_slot_: id 2 | task 92 | processing task, is_child = 0 0.43.573.093 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.317 (> 0.100 thold), f_keep = 0.216 0.43.573.147 I slot launch_slot_: id 3 | task 93 | processing task, is_child = 0 0.44.790.342 I slot print_timing: id 0 | task 90 | prompt eval time = 1178.59 ms / 170 tokens ( 6.93 ms per token, 144.24 tokens per second) 0.44.790.344 I slot print_timing: id 0 | task 90 | eval time = 38.60 ms / 2 tokens ( 38.60 ms per token, 25.91 tokens per second) 0.44.790.344 I slot print_timing: id 0 | task 90 | total time = 1217.19 ms / 172 tokens 0.44.790.345 I slot print_timing: id 0 | task 90 | graphs reused = 1 0.44.790.345 I slot print_timing: id 0 | task 90 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.790.364 I slot release: id 0 | task 90 | stop processing: n_tokens = 180, truncated = 0 0.44.791.455 I slot print_timing: id 1 | task 91 | prompt eval time = 1179.50 ms / 167 tokens ( 7.06 ms per token, 141.58 tokens per second) 0.44.791.458 I slot print_timing: id 1 | task 91 | eval time = 38.62 ms / 2 tokens ( 38.62 ms per token, 25.89 tokens per second) 0.44.791.459 I slot print_timing: id 1 | task 91 | total time = 1218.13 ms / 169 tokens 0.44.791.459 I slot print_timing: id 1 | task 91 | graphs reused = 1 0.44.791.459 I slot print_timing: id 1 | task 91 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.791.471 I slot release: id 1 | task 91 | stop processing: n_tokens = 177, truncated = 0 0.44.792.563 I slot print_timing: id 2 | task 92 | prompt eval time = 1180.41 ms / 113 tokens ( 10.45 ms per token, 95.73 tokens per second) 0.44.792.565 I slot print_timing: id 2 | task 92 | eval time = 38.66 ms / 2 tokens ( 38.66 ms per token, 25.87 tokens per second) 0.44.792.565 I slot print_timing: id 2 | task 92 | total time = 1219.07 ms / 115 tokens 0.44.792.565 I slot print_timing: id 2 | task 92 | graphs reused = 1 0.44.792.566 I slot print_timing: id 2 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.792.575 I slot release: id 2 | task 92 | stop processing: n_tokens = 123, truncated = 0 0.44.793.655 I slot print_timing: id 3 | task 93 | prompt eval time = 1181.35 ms / 111 tokens ( 10.64 ms per token, 93.96 tokens per second) 0.44.793.657 I slot print_timing: id 3 | task 93 | eval time = 38.66 ms / 2 tokens ( 38.66 ms per token, 25.86 tokens per second) 0.44.793.657 I slot print_timing: id 3 | task 93 | total time = 1220.01 ms / 113 tokens 0.44.793.657 I slot print_timing: id 3 | task 93 | graphs reused = 1 0.44.793.658 I slot print_timing: id 3 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.793.664 I slot release: id 3 | task 93 | stop processing: n_tokens = 121, truncated = 0 0.44.794.985 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.206 0.44.798.579 I slot launch_slot_: id 0 | task 98 | processing task, is_child = 0 0.44.805.545 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.209 0.44.806.104 I slot launch_slot_: id 1 | task 99 | processing task, is_child = 0 0.44.806.159 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.301 0.44.806.219 I slot launch_slot_: id 2 | task 100 | processing task, is_child = 0 0.44.806.245 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.306 0.44.806.306 I slot launch_slot_: id 3 | task 101 | processing task, is_child = 0 0.45.933.633 I slot print_timing: id 0 | task 98 | prompt eval time = 1088.39 ms / 136 tokens ( 8.00 ms per token, 124.96 tokens per second) 0.45.933.636 I slot print_timing: id 0 | task 98 | eval time = 38.93 ms / 2 tokens ( 38.93 ms per token, 25.69 tokens per second) 0.45.933.637 I slot print_timing: id 0 | task 98 | total time = 1127.32 ms / 138 tokens 0.45.933.637 I slot print_timing: id 0 | task 98 | graphs reused = 1 0.45.933.638 I slot print_timing: id 0 | task 98 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.933.657 I slot release: id 0 | task 98 | stop processing: n_tokens = 146, truncated = 0 0.45.934.785 I slot print_timing: id 1 | task 99 | prompt eval time = 1089.34 ms / 126 tokens ( 8.65 ms per token, 115.67 tokens per second) 0.45.934.787 I slot print_timing: id 1 | task 99 | eval time = 38.99 ms / 2 tokens ( 38.99 ms per token, 25.64 tokens per second) 0.45.934.787 I slot print_timing: id 1 | task 99 | total time = 1128.34 ms / 128 tokens 0.45.934.788 I slot print_timing: id 1 | task 99 | graphs reused = 1 0.45.934.788 I slot print_timing: id 1 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.934.798 I slot release: id 1 | task 99 | stop processing: n_tokens = 136, truncated = 0 0.45.935.897 I slot print_timing: id 2 | task 100 | prompt eval time = 1090.48 ms / 149 tokens ( 7.32 ms per token, 136.64 tokens per second) 0.45.935.899 I slot print_timing: id 2 | task 100 | eval time = 38.86 ms / 2 tokens ( 38.86 ms per token, 25.73 tokens per second) 0.45.935.899 I slot print_timing: id 2 | task 100 | total time = 1129.34 ms / 151 tokens 0.45.935.899 I slot print_timing: id 2 | task 100 | graphs reused = 1 0.45.935.900 I slot print_timing: id 2 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.935.909 I slot release: id 2 | task 100 | stop processing: n_tokens = 159, truncated = 0 0.45.937.009 I slot print_timing: id 3 | task 101 | prompt eval time = 1091.60 ms / 124 tokens ( 8.80 ms per token, 113.59 tokens per second) 0.45.937.011 I slot print_timing: id 3 | task 101 | eval time = 38.74 ms / 2 tokens ( 38.74 ms per token, 25.81 tokens per second) 0.45.937.012 I slot print_timing: id 3 | task 101 | total time = 1130.34 ms / 126 tokens 0.45.937.012 I slot print_timing: id 3 | task 101 | graphs reused = 1 0.45.937.012 I slot print_timing: id 3 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.937.020 I slot release: id 3 | task 101 | stop processing: n_tokens = 134, truncated = 0 0.45.937.597 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.253 0.45.941.057 I slot launch_slot_: id 0 | task 106 | processing task, is_child = 0 0.45.947.547 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.279 0.45.947.629 I slot launch_slot_: id 1 | task 107 | processing task, is_child = 0 0.45.947.680 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.233 0.45.948.183 I slot launch_slot_: id 2 | task 108 | processing task, is_child = 0 0.45.948.215 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.276 0.45.948.748 I slot launch_slot_: id 3 | task 109 | processing task, is_child = 0 0.47.140.016 I slot print_timing: id 0 | task 106 | prompt eval time = 1152.71 ms / 126 tokens ( 9.15 ms per token, 109.31 tokens per second) 0.47.140.018 I slot print_timing: id 0 | task 106 | eval time = 38.55 ms / 2 tokens ( 38.55 ms per token, 25.94 tokens per second) 0.47.140.019 I slot print_timing: id 0 | task 106 | total time = 1191.26 ms / 128 tokens 0.47.140.019 I slot print_timing: id 0 | task 106 | graphs reused = 1 0.47.140.019 I slot print_timing: id 0 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.140.041 I slot release: id 0 | task 106 | stop processing: n_tokens = 136, truncated = 0 0.47.141.150 I slot print_timing: id 1 | task 107 | prompt eval time = 1153.68 ms / 148 tokens ( 7.80 ms per token, 128.29 tokens per second) 0.47.141.152 I slot print_timing: id 1 | task 107 | eval time = 38.60 ms / 2 tokens ( 38.60 ms per token, 25.91 tokens per second) 0.47.141.152 I slot print_timing: id 1 | task 107 | total time = 1192.28 ms / 150 tokens 0.47.141.153 I slot print_timing: id 1 | task 107 | graphs reused = 1 0.47.141.153 I slot print_timing: id 1 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.141.166 I slot release: id 1 | task 107 | stop processing: n_tokens = 158, truncated = 0 0.47.142.261 I slot print_timing: id 2 | task 108 | prompt eval time = 1154.64 ms / 143 tokens ( 8.07 ms per token, 123.85 tokens per second) 0.47.142.263 I slot print_timing: id 2 | task 108 | eval time = 38.64 ms / 2 tokens ( 38.64 ms per token, 25.88 tokens per second) 0.47.142.264 I slot print_timing: id 2 | task 108 | total time = 1193.28 ms / 145 tokens 0.47.142.264 I slot print_timing: id 2 | task 108 | graphs reused = 1 0.47.142.265 I slot print_timing: id 2 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.142.277 I slot release: id 2 | task 108 | stop processing: n_tokens = 153, truncated = 0 0.47.143.386 I slot print_timing: id 3 | task 109 | prompt eval time = 1155.63 ms / 136 tokens ( 8.50 ms per token, 117.68 tokens per second) 0.47.143.388 I slot print_timing: id 3 | task 109 | eval time = 38.66 ms / 2 tokens ( 38.66 ms per token, 25.86 tokens per second) 0.47.143.389 I slot print_timing: id 3 | task 109 | total time = 1194.30 ms / 138 tokens 0.47.143.390 I slot print_timing: id 3 | task 109 | graphs reused = 1 0.47.143.390 I slot print_timing: id 3 | task 109 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.143.408 I slot release: id 3 | task 109 | stop processing: n_tokens = 146, truncated = 0 0.47.145.085 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.280 (> 0.100 thold), f_keep = 0.272 0.47.146.348 I slot launch_slot_: id 0 | task 114 | processing task, is_child = 0 0.47.154.901 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.319 (> 0.100 thold), f_keep = 0.241 0.47.154.962 I slot launch_slot_: id 1 | task 115 | processing task, is_child = 0 0.47.155.014 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.295 (> 0.100 thold), f_keep = 0.260 0.47.155.073 I slot launch_slot_: id 3 | task 116 | processing task, is_child = 0 0.47.155.102 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.248 0.47.155.155 I slot launch_slot_: id 2 | task 117 | processing task, is_child = 0 0.48.338.492 I slot print_timing: id 0 | task 114 | prompt eval time = 1144.20 ms / 123 tokens ( 9.30 ms per token, 107.50 tokens per second) 0.48.338.495 I slot print_timing: id 0 | task 114 | eval time = 39.13 ms / 2 tokens ( 39.13 ms per token, 25.56 tokens per second) 0.48.338.496 I slot print_timing: id 0 | task 114 | total time = 1183.32 ms / 125 tokens 0.48.338.497 I slot print_timing: id 0 | task 114 | graphs reused = 1 0.48.338.497 I slot print_timing: id 0 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.338.515 I slot release: id 0 | task 114 | stop processing: n_tokens = 133, truncated = 0 0.48.339.637 I slot print_timing: id 1 | task 115 | prompt eval time = 1145.28 ms / 110 tokens ( 10.41 ms per token, 96.05 tokens per second) 0.48.339.638 I slot print_timing: id 1 | task 115 | eval time = 39.01 ms / 2 tokens ( 39.01 ms per token, 25.63 tokens per second) 0.48.339.639 I slot print_timing: id 1 | task 115 | total time = 1184.29 ms / 112 tokens 0.48.339.639 I slot print_timing: id 1 | task 115 | graphs reused = 1 0.48.339.640 I slot print_timing: id 1 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.339.651 I slot release: id 1 | task 115 | stop processing: n_tokens = 120, truncated = 0 0.48.340.743 I slot print_timing: id 2 | task 117 | prompt eval time = 1146.36 ms / 175 tokens ( 6.55 ms per token, 152.66 tokens per second) 0.48.340.747 I slot print_timing: id 2 | task 117 | eval time = 38.88 ms / 2 tokens ( 38.88 ms per token, 25.72 tokens per second) 0.48.340.747 I slot print_timing: id 2 | task 117 | total time = 1185.24 ms / 177 tokens 0.48.340.748 I slot print_timing: id 2 | task 117 | graphs reused = 1 0.48.340.748 I slot print_timing: id 2 | task 117 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.340.760 I slot release: id 2 | task 117 | stop processing: n_tokens = 185, truncated = 0 0.48.341.849 I slot print_timing: id 3 | task 116 | prompt eval time = 1147.41 ms / 120 tokens ( 9.56 ms per token, 104.58 tokens per second) 0.48.341.850 I slot print_timing: id 3 | task 116 | eval time = 38.77 ms / 2 tokens ( 38.77 ms per token, 25.79 tokens per second) 0.48.341.851 I slot print_timing: id 3 | task 116 | total time = 1186.18 ms / 122 tokens 0.48.341.851 I slot print_timing: id 3 | task 116 | graphs reused = 1 0.48.341.851 I slot print_timing: id 3 | task 116 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.341.860 I slot release: id 3 | task 116 | stop processing: n_tokens = 130, truncated = 0 0.48.343.522 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.299 (> 0.100 thold), f_keep = 0.317 0.48.344.744 I slot launch_slot_: id 1 | task 122 | processing task, is_child = 0 0.48.351.831 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.292 0.48.351.896 I slot launch_slot_: id 3 | task 123 | processing task, is_child = 0 0.48.351.948 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.145 (> 0.100 thold), f_keep = 0.278 0.48.352.003 I slot launch_slot_: id 0 | task 124 | processing task, is_child = 0 0.48.352.034 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.200 0.48.352.595 I slot launch_slot_: id 2 | task 125 | processing task, is_child = 0 0.49.867.329 I slot print_timing: id 0 | task 124 | prompt eval time = 1475.73 ms / 247 tokens ( 5.97 ms per token, 167.37 tokens per second) 0.49.867.331 I slot print_timing: id 0 | task 124 | eval time = 38.99 ms / 2 tokens ( 38.99 ms per token, 25.65 tokens per second) 0.49.867.332 I slot print_timing: id 0 | task 124 | total time = 1514.72 ms / 249 tokens 0.49.867.332 I slot print_timing: id 0 | task 124 | graphs reused = 1 0.49.867.333 I slot print_timing: id 0 | task 124 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.867.355 I slot release: id 0 | task 124 | stop processing: n_tokens = 257, truncated = 0 0.49.868.452 I slot print_timing: id 1 | task 122 | prompt eval time = 1476.69 ms / 118 tokens ( 12.51 ms per token, 79.91 tokens per second) 0.49.868.455 I slot print_timing: id 1 | task 122 | eval time = 39.05 ms / 2 tokens ( 39.05 ms per token, 25.61 tokens per second) 0.49.868.456 I slot print_timing: id 1 | task 122 | total time = 1515.73 ms / 120 tokens 0.49.868.456 I slot print_timing: id 1 | task 122 | graphs reused = 1 0.49.868.456 I slot print_timing: id 1 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.868.467 I slot release: id 1 | task 122 | stop processing: n_tokens = 128, truncated = 0 0.49.869.555 I slot print_timing: id 2 | task 125 | prompt eval time = 1477.78 ms / 182 tokens ( 8.12 ms per token, 123.16 tokens per second) 0.49.869.556 I slot print_timing: id 2 | task 125 | eval time = 38.95 ms / 2 tokens ( 38.95 ms per token, 25.68 tokens per second) 0.49.869.556 I slot print_timing: id 2 | task 125 | total time = 1516.73 ms / 184 tokens 0.49.869.557 I slot print_timing: id 2 | task 125 | graphs reused = 1 0.49.869.557 I slot print_timing: id 2 | task 125 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.869.570 I slot release: id 2 | task 125 | stop processing: n_tokens = 192, truncated = 0 0.49.870.670 I slot print_timing: id 3 | task 123 | prompt eval time = 1478.90 ms / 138 tokens ( 10.72 ms per token, 93.31 tokens per second) 0.49.870.673 I slot print_timing: id 3 | task 123 | eval time = 38.83 ms / 2 tokens ( 38.83 ms per token, 25.75 tokens per second) 0.49.870.674 I slot print_timing: id 3 | task 123 | total time = 1517.73 ms / 140 tokens 0.49.870.674 I slot print_timing: id 3 | task 123 | graphs reused = 1 0.49.870.674 I slot print_timing: id 3 | task 123 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.870.683 I slot release: id 3 | task 123 | stop processing: n_tokens = 148, truncated = 0 0.49.871.835 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.305 0.49.872.979 I slot launch_slot_: id 1 | task 130 | processing task, is_child = 0 0.49.884.521 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.247 (> 0.100 thold), f_keep = 0.257 0.49.885.045 I slot launch_slot_: id 3 | task 131 | processing task, is_child = 0 0.49.885.106 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.144 0.49.885.168 I slot launch_slot_: id 0 | task 132 | processing task, is_child = 0 0.49.885.207 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.193 0.49.885.269 I slot launch_slot_: id 2 | task 133 | processing task, is_child = 0 0.51.391.941 I slot print_timing: id 0 | task 132 | prompt eval time = 1467.92 ms / 162 tokens ( 9.06 ms per token, 110.36 tokens per second) 0.51.391.944 I slot print_timing: id 0 | task 132 | eval time = 38.74 ms / 2 tokens ( 38.74 ms per token, 25.81 tokens per second) 0.51.391.945 I slot print_timing: id 0 | task 132 | total time = 1506.66 ms / 164 tokens 0.51.391.945 I slot print_timing: id 0 | task 132 | graphs reused = 1 0.51.391.946 I slot print_timing: id 0 | task 132 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.391.965 I slot release: id 0 | task 132 | stop processing: n_tokens = 172, truncated = 0 0.51.393.063 I slot print_timing: id 1 | task 130 | prompt eval time = 1468.84 ms / 158 tokens ( 9.30 ms per token, 107.57 tokens per second) 0.51.393.065 I slot print_timing: id 1 | task 130 | eval time = 38.82 ms / 2 tokens ( 38.82 ms per token, 25.76 tokens per second) 0.51.393.065 I slot print_timing: id 1 | task 130 | total time = 1507.65 ms / 160 tokens 0.51.393.066 I slot print_timing: id 1 | task 130 | graphs reused = 1 0.51.393.066 I slot print_timing: id 1 | task 130 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.393.076 I slot release: id 1 | task 130 | stop processing: n_tokens = 168, truncated = 0 0.51.394.159 I slot print_timing: id 2 | task 133 | prompt eval time = 1469.78 ms / 229 tokens ( 6.42 ms per token, 155.81 tokens per second) 0.51.394.161 I slot print_timing: id 2 | task 133 | eval time = 38.87 ms / 2 tokens ( 38.87 ms per token, 25.73 tokens per second) 0.51.394.161 I slot print_timing: id 2 | task 133 | total time = 1508.64 ms / 231 tokens 0.51.394.161 I slot print_timing: id 2 | task 133 | graphs reused = 1 0.51.394.162 I slot print_timing: id 2 | task 133 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.394.176 I slot release: id 2 | task 133 | stop processing: n_tokens = 239, truncated = 0 0.51.395.254 I slot print_timing: id 3 | task 131 | prompt eval time = 1470.81 ms / 145 tokens ( 10.14 ms per token, 98.59 tokens per second) 0.51.395.256 I slot print_timing: id 3 | task 131 | eval time = 38.81 ms / 2 tokens ( 38.81 ms per token, 25.76 tokens per second) 0.51.395.256 I slot print_timing: id 3 | task 131 | total time = 1509.62 ms / 147 tokens 0.51.395.257 I slot print_timing: id 3 | task 131 | graphs reused = 1 0.51.395.257 I slot print_timing: id 3 | task 131 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.395.265 I slot release: id 3 | task 131 | stop processing: n_tokens = 155, truncated = 0 0.51.395.828 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.345 (> 0.100 thold), f_keep = 0.258 0.51.398.891 I slot launch_slot_: id 3 | task 138 | processing task, is_child = 0 0.51.409.809 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.185 (> 0.100 thold), f_keep = 0.215 0.51.410.446 I slot launch_slot_: id 0 | task 139 | processing task, is_child = 0 0.51.410.509 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.302 (> 0.100 thold), f_keep = 0.226 0.51.410.572 I slot launch_slot_: id 1 | task 140 | processing task, is_child = 0 0.51.410.604 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.155 0.51.410.662 I slot launch_slot_: id 2 | task 141 | processing task, is_child = 0 0.52.622.338 I slot print_timing: id 0 | task 139 | prompt eval time = 1172.97 ms / 191 tokens ( 6.14 ms per token, 162.83 tokens per second) 0.52.622.340 I slot print_timing: id 0 | task 139 | eval time = 38.69 ms / 2 tokens ( 38.69 ms per token, 25.85 tokens per second) 0.52.622.341 I slot print_timing: id 0 | task 139 | total time = 1211.66 ms / 193 tokens 0.52.622.341 I slot print_timing: id 0 | task 139 | graphs reused = 1 0.52.622.342 I slot print_timing: id 0 | task 139 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.622.369 I slot release: id 0 | task 139 | stop processing: n_tokens = 201, truncated = 0 0.52.623.476 I slot print_timing: id 1 | task 140 | prompt eval time = 1173.97 ms / 117 tokens ( 10.03 ms per token, 99.66 tokens per second) 0.52.623.477 I slot print_timing: id 1 | task 140 | eval time = 38.71 ms / 2 tokens ( 38.71 ms per token, 25.83 tokens per second) 0.52.623.478 I slot print_timing: id 1 | task 140 | total time = 1212.68 ms / 119 tokens 0.52.623.478 I slot print_timing: id 1 | task 140 | graphs reused = 1 0.52.623.478 I slot print_timing: id 1 | task 140 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.623.489 I slot release: id 1 | task 140 | stop processing: n_tokens = 127, truncated = 0 0.52.624.579 I slot print_timing: id 2 | task 141 | prompt eval time = 1174.94 ms / 143 tokens ( 8.22 ms per token, 121.71 tokens per second) 0.52.624.581 I slot print_timing: id 2 | task 141 | eval time = 38.73 ms / 2 tokens ( 38.73 ms per token, 25.82 tokens per second) 0.52.624.581 I slot print_timing: id 2 | task 141 | total time = 1213.67 ms / 145 tokens 0.52.624.582 I slot print_timing: id 2 | task 141 | graphs reused = 1 0.52.624.582 I slot print_timing: id 2 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.624.596 I slot release: id 2 | task 141 | stop processing: n_tokens = 153, truncated = 0 0.52.625.710 I slot print_timing: id 3 | task 138 | prompt eval time = 1175.87 ms / 107 tokens ( 10.99 ms per token, 91.00 tokens per second) 0.52.625.712 I slot print_timing: id 3 | task 138 | eval time = 38.79 ms / 2 tokens ( 38.79 ms per token, 25.78 tokens per second) 0.52.625.712 I slot print_timing: id 3 | task 138 | total time = 1214.66 ms / 109 tokens 0.52.625.712 I slot print_timing: id 3 | task 138 | graphs reused = 1 0.52.625.712 I slot print_timing: id 3 | task 138 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.625.722 I slot release: id 3 | task 138 | stop processing: n_tokens = 117, truncated = 0 0.52.626.927 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.184 0.52.629.955 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.52.634.153 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.290 (> 0.100 thold), f_keep = 0.299 0.52.634.225 I slot launch_slot_: id 1 | task 147 | processing task, is_child = 0 0.52.634.275 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.242 0.52.634.333 I slot launch_slot_: id 2 | task 148 | processing task, is_child = 0 0.52.634.356 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.314 (> 0.100 thold), f_keep = 0.325 0.52.634.409 I slot launch_slot_: id 3 | task 149 | processing task, is_child = 0 0.53.854.746 I slot print_timing: id 0 | task 146 | prompt eval time = 1181.24 ms / 175 tokens ( 6.75 ms per token, 148.15 tokens per second) 0.53.854.749 I slot print_timing: id 0 | task 146 | eval time = 39.08 ms / 2 tokens ( 39.08 ms per token, 25.59 tokens per second) 0.53.854.749 I slot print_timing: id 0 | task 146 | total time = 1220.33 ms / 177 tokens 0.53.854.750 I slot print_timing: id 0 | task 146 | graphs reused = 1 0.53.854.750 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.854.774 I slot release: id 0 | task 146 | stop processing: n_tokens = 185, truncated = 0 0.53.855.878 I slot print_timing: id 1 | task 147 | prompt eval time = 1182.21 ms / 122 tokens ( 9.69 ms per token, 103.20 tokens per second) 0.53.855.880 I slot print_timing: id 1 | task 147 | eval time = 39.12 ms / 2 tokens ( 39.12 ms per token, 25.56 tokens per second) 0.53.855.881 I slot print_timing: id 1 | task 147 | total time = 1221.33 ms / 124 tokens 0.53.855.881 I slot print_timing: id 1 | task 147 | graphs reused = 1 0.53.855.881 I slot print_timing: id 1 | task 147 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.855.893 I slot release: id 1 | task 147 | stop processing: n_tokens = 132, truncated = 0 0.53.856.985 I slot print_timing: id 2 | task 148 | prompt eval time = 1183.35 ms / 140 tokens ( 8.45 ms per token, 118.31 tokens per second) 0.53.856.986 I slot print_timing: id 2 | task 148 | eval time = 38.96 ms / 2 tokens ( 38.96 ms per token, 25.67 tokens per second) 0.53.856.986 I slot print_timing: id 2 | task 148 | total time = 1222.32 ms / 142 tokens 0.53.856.987 I slot print_timing: id 2 | task 148 | graphs reused = 1 0.53.856.987 I slot print_timing: id 2 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.856.998 I slot release: id 2 | task 148 | stop processing: n_tokens = 150, truncated = 0 0.53.858.104 I slot print_timing: id 3 | task 149 | prompt eval time = 1184.50 ms / 112 tokens ( 10.58 ms per token, 94.55 tokens per second) 0.53.858.106 I slot print_timing: id 3 | task 149 | eval time = 38.82 ms / 2 tokens ( 38.82 ms per token, 25.76 tokens per second) 0.53.858.106 I slot print_timing: id 3 | task 149 | total time = 1223.32 ms / 114 tokens 0.53.858.106 I slot print_timing: id 3 | task 149 | graphs reused = 1 0.53.858.106 I slot print_timing: id 3 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.858.117 I slot release: id 3 | task 149 | stop processing: n_tokens = 122, truncated = 0 0.53.859.482 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.200 0.53.863.551 I slot launch_slot_: id 0 | task 154 | processing task, is_child = 0 0.53.869.069 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.253 (> 0.100 thold), f_keep = 0.280 0.53.869.131 I slot launch_slot_: id 1 | task 155 | processing task, is_child = 0 0.53.869.180 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.247 0.53.869.235 I slot launch_slot_: id 2 | task 156 | processing task, is_child = 0 0.53.869.263 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.290 (> 0.100 thold), f_keep = 0.311 0.53.869.721 I slot launch_slot_: id 3 | task 157 | processing task, is_child = 0 0.55.075.545 I slot print_timing: id 0 | task 154 | prompt eval time = 1167.07 ms / 162 tokens ( 7.20 ms per token, 138.81 tokens per second) 0.55.075.550 I slot print_timing: id 0 | task 154 | eval time = 38.75 ms / 2 tokens ( 38.75 ms per token, 25.81 tokens per second) 0.55.075.551 I slot print_timing: id 0 | task 154 | total time = 1205.82 ms / 164 tokens 0.55.075.552 I slot print_timing: id 0 | task 154 | graphs reused = 1 0.55.075.552 I slot print_timing: id 0 | task 154 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.075.582 I slot release: id 0 | task 154 | stop processing: n_tokens = 172, truncated = 0 0.55.076.718 I slot print_timing: id 1 | task 155 | prompt eval time = 1168.10 ms / 137 tokens ( 8.53 ms per token, 117.28 tokens per second) 0.55.076.720 I slot print_timing: id 1 | task 155 | eval time = 38.78 ms / 2 tokens ( 38.78 ms per token, 25.78 tokens per second) 0.55.076.721 I slot print_timing: id 1 | task 155 | total time = 1206.88 ms / 139 tokens 0.55.076.721 I slot print_timing: id 1 | task 155 | graphs reused = 1 0.55.076.721 I slot print_timing: id 1 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.076.731 I slot release: id 1 | task 155 | stop processing: n_tokens = 147, truncated = 0 0.55.077.833 I slot print_timing: id 2 | task 156 | prompt eval time = 1169.05 ms / 138 tokens ( 8.47 ms per token, 118.04 tokens per second) 0.55.077.837 I slot print_timing: id 2 | task 156 | eval time = 38.84 ms / 2 tokens ( 38.84 ms per token, 25.75 tokens per second) 0.55.077.837 I slot print_timing: id 2 | task 156 | total time = 1207.89 ms / 140 tokens 0.55.077.837 I slot print_timing: id 2 | task 156 | graphs reused = 1 0.55.077.838 I slot print_timing: id 2 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.077.848 I slot release: id 2 | task 156 | stop processing: n_tokens = 148, truncated = 0 0.55.078.948 I slot print_timing: id 3 | task 157 | prompt eval time = 1170.03 ms / 122 tokens ( 9.59 ms per token, 104.27 tokens per second) 0.55.078.960 I slot print_timing: id 3 | task 157 | eval time = 38.87 ms / 2 tokens ( 38.87 ms per token, 25.73 tokens per second) 0.55.078.962 I slot print_timing: id 3 | task 157 | total time = 1208.90 ms / 124 tokens 0.55.078.962 I slot print_timing: id 3 | task 157 | graphs reused = 1 0.55.078.962 I slot print_timing: id 3 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.078.973 I slot release: id 3 | task 157 | stop processing: n_tokens = 132, truncated = 0 0.55.079.269 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.215 0.55.082.753 I slot launch_slot_: id 0 | task 162 | processing task, is_child = 0 0.55.090.219 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.252 0.55.090.297 I slot launch_slot_: id 1 | task 163 | processing task, is_child = 0 0.55.090.346 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.250 0.55.090.400 I slot launch_slot_: id 2 | task 164 | processing task, is_child = 0 0.55.090.425 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.198 (> 0.100 thold), f_keep = 0.280 0.55.090.477 I slot launch_slot_: id 3 | task 165 | processing task, is_child = 0 0.56.456.447 I slot print_timing: id 0 | task 162 | prompt eval time = 1326.78 ms / 132 tokens ( 10.05 ms per token, 99.49 tokens per second) 0.56.456.450 I slot print_timing: id 0 | task 162 | eval time = 39.18 ms / 2 tokens ( 39.18 ms per token, 25.52 tokens per second) 0.56.456.450 I slot print_timing: id 0 | task 162 | total time = 1365.96 ms / 134 tokens 0.56.456.451 I slot print_timing: id 0 | task 162 | graphs reused = 1 0.56.456.451 I slot print_timing: id 0 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.456.471 I slot release: id 0 | task 162 | stop processing: n_tokens = 142, truncated = 0 0.56.457.578 I slot print_timing: id 1 | task 163 | prompt eval time = 1327.84 ms / 183 tokens ( 7.26 ms per token, 137.82 tokens per second) 0.56.457.580 I slot print_timing: id 1 | task 163 | eval time = 39.12 ms / 2 tokens ( 39.12 ms per token, 25.56 tokens per second) 0.56.457.581 I slot print_timing: id 1 | task 163 | total time = 1366.95 ms / 185 tokens 0.56.457.581 I slot print_timing: id 1 | task 163 | graphs reused = 1 0.56.457.582 I slot print_timing: id 1 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.457.604 I slot release: id 1 | task 163 | stop processing: n_tokens = 193, truncated = 0 0.56.458.699 I slot print_timing: id 2 | task 164 | prompt eval time = 1328.92 ms / 183 tokens ( 7.26 ms per token, 137.71 tokens per second) 0.56.458.707 I slot print_timing: id 2 | task 164 | eval time = 39.03 ms / 2 tokens ( 39.03 ms per token, 25.62 tokens per second) 0.56.458.707 I slot print_timing: id 2 | task 164 | total time = 1367.96 ms / 185 tokens 0.56.458.707 I slot print_timing: id 2 | task 164 | graphs reused = 1 0.56.458.708 I slot print_timing: id 2 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.458.720 I slot release: id 2 | task 164 | stop processing: n_tokens = 193, truncated = 0 0.56.459.825 I slot print_timing: id 3 | task 165 | prompt eval time = 1330.09 ms / 178 tokens ( 7.47 ms per token, 133.83 tokens per second) 0.56.459.827 I slot print_timing: id 3 | task 165 | eval time = 38.88 ms / 2 tokens ( 38.88 ms per token, 25.72 tokens per second) 0.56.459.827 I slot print_timing: id 3 | task 165 | total time = 1368.97 ms / 180 tokens 0.56.459.827 I slot print_timing: id 3 | task 165 | graphs reused = 1 0.56.459.828 I slot print_timing: id 3 | task 165 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.459.839 I slot release: id 3 | task 165 | stop processing: n_tokens = 188, truncated = 0 0.56.460.466 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.261 0.56.462.857 I slot launch_slot_: id 0 | task 170 | processing task, is_child = 0 0.56.474.437 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.192 0.56.474.514 I slot launch_slot_: id 1 | task 171 | processing task, is_child = 0 0.56.474.585 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.192 0.56.475.205 I slot launch_slot_: id 2 | task 172 | processing task, is_child = 0 0.56.475.244 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.197 0.56.475.829 I slot launch_slot_: id 3 | task 173 | processing task, is_child = 0 0.57.437.844 I slot print_timing: id 0 | task 170 | prompt eval time = 923.26 ms / 117 tokens ( 7.89 ms per token, 126.73 tokens per second) 0.57.437.847 I slot print_timing: id 0 | task 170 | eval time = 38.75 ms / 2 tokens ( 38.75 ms per token, 25.81 tokens per second) 0.57.437.847 I slot print_timing: id 0 | task 170 | total time = 962.01 ms / 119 tokens 0.57.437.847 I slot print_timing: id 0 | task 170 | graphs reused = 1 0.57.437.848 I slot print_timing: id 0 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.437.875 I slot release: id 0 | task 170 | stop processing: n_tokens = 127, truncated = 0 0.57.441.219 I slot print_timing: id 3 | task 173 | prompt eval time = 926.29 ms / 117 tokens ( 7.92 ms per token, 126.31 tokens per second) 0.57.441.221 I slot print_timing: id 3 | task 173 | eval time = 38.75 ms / 2 tokens ( 38.75 ms per token, 25.81 tokens per second) 0.57.441.222 I slot print_timing: id 3 | task 173 | total time = 965.04 ms / 119 tokens 0.57.441.222 I slot print_timing: id 3 | task 173 | graphs reused = 1 0.57.441.222 I slot print_timing: id 3 | task 173 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.441.233 I slot release: id 3 | task 173 | stop processing: n_tokens = 127, truncated = 0 0.57.441.238 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.293 (> 0.100 thold), f_keep = 0.323 0.57.442.475 I slot launch_slot_: id 3 | task 178 | processing task, is_child = 0 0.57.478.133 I slot print_timing: id 1 | task 171 | prompt eval time = 924.32 ms / 125 tokens ( 7.39 ms per token, 135.24 tokens per second) 0.57.478.134 I slot print_timing: id 1 | task 171 | eval time = 77.86 ms / 3 tokens ( 38.93 ms per token, 25.69 tokens per second) 0.57.478.135 I slot print_timing: id 1 | task 171 | total time = 1002.18 ms / 128 tokens 0.57.478.136 I slot print_timing: id 1 | task 171 | graphs reused = 1 0.57.478.136 I slot print_timing: id 1 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.478.154 I slot release: id 1 | task 171 | stop processing: n_tokens = 136, truncated = 0 0.57.479.386 I slot print_timing: id 2 | task 172 | prompt eval time = 925.30 ms / 125 tokens ( 7.40 ms per token, 135.09 tokens per second) 0.57.479.388 I slot print_timing: id 2 | task 172 | eval time = 78.01 ms / 3 tokens ( 39.00 ms per token, 25.64 tokens per second) 0.57.479.388 I slot print_timing: id 2 | task 172 | total time = 1003.31 ms / 128 tokens 0.57.479.389 I slot print_timing: id 2 | task 172 | graphs reused = 1 0.57.479.389 I slot print_timing: id 2 | task 172 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.479.404 I slot release: id 2 | task 172 | stop processing: n_tokens = 136, truncated = 0 0.57.479.408 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.291 0.57.479.490 I slot launch_slot_: id 0 | task 180 | processing task, is_child = 0 0.57.482.524 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.272 0.57.483.052 I slot launch_slot_: id 1 | task 181 | processing task, is_child = 0 0.57.483.079 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.272 0.57.483.597 I slot launch_slot_: id 2 | task 182 | processing task, is_child = 0 0.58.642.881 I slot print_timing: id 3 | task 178 | prompt eval time = 1115.84 ms / 131 tokens ( 8.52 ms per token, 117.40 tokens per second) 0.58.642.883 I slot print_timing: id 3 | task 178 | eval time = 83.47 ms / 2 tokens ( 83.47 ms per token, 11.98 tokens per second) 0.58.642.884 I slot print_timing: id 3 | task 178 | total time = 1199.31 ms / 133 tokens 0.58.642.884 I slot print_timing: id 3 | task 178 | graphs reused = 1 0.58.642.885 I slot print_timing: id 3 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.642.905 I slot release: id 3 | task 178 | stop processing: n_tokens = 141, truncated = 0 0.58.677.322 I slot print_timing: id 0 | task 180 | prompt eval time = 1155.65 ms / 143 tokens ( 8.08 ms per token, 123.74 tokens per second) 0.58.677.326 I slot print_timing: id 0 | task 180 | eval time = 38.07 ms / 2 tokens ( 38.07 ms per token, 26.27 tokens per second) 0.58.677.326 I slot print_timing: id 0 | task 180 | total time = 1193.72 ms / 145 tokens 0.58.677.326 I slot print_timing: id 0 | task 180 | graphs reused = 1 0.58.677.327 I slot print_timing: id 0 | task 180 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.677.346 I slot release: id 0 | task 180 | stop processing: n_tokens = 153, truncated = 0 0.58.678.499 I slot print_timing: id 1 | task 181 | prompt eval time = 1156.76 ms / 130 tokens ( 8.90 ms per token, 112.38 tokens per second) 0.58.678.501 I slot print_timing: id 1 | task 181 | eval time = 38.00 ms / 2 tokens ( 38.00 ms per token, 26.32 tokens per second) 0.58.678.501 I slot print_timing: id 1 | task 181 | total time = 1194.76 ms / 132 tokens 0.58.678.501 I slot print_timing: id 1 | task 181 | graphs reused = 1 0.58.678.501 I slot print_timing: id 1 | task 181 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.678.511 I slot release: id 1 | task 181 | stop processing: n_tokens = 140, truncated = 0 0.58.679.630 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.242 0.58.682.936 I slot launch_slot_: id 0 | task 187 | processing task, is_child = 0 0.58.688.354 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.264 0.58.688.417 I slot launch_slot_: id 1 | task 188 | processing task, is_child = 0 0.58.688.443 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.333 (> 0.100 thold), f_keep = 0.270 0.58.688.937 I slot launch_slot_: id 3 | task 189 | processing task, is_child = 0 0.58.750.508 I slot print_timing: id 2 | task 182 | prompt eval time = 1157.95 ms / 132 tokens ( 8.77 ms per token, 113.99 tokens per second) 0.58.750.513 I slot print_timing: id 2 | task 182 | eval time = 108.69 ms / 3 tokens ( 54.35 ms per token, 18.40 tokens per second) 0.58.750.513 I slot print_timing: id 2 | task 182 | total time = 1266.65 ms / 135 tokens 0.58.750.513 I slot print_timing: id 2 | task 182 | graphs reused = 1 0.58.750.514 I slot print_timing: id 2 | task 182 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.750.533 I slot release: id 2 | task 182 | stop processing: n_tokens = 143, truncated = 0 0.59.239.941 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.259 0.59.474.596 I slot launch_slot_: id 2 | task 192 | processing task, is_child = 0 0.59.924.855 I slot print_timing: id 0 | task 187 | prompt eval time = 887.49 ms / 124 tokens ( 7.16 ms per token, 139.72 tokens per second) 0.59.924.861 I slot print_timing: id 0 | task 187 | eval time = 348.42 ms / 2 tokens ( 348.42 ms per token, 2.87 tokens per second) 0.59.924.862 I slot print_timing: id 0 | task 187 | total time = 1235.91 ms / 126 tokens 0.59.924.862 I slot print_timing: id 0 | task 187 | graphs reused = 1 0.59.924.862 I slot print_timing: id 0 | task 187 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.924.887 I slot release: id 0 | task 187 | stop processing: n_tokens = 134, truncated = 0 0.59.926.022 I slot print_timing: id 1 | task 188 | prompt eval time = 888.59 ms / 131 tokens ( 6.78 ms per token, 147.42 tokens per second) 0.59.926.028 I slot print_timing: id 1 | task 188 | eval time = 348.37 ms / 2 tokens ( 348.37 ms per token, 2.87 tokens per second) 0.59.926.029 I slot print_timing: id 1 | task 188 | total time = 1236.96 ms / 133 tokens 0.59.926.029 I slot print_timing: id 1 | task 188 | graphs reused = 1 0.59.926.029 I slot print_timing: id 1 | task 188 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.926.051 I slot release: id 1 | task 188 | stop processing: n_tokens = 141, truncated = 0 0.59.927.192 I slot print_timing: id 3 | task 189 | prompt eval time = 889.73 ms / 105 tokens ( 8.47 ms per token, 118.01 tokens per second) 0.59.927.193 I slot print_timing: id 3 | task 189 | eval time = 348.29 ms / 2 tokens ( 348.29 ms per token, 2.87 tokens per second) 0.59.927.193 I slot print_timing: id 3 | task 189 | total time = 1238.02 ms / 107 tokens 0.59.927.194 I slot print_timing: id 3 | task 189 | graphs reused = 1 0.59.927.194 I slot print_timing: id 3 | task 189 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.927.204 I slot release: id 3 | task 189 | stop processing: n_tokens = 115, truncated = 0 0.59.963.583 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.276 0.59.966.117 I slot launch_slot_: id 0 | task 196 | processing task, is_child = 0 0.59.968.972 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.262 0.59.969.043 I slot launch_slot_: id 1 | task 197 | processing task, is_child = 0 0.59.969.070 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.322 0.59.969.130 I slot launch_slot_: id 3 | task 198 | processing task, is_child = 0 1.00.030.736 I slot print_timing: id 2 | task 192 | prompt eval time = 486.96 ms / 160 tokens ( 3.04 ms per token, 328.57 tokens per second) 1.00.030.739 I slot print_timing: id 2 | task 192 | eval time = 67.16 ms / 2 tokens ( 67.16 ms per token, 14.89 tokens per second) 1.00.030.739 I slot print_timing: id 2 | task 192 | total time = 554.11 ms / 162 tokens 1.00.030.740 I slot print_timing: id 2 | task 192 | graphs reused = 1 1.00.030.740 I slot print_timing: id 2 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.030.761 I slot release: id 2 | task 192 | stop processing: n_tokens = 170, truncated = 0 1.00.625.351 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.218 1.00.976.031 I slot launch_slot_: id 2 | task 201 | processing task, is_child = 0 1.01.372.101 I slot print_timing: id 0 | task 196 | prompt eval time = 1109.25 ms / 143 tokens ( 7.76 ms per token, 128.92 tokens per second) 1.01.372.106 I slot print_timing: id 0 | task 196 | eval time = 293.71 ms / 2 tokens ( 293.71 ms per token, 3.40 tokens per second) 1.01.372.107 I slot print_timing: id 0 | task 196 | total time = 1402.96 ms / 145 tokens 1.01.372.107 I slot print_timing: id 0 | task 196 | graphs reused = 1 1.01.372.108 I slot print_timing: id 0 | task 196 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.372.133 I slot release: id 0 | task 196 | stop processing: n_tokens = 153, truncated = 0 1.01.373.263 I slot print_timing: id 1 | task 197 | prompt eval time = 1110.21 ms / 161 tokens ( 6.90 ms per token, 145.02 tokens per second) 1.01.373.266 I slot print_timing: id 1 | task 197 | eval time = 293.81 ms / 2 tokens ( 293.81 ms per token, 3.40 tokens per second) 1.01.373.266 I slot print_timing: id 1 | task 197 | total time = 1404.01 ms / 163 tokens 1.01.373.266 I slot print_timing: id 1 | task 197 | graphs reused = 1 1.01.373.267 I slot print_timing: id 1 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.373.284 I slot release: id 1 | task 197 | stop processing: n_tokens = 171, truncated = 0 1.01.374.413 I slot print_timing: id 3 | task 198 | prompt eval time = 1111.34 ms / 173 tokens ( 6.42 ms per token, 155.67 tokens per second) 1.01.374.416 I slot print_timing: id 3 | task 198 | eval time = 293.71 ms / 2 tokens ( 293.71 ms per token, 3.40 tokens per second) 1.01.374.417 I slot print_timing: id 3 | task 198 | total time = 1405.05 ms / 175 tokens 1.01.374.417 I slot print_timing: id 3 | task 198 | graphs reused = 1 1.01.374.417 I slot print_timing: id 3 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.374.437 I slot release: id 3 | task 198 | stop processing: n_tokens = 183, truncated = 0 1.01.410.244 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.242 1.01.413.042 I slot launch_slot_: id 0 | task 205 | processing task, is_child = 0 1.01.418.933 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.216 1.01.419.474 I slot launch_slot_: id 1 | task 206 | processing task, is_child = 0 1.01.419.506 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.306 (> 0.100 thold), f_keep = 0.202 1.01.419.566 I slot launch_slot_: id 3 | task 207 | processing task, is_child = 0 1.02.307.204 I slot print_timing: id 2 | task 201 | prompt eval time = 432.28 ms / 113 tokens ( 3.83 ms per token, 261.40 tokens per second) 1.02.307.207 I slot print_timing: id 2 | task 201 | eval time = 896.96 ms / 3 tokens ( 448.48 ms per token, 2.23 tokens per second) 1.02.307.207 I slot print_timing: id 2 | task 201 | total time = 1329.24 ms / 116 tokens 1.02.307.208 I slot print_timing: id 2 | task 201 | graphs reused = 1 1.02.307.209 I slot print_timing: id 2 | task 201 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.307.241 I slot release: id 2 | task 201 | stop processing: n_tokens = 124, truncated = 0 1.02.384.652 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.314 (> 0.100 thold), f_keep = 0.306 1.02.385.939 I slot launch_slot_: id 2 | task 211 | processing task, is_child = 0 1.02.441.732 I slot print_timing: id 0 | task 205 | prompt eval time = 962.79 ms / 140 tokens ( 6.88 ms per token, 145.41 tokens per second) 1.02.441.735 I slot print_timing: id 0 | task 205 | eval time = 59.37 ms / 2 tokens ( 59.37 ms per token, 16.84 tokens per second) 1.02.441.736 I slot print_timing: id 0 | task 205 | total time = 1022.15 ms / 142 tokens 1.02.441.736 I slot print_timing: id 0 | task 205 | graphs reused = 1 1.02.441.737 I slot print_timing: id 0 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.441.757 I slot release: id 0 | task 205 | stop processing: n_tokens = 150, truncated = 0 1.02.442.958 I slot print_timing: id 1 | task 206 | prompt eval time = 963.82 ms / 152 tokens ( 6.34 ms per token, 157.71 tokens per second) 1.02.442.960 I slot print_timing: id 1 | task 206 | eval time = 59.44 ms / 2 tokens ( 59.44 ms per token, 16.82 tokens per second) 1.02.442.961 I slot print_timing: id 1 | task 206 | total time = 1023.27 ms / 154 tokens 1.02.442.961 I slot print_timing: id 1 | task 206 | graphs reused = 1 1.02.442.961 I slot print_timing: id 1 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.442.973 I slot release: id 1 | task 206 | stop processing: n_tokens = 162, truncated = 0 1.02.444.109 I slot print_timing: id 3 | task 207 | prompt eval time = 964.83 ms / 112 tokens ( 8.61 ms per token, 116.08 tokens per second) 1.02.444.110 I slot print_timing: id 3 | task 207 | eval time = 59.46 ms / 2 tokens ( 59.46 ms per token, 16.82 tokens per second) 1.02.444.111 I slot print_timing: id 3 | task 207 | total time = 1024.30 ms / 114 tokens 1.02.444.112 I slot print_timing: id 3 | task 207 | graphs reused = 1 1.02.444.112 I slot print_timing: id 3 | task 207 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.444.120 I slot release: id 3 | task 207 | stop processing: n_tokens = 122, truncated = 0 1.02.446.180 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.247 1.02.682.250 I slot launch_slot_: id 0 | task 215 | processing task, is_child = 0 1.02.685.890 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.301 (> 0.100 thold), f_keep = 0.228 1.02.686.460 I slot launch_slot_: id 1 | task 214 | processing task, is_child = 0 1.02.686.488 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.303 1.02.686.553 I slot launch_slot_: id 3 | task 216 | processing task, is_child = 0 1.03.553.761 I slot print_timing: id 2 | task 211 | prompt eval time = 365.21 ms / 112 tokens ( 3.26 ms per token, 306.68 tokens per second) 1.03.553.767 I slot print_timing: id 2 | task 211 | eval time = 802.60 ms / 2 tokens ( 802.60 ms per token, 1.25 tokens per second) 1.03.553.769 I slot print_timing: id 2 | task 211 | total time = 1167.80 ms / 114 tokens 1.03.553.769 I slot print_timing: id 2 | task 211 | graphs reused = 1 1.03.553.770 I slot print_timing: id 2 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.553.801 I slot release: id 2 | task 211 | stop processing: n_tokens = 122, truncated = 0 1.03.632.079 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.303 1.03.633.400 I slot launch_slot_: id 2 | task 220 | processing task, is_child = 0 1.03.689.337 I slot print_timing: id 0 | task 215 | prompt eval time = 943.20 ms / 155 tokens ( 6.09 ms per token, 164.33 tokens per second) 1.03.689.340 I slot print_timing: id 0 | task 215 | eval time = 59.58 ms / 2 tokens ( 59.58 ms per token, 16.78 tokens per second) 1.03.689.341 I slot print_timing: id 0 | task 215 | total time = 1002.78 ms / 157 tokens 1.03.689.341 I slot print_timing: id 0 | task 215 | graphs reused = 1 1.03.689.342 I slot print_timing: id 0 | task 215 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.689.361 I slot release: id 0 | task 215 | stop processing: n_tokens = 165, truncated = 0 1.03.690.474 I slot print_timing: id 1 | task 214 | prompt eval time = 944.18 ms / 114 tokens ( 8.28 ms per token, 120.74 tokens per second) 1.03.690.479 I slot print_timing: id 1 | task 214 | eval time = 59.59 ms / 2 tokens ( 59.59 ms per token, 16.78 tokens per second) 1.03.690.479 I slot print_timing: id 1 | task 214 | total time = 1003.77 ms / 116 tokens 1.03.690.480 I slot print_timing: id 1 | task 214 | graphs reused = 1 1.03.690.480 I slot print_timing: id 1 | task 214 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.690.491 I slot release: id 1 | task 214 | stop processing: n_tokens = 124, truncated = 0 1.03.691.585 I slot print_timing: id 3 | task 216 | prompt eval time = 944.80 ms / 134 tokens ( 7.05 ms per token, 141.83 tokens per second) 1.03.691.587 I slot print_timing: id 3 | task 216 | eval time = 59.51 ms / 2 tokens ( 59.51 ms per token, 16.80 tokens per second) 1.03.691.588 I slot print_timing: id 3 | task 216 | total time = 1004.31 ms / 136 tokens 1.03.691.588 I slot print_timing: id 3 | task 216 | graphs reused = 1 1.03.691.589 I slot print_timing: id 3 | task 216 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.691.598 I slot release: id 3 | task 216 | stop processing: n_tokens = 144, truncated = 0 1.03.693.499 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.292 (> 0.100 thold), f_keep = 0.306 1.03.930.924 I slot launch_slot_: id 1 | task 223 | processing task, is_child = 0 1.03.939.389 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.224 1.03.939.456 I slot launch_slot_: id 0 | task 224 | processing task, is_child = 0 1.03.939.484 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.257 1.03.939.546 I slot launch_slot_: id 3 | task 225 | processing task, is_child = 0 1.04.910.843 I slot print_timing: id 2 | task 220 | prompt eval time = 370.66 ms / 125 tokens ( 2.97 ms per token, 337.24 tokens per second) 1.04.910.849 I slot print_timing: id 2 | task 220 | eval time = 906.77 ms / 2 tokens ( 906.77 ms per token, 1.10 tokens per second) 1.04.910.850 I slot print_timing: id 2 | task 220 | total time = 1277.43 ms / 127 tokens 1.04.910.850 I slot print_timing: id 2 | task 220 | graphs reused = 1 1.04.910.851 I slot print_timing: id 2 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.910.886 I slot release: id 2 | task 220 | stop processing: n_tokens = 135, truncated = 0 1.04.989.780 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.274 1.04.994.064 I slot launch_slot_: id 2 | task 229 | processing task, is_child = 0 1.05.049.935 I slot print_timing: id 0 | task 224 | prompt eval time = 1047.33 ms / 170 tokens ( 6.16 ms per token, 162.32 tokens per second) 1.05.049.941 I slot print_timing: id 0 | task 224 | eval time = 63.05 ms / 2 tokens ( 63.05 ms per token, 15.86 tokens per second) 1.05.049.941 I slot print_timing: id 0 | task 224 | total time = 1110.38 ms / 172 tokens 1.05.049.941 I slot print_timing: id 0 | task 224 | graphs reused = 1 1.05.049.942 I slot print_timing: id 0 | task 224 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.049.963 I slot release: id 0 | task 224 | stop processing: n_tokens = 180, truncated = 0 1.05.051.099 I slot print_timing: id 1 | task 223 | prompt eval time = 1048.68 ms / 121 tokens ( 8.67 ms per token, 115.38 tokens per second) 1.05.051.103 I slot print_timing: id 1 | task 223 | eval time = 62.73 ms / 2 tokens ( 62.73 ms per token, 15.94 tokens per second) 1.05.051.103 I slot print_timing: id 1 | task 223 | total time = 1111.41 ms / 123 tokens 1.05.051.103 I slot print_timing: id 1 | task 223 | graphs reused = 1 1.05.051.104 I slot print_timing: id 1 | task 223 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.051.112 I slot release: id 1 | task 223 | stop processing: n_tokens = 131, truncated = 0 1.05.052.213 I slot print_timing: id 3 | task 225 | prompt eval time = 1049.44 ms / 159 tokens ( 6.60 ms per token, 151.51 tokens per second) 1.05.052.217 I slot print_timing: id 3 | task 225 | eval time = 62.44 ms / 2 tokens ( 62.44 ms per token, 16.02 tokens per second) 1.05.052.218 I slot print_timing: id 3 | task 225 | total time = 1111.88 ms / 161 tokens 1.05.052.218 I slot print_timing: id 3 | task 225 | graphs reused = 1 1.05.052.218 I slot print_timing: id 3 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.052.229 I slot release: id 3 | task 225 | stop processing: n_tokens = 169, truncated = 0 1.05.054.192 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.311 (> 0.100 thold), f_keep = 0.206 1.05.293.813 I slot launch_slot_: id 0 | task 232 | processing task, is_child = 0 1.05.298.818 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.282 1.05.298.889 I slot launch_slot_: id 1 | task 233 | processing task, is_child = 0 1.05.298.922 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.225 1.05.298.986 I slot launch_slot_: id 3 | task 234 | processing task, is_child = 0 1.06.272.133 I slot print_timing: id 2 | task 229 | prompt eval time = 369.56 ms / 131 tokens ( 2.82 ms per token, 354.47 tokens per second) 1.06.272.135 I slot print_timing: id 2 | task 229 | eval time = 908.49 ms / 2 tokens ( 908.49 ms per token, 1.10 tokens per second) 1.06.272.136 I slot print_timing: id 2 | task 229 | total time = 1278.06 ms / 133 tokens 1.06.272.136 I slot print_timing: id 2 | task 229 | graphs reused = 1 1.06.272.137 I slot print_timing: id 2 | task 229 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.272.168 I slot release: id 2 | task 229 | stop processing: n_tokens = 141, truncated = 0 1.06.351.820 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.262 1.06.355.756 I slot launch_slot_: id 2 | task 238 | processing task, is_child = 0 1.06.411.408 I slot print_timing: id 0 | task 232 | prompt eval time = 1050.06 ms / 110 tokens ( 9.55 ms per token, 104.76 tokens per second) 1.06.411.412 I slot print_timing: id 0 | task 232 | eval time = 62.36 ms / 2 tokens ( 62.36 ms per token, 16.04 tokens per second) 1.06.411.412 I slot print_timing: id 0 | task 232 | total time = 1112.41 ms / 112 tokens 1.06.411.413 I slot print_timing: id 0 | task 232 | graphs reused = 1 1.06.411.413 I slot print_timing: id 0 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.411.429 I slot release: id 0 | task 232 | stop processing: n_tokens = 120, truncated = 0 1.06.412.578 I slot print_timing: id 1 | task 233 | prompt eval time = 1051.29 ms / 188 tokens ( 5.59 ms per token, 178.83 tokens per second) 1.06.412.580 I slot print_timing: id 1 | task 233 | eval time = 62.17 ms / 2 tokens ( 62.17 ms per token, 16.08 tokens per second) 1.06.412.580 I slot print_timing: id 1 | task 233 | total time = 1113.46 ms / 190 tokens 1.06.412.581 I slot print_timing: id 1 | task 233 | graphs reused = 1 1.06.412.581 I slot print_timing: id 1 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.412.602 I slot release: id 1 | task 233 | stop processing: n_tokens = 198, truncated = 0 1.06.413.710 I slot print_timing: id 3 | task 234 | prompt eval time = 1052.11 ms / 155 tokens ( 6.79 ms per token, 147.32 tokens per second) 1.06.413.711 I slot print_timing: id 3 | task 234 | eval time = 61.90 ms / 2 tokens ( 61.90 ms per token, 16.16 tokens per second) 1.06.413.712 I slot print_timing: id 3 | task 234 | total time = 1114.01 ms / 157 tokens 1.06.413.713 I slot print_timing: id 3 | task 234 | graphs reused = 1 1.06.413.713 I slot print_timing: id 3 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.413.724 I slot release: id 3 | task 234 | stop processing: n_tokens = 165, truncated = 0 1.06.415.875 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.308 1.06.705.156 I slot launch_slot_: id 0 | task 241 | processing task, is_child = 0 1.06.713.392 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.187 1.06.713.992 I slot launch_slot_: id 1 | task 242 | processing task, is_child = 0 1.06.714.024 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.253 (> 0.100 thold), f_keep = 0.224 1.06.714.085 I slot launch_slot_: id 3 | task 243 | processing task, is_child = 0 1.07.627.516 I slot print_timing: id 2 | task 238 | prompt eval time = 422.91 ms / 148 tokens ( 2.86 ms per token, 349.95 tokens per second) 1.07.627.520 I slot print_timing: id 2 | task 238 | eval time = 848.83 ms / 2 tokens ( 848.83 ms per token, 1.18 tokens per second) 1.07.627.520 I slot print_timing: id 2 | task 238 | total time = 1271.74 ms / 150 tokens 1.07.627.521 I slot print_timing: id 2 | task 238 | graphs reused = 1 1.07.627.521 I slot print_timing: id 2 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.627.558 I slot release: id 2 | task 238 | stop processing: n_tokens = 158, truncated = 0 1.07.705.662 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.234 1.07.708.338 I slot launch_slot_: id 2 | task 247 | processing task, is_child = 0 1.07.764.059 I slot print_timing: id 0 | task 241 | prompt eval time = 989.37 ms / 117 tokens ( 8.46 ms per token, 118.26 tokens per second) 1.07.764.061 I slot print_timing: id 0 | task 241 | eval time = 60.60 ms / 2 tokens ( 60.60 ms per token, 16.50 tokens per second) 1.07.764.061 I slot print_timing: id 0 | task 241 | total time = 1049.97 ms / 119 tokens 1.07.764.062 I slot print_timing: id 0 | task 241 | graphs reused = 1 1.07.764.062 I slot print_timing: id 0 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.764.078 I slot release: id 0 | task 241 | stop processing: n_tokens = 127, truncated = 0 1.07.765.195 I slot print_timing: id 1 | task 242 | prompt eval time = 990.35 ms / 159 tokens ( 6.23 ms per token, 160.55 tokens per second) 1.07.765.200 I slot print_timing: id 1 | task 242 | eval time = 60.62 ms / 2 tokens ( 60.62 ms per token, 16.50 tokens per second) 1.07.765.200 I slot print_timing: id 1 | task 242 | total time = 1050.98 ms / 161 tokens 1.07.765.201 I slot print_timing: id 1 | task 242 | graphs reused = 1 1.07.765.201 I slot print_timing: id 1 | task 242 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.765.216 I slot release: id 1 | task 242 | stop processing: n_tokens = 169, truncated = 0 1.07.766.320 I slot print_timing: id 3 | task 243 | prompt eval time = 990.80 ms / 137 tokens ( 7.23 ms per token, 138.27 tokens per second) 1.07.766.325 I slot print_timing: id 3 | task 243 | eval time = 60.66 ms / 2 tokens ( 60.66 ms per token, 16.48 tokens per second) 1.07.766.325 I slot print_timing: id 3 | task 243 | total time = 1051.46 ms / 139 tokens 1.07.766.326 I slot print_timing: id 3 | task 243 | graphs reused = 1 1.07.766.326 I slot print_timing: id 3 | task 243 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.766.342 I slot release: id 3 | task 243 | stop processing: n_tokens = 147, truncated = 0 1.07.768.359 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.291 1.08.055.898 I slot launch_slot_: id 0 | task 250 | processing task, is_child = 0 1.08.063.793 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.219 1.08.064.477 I slot launch_slot_: id 1 | task 251 | processing task, is_child = 0 1.08.064.510 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.291 (> 0.100 thold), f_keep = 0.252 1.08.065.048 I slot launch_slot_: id 3 | task 252 | processing task, is_child = 0 1.08.933.779 I slot print_timing: id 2 | task 247 | prompt eval time = 421.25 ms / 136 tokens ( 3.10 ms per token, 322.85 tokens per second) 1.08.933.781 I slot print_timing: id 2 | task 247 | eval time = 804.18 ms / 2 tokens ( 804.18 ms per token, 1.24 tokens per second) 1.08.933.782 I slot print_timing: id 2 | task 247 | total time = 1225.43 ms / 138 tokens 1.08.933.782 I slot print_timing: id 2 | task 247 | graphs reused = 1 1.08.933.783 I slot print_timing: id 2 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.933.803 I slot release: id 2 | task 247 | stop processing: n_tokens = 146, truncated = 0 1.09.012.058 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.253 1.09.013.517 I slot launch_slot_: id 2 | task 256 | processing task, is_child = 0 1.09.069.377 I slot print_timing: id 0 | task 250 | prompt eval time = 944.43 ms / 152 tokens ( 6.21 ms per token, 160.94 tokens per second) 1.09.069.381 I slot print_timing: id 0 | task 250 | eval time = 59.89 ms / 2 tokens ( 59.89 ms per token, 16.70 tokens per second) 1.09.069.382 I slot print_timing: id 0 | task 250 | total time = 1004.32 ms / 154 tokens 1.09.069.382 I slot print_timing: id 0 | task 250 | graphs reused = 1 1.09.069.383 I slot print_timing: id 0 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.069.403 I slot release: id 0 | task 250 | stop processing: n_tokens = 162, truncated = 0 1.09.070.542 I slot print_timing: id 1 | task 251 | prompt eval time = 945.62 ms / 124 tokens ( 7.63 ms per token, 131.13 tokens per second) 1.09.070.546 I slot print_timing: id 1 | task 251 | eval time = 59.75 ms / 2 tokens ( 59.75 ms per token, 16.74 tokens per second) 1.09.070.546 I slot print_timing: id 1 | task 251 | total time = 1005.37 ms / 126 tokens 1.09.070.547 I slot print_timing: id 1 | task 251 | graphs reused = 1 1.09.070.547 I slot print_timing: id 1 | task 251 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.070.558 I slot release: id 1 | task 251 | stop processing: n_tokens = 134, truncated = 0 1.09.071.666 I slot print_timing: id 3 | task 252 | prompt eval time = 946.27 ms / 118 tokens ( 8.02 ms per token, 124.70 tokens per second) 1.09.071.669 I slot print_timing: id 3 | task 252 | eval time = 59.61 ms / 2 tokens ( 59.61 ms per token, 16.77 tokens per second) 1.09.071.669 I slot print_timing: id 3 | task 252 | total time = 1005.89 ms / 120 tokens 1.09.071.670 I slot print_timing: id 3 | task 252 | graphs reused = 1 1.09.071.670 I slot print_timing: id 3 | task 252 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.071.677 I slot release: id 3 | task 252 | stop processing: n_tokens = 128, truncated = 0 1.09.073.768 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.228 1.09.365.229 I slot launch_slot_: id 0 | task 259 | processing task, is_child = 0 1.09.369.534 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.276 1.09.369.608 I slot launch_slot_: id 1 | task 260 | processing task, is_child = 0 1.09.369.640 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.289 1.09.369.699 I slot launch_slot_: id 3 | task 261 | processing task, is_child = 0 1.10.366.866 I slot print_timing: id 2 | task 256 | prompt eval time = 420.88 ms / 159 tokens ( 2.65 ms per token, 377.78 tokens per second) 1.10.366.873 I slot print_timing: id 2 | task 256 | eval time = 932.46 ms / 2 tokens ( 932.46 ms per token, 1.07 tokens per second) 1.10.366.873 I slot print_timing: id 2 | task 256 | total time = 1353.33 ms / 161 tokens 1.10.366.874 I slot print_timing: id 2 | task 256 | graphs reused = 1 1.10.366.874 I slot print_timing: id 2 | task 256 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.366.900 I slot release: id 2 | task 256 | stop processing: n_tokens = 169, truncated = 0 1.10.448.501 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.219 1.10.452.320 I slot launch_slot_: id 2 | task 265 | processing task, is_child = 0 1.10.507.907 I slot print_timing: id 0 | task 259 | prompt eval time = 1076.35 ms / 164 tokens ( 6.56 ms per token, 152.37 tokens per second) 1.10.507.911 I slot print_timing: id 0 | task 259 | eval time = 61.85 ms / 2 tokens ( 61.85 ms per token, 16.17 tokens per second) 1.10.507.912 I slot print_timing: id 0 | task 259 | total time = 1138.20 ms / 166 tokens 1.10.507.912 I slot print_timing: id 0 | task 259 | graphs reused = 1 1.10.507.913 I slot print_timing: id 0 | task 259 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.507.934 I slot release: id 0 | task 259 | stop processing: n_tokens = 174, truncated = 0 1.10.509.040 I slot print_timing: id 1 | task 260 | prompt eval time = 1077.46 ms / 152 tokens ( 7.09 ms per token, 141.07 tokens per second) 1.10.509.042 I slot print_timing: id 1 | task 260 | eval time = 61.76 ms / 2 tokens ( 61.76 ms per token, 16.19 tokens per second) 1.10.509.043 I slot print_timing: id 1 | task 260 | total time = 1139.22 ms / 154 tokens 1.10.509.043 I slot print_timing: id 1 | task 260 | graphs reused = 1 1.10.509.043 I slot print_timing: id 1 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.509.056 I slot release: id 1 | task 260 | stop processing: n_tokens = 162, truncated = 0 1.10.510.168 I slot print_timing: id 3 | task 261 | prompt eval time = 1077.98 ms / 154 tokens ( 7.00 ms per token, 142.86 tokens per second) 1.10.510.170 I slot print_timing: id 3 | task 261 | eval time = 61.67 ms / 2 tokens ( 61.67 ms per token, 16.22 tokens per second) 1.10.510.171 I slot print_timing: id 3 | task 261 | total time = 1139.65 ms / 156 tokens 1.10.510.171 I slot print_timing: id 3 | task 261 | graphs reused = 1 1.10.510.171 I slot print_timing: id 3 | task 261 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.510.183 I slot release: id 3 | task 261 | stop processing: n_tokens = 164, truncated = 0 1.10.838.035 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.314 (> 0.100 thold), f_keep = 0.213 1.10.843.529 I slot launch_slot_: id 0 | task 269 | processing task, is_child = 0 1.10.848.482 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.228 1.10.848.561 I slot launch_slot_: id 1 | task 270 | processing task, is_child = 0 1.10.848.591 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.226 1.10.848.655 I slot launch_slot_: id 3 | task 271 | processing task, is_child = 0 1.10.910.166 I slot print_timing: id 2 | task 265 | prompt eval time = 385.70 ms / 158 tokens ( 2.44 ms per token, 409.65 tokens per second) 1.10.910.168 I slot print_timing: id 2 | task 265 | eval time = 72.14 ms / 2 tokens ( 72.14 ms per token, 13.86 tokens per second) 1.10.910.168 I slot print_timing: id 2 | task 265 | total time = 457.84 ms / 160 tokens 1.10.910.169 I slot print_timing: id 2 | task 265 | graphs reused = 1 1.10.910.169 I slot print_timing: id 2 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.910.186 I slot release: id 2 | task 265 | stop processing: n_tokens = 168, truncated = 0 1.11.348.381 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.330 (> 0.100 thold), f_keep = 0.220 1.11.701.531 I slot launch_slot_: id 2 | task 274 | processing task, is_child = 0 1.12.097.104 I slot print_timing: id 0 | task 269 | prompt eval time = 955.98 ms / 109 tokens ( 8.77 ms per token, 114.02 tokens per second) 1.12.097.110 I slot print_timing: id 0 | task 269 | eval time = 292.46 ms / 2 tokens ( 292.46 ms per token, 3.42 tokens per second) 1.12.097.111 I slot print_timing: id 0 | task 269 | total time = 1248.43 ms / 111 tokens 1.12.097.111 I slot print_timing: id 0 | task 269 | graphs reused = 1 1.12.097.112 I slot print_timing: id 0 | task 269 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.097.141 I slot release: id 0 | task 269 | stop processing: n_tokens = 119, truncated = 0 1.12.098.295 I slot print_timing: id 1 | task 270 | prompt eval time = 957.05 ms / 117 tokens ( 8.18 ms per token, 122.25 tokens per second) 1.12.098.297 I slot print_timing: id 1 | task 270 | eval time = 292.46 ms / 2 tokens ( 292.46 ms per token, 3.42 tokens per second) 1.12.098.298 I slot print_timing: id 1 | task 270 | total time = 1249.50 ms / 119 tokens 1.12.098.298 I slot print_timing: id 1 | task 270 | graphs reused = 1 1.12.098.298 I slot print_timing: id 1 | task 270 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.098.315 I slot release: id 1 | task 270 | stop processing: n_tokens = 127, truncated = 0 1.12.099.466 I slot print_timing: id 3 | task 271 | prompt eval time = 958.09 ms / 188 tokens ( 5.10 ms per token, 196.22 tokens per second) 1.12.099.467 I slot print_timing: id 3 | task 271 | eval time = 292.46 ms / 2 tokens ( 292.46 ms per token, 3.42 tokens per second) 1.12.099.468 I slot print_timing: id 3 | task 271 | total time = 1250.55 ms / 190 tokens 1.12.099.468 I slot print_timing: id 3 | task 271 | graphs reused = 1 1.12.099.468 I slot print_timing: id 3 | task 271 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.099.488 I slot release: id 3 | task 271 | stop processing: n_tokens = 198, truncated = 0 1.12.134.660 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.311 1.12.136.271 I slot launch_slot_: id 0 | task 278 | processing task, is_child = 0 1.12.141.301 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.291 1.12.141.378 I slot launch_slot_: id 1 | task 279 | processing task, is_child = 0 1.12.141.411 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.270 (> 0.100 thold), f_keep = 0.187 1.12.141.476 I slot launch_slot_: id 3 | task 280 | processing task, is_child = 0 1.12.203.062 I slot print_timing: id 2 | task 274 | prompt eval time = 431.12 ms / 103 tokens ( 4.19 ms per token, 238.91 tokens per second) 1.12.203.064 I slot print_timing: id 2 | task 274 | eval time = 68.40 ms / 2 tokens ( 68.40 ms per token, 14.62 tokens per second) 1.12.203.065 I slot print_timing: id 2 | task 274 | total time = 499.52 ms / 105 tokens 1.12.203.065 I slot print_timing: id 2 | task 274 | graphs reused = 1 1.12.203.066 I slot print_timing: id 2 | task 274 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.203.086 I slot release: id 2 | task 274 | stop processing: n_tokens = 113, truncated = 0 1.12.658.054 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.327 1.12.896.051 I slot launch_slot_: id 2 | task 283 | processing task, is_child = 0 1.13.342.820 I slot print_timing: id 0 | task 278 | prompt eval time = 856.16 ms / 113 tokens ( 7.58 ms per token, 131.98 tokens per second) 1.13.342.825 I slot print_timing: id 0 | task 278 | eval time = 345.17 ms / 2 tokens ( 345.17 ms per token, 2.90 tokens per second) 1.13.342.827 I slot print_timing: id 0 | task 278 | total time = 1201.34 ms / 115 tokens 1.13.342.827 I slot print_timing: id 0 | task 278 | graphs reused = 1 1.13.342.828 I slot print_timing: id 0 | task 278 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.342.850 I slot release: id 0 | task 278 | stop processing: n_tokens = 123, truncated = 0 1.13.343.941 I slot print_timing: id 1 | task 279 | prompt eval time = 857.14 ms / 125 tokens ( 6.86 ms per token, 145.83 tokens per second) 1.13.343.943 I slot print_timing: id 1 | task 279 | eval time = 345.20 ms / 2 tokens ( 345.20 ms per token, 2.90 tokens per second) 1.13.343.944 I slot print_timing: id 1 | task 279 | total time = 1202.34 ms / 127 tokens 1.13.343.944 I slot print_timing: id 1 | task 279 | graphs reused = 1 1.13.343.944 I slot print_timing: id 1 | task 279 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.343.961 I slot release: id 1 | task 279 | stop processing: n_tokens = 135, truncated = 0 1.13.345.115 I slot print_timing: id 3 | task 280 | prompt eval time = 858.20 ms / 128 tokens ( 6.70 ms per token, 149.15 tokens per second) 1.13.345.117 I slot print_timing: id 3 | task 280 | eval time = 345.20 ms / 2 tokens ( 345.20 ms per token, 2.90 tokens per second) 1.13.345.118 I slot print_timing: id 3 | task 280 | total time = 1203.41 ms / 130 tokens 1.13.345.118 I slot print_timing: id 3 | task 280 | graphs reused = 1 1.13.345.118 I slot print_timing: id 3 | task 280 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.345.134 I slot release: id 3 | task 280 | stop processing: n_tokens = 138, truncated = 0 1.13.381.679 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.247 (> 0.100 thold), f_keep = 0.309 1.13.382.767 I slot launch_slot_: id 0 | task 287 | processing task, is_child = 0 1.13.387.986 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.274 1.13.388.513 I slot launch_slot_: id 1 | task 288 | processing task, is_child = 0 1.13.388.542 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.268 1.13.388.602 I slot launch_slot_: id 3 | task 289 | processing task, is_child = 0 1.13.450.083 I slot print_timing: id 2 | task 283 | prompt eval time = 484.35 ms / 166 tokens ( 2.92 ms per token, 342.73 tokens per second) 1.13.450.089 I slot print_timing: id 2 | task 283 | eval time = 68.41 ms / 2 tokens ( 68.41 ms per token, 14.62 tokens per second) 1.13.450.089 I slot print_timing: id 2 | task 283 | total time = 552.75 ms / 168 tokens 1.13.450.090 I slot print_timing: id 2 | task 283 | graphs reused = 1 1.13.450.090 I slot print_timing: id 2 | task 283 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.450.110 I slot release: id 2 | task 283 | stop processing: n_tokens = 176, truncated = 0 1.13.993.818 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.210 1.14.232.067 I slot launch_slot_: id 2 | task 292 | processing task, is_child = 0 1.14.630.247 I slot print_timing: id 0 | task 287 | prompt eval time = 946.62 ms / 145 tokens ( 6.53 ms per token, 153.18 tokens per second) 1.14.630.252 I slot print_timing: id 0 | task 287 | eval time = 295.00 ms / 2 tokens ( 295.00 ms per token, 3.39 tokens per second) 1.14.630.253 I slot print_timing: id 0 | task 287 | total time = 1241.62 ms / 147 tokens 1.14.630.253 I slot print_timing: id 0 | task 287 | graphs reused = 1 1.14.630.254 I slot print_timing: id 0 | task 287 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.630.288 I slot release: id 0 | task 287 | stop processing: n_tokens = 155, truncated = 0 1.14.631.397 I slot print_timing: id 1 | task 288 | prompt eval time = 947.64 ms / 139 tokens ( 6.82 ms per token, 146.68 tokens per second) 1.14.631.398 I slot print_timing: id 1 | task 288 | eval time = 295.04 ms / 2 tokens ( 295.04 ms per token, 3.39 tokens per second) 1.14.631.399 I slot print_timing: id 1 | task 288 | total time = 1242.68 ms / 141 tokens 1.14.631.399 I slot print_timing: id 1 | task 288 | graphs reused = 1 1.14.631.400 I slot print_timing: id 1 | task 288 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.631.417 I slot release: id 1 | task 288 | stop processing: n_tokens = 149, truncated = 0 1.14.632.594 I slot print_timing: id 3 | task 289 | prompt eval time = 948.63 ms / 127 tokens ( 7.47 ms per token, 133.88 tokens per second) 1.14.632.595 I slot print_timing: id 3 | task 289 | eval time = 295.14 ms / 2 tokens ( 295.14 ms per token, 3.39 tokens per second) 1.14.632.596 I slot print_timing: id 3 | task 289 | total time = 1243.77 ms / 129 tokens 1.14.632.596 I slot print_timing: id 3 | task 289 | graphs reused = 1 1.14.632.597 I slot print_timing: id 3 | task 289 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.632.615 I slot release: id 3 | task 289 | stop processing: n_tokens = 137, truncated = 0 1.14.668.936 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.239 1.14.671.943 I slot launch_slot_: id 0 | task 296 | processing task, is_child = 0 1.14.676.216 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.248 1.14.676.285 I slot launch_slot_: id 1 | task 297 | processing task, is_child = 0 1.14.676.313 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.270 1.14.676.792 I slot launch_slot_: id 3 | task 298 | processing task, is_child = 0 1.14.738.242 I slot print_timing: id 2 | task 292 | prompt eval time = 433.66 ms / 124 tokens ( 3.50 ms per token, 285.94 tokens per second) 1.14.738.248 I slot print_timing: id 2 | task 292 | eval time = 69.31 ms / 2 tokens ( 69.31 ms per token, 14.43 tokens per second) 1.14.738.248 I slot print_timing: id 2 | task 292 | total time = 502.97 ms / 126 tokens 1.14.738.248 I slot print_timing: id 2 | task 292 | graphs reused = 1 1.14.738.249 I slot print_timing: id 2 | task 292 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.738.264 I slot release: id 2 | task 292 | stop processing: n_tokens = 134, truncated = 0 1.15.332.805 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.276 1.15.623.215 I slot launch_slot_: id 2 | task 301 | processing task, is_child = 0 1.16.022.906 I slot print_timing: id 0 | task 296 | prompt eval time = 1051.25 ms / 142 tokens ( 7.40 ms per token, 135.08 tokens per second) 1.16.022.909 I slot print_timing: id 0 | task 296 | eval time = 294.84 ms / 2 tokens ( 294.84 ms per token, 3.39 tokens per second) 1.16.022.914 I slot print_timing: id 0 | task 296 | total time = 1346.10 ms / 144 tokens 1.16.022.915 I slot print_timing: id 0 | task 296 | graphs reused = 1 1.16.022.915 I slot print_timing: id 0 | task 296 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.022.954 I slot release: id 0 | task 296 | stop processing: n_tokens = 152, truncated = 0 1.16.024.069 I slot print_timing: id 1 | task 297 | prompt eval time = 1052.27 ms / 173 tokens ( 6.08 ms per token, 164.41 tokens per second) 1.16.024.071 I slot print_timing: id 1 | task 297 | eval time = 294.89 ms / 2 tokens ( 294.89 ms per token, 3.39 tokens per second) 1.16.024.072 I slot print_timing: id 1 | task 297 | total time = 1347.15 ms / 175 tokens 1.16.024.072 I slot print_timing: id 1 | task 297 | graphs reused = 1 1.16.024.072 I slot print_timing: id 1 | task 297 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.024.091 I slot release: id 1 | task 297 | stop processing: n_tokens = 183, truncated = 0 1.16.025.219 I slot print_timing: id 3 | task 298 | prompt eval time = 1053.34 ms / 161 tokens ( 6.54 ms per token, 152.85 tokens per second) 1.16.025.222 I slot print_timing: id 3 | task 298 | eval time = 294.86 ms / 2 tokens ( 294.86 ms per token, 3.39 tokens per second) 1.16.025.222 I slot print_timing: id 3 | task 298 | total time = 1348.20 ms / 163 tokens 1.16.025.223 I slot print_timing: id 3 | task 298 | graphs reused = 1 1.16.025.223 I slot print_timing: id 3 | task 298 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.025.244 I slot release: id 3 | task 298 | stop processing: n_tokens = 171, truncated = 0 1.16.061.346 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.243 1.16.065.414 I slot launch_slot_: id 0 | task 305 | processing task, is_child = 0 1.16.071.343 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.325 (> 0.100 thold), f_keep = 0.202 1.16.071.431 I slot launch_slot_: id 1 | task 306 | processing task, is_child = 0 1.16.071.461 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.216 1.16.071.523 I slot launch_slot_: id 3 | task 307 | processing task, is_child = 0 1.16.132.969 I slot print_timing: id 2 | task 301 | prompt eval time = 434.73 ms / 122 tokens ( 3.56 ms per token, 280.63 tokens per second) 1.16.132.974 I slot print_timing: id 2 | task 301 | eval time = 71.62 ms / 2 tokens ( 71.62 ms per token, 13.96 tokens per second) 1.16.132.974 I slot print_timing: id 2 | task 301 | total time = 506.36 ms / 124 tokens 1.16.132.975 I slot print_timing: id 2 | task 301 | graphs reused = 1 1.16.132.975 I slot print_timing: id 2 | task 301 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.132.994 I slot release: id 2 | task 301 | stop processing: n_tokens = 132, truncated = 0 1.16.720.999 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.280 1.17.012.195 I slot launch_slot_: id 2 | task 310 | processing task, is_child = 0 1.17.461.633 I slot print_timing: id 0 | task 305 | prompt eval time = 1045.01 ms / 190 tokens ( 5.50 ms per token, 181.82 tokens per second) 1.17.461.639 I slot print_timing: id 0 | task 305 | eval time = 345.09 ms / 2 tokens ( 345.09 ms per token, 2.90 tokens per second) 1.17.461.639 I slot print_timing: id 0 | task 305 | total time = 1390.10 ms / 192 tokens 1.17.461.640 I slot print_timing: id 0 | task 305 | graphs reused = 1 1.17.461.640 I slot print_timing: id 0 | task 305 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.461.664 I slot release: id 0 | task 305 | stop processing: n_tokens = 200, truncated = 0 1.17.462.845 I slot print_timing: id 1 | task 306 | prompt eval time = 1046.02 ms / 105 tokens ( 9.96 ms per token, 100.38 tokens per second) 1.17.462.846 I slot print_timing: id 1 | task 306 | eval time = 345.17 ms / 2 tokens ( 345.17 ms per token, 2.90 tokens per second) 1.17.462.847 I slot print_timing: id 1 | task 306 | total time = 1391.19 ms / 107 tokens 1.17.462.847 I slot print_timing: id 1 | task 306 | graphs reused = 1 1.17.462.847 I slot print_timing: id 1 | task 306 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.462.866 I slot release: id 1 | task 306 | stop processing: n_tokens = 115, truncated = 0 1.17.464.026 I slot print_timing: id 3 | task 307 | prompt eval time = 1047.08 ms / 162 tokens ( 6.46 ms per token, 154.72 tokens per second) 1.17.464.029 I slot print_timing: id 3 | task 307 | eval time = 345.19 ms / 2 tokens ( 345.19 ms per token, 2.90 tokens per second) 1.17.464.030 I slot print_timing: id 3 | task 307 | total time = 1392.26 ms / 164 tokens 1.17.464.030 I slot print_timing: id 3 | task 307 | graphs reused = 1 1.17.464.030 I slot print_timing: id 3 | task 307 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.464.050 I slot release: id 3 | task 307 | stop processing: n_tokens = 172, truncated = 0 1.17.499.369 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.185 1.17.503.869 I slot launch_slot_: id 0 | task 314 | processing task, is_child = 0 1.17.507.333 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.322 1.17.507.405 I slot launch_slot_: id 1 | task 315 | processing task, is_child = 0 1.17.559.555 I slot print_timing: id 2 | task 310 | prompt eval time = 483.27 ms / 136 tokens ( 3.55 ms per token, 281.42 tokens per second) 1.17.559.559 I slot print_timing: id 2 | task 310 | eval time = 60.19 ms / 2 tokens ( 60.19 ms per token, 16.62 tokens per second) 1.17.559.559 I slot print_timing: id 2 | task 310 | total time = 543.45 ms / 138 tokens 1.17.559.560 I slot print_timing: id 2 | task 310 | graphs reused = 1 1.17.559.560 I slot print_timing: id 2 | task 310 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.559.579 I slot release: id 2 | task 310 | stop processing: n_tokens = 146, truncated = 0 1.18.173.161 I slot print_timing: id 0 | task 314 | prompt eval time = 630.54 ms / 126 tokens ( 5.00 ms per token, 199.83 tokens per second) 1.18.173.165 I slot print_timing: id 0 | task 314 | eval time = 35.18 ms / 2 tokens ( 35.18 ms per token, 28.43 tokens per second) 1.18.173.166 I slot print_timing: id 0 | task 314 | total time = 665.71 ms / 128 tokens 1.18.173.167 I slot print_timing: id 0 | task 314 | graphs reused = 1 1.18.173.167 I slot print_timing: id 0 | task 314 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.173.183 I slot release: id 0 | task 314 | stop processing: n_tokens = 136, truncated = 0 1.18.174.302 I slot print_timing: id 1 | task 315 | prompt eval time = 631.81 ms / 146 tokens ( 4.33 ms per token, 231.08 tokens per second) 1.18.174.304 I slot print_timing: id 1 | task 315 | eval time = 34.90 ms / 2 tokens ( 34.90 ms per token, 28.65 tokens per second) 1.18.174.304 I slot print_timing: id 1 | task 315 | total time = 666.72 ms / 148 tokens 1.18.174.305 I slot print_timing: id 1 | task 315 | graphs reused = 1 1.18.174.305 I slot print_timing: id 1 | task 315 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.174.315 I slot release: id 1 | task 315 | stop processing: n_tokens = 156, truncated = 0 1.18.189.674 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 172, t_last = 331024459892 1.18.189.779 I slot launch_slot_: id 3 | task 320 | processing task, is_child = 0 1.18.196.959 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 146, t_last = 331024555421 1.18.197.000 I slot launch_slot_: id 2 | task 321 | processing task, is_child = 0 1.18.197.052 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 136, t_last = 331025169025 1.18.197.093 I slot launch_slot_: id 0 | task 322 | processing task, is_child = 0 1.18.197.121 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 156, t_last = 331025170157 1.18.197.157 I slot launch_slot_: id 1 | task 323 | processing task, is_child = 0 1.21.971.239 I slot print_timing: id 0 | task 322 | prompt processing, n_tokens = 670, progress = 0.57, t = 3.77 s / 177.53 tokens per second 1.22.021.424 I slot print_timing: id 1 | task 323 | prompt processing, n_tokens = 683, progress = 0.57, t = 3.77 s / 180.98 tokens per second 1.22.025.991 I slot print_timing: id 2 | task 321 | prompt processing, n_tokens = 674, progress = 0.57, t = 3.77 s / 178.60 tokens per second 1.22.030.350 I slot print_timing: id 3 | task 320 | prompt processing, n_tokens = 21, progress = 0.03, t = 3.77 s / 5.56 tokens per second 1.25.154.243 I slot print_timing: id 0 | task 322 | prompt processing, n_tokens = 1086, progress = 0.92, t = 6.96 s / 156.10 tokens per second 1.25.579.974 I slot print_timing: id 1 | task 323 | prompt processing, n_tokens = 1086, progress = 0.91, t = 6.96 s / 156.10 tokens per second 1.25.585.213 I slot print_timing: id 2 | task 321 | prompt processing, n_tokens = 1086, progress = 0.91, t = 6.96 s / 156.10 tokens per second 1.25.589.514 I slot print_timing: id 3 | task 320 | prompt processing, n_tokens = 655, progress = 0.56, t = 6.96 s / 94.15 tokens per second 1.26.407.373 I slot print_timing: id 0 | task 322 | prompt processing, n_tokens = 1182, progress = 1.00, t = 8.21 s / 143.97 tokens per second 1.27.061.043 I slot print_timing: id 1 | task 323 | prompt processing, n_tokens = 1195, progress = 1.00, t = 8.21 s / 145.55 tokens per second 1.27.067.231 I slot print_timing: id 2 | task 321 | prompt processing, n_tokens = 1186, progress = 1.00, t = 8.21 s / 144.46 tokens per second 1.27.071.722 I slot print_timing: id 3 | task 320 | prompt processing, n_tokens = 1086, progress = 0.93, t = 8.21 s / 132.28 tokens per second 1.27.338.498 I slot print_timing: id 3 | task 320 | prompt processing, n_tokens = 1167, progress = 1.00, t = 9.14 s / 127.71 tokens per second 1.28.846.856 I slot print_timing: id 1 | task 323 | prompt eval time = 9140.37 ms / 1199 tokens ( 7.62 ms per token, 131.18 tokens per second) 1.28.846.861 I slot print_timing: id 1 | task 323 | eval time = 1509.22 ms / 36 tokens ( 43.12 ms per token, 23.19 tokens per second) 1.28.846.862 I slot print_timing: id 1 | task 323 | total time = 10649.59 ms / 1235 tokens 1.28.846.862 I slot print_timing: id 1 | task 323 | graphs reused = 35 1.28.846.863 I slot print_timing: id 1 | task 323 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.846.928 I slot release: id 1 | task 323 | stop processing: n_tokens = 1243, truncated = 0 1.28.910.992 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.897 1.28.911.018 I slot launch_slot_: id 1 | task 364 | processing task, is_child = 0 1.29.841.393 I slot print_timing: id 3 | task 320 | prompt eval time = 9221.23 ms / 1171 tokens ( 7.87 ms per token, 126.99 tokens per second) 1.29.841.400 I slot print_timing: id 3 | task 320 | eval time = 2422.73 ms / 50 tokens ( 49.44 ms per token, 20.23 tokens per second) 1.29.841.401 I slot print_timing: id 3 | task 320 | total time = 11643.96 ms / 1221 tokens 1.29.841.402 I slot print_timing: id 3 | task 320 | graphs reused = 46 1.29.841.402 I slot print_timing: id 3 | task 320 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.841.483 I slot release: id 3 | task 320 | stop processing: n_tokens = 1229, truncated = 0 1.29.881.974 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.907 1.29.881.996 I slot launch_slot_: id 3 | task 380 | processing task, is_child = 0 1.30.920.921 I slot print_timing: id 0 | task 322 | prompt eval time = 9139.29 ms / 1186 tokens ( 7.71 ms per token, 129.77 tokens per second) 1.30.920.927 I slot print_timing: id 0 | task 322 | eval time = 3584.47 ms / 70 tokens ( 51.95 ms per token, 19.25 tokens per second) 1.30.920.928 I slot print_timing: id 0 | task 322 | total time = 12723.75 ms / 1256 tokens 1.30.920.929 I slot print_timing: id 0 | task 322 | graphs reused = 61 1.30.920.929 I slot print_timing: id 0 | task 322 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.921.001 I slot release: id 0 | task 322 | stop processing: n_tokens = 1264, truncated = 0 1.30.966.422 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.882 1.30.966.449 I slot launch_slot_: id 0 | task 400 | processing task, is_child = 0 1.32.477.239 I slot print_timing: id 2 | task 321 | n_gen = 100, tg = 19.27 t/s, tg_3s = 19.46 t/s 1.34.004.483 I slot print_timing: id 1 | task 364 | prompt eval time = 427.11 ms / 107 tokens ( 3.99 ms per token, 250.52 tokens per second) 1.34.004.490 I slot print_timing: id 1 | task 364 | eval time = 4666.35 ms / 98 tokens ( 48.11 ms per token, 20.79 tokens per second) 1.34.004.491 I slot print_timing: id 1 | task 364 | total time = 5093.46 ms / 205 tokens 1.34.004.491 I slot print_timing: id 1 | task 364 | graphs reused = 123 1.34.004.492 I slot print_timing: id 1 | task 364 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.004.549 I slot release: id 1 | task 364 | stop processing: n_tokens = 1319, truncated = 0 1.34.068.244 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.845 1.34.068.275 I slot launch_slot_: id 1 | task 467 | processing task, is_child = 0 1.34.813.448 I slot print_timing: id 3 | task 380 | prompt eval time = 377.30 ms / 114 tokens ( 3.31 ms per token, 302.15 tokens per second) 1.34.813.453 I slot print_timing: id 3 | task 380 | eval time = 4554.15 ms / 95 tokens ( 48.45 ms per token, 20.64 tokens per second) 1.34.813.453 I slot print_timing: id 3 | task 380 | total time = 4931.44 ms / 209 tokens 1.34.813.454 I slot print_timing: id 3 | task 380 | graphs reused = 131 1.34.813.455 I slot print_timing: id 3 | task 380 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.813.525 I slot release: id 3 | task 380 | stop processing: n_tokens = 1323, truncated = 0 1.34.855.118 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.843 1.34.855.149 I slot launch_slot_: id 3 | task 480 | processing task, is_child = 0 1.35.511.361 I slot print_timing: id 2 | task 321 | n_gen = 158, tg = 19.21 t/s, tg_3s = 19.12 t/s 1.36.108.374 I slot print_timing: id 0 | task 400 | n_gen = 100, tg = 20.75 t/s, tg_3s = 20.96 t/s 1.38.521.025 I slot print_timing: id 2 | task 321 | n_gen = 229, tg = 20.39 t/s, tg_3s = 23.59 t/s 1.38.899.996 I slot print_timing: id 1 | task 467 | n_gen = 100, tg = 22.19 t/s, tg_3s = 22.42 t/s 1.39.080.893 I slot print_timing: id 1 | task 467 | prompt eval time = 370.51 ms / 89 tokens ( 4.16 ms per token, 240.21 tokens per second) 1.39.080.897 I slot print_timing: id 1 | task 467 | eval time = 4642.10 ms / 104 tokens ( 45.07 ms per token, 22.19 tokens per second) 1.39.080.897 I slot print_timing: id 1 | task 467 | total time = 5012.61 ms / 193 tokens 1.39.080.898 I slot print_timing: id 1 | task 467 | graphs reused = 221 1.39.080.899 I slot print_timing: id 1 | task 467 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.080.960 I slot release: id 1 | task 467 | stop processing: n_tokens = 1307, truncated = 0 1.39.141.693 I slot print_timing: id 0 | task 400 | n_gen = 171, tg = 21.78 t/s, tg_3s = 23.41 t/s 1.39.145.277 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.853 1.39.145.301 I slot launch_slot_: id 1 | task 575 | processing task, is_child = 0 1.39.833.067 I slot print_timing: id 3 | task 480 | n_gen = 100, tg = 21.51 t/s, tg_3s = 21.72 t/s 1.40.988.393 I slot print_timing: id 3 | task 480 | prompt eval time = 374.56 ms / 118 tokens ( 3.17 ms per token, 315.04 tokens per second) 1.40.988.397 I slot print_timing: id 3 | task 480 | eval time = 5758.68 ms / 127 tokens ( 45.70 ms per token, 21.88 tokens per second) 1.40.988.398 I slot print_timing: id 3 | task 480 | total time = 6133.24 ms / 245 tokens 1.40.988.398 I slot print_timing: id 3 | task 480 | graphs reused = 252 1.40.988.399 I slot print_timing: id 3 | task 480 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.988.455 I slot release: id 3 | task 480 | stop processing: n_tokens = 1359, truncated = 0 1.41.028.742 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.820 1.41.028.766 I slot launch_slot_: id 3 | task 611 | processing task, is_child = 0 1.41.547.813 I slot print_timing: id 2 | task 321 | n_gen = 285, tg = 19.99 t/s, tg_3s = 18.50 t/s 1.42.179.502 I slot print_timing: id 0 | task 400 | n_gen = 228, tg = 20.94 t/s, tg_3s = 18.76 t/s 1.44.050.314 I slot print_timing: id 1 | task 575 | n_gen = 100, tg = 22.39 t/s, tg_3s = 22.62 t/s 1.44.560.040 I slot print_timing: id 2 | task 321 | n_gen = 356, tg = 20.61 t/s, tg_3s = 23.57 t/s 1.45.194.374 I slot print_timing: id 0 | task 400 | n_gen = 299, tg = 21.51 t/s, tg_3s = 23.55 t/s 1.45.537.188 I slot print_timing: id 3 | task 611 | n_gen = 100, tg = 23.63 t/s, tg_3s = 23.87 t/s 1.47.072.529 I slot print_timing: id 1 | task 575 | n_gen = 171, tg = 22.84 t/s, tg_3s = 23.49 t/s 1.47.583.957 I slot print_timing: id 2 | task 321 | n_gen = 427, tg = 21.04 t/s, tg_3s = 23.48 t/s 1.47.752.951 I slot print_timing: id 1 | task 575 | prompt eval time = 483.86 ms / 145 tokens ( 3.34 ms per token, 299.67 tokens per second) 1.47.752.958 I slot print_timing: id 1 | task 575 | eval time = 8123.78 ms / 187 tokens ( 43.68 ms per token, 22.90 tokens per second) 1.47.752.959 I slot print_timing: id 1 | task 575 | total time = 8607.64 ms / 332 tokens 1.47.752.960 I slot print_timing: id 1 | task 575 | graphs reused = 401 1.47.752.960 I slot print_timing: id 1 | task 575 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.753.033 I slot release: id 1 | task 575 | stop processing: n_tokens = 1446, truncated = 0 1.47.817.462 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.771 1.47.817.490 I slot launch_slot_: id 1 | task 766 | processing task, is_child = 0 1.48.224.692 I slot print_timing: id 0 | task 400 | n_gen = 363, tg = 21.44 t/s, tg_3s = 21.12 t/s 1.48.563.150 I slot print_timing: id 3 | task 611 | n_gen = 164, tg = 22.59 t/s, tg_3s = 21.15 t/s 1.48.649.688 I slot print_timing: id 3 | task 611 | prompt eval time = 318.52 ms / 100 tokens ( 3.19 ms per token, 313.95 tokens per second) 1.48.649.695 I slot print_timing: id 3 | task 611 | eval time = 7302.39 ms / 166 tokens ( 44.26 ms per token, 22.60 tokens per second) 1.48.649.695 I slot print_timing: id 3 | task 611 | total time = 7620.91 ms / 266 tokens 1.48.649.696 I slot print_timing: id 3 | task 611 | graphs reused = 411 1.48.649.705 I slot print_timing: id 3 | task 611 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.649.777 I slot release: id 3 | task 611 | stop processing: n_tokens = 1380, truncated = 0 1.48.690.448 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.808 1.48.690.470 I slot launch_slot_: id 3 | task 781 | processing task, is_child = 0 1.50.619.067 I slot print_timing: id 2 | task 321 | n_gen = 486, tg = 20.83 t/s, tg_3s = 19.44 t/s 1.51.257.075 I slot print_timing: id 0 | task 400 | n_gen = 429, tg = 21.49 t/s, tg_3s = 21.77 t/s 1.51.939.766 I slot print_timing: id 3 | task 781 | prompt eval time = 313.39 ms / 76 tokens ( 4.12 ms per token, 242.51 tokens per second) 1.51.939.769 I slot print_timing: id 3 | task 781 | eval time = 2935.90 ms / 70 tokens ( 42.55 ms per token, 23.50 tokens per second) 1.51.939.770 I slot print_timing: id 3 | task 781 | total time = 3249.29 ms / 146 tokens 1.51.939.771 I slot print_timing: id 3 | task 781 | graphs reused = 479 1.51.939.771 I slot print_timing: id 3 | task 781 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.939.825 I slot release: id 3 | task 781 | stop processing: n_tokens = 1260, truncated = 0 1.51.980.112 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.885 1.51.980.138 I slot launch_slot_: id 3 | task 854 | processing task, is_child = 0 1.52.534.198 I slot print_timing: id 1 | task 766 | prompt eval time = 367.52 ms / 76 tokens ( 4.84 ms per token, 206.79 tokens per second) 1.52.534.200 I slot print_timing: id 1 | task 766 | eval time = 4349.18 ms / 93 tokens ( 47.27 ms per token, 21.15 tokens per second) 1.52.534.201 I slot print_timing: id 1 | task 766 | total time = 4716.70 ms / 169 tokens 1.52.534.201 I slot print_timing: id 1 | task 766 | graphs reused = 484 1.52.534.202 I slot print_timing: id 1 | task 766 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.534.250 I slot release: id 1 | task 766 | stop processing: n_tokens = 1283, truncated = 0 1.52.594.940 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.869 1.52.594.965 I slot launch_slot_: id 1 | task 864 | processing task, is_child = 0 1.53.649.533 I slot print_timing: id 2 | task 321 | n_gen = 545, tg = 20.68 t/s, tg_3s = 19.47 t/s 1.54.285.940 I slot print_timing: id 0 | task 400 | n_gen = 488, tg = 21.22 t/s, tg_3s = 19.48 t/s 1.56.034.211 I slot print_timing: id 1 | task 864 | prompt eval time = 382.01 ms / 99 tokens ( 3.86 ms per token, 259.16 tokens per second) 1.56.034.215 I slot print_timing: id 1 | task 864 | eval time = 3057.23 ms / 73 tokens ( 42.46 ms per token, 23.55 tokens per second) 1.56.034.216 I slot print_timing: id 1 | task 864 | total time = 3439.24 ms / 172 tokens 1.56.034.216 I slot print_timing: id 1 | task 864 | graphs reused = 554 1.56.034.217 I slot print_timing: id 1 | task 864 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.034.276 I slot release: id 1 | task 864 | stop processing: n_tokens = 1286, truncated = 0 1.56.098.719 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.867 1.56.098.746 I slot launch_slot_: id 1 | task 940 | processing task, is_child = 0 1.56.651.048 I slot print_timing: id 2 | task 321 | n_gen = 607, tg = 20.67 t/s, tg_3s = 20.66 t/s 1.57.155.671 I slot print_timing: id 3 | task 854 | n_gen = 100, tg = 20.36 t/s, tg_3s = 20.57 t/s 1.57.322.218 I slot print_timing: id 0 | task 400 | n_gen = 551, tg = 21.17 t/s, tg_3s = 20.75 t/s 1.59.666.251 I slot print_timing: id 2 | task 321 | n_gen = 678, tg = 20.94 t/s, tg_3s = 23.55 t/s 2.00.178.584 I slot print_timing: id 3 | task 854 | n_gen = 171, tg = 21.56 t/s, tg_3s = 23.49 t/s 2.00.344.716 I slot print_timing: id 0 | task 400 | n_gen = 622, tg = 21.41 t/s, tg_3s = 23.49 t/s 2.00.731.701 I slot print_timing: id 1 | task 940 | n_gen = 100, tg = 23.55 t/s, tg_3s = 23.79 t/s 2.02.701.753 I slot print_timing: id 2 | task 321 | n_gen = 749, tg = 21.15 t/s, tg_3s = 23.39 t/s 2.03.211.247 I slot print_timing: id 3 | task 854 | n_gen = 242, tg = 22.08 t/s, tg_3s = 23.41 t/s 2.03.375.631 I slot print_timing: id 0 | task 400 | n_gen = 693, tg = 21.60 t/s, tg_3s = 23.43 t/s 2.03.759.503 I slot print_timing: id 1 | task 940 | n_gen = 171, tg = 23.51 t/s, tg_3s = 23.45 t/s 2.05.722.133 I slot print_timing: id 2 | task 321 | n_gen = 820, tg = 21.34 t/s, tg_3s = 23.51 t/s 2.06.190.783 I slot print_timing: id 1 | task 940 | prompt eval time = 429.49 ms / 125 tokens ( 3.44 ms per token, 291.04 tokens per second) 2.06.190.790 I slot print_timing: id 1 | task 940 | eval time = 9662.54 ms / 228 tokens ( 42.57 ms per token, 23.49 tokens per second) 2.06.190.790 I slot print_timing: id 1 | task 940 | total time = 10092.03 ms / 353 tokens 2.06.190.791 I slot print_timing: id 1 | task 940 | graphs reused = 780 2.06.190.792 I slot print_timing: id 1 | task 940 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.190.849 I slot release: id 1 | task 940 | stop processing: n_tokens = 1467, truncated = 0 2.06.255.533 I slot print_timing: id 3 | task 854 | n_gen = 313, tg = 22.35 t/s, tg_3s = 23.32 t/s 2.06.255.540 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.760 2.06.255.566 I slot launch_slot_: id 1 | task 1171 | processing task, is_child = 0 2.06.467.650 I slot print_timing: id 0 | task 400 | n_gen = 761, tg = 21.63 t/s, tg_3s = 21.99 t/s 2.07.077.062 I slot print_timing: id 3 | task 854 | prompt eval time = 314.15 ms / 72 tokens ( 4.36 ms per token, 229.19 tokens per second) 2.07.077.070 I slot print_timing: id 3 | task 854 | eval time = 14782.75 ms / 327 tokens ( 45.35 ms per token, 22.05 tokens per second) 2.07.077.070 I slot print_timing: id 3 | task 854 | total time = 15096.91 ms / 399 tokens 2.07.077.071 I slot print_timing: id 3 | task 854 | graphs reused = 791 2.07.077.072 I slot print_timing: id 3 | task 854 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.077.144 I slot release: id 3 | task 854 | stop processing: n_tokens = 1513, truncated = 0 2.07.118.635 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.737 2.07.118.658 I slot launch_slot_: id 3 | task 1187 | processing task, is_child = 0 2.08.761.154 I slot print_timing: id 2 | task 321 | n_gen = 879, tg = 21.20 t/s, tg_3s = 19.41 t/s 2.09.486.103 I slot print_timing: id 0 | task 400 | n_gen = 824, tg = 21.57 t/s, tg_3s = 20.87 t/s 2.10.769.329 I slot print_timing: id 1 | task 1171 | prompt eval time = 317.70 ms / 62 tokens ( 5.12 ms per token, 195.15 tokens per second) 2.10.769.333 I slot print_timing: id 1 | task 1171 | eval time = 4196.05 ms / 93 tokens ( 45.61 ms per token, 21.93 tokens per second) 2.10.769.334 I slot print_timing: id 1 | task 1171 | total time = 4513.75 ms / 155 tokens 2.10.769.334 I slot print_timing: id 1 | task 1171 | graphs reused = 866 2.10.769.335 I slot print_timing: id 1 | task 1171 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.769.395 I slot release: id 1 | task 1171 | stop processing: n_tokens = 1269, truncated = 0 2.10.834.100 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.879 2.10.834.128 I slot launch_slot_: id 1 | task 1268 | processing task, is_child = 0 2.11.800.978 I slot print_timing: id 2 | task 321 | n_gen = 943, tg = 21.19 t/s, tg_3s = 21.05 t/s 2.12.016.365 I slot print_timing: id 3 | task 1187 | n_gen = 100, tg = 21.88 t/s, tg_3s = 22.10 t/s 2.12.525.447 I slot print_timing: id 0 | task 400 | n_gen = 888, tg = 21.54 t/s, tg_3s = 21.06 t/s 2.12.615.787 I slot print_timing: id 3 | task 1187 | prompt eval time = 372.91 ms / 111 tokens ( 3.36 ms per token, 297.66 tokens per second) 2.12.615.794 I slot print_timing: id 3 | task 1187 | eval time = 5124.21 ms / 114 tokens ( 45.35 ms per token, 22.05 tokens per second) 2.12.615.795 I slot print_timing: id 3 | task 1187 | total time = 5497.12 ms / 225 tokens 2.12.615.795 I slot print_timing: id 3 | task 1187 | graphs reused = 898 2.12.615.796 I slot print_timing: id 3 | task 1187 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.615.855 I slot release: id 3 | task 1187 | stop processing: n_tokens = 1339, truncated = 0 2.12.656.392 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.833 2.12.656.416 I slot launch_slot_: id 3 | task 1305 | processing task, is_child = 0 2.14.449.576 I slot print_timing: id 1 | task 1268 | prompt eval time = 369.53 ms / 74 tokens ( 4.99 ms per token, 200.25 tokens per second) 2.14.449.583 I slot print_timing: id 1 | task 1268 | eval time = 3245.91 ms / 73 tokens ( 45.08 ms per token, 22.18 tokens per second) 2.14.449.584 I slot print_timing: id 1 | task 1268 | total time = 3615.44 ms / 147 tokens 2.14.449.584 I slot print_timing: id 1 | task 1268 | graphs reused = 933 2.14.449.585 I slot print_timing: id 1 | task 1268 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.449.660 I slot release: id 1 | task 1268 | stop processing: n_tokens = 1261, truncated = 0 2.14.514.413 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.884 2.14.514.441 I slot launch_slot_: id 1 | task 1345 | processing task, is_child = 0 2.14.883.345 I slot print_timing: id 2 | task 321 | n_gen = 1004, tg = 21.10 t/s, tg_3s = 19.79 t/s 2.15.561.005 I slot print_timing: id 0 | task 400 | n_gen = 948, tg = 21.41 t/s, tg_3s = 19.77 t/s 2.15.734.291 I slot print_timing: id 2 | task 321 | prompt eval time = 9141.14 ms / 1190 tokens ( 7.68 ms per token, 130.18 tokens per second) 2.15.734.298 I slot print_timing: id 2 | task 321 | eval time = 48395.81 ms / 1024 tokens ( 47.31 ms per token, 21.14 tokens per second) 2.15.734.298 I slot print_timing: id 2 | task 321 | total time = 57536.95 ms / 2214 tokens 2.15.734.299 I slot print_timing: id 2 | task 321 | graphs reused = 952 2.15.734.300 I slot print_timing: id 2 | task 321 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.734.353 I slot release: id 2 | task 321 | stop processing: n_tokens = 2222, truncated = 0 2.15.735.972 I slot print_timing: id 3 | task 1305 | prompt eval time = 260.50 ms / 59 tokens ( 4.42 ms per token, 226.48 tokens per second) 2.15.735.975 I slot print_timing: id 3 | task 1305 | eval time = 2819.05 ms / 60 tokens ( 47.78 ms per token, 20.93 tokens per second) 2.15.735.975 I slot print_timing: id 3 | task 1305 | total time = 3079.55 ms / 119 tokens 2.15.735.976 I slot print_timing: id 3 | task 1305 | graphs reused = 952 2.15.735.976 I slot print_timing: id 3 | task 1305 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.736.019 I slot release: id 3 | task 1305 | stop processing: n_tokens = 1233, truncated = 0 2.15.773.366 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.502 2.15.773.393 I slot launch_slot_: id 2 | task 1369 | processing task, is_child = 0 2.15.801.450 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.904 2.15.801.471 I slot launch_slot_: id 3 | task 1370 | processing task, is_child = 0 2.18.598.930 I slot print_timing: id 0 | task 400 | n_gen = 1006, tg = 21.26 t/s, tg_3s = 19.09 t/s 2.19.369.655 I slot print_timing: id 0 | task 400 | prompt eval time = 370.80 ms / 117 tokens ( 3.17 ms per token, 315.53 tokens per second) 2.19.369.663 I slot print_timing: id 0 | task 400 | eval time = 48032.40 ms / 1024 tokens ( 46.95 ms per token, 21.30 tokens per second) 2.19.369.663 I slot print_timing: id 0 | task 400 | total time = 48403.20 ms / 1141 tokens 2.19.369.664 I slot print_timing: id 0 | task 400 | graphs reused = 1019 2.19.369.665 I slot print_timing: id 0 | task 400 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.369.738 I slot release: id 0 | task 400 | stop processing: n_tokens = 2255, truncated = 0 2.19.414.742 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.494 2.19.444.784 I slot launch_slot_: id 0 | task 1443 | processing task, is_child = 0 2.19.866.958 I slot print_timing: id 1 | task 1345 | n_gen = 100, tg = 19.86 t/s, tg_3s = 20.06 t/s 2.20.124.689 I slot print_timing: id 3 | task 1370 | prompt eval time = 572.81 ms / 70 tokens ( 8.18 ms per token, 122.20 tokens per second) 2.20.124.694 I slot print_timing: id 3 | task 1370 | eval time = 3746.87 ms / 83 tokens ( 45.69 ms per token, 21.88 tokens per second) 2.20.124.695 I slot print_timing: id 3 | task 1370 | total time = 4319.68 ms / 153 tokens 2.20.124.695 I slot print_timing: id 3 | task 1370 | graphs reused = 1029 2.20.124.696 I slot print_timing: id 3 | task 1370 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.124.784 I slot release: id 3 | task 1370 | stop processing: n_tokens = 1267, truncated = 0 2.20.165.961 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.880 2.20.165.988 I slot launch_slot_: id 3 | task 1457 | processing task, is_child = 0 2.21.111.020 I slot print_timing: id 2 | task 1369 | n_gen = 100, tg = 21.36 t/s, tg_3s = 21.57 t/s 2.22.891.343 I slot print_timing: id 1 | task 1345 | n_gen = 166, tg = 20.60 t/s, tg_3s = 21.82 t/s 2.23.867.047 I slot print_timing: id 0 | task 1443 | prompt eval time = 260.05 ms / 66 tokens ( 3.94 ms per token, 253.79 tokens per second) 2.23.867.054 I slot print_timing: id 0 | task 1443 | eval time = 4162.19 ms / 94 tokens ( 44.75 ms per token, 22.34 tokens per second) 2.23.867.054 I slot print_timing: id 0 | task 1443 | total time = 4422.25 ms / 160 tokens 2.23.867.055 I slot print_timing: id 0 | task 1443 | graphs reused = 1108 2.23.867.056 I slot print_timing: id 0 | task 1443 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.867.136 I slot release: id 0 | task 1443 | stop processing: n_tokens = 1273, truncated = 0 2.23.912.150 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.876 2.23.912.175 I slot launch_slot_: id 0 | task 1541 | processing task, is_child = 0 2.24.169.578 I slot print_timing: id 2 | task 1369 | n_gen = 168, tg = 21.70 t/s, tg_3s = 22.23 t/s 2.24.627.369 I slot print_timing: id 3 | task 1457 | prompt eval time = 320.74 ms / 71 tokens ( 4.52 ms per token, 221.36 tokens per second) 2.24.627.375 I slot print_timing: id 3 | task 1457 | eval time = 4140.63 ms / 95 tokens ( 44.05 ms per token, 22.70 tokens per second) 2.24.627.376 I slot print_timing: id 3 | task 1457 | total time = 4461.37 ms / 166 tokens 2.24.627.377 I slot print_timing: id 3 | task 1457 | graphs reused = 1119 2.24.627.378 I slot print_timing: id 3 | task 1457 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.627.455 I slot release: id 3 | task 1457 | stop processing: n_tokens = 1280, truncated = 0 2.24.668.312 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.871 2.24.668.337 I slot launch_slot_: id 3 | task 1556 | processing task, is_child = 0 2.25.915.528 I slot print_timing: id 1 | task 1345 | n_gen = 227, tg = 20.48 t/s, tg_3s = 20.17 t/s 2.27.191.648 I slot print_timing: id 2 | task 1369 | n_gen = 233, tg = 21.65 t/s, tg_3s = 21.51 t/s 2.28.039.249 I slot print_timing: id 2 | task 1369 | prompt eval time = 673.90 ms / 127 tokens ( 5.31 ms per token, 188.46 tokens per second) 2.28.039.256 I slot print_timing: id 2 | task 1369 | eval time = 11563.86 ms / 253 tokens ( 45.89 ms per token, 21.79 tokens per second) 2.28.039.257 I slot print_timing: id 2 | task 1369 | total time = 12237.76 ms / 380 tokens 2.28.039.258 I slot print_timing: id 2 | task 1369 | graphs reused = 1189 2.28.039.258 I slot print_timing: id 2 | task 1369 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.039.327 I slot release: id 2 | task 1369 | stop processing: n_tokens = 1473, truncated = 0 2.28.102.356 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.757 2.28.102.379 I slot launch_slot_: id 2 | task 1631 | processing task, is_child = 0 2.28.932.282 I slot print_timing: id 1 | task 1345 | prompt eval time = 367.86 ms / 76 tokens ( 4.84 ms per token, 206.60 tokens per second) 2.28.932.290 I slot print_timing: id 1 | task 1345 | eval time = 14049.98 ms / 290 tokens ( 48.62 ms per token, 20.57 tokens per second) 2.28.932.290 I slot print_timing: id 1 | task 1345 | total time = 14417.83 ms / 366 tokens 2.28.932.291 I slot print_timing: id 1 | task 1345 | graphs reused = 1198 2.28.932.292 I slot print_timing: id 1 | task 1345 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.932.359 I slot release: id 1 | task 1345 | stop processing: n_tokens = 1480, truncated = 0 2.28.993.820 I slot print_timing: id 0 | task 1541 | n_gen = 100, tg = 20.51 t/s, tg_3s = 20.72 t/s 2.28.997.660 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.753 2.28.997.684 I slot launch_slot_: id 1 | task 1645 | processing task, is_child = 0 2.29.428.428 I slot print_timing: id 0 | task 1541 | prompt eval time = 255.25 ms / 62 tokens ( 4.12 ms per token, 242.90 tokens per second) 2.29.428.434 I slot print_timing: id 0 | task 1541 | eval time = 5260.99 ms / 102 tokens ( 52.09 ms per token, 19.20 tokens per second) 2.29.428.434 I slot print_timing: id 0 | task 1541 | total time = 5516.25 ms / 164 tokens 2.29.428.435 I slot print_timing: id 0 | task 1541 | graphs reused = 1198 2.29.428.435 I slot print_timing: id 0 | task 1541 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.428.490 I slot release: id 0 | task 1541 | stop processing: n_tokens = 1278, truncated = 0 2.29.469.885 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.872 2.29.469.902 I slot launch_slot_: id 0 | task 1649 | processing task, is_child = 0 2.30.097.757 I slot print_timing: id 3 | task 1556 | n_gen = 100, tg = 19.57 t/s, tg_3s = 19.77 t/s 2.30.227.834 I slot print_timing: id 3 | task 1556 | prompt eval time = 370.38 ms / 106 tokens ( 3.49 ms per token, 286.19 tokens per second) 2.30.227.842 I slot print_timing: id 3 | task 1556 | eval time = 5189.11 ms / 103 tokens ( 50.87 ms per token, 19.66 tokens per second) 2.30.227.842 I slot print_timing: id 3 | task 1556 | total time = 5559.49 ms / 209 tokens 2.30.227.843 I slot print_timing: id 3 | task 1556 | graphs reused = 1210 2.30.227.844 I slot print_timing: id 3 | task 1556 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.227.918 I slot release: id 3 | task 1556 | stop processing: n_tokens = 1323, truncated = 0 2.30.268.366 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.843 2.30.268.387 I slot launch_slot_: id 3 | task 1665 | processing task, is_child = 0 2.33.197.365 I slot print_timing: id 0 | task 1649 | prompt eval time = 253.91 ms / 68 tokens ( 3.73 ms per token, 267.82 tokens per second) 2.33.197.373 I slot print_timing: id 0 | task 1649 | eval time = 3473.55 ms / 79 tokens ( 44.53 ms per token, 22.46 tokens per second) 2.33.197.374 I slot print_timing: id 0 | task 1649 | total time = 3727.45 ms / 147 tokens 2.33.197.375 I slot print_timing: id 0 | task 1649 | graphs reused = 1271 2.33.197.376 I slot print_timing: id 0 | task 1649 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.197.460 I slot release: id 0 | task 1649 | stop processing: n_tokens = 1261, truncated = 0 2.33.242.572 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.884 2.33.242.598 I slot launch_slot_: id 0 | task 1732 | processing task, is_child = 0 2.33.632.566 I slot print_timing: id 2 | task 1631 | n_gen = 100, tg = 19.34 t/s, tg_3s = 19.54 t/s 2.33.876.111 I slot print_timing: id 3 | task 1665 | prompt eval time = 260.40 ms / 62 tokens ( 4.20 ms per token, 238.09 tokens per second) 2.33.876.117 I slot print_timing: id 3 | task 1665 | eval time = 3347.31 ms / 75 tokens ( 45.23 ms per token, 22.11 tokens per second) 2.33.876.118 I slot print_timing: id 3 | task 1665 | total time = 3607.72 ms / 137 tokens 2.33.876.119 I slot print_timing: id 3 | task 1665 | graphs reused = 1279 2.33.876.119 I slot print_timing: id 3 | task 1665 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.876.180 I slot release: id 3 | task 1665 | stop processing: n_tokens = 1251, truncated = 0 2.33.917.934 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.891 2.33.917.967 I slot launch_slot_: id 3 | task 1744 | processing task, is_child = 0 2.34.393.375 I slot print_timing: id 1 | task 1645 | n_gen = 100, tg = 19.94 t/s, tg_3s = 20.15 t/s 2.36.513.401 I slot print_timing: id 0 | task 1732 | prompt eval time = 306.94 ms / 74 tokens ( 4.15 ms per token, 241.09 tokens per second) 2.36.513.406 I slot print_timing: id 0 | task 1732 | eval time = 2963.86 ms / 66 tokens ( 45.60 ms per token, 21.93 tokens per second) 2.36.513.407 I slot print_timing: id 0 | task 1732 | total time = 3270.79 ms / 140 tokens 2.36.513.407 I slot print_timing: id 0 | task 1732 | graphs reused = 1332 2.36.513.408 I slot print_timing: id 0 | task 1732 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.513.492 I slot release: id 0 | task 1732 | stop processing: n_tokens = 1254, truncated = 0 2.36.558.656 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.889 2.36.558.691 I slot launch_slot_: id 0 | task 1802 | processing task, is_child = 0 2.36.794.483 I slot print_timing: id 2 | task 1631 | n_gen = 165, tg = 19.81 t/s, tg_3s = 20.56 t/s 2.37.408.994 I slot print_timing: id 1 | task 1645 | n_gen = 166, tg = 20.68 t/s, tg_3s = 21.89 t/s 2.38.639.506 I slot print_timing: id 3 | task 1744 | n_gen = 100, tg = 22.47 t/s, tg_3s = 22.70 t/s 2.38.893.600 I slot print_timing: id 3 | task 1744 | prompt eval time = 316.38 ms / 80 tokens ( 3.95 ms per token, 252.86 tokens per second) 2.38.893.607 I slot print_timing: id 3 | task 1744 | eval time = 4659.25 ms / 106 tokens ( 44.37 ms per token, 22.54 tokens per second) 2.38.893.607 I slot print_timing: id 3 | task 1744 | total time = 4975.63 ms / 186 tokens 2.38.893.608 I slot print_timing: id 3 | task 1744 | graphs reused = 1380 2.38.893.608 I slot print_timing: id 3 | task 1744 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.893.663 I slot release: id 3 | task 1744 | stop processing: n_tokens = 1300, truncated = 0 2.38.933.889 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.858 2.38.933.912 I slot launch_slot_: id 3 | task 1854 | processing task, is_child = 0 2.39.835.554 I slot print_timing: id 2 | task 1631 | n_gen = 231, tg = 20.32 t/s, tg_3s = 21.70 t/s 2.40.426.357 I slot print_timing: id 1 | task 1645 | n_gen = 232, tg = 21.01 t/s, tg_3s = 21.87 t/s 2.41.269.920 I slot print_timing: id 0 | task 1802 | n_gen = 100, tg = 22.49 t/s, tg_3s = 22.72 t/s 2.42.859.007 I slot print_timing: id 2 | task 1631 | n_gen = 302, tg = 20.98 t/s, tg_3s = 23.48 t/s 2.43.447.653 I slot print_timing: id 1 | task 1645 | n_gen = 303, tg = 21.54 t/s, tg_3s = 23.50 t/s 2.43.450.439 I slot print_timing: id 3 | task 1854 | n_gen = 100, tg = 23.58 t/s, tg_3s = 23.82 t/s 2.44.293.151 I slot print_timing: id 0 | task 1802 | n_gen = 171, tg = 22.90 t/s, tg_3s = 23.48 t/s 2.45.653.875 I slot print_timing: id 0 | task 1802 | prompt eval time = 310.06 ms / 88 tokens ( 3.52 ms per token, 283.81 tokens per second) 2.45.653.881 I slot print_timing: id 0 | task 1802 | eval time = 8785.11 ms / 203 tokens ( 43.49 ms per token, 22.99 tokens per second) 2.45.653.882 I slot print_timing: id 0 | task 1802 | total time = 9095.18 ms / 291 tokens 2.45.653.883 I slot print_timing: id 0 | task 1802 | graphs reused = 1529 2.45.653.883 I slot print_timing: id 0 | task 1802 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.653.939 I slot release: id 0 | task 1802 | stop processing: n_tokens = 1405, truncated = 0 2.45.699.309 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.794 2.45.699.332 I slot launch_slot_: id 0 | task 2009 | processing task, is_child = 0 2.45.932.000 I slot print_timing: id 2 | task 1631 | n_gen = 370, tg = 21.19 t/s, tg_3s = 22.13 t/s 2.46.257.463 I slot print_timing: id 3 | task 1854 | prompt eval time = 318.00 ms / 97 tokens ( 3.28 ms per token, 305.03 tokens per second) 2.46.257.468 I slot print_timing: id 3 | task 1854 | eval time = 7005.55 ms / 161 tokens ( 43.78 ms per token, 22.84 tokens per second) 2.46.257.469 I slot print_timing: id 3 | task 1854 | total time = 7323.54 ms / 258 tokens 2.46.257.470 I slot print_timing: id 3 | task 1854 | graphs reused = 1535 2.46.257.471 I slot print_timing: id 3 | task 1854 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.257.544 I slot release: id 3 | task 1854 | stop processing: n_tokens = 1372, truncated = 0 2.46.299.593 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.813 2.46.299.621 I slot launch_slot_: id 3 | task 2019 | processing task, is_child = 0 2.46.539.584 I slot print_timing: id 1 | task 1645 | n_gen = 366, tg = 21.33 t/s, tg_3s = 20.38 t/s 2.48.934.259 I slot print_timing: id 2 | task 1631 | n_gen = 435, tg = 21.25 t/s, tg_3s = 21.65 t/s 2.49.143.941 I slot print_timing: id 0 | task 2009 | prompt eval time = 306.35 ms / 71 tokens ( 4.31 ms per token, 231.76 tokens per second) 2.49.143.948 I slot print_timing: id 0 | task 2009 | eval time = 3138.26 ms / 70 tokens ( 45.48 ms per token, 21.99 tokens per second) 2.49.143.949 I slot print_timing: id 0 | task 2009 | total time = 3444.60 ms / 141 tokens 2.49.143.949 I slot print_timing: id 0 | task 2009 | graphs reused = 1594 2.49.143.950 I slot print_timing: id 0 | task 2009 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.144.006 I slot release: id 0 | task 2009 | stop processing: n_tokens = 1255, truncated = 0 2.49.189.141 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.888 2.49.189.163 I slot launch_slot_: id 0 | task 2083 | processing task, is_child = 0 2.49.560.347 I slot print_timing: id 1 | task 1645 | n_gen = 430, tg = 21.31 t/s, tg_3s = 21.19 t/s 2.51.088.172 I slot print_timing: id 3 | task 2019 | n_gen = 100, tg = 22.14 t/s, tg_3s = 22.37 t/s 2.51.938.726 I slot print_timing: id 2 | task 1631 | n_gen = 499, tg = 21.26 t/s, tg_3s = 21.30 t/s 2.52.537.124 I slot print_timing: id 3 | task 2019 | prompt eval time = 318.00 ms / 90 tokens ( 3.53 ms per token, 283.02 tokens per second) 2.52.537.129 I slot print_timing: id 3 | task 2019 | eval time = 5919.49 ms / 134 tokens ( 44.51 ms per token, 22.47 tokens per second) 2.52.537.130 I slot print_timing: id 3 | task 2019 | total time = 6237.49 ms / 224 tokens 2.52.537.131 I slot print_timing: id 3 | task 2019 | graphs reused = 1664 2.52.537.132 I slot print_timing: id 3 | task 2019 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.537.200 I slot release: id 3 | task 2019 | stop processing: n_tokens = 1338, truncated = 0 2.52.576.190 I slot print_timing: id 1 | task 1645 | n_gen = 501, tg = 21.60 t/s, tg_3s = 23.54 t/s 2.52.577.792 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.833 2.52.577.814 I slot launch_slot_: id 3 | task 2157 | processing task, is_child = 0 2.54.037.438 I slot print_timing: id 0 | task 2083 | n_gen = 100, tg = 22.11 t/s, tg_3s = 22.33 t/s 2.54.978.885 I slot print_timing: id 2 | task 1631 | n_gen = 564, tg = 21.27 t/s, tg_3s = 21.38 t/s 2.55.616.181 I slot print_timing: id 1 | task 1645 | n_gen = 566, tg = 21.58 t/s, tg_3s = 21.38 t/s 2.57.063.550 I slot print_timing: id 0 | task 2083 | n_gen = 171, tg = 22.65 t/s, tg_3s = 23.46 t/s 2.57.153.448 I slot print_timing: id 3 | task 2157 | n_gen = 100, tg = 23.54 t/s, tg_3s = 23.78 t/s 2.58.004.191 I slot print_timing: id 2 | task 1631 | n_gen = 635, tg = 21.50 t/s, tg_3s = 23.47 t/s 2.58.653.642 I slot print_timing: id 1 | task 1645 | n_gen = 637, tg = 21.76 t/s, tg_3s = 23.37 t/s 2.59.545.726 I slot print_timing: id 0 | task 2083 | prompt eval time = 370.10 ms / 125 tokens ( 2.96 ms per token, 337.75 tokens per second) 2.59.545.734 I slot print_timing: id 0 | task 2083 | eval time = 9986.45 ms / 229 tokens ( 43.80 ms per token, 22.83 tokens per second) 2.59.545.735 I slot print_timing: id 0 | task 2083 | total time = 10356.55 ms / 354 tokens 2.59.545.736 I slot print_timing: id 0 | task 2083 | graphs reused = 1817 2.59.545.736 I slot print_timing: id 0 | task 2083 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.545.827 I slot release: id 0 | task 2083 | stop processing: n_tokens = 1468, truncated = 0 2.59.591.339 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.760 2.59.591.365 I slot launch_slot_: id 0 | task 2316 | processing task, is_child = 0 3.00.188.671 I slot print_timing: id 3 | task 2157 | n_gen = 166, tg = 22.79 t/s, tg_3s = 21.74 t/s 3.01.004.960 I slot print_timing: id 2 | task 1631 | n_gen = 700, tg = 21.51 t/s, tg_3s = 21.66 t/s 3.01.688.804 I slot print_timing: id 1 | task 1645 | n_gen = 703, tg = 21.76 t/s, tg_3s = 21.75 t/s 3.01.734.856 I slot print_timing: id 3 | task 2157 | prompt eval time = 370.81 ms / 106 tokens ( 3.50 ms per token, 285.86 tokens per second) 3.01.734.859 I slot print_timing: id 3 | task 2157 | eval time = 8786.23 ms / 202 tokens ( 43.71 ms per token, 22.88 tokens per second) 3.01.734.860 I slot print_timing: id 3 | task 2157 | total time = 9157.04 ms / 308 tokens 3.01.734.860 I slot print_timing: id 3 | task 2157 | graphs reused = 1860 3.01.734.861 I slot print_timing: id 3 | task 2157 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.734.921 I slot release: id 3 | task 2157 | stop processing: n_tokens = 1422, truncated = 0 3.01.774.986 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.784 3.01.775.018 I slot launch_slot_: id 3 | task 2363 | processing task, is_child = 0 3.04.009.132 I slot print_timing: id 2 | task 1631 | n_gen = 764, tg = 21.50 t/s, tg_3s = 21.30 t/s 3.04.389.387 I slot print_timing: id 0 | task 2316 | n_gen = 100, tg = 22.07 t/s, tg_3s = 22.29 t/s 3.04.688.872 I slot print_timing: id 1 | task 1645 | n_gen = 767, tg = 21.72 t/s, tg_3s = 21.33 t/s 3.05.876.675 I slot print_timing: id 0 | task 2316 | prompt eval time = 311.70 ms / 94 tokens ( 3.32 ms per token, 301.57 tokens per second) 3.05.876.679 I slot print_timing: id 0 | task 2316 | eval time = 5973.60 ms / 135 tokens ( 44.58 ms per token, 22.43 tokens per second) 3.05.876.680 I slot print_timing: id 0 | task 2316 | total time = 6285.30 ms / 229 tokens 3.05.876.680 I slot print_timing: id 0 | task 2316 | graphs reused = 1947 3.05.876.681 I slot print_timing: id 0 | task 2316 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.876.769 I slot release: id 0 | task 2316 | stop processing: n_tokens = 1343, truncated = 0 3.05.922.150 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.830 3.05.922.177 I slot launch_slot_: id 0 | task 2455 | processing task, is_child = 0 3.06.616.260 I slot print_timing: id 3 | task 2363 | n_gen = 100, tg = 22.14 t/s, tg_3s = 22.37 t/s 3.07.009.626 I slot print_timing: id 2 | task 1631 | n_gen = 828, tg = 21.48 t/s, tg_3s = 21.33 t/s 3.07.691.548 I slot print_timing: id 1 | task 1645 | n_gen = 831, tg = 21.69 t/s, tg_3s = 21.31 t/s 3.09.150.309 I slot print_timing: id 3 | task 2363 | prompt eval time = 370.68 ms / 103 tokens ( 3.60 ms per token, 277.87 tokens per second) 3.09.150.313 I slot print_timing: id 3 | task 2363 | eval time = 7004.60 ms / 159 tokens ( 44.33 ms per token, 22.56 tokens per second) 3.09.150.313 I slot print_timing: id 3 | task 2363 | total time = 7375.28 ms / 262 tokens 3.09.150.314 I slot print_timing: id 3 | task 2363 | graphs reused = 2013 3.09.150.314 I slot print_timing: id 3 | task 2363 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.150.369 I slot release: id 3 | task 2363 | stop processing: n_tokens = 1376, truncated = 0 3.09.191.252 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.810 3.09.191.274 I slot launch_slot_: id 3 | task 2526 | processing task, is_child = 0 3.10.015.442 I slot print_timing: id 2 | task 1631 | n_gen = 893, tg = 21.49 t/s, tg_3s = 21.62 t/s 3.10.698.319 I slot print_timing: id 1 | task 1645 | n_gen = 896, tg = 21.69 t/s, tg_3s = 21.62 t/s 3.10.739.565 I slot print_timing: id 0 | task 2455 | n_gen = 100, tg = 22.25 t/s, tg_3s = 22.47 t/s 3.13.015.450 I slot print_timing: id 2 | task 1631 | n_gen = 963, tg = 21.62 t/s, tg_3s = 23.33 t/s 3.13.567.214 I slot print_timing: id 0 | task 2455 | prompt eval time = 367.31 ms / 114 tokens ( 3.22 ms per token, 310.37 tokens per second) 3.13.567.219 I slot print_timing: id 0 | task 2455 | eval time = 7277.72 ms / 166 tokens ( 44.11 ms per token, 22.67 tokens per second) 3.13.567.220 I slot print_timing: id 0 | task 2455 | total time = 7645.03 ms / 280 tokens 3.13.567.220 I slot print_timing: id 0 | task 2455 | graphs reused = 2107 3.13.567.221 I slot print_timing: id 0 | task 2455 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.567.299 I slot release: id 0 | task 2455 | stop processing: n_tokens = 1394, truncated = 0 3.13.572.231 I slot print_timing: id 3 | task 2526 | prompt eval time = 313.38 ms / 71 tokens ( 4.41 ms per token, 226.56 tokens per second) 3.13.572.237 I slot print_timing: id 3 | task 2526 | eval time = 4067.57 ms / 96 tokens ( 42.82 ms per token, 23.36 tokens per second) 3.13.572.238 I slot print_timing: id 3 | task 2526 | total time = 4380.95 ms / 167 tokens 3.13.572.238 I slot print_timing: id 3 | task 2526 | graphs reused = 2107 3.13.572.239 I slot print_timing: id 3 | task 2526 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.572.281 I slot release: id 3 | task 2526 | stop processing: n_tokens = 1281, truncated = 0 3.13.609.819 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.800 3.13.609.843 I slot launch_slot_: id 0 | task 2625 | processing task, is_child = 0 3.13.638.617 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.870 3.13.638.637 I slot launch_slot_: id 3 | task 2626 | processing task, is_child = 0 3.14.069.083 I slot print_timing: id 1 | task 1645 | n_gen = 965, tg = 21.60 t/s, tg_3s = 20.47 t/s 3.16.049.114 I slot print_timing: id 2 | task 1631 | n_gen = 1023, tg = 21.50 t/s, tg_3s = 19.78 t/s 3.16.091.925 I slot print_timing: id 2 | task 1631 | prompt eval time = 412.50 ms / 111 tokens ( 3.72 ms per token, 269.09 tokens per second) 3.16.091.929 I slot print_timing: id 2 | task 1631 | eval time = 47577.04 ms / 1024 tokens ( 46.51 ms per token, 21.50 tokens per second) 3.16.091.930 I slot print_timing: id 2 | task 1631 | total time = 47989.54 ms / 1135 tokens 3.16.091.931 I slot print_timing: id 2 | task 1631 | graphs reused = 2151 3.16.091.931 I slot print_timing: id 2 | task 1631 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.092.002 I slot release: id 2 | task 1631 | stop processing: n_tokens = 2249, truncated = 0 3.16.155.033 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.496 3.16.195.798 I slot launch_slot_: id 2 | task 2675 | processing task, is_child = 0 3.16.957.242 I slot print_timing: id 1 | task 1645 | prompt eval time = 431.94 ms / 128 tokens ( 3.37 ms per token, 296.34 tokens per second) 3.16.957.247 I slot print_timing: id 1 | task 1645 | eval time = 47527.61 ms / 1024 tokens ( 46.46 ms per token, 21.52 tokens per second) 3.16.957.248 I slot print_timing: id 1 | task 1645 | total time = 47959.55 ms / 1152 tokens 3.16.957.249 I slot print_timing: id 1 | task 1645 | graphs reused = 2160 3.16.957.249 I slot print_timing: id 1 | task 1645 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.957.314 I slot release: id 1 | task 1645 | stop processing: n_tokens = 2266, truncated = 0 3.17.018.851 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.492 3.17.045.990 I slot launch_slot_: id 1 | task 2689 | processing task, is_child = 0 3.18.473.794 I slot print_timing: id 3 | task 2626 | prompt eval time = 540.00 ms / 74 tokens ( 7.30 ms per token, 137.04 tokens per second) 3.18.473.798 I slot print_timing: id 3 | task 2626 | eval time = 4293.22 ms / 87 tokens ( 49.92 ms per token, 20.03 tokens per second) 3.18.473.798 I slot print_timing: id 3 | task 2626 | total time = 4833.22 ms / 161 tokens 3.18.473.799 I slot print_timing: id 3 | task 2626 | graphs reused = 2183 3.18.473.799 I slot print_timing: id 3 | task 2626 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.473.853 I slot release: id 3 | task 2626 | stop processing: n_tokens = 1275, truncated = 0 3.18.513.907 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.875 3.18.513.928 I slot launch_slot_: id 3 | task 2718 | processing task, is_child = 0 3.19.230.640 I slot print_timing: id 0 | task 2625 | n_gen = 100, tg = 19.59 t/s, tg_3s = 19.79 t/s 3.19.233.593 I slot print_timing: id 2 | task 2675 | prompt eval time = 357.19 ms / 78 tokens ( 4.58 ms per token, 218.37 tokens per second) 3.19.233.595 I slot print_timing: id 2 | task 2675 | eval time = 2680.59 ms / 52 tokens ( 52.56 ms per token, 19.03 tokens per second) 3.19.233.596 I slot print_timing: id 2 | task 2675 | total time = 3037.78 ms / 130 tokens 3.19.233.597 I slot print_timing: id 2 | task 2675 | graphs reused = 2192 3.19.233.597 I slot print_timing: id 2 | task 2675 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.233.659 I slot release: id 2 | task 2675 | stop processing: n_tokens = 1243, truncated = 0 3.19.296.072 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.897 3.19.296.125 I slot launch_slot_: id 2 | task 2732 | processing task, is_child = 0 3.20.580.316 I slot print_timing: id 0 | task 2625 | prompt eval time = 538.75 ms / 81 tokens ( 6.65 ms per token, 150.35 tokens per second) 3.20.580.319 I slot print_timing: id 0 | task 2625 | eval time = 6402.91 ms / 125 tokens ( 51.64 ms per token, 19.37 tokens per second) 3.20.580.319 I slot print_timing: id 0 | task 2625 | total time = 6941.67 ms / 206 tokens 3.20.580.320 I slot print_timing: id 0 | task 2625 | graphs reused = 2213 3.20.580.321 I slot print_timing: id 0 | task 2625 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.580.376 I slot release: id 0 | task 2625 | stop processing: n_tokens = 1320, truncated = 0 3.20.625.230 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.845 3.20.625.255 I slot launch_slot_: id 0 | task 2758 | processing task, is_child = 0 3.22.323.807 I slot print_timing: id 1 | task 2689 | n_gen = 100, tg = 20.18 t/s, tg_3s = 20.39 t/s 3.22.623.311 I slot print_timing: id 1 | task 2689 | prompt eval time = 373.08 ms / 87 tokens ( 4.29 ms per token, 233.19 tokens per second) 3.22.623.318 I slot print_timing: id 1 | task 2689 | eval time = 5204.23 ms / 107 tokens ( 49.10 ms per token, 20.37 tokens per second) 3.22.623.319 I slot print_timing: id 1 | task 2689 | total time = 5577.31 ms / 194 tokens 3.22.623.319 I slot print_timing: id 1 | task 2689 | graphs reused = 2252 3.22.623.320 I slot print_timing: id 1 | task 2689 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.623.390 I slot release: id 1 | task 2689 | stop processing: n_tokens = 1307, truncated = 0 3.22.687.740 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.853 3.22.687.767 I slot launch_slot_: id 1 | task 2802 | processing task, is_child = 0 3.23.509.949 I slot print_timing: id 3 | task 2718 | prompt eval time = 318.46 ms / 97 tokens ( 3.28 ms per token, 304.59 tokens per second) 3.23.509.956 I slot print_timing: id 3 | task 2718 | eval time = 4677.56 ms / 94 tokens ( 50.30 ms per token, 19.88 tokens per second) 3.23.509.957 I slot print_timing: id 3 | task 2718 | total time = 4996.01 ms / 191 tokens 3.23.509.958 I slot print_timing: id 3 | task 2718 | graphs reused = 2263 3.23.509.958 I slot print_timing: id 3 | task 2718 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.510.016 I slot release: id 3 | task 2718 | stop processing: n_tokens = 1305, truncated = 0 3.23.550.230 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.854 3.23.550.251 I slot launch_slot_: id 3 | task 2818 | processing task, is_child = 0 3.24.533.701 I slot print_timing: id 2 | task 2732 | n_gen = 100, tg = 20.28 t/s, tg_3s = 20.49 t/s 3.24.619.339 I slot print_timing: id 2 | task 2732 | prompt eval time = 356.31 ms / 101 tokens ( 3.53 ms per token, 283.46 tokens per second) 3.24.619.344 I slot print_timing: id 2 | task 2732 | eval time = 4966.89 ms / 102 tokens ( 49.18 ms per token, 20.33 tokens per second) 3.24.619.344 I slot print_timing: id 2 | task 2732 | total time = 5323.20 ms / 203 tokens 3.24.619.345 I slot print_timing: id 2 | task 2732 | graphs reused = 2280 3.24.619.346 I slot print_timing: id 2 | task 2732 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.619.417 I slot release: id 2 | task 2732 | stop processing: n_tokens = 1317, truncated = 0 3.24.682.358 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.847 3.24.682.388 I slot launch_slot_: id 2 | task 2840 | processing task, is_child = 0 3.25.834.073 I slot print_timing: id 0 | task 2758 | prompt eval time = 309.59 ms / 86 tokens ( 3.60 ms per token, 277.78 tokens per second) 3.25.834.077 I slot print_timing: id 0 | task 2758 | eval time = 4899.21 ms / 99 tokens ( 49.99 ms per token, 20.00 tokens per second) 3.25.834.078 I slot print_timing: id 0 | task 2758 | total time = 5208.81 ms / 185 tokens 3.25.834.079 I slot print_timing: id 0 | task 2758 | graphs reused = 2298 3.25.834.079 I slot print_timing: id 0 | task 2758 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.834.166 I slot release: id 0 | task 2758 | stop processing: n_tokens = 1299, truncated = 0 3.25.879.296 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.858 3.25.879.318 I slot launch_slot_: id 0 | task 2863 | processing task, is_child = 0 3.26.720.058 I slot print_timing: id 3 | task 2818 | prompt eval time = 314.67 ms / 81 tokens ( 3.88 ms per token, 257.42 tokens per second) 3.26.720.066 I slot print_timing: id 3 | task 2818 | eval time = 2855.13 ms / 58 tokens ( 50.09 ms per token, 19.96 tokens per second) 3.26.720.067 I slot print_timing: id 3 | task 2818 | total time = 3169.80 ms / 139 tokens 3.26.720.068 I slot print_timing: id 3 | task 2818 | graphs reused = 2312 3.26.720.068 I slot print_timing: id 3 | task 2818 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.720.156 I slot release: id 3 | task 2818 | stop processing: n_tokens = 1253, truncated = 0 3.26.761.055 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.890 3.26.761.075 I slot launch_slot_: id 3 | task 2881 | processing task, is_child = 0 3.28.078.758 I slot print_timing: id 1 | task 2802 | n_gen = 100, tg = 19.52 t/s, tg_3s = 19.71 t/s 3.29.565.135 I slot print_timing: id 3 | task 2881 | prompt eval time = 318.92 ms / 96 tokens ( 3.32 ms per token, 301.02 tokens per second) 3.29.565.139 I slot print_timing: id 3 | task 2881 | eval time = 2485.14 ms / 60 tokens ( 42.12 ms per token, 23.74 tokens per second) 3.29.565.140 I slot print_timing: id 3 | task 2881 | total time = 2804.05 ms / 156 tokens 3.29.565.141 I slot print_timing: id 3 | task 2881 | graphs reused = 2369 3.29.565.141 I slot print_timing: id 3 | task 2881 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.565.200 I slot release: id 3 | task 2881 | stop processing: n_tokens = 1270, truncated = 0 3.29.605.393 I slot print_timing: id 2 | task 2840 | n_gen = 100, tg = 21.66 t/s, tg_3s = 21.88 t/s 3.29.605.401 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.878 3.29.605.426 I slot launch_slot_: id 3 | task 2944 | processing task, is_child = 0 3.29.997.466 I slot print_timing: id 0 | task 2863 | prompt eval time = 255.73 ms / 66 tokens ( 3.87 ms per token, 258.09 tokens per second) 3.29.997.470 I slot print_timing: id 0 | task 2863 | eval time = 3862.41 ms / 82 tokens ( 47.68 ms per token, 20.97 tokens per second) 3.29.997.470 I slot print_timing: id 0 | task 2863 | total time = 4118.14 ms / 148 tokens 3.29.997.471 I slot print_timing: id 0 | task 2863 | graphs reused = 2370 3.29.997.471 I slot print_timing: id 0 | task 2863 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.997.514 I slot release: id 0 | task 2863 | stop processing: n_tokens = 1262, truncated = 0 3.30.038.824 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.884 3.30.038.849 I slot launch_slot_: id 0 | task 2950 | processing task, is_child = 0 3.31.105.492 I slot print_timing: id 1 | task 2802 | n_gen = 161, tg = 19.75 t/s, tg_3s = 20.15 t/s 3.31.527.417 I slot print_timing: id 1 | task 2802 | prompt eval time = 317.98 ms / 65 tokens ( 4.89 ms per token, 204.42 tokens per second) 3.31.527.422 I slot print_timing: id 1 | task 2802 | eval time = 8521.67 ms / 171 tokens ( 50.13 ms per token, 19.95 tokens per second) 3.31.527.422 I slot print_timing: id 1 | task 2802 | total time = 8839.64 ms / 236 tokens 3.31.527.423 I slot print_timing: id 1 | task 2802 | graphs reused = 2398 3.31.527.423 I slot print_timing: id 1 | task 2802 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.527.483 I slot release: id 1 | task 2802 | stop processing: n_tokens = 1350, truncated = 0 3.31.529.072 I slot print_timing: id 2 | task 2840 | prompt eval time = 352.11 ms / 73 tokens ( 4.82 ms per token, 207.32 tokens per second) 3.31.529.077 I slot print_timing: id 2 | task 2840 | eval time = 6494.57 ms / 135 tokens ( 48.47 ms per token, 20.63 tokens per second) 3.31.529.078 I slot print_timing: id 2 | task 2840 | total time = 6846.68 ms / 208 tokens 3.31.529.078 I slot print_timing: id 2 | task 2840 | graphs reused = 2398 3.31.529.079 I slot print_timing: id 2 | task 2840 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.529.129 I slot release: id 2 | task 2840 | stop processing: n_tokens = 1322, truncated = 0 3.31.578.956 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.826 3.31.578.982 I slot launch_slot_: id 1 | task 2982 | processing task, is_child = 0 3.31.618.826 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.843 3.31.618.856 I slot launch_slot_: id 2 | task 2983 | processing task, is_child = 0 3.34.913.351 I slot print_timing: id 3 | task 2944 | n_gen = 100, tg = 19.83 t/s, tg_3s = 20.03 t/s 3.34.952.842 I slot print_timing: id 1 | task 2982 | prompt eval time = 623.19 ms / 89 tokens ( 7.00 ms per token, 142.81 tokens per second) 3.34.952.849 I slot print_timing: id 1 | task 2982 | eval time = 2710.78 ms / 65 tokens ( 42.36 ms per token, 23.61 tokens per second) 3.34.952.850 I slot print_timing: id 1 | task 2982 | total time = 3333.97 ms / 154 tokens 3.34.952.851 I slot print_timing: id 1 | task 2982 | graphs reused = 2460 3.34.952.851 I slot print_timing: id 1 | task 2982 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.952.932 I slot release: id 1 | task 2982 | stop processing: n_tokens = 1267, truncated = 0 3.35.017.473 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.880 3.35.017.499 I slot launch_slot_: id 1 | task 3051 | processing task, is_child = 0 3.35.485.528 I slot print_timing: id 0 | task 2950 | n_gen = 100, tg = 19.26 t/s, tg_3s = 19.45 t/s 3.35.724.901 I slot print_timing: id 0 | task 2950 | prompt eval time = 305.93 ms / 70 tokens ( 4.37 ms per token, 228.81 tokens per second) 3.35.724.907 I slot print_timing: id 0 | task 2950 | eval time = 5380.11 ms / 106 tokens ( 51.24 ms per token, 19.52 tokens per second) 3.35.724.908 I slot print_timing: id 0 | task 2950 | total time = 5686.05 ms / 176 tokens 3.35.724.913 I slot print_timing: id 0 | task 2950 | graphs reused = 2466 3.35.724.913 I slot print_timing: id 0 | task 2950 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.724.958 I slot release: id 0 | task 2950 | stop processing: n_tokens = 1290, truncated = 0 3.35.728.888 I slot print_timing: id 3 | task 2944 | prompt eval time = 314.66 ms / 84 tokens ( 3.75 ms per token, 266.96 tokens per second) 3.35.728.890 I slot print_timing: id 3 | task 2944 | eval time = 5808.80 ms / 111 tokens ( 52.81 ms per token, 18.94 tokens per second) 3.35.728.891 I slot print_timing: id 3 | task 2944 | total time = 6123.46 ms / 195 tokens 3.35.728.891 I slot print_timing: id 3 | task 2944 | graphs reused = 2466 3.35.728.892 I slot print_timing: id 3 | task 2944 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.728.929 I slot release: id 3 | task 2944 | stop processing: n_tokens = 1309, truncated = 0 3.35.766.372 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.864 3.35.766.396 I slot launch_slot_: id 0 | task 3062 | processing task, is_child = 0 3.35.805.247 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.852 3.35.805.271 I slot launch_slot_: id 3 | task 3063 | processing task, is_child = 0 3.37.328.826 I slot print_timing: id 2 | task 2983 | n_gen = 100, tg = 19.47 t/s, tg_3s = 19.66 t/s 3.40.157.053 I slot print_timing: id 1 | task 3051 | n_gen = 100, tg = 21.01 t/s, tg_3s = 21.23 t/s 3.40.368.765 I slot print_timing: id 2 | task 2983 | n_gen = 172, tg = 21.04 t/s, tg_3s = 23.68 t/s 3.40.577.050 I slot print_timing: id 0 | task 3062 | n_gen = 100, tg = 23.73 t/s, tg_3s = 23.97 t/s 3.40.581.859 I slot print_timing: id 3 | task 3063 | n_gen = 100, tg = 23.72 t/s, tg_3s = 23.96 t/s 3.40.998.941 I slot print_timing: id 0 | task 3062 | prompt eval time = 599.47 ms / 93 tokens ( 6.45 ms per token, 155.14 tokens per second) 3.40.998.948 I slot print_timing: id 0 | task 3062 | eval time = 4594.19 ms / 110 tokens ( 42.15 ms per token, 23.73 tokens per second) 3.40.998.948 I slot print_timing: id 0 | task 3062 | total time = 5193.66 ms / 203 tokens 3.40.998.949 I slot print_timing: id 0 | task 3062 | graphs reused = 2574 3.40.998.949 I slot print_timing: id 0 | task 3062 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.999.003 I slot release: id 0 | task 3062 | stop processing: n_tokens = 1317, truncated = 0 3.41.043.983 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.951 (> 0.100 thold), f_keep = 0.847 3.41.044.009 I slot launch_slot_: id 0 | task 3176 | processing task, is_child = 0 3.43.162.707 I slot print_timing: id 1 | task 3051 | n_gen = 167, tg = 21.51 t/s, tg_3s = 22.29 t/s 3.43.374.160 I slot print_timing: id 2 | task 2983 | n_gen = 239, tg = 21.38 t/s, tg_3s = 22.29 t/s 3.43.416.856 I slot print_timing: id 2 | task 2983 | prompt eval time = 620.95 ms / 119 tokens ( 5.22 ms per token, 191.64 tokens per second) 3.43.416.861 I slot print_timing: id 2 | task 2983 | eval time = 11173.64 ms / 240 tokens ( 46.75 ms per token, 21.39 tokens per second) 3.43.416.862 I slot print_timing: id 2 | task 2983 | total time = 11794.59 ms / 359 tokens 3.43.416.863 I slot print_timing: id 2 | task 2983 | graphs reused = 2624 3.43.416.863 I slot print_timing: id 2 | task 2983 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.416.927 I slot release: id 2 | task 2983 | stop processing: n_tokens = 1473, truncated = 0 3.43.479.714 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.757 3.43.479.744 I slot launch_slot_: id 2 | task 3230 | processing task, is_child = 0 3.43.736.682 I slot print_timing: id 3 | task 3063 | n_gen = 165, tg = 22.38 t/s, tg_3s = 20.60 t/s 3.44.559.429 I slot print_timing: id 0 | task 3176 | prompt eval time = 251.75 ms / 57 tokens ( 4.42 ms per token, 226.42 tokens per second) 3.44.559.432 I slot print_timing: id 0 | task 3176 | eval time = 3263.66 ms / 71 tokens ( 46.62 ms per token, 21.45 tokens per second) 3.44.559.433 I slot print_timing: id 0 | task 3176 | total time = 3515.41 ms / 128 tokens 3.44.559.433 I slot print_timing: id 0 | task 3176 | graphs reused = 2640 3.44.559.434 I slot print_timing: id 0 | task 3176 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.559.516 I slot release: id 0 | task 3176 | stop processing: n_tokens = 1242, truncated = 0 3.44.604.779 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.898 3.44.604.803 I slot launch_slot_: id 0 | task 3251 | processing task, is_child = 0 3.46.192.497 I slot print_timing: id 1 | task 3051 | n_gen = 225, tg = 20.84 t/s, tg_3s = 19.14 t/s 3.46.745.013 I slot print_timing: id 3 | task 3063 | n_gen = 228, tg = 21.96 t/s, tg_3s = 20.94 t/s 3.47.462.453 I slot print_timing: id 1 | task 3051 | prompt eval time = 428.18 ms / 133 tokens ( 3.22 ms per token, 310.62 tokens per second) 3.47.462.460 I slot print_timing: id 1 | task 3051 | eval time = 12016.77 ms / 255 tokens ( 47.31 ms per token, 21.14 tokens per second) 3.47.462.461 I slot print_timing: id 1 | task 3051 | total time = 12444.95 ms / 388 tokens 3.47.462.461 I slot print_timing: id 1 | task 3051 | graphs reused = 2699 3.47.462.462 I slot print_timing: id 1 | task 3051 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.462.532 I slot release: id 1 | task 3051 | stop processing: n_tokens = 1502, truncated = 0 3.47.526.916 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.742 3.47.526.940 I slot launch_slot_: id 1 | task 3314 | processing task, is_child = 0 3.48.487.449 I slot print_timing: id 2 | task 3230 | prompt eval time = 352.23 ms / 79 tokens ( 4.46 ms per token, 224.29 tokens per second) 3.48.487.454 I slot print_timing: id 2 | task 3230 | eval time = 4655.47 ms / 97 tokens ( 48.49 ms per token, 20.62 tokens per second) 3.48.487.455 I slot print_timing: id 2 | task 3230 | total time = 5007.69 ms / 176 tokens 3.48.487.455 I slot print_timing: id 2 | task 3230 | graphs reused = 2712 3.48.487.456 I slot print_timing: id 2 | task 3230 | graph reallocs = 0 / 0 (same size) / (changed size) 3.48.487.509 I slot release: id 2 | task 3230 | stop processing: n_tokens = 1290, truncated = 0 3.48.550.062 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.864 3.48.550.092 I slot launch_slot_: id 2 | task 3332 | processing task, is_child = 0 3.49.757.905 I slot print_timing: id 3 | task 3063 | n_gen = 284, tg = 21.20 t/s, tg_3s = 18.59 t/s 3.49.795.568 I slot print_timing: id 0 | task 3251 | n_gen = 100, tg = 20.51 t/s, tg_3s = 20.72 t/s 3.52.432.355 I slot print_timing: id 1 | task 3314 | n_gen = 100, tg = 21.82 t/s, tg_3s = 22.04 t/s 3.52.773.669 I slot print_timing: id 3 | task 3063 | n_gen = 355, tg = 21.63 t/s, tg_3s = 23.54 t/s 3.52.810.949 I slot print_timing: id 0 | task 3251 | n_gen = 171, tg = 21.68 t/s, tg_3s = 23.55 t/s 3.53.154.157 I slot print_timing: id 2 | task 3332 | n_gen = 100, tg = 23.58 t/s, tg_3s = 23.82 t/s 3.53.239.595 I slot print_timing: id 2 | task 3332 | prompt eval time = 406.17 ms / 103 tokens ( 3.94 ms per token, 253.59 tokens per second) 3.53.239.602 I slot print_timing: id 2 | task 3332 | eval time = 4283.32 ms / 102 tokens ( 42.41 ms per token, 23.58 tokens per second) 3.53.239.604 I slot print_timing: id 2 | task 3332 | total time = 4689.50 ms / 205 tokens 3.53.239.605 I slot print_timing: id 2 | task 3332 | graphs reused = 2811 3.53.239.606 I slot print_timing: id 2 | task 3332 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.239.690 I slot release: id 2 | task 3332 | stop processing: n_tokens = 1319, truncated = 0 3.53.302.790 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.845 3.53.302.817 I slot launch_slot_: id 2 | task 3437 | processing task, is_child = 0 3.53.939.768 I slot print_timing: id 0 | task 3251 | prompt eval time = 364.19 ms / 101 tokens ( 3.61 ms per token, 277.33 tokens per second) 3.53.939.773 I slot print_timing: id 0 | task 3251 | eval time = 8970.76 ms / 191 tokens ( 47.21 ms per token, 21.18 tokens per second) 3.53.939.774 I slot print_timing: id 0 | task 3251 | total time = 9334.95 ms / 292 tokens 3.53.939.774 I slot print_timing: id 0 | task 3251 | graphs reused = 2817 3.53.939.775 I slot print_timing: id 0 | task 3251 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.939.831 I slot release: id 0 | task 3251 | stop processing: n_tokens = 1406, truncated = 0 3.53.984.917 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.793 3.53.984.951 I slot launch_slot_: id 0 | task 3448 | processing task, is_child = 0 3.55.470.094 I slot print_timing: id 1 | task 3314 | n_gen = 160, tg = 20.99 t/s, tg_3s = 19.75 t/s 3.55.811.476 I slot print_timing: id 3 | task 3063 | n_gen = 415, tg = 21.34 t/s, tg_3s = 19.75 t/s 3.58.057.378 I slot print_timing: id 2 | task 3437 | n_gen = 100, tg = 22.51 t/s, tg_3s = 22.74 t/s 3.58.478.030 I slot print_timing: id 0 | task 3448 | n_gen = 100, tg = 23.66 t/s, tg_3s = 23.90 t/s 3.58.479.620 I slot print_timing: id 1 | task 3314 | n_gen = 231, tg = 21.73 t/s, tg_3s = 23.59 t/s 3.58.822.989 I slot print_timing: id 3 | task 3063 | n_gen = 486, tg = 21.64 t/s, tg_3s = 23.58 t/s 4.00.395.246 I slot print_timing: id 2 | task 3437 | prompt eval time = 356.94 ms / 100 tokens ( 3.57 ms per token, 280.16 tokens per second) 4.00.395.251 I slot print_timing: id 2 | task 3437 | eval time = 6735.48 ms / 155 tokens ( 43.74 ms per token, 22.86 tokens per second) 4.00.395.251 I slot print_timing: id 2 | task 3437 | total time = 7092.42 ms / 255 tokens 4.00.395.252 I slot print_timing: id 2 | task 3437 | graphs reused = 2961 4.00.395.253 I slot print_timing: id 2 | task 3437 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.395.307 I slot release: id 2 | task 3437 | stop processing: n_tokens = 1369, truncated = 0 4.00.458.283 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.814 4.00.458.315 I slot launch_slot_: id 2 | task 3596 | processing task, is_child = 0 4.01.516.940 I slot print_timing: id 0 | task 3448 | n_gen = 165, tg = 22.70 t/s, tg_3s = 21.39 t/s 4.01.518.712 I slot print_timing: id 1 | task 3314 | n_gen = 296, tg = 21.65 t/s, tg_3s = 21.39 t/s 4.01.862.896 I slot print_timing: id 3 | task 3063 | n_gen = 551, tg = 21.61 t/s, tg_3s = 21.38 t/s 4.04.534.363 I slot print_timing: id 0 | task 3448 | n_gen = 236, tg = 22.95 t/s, tg_3s = 23.53 t/s 4.04.535.968 I slot print_timing: id 1 | task 3314 | n_gen = 367, tg = 21.99 t/s, tg_3s = 23.53 t/s 4.04.878.429 I slot print_timing: id 3 | task 3063 | n_gen = 622, tg = 21.81 t/s, tg_3s = 23.54 t/s 4.05.003.986 I slot print_timing: id 2 | task 3596 | n_gen = 100, tg = 23.61 t/s, tg_3s = 23.84 t/s 4.07.559.029 I slot print_timing: id 0 | task 3448 | n_gen = 307, tg = 23.07 t/s, tg_3s = 23.47 t/s 4.07.560.672 I slot print_timing: id 1 | task 3314 | n_gen = 438, tg = 22.22 t/s, tg_3s = 23.47 t/s 4.07.904.999 I slot print_timing: id 3 | task 3063 | n_gen = 693, tg = 21.97 t/s, tg_3s = 23.46 t/s 4.08.030.684 I slot print_timing: id 2 | task 3596 | n_gen = 171, tg = 23.54 t/s, tg_3s = 23.46 t/s 4.08.754.204 I slot print_timing: id 2 | task 3596 | prompt eval time = 351.87 ms / 77 tokens ( 4.57 ms per token, 218.83 tokens per second) 4.08.754.208 I slot print_timing: id 2 | task 3596 | eval time = 7944.01 ms / 188 tokens ( 42.48 ms per token, 23.54 tokens per second) 4.08.754.208 I slot print_timing: id 2 | task 3596 | total time = 8295.88 ms / 265 tokens 4.08.754.209 I slot print_timing: id 2 | task 3596 | graphs reused = 3146 4.08.754.210 I slot print_timing: id 2 | task 3596 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.754.270 I slot release: id 2 | task 3596 | stop processing: n_tokens = 1379, truncated = 0 4.08.817.438 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.809 4.08.817.462 I slot launch_slot_: id 2 | task 3787 | processing task, is_child = 0 4.10.559.999 I slot print_timing: id 0 | task 3448 | n_gen = 368, tg = 22.56 t/s, tg_3s = 20.33 t/s 4.10.561.672 I slot print_timing: id 1 | task 3314 | n_gen = 499, tg = 21.97 t/s, tg_3s = 20.33 t/s 4.10.908.027 I slot print_timing: id 3 | task 3063 | n_gen = 754, tg = 21.83 t/s, tg_3s = 20.31 t/s 4.12.104.408 I slot print_timing: id 2 | task 3787 | prompt eval time = 467.77 ms / 146 tokens ( 3.20 ms per token, 312.12 tokens per second) 4.12.104.415 I slot print_timing: id 2 | task 3787 | eval time = 2819.16 ms / 67 tokens ( 42.71 ms per token, 23.41 tokens per second) 4.12.104.415 I slot print_timing: id 2 | task 3787 | total time = 3286.93 ms / 213 tokens 4.12.104.416 I slot print_timing: id 2 | task 3787 | graphs reused = 3211 4.12.104.421 I slot print_timing: id 2 | task 3787 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.104.485 I slot release: id 2 | task 3787 | stop processing: n_tokens = 1327, truncated = 0 4.12.167.358 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.840 4.12.167.387 I slot launch_slot_: id 2 | task 3857 | processing task, is_child = 0 4.13.578.201 I slot print_timing: id 0 | task 3448 | n_gen = 433, tg = 22.40 t/s, tg_3s = 21.54 t/s 4.13.579.979 I slot print_timing: id 1 | task 3314 | n_gen = 564, tg = 21.92 t/s, tg_3s = 21.54 t/s 4.13.924.776 I slot print_timing: id 3 | task 3063 | n_gen = 819, tg = 21.80 t/s, tg_3s = 21.55 t/s 4.15.984.795 I slot print_timing: id 2 | task 3857 | prompt eval time = 299.53 ms / 67 tokens ( 4.47 ms per token, 223.69 tokens per second) 4.15.984.800 I slot print_timing: id 2 | task 3857 | eval time = 3517.87 ms / 83 tokens ( 42.90 ms per token, 23.31 tokens per second) 4.15.984.801 I slot print_timing: id 2 | task 3857 | total time = 3817.40 ms / 150 tokens 4.15.984.801 I slot print_timing: id 2 | task 3857 | graphs reused = 3291 4.15.984.802 I slot print_timing: id 2 | task 3857 | graph reallocs = 0 / 0 (same size) / (changed size) 4.15.984.881 I slot release: id 2 | task 3857 | stop processing: n_tokens = 1264, truncated = 0 4.16.047.808 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.951 (> 0.100 thold), f_keep = 0.882 4.16.047.832 I slot launch_slot_: id 2 | task 3943 | processing task, is_child = 0 4.16.588.657 I slot print_timing: id 0 | task 3448 | n_gen = 498, tg = 22.29 t/s, tg_3s = 21.59 t/s 4.16.589.777 I slot print_timing: id 1 | task 3314 | n_gen = 629, tg = 21.89 t/s, tg_3s = 21.60 t/s 4.16.941.095 I slot print_timing: id 3 | task 3063 | n_gen = 884, tg = 21.78 t/s, tg_3s = 21.55 t/s 4.19.079.533 I slot print_timing: id 2 | task 3943 | prompt eval time = 299.08 ms / 57 tokens ( 5.25 ms per token, 190.58 tokens per second) 4.19.079.540 I slot print_timing: id 2 | task 3943 | eval time = 2732.61 ms / 65 tokens ( 42.70 ms per token, 23.42 tokens per second) 4.19.079.540 I slot print_timing: id 2 | task 3943 | total time = 3031.69 ms / 122 tokens 4.19.079.541 I slot print_timing: id 2 | task 3943 | graphs reused = 3354 4.19.079.542 I slot print_timing: id 2 | task 3943 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.079.597 I slot release: id 2 | task 3943 | stop processing: n_tokens = 1236, truncated = 0 4.19.142.694 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.902 4.19.142.720 I slot launch_slot_: id 2 | task 4011 | processing task, is_child = 0 4.19.617.330 I slot print_timing: id 0 | task 3448 | n_gen = 562, tg = 22.15 t/s, tg_3s = 21.13 t/s 4.19.618.426 I slot print_timing: id 1 | task 3314 | n_gen = 693, tg = 21.81 t/s, tg_3s = 21.13 t/s 4.19.964.623 I slot print_timing: id 3 | task 3063 | n_gen = 948, tg = 21.74 t/s, tg_3s = 21.17 t/s 4.22.231.448 I slot print_timing: id 2 | task 4011 | prompt eval time = 354.81 ms / 89 tokens ( 3.99 ms per token, 250.84 tokens per second) 4.22.231.455 I slot print_timing: id 2 | task 4011 | eval time = 2733.91 ms / 65 tokens ( 42.72 ms per token, 23.41 tokens per second) 4.22.231.455 I slot print_timing: id 2 | task 4011 | total time = 3088.72 ms / 154 tokens 4.22.231.456 I slot print_timing: id 2 | task 4011 | graphs reused = 3417 4.22.231.456 I slot print_timing: id 2 | task 4011 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.231.510 I slot release: id 2 | task 4011 | stop processing: n_tokens = 1268, truncated = 0 4.22.294.493 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.879 4.22.294.521 I slot launch_slot_: id 2 | task 4079 | processing task, is_child = 0 4.22.643.558 I slot print_timing: id 0 | task 3448 | n_gen = 626, tg = 22.05 t/s, tg_3s = 21.15 t/s 4.22.644.640 I slot print_timing: id 1 | task 3314 | n_gen = 757, tg = 21.76 t/s, tg_3s = 21.15 t/s 4.22.976.689 I slot print_timing: id 3 | task 3063 | n_gen = 1012, tg = 21.71 t/s, tg_3s = 21.25 t/s 4.23.501.391 I slot print_timing: id 3 | task 3063 | prompt eval time = 600.21 ms / 103 tokens ( 5.83 ms per token, 171.61 tokens per second) 4.23.501.399 I slot print_timing: id 3 | task 3063 | eval time = 47093.44 ms / 1024 tokens ( 46.03 ms per token, 21.72 tokens per second) 4.23.501.400 I slot print_timing: id 3 | task 3063 | total time = 47693.66 ms / 1127 tokens 4.23.501.400 I slot print_timing: id 3 | task 3063 | graphs reused = 3436 4.23.501.401 I slot print_timing: id 3 | task 3063 | graph reallocs = 0 / 0 (same size) / (changed size) 4.23.501.457 I slot release: id 3 | task 3063 | stop processing: n_tokens = 2241, truncated = 0 4.23.541.903 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.498 4.23.578.322 I slot launch_slot_: id 3 | task 4103 | processing task, is_child = 0 4.25.675.777 I slot print_timing: id 0 | task 3448 | n_gen = 691, tg = 21.99 t/s, tg_3s = 21.44 t/s 4.25.677.365 I slot print_timing: id 1 | task 3314 | n_gen = 822, tg = 21.73 t/s, tg_3s = 21.43 t/s 4.26.485.193 I slot print_timing: id 2 | task 4079 | prompt eval time = 351.18 ms / 71 tokens ( 4.95 ms per token, 202.18 tokens per second) 4.26.485.196 I slot print_timing: id 2 | task 4079 | eval time = 3839.49 ms / 85 tokens ( 45.71 ms per token, 21.88 tokens per second) 4.26.485.197 I slot print_timing: id 2 | task 4079 | total time = 4190.66 ms / 156 tokens 4.26.485.198 I slot print_timing: id 2 | task 4079 | graphs reused = 3496 4.26.485.198 I slot print_timing: id 2 | task 4079 | graph reallocs = 0 / 0 (same size) / (changed size) 4.26.485.251 I slot release: id 2 | task 4079 | stop processing: n_tokens = 1270, truncated = 0 4.26.548.114 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.878 4.26.548.140 I slot launch_slot_: id 2 | task 4168 | processing task, is_child = 0 4.28.388.156 I slot print_timing: id 3 | task 4103 | n_gen = 100, tg = 22.05 t/s, tg_3s = 22.27 t/s 4.28.681.319 I slot print_timing: id 0 | task 3448 | n_gen = 755, tg = 21.93 t/s, tg_3s = 21.29 t/s 4.28.682.924 I slot print_timing: id 1 | task 3314 | n_gen = 886, tg = 21.70 t/s, tg_3s = 21.29 t/s 4.29.153.503 I slot print_timing: id 3 | task 4103 | prompt eval time = 319.99 ms / 85 tokens ( 3.76 ms per token, 265.63 tokens per second) 4.29.153.509 I slot print_timing: id 3 | task 4103 | eval time = 5255.18 ms / 118 tokens ( 44.92 ms per token, 22.26 tokens per second) 4.29.153.510 I slot print_timing: id 3 | task 4103 | total time = 5575.17 ms / 203 tokens 4.29.153.511 I slot print_timing: id 3 | task 4103 | graphs reused = 3547 4.29.153.511 I slot print_timing: id 3 | task 4103 | graph reallocs = 0 / 0 (same size) / (changed size) 4.29.153.567 I slot release: id 3 | task 4103 | stop processing: n_tokens = 1316, truncated = 0 4.29.194.047 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.847 4.29.194.072 I slot launch_slot_: id 3 | task 4225 | processing task, is_child = 0 4.31.338.724 I slot print_timing: id 2 | task 4168 | n_gen = 100, tg = 22.30 t/s, tg_3s = 22.52 t/s 4.31.722.502 I slot print_timing: id 0 | task 3448 | n_gen = 821, tg = 21.91 t/s, tg_3s = 21.70 t/s 4.31.724.140 I slot print_timing: id 1 | task 3314 | n_gen = 952, tg = 21.70 t/s, tg_3s = 21.70 t/s 4.32.070.331 I slot print_timing: id 2 | task 4168 | prompt eval time = 350.99 ms / 72 tokens ( 4.87 ms per token, 205.13 tokens per second) 4.32.070.339 I slot print_timing: id 2 | task 4168 | eval time = 5171.19 ms / 117 tokens ( 44.58 ms per token, 22.43 tokens per second) 4.32.070.339 I slot print_timing: id 2 | task 4168 | total time = 5522.18 ms / 189 tokens 4.32.070.340 I slot print_timing: id 2 | task 4168 | graphs reused = 3606 4.32.070.341 I slot print_timing: id 2 | task 4168 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.070.420 I slot release: id 2 | task 4168 | stop processing: n_tokens = 1303, truncated = 0 4.32.133.969 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.856 4.32.133.997 I slot launch_slot_: id 2 | task 4289 | processing task, is_child = 0 4.34.021.102 I slot print_timing: id 3 | task 4225 | n_gen = 100, tg = 21.96 t/s, tg_3s = 22.18 t/s 4.34.744.097 I slot print_timing: id 0 | task 3448 | n_gen = 885, tg = 21.85 t/s, tg_3s = 21.18 t/s 4.34.745.917 I slot print_timing: id 1 | task 3314 | n_gen = 1016, tg = 21.66 t/s, tg_3s = 21.18 t/s 4.35.090.766 I slot print_timing: id 1 | task 3314 | prompt eval time = 368.70 ms / 78 tokens ( 4.73 ms per token, 211.56 tokens per second) 4.35.090.773 I slot print_timing: id 1 | task 3314 | eval time = 47195.12 ms / 1024 tokens ( 46.13 ms per token, 21.68 tokens per second) 4.35.090.774 I slot print_timing: id 1 | task 3314 | total time = 47563.82 ms / 1102 tokens 4.35.090.775 I slot print_timing: id 1 | task 3314 | graphs reused = 3666 4.35.090.775 I slot print_timing: id 1 | task 3314 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.090.844 I slot release: id 1 | task 3314 | stop processing: n_tokens = 2216, truncated = 0 4.35.155.510 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.503 4.35.155.539 I slot launch_slot_: id 1 | task 4354 | processing task, is_child = 0 4.35.828.144 I slot print_timing: id 2 | task 4289 | prompt eval time = 356.16 ms / 94 tokens ( 3.79 ms per token, 263.93 tokens per second) 4.35.828.148 I slot print_timing: id 2 | task 4289 | eval time = 3337.98 ms / 71 tokens ( 47.69 ms per token, 20.97 tokens per second) 4.35.828.148 I slot print_timing: id 2 | task 4289 | total time = 3694.14 ms / 165 tokens 4.35.828.149 I slot print_timing: id 2 | task 4289 | graphs reused = 3671 4.35.828.149 I slot print_timing: id 2 | task 4289 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.828.198 I slot release: id 2 | task 4289 | stop processing: n_tokens = 1279, truncated = 0 4.35.888.444 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.872 4.35.888.464 I slot launch_slot_: id 2 | task 4364 | processing task, is_child = 0 4.37.053.215 I slot print_timing: id 3 | task 4225 | n_gen = 156, tg = 20.55 t/s, tg_3s = 18.47 t/s 4.37.776.824 I slot print_timing: id 0 | task 3448 | n_gen = 941, tg = 21.62 t/s, tg_3s = 18.47 t/s 4.40.085.982 I slot print_timing: id 1 | task 4354 | n_gen = 100, tg = 21.99 t/s, tg_3s = 22.21 t/s 4.40.089.227 I slot print_timing: id 3 | task 4225 | n_gen = 227, tg = 21.37 t/s, tg_3s = 23.39 t/s 4.40.471.943 I slot print_timing: id 2 | task 4364 | n_gen = 100, tg = 23.41 t/s, tg_3s = 23.65 t/s 4.40.812.416 I slot print_timing: id 0 | task 3448 | n_gen = 1012, tg = 21.73 t/s, tg_3s = 23.39 t/s 4.41.324.514 I slot print_timing: id 0 | task 3448 | prompt eval time = 308.83 ms / 83 tokens ( 3.72 ms per token, 268.76 tokens per second) 4.41.324.518 I slot print_timing: id 0 | task 3448 | eval time = 47030.73 ms / 1024 tokens ( 45.97 ms per token, 21.75 tokens per second) 4.41.324.519 I slot print_timing: id 0 | task 3448 | total time = 47339.56 ms / 1107 tokens 4.41.324.520 I slot print_timing: id 0 | task 3448 | graphs reused = 3789 4.41.324.520 I slot print_timing: id 0 | task 3448 | graph reallocs = 0 / 0 (same size) / (changed size) 4.41.324.587 I slot release: id 0 | task 3448 | stop processing: n_tokens = 2221, truncated = 0 4.41.369.816 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.502 4.41.369.840 I slot launch_slot_: id 0 | task 4487 | processing task, is_child = 0 4.43.112.400 I slot print_timing: id 1 | task 4354 | n_gen = 166, tg = 21.92 t/s, tg_3s = 21.81 t/s 4.43.115.593 I slot print_timing: id 3 | task 4225 | n_gen = 293, tg = 21.46 t/s, tg_3s = 21.81 t/s 4.43.495.251 I slot print_timing: id 2 | task 4364 | n_gen = 166, tg = 22.75 t/s, tg_3s = 21.83 t/s 4.44.426.507 I slot print_timing: id 1 | task 4354 | prompt eval time = 428.75 ms / 112 tokens ( 3.83 ms per token, 261.22 tokens per second) 4.44.426.510 I slot print_timing: id 1 | task 4354 | eval time = 8842.20 ms / 197 tokens ( 45.11 ms per token, 22.17 tokens per second) 4.44.426.510 I slot print_timing: id 1 | task 4354 | total time = 9270.96 ms / 309 tokens 4.44.426.511 I slot print_timing: id 1 | task 4354 | graphs reused = 3854 4.44.426.512 I slot print_timing: id 1 | task 4354 | graph reallocs = 0 / 0 (same size) / (changed size) 4.44.426.569 I slot release: id 1 | task 4354 | stop processing: n_tokens = 1422, truncated = 0 4.44.490.872 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.784 4.44.490.898 I slot launch_slot_: id 1 | task 4556 | processing task, is_child = 0 4.46.122.218 I slot print_timing: id 3 | task 4225 | n_gen = 357, tg = 21.43 t/s, tg_3s = 21.29 t/s 4.46.159.914 I slot print_timing: id 0 | task 4487 | n_gen = 100, tg = 22.10 t/s, tg_3s = 22.33 t/s 4.46.502.152 I slot print_timing: id 2 | task 4364 | n_gen = 230, tg = 22.32 t/s, tg_3s = 21.28 t/s 4.49.062.344 I slot print_timing: id 1 | task 4556 | n_gen = 100, tg = 23.55 t/s, tg_3s = 23.79 t/s 4.49.150.438 I slot print_timing: id 3 | task 4225 | n_gen = 428, tg = 21.74 t/s, tg_3s = 23.45 t/s 4.49.187.852 I slot print_timing: id 0 | task 4487 | n_gen = 171, tg = 22.65 t/s, tg_3s = 23.45 t/s 4.49.531.341 I slot print_timing: id 2 | task 4364 | n_gen = 301, tg = 22.58 t/s, tg_3s = 23.44 t/s 4.51.827.642 I slot print_timing: id 1 | task 4556 | prompt eval time = 367.55 ms / 74 tokens ( 4.97 ms per token, 201.33 tokens per second) 4.51.827.649 I slot print_timing: id 1 | task 4556 | eval time = 6969.19 ms / 165 tokens ( 42.50 ms per token, 23.53 tokens per second) 4.51.827.650 I slot print_timing: id 1 | task 4556 | total time = 7336.74 ms / 239 tokens 4.51.827.650 I slot print_timing: id 1 | task 4556 | graphs reused = 4016 4.51.827.651 I slot print_timing: id 1 | task 4556 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.827.703 I slot release: id 1 | task 4556 | stop processing: n_tokens = 1353, truncated = 0 4.51.892.246 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.824 4.51.892.271 I slot launch_slot_: id 1 | task 4724 | processing task, is_child = 0 4.52.156.712 I slot print_timing: id 3 | task 4225 | n_gen = 493, tg = 21.73 t/s, tg_3s = 21.62 t/s 4.52.258.496 I slot print_timing: id 0 | task 4487 | n_gen = 236, tg = 22.22 t/s, tg_3s = 21.17 t/s 4.52.542.993 I slot print_timing: id 2 | task 4364 | n_gen = 365, tg = 22.33 t/s, tg_3s = 21.25 t/s 4.54.250.044 I slot print_timing: id 1 | task 4724 | prompt eval time = 367.08 ms / 73 tokens ( 5.03 ms per token, 198.87 tokens per second) 4.54.250.050 I slot print_timing: id 1 | task 4724 | eval time = 1990.69 ms / 48 tokens ( 42.36 ms per token, 23.61 tokens per second) 4.54.250.051 I slot print_timing: id 1 | task 4724 | total time = 2357.77 ms / 121 tokens 4.54.250.051 I slot print_timing: id 1 | task 4724 | graphs reused = 4062 4.54.250.052 I slot print_timing: id 1 | task 4724 | graph reallocs = 0 / 0 (same size) / (changed size) 4.54.250.106 I slot release: id 1 | task 4724 | stop processing: n_tokens = 1235, truncated = 0 4.54.314.614 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.903 4.54.314.641 I slot launch_slot_: id 1 | task 4775 | processing task, is_child = 0 4.55.192.800 I slot print_timing: id 3 | task 4225 | n_gen = 556, tg = 21.61 t/s, tg_3s = 20.75 t/s 4.55.273.294 I slot print_timing: id 0 | task 4487 | n_gen = 300, tg = 22.00 t/s, tg_3s = 21.23 t/s 4.55.576.161 I slot print_timing: id 2 | task 4364 | n_gen = 429, tg = 22.14 t/s, tg_3s = 21.10 t/s 4.58.220.739 I slot print_timing: id 3 | task 4225 | n_gen = 627, tg = 21.81 t/s, tg_3s = 23.45 t/s 4.58.300.831 I slot print_timing: id 0 | task 4487 | n_gen = 371, tg = 22.26 t/s, tg_3s = 23.45 t/s 4.58.601.972 I slot print_timing: id 2 | task 4364 | n_gen = 500, tg = 22.32 t/s, tg_3s = 23.46 t/s 4.58.900.071 I slot print_timing: id 1 | task 4775 | prompt eval time = 370.15 ms / 97 tokens ( 3.82 ms per token, 262.06 tokens per second) 4.58.900.078 I slot print_timing: id 1 | task 4775 | eval time = 4215.27 ms / 100 tokens ( 42.58 ms per token, 23.49 tokens per second) 4.58.900.079 I slot print_timing: id 1 | task 4775 | total time = 4585.42 ms / 197 tokens 4.58.900.079 I slot print_timing: id 1 | task 4775 | graphs reused = 4159 4.58.900.080 I slot print_timing: id 1 | task 4775 | graph reallocs = 0 / 0 (same size) / (changed size) 4.58.900.161 I slot release: id 1 | task 4775 | stop processing: n_tokens = 1311, truncated = 0 4.58.964.847 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.850 4.58.964.875 I slot launch_slot_: id 1 | task 4878 | processing task, is_child = 0 5.01.225.005 I slot print_timing: id 3 | task 4225 | n_gen = 688, tg = 21.66 t/s, tg_3s = 20.30 t/s 5.01.305.321 I slot print_timing: id 0 | task 4487 | n_gen = 432, tg = 21.96 t/s, tg_3s = 20.30 t/s 5.01.605.711 I slot print_timing: id 2 | task 4364 | n_gen = 561, tg = 22.08 t/s, tg_3s = 20.31 t/s 5.03.652.148 I slot print_timing: id 1 | task 4878 | n_gen = 100, tg = 23.53 t/s, tg_3s = 23.77 t/s 5.04.252.647 I slot print_timing: id 3 | task 4225 | n_gen = 759, tg = 21.82 t/s, tg_3s = 23.45 t/s 5.04.333.000 I slot print_timing: id 0 | task 4487 | n_gen = 503, tg = 22.16 t/s, tg_3s = 23.45 t/s 5.04.634.546 I slot print_timing: id 2 | task 4364 | n_gen = 632, tg = 22.23 t/s, tg_3s = 23.44 t/s 5.06.678.007 I slot print_timing: id 1 | task 4878 | n_gen = 171, tg = 23.50 t/s, tg_3s = 23.46 t/s 5.07.281.643 I slot print_timing: id 3 | task 4225 | n_gen = 830, tg = 21.95 t/s, tg_3s = 23.44 t/s 5.07.363.112 I slot print_timing: id 0 | task 4487 | n_gen = 574, tg = 22.31 t/s, tg_3s = 23.43 t/s 5.07.667.577 I slot print_timing: id 2 | task 4364 | n_gen = 703, tg = 22.34 t/s, tg_3s = 23.41 t/s 5.09.688.253 I slot print_timing: id 1 | task 4878 | n_gen = 241, tg = 23.43 t/s, tg_3s = 23.25 t/s 5.10.292.815 I slot print_timing: id 3 | task 4225 | n_gen = 900, tg = 22.04 t/s, tg_3s = 23.25 t/s 5.10.373.753 I slot print_timing: id 0 | task 4487 | n_gen = 644, tg = 22.41 t/s, tg_3s = 23.25 t/s 5.10.678.774 I slot print_timing: id 2 | task 4364 | n_gen = 773, tg = 22.42 t/s, tg_3s = 23.25 t/s 5.10.935.497 I slot print_timing: id 1 | task 4878 | prompt eval time = 479.73 ms / 142 tokens ( 3.38 ms per token, 296.00 tokens per second) 5.10.935.504 I slot print_timing: id 1 | task 4878 | eval time = 11490.88 ms / 270 tokens ( 42.72 ms per token, 23.41 tokens per second) 5.10.935.505 I slot print_timing: id 1 | task 4878 | total time = 11970.62 ms / 412 tokens 5.10.935.505 I slot print_timing: id 1 | task 4878 | graphs reused = 4426 5.10.935.506 I slot print_timing: id 1 | task 4878 | graph reallocs = 0 / 0 (same size) / (changed size) 5.10.935.566 I slot release: id 1 | task 4878 | stop processing: n_tokens = 1526, truncated = 0 5.11.000.604 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.731 5.11.000.633 I slot launch_slot_: id 1 | task 5151 | processing task, is_child = 0 5.13.297.296 I slot print_timing: id 3 | task 4225 | n_gen = 963, tg = 21.97 t/s, tg_3s = 20.97 t/s 5.13.378.187 I slot print_timing: id 0 | task 4487 | n_gen = 707, tg = 22.27 t/s, tg_3s = 20.97 t/s 5.13.682.304 I slot print_timing: id 2 | task 4364 | n_gen = 836, tg = 22.30 t/s, tg_3s = 20.98 t/s 5.15.141.571 I slot print_timing: id 1 | task 5151 | prompt eval time = 371.42 ms / 92 tokens ( 4.04 ms per token, 247.70 tokens per second) 5.15.141.578 I slot print_timing: id 1 | task 5151 | eval time = 3769.50 ms / 89 tokens ( 42.84 ms per token, 23.35 tokens per second) 5.15.141.579 I slot print_timing: id 1 | task 5151 | total time = 4140.93 ms / 181 tokens 5.15.141.579 I slot print_timing: id 1 | task 5151 | graphs reused = 4513 5.15.141.580 I slot print_timing: id 1 | task 5151 | graph reallocs = 0 / 0 (same size) / (changed size) 5.15.141.648 I slot release: id 1 | task 5151 | stop processing: n_tokens = 1295, truncated = 0 5.15.206.872 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.861 5.15.206.904 I slot launch_slot_: id 1 | task 5243 | processing task, is_child = 0 5.16.199.586 I slot print_timing: id 3 | task 4225 | prompt eval time = 317.91 ms / 88 tokens ( 3.61 ms per token, 276.80 tokens per second) 5.16.199.592 I slot print_timing: id 3 | task 4225 | eval time = 46687.59 ms / 1024 tokens ( 45.64 ms per token, 21.91 tokens per second) 5.16.199.594 I slot print_timing: id 3 | task 4225 | total time = 47005.50 ms / 1112 tokens 5.16.199.594 I slot print_timing: id 3 | task 4225 | graphs reused = 4527 5.16.199.595 I slot print_timing: id 3 | task 4225 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.199.661 I slot release: id 3 | task 4225 | stop processing: n_tokens = 2226, truncated = 0 5.16.241.020 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.501 5.16.241.050 I slot launch_slot_: id 3 | task 5262 | processing task, is_child = 0 5.16.478.602 I slot print_timing: id 0 | task 4487 | n_gen = 768, tg = 22.04 t/s, tg_3s = 19.67 t/s 5.16.718.072 I slot print_timing: id 2 | task 4364 | n_gen = 895, tg = 22.09 t/s, tg_3s = 19.43 t/s 5.19.501.295 I slot print_timing: id 0 | task 4487 | n_gen = 838, tg = 22.13 t/s, tg_3s = 23.16 t/s 5.19.761.233 I slot print_timing: id 2 | task 4364 | n_gen = 966, tg = 22.17 t/s, tg_3s = 23.33 t/s 5.20.018.295 I slot print_timing: id 1 | task 5243 | n_gen = 100, tg = 22.29 t/s, tg_3s = 22.51 t/s 5.20.703.835 I slot print_timing: id 1 | task 5243 | prompt eval time = 369.10 ms / 79 tokens ( 4.67 ms per token, 214.04 tokens per second) 5.20.703.842 I slot print_timing: id 1 | task 5243 | eval time = 5127.82 ms / 116 tokens ( 44.59 ms per token, 22.43 tokens per second) 5.20.703.842 I slot print_timing: id 1 | task 5243 | total time = 5496.92 ms / 195 tokens 5.20.703.843 I slot print_timing: id 1 | task 5243 | graphs reused = 4623 5.20.703.843 I slot print_timing: id 1 | task 5243 | graph reallocs = 0 / 0 (same size) / (changed size) 5.20.703.925 I slot release: id 1 | task 5243 | stop processing: n_tokens = 1309, truncated = 0 5.20.768.874 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.852 5.20.768.899 I slot launch_slot_: id 1 | task 5363 | processing task, is_child = 0 5.21.091.679 I slot print_timing: id 3 | task 5262 | n_gen = 100, tg = 21.83 t/s, tg_3s = 22.05 t/s 5.22.514.176 I slot print_timing: id 0 | task 4487 | n_gen = 900, tg = 22.02 t/s, tg_3s = 20.58 t/s 5.22.603.094 I slot print_timing: id 2 | task 4364 | prompt eval time = 354.83 ms / 88 tokens ( 4.03 ms per token, 248.01 tokens per second) 5.22.603.098 I slot print_timing: id 2 | task 4364 | eval time = 46359.79 ms / 1024 tokens ( 45.32 ms per token, 22.07 tokens per second) 5.22.603.099 I slot print_timing: id 2 | task 4364 | total time = 46714.62 ms / 1112 tokens 5.22.603.100 I slot print_timing: id 2 | task 4364 | graphs reused = 4655 5.22.603.100 I slot print_timing: id 2 | task 4364 | graph reallocs = 0 / 0 (same size) / (changed size) 5.22.603.158 I slot release: id 2 | task 4364 | stop processing: n_tokens = 2226, truncated = 0 5.22.666.029 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.501 5.22.666.058 I slot launch_slot_: id 2 | task 5400 | processing task, is_child = 0 5.24.127.666 I slot print_timing: id 3 | task 5262 | n_gen = 163, tg = 21.40 t/s, tg_3s = 20.75 t/s 5.24.212.975 I slot print_timing: id 3 | task 5262 | prompt eval time = 316.47 ms / 84 tokens ( 3.77 ms per token, 265.43 tokens per second) 5.24.212.982 I slot print_timing: id 3 | task 5262 | eval time = 7655.45 ms / 165 tokens ( 46.68 ms per token, 21.42 tokens per second) 5.24.212.982 I slot print_timing: id 3 | task 5262 | total time = 7971.92 ms / 249 tokens 5.24.212.983 I slot print_timing: id 3 | task 5262 | graphs reused = 4682 5.24.212.983 I slot print_timing: id 3 | task 5262 | graph reallocs = 0 / 0 (same size) / (changed size) 5.24.213.039 I slot release: id 3 | task 5262 | stop processing: n_tokens = 1362, truncated = 0 5.24.253.409 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.819 5.24.253.431 I slot launch_slot_: id 3 | task 5432 | processing task, is_child = 0 5.25.534.521 I slot print_timing: id 0 | task 4487 | n_gen = 959, tg = 21.85 t/s, tg_3s = 19.53 t/s 5.25.922.144 I slot print_timing: id 1 | task 5363 | n_gen = 100, tg = 20.94 t/s, tg_3s = 21.15 t/s 5.26.649.854 I slot print_timing: id 1 | task 5363 | prompt eval time = 426.00 ms / 108 tokens ( 3.94 ms per token, 253.52 tokens per second) 5.26.649.860 I slot print_timing: id 1 | task 5363 | eval time = 5454.95 ms / 117 tokens ( 47.03 ms per token, 21.27 tokens per second) 5.26.649.861 I slot print_timing: id 1 | task 5363 | total time = 5880.95 ms / 225 tokens 5.26.649.861 I slot print_timing: id 1 | task 5363 | graphs reused = 4730 5.26.649.862 I slot print_timing: id 1 | task 5363 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.649.917 I slot release: id 1 | task 5363 | stop processing: n_tokens = 1339, truncated = 0 5.26.714.526 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.833 5.26.714.551 I slot launch_slot_: id 1 | task 5485 | processing task, is_child = 0 5.27.495.671 I slot print_timing: id 2 | task 5400 | prompt eval time = 356.56 ms / 89 tokens ( 4.01 ms per token, 249.61 tokens per second) 5.27.495.675 I slot print_timing: id 2 | task 5400 | eval time = 4473.04 ms / 94 tokens ( 48.10 ms per token, 20.79 tokens per second) 5.27.495.676 I slot print_timing: id 2 | task 5400 | total time = 4829.60 ms / 183 tokens 5.27.495.677 I slot print_timing: id 2 | task 5400 | graphs reused = 4739 5.27.495.678 I slot print_timing: id 2 | task 5400 | graph reallocs = 0 / 0 (same size) / (changed size) 5.27.495.751 I slot release: id 2 | task 5400 | stop processing: n_tokens = 1296, truncated = 0 5.27.562.222 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.860 5.27.562.254 I slot launch_slot_: id 2 | task 5499 | processing task, is_child = 0 5.28.554.534 I slot print_timing: id 0 | task 4487 | n_gen = 1016, tg = 21.65 t/s, tg_3s = 18.87 t/s 5.28.687.494 I slot print_timing: id 3 | task 5432 | prompt eval time = 317.84 ms / 91 tokens ( 3.49 ms per token, 286.30 tokens per second) 5.28.687.501 I slot print_timing: id 3 | task 5432 | eval time = 4116.21 ms / 84 tokens ( 49.59 ms per token, 20.16 tokens per second) 5.28.687.502 I slot print_timing: id 3 | task 5432 | total time = 4434.05 ms / 175 tokens 5.28.687.502 I slot print_timing: id 3 | task 5432 | graphs reused = 4756 5.28.687.503 I slot print_timing: id 3 | task 5432 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.687.568 I slot release: id 3 | task 5432 | stop processing: n_tokens = 1289, truncated = 0 5.28.728.386 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.865 5.28.728.409 I slot launch_slot_: id 3 | task 5521 | processing task, is_child = 0 5.29.121.817 I slot print_timing: id 0 | task 4487 | prompt eval time = 311.32 ms / 85 tokens ( 3.66 ms per token, 273.03 tokens per second) 5.29.121.822 I slot print_timing: id 0 | task 4487 | eval time = 47440.65 ms / 1024 tokens ( 46.37 ms per token, 21.56 tokens per second) 5.29.121.823 I slot print_timing: id 0 | task 4487 | total time = 47751.97 ms / 1109 tokens 5.29.121.823 I slot print_timing: id 0 | task 4487 | graphs reused = 4757 5.29.121.824 I slot print_timing: id 0 | task 4487 | graph reallocs = 0 / 0 (same size) / (changed size) 5.29.121.881 I slot release: id 0 | task 4487 | stop processing: n_tokens = 2222, truncated = 0 5.29.163.373 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.502 5.29.163.393 I slot launch_slot_: id 0 | task 5527 | processing task, is_child = 0 5.32.007.704 I slot print_timing: id 1 | task 5485 | n_gen = 100, tg = 20.12 t/s, tg_3s = 20.32 t/s 5.32.305.645 I slot print_timing: id 2 | task 5499 | prompt eval time = 356.89 ms / 97 tokens ( 3.68 ms per token, 271.79 tokens per second) 5.32.305.649 I slot print_timing: id 2 | task 5499 | eval time = 4386.49 ms / 94 tokens ( 47.17 ms per token, 21.20 tokens per second) 5.32.305.650 I slot print_timing: id 2 | task 5499 | total time = 4743.38 ms / 191 tokens 5.32.305.651 I slot print_timing: id 2 | task 5499 | graphs reused = 4823 5.32.305.651 I slot print_timing: id 2 | task 5499 | graph reallocs = 0 / 0 (same size) / (changed size) 5.32.305.709 I slot release: id 2 | task 5499 | stop processing: n_tokens = 1305, truncated = 0 5.32.368.659 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.854 5.32.368.685 I slot launch_slot_: id 2 | task 5598 | processing task, is_child = 0 5.33.733.800 I slot print_timing: id 3 | task 5521 | n_gen = 100, tg = 21.11 t/s, tg_3s = 21.32 t/s 5.33.940.454 I slot print_timing: id 0 | task 5527 | n_gen = 100, tg = 22.18 t/s, tg_3s = 22.40 t/s 5.34.111.050 I slot print_timing: id 1 | task 5485 | prompt eval time = 371.55 ms / 95 tokens ( 3.91 ms per token, 255.69 tokens per second) 5.34.111.054 I slot print_timing: id 1 | task 5485 | eval time = 7024.94 ms / 143 tokens ( 49.47 ms per token, 20.21 tokens per second) 5.34.111.054 I slot print_timing: id 1 | task 5485 | total time = 7396.49 ms / 238 tokens 5.34.111.055 I slot print_timing: id 1 | task 5485 | graphs reused = 4855 5.34.111.055 I slot print_timing: id 1 | task 5485 | graph reallocs = 0 / 0 (same size) / (changed size) 5.34.111.115 I slot release: id 1 | task 5485 | stop processing: n_tokens = 1352, truncated = 0 5.34.175.357 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.825 5.34.175.382 I slot launch_slot_: id 1 | task 5635 | processing task, is_child = 0 5.35.429.957 I slot print_timing: id 0 | task 5527 | prompt eval time = 312.92 ms / 97 tokens ( 3.23 ms per token, 309.98 tokens per second) 5.35.429.960 I slot print_timing: id 0 | task 5527 | eval time = 5953.63 ms / 128 tokens ( 46.88 ms per token, 21.33 tokens per second) 5.35.429.961 I slot print_timing: id 0 | task 5527 | total time = 6266.56 ms / 225 tokens 5.35.429.962 I slot print_timing: id 0 | task 5527 | graphs reused = 4875 5.35.429.962 I slot print_timing: id 0 | task 5527 | graph reallocs = 0 / 0 (same size) / (changed size) 5.35.430.020 I slot release: id 0 | task 5527 | stop processing: n_tokens = 1337, truncated = 0 5.35.475.072 I slot print_timing: id 3 | task 5521 | prompt eval time = 315.02 ms / 78 tokens ( 4.04 ms per token, 247.60 tokens per second) 5.35.475.080 I slot print_timing: id 3 | task 5521 | eval time = 6431.64 ms / 134 tokens ( 48.36 ms per token, 20.68 tokens per second) 5.35.475.080 I slot print_timing: id 3 | task 5521 | total time = 6746.66 ms / 212 tokens 5.35.475.081 I slot print_timing: id 3 | task 5521 | graphs reused = 4875 5.35.475.082 I slot print_timing: id 3 | task 5521 | graph reallocs = 0 / 0 (same size) / (changed size) 5.35.475.132 I slot release: id 3 | task 5521 | stop processing: n_tokens = 1326, truncated = 0 5.35.475.141 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.834 5.35.475.160 I slot launch_slot_: id 0 | task 5660 | processing task, is_child = 0 5.35.509.448 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.881 (> 0.100 thold), f_keep = 0.841 5.35.509.474 I slot launch_slot_: id 3 | task 5661 | processing task, is_child = 0 5.37.818.804 I slot print_timing: id 2 | task 5598 | n_gen = 100, tg = 19.43 t/s, tg_3s = 19.62 t/s 5.38.172.586 I slot print_timing: id 2 | task 5598 | prompt eval time = 354.33 ms / 89 tokens ( 3.98 ms per token, 251.17 tokens per second) 5.38.172.590 I slot print_timing: id 2 | task 5598 | eval time = 5449.56 ms / 108 tokens ( 50.93 ms per token, 19.63 tokens per second) 5.38.172.590 I slot print_timing: id 2 | task 5598 | total time = 5803.89 ms / 197 tokens 5.38.172.591 I slot print_timing: id 2 | task 5598 | graphs reused = 4920 5.38.172.592 I slot print_timing: id 2 | task 5598 | graph reallocs = 0 / 0 (same size) / (changed size) 5.38.172.648 I slot release: id 2 | task 5598 | stop processing: n_tokens = 1311, truncated = 0 5.38.234.536 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.850 5.38.234.558 I slot launch_slot_: id 2 | task 5712 | processing task, is_child = 0 5.38.628.176 I slot print_timing: id 1 | task 5635 | prompt eval time = 367.54 ms / 74 tokens ( 4.97 ms per token, 201.34 tokens per second) 5.38.628.180 I slot print_timing: id 1 | task 5635 | eval time = 4085.25 ms / 76 tokens ( 54.47 ms per token, 18.36 tokens per second) 5.38.628.180 I slot print_timing: id 1 | task 5635 | total time = 4452.79 ms / 150 tokens 5.38.628.181 I slot print_timing: id 1 | task 5635 | graphs reused = 4920 5.38.628.181 I slot print_timing: id 1 | task 5635 | graph reallocs = 0 / 0 (same size) / (changed size) 5.38.628.227 I slot release: id 1 | task 5635 | stop processing: n_tokens = 1264, truncated = 0 5.38.688.758 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.882 5.38.688.777 I slot launch_slot_: id 1 | task 5717 | processing task, is_child = 0 5.40.315.758 I slot print_timing: id 0 | task 5660 | prompt eval time = 656.06 ms / 75 tokens ( 8.75 ms per token, 114.32 tokens per second) 5.40.315.766 I slot print_timing: id 0 | task 5660 | eval time = 4150.22 ms / 85 tokens ( 49.41 ms per token, 20.24 tokens per second) 5.40.315.767 I slot print_timing: id 0 | task 5660 | total time = 4806.27 ms / 160 tokens 5.40.315.768 I slot print_timing: id 0 | task 5660 | graphs reused = 4949 5.40.315.768 I slot print_timing: id 0 | task 5660 | graph reallocs = 0 / 0 (same size) / (changed size) 5.40.315.839 I slot release: id 0 | task 5660 | stop processing: n_tokens = 1274, truncated = 0 5.40.360.968 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.875 5.40.360.990 I slot launch_slot_: id 0 | task 5751 | processing task, is_child = 0 5.41.169.590 I slot print_timing: id 3 | task 5661 | n_gen = 100, tg = 19.80 t/s, tg_3s = 20.00 t/s 5.42.018.832 I slot print_timing: id 3 | task 5661 | prompt eval time = 657.46 ms / 151 tokens ( 4.35 ms per token, 229.67 tokens per second) 5.42.018.836 I slot print_timing: id 3 | task 5661 | eval time = 5849.98 ms / 120 tokens ( 49.16 ms per token, 20.34 tokens per second) 5.42.018.837 I slot print_timing: id 3 | task 5661 | total time = 6507.44 ms / 271 tokens 5.42.018.837 I slot print_timing: id 3 | task 5661 | graphs reused = 4980 5.42.018.838 I slot print_timing: id 3 | task 5661 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.018.894 I slot release: id 3 | task 5661 | stop processing: n_tokens = 1385, truncated = 0 5.42.059.089 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.805 5.42.059.113 I slot launch_slot_: id 3 | task 5787 | processing task, is_child = 0 5.43.524.599 I slot print_timing: id 2 | task 5712 | n_gen = 100, tg = 20.06 t/s, tg_3s = 20.26 t/s 5.43.692.069 I slot print_timing: id 1 | task 5717 | n_gen = 100, tg = 21.36 t/s, tg_3s = 21.58 t/s 5.43.732.702 I slot print_timing: id 0 | task 5751 | prompt eval time = 309.05 ms / 80 tokens ( 3.86 ms per token, 258.86 tokens per second) 5.43.732.708 I slot print_timing: id 0 | task 5751 | eval time = 3062.65 ms / 68 tokens ( 45.71 ms per token, 21.88 tokens per second) 5.43.732.709 I slot print_timing: id 0 | task 5751 | total time = 3371.71 ms / 148 tokens 5.43.732.710 I slot print_timing: id 0 | task 5751 | graphs reused = 5011 5.43.732.710 I slot print_timing: id 0 | task 5751 | graph reallocs = 0 / 0 (same size) / (changed size) 5.43.732.764 I slot release: id 0 | task 5751 | stop processing: n_tokens = 1262, truncated = 0 5.43.777.725 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.884 5.43.777.754 I slot launch_slot_: id 0 | task 5823 | processing task, is_child = 0 5.44.701.469 I slot print_timing: id 1 | task 5717 | prompt eval time = 369.21 ms / 92 tokens ( 4.01 ms per token, 249.18 tokens per second) 5.44.701.476 I slot print_timing: id 1 | task 5717 | eval time = 5643.48 ms / 120 tokens ( 47.42 ms per token, 21.09 tokens per second) 5.44.701.477 I slot print_timing: id 1 | task 5717 | total time = 6012.68 ms / 212 tokens 5.44.701.477 I slot print_timing: id 1 | task 5717 | graphs reused = 5027 5.44.701.478 I slot print_timing: id 1 | task 5717 | graph reallocs = 0 / 0 (same size) / (changed size) 5.44.701.550 I slot release: id 1 | task 5717 | stop processing: n_tokens = 1326, truncated = 0 5.44.703.252 I slot print_timing: id 2 | task 5712 | prompt eval time = 353.76 ms / 95 tokens ( 3.72 ms per token, 268.54 tokens per second) 5.44.703.254 I slot print_timing: id 2 | task 5712 | eval time = 6114.93 ms / 124 tokens ( 49.71 ms per token, 20.11 tokens per second) 5.44.703.255 I slot print_timing: id 2 | task 5712 | total time = 6468.69 ms / 219 tokens 5.44.703.255 I slot print_timing: id 2 | task 5712 | graphs reused = 5027 5.44.703.256 I slot print_timing: id 2 | task 5712 | graph reallocs = 0 / 0 (same size) / (changed size) 5.44.703.307 I slot release: id 2 | task 5712 | stop processing: n_tokens = 1333, truncated = 0 5.44.752.915 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.841 5.44.752.940 I slot launch_slot_: id 1 | task 5843 | processing task, is_child = 0 5.44.793.044 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.836 5.44.793.074 I slot launch_slot_: id 2 | task 5844 | processing task, is_child = 0 5.47.264.819 I slot print_timing: id 3 | task 5787 | n_gen = 100, tg = 20.26 t/s, tg_3s = 20.47 t/s 5.48.063.755 I slot print_timing: id 1 | task 5843 | prompt eval time = 555.97 ms / 62 tokens ( 8.97 ms per token, 111.52 tokens per second) 5.48.063.763 I slot print_timing: id 1 | task 5843 | eval time = 2714.70 ms / 65 tokens ( 42.42 ms per token, 23.58 tokens per second) 5.48.063.764 I slot print_timing: id 1 | task 5843 | total time = 3270.67 ms / 127 tokens 5.48.063.764 I slot print_timing: id 1 | task 5843 | graphs reused = 5089 5.48.063.765 I slot print_timing: id 1 | task 5843 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.063.826 I slot release: id 1 | task 5843 | stop processing: n_tokens = 1241, truncated = 0 5.48.128.006 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.898 5.48.128.036 I slot launch_slot_: id 1 | task 5912 | processing task, is_child = 0 5.48.557.364 I slot print_timing: id 3 | task 5787 | prompt eval time = 320.24 ms / 95 tokens ( 3.37 ms per token, 296.65 tokens per second) 5.48.557.367 I slot print_timing: id 3 | task 5787 | eval time = 6178.00 ms / 122 tokens ( 51.06 ms per token, 19.59 tokens per second) 5.48.557.368 I slot print_timing: id 3 | task 5787 | total time = 6498.24 ms / 217 tokens 5.48.557.368 I slot print_timing: id 3 | task 5787 | graphs reused = 5089 5.48.557.368 I slot print_timing: id 3 | task 5787 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.557.418 I slot release: id 3 | task 5787 | stop processing: n_tokens = 1331, truncated = 0 5.48.595.442 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.838 5.48.595.461 I slot launch_slot_: id 3 | task 5916 | processing task, is_child = 0 5.49.322.022 I slot print_timing: id 0 | task 5823 | n_gen = 100, tg = 18.72 t/s, tg_3s = 18.91 t/s 5.49.578.570 I slot print_timing: id 0 | task 5823 | prompt eval time = 255.62 ms / 63 tokens ( 4.06 ms per token, 246.46 tokens per second) 5.49.578.577 I slot print_timing: id 0 | task 5823 | eval time = 5545.19 ms / 106 tokens ( 52.81 ms per token, 18.94 tokens per second) 5.49.578.577 I slot print_timing: id 0 | task 5823 | total time = 5800.81 ms / 169 tokens 5.49.578.578 I slot print_timing: id 0 | task 5823 | graphs reused = 5104 5.49.578.578 I slot print_timing: id 0 | task 5823 | graph reallocs = 0 / 0 (same size) / (changed size) 5.49.578.646 I slot release: id 0 | task 5823 | stop processing: n_tokens = 1283, truncated = 0 5.49.623.482 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.869 5.49.623.505 I slot launch_slot_: id 0 | task 5936 | processing task, is_child = 0 5.50.341.612 I slot print_timing: id 2 | task 5844 | n_gen = 100, tg = 19.83 t/s, tg_3s = 20.03 t/s 5.53.183.257 I slot print_timing: id 1 | task 5912 | n_gen = 100, tg = 21.39 t/s, tg_3s = 21.61 t/s 5.53.313.113 I slot print_timing: id 3 | task 5916 | n_gen = 100, tg = 22.49 t/s, tg_3s = 22.72 t/s 5.53.353.938 I slot print_timing: id 2 | task 5844 | n_gen = 171, tg = 21.24 t/s, tg_3s = 23.57 t/s 5.53.862.395 I slot print_timing: id 3 | task 5916 | prompt eval time = 315.50 ms / 94 tokens ( 3.36 ms per token, 297.94 tokens per second) 5.53.862.399 I slot print_timing: id 3 | task 5916 | eval time = 4951.43 ms / 113 tokens ( 44.21 ms per token, 22.62 tokens per second) 5.53.862.399 I slot print_timing: id 3 | task 5916 | total time = 5266.93 ms / 207 tokens 5.53.862.400 I slot print_timing: id 3 | task 5916 | graphs reused = 5196 5.53.862.400 I slot print_timing: id 3 | task 5916 | graph reallocs = 0 / 0 (same size) / (changed size) 5.53.862.460 I slot release: id 3 | task 5916 | stop processing: n_tokens = 1321, truncated = 0 5.53.902.773 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.844 5.53.902.795 I slot launch_slot_: id 3 | task 6033 | processing task, is_child = 0 5.54.392.159 I slot print_timing: id 0 | task 5936 | n_gen = 100, tg = 22.20 t/s, tg_3s = 22.42 t/s 5.56.217.134 I slot print_timing: id 1 | task 5912 | n_gen = 165, tg = 21.40 t/s, tg_3s = 21.42 t/s 5.56.388.890 I slot print_timing: id 2 | task 5844 | n_gen = 236, tg = 21.29 t/s, tg_3s = 21.42 t/s 5.57.428.895 I slot print_timing: id 0 | task 5936 | n_gen = 171, tg = 22.68 t/s, tg_3s = 23.38 t/s 5.58.150.885 I slot print_timing: id 1 | task 5912 | prompt eval time = 427.21 ms / 133 tokens ( 3.21 ms per token, 311.32 tokens per second) 5.58.150.893 I slot print_timing: id 1 | task 5912 | eval time = 9595.63 ms / 210 tokens ( 45.91 ms per token, 21.78 tokens per second) 5.58.150.894 I slot print_timing: id 1 | task 5912 | total time = 10022.84 ms / 343 tokens 5.58.150.894 I slot print_timing: id 1 | task 5912 | graphs reused = 5286 5.58.150.895 I slot print_timing: id 1 | task 5912 | graph reallocs = 0 / 0 (same size) / (changed size) 5.58.150.967 I slot release: id 1 | task 5912 | stop processing: n_tokens = 1457, truncated = 0 5.58.215.521 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.765 5.58.215.547 I slot launch_slot_: id 1 | task 6128 | processing task, is_child = 0 5.58.734.803 I slot print_timing: id 3 | task 6033 | n_gen = 100, tg = 22.20 t/s, tg_3s = 22.42 t/s 5.59.417.637 I slot print_timing: id 2 | task 5844 | n_gen = 301, tg = 21.33 t/s, tg_3s = 21.46 t/s 6.00.432.934 I slot print_timing: id 0 | task 5936 | n_gen = 236, tg = 22.38 t/s, tg_3s = 21.64 t/s 6.01.760.729 I slot print_timing: id 3 | task 6033 | prompt eval time = 371.88 ms / 110 tokens ( 3.38 ms per token, 295.80 tokens per second) 6.01.760.736 I slot print_timing: id 3 | task 6033 | eval time = 7486.05 ms / 171 tokens ( 44.04 ms per token, 22.71 tokens per second) 6.01.760.736 I slot print_timing: id 3 | task 6033 | total time = 7857.93 ms / 281 tokens 6.01.760.737 I slot print_timing: id 3 | task 6033 | graphs reused = 5360 6.01.760.737 I slot print_timing: id 3 | task 6033 | graph reallocs = 0 / 0 (same size) / (changed size) 6.01.760.794 I slot release: id 3 | task 6033 | stop processing: n_tokens = 1395, truncated = 0 6.01.801.101 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.799 6.01.801.122 I slot launch_slot_: id 3 | task 6208 | processing task, is_child = 0 6.02.440.242 I slot print_timing: id 2 | task 5844 | n_gen = 367, tg = 21.42 t/s, tg_3s = 21.84 t/s 6.02.523.626 I slot print_timing: id 1 | task 6128 | prompt eval time = 315.65 ms / 68 tokens ( 4.64 ms per token, 215.43 tokens per second) 6.02.523.633 I slot print_timing: id 1 | task 6128 | eval time = 3992.41 ms / 90 tokens ( 44.86 ms per token, 22.29 tokens per second) 6.02.523.634 I slot print_timing: id 1 | task 6128 | total time = 4308.06 ms / 158 tokens 6.02.523.635 I slot print_timing: id 1 | task 6128 | graphs reused = 5369 6.02.523.636 I slot print_timing: id 1 | task 6128 | graph reallocs = 0 / 0 (same size) / (changed size) 6.02.523.731 I slot release: id 1 | task 6128 | stop processing: n_tokens = 1272, truncated = 0 6.02.592.378 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.877 6.02.592.409 I slot launch_slot_: id 1 | task 6222 | processing task, is_child = 0 6.02.912.132 I slot print_timing: id 0 | task 5936 | prompt eval time = 308.91 ms / 85 tokens ( 3.63 ms per token, 275.16 tokens per second) 6.02.912.137 I slot print_timing: id 0 | task 5936 | eval time = 12979.71 ms / 282 tokens ( 46.19 ms per token, 21.65 tokens per second) 6.02.912.137 I slot print_timing: id 0 | task 5936 | total time = 13288.62 ms / 367 tokens 6.02.912.138 I slot print_timing: id 0 | task 5936 | graphs reused = 5369 6.02.912.138 I slot print_timing: id 0 | task 5936 | graph reallocs = 0 / 0 (same size) / (changed size) 6.02.912.222 I slot release: id 0 | task 5936 | stop processing: n_tokens = 1481, truncated = 0 6.02.987.710 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.753 6.02.987.730 I slot launch_slot_: id 0 | task 6225 | processing task, is_child = 0 6.05.460.357 I slot print_timing: id 2 | task 5844 | n_gen = 425, tg = 21.08 t/s, tg_3s = 19.20 t/s 6.06.661.970 I slot print_timing: id 3 | task 6208 | prompt eval time = 318.12 ms / 100 tokens ( 3.18 ms per token, 314.35 tokens per second) 6.06.661.975 I slot print_timing: id 3 | task 6208 | eval time = 4542.72 ms / 95 tokens ( 48.33 ms per token, 20.69 tokens per second) 6.06.661.976 I slot print_timing: id 3 | task 6208 | total time = 4860.84 ms / 195 tokens 6.06.661.977 I slot print_timing: id 3 | task 6208 | graphs reused = 5447 6.06.661.977 I slot print_timing: id 3 | task 6208 | graph reallocs = 0 / 0 (same size) / (changed size) 6.06.662.032 I slot release: id 3 | task 6208 | stop processing: n_tokens = 1309, truncated = 0 6.06.702.331 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.852 6.06.702.355 I slot launch_slot_: id 3 | task 6308 | processing task, is_child = 0 6.07.636.920 I slot print_timing: id 1 | task 6222 | n_gen = 100, tg = 21.28 t/s, tg_3s = 21.50 t/s 6.07.720.348 I slot print_timing: id 0 | task 6225 | n_gen = 100, tg = 22.37 t/s, tg_3s = 22.60 t/s 6.08.488.791 I slot print_timing: id 2 | task 5844 | n_gen = 491, tg = 21.18 t/s, tg_3s = 21.79 t/s 6.10.654.641 I slot print_timing: id 1 | task 6222 | n_gen = 171, tg = 22.17 t/s, tg_3s = 23.53 t/s 6.10.737.794 I slot print_timing: id 0 | task 6225 | n_gen = 171, tg = 22.84 t/s, tg_3s = 23.53 t/s 6.11.209.608 I slot print_timing: id 3 | task 6308 | n_gen = 100, tg = 23.60 t/s, tg_3s = 23.84 t/s 6.11.506.078 I slot print_timing: id 2 | task 5844 | n_gen = 562, tg = 21.45 t/s, tg_3s = 23.53 t/s 6.11.587.249 I slot print_timing: id 0 | task 6225 | prompt eval time = 307.30 ms / 70 tokens ( 4.39 ms per token, 227.79 tokens per second) 6.11.587.255 I slot print_timing: id 0 | task 6225 | eval time = 8292.22 ms / 191 tokens ( 43.64 ms per token, 22.91 tokens per second) 6.11.587.256 I slot print_timing: id 0 | task 6225 | total time = 8599.51 ms / 261 tokens 6.11.587.256 I slot print_timing: id 0 | task 6225 | graphs reused = 5554 6.11.587.257 I slot print_timing: id 0 | task 6225 | graph reallocs = 0 / 0 (same size) / (changed size) 6.11.587.322 I slot release: id 0 | task 6225 | stop processing: n_tokens = 1375, truncated = 0 6.11.632.548 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.811 6.11.632.570 I slot launch_slot_: id 0 | task 6420 | processing task, is_child = 0 6.12.495.873 I slot print_timing: id 3 | task 6308 | prompt eval time = 312.12 ms / 73 tokens ( 4.28 ms per token, 233.89 tokens per second) 6.12.495.881 I slot print_timing: id 3 | task 6308 | eval time = 5481.39 ms / 125 tokens ( 44.20 ms per token, 22.62 tokens per second) 6.12.495.881 I slot print_timing: id 3 | task 6308 | total time = 5793.51 ms / 198 tokens 6.12.495.882 I slot print_timing: id 3 | task 6308 | graphs reused = 5566 6.12.495.883 I slot print_timing: id 3 | task 6308 | graph reallocs = 0 / 0 (same size) / (changed size) 6.12.495.965 I slot release: id 3 | task 6308 | stop processing: n_tokens = 1312, truncated = 0 6.12.536.731 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.850 6.12.536.753 I slot launch_slot_: id 3 | task 6437 | processing task, is_child = 0 6.13.659.141 I slot print_timing: id 1 | task 6222 | n_gen = 230, tg = 21.45 t/s, tg_3s = 19.64 t/s 6.14.510.567 I slot print_timing: id 2 | task 5844 | n_gen = 621, tg = 21.26 t/s, tg_3s = 19.64 t/s 6.14.807.023 I slot print_timing: id 1 | task 6222 | prompt eval time = 393.10 ms / 106 tokens ( 3.71 ms per token, 269.65 tokens per second) 6.14.807.028 I slot print_timing: id 1 | task 6222 | eval time = 11821.50 ms / 257 tokens ( 46.18 ms per token, 21.66 tokens per second) 6.14.807.028 I slot print_timing: id 1 | task 6222 | total time = 12214.60 ms / 363 tokens 6.14.807.029 I slot print_timing: id 1 | task 6222 | graphs reused = 5610 6.14.807.030 I slot print_timing: id 1 | task 6222 | graph reallocs = 0 / 0 (same size) / (changed size) 6.14.807.097 I slot release: id 1 | task 6222 | stop processing: n_tokens = 1477, truncated = 0 6.14.871.530 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.755 6.14.871.562 I slot launch_slot_: id 1 | task 6486 | processing task, is_child = 0 6.15.518.971 I slot print_timing: id 0 | task 6420 | prompt eval time = 309.98 ms / 91 tokens ( 3.41 ms per token, 293.57 tokens per second) 6.15.518.973 I slot print_timing: id 0 | task 6420 | eval time = 3576.42 ms / 72 tokens ( 50.37 ms per token, 19.85 tokens per second) 6.15.518.974 I slot print_timing: id 0 | task 6420 | total time = 3886.39 ms / 163 tokens 6.15.518.975 I slot print_timing: id 0 | task 6420 | graphs reused = 5616 6.15.518.975 I slot print_timing: id 0 | task 6420 | graph reallocs = 0 / 0 (same size) / (changed size) 6.15.519.024 I slot release: id 0 | task 6420 | stop processing: n_tokens = 1277, truncated = 0 6.15.561.853 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.873 6.15.561.878 I slot launch_slot_: id 0 | task 6497 | processing task, is_child = 0 6.17.523.089 I slot print_timing: id 2 | task 5844 | n_gen = 680, tg = 21.10 t/s, tg_3s = 19.58 t/s 6.17.609.571 I slot print_timing: id 3 | task 6437 | n_gen = 100, tg = 21.05 t/s, tg_3s = 21.26 t/s 6.19.630.997 I slot print_timing: id 1 | task 6486 | n_gen = 100, tg = 22.54 t/s, tg_3s = 22.76 t/s 6.19.888.862 I slot print_timing: id 3 | task 6437 | prompt eval time = 368.92 ms / 105 tokens ( 3.51 ms per token, 284.62 tokens per second) 6.19.888.867 I slot print_timing: id 3 | task 6437 | eval time = 6983.18 ms / 154 tokens ( 45.64 ms per token, 21.91 tokens per second) 6.19.888.867 I slot print_timing: id 3 | task 6437 | total time = 7352.10 ms / 259 tokens 6.19.888.868 I slot print_timing: id 3 | task 6437 | graphs reused = 5711 6.19.888.869 I slot print_timing: id 3 | task 6437 | graph reallocs = 0 / 0 (same size) / (changed size) 6.19.888.946 I slot release: id 3 | task 6437 | stop processing: n_tokens = 1373, truncated = 0 6.19.929.622 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.812 6.19.929.645 I slot launch_slot_: id 3 | task 6596 | processing task, is_child = 0 6.20.337.120 I slot print_timing: id 0 | task 6497 | n_gen = 100, tg = 22.18 t/s, tg_3s = 22.40 t/s 6.20.540.394 I slot print_timing: id 2 | task 5844 | n_gen = 745, tg = 21.14 t/s, tg_3s = 21.54 t/s 6.21.090.105 I slot print_timing: id 1 | task 6486 | prompt eval time = 366.58 ms / 79 tokens ( 4.64 ms per token, 215.50 tokens per second) 6.21.090.109 I slot print_timing: id 1 | task 6486 | eval time = 5851.95 ms / 128 tokens ( 46.08 ms per token, 21.70 tokens per second) 6.21.090.110 I slot print_timing: id 1 | task 6486 | total time = 6218.53 ms / 207 tokens 6.21.090.111 I slot print_timing: id 1 | task 6486 | graphs reused = 5729 6.21.090.111 I slot print_timing: id 1 | task 6486 | graph reallocs = 0 / 0 (same size) / (changed size) 6.21.090.178 I slot release: id 1 | task 6486 | stop processing: n_tokens = 1321, truncated = 0 6.21.154.825 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.844 6.21.154.852 I slot launch_slot_: id 1 | task 6619 | processing task, is_child = 0 6.22.155.442 I slot print_timing: id 0 | task 6497 | prompt eval time = 311.63 ms / 97 tokens ( 3.21 ms per token, 311.27 tokens per second) 6.22.155.448 I slot print_timing: id 0 | task 6497 | eval time = 6281.93 ms / 136 tokens ( 46.53 ms per token, 21.49 tokens per second) 6.22.155.449 I slot print_timing: id 0 | task 6497 | total time = 6593.56 ms / 233 tokens 6.22.155.454 I slot print_timing: id 0 | task 6497 | graphs reused = 5743 6.22.155.455 I slot print_timing: id 0 | task 6497 | graph reallocs = 0 / 0 (same size) / (changed size) 6.22.155.509 I slot release: id 0 | task 6497 | stop processing: n_tokens = 1347, truncated = 0 6.22.200.525 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.828 6.22.200.548 I slot launch_slot_: id 0 | task 6638 | processing task, is_child = 0 6.23.577.834 I slot print_timing: id 2 | task 5844 | n_gen = 804, tg = 21.01 t/s, tg_3s = 19.42 t/s 6.25.025.406 I slot print_timing: id 3 | task 6596 | n_gen = 100, tg = 20.95 t/s, tg_3s = 21.16 t/s 6.25.959.542 I slot print_timing: id 1 | task 6619 | n_gen = 100, tg = 22.32 t/s, tg_3s = 22.55 t/s 6.26.602.589 I slot print_timing: id 2 | task 5844 | n_gen = 875, tg = 21.19 t/s, tg_3s = 23.47 t/s 6.26.727.721 I slot print_timing: id 0 | task 6638 | n_gen = 100, tg = 23.48 t/s, tg_3s = 23.72 t/s 6.27.067.212 I slot print_timing: id 0 | task 6638 | prompt eval time = 311.36 ms / 93 tokens ( 3.35 ms per token, 298.69 tokens per second) 6.27.067.218 I slot print_timing: id 0 | task 6638 | eval time = 4555.29 ms / 108 tokens ( 42.57 ms per token, 23.49 tokens per second) 6.27.067.219 I slot print_timing: id 0 | task 6638 | total time = 4866.65 ms / 201 tokens 6.27.067.220 I slot print_timing: id 0 | task 6638 | graphs reused = 5849 6.27.067.220 I slot print_timing: id 0 | task 6638 | graph reallocs = 0 / 0 (same size) / (changed size) 6.27.067.305 I slot release: id 0 | task 6638 | stop processing: n_tokens = 1315, truncated = 0 6.27.112.842 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.848 6.27.112.871 I slot launch_slot_: id 0 | task 6749 | processing task, is_child = 0 6.27.826.159 I slot print_timing: id 1 | task 6619 | prompt eval time = 369.95 ms / 98 tokens ( 3.78 ms per token, 264.90 tokens per second) 6.27.826.168 I slot print_timing: id 1 | task 6619 | eval time = 6301.35 ms / 139 tokens ( 45.66 ms per token, 21.90 tokens per second) 6.27.826.169 I slot print_timing: id 1 | task 6619 | total time = 6671.30 ms / 237 tokens 6.27.826.169 I slot print_timing: id 1 | task 6619 | graphs reused = 5859 6.27.826.170 I slot print_timing: id 1 | task 6619 | graph reallocs = 0 / 0 (same size) / (changed size) 6.27.826.216 I slot release: id 1 | task 6619 | stop processing: n_tokens = 1351, truncated = 0 6.27.888.040 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.825 6.27.888.064 I slot launch_slot_: id 1 | task 6763 | processing task, is_child = 0 6.28.150.828 I slot print_timing: id 3 | task 6596 | n_gen = 163, tg = 20.63 t/s, tg_3s = 20.16 t/s 6.29.621.503 I slot print_timing: id 2 | task 5844 | n_gen = 934, tg = 21.07 t/s, tg_3s = 19.54 t/s 6.30.945.477 I slot print_timing: id 1 | task 6763 | prompt eval time = 365.83 ms / 71 tokens ( 5.15 ms per token, 194.08 tokens per second) 6.30.945.483 I slot print_timing: id 1 | task 6763 | eval time = 2691.58 ms / 64 tokens ( 42.72 ms per token, 23.41 tokens per second) 6.30.945.484 I slot print_timing: id 1 | task 6763 | total time = 3057.40 ms / 135 tokens 6.30.945.485 I slot print_timing: id 1 | task 6763 | graphs reused = 5921 6.30.945.486 I slot print_timing: id 1 | task 6763 | graph reallocs = 0 / 0 (same size) / (changed size) 6.30.945.554 I slot release: id 1 | task 6763 | stop processing: n_tokens = 1249, truncated = 0 6.31.010.138 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.893 6.31.010.163 I slot launch_slot_: id 1 | task 6830 | processing task, is_child = 0 6.31.337.886 I slot print_timing: id 3 | task 6596 | n_gen = 229, tg = 20.65 t/s, tg_3s = 20.71 t/s 6.32.287.400 I slot print_timing: id 0 | task 6749 | n_gen = 100, tg = 20.34 t/s, tg_3s = 20.54 t/s 6.32.458.130 I slot print_timing: id 0 | task 6749 | prompt eval time = 306.50 ms / 76 tokens ( 4.03 ms per token, 247.96 tokens per second) 6.32.458.135 I slot print_timing: id 0 | task 6749 | eval time = 5038.75 ms / 104 tokens ( 48.92 ms per token, 20.44 tokens per second) 6.32.458.135 I slot print_timing: id 0 | task 6749 | total time = 5345.25 ms / 180 tokens 6.32.458.136 I slot print_timing: id 0 | task 6749 | graphs reused = 5944 6.32.458.137 I slot print_timing: id 0 | task 6749 | graph reallocs = 0 / 0 (same size) / (changed size) 6.32.458.206 I slot release: id 0 | task 6749 | stop processing: n_tokens = 1294, truncated = 0 6.32.503.896 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.862 6.32.503.919 I slot launch_slot_: id 0 | task 6858 | processing task, is_child = 0 6.32.684.449 I slot print_timing: id 2 | task 5844 | n_gen = 994, tg = 20.98 t/s, tg_3s = 19.59 t/s 6.33.221.937 I slot print_timing: id 3 | task 6596 | prompt eval time = 369.57 ms / 108 tokens ( 3.42 ms per token, 292.23 tokens per second) 6.33.221.947 I slot print_timing: id 3 | task 6596 | eval time = 12922.71 ms / 268 tokens ( 48.40 ms per token, 20.66 tokens per second) 6.33.221.948 I slot print_timing: id 3 | task 6596 | total time = 13292.28 ms / 376 tokens 6.33.221.949 I slot print_timing: id 3 | task 6596 | graphs reused = 5955 6.33.221.950 I slot print_timing: id 3 | task 6596 | graph reallocs = 0 / 0 (same size) / (changed size) 6.33.222.038 I slot release: id 3 | task 6596 | stop processing: n_tokens = 1490, truncated = 0 6.33.263.743 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.748 6.33.263.771 I slot launch_slot_: id 3 | task 6873 | processing task, is_child = 0 6.34.201.566 I slot print_timing: id 2 | task 5844 | prompt eval time = 555.31 ms / 105 tokens ( 5.29 ms per token, 189.08 tokens per second) 6.34.201.570 I slot print_timing: id 2 | task 5844 | eval time = 48851.27 ms / 1024 tokens ( 47.75 ms per token, 20.94 tokens per second) 6.34.201.571 I slot print_timing: id 2 | task 5844 | total time = 49406.58 ms / 1129 tokens 6.34.201.572 I slot print_timing: id 2 | task 5844 | graphs reused = 5969 6.34.201.572 I slot print_timing: id 2 | task 5844 | graph reallocs = 0 / 0 (same size) / (changed size) 6.34.201.633 I slot release: id 2 | task 5844 | stop processing: n_tokens = 2243, truncated = 0 6.34.265.076 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.497 6.34.265.293 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.306 MiB) 6.34.265.299 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.151 MiB) 6.34.265.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.106 MiB) 6.34.265.306 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 49.228 MiB) 6.34.265.309 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.629 MiB) 6.34.318.244 I slot launch_slot_: id 2 | task 6892 | processing task, is_child = 0 6.36.373.776 I slot print_timing: id 1 | task 6830 | n_gen = 100, tg = 20.07 t/s, tg_3s = 20.27 t/s 6.37.178.893 I slot print_timing: id 0 | task 6858 | prompt eval time = 254.23 ms / 64 tokens ( 3.97 ms per token, 251.74 tokens per second) 6.37.178.900 I slot print_timing: id 0 | task 6858 | eval time = 4420.73 ms / 92 tokens ( 48.58 ms per token, 20.58 tokens per second) 6.37.178.900 I slot print_timing: id 0 | task 6858 | total time = 4674.97 ms / 156 tokens 6.37.178.901 I slot print_timing: id 0 | task 6858 | graphs reused = 6027 6.37.178.902 I slot print_timing: id 0 | task 6858 | graph reallocs = 0 / 0 (same size) / (changed size) 6.37.178.971 I slot release: id 0 | task 6858 | stop processing: n_tokens = 1270, truncated = 0 6.37.223.899 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.878 6.37.223.923 I slot launch_slot_: id 0 | task 6955 | processing task, is_child = 0 6.37.821.187 I slot print_timing: id 2 | task 6892 | prompt eval time = 352.77 ms / 70 tokens ( 5.04 ms per token, 198.43 tokens per second) 6.37.821.192 I slot print_timing: id 2 | task 6892 | eval time = 3150.16 ms / 70 tokens ( 45.65 ms per token, 21.90 tokens per second) 6.37.821.193 I slot print_timing: id 2 | task 6892 | total time = 3502.93 ms / 140 tokens 6.37.821.194 I slot print_timing: id 2 | task 6892 | graphs reused = 6034 6.37.821.195 I slot print_timing: id 2 | task 6892 | graph reallocs = 0 / 0 (same size) / (changed size) 6.37.821.258 I slot release: id 2 | task 6892 | stop processing: n_tokens = 1253, truncated = 0 6.37.887.595 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.890 6.37.887.626 I slot launch_slot_: id 2 | task 6966 | processing task, is_child = 0 6.38.243.363 I slot print_timing: id 1 | task 6830 | prompt eval time = 430.68 ms / 127 tokens ( 3.39 ms per token, 294.88 tokens per second) 6.38.243.366 I slot print_timing: id 1 | task 6830 | eval time = 6802.52 ms / 132 tokens ( 51.93 ms per token, 19.26 tokens per second) 6.38.243.367 I slot print_timing: id 1 | task 6830 | total time = 7233.19 ms / 259 tokens 6.38.243.367 I slot print_timing: id 1 | task 6830 | graphs reused = 6034 6.38.243.368 I slot print_timing: id 1 | task 6830 | graph reallocs = 0 / 0 (same size) / (changed size) 6.38.243.409 I slot release: id 1 | task 6830 | stop processing: n_tokens = 1373, truncated = 0 6.38.304.100 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.812 6.38.304.128 I slot launch_slot_: id 1 | task 6970 | processing task, is_child = 0 6.38.873.856 I slot print_timing: id 3 | task 6873 | n_gen = 100, tg = 18.69 t/s, tg_3s = 18.88 t/s 6.39.723.291 I slot print_timing: id 3 | task 6873 | prompt eval time = 312.85 ms / 74 tokens ( 4.23 ms per token, 236.54 tokens per second) 6.39.723.295 I slot print_timing: id 3 | task 6873 | eval time = 6146.66 ms / 120 tokens ( 51.65 ms per token, 19.36 tokens per second) 6.39.723.295 I slot print_timing: id 3 | task 6873 | total time = 6459.51 ms / 194 tokens 6.39.723.296 I slot print_timing: id 3 | task 6873 | graphs reused = 6059 6.39.723.297 I slot print_timing: id 3 | task 6873 | graph reallocs = 0 / 0 (same size) / (changed size) 6.39.723.360 I slot release: id 3 | task 6873 | stop processing: n_tokens = 1308, truncated = 0 6.39.763.501 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.852 6.39.763.525 I slot launch_slot_: id 3 | task 7000 | processing task, is_child = 0 6.41.449.190 I slot print_timing: id 1 | task 6970 | prompt eval time = 313.68 ms / 65 tokens ( 4.83 ms per token, 207.22 tokens per second) 6.41.449.194 I slot print_timing: id 1 | task 6970 | eval time = 2831.37 ms / 60 tokens ( 47.99 ms per token, 20.84 tokens per second) 6.41.449.195 I slot print_timing: id 1 | task 6970 | total time = 3145.05 ms / 125 tokens 6.41.449.196 I slot print_timing: id 1 | task 6970 | graphs reused = 6087 6.41.449.196 I slot print_timing: id 1 | task 6970 | graph reallocs = 0 / 0 (same size) / (changed size) 6.41.449.262 I slot release: id 1 | task 6970 | stop processing: n_tokens = 1239, truncated = 0 6.41.513.556 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.900 6.41.513.589 I slot launch_slot_: id 1 | task 7034 | processing task, is_child = 0 6.42.891.455 I slot print_timing: id 0 | task 6955 | n_gen = 100, tg = 18.48 t/s, tg_3s = 18.67 t/s 6.43.319.562 I slot print_timing: id 2 | task 6966 | n_gen = 100, tg = 19.51 t/s, tg_3s = 19.70 t/s 6.43.485.944 I slot print_timing: id 0 | task 6955 | prompt eval time = 310.35 ms / 88 tokens ( 3.53 ms per token, 283.55 tokens per second) 6.43.485.947 I slot print_timing: id 0 | task 6955 | eval time = 5951.66 ms / 114 tokens ( 52.67 ms per token, 18.99 tokens per second) 6.43.485.948 I slot print_timing: id 0 | task 6955 | total time = 6262.01 ms / 202 tokens 6.43.485.949 I slot print_timing: id 0 | task 6955 | graphs reused = 6124 6.43.485.949 I slot print_timing: id 0 | task 6955 | graph reallocs = 0 / 0 (same size) / (changed size) 6.43.486.011 I slot release: id 0 | task 6955 | stop processing: n_tokens = 1316, truncated = 0 6.43.531.076 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.847 6.43.531.103 I slot launch_slot_: id 0 | task 7076 | processing task, is_child = 0 6.44.954.010 I slot print_timing: id 3 | task 7000 | n_gen = 100, tg = 20.78 t/s, tg_3s = 20.99 t/s 6.46.348.991 I slot print_timing: id 1 | task 7034 | n_gen = 100, tg = 22.16 t/s, tg_3s = 22.39 t/s 6.46.350.593 I slot print_timing: id 2 | task 6966 | n_gen = 165, tg = 20.23 t/s, tg_3s = 21.44 t/s 6.47.961.460 I slot print_timing: id 3 | task 7000 | n_gen = 171, tg = 21.88 t/s, tg_3s = 23.61 t/s 6.48.083.610 I slot print_timing: id 0 | task 7076 | n_gen = 100, tg = 23.66 t/s, tg_3s = 23.90 t/s 6.48.256.049 I slot print_timing: id 2 | task 6966 | prompt eval time = 356.88 ms / 95 tokens ( 3.76 ms per token, 266.19 tokens per second) 6.48.256.052 I slot print_timing: id 2 | task 6966 | eval time = 10011.53 ms / 210 tokens ( 47.90 ms per token, 20.88 tokens per second) 6.48.256.053 I slot print_timing: id 2 | task 6966 | total time = 10368.41 ms / 305 tokens 6.48.256.053 I slot print_timing: id 2 | task 6966 | graphs reused = 6226 6.48.256.054 I slot print_timing: id 2 | task 6966 | graph reallocs = 0 / 0 (same size) / (changed size) 6.48.256.111 I slot release: id 2 | task 6966 | stop processing: n_tokens = 1419, truncated = 0 6.48.318.994 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.786 6.48.319.023 I slot launch_slot_: id 2 | task 7183 | processing task, is_child = 0 6.49.354.949 I slot print_timing: id 1 | task 7034 | n_gen = 164, tg = 21.81 t/s, tg_3s = 21.29 t/s 6.50.978.450 I slot print_timing: id 3 | task 7000 | n_gen = 235, tg = 21.69 t/s, tg_3s = 21.21 t/s 6.51.058.035 I slot print_timing: id 0 | task 7076 | prompt eval time = 368.56 ms / 123 tokens ( 3.00 ms per token, 333.73 tokens per second) 6.51.058.041 I slot print_timing: id 0 | task 7076 | eval time = 7158.36 ms / 163 tokens ( 44.19 ms per token, 22.63 tokens per second) 6.51.058.041 I slot print_timing: id 0 | task 7076 | total time = 7526.92 ms / 286 tokens 6.51.058.042 I slot print_timing: id 0 | task 7076 | graphs reused = 6281 6.51.058.043 I slot print_timing: id 0 | task 7076 | graph reallocs = 0 / 0 (same size) / (changed size) 6.51.058.103 I slot release: id 0 | task 7076 | stop processing: n_tokens = 1400, truncated = 0 6.51.103.684 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.796 6.51.103.706 I slot launch_slot_: id 0 | task 7243 | processing task, is_child = 0 6.52.223.976 I slot print_timing: id 2 | task 7183 | prompt eval time = 355.68 ms / 86 tokens ( 4.14 ms per token, 241.79 tokens per second) 6.52.223.980 I slot print_timing: id 2 | task 7183 | eval time = 3549.26 ms / 78 tokens ( 46.09 ms per token, 21.69 tokens per second) 6.52.223.980 I slot print_timing: id 2 | task 7183 | total time = 3904.94 ms / 164 tokens 6.52.223.981 I slot print_timing: id 2 | task 7183 | graphs reused = 6299 6.52.223.982 I slot print_timing: id 2 | task 7183 | graph reallocs = 0 / 0 (same size) / (changed size) 6.52.224.035 I slot release: id 2 | task 7183 | stop processing: n_tokens = 1277, truncated = 0 6.52.286.663 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.873 6.52.286.689 I slot launch_slot_: id 2 | task 7265 | processing task, is_child = 0 6.52.542.523 I slot print_timing: id 1 | task 7034 | n_gen = 227, tg = 21.20 t/s, tg_3s = 19.76 t/s 6.54.002.657 I slot print_timing: id 3 | task 7000 | n_gen = 293, tg = 21.14 t/s, tg_3s = 19.18 t/s 6.55.406.619 I slot print_timing: id 3 | task 7000 | prompt eval time = 426.60 ms / 145 tokens ( 2.94 ms per token, 339.89 tokens per second) 6.55.406.626 I slot print_timing: id 3 | task 7000 | eval time = 15216.48 ms / 326 tokens ( 46.82 ms per token, 21.36 tokens per second) 6.55.406.628 I slot print_timing: id 3 | task 7000 | total time = 15643.08 ms / 471 tokens 6.55.406.629 I slot print_timing: id 3 | task 7000 | graphs reused = 6362 6.55.406.629 I slot print_timing: id 3 | task 7000 | graph reallocs = 0 / 0 (same size) / (changed size) 6.55.406.701 I slot release: id 3 | task 7000 | stop processing: n_tokens = 1585, truncated = 0 6.55.447.051 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.703 6.55.447.074 I slot launch_slot_: id 3 | task 7334 | processing task, is_child = 0 6.55.741.362 I slot print_timing: id 1 | task 7034 | n_gen = 295, tg = 21.21 t/s, tg_3s = 21.26 t/s 6.56.228.304 I slot print_timing: id 0 | task 7243 | n_gen = 100, tg = 20.81 t/s, tg_3s = 21.02 t/s 6.57.128.361 I slot print_timing: id 2 | task 7265 | n_gen = 100, tg = 22.05 t/s, tg_3s = 22.28 t/s 6.58.779.029 I slot print_timing: id 1 | task 7034 | n_gen = 366, tg = 21.60 t/s, tg_3s = 23.37 t/s 6.59.242.891 I slot print_timing: id 0 | task 7243 | n_gen = 171, tg = 21.87 t/s, tg_3s = 23.55 t/s 7.00.013.984 I slot print_timing: id 3 | task 7334 | n_gen = 100, tg = 23.60 t/s, tg_3s = 23.84 t/s 7.00.140.298 I slot print_timing: id 2 | task 7265 | n_gen = 171, tg = 22.66 t/s, tg_3s = 23.57 t/s 7.00.350.202 I slot print_timing: id 0 | task 7243 | prompt eval time = 367.41 ms / 120 tokens ( 3.06 ms per token, 326.61 tokens per second) 7.00.350.208 I slot print_timing: id 0 | task 7243 | eval time = 8879.08 ms / 197 tokens ( 45.30 ms per token, 22.07 tokens per second) 7.00.350.209 I slot print_timing: id 0 | task 7243 | total time = 9246.49 ms / 317 tokens 7.00.350.210 I slot print_timing: id 0 | task 7243 | graphs reused = 6467 7.00.350.210 I slot print_timing: id 0 | task 7243 | graph reallocs = 0 / 0 (same size) / (changed size) 7.00.350.269 I slot release: id 0 | task 7243 | stop processing: n_tokens = 1431, truncated = 0 7.00.395.431 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.779 7.00.395.453 I slot launch_slot_: id 0 | task 7445 | processing task, is_child = 0 7.01.798.688 I slot print_timing: id 1 | task 7034 | n_gen = 432, tg = 21.64 t/s, tg_3s = 21.86 t/s 7.03.037.726 I slot print_timing: id 3 | task 7334 | n_gen = 166, tg = 22.86 t/s, tg_3s = 21.83 t/s 7.03.163.546 I slot print_timing: id 2 | task 7265 | n_gen = 237, tg = 22.42 t/s, tg_3s = 21.83 t/s 7.03.799.354 I slot print_timing: id 3 | task 7334 | prompt eval time = 371.63 ms / 111 tokens ( 3.35 ms per token, 298.69 tokens per second) 7.03.799.359 I slot print_timing: id 3 | task 7334 | eval time = 7980.64 ms / 184 tokens ( 43.61 ms per token, 22.93 tokens per second) 7.03.799.360 I slot print_timing: id 3 | task 7334 | total time = 8352.27 ms / 295 tokens 7.03.799.361 I slot print_timing: id 3 | task 7334 | graphs reused = 6540 7.03.799.361 I slot print_timing: id 3 | task 7334 | graph reallocs = 0 / 0 (same size) / (changed size) 7.03.799.430 I slot release: id 3 | task 7334 | stop processing: n_tokens = 1409, truncated = 0 7.03.839.965 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.791 7.03.839.992 I slot launch_slot_: id 3 | task 7522 | processing task, is_child = 0 7.04.819.660 I slot print_timing: id 1 | task 7034 | n_gen = 498, tg = 21.67 t/s, tg_3s = 21.85 t/s 7.05.114.696 I slot print_timing: id 0 | task 7445 | n_gen = 100, tg = 22.46 t/s, tg_3s = 22.69 t/s 7.06.190.138 I slot print_timing: id 2 | task 7265 | n_gen = 303, tg = 22.29 t/s, tg_3s = 21.81 t/s 7.06.313.841 I slot print_timing: id 0 | task 7445 | prompt eval time = 311.15 ms / 96 tokens ( 3.24 ms per token, 308.53 tokens per second) 7.06.313.847 I slot print_timing: id 0 | task 7445 | eval time = 5607.23 ms / 128 tokens ( 44.15 ms per token, 22.65 tokens per second) 7.06.313.848 I slot print_timing: id 0 | task 7445 | total time = 5918.38 ms / 224 tokens 7.06.313.848 I slot print_timing: id 0 | task 7445 | graphs reused = 6590 7.06.313.849 I slot print_timing: id 0 | task 7445 | graph reallocs = 0 / 0 (same size) / (changed size) 7.06.313.911 I slot release: id 0 | task 7445 | stop processing: n_tokens = 1338, truncated = 0 7.06.359.046 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.833 7.06.359.071 I slot launch_slot_: id 0 | task 7577 | processing task, is_child = 0 7.07.857.167 I slot print_timing: id 1 | task 7034 | n_gen = 564, tg = 21.67 t/s, tg_3s = 21.73 t/s 7.08.374.334 I slot print_timing: id 3 | task 7522 | prompt eval time = 312.22 ms / 71 tokens ( 4.40 ms per token, 227.40 tokens per second) 7.08.374.338 I slot print_timing: id 3 | task 7522 | eval time = 4222.12 ms / 95 tokens ( 44.92 ms per token, 22.26 tokens per second) 7.08.374.338 I slot print_timing: id 3 | task 7522 | total time = 4534.34 ms / 166 tokens 7.08.374.339 I slot print_timing: id 3 | task 7522 | graphs reused = 6630 7.08.374.340 I slot print_timing: id 3 | task 7522 | graph reallocs = 0 / 0 (same size) / (changed size) 7.08.374.393 I slot release: id 3 | task 7522 | stop processing: n_tokens = 1280, truncated = 0 7.08.414.775 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.871 7.08.414.797 I slot launch_slot_: id 3 | task 7621 | processing task, is_child = 0 7.09.195.243 I slot print_timing: id 2 | task 7265 | n_gen = 363, tg = 21.87 t/s, tg_3s = 19.97 t/s 7.10.857.648 I slot print_timing: id 1 | task 7034 | n_gen = 629, tg = 21.67 t/s, tg_3s = 21.66 t/s 7.11.110.218 I slot print_timing: id 0 | task 7577 | n_gen = 100, tg = 22.29 t/s, tg_3s = 22.52 t/s 7.12.215.090 I slot print_timing: id 2 | task 7265 | n_gen = 434, tg = 22.12 t/s, tg_3s = 23.51 t/s 7.12.938.992 I slot print_timing: id 3 | task 7621 | n_gen = 100, tg = 23.51 t/s, tg_3s = 23.75 t/s 7.13.061.273 I slot print_timing: id 0 | task 7577 | prompt eval time = 310.11 ms / 86 tokens ( 3.61 ms per token, 277.32 tokens per second) 7.13.061.280 I slot print_timing: id 0 | task 7577 | eval time = 6392.07 ms / 146 tokens ( 44.08 ms per token, 22.68 tokens per second) 7.13.061.281 I slot print_timing: id 0 | task 7577 | total time = 6702.19 ms / 232 tokens 7.13.061.281 I slot print_timing: id 0 | task 7577 | graphs reused = 6730 7.13.061.282 I slot print_timing: id 0 | task 7577 | graph reallocs = 0 / 0 (same size) / (changed size) 7.13.061.349 I slot release: id 0 | task 7577 | stop processing: n_tokens = 1346, truncated = 0 7.13.106.751 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.828 7.13.106.772 I slot launch_slot_: id 0 | task 7727 | processing task, is_child = 0 7.13.867.595 I slot print_timing: id 1 | task 7034 | n_gen = 695, tg = 21.70 t/s, tg_3s = 21.93 t/s 7.13.872.443 I slot print_timing: id 3 | task 7621 | prompt eval time = 313.01 ms / 76 tokens ( 4.12 ms per token, 242.80 tokens per second) 7.13.872.447 I slot print_timing: id 3 | task 7621 | eval time = 5144.62 ms / 117 tokens ( 44.35 ms per token, 22.55 tokens per second) 7.13.872.448 I slot print_timing: id 3 | task 7621 | total time = 5457.64 ms / 193 tokens 7.13.872.449 I slot print_timing: id 3 | task 7621 | graphs reused = 6741 7.13.872.450 I slot print_timing: id 3 | task 7621 | graph reallocs = 0 / 0 (same size) / (changed size) 7.13.872.531 I slot release: id 3 | task 7621 | stop processing: n_tokens = 1307, truncated = 0 7.13.914.895 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.853 7.13.914.920 I slot launch_slot_: id 3 | task 7742 | processing task, is_child = 0 7.15.224.677 I slot print_timing: id 2 | task 7265 | n_gen = 492, tg = 21.74 t/s, tg_3s = 19.27 t/s 7.16.883.534 I slot print_timing: id 1 | task 7034 | n_gen = 758, tg = 21.63 t/s, tg_3s = 20.89 t/s 7.17.949.438 I slot print_timing: id 0 | task 7727 | n_gen = 100, tg = 21.84 t/s, tg_3s = 22.06 t/s 7.18.251.312 I slot print_timing: id 2 | task 7265 | n_gen = 563, tg = 21.94 t/s, tg_3s = 23.46 t/s 7.18.551.071 I slot print_timing: id 3 | task 7742 | n_gen = 100, tg = 23.52 t/s, tg_3s = 23.76 t/s 7.19.396.109 I slot print_timing: id 0 | task 7727 | prompt eval time = 309.78 ms / 83 tokens ( 3.73 ms per token, 267.94 tokens per second) 7.19.396.115 I slot print_timing: id 0 | task 7727 | eval time = 5979.55 ms / 134 tokens ( 44.96 ms per token, 22.24 tokens per second) 7.19.396.116 I slot print_timing: id 0 | task 7727 | total time = 6289.33 ms / 217 tokens 7.19.396.116 I slot print_timing: id 0 | task 7727 | graphs reused = 6859 7.19.396.117 I slot print_timing: id 0 | task 7727 | graph reallocs = 0 / 0 (same size) / (changed size) 7.19.396.173 I slot release: id 0 | task 7727 | stop processing: n_tokens = 1331, truncated = 0 7.19.441.487 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.838 7.19.441.510 I slot launch_slot_: id 0 | task 7865 | processing task, is_child = 0 7.19.914.343 I slot print_timing: id 1 | task 7034 | n_gen = 824, tg = 21.64 t/s, tg_3s = 21.78 t/s 7.21.283.101 I slot print_timing: id 2 | task 7265 | n_gen = 629, tg = 21.92 t/s, tg_3s = 21.77 t/s 7.21.586.286 I slot print_timing: id 3 | task 7742 | n_gen = 166, tg = 22.78 t/s, tg_3s = 21.74 t/s 7.22.949.091 I slot print_timing: id 1 | task 7034 | n_gen = 895, tg = 21.77 t/s, tg_3s = 23.40 t/s 7.23.975.524 I slot print_timing: id 0 | task 7865 | n_gen = 100, tg = 23.44 t/s, tg_3s = 23.68 t/s 7.24.321.220 I slot print_timing: id 2 | task 7265 | n_gen = 700, tg = 22.06 t/s, tg_3s = 23.37 t/s 7.24.622.186 I slot print_timing: id 3 | task 7742 | n_gen = 237, tg = 22.96 t/s, tg_3s = 23.39 t/s 7.25.987.875 I slot print_timing: id 1 | task 7034 | n_gen = 966, tg = 21.88 t/s, tg_3s = 23.36 t/s 7.26.633.200 I slot print_timing: id 3 | task 7742 | prompt eval time = 427.46 ms / 142 tokens ( 3.01 ms per token, 332.19 tokens per second) 7.26.633.207 I slot print_timing: id 3 | task 7742 | eval time = 12290.81 ms / 284 tokens ( 43.43 ms per token, 23.03 tokens per second) 7.26.633.208 I slot print_timing: id 3 | task 7742 | total time = 12718.27 ms / 426 tokens 7.26.633.209 I slot print_timing: id 3 | task 7742 | graphs reused = 7019 7.26.633.209 I slot print_timing: id 3 | task 7742 | graph reallocs = 0 / 0 (same size) / (changed size) 7.26.633.289 I slot release: id 3 | task 7742 | stop processing: n_tokens = 1540, truncated = 0 7.26.674.072 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.724 7.26.674.093 I slot launch_slot_: id 3 | task 8030 | processing task, is_child = 0 7.26.965.696 I slot print_timing: id 0 | task 7865 | prompt eval time = 310.39 ms / 86 tokens ( 3.61 ms per token, 277.07 tokens per second) 7.26.965.702 I slot print_timing: id 0 | task 7865 | eval time = 7213.78 ms / 164 tokens ( 44.26 ms per token, 22.60 tokens per second) 7.26.965.702 I slot print_timing: id 0 | task 7865 | total time = 7524.17 ms / 250 tokens 7.26.965.703 I slot print_timing: id 0 | task 7865 | graphs reused = 7019 7.26.965.703 I slot print_timing: id 0 | task 7865 | graph reallocs = 0 / 0 (same size) / (changed size) 7.26.965.775 I slot release: id 0 | task 7865 | stop processing: n_tokens = 1364, truncated = 0 7.27.041.340 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.817 7.27.041.358 I slot launch_slot_: id 0 | task 8033 | processing task, is_child = 0 7.27.351.573 I slot print_timing: id 2 | task 7265 | n_gen = 759, tg = 21.84 t/s, tg_3s = 19.47 t/s 7.28.965.394 I slot print_timing: id 1 | task 7034 | prompt eval time = 368.64 ms / 82 tokens ( 4.50 ms per token, 222.44 tokens per second) 7.28.965.401 I slot print_timing: id 1 | task 7034 | eval time = 47083.15 ms / 1024 tokens ( 46.02 ms per token, 21.73 tokens per second) 7.28.965.402 I slot print_timing: id 1 | task 7034 | total time = 47451.80 ms / 1106 tokens 7.28.965.402 I slot print_timing: id 1 | task 7034 | graphs reused = 7056 7.28.965.403 I slot print_timing: id 1 | task 7034 | graph reallocs = 0 / 0 (same size) / (changed size) 7.28.965.471 I slot release: id 1 | task 7034 | stop processing: n_tokens = 2220, truncated = 0 7.29.030.106 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.502 7.29.030.131 I slot launch_slot_: id 1 | task 8075 | processing task, is_child = 0 7.30.385.969 I slot print_timing: id 2 | task 7265 | n_gen = 822, tg = 21.75 t/s, tg_3s = 20.76 t/s 7.30.681.635 I slot print_timing: id 0 | task 8033 | prompt eval time = 308.10 ms / 71 tokens ( 4.34 ms per token, 230.45 tokens per second) 7.30.681.642 I slot print_timing: id 0 | task 8033 | eval time = 3332.17 ms / 71 tokens ( 47.60 ms per token, 21.01 tokens per second) 7.30.681.642 I slot print_timing: id 0 | task 8033 | total time = 3640.27 ms / 142 tokens 7.30.681.643 I slot print_timing: id 0 | task 8033 | graphs reused = 7084 7.30.681.643 I slot print_timing: id 0 | task 8033 | graph reallocs = 0 / 0 (same size) / (changed size) 7.30.681.699 I slot release: id 0 | task 8033 | stop processing: n_tokens = 1256, truncated = 0 7.30.726.833 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.889 7.30.726.857 I slot launch_slot_: id 0 | task 8108 | processing task, is_child = 0 7.32.053.246 I slot print_timing: id 3 | task 8030 | n_gen = 100, tg = 19.75 t/s, tg_3s = 19.95 t/s 7.33.423.397 I slot print_timing: id 2 | task 7265 | n_gen = 888, tg = 21.75 t/s, tg_3s = 21.73 t/s 7.33.893.376 I slot print_timing: id 1 | task 8075 | n_gen = 100, tg = 22.33 t/s, tg_3s = 22.56 t/s 7.33.982.472 I slot print_timing: id 3 | task 8030 | prompt eval time = 367.24 ms / 103 tokens ( 3.57 ms per token, 280.47 tokens per second) 7.33.982.480 I slot print_timing: id 3 | task 8030 | eval time = 6941.13 ms / 145 tokens ( 48.20 ms per token, 20.75 tokens per second) 7.33.982.481 I slot print_timing: id 3 | task 8030 | total time = 7308.37 ms / 248 tokens 7.33.982.482 I slot print_timing: id 3 | task 8030 | graphs reused = 7152 7.33.982.482 I slot print_timing: id 3 | task 8030 | graph reallocs = 0 / 0 (same size) / (changed size) 7.33.982.566 I slot release: id 3 | task 8030 | stop processing: n_tokens = 1362, truncated = 0 7.34.375.560 I slot print_timing: id 0 | task 8108 | prompt eval time = 306.39 ms / 70 tokens ( 4.38 ms per token, 228.46 tokens per second) 7.34.375.564 I slot print_timing: id 0 | task 8108 | eval time = 3342.30 ms / 80 tokens ( 42.31 ms per token, 23.64 tokens per second) 7.34.375.565 I slot print_timing: id 0 | task 8108 | total time = 3648.69 ms / 150 tokens 7.34.375.566 I slot print_timing: id 0 | task 8108 | graphs reused = 7161 7.34.375.567 I slot print_timing: id 0 | task 8108 | graph reallocs = 0 / 0 (same size) / (changed size) 7.34.375.623 I slot release: id 0 | task 8108 | stop processing: n_tokens = 1265, truncated = 0 7.36.438.259 I slot print_timing: id 2 | task 7265 | n_gen = 967, tg = 22.06 t/s, tg_3s = 26.20 t/s 7.36.914.586 I slot print_timing: id 1 | task 8075 | n_gen = 181, tg = 24.15 t/s, tg_3s = 26.81 t/s 7.38.534.231 I slot print_timing: id 2 | task 7265 | prompt eval time = 352.44 ms / 85 tokens ( 4.15 ms per token, 241.18 tokens per second) 7.38.534.238 I slot print_timing: id 2 | task 7265 | eval time = 45895.10 ms / 1024 tokens ( 44.86 ms per token, 22.29 tokens per second) 7.38.534.239 I slot print_timing: id 2 | task 7265 | total time = 46247.53 ms / 1109 tokens 7.38.534.239 I slot print_timing: id 2 | task 7265 | graphs reused = 7273 7.38.534.240 I slot print_timing: id 2 | task 7265 | graph reallocs = 0 / 0 (same size) / (changed size) 7.38.534.296 I slot release: id 2 | task 7265 | stop processing: n_tokens = 2223, truncated = 0 7.38.582.898 I slot print_timing: id 1 | task 8075 | prompt eval time = 429.67 ms / 118 tokens ( 3.64 ms per token, 274.63 tokens per second) 7.38.582.901 I slot print_timing: id 1 | task 8075 | eval time = 9123.09 ms / 227 tokens ( 40.37 ms per token, 24.77 tokens per second) 7.38.582.902 I slot print_timing: id 1 | task 8075 | total time = 9552.76 ms / 345 tokens 7.38.582.902 I slot print_timing: id 1 | task 8075 | graphs reused = 7274 7.38.582.903 I slot print_timing: id 1 | task 8075 | graph reallocs = 0 / 0 (same size) / (changed size) 7.38.582.944 I slot release: id 1 | task 8075 | stop processing: n_tokens = 1458, truncated = 0 7.38.601.533 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1362, t_last = 331400978408 7.38.601.711 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.614 MiB) 7.38.623.909 I slot launch_slot_: id 3 | task 8305 | processing task, is_child = 0 7.38.624.021 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.490 MiB) 7.38.624.025 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.383 MiB) 7.38.624.028 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.461 MiB) 7.38.624.030 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.368 MiB) 7.38.624.032 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 30.030 MiB) 7.38.624.034 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 51.690 MiB) 7.38.624.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.490 MiB) 7.38.624.039 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.922 MiB) 7.38.624.045 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.290 MiB) 7.38.624.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.029 MiB) 7.38.624.049 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 7.38.653.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 7.38.653.958 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.321 MiB) 7.38.653.960 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.798 MiB) 7.38.653.963 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.783 MiB) 7.38.653.965 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.044 MiB) 7.38.653.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.953 MiB) 7.38.653.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.614 MiB) 7.38.653.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.368 MiB) 7.38.653.973 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 7.38.693.920 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.215 MiB) 7.38.693.925 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 47.013 MiB) 7.38.693.927 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.735 MiB) 7.38.693.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.736 MiB) 7.38.694.176 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.907 MiB) 7.38.694.388 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.629 MiB) 7.38.694.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.814 MiB) 7.38.694.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.829 MiB) 7.38.695.311 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.304 MiB) 7.38.728.212 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1265, t_last = 331401371465 7.38.729.983 I slot launch_slot_: id 0 | task 8306 | processing task, is_child = 0 7.38.730.202 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2223, t_last = 331405530138 7.38.731.777 I slot launch_slot_: id 2 | task 8307 | processing task, is_child = 0 7.38.731.867 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1458, t_last = 331405578786 7.38.733.365 I slot launch_slot_: id 1 | task 8308 | processing task, is_child = 0 7.44.347.073 I slot print_timing: id 0 | task 8306 | prompt processing, n_tokens = 616, progress = 0.79, t = 5.61 s / 109.73 tokens per second 7.44.381.510 I slot print_timing: id 1 | task 8308 | prompt processing, n_tokens = 842, progress = 0.88, t = 5.61 s / 150.00 tokens per second 7.44.385.185 I slot print_timing: id 2 | task 8307 | prompt processing, n_tokens = 865, progress = 0.89, t = 5.61 s / 154.10 tokens per second 7.44.387.388 I slot print_timing: id 3 | task 8305 | prompt processing, n_tokens = 642, progress = 0.84, t = 5.61 s / 114.38 tokens per second 7.45.416.678 I slot print_timing: id 0 | task 8306 | prompt processing, n_tokens = 774, progress = 0.99, t = 6.68 s / 115.81 tokens per second 7.45.470.716 I slot print_timing: id 1 | task 8308 | prompt processing, n_tokens = 955, progress = 1.00, t = 6.68 s / 142.90 tokens per second 7.45.473.699 I slot print_timing: id 2 | task 8307 | prompt processing, n_tokens = 972, progress = 1.00, t = 6.68 s / 145.45 tokens per second 7.45.475.686 I slot print_timing: id 3 | task 8305 | prompt processing, n_tokens = 762, progress = 0.99, t = 6.68 s / 114.03 tokens per second 7.45.581.845 I slot print_timing: id 0 | task 8306 | prompt eval time = 6807.61 ms / 778 tokens ( 8.75 ms per token, 114.28 tokens per second) 7.45.581.850 I slot print_timing: id 0 | task 8306 | eval time = 40.86 ms / 2 tokens ( 40.86 ms per token, 24.47 tokens per second) 7.45.581.851 I slot print_timing: id 0 | task 8306 | total time = 6848.47 ms / 780 tokens 7.45.581.851 I slot print_timing: id 0 | task 8306 | graphs reused = 7275 7.45.581.852 I slot print_timing: id 0 | task 8306 | graph reallocs = 0 / 0 (same size) / (changed size) 7.45.581.892 I slot release: id 0 | task 8306 | stop processing: n_tokens = 788, truncated = 0 7.45.583.000 I slot print_timing: id 1 | task 8308 | prompt eval time = 6808.55 ms / 959 tokens ( 7.10 ms per token, 140.85 tokens per second) 7.45.583.001 I slot print_timing: id 1 | task 8308 | eval time = 40.84 ms / 2 tokens ( 40.84 ms per token, 24.48 tokens per second) 7.45.583.002 I slot print_timing: id 1 | task 8308 | total time = 6849.40 ms / 961 tokens 7.45.583.002 I slot print_timing: id 1 | task 8308 | graphs reused = 7275 7.45.583.002 I slot print_timing: id 1 | task 8308 | graph reallocs = 0 / 0 (same size) / (changed size) 7.45.583.037 I slot release: id 1 | task 8308 | stop processing: n_tokens = 969, truncated = 0 7.45.584.133 I slot print_timing: id 2 | task 8307 | prompt eval time = 6809.44 ms / 976 tokens ( 6.98 ms per token, 143.33 tokens per second) 7.45.584.136 I slot print_timing: id 2 | task 8307 | eval time = 40.91 ms / 2 tokens ( 40.91 ms per token, 24.45 tokens per second) 7.45.584.136 I slot print_timing: id 2 | task 8307 | total time = 6850.35 ms / 978 tokens 7.45.584.136 I slot print_timing: id 2 | task 8307 | graphs reused = 7275 7.45.584.137 I slot print_timing: id 2 | task 8307 | graph reallocs = 0 / 0 (same size) / (changed size) 7.45.584.168 I slot release: id 2 | task 8307 | stop processing: n_tokens = 986, truncated = 0 7.45.585.265 I slot print_timing: id 3 | task 8305 | prompt eval time = 6810.29 ms / 766 tokens ( 8.89 ms per token, 112.48 tokens per second) 7.45.585.267 I slot print_timing: id 3 | task 8305 | eval time = 40.95 ms / 2 tokens ( 40.95 ms per token, 24.42 tokens per second) 7.45.585.267 I slot print_timing: id 3 | task 8305 | total time = 6851.25 ms / 768 tokens 7.45.585.267 I slot print_timing: id 3 | task 8305 | graphs reused = 7275 7.45.585.268 I slot print_timing: id 3 | task 8305 | graph reallocs = 0 / 0 (same size) / (changed size) 7.45.585.293 I slot release: id 3 | task 8305 | stop processing: n_tokens = 776, truncated = 0 7.45.589.934 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 788, t_last = 331412577734 7.45.590.006 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.951 MiB) 7.45.590.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 47.013 MiB) 7.45.599.586 I slot launch_slot_: id 0 | task 8314 | processing task, is_child = 0 7.45.599.669 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 38.399 MiB) 7.45.599.673 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.814 MiB) 7.45.599.676 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.660 MiB) 7.45.599.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.907 MiB) 7.45.599.679 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.430 MiB) 7.45.599.681 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.982 MiB) 7.45.610.166 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.982 MiB) 7.45.610.173 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 47.752 MiB) 7.45.610.310 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 32.738 MiB) 7.45.610.598 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.848 MiB) 7.45.610.874 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.848 MiB) 7.45.611.118 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 7.45.626.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.184 MiB) 7.45.626.841 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.184 MiB) 7.45.627.102 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.784 MiB) 7.45.627.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.321 MiB) 7.45.627.588 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 7.45.627.803 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.568 MiB) 7.45.642.239 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 969, t_last = 331412578879 7.45.642.402 I slot launch_slot_: id 1 | task 8315 | processing task, is_child = 0 7.45.642.533 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 331412580010 7.45.642.640 I slot launch_slot_: id 2 | task 8316 | processing task, is_child = 0 7.45.642.703 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 776, t_last = 331412581135 7.45.642.803 I slot launch_slot_: id 3 | task 8317 | processing task, is_child = 0 7.50.733.680 I slot print_timing: id 0 | task 8314 | prompt processing, n_tokens = 690, progress = 0.87, t = 5.09 s / 135.54 tokens per second 7.50.764.185 I slot print_timing: id 1 | task 8315 | prompt processing, n_tokens = 690, progress = 0.87, t = 5.09 s / 135.55 tokens per second 7.50.766.753 I slot print_timing: id 2 | task 8316 | prompt processing, n_tokens = 690, progress = 0.82, t = 5.09 s / 135.56 tokens per second 7.50.768.760 I slot print_timing: id 3 | task 8317 | prompt processing, n_tokens = 690, progress = 0.81, t = 5.09 s / 135.58 tokens per second 7.51.775.128 I slot print_timing: id 0 | task 8314 | prompt processing, n_tokens = 792, progress = 1.00, t = 6.13 s / 129.15 tokens per second 7.51.812.186 I slot print_timing: id 1 | task 8315 | prompt processing, n_tokens = 794, progress = 1.00, t = 6.13 s / 129.49 tokens per second 7.51.814.351 I slot print_timing: id 2 | task 8316 | prompt processing, n_tokens = 837, progress = 1.00, t = 6.13 s / 136.51 tokens per second 7.51.816.381 I slot print_timing: id 3 | task 8317 | prompt processing, n_tokens = 845, progress = 1.00, t = 6.13 s / 137.83 tokens per second 7.51.921.914 I slot print_timing: id 0 | task 8314 | prompt eval time = 6238.64 ms / 796 tokens ( 7.84 ms per token, 127.59 tokens per second) 7.51.921.919 I slot print_timing: id 0 | task 8314 | eval time = 40.46 ms / 2 tokens ( 40.46 ms per token, 24.72 tokens per second) 7.51.921.919 I slot print_timing: id 0 | task 8314 | total time = 6279.10 ms / 798 tokens 7.51.921.920 I slot print_timing: id 0 | task 8314 | graphs reused = 7275 7.51.921.920 I slot print_timing: id 0 | task 8314 | graph reallocs = 0 / 0 (same size) / (changed size) 7.51.921.958 I slot release: id 0 | task 8314 | stop processing: n_tokens = 806, truncated = 0 7.51.923.085 I slot print_timing: id 1 | task 8315 | prompt eval time = 6239.36 ms / 798 tokens ( 7.82 ms per token, 127.90 tokens per second) 7.51.923.087 I slot print_timing: id 1 | task 8315 | eval time = 40.51 ms / 2 tokens ( 40.51 ms per token, 24.69 tokens per second) 7.51.923.087 I slot print_timing: id 1 | task 8315 | total time = 6279.87 ms / 800 tokens 7.51.923.088 I slot print_timing: id 1 | task 8315 | graphs reused = 7275 7.51.923.088 I slot print_timing: id 1 | task 8315 | graph reallocs = 0 / 0 (same size) / (changed size) 7.51.923.113 I slot release: id 1 | task 8315 | stop processing: n_tokens = 808, truncated = 0 7.51.924.220 I slot print_timing: id 2 | task 8316 | prompt eval time = 6239.90 ms / 841 tokens ( 7.42 ms per token, 134.78 tokens per second) 7.51.924.223 I slot print_timing: id 2 | task 8316 | eval time = 40.56 ms / 2 tokens ( 40.56 ms per token, 24.66 tokens per second) 7.51.924.223 I slot print_timing: id 2 | task 8316 | total time = 6280.45 ms / 843 tokens 7.51.924.223 I slot print_timing: id 2 | task 8316 | graphs reused = 7275 7.51.924.224 I slot print_timing: id 2 | task 8316 | graph reallocs = 0 / 0 (same size) / (changed size) 7.51.924.250 I slot release: id 2 | task 8316 | stop processing: n_tokens = 851, truncated = 0 7.51.925.351 I slot print_timing: id 3 | task 8317 | prompt eval time = 6240.37 ms / 849 tokens ( 7.35 ms per token, 136.05 tokens per second) 7.51.925.353 I slot print_timing: id 3 | task 8317 | eval time = 40.63 ms / 2 tokens ( 40.63 ms per token, 24.61 tokens per second) 7.51.925.354 I slot print_timing: id 3 | task 8317 | total time = 6281.00 ms / 851 tokens 7.51.925.354 I slot print_timing: id 3 | task 8317 | graphs reused = 7275 7.51.925.354 I slot print_timing: id 3 | task 8317 | graph reallocs = 0 / 0 (same size) / (changed size) 7.51.925.375 I slot release: id 3 | task 8317 | stop processing: n_tokens = 859, truncated = 0 7.51.930.314 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.874 (> 0.100 thold), f_keep = 0.901 7.51.930.363 I slot launch_slot_: id 0 | task 8323 | processing task, is_child = 0 7.51.930.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.521 MiB) 7.51.930.444 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.894 MiB) 7.51.930.446 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 7.51.930.449 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.507 MiB) 7.51.930.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.507 MiB) 7.51.930.453 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.999 MiB) 7.51.947.831 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.091 MiB) 7.51.948.103 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.922 MiB) 7.51.948.378 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 7.51.948.636 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.783 MiB) 7.51.948.938 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.075 MiB) 7.51.949.156 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.184 MiB) 7.51.966.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.015 MiB) 7.51.966.717 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.213 MiB) 7.51.966.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.091 MiB) 7.51.967.209 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.368 MiB) 7.51.967.445 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 32.738 MiB) 7.51.967.651 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.075 MiB) 7.51.984.454 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 808, t_last = 331418918955 7.51.984.601 I slot launch_slot_: id 1 | task 8324 | processing task, is_child = 0 7.51.984.729 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 851, t_last = 331418920092 7.51.984.832 I slot launch_slot_: id 2 | task 8325 | processing task, is_child = 0 7.51.984.898 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 859, t_last = 331418921217 7.51.984.997 I slot launch_slot_: id 3 | task 8326 | processing task, is_child = 0 7.56.615.004 I slot print_timing: id 1 | task 8324 | prompt processing, n_tokens = 739, progress = 0.84, t = 4.63 s / 159.71 tokens per second 7.56.618.315 I slot print_timing: id 2 | task 8325 | prompt processing, n_tokens = 739, progress = 0.85, t = 4.63 s / 159.73 tokens per second 7.56.620.028 I slot print_timing: id 3 | task 8326 | prompt processing, n_tokens = 817, progress = 0.86, t = 4.63 s / 176.61 tokens per second 7.57.451.331 I slot print_timing: id 0 | task 8323 | prompt eval time = 4629.98 ms / 105 tokens ( 44.10 ms per token, 22.68 tokens per second) 7.57.451.334 I slot print_timing: id 0 | task 8323 | eval time = 836.33 ms / 2 tokens ( 836.33 ms per token, 1.20 tokens per second) 7.57.451.334 I slot print_timing: id 0 | task 8323 | total time = 5466.32 ms / 107 tokens 7.57.451.335 I slot print_timing: id 0 | task 8323 | graphs reused = 7275 7.57.451.335 I slot print_timing: id 0 | task 8323 | graph reallocs = 0 / 0 (same size) / (changed size) 7.57.451.391 I slot release: id 0 | task 8323 | stop processing: n_tokens = 832, truncated = 0 7.57.451.411 I slot print_timing: id 1 | task 8324 | prompt processing, n_tokens = 874, progress = 1.00, t = 5.46 s / 159.97 tokens per second 7.57.455.133 I slot print_timing: id 2 | task 8325 | prompt processing, n_tokens = 864, progress = 1.00, t = 5.46 s / 158.16 tokens per second 7.57.459.892 I slot print_timing: id 3 | task 8326 | prompt processing, n_tokens = 945, progress = 1.00, t = 5.46 s / 173.00 tokens per second 7.57.525.114 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 832, t_last = 331424447233 7.57.525.198 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.660 MiB) 7.57.525.201 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.414 MiB) 7.57.525.204 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 7.57.525.206 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.461 MiB) 7.57.525.208 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.075 MiB) 7.57.525.461 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.306 MiB) 7.57.525.699 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 7.57.545.645 I slot launch_slot_: id 0 | task 8331 | processing task, is_child = 0 7.58.427.540 I slot print_timing: id 1 | task 8324 | prompt eval time = 5536.09 ms / 878 tokens ( 6.31 ms per token, 158.60 tokens per second) 7.58.427.544 I slot print_timing: id 1 | task 8324 | eval time = 904.58 ms / 2 tokens ( 904.58 ms per token, 1.11 tokens per second) 7.58.427.545 I slot print_timing: id 1 | task 8324 | total time = 6440.67 ms / 880 tokens 7.58.427.545 I slot print_timing: id 1 | task 8324 | graphs reused = 7275 7.58.427.546 I slot print_timing: id 1 | task 8324 | graph reallocs = 0 / 0 (same size) / (changed size) 7.58.427.611 I slot release: id 1 | task 8324 | stop processing: n_tokens = 888, truncated = 0 7.58.428.762 I slot print_timing: id 2 | task 8325 | prompt eval time = 5536.73 ms / 868 tokens ( 6.38 ms per token, 156.77 tokens per second) 7.58.428.765 I slot print_timing: id 2 | task 8325 | eval time = 904.70 ms / 2 tokens ( 904.70 ms per token, 1.11 tokens per second) 7.58.428.765 I slot print_timing: id 2 | task 8325 | total time = 6441.44 ms / 870 tokens 7.58.428.765 I slot print_timing: id 2 | task 8325 | graphs reused = 7275 7.58.428.766 I slot print_timing: id 2 | task 8325 | graph reallocs = 0 / 0 (same size) / (changed size) 7.58.428.797 I slot release: id 2 | task 8325 | stop processing: n_tokens = 878, truncated = 0 7.58.429.948 I slot print_timing: id 3 | task 8326 | prompt eval time = 5537.23 ms / 949 tokens ( 5.83 ms per token, 171.39 tokens per second) 7.58.429.950 I slot print_timing: id 3 | task 8326 | eval time = 904.84 ms / 2 tokens ( 904.84 ms per token, 1.11 tokens per second) 7.58.429.951 I slot print_timing: id 3 | task 8326 | total time = 6442.06 ms / 951 tokens 7.58.429.951 I slot print_timing: id 3 | task 8326 | graphs reused = 7275 7.58.429.951 I slot print_timing: id 3 | task 8326 | graph reallocs = 0 / 0 (same size) / (changed size) 7.58.429.993 I slot release: id 3 | task 8326 | stop processing: n_tokens = 959, truncated = 0 7.59.202.647 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 888, t_last = 331425423453 7.59.202.747 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.845 MiB) 7.59.202.753 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.829 MiB) 7.59.203.144 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 32.738 MiB) 7.59.203.382 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.213 MiB) 7.59.203.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.292 MiB) 7.59.203.887 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.753 MiB) 7.59.457.678 I slot launch_slot_: id 1 | task 8335 | processing task, is_child = 0 7.59.457.760 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 7.59.457.952 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.798 MiB) 7.59.458.196 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.629 MiB) 7.59.458.422 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 38.153 MiB) 7.59.458.674 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 35.199 MiB) 7.59.458.887 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.461 MiB) 7.59.475.839 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 38.891 MiB) 7.59.476.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.521 MiB) 7.59.476.295 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.568 MiB) 7.59.476.512 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 33.969 MiB) 7.59.476.753 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.705 MiB) 7.59.477.024 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.784 MiB) 7.59.494.723 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 878, t_last = 331425424639 7.59.494.867 I slot launch_slot_: id 2 | task 8336 | processing task, is_child = 0 7.59.494.935 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 959, t_last = 331425425835 7.59.495.036 I slot launch_slot_: id 3 | task 8337 | processing task, is_child = 0 8.02.612.571 I slot print_timing: id 1 | task 8335 | prompt processing, n_tokens = 507, progress = 0.50, t = 3.11 s / 162.91 tokens per second 8.02.616.309 I slot print_timing: id 2 | task 8336 | prompt processing, n_tokens = 402, progress = 0.44, t = 3.11 s / 129.20 tokens per second 8.02.617.922 I slot print_timing: id 3 | task 8337 | prompt processing, n_tokens = 747, progress = 0.42, t = 3.11 s / 240.12 tokens per second 8.05.113.483 I slot print_timing: id 0 | task 8331 | prompt eval time = 5066.88 ms / 988 tokens ( 5.13 ms per token, 194.99 tokens per second) 8.05.113.485 I slot print_timing: id 0 | task 8331 | eval time = 2500.94 ms / 2 tokens ( 2500.94 ms per token, 0.40 tokens per second) 8.05.113.486 I slot print_timing: id 0 | task 8331 | total time = 7567.82 ms / 990 tokens 8.05.113.487 I slot print_timing: id 0 | task 8331 | graphs reused = 7275 8.05.113.487 I slot print_timing: id 0 | task 8331 | graph reallocs = 0 / 0 (same size) / (changed size) 8.05.113.538 I slot release: id 0 | task 8331 | stop processing: n_tokens = 998, truncated = 0 8.05.113.571 I slot print_timing: id 1 | task 8335 | prompt processing, n_tokens = 871, progress = 0.85, t = 5.61 s / 155.17 tokens per second 8.05.117.314 I slot print_timing: id 2 | task 8336 | prompt processing, n_tokens = 747, progress = 0.82, t = 5.61 s / 133.10 tokens per second 8.05.119.247 I slot print_timing: id 3 | task 8337 | prompt processing, n_tokens = 1294, progress = 0.72, t = 5.61 s / 230.58 tokens per second 8.06.114.060 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 998, t_last = 331432109380 8.06.114.158 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.814 MiB) 8.06.114.163 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.953 MiB) 8.06.114.165 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.876 MiB) 8.06.114.167 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.414 MiB) 8.06.114.443 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 351.341 MiB) 8.06.784.739 I slot launch_slot_: id 0 | task 8341 | processing task, is_child = 0 8.06.785.022 I slot print_timing: id 1 | task 8335 | prompt processing, n_tokens = 1019, progress = 1.00, t = 6.61 s / 154.05 tokens per second 8.06.787.336 I slot print_timing: id 2 | task 8336 | prompt processing, n_tokens = 914, progress = 1.00, t = 6.61 s / 138.19 tokens per second 8.06.789.123 I slot print_timing: id 3 | task 8337 | prompt processing, n_tokens = 1806, progress = 1.00, t = 6.61 s / 273.08 tokens per second 8.08.273.797 I slot print_timing: id 1 | task 8335 | prompt eval time = 8088.46 ms / 1023 tokens ( 7.91 ms per token, 126.48 tokens per second) 8.08.273.799 I slot print_timing: id 1 | task 8335 | eval time = 685.97 ms / 2 tokens ( 685.97 ms per token, 1.46 tokens per second) 8.08.273.800 I slot print_timing: id 1 | task 8335 | total time = 8774.43 ms / 1025 tokens 8.08.273.800 I slot print_timing: id 1 | task 8335 | graphs reused = 7275 8.08.273.800 I slot print_timing: id 1 | task 8335 | graph reallocs = 0 / 0 (same size) / (changed size) 8.08.273.870 I slot release: id 1 | task 8335 | stop processing: n_tokens = 1033, truncated = 0 8.08.275.038 I slot print_timing: id 2 | task 8336 | prompt eval time = 8089.11 ms / 918 tokens ( 8.81 ms per token, 113.49 tokens per second) 8.08.275.040 I slot print_timing: id 2 | task 8336 | eval time = 686.02 ms / 2 tokens ( 686.02 ms per token, 1.46 tokens per second) 8.08.275.041 I slot print_timing: id 2 | task 8336 | total time = 8775.13 ms / 920 tokens 8.08.275.041 I slot print_timing: id 2 | task 8336 | graphs reused = 7275 8.08.275.042 I slot print_timing: id 2 | task 8336 | graph reallocs = 0 / 0 (same size) / (changed size) 8.08.275.101 I slot release: id 2 | task 8336 | stop processing: n_tokens = 928, truncated = 0 8.08.276.257 I slot print_timing: id 3 | task 8337 | prompt eval time = 8089.69 ms / 1810 tokens ( 4.47 ms per token, 223.74 tokens per second) 8.08.276.261 I slot print_timing: id 3 | task 8337 | eval time = 686.06 ms / 2 tokens ( 686.06 ms per token, 1.46 tokens per second) 8.08.276.261 I slot print_timing: id 3 | task 8337 | total time = 8775.75 ms / 1812 tokens 8.08.276.262 I slot print_timing: id 3 | task 8337 | graphs reused = 7275 8.08.276.262 I slot print_timing: id 3 | task 8337 | graph reallocs = 0 / 0 (same size) / (changed size) 8.08.276.344 I slot release: id 3 | task 8337 | stop processing: n_tokens = 1820, truncated = 0 8.08.693.650 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1033, t_last = 331435269712 8.08.710.464 I slot launch_slot_: id 1 | task 8346 | processing task, is_child = 0 8.08.710.545 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.088 MiB) 8.08.716.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 405.031 MiB) 8.08.723.607 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 331435270944 8.08.723.737 I slot launch_slot_: id 2 | task 8347 | processing task, is_child = 0 8.08.723.835 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1820, t_last = 331435272188 8.08.723.965 I slot launch_slot_: id 3 | task 8348 | processing task, is_child = 0 8.10.214.934 I slot print_timing: id 0 | task 8341 | prompt eval time = 1908.88 ms / 934 tokens ( 2.04 ms per token, 489.29 tokens per second) 8.10.214.937 I slot print_timing: id 0 | task 8341 | eval time = 1521.28 ms / 2 tokens ( 1521.28 ms per token, 0.66 tokens per second) 8.10.214.938 I slot print_timing: id 0 | task 8341 | total time = 3430.17 ms / 936 tokens 8.10.214.938 I slot print_timing: id 0 | task 8341 | graphs reused = 7275 8.10.214.939 I slot print_timing: id 0 | task 8341 | graph reallocs = 0 / 0 (same size) / (changed size) 8.10.215.016 I slot release: id 0 | task 8341 | stop processing: n_tokens = 944, truncated = 0 8.12.408.056 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 944, t_last = 331437210859 8.12.408.158 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 351.728 MiB) 8.12.495.277 I slot launch_slot_: id 0 | task 8351 | processing task, is_child = 0 8.12.495.490 I slot print_timing: id 1 | task 8346 | prompt processing, n_tokens = 590, progress = 0.84, t = 3.68 s / 160.15 tokens per second 8.12.497.390 I slot print_timing: id 2 | task 8347 | prompt processing, n_tokens = 590, progress = 0.81, t = 3.68 s / 160.16 tokens per second 8.12.499.051 I slot print_timing: id 3 | task 8348 | prompt processing, n_tokens = 759, progress = 0.87, t = 3.68 s / 206.05 tokens per second 8.13.627.922 I slot print_timing: id 1 | task 8346 | prompt processing, n_tokens = 696, progress = 0.99, t = 4.82 s / 144.44 tokens per second 8.13.632.128 I slot print_timing: id 2 | task 8347 | prompt processing, n_tokens = 724, progress = 0.99, t = 4.82 s / 150.26 tokens per second 8.13.634.115 I slot print_timing: id 3 | task 8348 | prompt processing, n_tokens = 868, progress = 1.00, t = 4.82 s / 180.15 tokens per second 8.14.737.600 I slot print_timing: id 1 | task 8346 | prompt eval time = 5721.85 ms / 700 tokens ( 8.17 ms per token, 122.34 tokens per second) 8.14.737.606 I slot print_timing: id 1 | task 8346 | eval time = 291.77 ms / 2 tokens ( 291.77 ms per token, 3.43 tokens per second) 8.14.737.606 I slot print_timing: id 1 | task 8346 | total time = 6013.62 ms / 702 tokens 8.14.737.607 I slot print_timing: id 1 | task 8346 | graphs reused = 7276 8.14.737.607 I slot print_timing: id 1 | task 8346 | graph reallocs = 0 / 0 (same size) / (changed size) 8.14.737.670 I slot release: id 1 | task 8346 | stop processing: n_tokens = 710, truncated = 0 8.14.738.804 I slot print_timing: id 2 | task 8347 | prompt eval time = 5722.81 ms / 728 tokens ( 7.86 ms per token, 127.21 tokens per second) 8.14.738.810 I slot print_timing: id 2 | task 8347 | eval time = 291.81 ms / 2 tokens ( 291.81 ms per token, 3.43 tokens per second) 8.14.738.811 I slot print_timing: id 2 | task 8347 | total time = 6014.63 ms / 730 tokens 8.14.738.811 I slot print_timing: id 2 | task 8347 | graphs reused = 7276 8.14.738.812 I slot print_timing: id 2 | task 8347 | graph reallocs = 0 / 0 (same size) / (changed size) 8.14.738.845 I slot release: id 2 | task 8347 | stop processing: n_tokens = 738, truncated = 0 8.14.740.009 I slot print_timing: id 3 | task 8348 | prompt eval time = 5723.70 ms / 872 tokens ( 6.56 ms per token, 152.35 tokens per second) 8.14.740.011 I slot print_timing: id 3 | task 8348 | eval time = 291.83 ms / 2 tokens ( 291.83 ms per token, 3.43 tokens per second) 8.14.740.012 I slot print_timing: id 3 | task 8348 | total time = 6015.53 ms / 874 tokens 8.14.740.012 I slot print_timing: id 3 | task 8348 | graphs reused = 7276 8.14.740.012 I slot print_timing: id 3 | task 8348 | graph reallocs = 0 / 0 (same size) / (changed size) 8.14.740.058 I slot release: id 3 | task 8348 | stop processing: n_tokens = 882, truncated = 0 8.14.777.954 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.882 8.14.778.013 I slot launch_slot_: id 1 | task 8356 | processing task, is_child = 0 8.14.787.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 426.332 MiB) 8.14.796.295 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.848 8.14.796.350 I slot launch_slot_: id 2 | task 8357 | processing task, is_child = 0 8.14.796.417 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 331441735900 8.14.796.512 I slot launch_slot_: id 3 | task 8358 | processing task, is_child = 0 8.15.862.268 I slot print_timing: id 0 | task 8351 | prompt eval time = 2282.66 ms / 703 tokens ( 3.25 ms per token, 307.97 tokens per second) 8.15.862.271 I slot print_timing: id 0 | task 8351 | eval time = 1084.31 ms / 2 tokens ( 1084.31 ms per token, 0.92 tokens per second) 8.15.862.272 I slot print_timing: id 0 | task 8351 | total time = 3366.97 ms / 705 tokens 8.15.862.272 I slot print_timing: id 0 | task 8351 | graphs reused = 7276 8.15.862.272 I slot print_timing: id 0 | task 8351 | graph reallocs = 0 / 0 (same size) / (changed size) 8.15.862.320 I slot release: id 0 | task 8351 | stop processing: n_tokens = 713, truncated = 0 8.16.686.356 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 713, t_last = 331442858162 8.16.699.344 I slot launch_slot_: id 0 | task 8361 | processing task, is_child = 0 8.17.829.539 I slot print_timing: id 1 | task 8356 | prompt eval time = 1888.65 ms / 95 tokens ( 19.88 ms per token, 50.30 tokens per second) 8.17.829.541 I slot print_timing: id 1 | task 8356 | eval time = 1144.36 ms / 2 tokens ( 1144.36 ms per token, 0.87 tokens per second) 8.17.829.543 I slot print_timing: id 1 | task 8356 | total time = 3033.02 ms / 97 tokens 8.17.829.543 I slot print_timing: id 1 | task 8356 | graphs reused = 7276 8.17.829.544 I slot print_timing: id 1 | task 8356 | graph reallocs = 0 / 0 (same size) / (changed size) 8.17.829.590 I slot release: id 1 | task 8356 | stop processing: n_tokens = 722, truncated = 0 8.17.830.771 I slot print_timing: id 2 | task 8357 | prompt eval time = 1888.14 ms / 89 tokens ( 21.22 ms per token, 47.14 tokens per second) 8.17.830.775 I slot print_timing: id 2 | task 8357 | eval time = 1144.43 ms / 2 tokens ( 1144.43 ms per token, 0.87 tokens per second) 8.17.830.775 I slot print_timing: id 2 | task 8357 | total time = 3032.57 ms / 91 tokens 8.17.830.775 I slot print_timing: id 2 | task 8357 | graphs reused = 7276 8.17.830.776 I slot print_timing: id 2 | task 8357 | graph reallocs = 0 / 0 (same size) / (changed size) 8.17.830.816 I slot release: id 2 | task 8357 | stop processing: n_tokens = 716, truncated = 0 8.17.835.441 I slot print_timing: id 3 | task 8358 | prompt processing, n_tokens = 860, progress = 1.00, t = 3.03 s / 283.96 tokens per second 8.18.633.321 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 722, t_last = 331444825432 8.18.633.421 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.073 MiB) 8.18.648.850 I slot launch_slot_: id 1 | task 8364 | processing task, is_child = 0 8.18.648.916 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 350.849 MiB) 8.18.658.783 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 716, t_last = 331444826658 8.18.658.894 I slot launch_slot_: id 2 | task 8365 | processing task, is_child = 0 8.20.720.093 I slot print_timing: id 3 | task 8358 | prompt eval time = 3833.41 ms / 864 tokens ( 4.44 ms per token, 225.39 tokens per second) 8.20.720.099 I slot print_timing: id 3 | task 8358 | eval time = 2086.77 ms / 2 tokens ( 2086.77 ms per token, 0.48 tokens per second) 8.20.720.099 I slot print_timing: id 3 | task 8358 | total time = 5920.18 ms / 866 tokens 8.20.720.100 I slot print_timing: id 3 | task 8358 | graphs reused = 7276 8.20.720.100 I slot print_timing: id 3 | task 8358 | graph reallocs = 0 / 0 (same size) / (changed size) 8.20.720.146 I slot release: id 3 | task 8358 | stop processing: n_tokens = 874, truncated = 0 8.20.720.164 I slot print_timing: id 0 | task 8361 | prompt processing, n_tokens = 977, progress = 1.00, t = 4.02 s / 243.06 tokens per second 8.22.167.771 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 874, t_last = 331447715988 8.22.180.699 I slot launch_slot_: id 3 | task 8368 | processing task, is_child = 0 8.22.180.711 I slot print_timing: id 1 | task 8364 | prompt processing, n_tokens = 850, progress = 0.86, t = 3.51 s / 242.48 tokens per second 8.22.184.200 I slot print_timing: id 2 | task 8365 | prompt processing, n_tokens = 850, progress = 0.83, t = 3.51 s / 242.49 tokens per second 8.23.758.840 I slot print_timing: id 0 | task 8361 | prompt eval time = 5468.40 ms / 981 tokens ( 5.57 ms per token, 179.39 tokens per second) 8.23.758.847 I slot print_timing: id 0 | task 8361 | eval time = 1591.07 ms / 2 tokens ( 1591.07 ms per token, 0.63 tokens per second) 8.23.758.848 I slot print_timing: id 0 | task 8361 | total time = 7059.47 ms / 983 tokens 8.23.758.849 I slot print_timing: id 0 | task 8361 | graphs reused = 7276 8.23.758.849 I slot print_timing: id 0 | task 8361 | graph reallocs = 0 / 0 (same size) / (changed size) 8.23.758.924 I slot release: id 0 | task 8361 | stop processing: n_tokens = 991, truncated = 0 8.23.758.951 I slot print_timing: id 1 | task 8364 | prompt processing, n_tokens = 991, progress = 1.00, t = 5.10 s / 194.44 tokens per second 8.23.763.077 I slot print_timing: id 2 | task 8365 | prompt processing, n_tokens = 1021, progress = 1.00, t = 5.10 s / 200.34 tokens per second 8.24.534.972 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.894 (> 0.100 thold), f_keep = 0.894 8.24.535.121 I slot launch_slot_: id 0 | task 8371 | processing task, is_child = 0 8.25.132.357 I slot print_timing: id 1 | task 8364 | prompt eval time = 5872.68 ms / 995 tokens ( 5.90 ms per token, 169.43 tokens per second) 8.25.132.362 I slot print_timing: id 1 | task 8364 | eval time = 598.55 ms / 2 tokens ( 598.55 ms per token, 1.67 tokens per second) 8.25.132.363 I slot print_timing: id 1 | task 8364 | total time = 6471.23 ms / 997 tokens 8.25.132.363 I slot print_timing: id 1 | task 8364 | graphs reused = 7276 8.25.132.364 I slot print_timing: id 1 | task 8364 | graph reallocs = 0 / 0 (same size) / (changed size) 8.25.132.439 I slot release: id 1 | task 8364 | stop processing: n_tokens = 1005, truncated = 0 8.25.133.591 I slot print_timing: id 2 | task 8365 | prompt eval time = 5873.68 ms / 1025 tokens ( 5.73 ms per token, 174.51 tokens per second) 8.25.133.594 I slot print_timing: id 2 | task 8365 | eval time = 598.63 ms / 2 tokens ( 598.63 ms per token, 1.67 tokens per second) 8.25.133.595 I slot print_timing: id 2 | task 8365 | total time = 6472.31 ms / 1027 tokens 8.25.133.595 I slot print_timing: id 2 | task 8365 | graphs reused = 7276 8.25.133.595 I slot print_timing: id 2 | task 8365 | graph reallocs = 0 / 0 (same size) / (changed size) 8.25.133.638 I slot release: id 2 | task 8365 | stop processing: n_tokens = 1035, truncated = 0 8.25.207.659 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1005, t_last = 331452128281 8.25.207.747 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.361 MiB) 8.25.217.849 I slot launch_slot_: id 1 | task 8374 | processing task, is_child = 0 8.25.217.928 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 426.719 MiB) 8.25.229.256 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 331452129480 8.25.229.381 I slot launch_slot_: id 2 | task 8375 | processing task, is_child = 0 8.26.880.685 I slot print_timing: id 0 | task 8371 | prompt eval time = 671.37 ms / 105 tokens ( 6.39 ms per token, 156.40 tokens per second) 8.26.880.688 I slot print_timing: id 0 | task 8371 | eval time = 1674.17 ms / 2 tokens ( 1674.17 ms per token, 0.60 tokens per second) 8.26.880.689 I slot print_timing: id 0 | task 8371 | total time = 2345.54 ms / 107 tokens 8.26.880.690 I slot print_timing: id 0 | task 8371 | graphs reused = 7276 8.26.880.690 I slot print_timing: id 0 | task 8371 | graph reallocs = 0 / 0 (same size) / (changed size) 8.26.880.765 I slot release: id 0 | task 8371 | stop processing: n_tokens = 992, truncated = 0 8.26.881.905 I slot print_timing: id 3 | task 8368 | prompt eval time = 3021.77 ms / 987 tokens ( 3.06 ms per token, 326.63 tokens per second) 8.26.881.912 I slot print_timing: id 3 | task 8368 | eval time = 1674.25 ms / 2 tokens ( 1674.25 ms per token, 0.60 tokens per second) 8.26.881.913 I slot print_timing: id 3 | task 8368 | total time = 4696.02 ms / 989 tokens 8.26.881.913 I slot print_timing: id 3 | task 8368 | graphs reused = 7276 8.26.881.913 I slot print_timing: id 3 | task 8368 | graph reallocs = 0 / 0 (same size) / (changed size) 8.26.881.956 I slot release: id 3 | task 8368 | stop processing: n_tokens = 997, truncated = 0 8.27.907.202 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 992, t_last = 331453876607 8.27.907.297 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.721 MiB) 8.28.104.341 I slot launch_slot_: id 0 | task 8378 | processing task, is_child = 0 8.28.115.986 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 997, t_last = 331453877798 8.28.116.117 I slot launch_slot_: id 3 | task 8379 | processing task, is_child = 0 8.30.522.453 I slot print_timing: id 1 | task 8374 | prompt processing, n_tokens = 871, progress = 1.00, t = 4.82 s / 180.54 tokens per second 8.30.525.270 I slot print_timing: id 2 | task 8375 | prompt processing, n_tokens = 1010, progress = 1.00, t = 4.82 s / 209.36 tokens per second 8.31.888.326 I slot print_timing: id 0 | task 8378 | prompt processing, n_tokens = 768, progress = 0.86, t = 3.77 s / 203.71 tokens per second 8.31.891.649 I slot print_timing: id 3 | task 8379 | prompt processing, n_tokens = 768, progress = 0.77, t = 3.77 s / 203.91 tokens per second 8.32.665.298 I slot print_timing: id 1 | task 8374 | prompt eval time = 6657.81 ms / 875 tokens ( 7.61 ms per token, 131.42 tokens per second) 8.32.665.301 I slot print_timing: id 1 | task 8374 | eval time = 778.09 ms / 2 tokens ( 778.09 ms per token, 1.29 tokens per second) 8.32.665.302 I slot print_timing: id 1 | task 8374 | total time = 7435.90 ms / 877 tokens 8.32.665.302 I slot print_timing: id 1 | task 8374 | graphs reused = 7276 8.32.665.303 I slot print_timing: id 1 | task 8374 | graph reallocs = 0 / 0 (same size) / (changed size) 8.32.665.375 I slot release: id 1 | task 8374 | stop processing: n_tokens = 885, truncated = 0 8.32.666.546 I slot print_timing: id 2 | task 8375 | prompt eval time = 6658.67 ms / 1014 tokens ( 6.57 ms per token, 152.28 tokens per second) 8.32.666.550 I slot print_timing: id 2 | task 8375 | eval time = 778.24 ms / 2 tokens ( 778.24 ms per token, 1.28 tokens per second) 8.32.666.550 I slot print_timing: id 2 | task 8375 | total time = 7436.91 ms / 1016 tokens 8.32.666.551 I slot print_timing: id 2 | task 8375 | graphs reused = 7276 8.32.666.551 I slot print_timing: id 2 | task 8375 | graph reallocs = 0 / 0 (same size) / (changed size) 8.32.666.603 I slot release: id 2 | task 8375 | stop processing: n_tokens = 1024, truncated = 0 8.32.666.617 I slot print_timing: id 0 | task 8378 | prompt processing, n_tokens = 890, progress = 1.00, t = 4.55 s / 195.69 tokens per second 8.32.670.747 I slot print_timing: id 3 | task 8379 | prompt processing, n_tokens = 998, progress = 1.00, t = 4.54 s / 219.60 tokens per second 8.32.742.330 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.785 8.32.742.397 I slot launch_slot_: id 2 | task 8384 | processing task, is_child = 0 8.32.742.482 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.627 MiB) 8.32.749.066 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 885, t_last = 331459661217 8.32.749.177 I slot launch_slot_: id 1 | task 8385 | processing task, is_child = 0 8.33.906.967 I slot print_timing: id 0 | task 8378 | prompt eval time = 4625.06 ms / 894 tokens ( 5.17 ms per token, 193.29 tokens per second) 8.33.906.974 I slot print_timing: id 0 | task 8378 | eval time = 1165.77 ms / 2 tokens ( 1165.77 ms per token, 0.86 tokens per second) 8.33.906.974 I slot print_timing: id 0 | task 8378 | total time = 5790.83 ms / 896 tokens 8.33.906.975 I slot print_timing: id 0 | task 8378 | graphs reused = 7276 8.33.906.976 I slot print_timing: id 0 | task 8378 | graph reallocs = 0 / 0 (same size) / (changed size) 8.33.907.022 I slot release: id 0 | task 8378 | stop processing: n_tokens = 904, truncated = 0 8.33.908.139 I slot print_timing: id 3 | task 8379 | prompt eval time = 4622.64 ms / 1002 tokens ( 4.61 ms per token, 216.76 tokens per second) 8.33.908.142 I slot print_timing: id 3 | task 8379 | eval time = 1165.81 ms / 2 tokens ( 1165.81 ms per token, 0.86 tokens per second) 8.33.908.142 I slot print_timing: id 3 | task 8379 | total time = 5788.45 ms / 1004 tokens 8.33.908.142 I slot print_timing: id 3 | task 8379 | graphs reused = 7276 8.33.908.143 I slot print_timing: id 3 | task 8379 | graph reallocs = 0 / 0 (same size) / (changed size) 8.33.908.186 I slot release: id 3 | task 8379 | stop processing: n_tokens = 1012, truncated = 0 8.34.546.460 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.889 8.34.546.568 I slot launch_slot_: id 0 | task 8388 | processing task, is_child = 0 8.34.554.840 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1012, t_last = 331460904028 8.34.554.956 I slot launch_slot_: id 3 | task 8389 | processing task, is_child = 0 8.35.941.851 I slot print_timing: id 2 | task 8384 | prompt eval time = 1797.07 ms / 102 tokens ( 17.62 ms per token, 56.76 tokens per second) 8.35.941.854 I slot print_timing: id 2 | task 8384 | eval time = 1395.40 ms / 2 tokens ( 1395.40 ms per token, 0.72 tokens per second) 8.35.941.854 I slot print_timing: id 2 | task 8384 | total time = 3192.47 ms / 104 tokens 8.35.941.855 I slot print_timing: id 2 | task 8384 | graphs reused = 7276 8.35.941.855 I slot print_timing: id 2 | task 8384 | graph reallocs = 0 / 0 (same size) / (changed size) 8.35.941.919 I slot release: id 2 | task 8384 | stop processing: n_tokens = 907, truncated = 0 8.35.946.070 I slot print_timing: id 1 | task 8385 | prompt processing, n_tokens = 979, progress = 1.00, t = 3.19 s / 306.75 tokens per second 8.36.639.567 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 907, t_last = 331462937761 8.36.639.685 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 478.229 MiB) 8.36.654.252 I slot launch_slot_: id 2 | task 8392 | processing task, is_child = 0 8.37.741.463 I slot print_timing: id 0 | task 8388 | prompt eval time = 2083.43 ms / 81 tokens ( 25.72 ms per token, 38.88 tokens per second) 8.37.741.466 I slot print_timing: id 0 | task 8388 | eval time = 1103.05 ms / 2 tokens ( 1103.05 ms per token, 0.91 tokens per second) 8.37.741.467 I slot print_timing: id 0 | task 8388 | total time = 3186.48 ms / 83 tokens 8.37.741.468 I slot print_timing: id 0 | task 8388 | graphs reused = 7276 8.37.741.468 I slot print_timing: id 0 | task 8388 | graph reallocs = 0 / 0 (same size) / (changed size) 8.37.741.558 I slot release: id 0 | task 8388 | stop processing: n_tokens = 886, truncated = 0 8.37.742.714 I slot print_timing: id 1 | task 8385 | prompt eval time = 3890.38 ms / 983 tokens ( 3.96 ms per token, 252.67 tokens per second) 8.37.742.717 I slot print_timing: id 1 | task 8385 | eval time = 1103.15 ms / 2 tokens ( 1103.15 ms per token, 0.91 tokens per second) 8.37.742.718 I slot print_timing: id 1 | task 8385 | total time = 4993.53 ms / 985 tokens 8.37.742.718 I slot print_timing: id 1 | task 8385 | graphs reused = 7276 8.37.742.719 I slot print_timing: id 1 | task 8385 | graph reallocs = 0 / 0 (same size) / (changed size) 8.37.742.776 I slot release: id 1 | task 8385 | stop processing: n_tokens = 993, truncated = 0 8.37.745.492 I slot print_timing: id 3 | task 8389 | prompt processing, n_tokens = 927, progress = 1.00, t = 3.18 s / 291.33 tokens per second 8.38.492.240 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 886, t_last = 331464737400 8.38.492.368 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.003 MiB) 8.38.509.020 I slot launch_slot_: id 0 | task 8395 | processing task, is_child = 0 8.38.521.380 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 993, t_last = 331464738618 8.38.521.506 I slot launch_slot_: id 1 | task 8396 | processing task, is_child = 0 8.41.098.107 I slot print_timing: id 3 | task 8389 | prompt eval time = 3933.85 ms / 931 tokens ( 4.23 ms per token, 236.66 tokens per second) 8.41.098.111 I slot print_timing: id 3 | task 8389 | eval time = 2605.86 ms / 2 tokens ( 2605.86 ms per token, 0.38 tokens per second) 8.41.098.111 I slot print_timing: id 3 | task 8389 | total time = 6539.71 ms / 933 tokens 8.41.098.112 I slot print_timing: id 3 | task 8389 | graphs reused = 7276 8.41.098.112 I slot print_timing: id 3 | task 8389 | graph reallocs = 0 / 0 (same size) / (changed size) 8.41.098.183 I slot release: id 3 | task 8389 | stop processing: n_tokens = 941, truncated = 0 8.41.103.077 I slot print_timing: id 2 | task 8392 | prompt processing, n_tokens = 880, progress = 1.00, t = 4.44 s / 198.08 tokens per second 8.42.474.876 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 331468094025 8.42.474.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 403.906 MiB) 8.42.487.822 I slot launch_slot_: id 3 | task 8399 | processing task, is_child = 0 8.42.487.832 I slot print_timing: id 0 | task 8395 | prompt processing, n_tokens = 753, progress = 0.82, t = 3.95 s / 190.52 tokens per second 8.42.489.511 I slot print_timing: id 1 | task 8396 | prompt processing, n_tokens = 1148, progress = 0.85, t = 3.95 s / 290.48 tokens per second 8.44.807.343 I slot print_timing: id 2 | task 8392 | prompt eval time = 5820.61 ms / 884 tokens ( 6.58 ms per token, 151.87 tokens per second) 8.44.807.350 I slot print_timing: id 2 | task 8392 | eval time = 2332.47 ms / 2 tokens ( 2332.47 ms per token, 0.43 tokens per second) 8.44.807.350 I slot print_timing: id 2 | task 8392 | total time = 8153.08 ms / 886 tokens 8.44.807.351 I slot print_timing: id 2 | task 8392 | graphs reused = 7276 8.44.807.351 I slot print_timing: id 2 | task 8392 | graph reallocs = 0 / 0 (same size) / (changed size) 8.44.807.398 I slot release: id 2 | task 8392 | stop processing: n_tokens = 894, truncated = 0 8.44.807.414 I slot print_timing: id 0 | task 8395 | prompt processing, n_tokens = 914, progress = 1.00, t = 6.28 s / 145.43 tokens per second 8.44.811.612 I slot print_timing: id 1 | task 8396 | prompt processing, n_tokens = 1349, progress = 1.00, t = 6.28 s / 214.65 tokens per second 8.45.511.388 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 894, t_last = 331471803240 8.45.524.481 I slot launch_slot_: id 2 | task 8402 | processing task, is_child = 0 8.45.524.690 I slot print_timing: id 3 | task 8399 | prompt processing, n_tokens = 1148, progress = 0.86, t = 3.02 s / 380.40 tokens per second 8.47.310.497 I slot print_timing: id 0 | task 8395 | prompt eval time = 6988.67 ms / 918 tokens ( 7.61 ms per token, 131.36 tokens per second) 8.47.310.500 I slot print_timing: id 0 | task 8395 | eval time = 1800.31 ms / 2 tokens ( 1800.31 ms per token, 0.56 tokens per second) 8.47.310.501 I slot print_timing: id 0 | task 8395 | total time = 8788.98 ms / 920 tokens 8.47.310.501 I slot print_timing: id 0 | task 8395 | graphs reused = 7276 8.47.310.502 I slot print_timing: id 0 | task 8395 | graph reallocs = 0 / 0 (same size) / (changed size) 8.47.310.554 I slot release: id 0 | task 8395 | stop processing: n_tokens = 928, truncated = 0 8.47.311.692 I slot print_timing: id 1 | task 8396 | prompt eval time = 6989.66 ms / 1353 tokens ( 5.17 ms per token, 193.57 tokens per second) 8.47.311.693 I slot print_timing: id 1 | task 8396 | eval time = 1800.31 ms / 2 tokens ( 1800.31 ms per token, 0.56 tokens per second) 8.47.311.694 I slot print_timing: id 1 | task 8396 | total time = 8789.97 ms / 1355 tokens 8.47.311.694 I slot print_timing: id 1 | task 8396 | graphs reused = 7276 8.47.311.695 I slot print_timing: id 1 | task 8396 | graph reallocs = 0 / 0 (same size) / (changed size) 8.47.311.742 I slot release: id 1 | task 8396 | stop processing: n_tokens = 1363, truncated = 0 8.47.313.587 I slot print_timing: id 3 | task 8399 | prompt processing, n_tokens = 1336, progress = 1.00, t = 4.82 s / 277.29 tokens per second 8.48.126.068 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 331474306396 8.48.126.206 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.323 MiB) 8.48.144.820 I slot launch_slot_: id 0 | task 8405 | processing task, is_child = 0 8.48.144.911 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 245.780 MiB) 8.48.144.918 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 248.171 MiB) 8.48.160.945 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.869 8.48.161.002 I slot launch_slot_: id 1 | task 8406 | processing task, is_child = 0 8.49.168.903 I slot print_timing: id 3 | task 8399 | prompt eval time = 5634.82 ms / 1340 tokens ( 4.21 ms per token, 237.81 tokens per second) 8.49.168.906 I slot print_timing: id 3 | task 8399 | eval time = 1042.84 ms / 2 tokens ( 1042.84 ms per token, 0.96 tokens per second) 8.49.168.906 I slot print_timing: id 3 | task 8399 | total time = 6677.66 ms / 1342 tokens 8.49.168.907 I slot print_timing: id 3 | task 8399 | graphs reused = 7276 8.49.168.907 I slot print_timing: id 3 | task 8399 | graph reallocs = 0 / 0 (same size) / (changed size) 8.49.168.967 I slot release: id 3 | task 8399 | stop processing: n_tokens = 1350, truncated = 0 8.49.173.451 I slot print_timing: id 2 | task 8402 | prompt processing, n_tokens = 1251, progress = 1.00, t = 3.64 s / 343.37 tokens per second 8.49.987.176 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1350, t_last = 331476164809 8.49.987.334 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.635 MiB) 8.50.006.127 I slot launch_slot_: id 3 | task 8409 | processing task, is_child = 0 8.50.810.191 I slot print_timing: id 1 | task 8406 | prompt eval time = 1824.81 ms / 121 tokens ( 15.08 ms per token, 66.31 tokens per second) 8.50.810.197 I slot print_timing: id 1 | task 8406 | eval time = 824.15 ms / 2 tokens ( 824.15 ms per token, 1.21 tokens per second) 8.50.810.197 I slot print_timing: id 1 | task 8406 | total time = 2648.96 ms / 123 tokens 8.50.810.198 I slot print_timing: id 1 | task 8406 | graphs reused = 7276 8.50.810.198 I slot print_timing: id 1 | task 8406 | graph reallocs = 0 / 0 (same size) / (changed size) 8.50.810.294 I slot release: id 1 | task 8406 | stop processing: n_tokens = 1306, truncated = 0 8.50.811.467 I slot print_timing: id 2 | task 8402 | prompt eval time = 4462.68 ms / 1255 tokens ( 3.56 ms per token, 281.22 tokens per second) 8.50.811.470 I slot print_timing: id 2 | task 8402 | eval time = 824.30 ms / 2 tokens ( 824.30 ms per token, 1.21 tokens per second) 8.50.811.473 I slot print_timing: id 2 | task 8402 | total time = 5286.98 ms / 1257 tokens 8.50.811.473 I slot print_timing: id 2 | task 8402 | graphs reused = 7276 8.50.811.473 I slot print_timing: id 2 | task 8402 | graph reallocs = 0 / 0 (same size) / (changed size) 8.50.811.514 I slot release: id 2 | task 8402 | stop processing: n_tokens = 1265, truncated = 0 8.51.601.986 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1306, t_last = 331477806137 8.51.602.129 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 223.136 MiB) 8.51.624.682 I slot launch_slot_: id 1 | task 8412 | processing task, is_child = 0 8.51.624.786 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.184 MiB) 8.51.640.379 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1265, t_last = 331477807356 8.51.640.517 I slot launch_slot_: id 2 | task 8413 | processing task, is_child = 0 8.53.244.777 I slot print_timing: id 0 | task 8405 | prompt eval time = 3440.97 ms / 782 tokens ( 4.40 ms per token, 227.26 tokens per second) 8.53.244.780 I slot print_timing: id 0 | task 8405 | eval time = 1642.80 ms / 2 tokens ( 1642.80 ms per token, 0.61 tokens per second) 8.53.244.780 I slot print_timing: id 0 | task 8405 | total time = 5083.76 ms / 784 tokens 8.53.244.781 I slot print_timing: id 0 | task 8405 | graphs reused = 7276 8.53.244.781 I slot print_timing: id 0 | task 8405 | graph reallocs = 0 / 0 (same size) / (changed size) 8.53.244.816 I slot release: id 0 | task 8405 | stop processing: n_tokens = 792, truncated = 0 8.53.251.843 I slot print_timing: id 3 | task 8409 | prompt processing, n_tokens = 797, progress = 1.00, t = 3.24 s / 246.30 tokens per second 8.54.738.269 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 792, t_last = 331480240658 8.54.738.415 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 230.309 MiB) 8.54.747.486 I slot launch_slot_: id 0 | task 8416 | processing task, is_child = 0 8.54.747.674 I slot print_timing: id 1 | task 8412 | prompt processing, n_tokens = 736, progress = 0.86, t = 3.10 s / 237.68 tokens per second 8.54.749.321 I slot print_timing: id 2 | task 8413 | prompt processing, n_tokens = 736, progress = 0.83, t = 3.10 s / 237.69 tokens per second 8.55.802.466 I slot print_timing: id 3 | task 8409 | prompt eval time = 4730.46 ms / 801 tokens ( 5.91 ms per token, 169.33 tokens per second) 8.55.802.470 I slot print_timing: id 3 | task 8409 | eval time = 1064.21 ms / 2 tokens ( 1064.21 ms per token, 0.94 tokens per second) 8.55.802.470 I slot print_timing: id 3 | task 8409 | total time = 5794.67 ms / 803 tokens 8.55.802.471 I slot print_timing: id 3 | task 8409 | graphs reused = 7276 8.55.802.471 I slot print_timing: id 3 | task 8409 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.802.544 I slot release: id 3 | task 8409 | stop processing: n_tokens = 811, truncated = 0 8.55.804.901 I slot print_timing: id 1 | task 8412 | prompt processing, n_tokens = 853, progress = 1.00, t = 4.16 s / 205.01 tokens per second 8.55.807.018 I slot print_timing: id 2 | task 8413 | prompt processing, n_tokens = 882, progress = 1.00, t = 4.16 s / 211.99 tokens per second 8.56.566.931 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 811, t_last = 331482798386 8.56.567.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.776 MiB) 8.56.575.358 I slot launch_slot_: id 3 | task 8419 | processing task, is_child = 0 8.57.535.285 I slot print_timing: id 1 | task 8412 | prompt eval time = 4925.18 ms / 857 tokens ( 5.75 ms per token, 174.00 tokens per second) 8.57.535.287 I slot print_timing: id 1 | task 8412 | eval time = 969.57 ms / 2 tokens ( 969.57 ms per token, 1.03 tokens per second) 8.57.535.288 I slot print_timing: id 1 | task 8412 | total time = 5894.75 ms / 859 tokens 8.57.535.289 I slot print_timing: id 1 | task 8412 | graphs reused = 7276 8.57.535.289 I slot print_timing: id 1 | task 8412 | graph reallocs = 0 / 0 (same size) / (changed size) 8.57.535.362 I slot release: id 1 | task 8412 | stop processing: n_tokens = 867, truncated = 0 8.57.536.536 I slot print_timing: id 2 | task 8413 | prompt eval time = 4926.16 ms / 886 tokens ( 5.56 ms per token, 179.86 tokens per second) 8.57.536.539 I slot print_timing: id 2 | task 8413 | eval time = 969.61 ms / 2 tokens ( 969.61 ms per token, 1.03 tokens per second) 8.57.536.539 I slot print_timing: id 2 | task 8413 | total time = 5895.78 ms / 888 tokens 8.57.536.539 I slot print_timing: id 2 | task 8413 | graphs reused = 7276 8.57.536.540 I slot print_timing: id 2 | task 8413 | graph reallocs = 0 / 0 (same size) / (changed size) 8.57.536.576 I slot release: id 2 | task 8413 | stop processing: n_tokens = 896, truncated = 0 8.58.167.107 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 867, t_last = 331484531204 8.58.167.234 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 234.388 MiB) 8.58.175.533 I slot launch_slot_: id 1 | task 8422 | processing task, is_child = 0 8.58.175.608 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 232.981 MiB) 8.58.181.281 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 896, t_last = 331484532418 8.58.181.400 I slot launch_slot_: id 2 | task 8423 | processing task, is_child = 0 8.59.594.597 I slot print_timing: id 0 | task 8416 | prompt eval time = 3419.60 ms / 778 tokens ( 4.40 ms per token, 227.51 tokens per second) 8.59.594.600 I slot print_timing: id 0 | task 8416 | eval time = 1427.50 ms / 2 tokens ( 1427.50 ms per token, 0.70 tokens per second) 8.59.594.600 I slot print_timing: id 0 | task 8416 | total time = 4847.10 ms / 780 tokens 8.59.594.601 I slot print_timing: id 0 | task 8416 | graphs reused = 7276 8.59.594.601 I slot print_timing: id 0 | task 8416 | graph reallocs = 0 / 0 (same size) / (changed size) 8.59.594.646 I slot release: id 0 | task 8416 | stop processing: n_tokens = 788, truncated = 0 8.59.598.969 I slot print_timing: id 3 | task 8419 | prompt processing, n_tokens = 839, progress = 1.00, t = 3.02 s / 278.14 tokens per second 9.01.132.258 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.849 (> 0.100 thold), f_keep = 0.862 9.01.132.411 I slot launch_slot_: id 0 | task 8426 | processing task, is_child = 0 9.01.880.083 I slot print_timing: id 3 | task 8419 | prompt eval time = 4555.20 ms / 843 tokens ( 5.40 ms per token, 185.06 tokens per second) 9.01.880.087 I slot print_timing: id 3 | task 8419 | eval time = 747.83 ms / 2 tokens ( 747.83 ms per token, 1.34 tokens per second) 9.01.880.088 I slot print_timing: id 3 | task 8419 | total time = 5303.03 ms / 845 tokens 9.01.880.088 I slot print_timing: id 3 | task 8419 | graphs reused = 7276 9.01.880.089 I slot print_timing: id 3 | task 8419 | graph reallocs = 0 / 0 (same size) / (changed size) 9.01.880.161 I slot release: id 3 | task 8419 | stop processing: n_tokens = 853, truncated = 0 9.01.883.994 I slot print_timing: id 1 | task 8422 | prompt processing, n_tokens = 758, progress = 0.99, t = 3.70 s / 205.00 tokens per second 9.01.886.017 I slot print_timing: id 2 | task 8423 | prompt processing, n_tokens = 764, progress = 0.99, t = 3.70 s / 206.63 tokens per second 9.01.948.658 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 853, t_last = 331488876003 9.01.948.737 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 244.374 MiB) 9.01.954.934 I slot launch_slot_: id 3 | task 8429 | processing task, is_child = 0 9.02.787.492 I slot print_timing: id 0 | task 8426 | prompt eval time = 813.84 ms / 121 tokens ( 6.73 ms per token, 148.68 tokens per second) 9.02.787.494 I slot print_timing: id 0 | task 8426 | eval time = 841.21 ms / 2 tokens ( 841.21 ms per token, 1.19 tokens per second) 9.02.787.495 I slot print_timing: id 0 | task 8426 | total time = 1655.06 ms / 123 tokens 9.02.787.495 I slot print_timing: id 0 | task 8426 | graphs reused = 7276 9.02.787.496 I slot print_timing: id 0 | task 8426 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.787.557 I slot release: id 0 | task 8426 | stop processing: n_tokens = 801, truncated = 0 9.02.788.699 I slot print_timing: id 1 | task 8422 | prompt eval time = 3765.97 ms / 762 tokens ( 4.94 ms per token, 202.34 tokens per second) 9.02.788.701 I slot print_timing: id 1 | task 8422 | eval time = 841.32 ms / 2 tokens ( 841.32 ms per token, 1.19 tokens per second) 9.02.788.702 I slot print_timing: id 1 | task 8422 | total time = 4607.29 ms / 764 tokens 9.02.788.702 I slot print_timing: id 1 | task 8422 | graphs reused = 7276 9.02.788.702 I slot print_timing: id 1 | task 8422 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.788.740 I slot release: id 1 | task 8422 | stop processing: n_tokens = 772, truncated = 0 9.02.789.881 I slot print_timing: id 2 | task 8423 | prompt eval time = 3767.05 ms / 768 tokens ( 4.91 ms per token, 203.87 tokens per second) 9.02.789.883 I slot print_timing: id 2 | task 8423 | eval time = 841.23 ms / 2 tokens ( 841.23 ms per token, 1.19 tokens per second) 9.02.789.884 I slot print_timing: id 2 | task 8423 | total time = 4608.27 ms / 770 tokens 9.02.789.884 I slot print_timing: id 2 | task 8423 | graphs reused = 7276 9.02.789.884 I slot print_timing: id 2 | task 8423 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.789.912 I slot release: id 2 | task 8423 | stop processing: n_tokens = 778, truncated = 0 9.03.506.989 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 801, t_last = 331489783399 9.03.507.066 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.859 MiB) 9.03.814.032 I slot launch_slot_: id 0 | task 8433 | processing task, is_child = 0 9.03.814.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 254.360 MiB) 9.03.821.006 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 240.014 MiB) 9.03.826.310 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 331489784582 9.03.826.428 I slot launch_slot_: id 1 | task 8434 | processing task, is_child = 0 9.03.826.491 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 331489785754 9.03.826.584 I slot launch_slot_: id 2 | task 8435 | processing task, is_child = 0 9.08.525.519 I slot print_timing: id 3 | task 8429 | prompt eval time = 4229.39 ms / 952 tokens ( 4.44 ms per token, 225.09 tokens per second) 9.08.525.525 I slot print_timing: id 3 | task 8429 | eval time = 2341.18 ms / 2 tokens ( 2341.18 ms per token, 0.43 tokens per second) 9.08.525.525 I slot print_timing: id 3 | task 8429 | total time = 6570.57 ms / 954 tokens 9.08.525.526 I slot print_timing: id 3 | task 8429 | graphs reused = 7276 9.08.525.526 I slot print_timing: id 3 | task 8429 | graph reallocs = 0 / 0 (same size) / (changed size) 9.08.525.578 I slot release: id 3 | task 8429 | stop processing: n_tokens = 962, truncated = 0 9.08.525.608 I slot print_timing: id 0 | task 8433 | prompt processing, n_tokens = 817, progress = 0.88, t = 4.70 s / 173.91 tokens per second 9.08.528.810 I slot print_timing: id 1 | task 8434 | prompt processing, n_tokens = 817, progress = 0.88, t = 4.70 s / 173.92 tokens per second 9.08.530.746 I slot print_timing: id 2 | task 8435 | prompt processing, n_tokens = 817, progress = 0.87, t = 4.70 s / 173.92 tokens per second 9.09.171.542 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.889 (> 0.100 thold), f_keep = 0.887 9.09.171.606 I slot launch_slot_: id 3 | task 8439 | processing task, is_child = 0 9.09.171.610 I slot print_timing: id 0 | task 8433 | prompt processing, n_tokens = 922, progress = 1.00, t = 5.34 s / 172.50 tokens per second 9.09.229.170 I slot print_timing: id 1 | task 8434 | prompt processing, n_tokens = 924, progress = 1.00, t = 5.34 s / 172.88 tokens per second 9.09.231.261 I slot print_timing: id 2 | task 8435 | prompt processing, n_tokens = 940, progress = 1.00, t = 5.34 s / 175.88 tokens per second 9.09.621.138 I slot print_timing: id 0 | task 8433 | prompt eval time = 5720.81 ms / 926 tokens ( 6.18 ms per token, 161.87 tokens per second) 9.09.621.144 I slot print_timing: id 0 | task 8433 | eval time = 73.73 ms / 2 tokens ( 73.73 ms per token, 13.56 tokens per second) 9.09.621.144 I slot print_timing: id 0 | task 8433 | total time = 5794.54 ms / 928 tokens 9.09.621.145 I slot print_timing: id 0 | task 8433 | graphs reused = 7276 9.09.621.145 I slot print_timing: id 0 | task 8433 | graph reallocs = 0 / 0 (same size) / (changed size) 9.09.621.189 I slot release: id 0 | task 8433 | stop processing: n_tokens = 936, truncated = 0 9.09.622.322 I slot print_timing: id 1 | task 8434 | prompt eval time = 5721.81 ms / 928 tokens ( 6.17 ms per token, 162.19 tokens per second) 9.09.622.323 I slot print_timing: id 1 | task 8434 | eval time = 73.73 ms / 2 tokens ( 73.73 ms per token, 13.56 tokens per second) 9.09.622.324 I slot print_timing: id 1 | task 8434 | total time = 5795.55 ms / 930 tokens 9.09.622.324 I slot print_timing: id 1 | task 8434 | graphs reused = 7276 9.09.622.325 I slot print_timing: id 1 | task 8434 | graph reallocs = 0 / 0 (same size) / (changed size) 9.09.622.353 I slot release: id 1 | task 8434 | stop processing: n_tokens = 938, truncated = 0 9.09.623.473 I slot print_timing: id 2 | task 8435 | prompt eval time = 5722.80 ms / 944 tokens ( 6.06 ms per token, 164.95 tokens per second) 9.09.623.475 I slot print_timing: id 2 | task 8435 | eval time = 73.75 ms / 2 tokens ( 73.75 ms per token, 13.56 tokens per second) 9.09.623.476 I slot print_timing: id 2 | task 8435 | total time = 5796.55 ms / 946 tokens 9.09.623.476 I slot print_timing: id 2 | task 8435 | graphs reused = 7276 9.09.623.476 I slot print_timing: id 2 | task 8435 | graph reallocs = 0 / 0 (same size) / (changed size) 9.09.623.505 I slot release: id 2 | task 8435 | stop processing: n_tokens = 954, truncated = 0 9.09.648.287 I slot print_timing: id 3 | task 8439 | prompt eval time = 391.39 ms / 107 tokens ( 3.66 ms per token, 273.38 tokens per second) 9.09.648.289 I slot print_timing: id 3 | task 8439 | eval time = 23.65 ms / 2 tokens ( 23.65 ms per token, 42.28 tokens per second) 9.09.648.290 I slot print_timing: id 3 | task 8439 | total time = 415.04 ms / 109 tokens 9.09.648.290 I slot print_timing: id 3 | task 8439 | graphs reused = 7276 9.09.648.290 I slot print_timing: id 3 | task 8439 | graph reallocs = 0 / 0 (same size) / (changed size) 9.09.648.319 I slot release: id 3 | task 8439 | stop processing: n_tokens = 961, truncated = 0 9.09.648.327 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 331496617031 9.09.648.406 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.037 MiB) 9.09.654.495 I slot launch_slot_: id 0 | task 8443 | processing task, is_child = 0 9.09.654.571 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 242.264 MiB) 9.09.660.874 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.291 MiB) 9.09.666.842 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 233.544 MiB) 9.09.673.976 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 938, t_last = 331496618195 9.09.674.114 I slot launch_slot_: id 1 | task 8444 | processing task, is_child = 0 9.09.674.248 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 331496619347 9.09.674.350 I slot launch_slot_: id 2 | task 8445 | processing task, is_child = 0 9.09.674.418 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 331496644161 9.09.674.517 I slot launch_slot_: id 3 | task 8446 | processing task, is_child = 0 9.15.121.270 I slot print_timing: id 0 | task 8443 | prompt processing, n_tokens = 668, progress = 0.85, t = 5.45 s / 122.64 tokens per second 9.15.208.009 I slot print_timing: id 1 | task 8444 | prompt processing, n_tokens = 668, progress = 0.85, t = 5.45 s / 122.65 tokens per second 9.15.211.297 I slot print_timing: id 2 | task 8445 | prompt processing, n_tokens = 818, progress = 0.85, t = 5.45 s / 150.19 tokens per second 9.15.212.982 I slot print_timing: id 3 | task 8446 | prompt processing, n_tokens = 818, progress = 0.87, t = 5.45 s / 150.20 tokens per second 9.16.158.360 I slot print_timing: id 0 | task 8443 | prompt processing, n_tokens = 785, progress = 0.99, t = 6.48 s / 121.07 tokens per second 9.16.244.952 I slot print_timing: id 1 | task 8444 | prompt processing, n_tokens = 785, progress = 0.99, t = 6.48 s / 121.07 tokens per second 9.16.247.126 I slot print_timing: id 2 | task 8445 | prompt processing, n_tokens = 963, progress = 1.00, t = 6.48 s / 148.53 tokens per second 9.16.250.345 I slot print_timing: id 3 | task 8446 | prompt processing, n_tokens = 943, progress = 1.00, t = 6.48 s / 145.45 tokens per second 9.16.356.261 I slot print_timing: id 0 | task 8443 | prompt eval time = 6641.00 ms / 789 tokens ( 8.42 ms per token, 118.81 tokens per second) 9.16.356.265 I slot print_timing: id 0 | task 8443 | eval time = 40.74 ms / 2 tokens ( 40.74 ms per token, 24.55 tokens per second) 9.16.356.266 I slot print_timing: id 0 | task 8443 | total time = 6681.74 ms / 791 tokens 9.16.356.266 I slot print_timing: id 0 | task 8443 | graphs reused = 7277 9.16.356.267 I slot print_timing: id 0 | task 8443 | graph reallocs = 0 / 0 (same size) / (changed size) 9.16.356.301 I slot release: id 0 | task 8443 | stop processing: n_tokens = 799, truncated = 0 9.16.357.435 I slot print_timing: id 1 | task 8444 | prompt eval time = 6641.89 ms / 789 tokens ( 8.42 ms per token, 118.79 tokens per second) 9.16.357.437 I slot print_timing: id 1 | task 8444 | eval time = 40.80 ms / 2 tokens ( 40.80 ms per token, 24.51 tokens per second) 9.16.357.438 I slot print_timing: id 1 | task 8444 | total time = 6682.69 ms / 791 tokens 9.16.357.438 I slot print_timing: id 1 | task 8444 | graphs reused = 7277 9.16.357.438 I slot print_timing: id 1 | task 8444 | graph reallocs = 0 / 0 (same size) / (changed size) 9.16.357.465 I slot release: id 1 | task 8444 | stop processing: n_tokens = 799, truncated = 0 9.16.358.586 I slot print_timing: id 2 | task 8445 | prompt eval time = 6642.90 ms / 967 tokens ( 6.87 ms per token, 145.57 tokens per second) 9.16.358.589 I slot print_timing: id 2 | task 8445 | eval time = 40.77 ms / 2 tokens ( 40.77 ms per token, 24.53 tokens per second) 9.16.358.590 I slot print_timing: id 2 | task 8445 | total time = 6683.67 ms / 969 tokens 9.16.358.590 I slot print_timing: id 2 | task 8445 | graphs reused = 7277 9.16.358.590 I slot print_timing: id 2 | task 8445 | graph reallocs = 0 / 0 (same size) / (changed size) 9.16.358.623 I slot release: id 2 | task 8445 | stop processing: n_tokens = 977, truncated = 0 9.16.359.698 I slot print_timing: id 3 | task 8446 | prompt eval time = 6643.95 ms / 947 tokens ( 7.02 ms per token, 142.54 tokens per second) 9.16.359.699 I slot print_timing: id 3 | task 8446 | eval time = 40.65 ms / 2 tokens ( 40.65 ms per token, 24.60 tokens per second) 9.16.359.700 I slot print_timing: id 3 | task 8446 | total time = 6684.60 ms / 949 tokens 9.16.359.700 I slot print_timing: id 3 | task 8446 | graphs reused = 7277 9.16.359.700 I slot print_timing: id 3 | task 8446 | graph reallocs = 0 / 0 (same size) / (changed size) 9.16.359.722 I slot release: id 3 | task 8446 | stop processing: n_tokens = 957, truncated = 0 9.16.365.074 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.874 9.16.365.128 I slot launch_slot_: id 2 | task 8452 | processing task, is_child = 0 9.16.365.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 209.775 MiB) 9.16.370.789 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.781 MiB) 9.16.376.311 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 266.524 MiB) 9.16.382.278 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 331503352143 9.16.382.399 I slot launch_slot_: id 0 | task 8453 | processing task, is_child = 0 9.16.382.528 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 331503353307 9.16.382.629 I slot launch_slot_: id 1 | task 8454 | processing task, is_child = 0 9.16.382.695 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 957, t_last = 331503355564 9.16.382.797 I slot launch_slot_: id 3 | task 8455 | processing task, is_child = 0 9.20.958.700 I slot print_timing: id 0 | task 8453 | prompt processing, n_tokens = 771, progress = 0.87, t = 4.57 s / 168.53 tokens per second 9.20.962.636 I slot print_timing: id 1 | task 8454 | prompt processing, n_tokens = 771, progress = 0.86, t = 4.57 s / 168.54 tokens per second 9.20.964.516 I slot print_timing: id 3 | task 8455 | prompt processing, n_tokens = 771, progress = 0.84, t = 4.57 s / 168.61 tokens per second 9.21.821.569 I slot print_timing: id 2 | task 8452 | prompt eval time = 4575.53 ms / 108 tokens ( 42.37 ms per token, 23.60 tokens per second) 9.21.821.572 I slot print_timing: id 2 | task 8452 | eval time = 862.88 ms / 2 tokens ( 862.88 ms per token, 1.16 tokens per second) 9.21.821.573 I slot print_timing: id 2 | task 8452 | total time = 5438.41 ms / 110 tokens 9.21.821.573 I slot print_timing: id 2 | task 8452 | graphs reused = 7277 9.21.821.574 I slot print_timing: id 2 | task 8452 | graph reallocs = 0 / 0 (same size) / (changed size) 9.21.821.619 I slot release: id 2 | task 8452 | stop processing: n_tokens = 963, truncated = 0 9.21.821.635 I slot print_timing: id 0 | task 8453 | prompt processing, n_tokens = 886, progress = 1.00, t = 5.44 s / 162.94 tokens per second 9.21.825.745 I slot print_timing: id 1 | task 8454 | prompt processing, n_tokens = 890, progress = 1.00, t = 5.44 s / 163.68 tokens per second 9.21.827.677 I slot print_timing: id 3 | task 8455 | prompt processing, n_tokens = 917, progress = 1.00, t = 5.44 s / 168.70 tokens per second 9.21.907.239 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 963, t_last = 331508817461 9.21.907.329 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 232.419 MiB) 9.21.915.942 I slot launch_slot_: id 2 | task 8460 | processing task, is_child = 0 9.22.651.723 I slot print_timing: id 0 | task 8453 | prompt eval time = 5522.22 ms / 890 tokens ( 6.20 ms per token, 161.17 tokens per second) 9.22.651.726 I slot print_timing: id 0 | task 8453 | eval time = 746.70 ms / 2 tokens ( 746.70 ms per token, 1.34 tokens per second) 9.22.651.727 I slot print_timing: id 0 | task 8453 | total time = 6268.91 ms / 892 tokens 9.22.651.727 I slot print_timing: id 0 | task 8453 | graphs reused = 7277 9.22.651.728 I slot print_timing: id 0 | task 8453 | graph reallocs = 0 / 0 (same size) / (changed size) 9.22.651.803 I slot release: id 0 | task 8453 | stop processing: n_tokens = 900, truncated = 0 9.22.652.984 I slot print_timing: id 1 | task 8454 | prompt eval time = 5523.17 ms / 894 tokens ( 6.18 ms per token, 161.86 tokens per second) 9.22.652.989 I slot print_timing: id 1 | task 8454 | eval time = 746.83 ms / 2 tokens ( 746.83 ms per token, 1.34 tokens per second) 9.22.652.991 I slot print_timing: id 1 | task 8454 | total time = 6270.01 ms / 896 tokens 9.22.652.991 I slot print_timing: id 1 | task 8454 | graphs reused = 7277 9.22.652.992 I slot print_timing: id 1 | task 8454 | graph reallocs = 0 / 0 (same size) / (changed size) 9.22.653.033 I slot release: id 1 | task 8454 | stop processing: n_tokens = 904, truncated = 0 9.22.654.216 I slot print_timing: id 3 | task 8455 | prompt eval time = 5522.29 ms / 921 tokens ( 6.00 ms per token, 166.78 tokens per second) 9.22.654.218 I slot print_timing: id 3 | task 8455 | eval time = 746.98 ms / 2 tokens ( 746.98 ms per token, 1.34 tokens per second) 9.22.654.218 I slot print_timing: id 3 | task 8455 | total time = 6269.27 ms / 923 tokens 9.22.654.218 I slot print_timing: id 3 | task 8455 | graphs reused = 7277 9.22.654.219 I slot print_timing: id 3 | task 8455 | graph reallocs = 0 / 0 (same size) / (changed size) 9.22.654.246 I slot release: id 3 | task 8455 | stop processing: n_tokens = 931, truncated = 0 9.23.420.661 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.897 9.23.420.740 I slot launch_slot_: id 0 | task 8464 | processing task, is_child = 0 9.23.420.823 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 250.844 MiB) 9.23.676.225 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 254.430 MiB) 9.23.683.278 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 331509648875 9.23.683.437 I slot launch_slot_: id 1 | task 8465 | processing task, is_child = 0 9.23.683.513 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 331509650088 9.23.683.632 I slot launch_slot_: id 3 | task 8466 | processing task, is_child = 0 9.27.859.465 I slot print_timing: id 2 | task 8460 | prompt eval time = 4552.58 ms / 894 tokens ( 5.09 ms per token, 196.37 tokens per second) 9.27.859.469 I slot print_timing: id 2 | task 8460 | eval time = 1390.92 ms / 2 tokens ( 1390.92 ms per token, 0.72 tokens per second) 9.27.859.469 I slot print_timing: id 2 | task 8460 | total time = 5943.50 ms / 896 tokens 9.27.859.470 I slot print_timing: id 2 | task 8460 | graphs reused = 7277 9.27.859.470 I slot print_timing: id 2 | task 8460 | graph reallocs = 0 / 0 (same size) / (changed size) 9.27.859.547 I slot release: id 2 | task 8460 | stop processing: n_tokens = 904, truncated = 0 9.27.859.574 I slot print_timing: id 1 | task 8465 | prompt processing, n_tokens = 1051, progress = 0.86, t = 4.17 s / 251.93 tokens per second 9.27.862.046 I slot print_timing: id 3 | task 8466 | prompt processing, n_tokens = 1051, progress = 0.87, t = 4.17 s / 252.05 tokens per second 9.28.579.850 I slot print_timing: id 0 | task 8464 | prompt eval time = 4174.66 ms / 83 tokens ( 50.30 ms per token, 19.88 tokens per second) 9.28.579.854 I slot print_timing: id 0 | task 8464 | eval time = 721.53 ms / 2 tokens ( 721.53 ms per token, 1.39 tokens per second) 9.28.579.854 I slot print_timing: id 0 | task 8464 | total time = 4896.19 ms / 85 tokens 9.28.579.855 I slot print_timing: id 0 | task 8464 | graphs reused = 7277 9.28.579.856 I slot print_timing: id 0 | task 8464 | graph reallocs = 0 / 0 (same size) / (changed size) 9.28.579.942 I slot release: id 0 | task 8464 | stop processing: n_tokens = 891, truncated = 0 9.28.579.961 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 331514855389 9.28.580.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 302.916 MiB) 9.28.587.720 I slot launch_slot_: id 2 | task 8470 | processing task, is_child = 0 9.28.587.799 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.719 MiB) 9.28.594.714 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 331515575784 9.28.594.848 I slot launch_slot_: id 0 | task 8471 | processing task, is_child = 0 9.31.366.582 I slot print_timing: id 1 | task 8465 | prompt processing, n_tokens = 1222, progress = 1.00, t = 4.89 s / 249.73 tokens per second 9.32.321.270 I slot print_timing: id 3 | task 8466 | prompt processing, n_tokens = 1211, progress = 1.00, t = 4.89 s / 247.58 tokens per second 9.33.981.551 I slot print_timing: id 0 | task 8471 | prompt processing, n_tokens = 2146, progress = 0.81, t = 5.38 s / 398.58 tokens per second 9.35.028.211 I slot print_timing: id 1 | task 8465 | prompt eval time = 10294.92 ms / 1226 tokens ( 8.40 ms per token, 119.09 tokens per second) 9.35.028.213 I slot print_timing: id 1 | task 8465 | eval time = 1047.94 ms / 2 tokens ( 1047.94 ms per token, 0.95 tokens per second) 9.35.028.214 I slot print_timing: id 1 | task 8465 | total time = 11342.85 ms / 1228 tokens 9.35.028.215 I slot print_timing: id 1 | task 8465 | graphs reused = 7277 9.35.028.215 I slot print_timing: id 1 | task 8465 | graph reallocs = 0 / 0 (same size) / (changed size) 9.35.028.275 I slot release: id 1 | task 8465 | stop processing: n_tokens = 1236, truncated = 0 9.35.029.443 I slot print_timing: id 3 | task 8466 | prompt eval time = 10294.20 ms / 1215 tokens ( 8.47 ms per token, 118.03 tokens per second) 9.35.029.452 I slot print_timing: id 3 | task 8466 | eval time = 1047.89 ms / 2 tokens ( 1047.89 ms per token, 0.95 tokens per second) 9.35.029.453 I slot print_timing: id 3 | task 8466 | total time = 11342.10 ms / 1217 tokens 9.35.029.453 I slot print_timing: id 3 | task 8466 | graphs reused = 7277 9.35.029.453 I slot print_timing: id 3 | task 8466 | graph reallocs = 0 / 0 (same size) / (changed size) 9.35.029.498 I slot release: id 3 | task 8466 | stop processing: n_tokens = 1225, truncated = 0 9.35.029.514 I slot print_timing: id 0 | task 8471 | prompt processing, n_tokens = 2353, progress = 0.88, t = 6.43 s / 365.81 tokens per second 9.35.667.853 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1236, t_last = 331522024117 9.35.667.968 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 233.966 MiB) 9.36.155.121 I slot launch_slot_: id 1 | task 8476 | processing task, is_child = 0 9.36.155.213 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 251.828 MiB) 9.36.161.683 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1225, t_last = 331522025340 9.36.161.821 I slot launch_slot_: id 3 | task 8477 | processing task, is_child = 0 9.36.161.828 I slot print_timing: id 0 | task 8471 | prompt processing, n_tokens = 2658, progress = 1.00, t = 7.07 s / 375.80 tokens per second 9.39.947.583 I slot print_timing: id 1 | task 8476 | prompt processing, n_tokens = 2044, progress = 0.73, t = 3.78 s / 540.73 tokens per second 9.39.947.606 I slot print_timing: id 2 | task 8470 | prompt processing, n_tokens = 1276, progress = 1.00, t = 3.35 s / 381.26 tokens per second 9.43.837.602 I slot print_timing: id 0 | task 8471 | prompt eval time = 11352.71 ms / 2662 tokens ( 4.26 ms per token, 234.48 tokens per second) 9.43.837.606 I slot print_timing: id 0 | task 8471 | eval time = 3890.03 ms / 2 tokens ( 3890.03 ms per token, 0.26 tokens per second) 9.43.837.606 I slot print_timing: id 0 | task 8471 | total time = 15242.74 ms / 2664 tokens 9.43.837.607 I slot print_timing: id 0 | task 8471 | graphs reused = 7277 9.43.837.607 I slot print_timing: id 0 | task 8471 | graph reallocs = 0 / 0 (same size) / (changed size) 9.43.837.790 I slot release: id 0 | task 8471 | stop processing: n_tokens = 2672, truncated = 0 9.43.839.309 I slot print_timing: id 1 | task 8476 | prompt processing, n_tokens = 2301, progress = 0.82, t = 7.67 s / 300.00 tokens per second 9.43.841.481 I slot print_timing: id 3 | task 8477 | prompt processing, n_tokens = 1786, progress = 0.70, t = 3.88 s / 459.72 tokens per second 9.44.574.876 I slot print_timing: id 2 | task 8470 | prompt eval time = 11518.22 ms / 1280 tokens ( 9.00 ms per token, 111.13 tokens per second) 9.44.574.879 I slot print_timing: id 2 | task 8470 | eval time = 735.59 ms / 2 tokens ( 735.59 ms per token, 1.36 tokens per second) 9.44.574.879 I slot print_timing: id 2 | task 8470 | total time = 12253.81 ms / 1282 tokens 9.44.574.880 I slot print_timing: id 2 | task 8470 | graphs reused = 7277 9.44.574.880 I slot print_timing: id 2 | task 8470 | graph reallocs = 0 / 0 (same size) / (changed size) 9.44.574.940 I slot release: id 2 | task 8470 | stop processing: n_tokens = 1290, truncated = 0 9.44.574.966 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.897 9.44.575.089 I slot launch_slot_: id 0 | task 8481 | processing task, is_child = 0 9.44.575.237 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 303.408 MiB) 9.44.586.133 I slot print_timing: id 1 | task 8476 | prompt processing, n_tokens = 2353, progress = 0.84, t = 8.41 s / 279.87 tokens per second 9.44.587.929 I slot print_timing: id 3 | task 8477 | prompt processing, n_tokens = 2052, progress = 0.80, t = 4.62 s / 443.94 tokens per second 9.46.154.885 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1290, t_last = 331531570782 9.46.155.063 I slot launch_slot_: id 2 | task 8483 | processing task, is_child = 0 9.46.772.215 I slot print_timing: id 1 | task 8476 | prompt processing, n_tokens = 2813, progress = 1.00, t = 9.99 s / 281.62 tokens per second 9.46.775.535 I slot print_timing: id 3 | task 8477 | prompt processing, n_tokens = 2353, progress = 0.92, t = 6.20 s / 379.31 tokens per second 9.49.614.830 I slot print_timing: id 3 | task 8477 | prompt processing, n_tokens = 2564, progress = 1.00, t = 9.66 s / 265.49 tokens per second 9.50.069.172 I slot print_timing: id 0 | task 8481 | prompt eval time = 5025.76 ms / 340 tokens ( 14.78 ms per token, 67.65 tokens per second) 9.50.069.177 I slot print_timing: id 0 | task 8481 | eval time = 459.07 ms / 2 tokens ( 459.07 ms per token, 2.18 tokens per second) 9.50.069.178 I slot print_timing: id 0 | task 8481 | total time = 5484.83 ms / 342 tokens 9.50.069.178 I slot print_timing: id 0 | task 8481 | graphs reused = 7277 9.50.069.179 I slot print_timing: id 0 | task 8481 | graph reallocs = 0 / 0 (same size) / (changed size) 9.50.069.316 I slot release: id 0 | task 8481 | stop processing: n_tokens = 2739, truncated = 0 9.50.070.504 I slot print_timing: id 1 | task 8476 | prompt eval time = 13444.94 ms / 2817 tokens ( 4.77 ms per token, 209.52 tokens per second) 9.50.070.506 I slot print_timing: id 1 | task 8476 | eval time = 459.16 ms / 2 tokens ( 459.16 ms per token, 2.18 tokens per second) 9.50.070.507 I slot print_timing: id 1 | task 8476 | total time = 13904.09 ms / 2819 tokens 9.50.070.507 I slot print_timing: id 1 | task 8476 | graphs reused = 7277 9.50.070.507 I slot print_timing: id 1 | task 8476 | graph reallocs = 0 / 0 (same size) / (changed size) 9.50.070.596 I slot release: id 1 | task 8476 | stop processing: n_tokens = 2827, truncated = 0 9.50.071.978 I slot print_timing: id 2 | task 8483 | prompt processing, n_tokens = 1467, progress = 0.81, t = 3.29 s / 445.52 tokens per second 9.50.766.922 I slot print_timing: id 3 | task 8477 | prompt eval time = 10120.43 ms / 2568 tokens ( 3.94 ms per token, 253.74 tokens per second) 9.50.766.926 I slot print_timing: id 3 | task 8477 | eval time = 694.95 ms / 2 tokens ( 694.95 ms per token, 1.44 tokens per second) 9.50.766.926 I slot print_timing: id 3 | task 8477 | total time = 10815.38 ms / 2570 tokens 9.50.766.926 I slot print_timing: id 3 | task 8477 | graphs reused = 7277 9.50.766.931 I slot print_timing: id 3 | task 8477 | graph reallocs = 0 / 0 (same size) / (changed size) 9.50.767.084 I slot release: id 3 | task 8477 | stop processing: n_tokens = 2578, truncated = 0 9.50.767.104 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2739, t_last = 331537065160 9.50.767.310 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 290.012 MiB) 9.50.787.059 I slot launch_slot_: id 0 | task 8487 | processing task, is_child = 0 9.50.787.200 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.156 MiB) 9.50.802.620 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 241.842 MiB) 9.50.802.625 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 235.232 MiB) 9.50.817.254 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2827, t_last = 331537066439 9.50.817.463 I slot launch_slot_: id 1 | task 8488 | processing task, is_child = 0 9.50.817.594 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2578, t_last = 331537762928 9.50.817.758 I slot launch_slot_: id 3 | task 8489 | processing task, is_child = 0 9.53.841.967 I slot print_timing: id 0 | task 8487 | prompt processing, n_tokens = 1467, progress = 0.71, t = 3.02 s / 485.09 tokens per second 9.54.561.955 I slot print_timing: id 1 | task 8488 | prompt processing, n_tokens = 581, progress = 0.31, t = 3.02 s / 192.14 tokens per second 9.54.561.980 I slot print_timing: id 2 | task 8483 | prompt processing, n_tokens = 1806, progress = 1.00, t = 3.99 s / 452.57 tokens per second 9.58.446.913 I slot print_timing: id 0 | task 8487 | prompt processing, n_tokens = 1565, progress = 0.75, t = 7.63 s / 205.17 tokens per second 9.58.450.731 I slot print_timing: id 1 | task 8488 | prompt processing, n_tokens = 1354, progress = 0.73, t = 7.63 s / 177.51 tokens per second 9.58.452.528 I slot print_timing: id 3 | task 8489 | prompt processing, n_tokens = 1173, progress = 0.62, t = 3.88 s / 302.28 tokens per second 10.00.189.205 I slot print_timing: id 2 | task 8483 | prompt eval time = 11671.57 ms / 1810 tokens ( 6.45 ms per token, 155.08 tokens per second) 10.00.189.209 I slot print_timing: id 2 | task 8483 | eval time = 1742.34 ms / 2 tokens ( 1742.34 ms per token, 0.57 tokens per second) 10.00.189.210 I slot print_timing: id 2 | task 8483 | total time = 13413.91 ms / 1812 tokens 10.00.189.210 I slot print_timing: id 2 | task 8483 | graphs reused = 7277 10.00.189.210 I slot print_timing: id 2 | task 8483 | graph reallocs = 0 / 0 (same size) / (changed size) 10.00.189.358 I slot release: id 2 | task 8483 | stop processing: n_tokens = 1820, truncated = 0 10.00.189.386 I slot print_timing: id 0 | task 8487 | prompt processing, n_tokens = 2077, progress = 1.00, t = 9.37 s / 221.66 tokens per second 10.00.193.675 I slot print_timing: id 1 | task 8488 | prompt processing, n_tokens = 1467, progress = 0.79, t = 9.37 s / 156.56 tokens per second 10.00.195.461 I slot print_timing: id 3 | task 8489 | prompt processing, n_tokens = 1368, progress = 0.73, t = 5.62 s / 243.29 tokens per second 10.01.273.582 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.756 (> 0.100 thold), f_keep = 0.831 10.01.273.746 I slot launch_slot_: id 2 | task 8494 | processing task, is_child = 0 10.01.273.766 I slot print_timing: id 1 | task 8488 | prompt processing, n_tokens = 1866, progress = 1.00, t = 10.45 s / 178.49 tokens per second 10.01.279.117 I slot print_timing: id 3 | task 8489 | prompt processing, n_tokens = 1467, progress = 0.78, t = 6.71 s / 218.72 tokens per second 10.03.134.349 I slot print_timing: id 0 | task 8487 | prompt eval time = 10455.80 ms / 2081 tokens ( 5.02 ms per token, 199.03 tokens per second) 10.03.134.352 I slot print_timing: id 0 | task 8487 | eval time = 1860.78 ms / 2 tokens ( 1860.78 ms per token, 0.54 tokens per second) 10.03.134.353 I slot print_timing: id 0 | task 8487 | total time = 12316.58 ms / 2083 tokens 10.03.134.354 I slot print_timing: id 0 | task 8487 | graphs reused = 7277 10.03.134.354 I slot print_timing: id 0 | task 8487 | graph reallocs = 0 / 0 (same size) / (changed size) 10.03.134.509 I slot release: id 0 | task 8487 | stop processing: n_tokens = 2091, truncated = 0 10.03.139.145 I slot print_timing: id 3 | task 8489 | prompt processing, n_tokens = 1880, progress = 1.00, t = 8.57 s / 219.42 tokens per second 10.03.214.258 I slot print_timing: id 1 | task 8488 | prompt eval time = 12317.60 ms / 1870 tokens ( 6.59 ms per token, 151.82 tokens per second) 10.03.214.263 I slot print_timing: id 1 | task 8488 | eval time = 78.52 ms / 2 tokens ( 78.52 ms per token, 12.74 tokens per second) 10.03.214.264 I slot print_timing: id 1 | task 8488 | total time = 12396.12 ms / 1872 tokens 10.03.214.264 I slot print_timing: id 1 | task 8488 | graphs reused = 7277 10.03.214.265 I slot print_timing: id 1 | task 8488 | graph reallocs = 0 / 0 (same size) / (changed size) 10.03.214.348 I slot release: id 1 | task 8488 | stop processing: n_tokens = 1880, truncated = 0 10.03.217.019 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.834 (> 0.100 thold), f_keep = 0.723 10.03.217.114 I slot launch_slot_: id 0 | task 8497 | processing task, is_child = 0 10.03.217.234 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 240.014 MiB) 10.03.224.404 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1880, t_last = 331550210190 10.03.224.556 I slot launch_slot_: id 1 | task 8498 | processing task, is_child = 0 10.03.694.022 I slot print_timing: id 2 | task 8494 | prompt eval time = 1938.63 ms / 488 tokens ( 3.97 ms per token, 251.72 tokens per second) 10.03.694.024 I slot print_timing: id 2 | task 8494 | eval time = 478.29 ms / 2 tokens ( 478.29 ms per token, 2.09 tokens per second) 10.03.694.025 I slot print_timing: id 2 | task 8494 | total time = 2416.92 ms / 490 tokens 10.03.694.025 I slot print_timing: id 2 | task 8494 | graphs reused = 7277 10.03.694.026 I slot print_timing: id 2 | task 8494 | graph reallocs = 0 / 0 (same size) / (changed size) 10.03.694.115 I slot release: id 2 | task 8494 | stop processing: n_tokens = 2001, truncated = 0 10.03.695.254 I slot print_timing: id 3 | task 8489 | prompt eval time = 8651.73 ms / 1884 tokens ( 4.59 ms per token, 217.76 tokens per second) 10.03.695.256 I slot print_timing: id 3 | task 8489 | eval time = 478.24 ms / 2 tokens ( 478.24 ms per token, 2.09 tokens per second) 10.03.695.256 I slot print_timing: id 3 | task 8489 | total time = 9129.97 ms / 1886 tokens 10.03.695.256 I slot print_timing: id 3 | task 8489 | graphs reused = 7277 10.03.695.257 I slot print_timing: id 3 | task 8489 | graph reallocs = 0 / 0 (same size) / (changed size) 10.03.695.310 I slot release: id 3 | task 8489 | stop processing: n_tokens = 1894, truncated = 0 10.04.944.894 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2001, t_last = 331550689958 10.04.945.048 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.965 MiB) 10.05.140.102 I slot launch_slot_: id 2 | task 8501 | processing task, is_child = 0 10.05.140.223 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.508 MiB) 10.05.153.236 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1894, t_last = 331550691152 10.05.153.391 I slot launch_slot_: id 3 | task 8502 | processing task, is_child = 0 10.06.254.993 I slot print_timing: id 1 | task 8498 | prompt processing, n_tokens = 712, progress = 0.99, t = 3.03 s / 235.27 tokens per second 10.07.730.311 I slot print_timing: id 0 | task 8497 | prompt eval time = 3030.42 ms / 338 tokens ( 8.97 ms per token, 111.54 tokens per second) 10.07.730.314 I slot print_timing: id 0 | task 8497 | eval time = 1475.33 ms / 2 tokens ( 1475.33 ms per token, 0.68 tokens per second) 10.07.730.314 I slot print_timing: id 0 | task 8497 | total time = 4505.74 ms / 340 tokens 10.07.730.315 I slot print_timing: id 0 | task 8497 | graphs reused = 7277 10.07.730.316 I slot print_timing: id 0 | task 8497 | graph reallocs = 0 / 0 (same size) / (changed size) 10.07.730.444 I slot release: id 0 | task 8497 | stop processing: n_tokens = 1814, truncated = 0 10.08.301.391 I slot print_timing: id 1 | task 8498 | prompt eval time = 4504.16 ms / 716 tokens ( 6.29 ms per token, 158.96 tokens per second) 10.08.301.394 I slot print_timing: id 1 | task 8498 | eval time = 569.67 ms / 2 tokens ( 569.67 ms per token, 1.76 tokens per second) 10.08.301.394 I slot print_timing: id 1 | task 8498 | total time = 5073.83 ms / 718 tokens 10.08.301.394 I slot print_timing: id 1 | task 8498 | graphs reused = 7277 10.08.301.395 I slot print_timing: id 1 | task 8498 | graph reallocs = 0 / 0 (same size) / (changed size) 10.08.301.427 I slot release: id 1 | task 8498 | stop processing: n_tokens = 726, truncated = 0 10.08.301.435 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.879 10.08.301.497 I slot launch_slot_: id 1 | task 8506 | processing task, is_child = 0 10.08.301.626 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.967 MiB) 10.08.315.860 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1814, t_last = 331554726288 10.08.316.012 I slot launch_slot_: id 0 | task 8507 | processing task, is_child = 0 10.08.317.975 I slot print_timing: id 2 | task 8501 | prompt processing, n_tokens = 731, progress = 0.99, t = 3.14 s / 232.55 tokens per second 10.08.319.729 I slot print_timing: id 3 | task 8502 | prompt processing, n_tokens = 744, progress = 0.99, t = 3.14 s / 236.71 tokens per second 10.09.739.557 I slot print_timing: id 2 | task 8501 | prompt eval time = 3815.70 ms / 735 tokens ( 5.19 ms per token, 192.63 tokens per second) 10.09.739.561 I slot print_timing: id 2 | task 8501 | eval time = 766.91 ms / 2 tokens ( 766.91 ms per token, 1.30 tokens per second) 10.09.739.562 I slot print_timing: id 2 | task 8501 | total time = 4582.60 ms / 737 tokens 10.09.739.562 I slot print_timing: id 2 | task 8501 | graphs reused = 7277 10.09.739.563 I slot print_timing: id 2 | task 8501 | graph reallocs = 0 / 0 (same size) / (changed size) 10.09.739.621 I slot release: id 2 | task 8501 | stop processing: n_tokens = 745, truncated = 0 10.09.740.774 I slot print_timing: id 3 | task 8502 | prompt eval time = 3816.66 ms / 748 tokens ( 5.10 ms per token, 195.98 tokens per second) 10.09.740.778 I slot print_timing: id 3 | task 8502 | eval time = 766.86 ms / 2 tokens ( 766.86 ms per token, 1.30 tokens per second) 10.09.740.779 I slot print_timing: id 3 | task 8502 | total time = 4583.52 ms / 750 tokens 10.09.740.779 I slot print_timing: id 3 | task 8502 | graphs reused = 7277 10.09.740.779 I slot print_timing: id 3 | task 8502 | graph reallocs = 0 / 0 (same size) / (changed size) 10.09.740.808 I slot release: id 3 | task 8502 | stop processing: n_tokens = 758, truncated = 0 10.10.021.204 I slot print_timing: id 1 | task 8506 | prompt eval time = 1422.11 ms / 83 tokens ( 17.13 ms per token, 58.36 tokens per second) 10.10.021.208 I slot print_timing: id 1 | task 8506 | eval time = 282.80 ms / 2 tokens ( 282.80 ms per token, 3.54 tokens per second) 10.10.021.208 I slot print_timing: id 1 | task 8506 | total time = 1704.91 ms / 85 tokens 10.10.021.209 I slot print_timing: id 1 | task 8506 | graphs reused = 7277 10.10.021.209 I slot print_timing: id 1 | task 8506 | graph reallocs = 0 / 0 (same size) / (changed size) 10.10.021.253 I slot release: id 1 | task 8506 | stop processing: n_tokens = 722, truncated = 0 10.10.021.265 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 745, t_last = 331556735463 10.10.021.367 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 262.519 MiB) 10.10.030.074 I slot launch_slot_: id 2 | task 8511 | processing task, is_child = 0 10.10.030.140 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.886 MiB) 10.10.036.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 223.558 MiB) 10.10.041.864 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 758, t_last = 331556736650 10.10.041.985 I slot launch_slot_: id 3 | task 8512 | processing task, is_child = 0 10.10.042.046 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 722, t_last = 331557017095 10.10.042.138 I slot launch_slot_: id 1 | task 8513 | processing task, is_child = 0 10.14.264.034 I slot print_timing: id 0 | task 8507 | prompt eval time = 3758.68 ms / 730 tokens ( 5.15 ms per token, 194.22 tokens per second) 10.14.264.041 I slot print_timing: id 0 | task 8507 | eval time = 2189.31 ms / 2 tokens ( 2189.31 ms per token, 0.46 tokens per second) 10.14.264.041 I slot print_timing: id 0 | task 8507 | total time = 5948.00 ms / 732 tokens 10.14.264.043 I slot print_timing: id 0 | task 8507 | graphs reused = 7277 10.14.264.043 I slot print_timing: id 0 | task 8507 | graph reallocs = 0 / 0 (same size) / (changed size) 10.14.264.103 I slot release: id 0 | task 8507 | stop processing: n_tokens = 740, truncated = 0 10.14.264.135 I slot print_timing: id 1 | task 8513 | prompt processing, n_tokens = 672, progress = 0.84, t = 4.22 s / 159.28 tokens per second 10.14.267.005 I slot print_timing: id 2 | task 8511 | prompt processing, n_tokens = 628, progress = 0.79, t = 4.22 s / 148.86 tokens per second 10.14.268.968 I slot print_timing: id 3 | task 8512 | prompt processing, n_tokens = 891, progress = 0.86, t = 4.22 s / 211.21 tokens per second 10.15.127.870 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 331561259945 10.15.127.965 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 231.434 MiB) 10.15.186.038 I slot launch_slot_: id 0 | task 8517 | processing task, is_child = 0 10.15.186.220 I slot print_timing: id 1 | task 8513 | prompt processing, n_tokens = 799, progress = 1.00, t = 5.08 s / 157.16 tokens per second 10.15.187.984 I slot print_timing: id 2 | task 8511 | prompt processing, n_tokens = 792, progress = 1.00, t = 5.08 s / 155.79 tokens per second 10.15.189.746 I slot print_timing: id 3 | task 8512 | prompt processing, n_tokens = 1039, progress = 1.00, t = 5.08 s / 204.38 tokens per second 10.16.560.616 I slot print_timing: id 1 | task 8513 | prompt eval time = 5723.63 ms / 803 tokens ( 7.13 ms per token, 140.30 tokens per second) 10.16.560.619 I slot print_timing: id 1 | task 8513 | eval time = 793.05 ms / 2 tokens ( 793.05 ms per token, 1.26 tokens per second) 10.16.560.620 I slot print_timing: id 1 | task 8513 | total time = 6516.67 ms / 805 tokens 10.16.560.620 I slot print_timing: id 1 | task 8513 | graphs reused = 7277 10.16.560.620 I slot print_timing: id 1 | task 8513 | graph reallocs = 0 / 0 (same size) / (changed size) 10.16.560.697 I slot release: id 1 | task 8513 | stop processing: n_tokens = 813, truncated = 0 10.16.561.857 I slot print_timing: id 2 | task 8511 | prompt eval time = 5724.63 ms / 796 tokens ( 7.19 ms per token, 139.05 tokens per second) 10.16.561.862 I slot print_timing: id 2 | task 8511 | eval time = 793.12 ms / 2 tokens ( 793.12 ms per token, 1.26 tokens per second) 10.16.561.862 I slot print_timing: id 2 | task 8511 | total time = 6517.74 ms / 798 tokens 10.16.561.862 I slot print_timing: id 2 | task 8511 | graphs reused = 7277 10.16.561.863 I slot print_timing: id 2 | task 8511 | graph reallocs = 0 / 0 (same size) / (changed size) 10.16.561.906 I slot release: id 2 | task 8511 | stop processing: n_tokens = 806, truncated = 0 10.16.563.073 I slot print_timing: id 3 | task 8512 | prompt eval time = 5725.74 ms / 1043 tokens ( 5.49 ms per token, 182.16 tokens per second) 10.16.563.075 I slot print_timing: id 3 | task 8512 | eval time = 793.05 ms / 2 tokens ( 793.05 ms per token, 1.26 tokens per second) 10.16.563.076 I slot print_timing: id 3 | task 8512 | total time = 6518.80 ms / 1045 tokens 10.16.563.076 I slot print_timing: id 3 | task 8512 | graphs reused = 7277 10.16.563.076 I slot print_timing: id 3 | task 8512 | graph reallocs = 0 / 0 (same size) / (changed size) 10.16.563.142 I slot release: id 3 | task 8512 | stop processing: n_tokens = 1053, truncated = 0 10.16.857.526 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 813, t_last = 331563556539 10.16.857.612 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 235.513 MiB) 10.16.863.205 I slot launch_slot_: id 1 | task 8522 | processing task, is_child = 0 10.16.863.276 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.465 MiB) 10.16.868.782 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.787 MiB) 10.16.875.055 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 331563557748 10.16.875.181 I slot launch_slot_: id 2 | task 8523 | processing task, is_child = 0 10.16.875.253 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1053, t_last = 331563558984 10.16.875.372 I slot launch_slot_: id 3 | task 8524 | processing task, is_child = 0 10.18.816.699 I slot print_timing: id 0 | task 8517 | prompt eval time = 1671.48 ms / 793 tokens ( 2.11 ms per token, 474.43 tokens per second) 10.18.816.702 I slot print_timing: id 0 | task 8517 | eval time = 1959.17 ms / 2 tokens ( 1959.17 ms per token, 0.51 tokens per second) 10.18.816.702 I slot print_timing: id 0 | task 8517 | total time = 3630.65 ms / 795 tokens 10.18.816.703 I slot print_timing: id 0 | task 8517 | graphs reused = 7277 10.18.816.703 I slot print_timing: id 0 | task 8517 | graph reallocs = 0 / 0 (same size) / (changed size) 10.18.816.750 I slot release: id 0 | task 8517 | stop processing: n_tokens = 803, truncated = 0 10.20.939.113 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 331565812592 10.20.939.201 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.073 MiB) 10.20.976.932 I slot launch_slot_: id 0 | task 8527 | processing task, is_child = 0 10.20.977.120 I slot print_timing: id 1 | task 8522 | prompt processing, n_tokens = 712, progress = 0.80, t = 4.06 s / 175.21 tokens per second 10.20.978.778 I slot print_timing: id 2 | task 8523 | prompt processing, n_tokens = 712, progress = 0.86, t = 4.06 s / 175.22 tokens per second 10.20.980.473 I slot print_timing: id 3 | task 8524 | prompt processing, n_tokens = 712, progress = 0.85, t = 4.06 s / 175.22 tokens per second 10.22.544.468 I slot print_timing: id 1 | task 8522 | prompt processing, n_tokens = 889, progress = 1.00, t = 5.63 s / 157.84 tokens per second 10.22.548.264 I slot print_timing: id 2 | task 8523 | prompt processing, n_tokens = 824, progress = 1.00, t = 5.63 s / 146.30 tokens per second 10.22.550.742 I slot print_timing: id 3 | task 8524 | prompt processing, n_tokens = 832, progress = 1.00, t = 5.63 s / 147.73 tokens per second 10.23.674.111 I slot print_timing: id 1 | task 8522 | prompt eval time = 6382.38 ms / 893 tokens ( 7.15 ms per token, 139.92 tokens per second) 10.23.674.114 I slot print_timing: id 1 | task 8522 | eval time = 416.35 ms / 2 tokens ( 416.35 ms per token, 2.40 tokens per second) 10.23.674.114 I slot print_timing: id 1 | task 8522 | total time = 6798.73 ms / 895 tokens 10.23.674.115 I slot print_timing: id 1 | task 8522 | graphs reused = 7277 10.23.674.115 I slot print_timing: id 1 | task 8522 | graph reallocs = 0 / 0 (same size) / (changed size) 10.23.674.160 I slot release: id 1 | task 8522 | stop processing: n_tokens = 903, truncated = 0 10.23.675.264 I slot print_timing: id 2 | task 8523 | prompt eval time = 6383.39 ms / 828 tokens ( 7.71 ms per token, 129.71 tokens per second) 10.23.675.266 I slot print_timing: id 2 | task 8523 | eval time = 416.31 ms / 2 tokens ( 416.31 ms per token, 2.40 tokens per second) 10.23.675.266 I slot print_timing: id 2 | task 8523 | total time = 6799.69 ms / 830 tokens 10.23.675.266 I slot print_timing: id 2 | task 8523 | graphs reused = 7277 10.23.675.267 I slot print_timing: id 2 | task 8523 | graph reallocs = 0 / 0 (same size) / (changed size) 10.23.675.292 I slot release: id 2 | task 8523 | stop processing: n_tokens = 838, truncated = 0 10.23.676.398 I slot print_timing: id 3 | task 8524 | prompt eval time = 6384.41 ms / 836 tokens ( 7.64 ms per token, 130.94 tokens per second) 10.23.676.399 I slot print_timing: id 3 | task 8524 | eval time = 416.25 ms / 2 tokens ( 416.25 ms per token, 2.40 tokens per second) 10.23.676.400 I slot print_timing: id 3 | task 8524 | total time = 6800.67 ms / 838 tokens 10.23.676.400 I slot print_timing: id 3 | task 8524 | graphs reused = 7277 10.23.676.400 I slot print_timing: id 3 | task 8524 | graph reallocs = 0 / 0 (same size) / (changed size) 10.23.676.432 I slot release: id 3 | task 8524 | stop processing: n_tokens = 846, truncated = 0 10.23.714.198 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 331570670002 10.23.714.280 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.917 MiB) 10.23.720.923 I slot launch_slot_: id 1 | task 8532 | processing task, is_child = 0 10.23.720.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 241.139 MiB) 10.23.726.610 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 241.420 MiB) 10.23.732.189 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.869 (> 0.100 thold), f_keep = 0.893 10.23.732.239 I slot launch_slot_: id 2 | task 8533 | processing task, is_child = 0 10.23.732.307 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 846, t_last = 331570672274 10.23.732.401 I slot launch_slot_: id 3 | task 8534 | processing task, is_child = 0 10.24.939.353 I slot print_timing: id 0 | task 8527 | prompt eval time = 2737.25 ms / 899 tokens ( 3.04 ms per token, 328.43 tokens per second) 10.24.939.356 I slot print_timing: id 0 | task 8527 | eval time = 1225.15 ms / 2 tokens ( 1225.15 ms per token, 0.82 tokens per second) 10.24.939.357 I slot print_timing: id 0 | task 8527 | total time = 3962.40 ms / 901 tokens 10.24.939.357 I slot print_timing: id 0 | task 8527 | graphs reused = 7277 10.24.939.357 I slot print_timing: id 0 | task 8527 | graph reallocs = 0 / 0 (same size) / (changed size) 10.24.939.409 I slot release: id 0 | task 8527 | stop processing: n_tokens = 909, truncated = 0 10.26.500.543 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 909, t_last = 331571935251 10.26.500.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 243.671 MiB) 10.26.510.518 I slot launch_slot_: id 0 | task 8537 | processing task, is_child = 0 10.27.674.403 I slot print_timing: id 2 | task 8533 | prompt eval time = 2767.92 ms / 113 tokens ( 24.49 ms per token, 40.82 tokens per second) 10.27.674.406 I slot print_timing: id 2 | task 8533 | eval time = 1173.87 ms / 2 tokens ( 1173.87 ms per token, 0.85 tokens per second) 10.27.674.406 I slot print_timing: id 2 | task 8533 | total time = 3941.79 ms / 115 tokens 10.27.674.407 I slot print_timing: id 2 | task 8533 | graphs reused = 7277 10.27.674.407 I slot print_timing: id 2 | task 8533 | graph reallocs = 0 / 0 (same size) / (changed size) 10.27.674.474 I slot release: id 2 | task 8533 | stop processing: n_tokens = 862, truncated = 0 10.27.677.246 I slot print_timing: id 1 | task 8532 | prompt processing, n_tokens = 678, progress = 0.99, t = 3.94 s / 172.04 tokens per second 10.27.679.293 I slot print_timing: id 3 | task 8534 | prompt processing, n_tokens = 818, progress = 1.00, t = 3.94 s / 207.67 tokens per second 10.28.454.196 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 862, t_last = 331574670316 10.28.454.323 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 298.767 MiB) 10.28.463.462 I slot launch_slot_: id 2 | task 8540 | processing task, is_child = 0 10.29.280.522 I slot print_timing: id 1 | task 8532 | prompt eval time = 4720.49 ms / 682 tokens ( 6.92 ms per token, 144.48 tokens per second) 10.29.280.524 I slot print_timing: id 1 | task 8532 | eval time = 827.62 ms / 2 tokens ( 827.62 ms per token, 1.21 tokens per second) 10.29.280.525 I slot print_timing: id 1 | task 8532 | total time = 5548.11 ms / 684 tokens 10.29.280.525 I slot print_timing: id 1 | task 8532 | graphs reused = 7277 10.29.280.526 I slot print_timing: id 1 | task 8532 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.280.568 I slot release: id 1 | task 8532 | stop processing: n_tokens = 692, truncated = 0 10.29.281.688 I slot print_timing: id 3 | task 8534 | prompt eval time = 4719.91 ms / 822 tokens ( 5.74 ms per token, 174.16 tokens per second) 10.29.281.693 I slot print_timing: id 3 | task 8534 | eval time = 827.50 ms / 2 tokens ( 827.50 ms per token, 1.21 tokens per second) 10.29.281.693 I slot print_timing: id 3 | task 8534 | total time = 5547.41 ms / 824 tokens 10.29.281.694 I slot print_timing: id 3 | task 8534 | graphs reused = 7277 10.29.281.694 I slot print_timing: id 3 | task 8534 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.281.723 I slot release: id 3 | task 8534 | stop processing: n_tokens = 832, truncated = 0 10.30.018.412 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 692, t_last = 331576276410 10.30.018.550 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.870 MiB) 10.30.027.329 I slot launch_slot_: id 1 | task 8543 | processing task, is_child = 0 10.30.027.403 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.870 MiB) 10.30.032.909 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 832, t_last = 331576277565 10.30.033.023 I slot launch_slot_: id 3 | task 8544 | processing task, is_child = 0 10.31.125.813 I slot print_timing: id 0 | task 8537 | prompt eval time = 3507.86 ms / 845 tokens ( 4.15 ms per token, 240.89 tokens per second) 10.31.125.816 I slot print_timing: id 0 | task 8537 | eval time = 1107.41 ms / 2 tokens ( 1107.41 ms per token, 0.90 tokens per second) 10.31.125.817 I slot print_timing: id 0 | task 8537 | total time = 4615.28 ms / 847 tokens 10.31.125.818 I slot print_timing: id 0 | task 8537 | graphs reused = 7277 10.31.125.818 I slot print_timing: id 0 | task 8537 | graph reallocs = 0 / 0 (same size) / (changed size) 10.31.125.895 I slot release: id 0 | task 8537 | stop processing: n_tokens = 855, truncated = 0 10.32.682.779 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 331578121737 10.32.682.905 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 244.093 MiB) 10.32.691.821 I slot launch_slot_: id 0 | task 8547 | processing task, is_child = 0 10.33.633.821 I slot print_timing: id 2 | task 8540 | prompt eval time = 4217.53 ms / 750 tokens ( 5.62 ms per token, 177.83 tokens per second) 10.33.633.824 I slot print_timing: id 2 | task 8540 | eval time = 951.05 ms / 2 tokens ( 951.05 ms per token, 1.05 tokens per second) 10.33.633.824 I slot print_timing: id 2 | task 8540 | total time = 5168.58 ms / 752 tokens 10.33.633.825 I slot print_timing: id 2 | task 8540 | graphs reused = 7277 10.33.633.825 I slot print_timing: id 2 | task 8540 | graph reallocs = 0 / 0 (same size) / (changed size) 10.33.633.870 I slot release: id 2 | task 8540 | stop processing: n_tokens = 760, truncated = 0 10.33.635.801 I slot print_timing: id 1 | task 8543 | prompt processing, n_tokens = 697, progress = 0.99, t = 3.60 s / 193.63 tokens per second 10.33.639.192 I slot print_timing: id 3 | task 8544 | prompt processing, n_tokens = 732, progress = 0.99, t = 3.60 s / 203.45 tokens per second 10.34.411.251 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 760, t_last = 331580629712 10.34.411.355 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 300.420 MiB) 10.34.420.198 I slot launch_slot_: id 2 | task 8550 | processing task, is_child = 0 10.35.130.887 I slot print_timing: id 1 | task 8543 | prompt eval time = 4376.96 ms / 701 tokens ( 6.24 ms per token, 160.16 tokens per second) 10.35.130.890 I slot print_timing: id 1 | task 8543 | eval time = 720.89 ms / 2 tokens ( 720.89 ms per token, 1.39 tokens per second) 10.35.130.890 I slot print_timing: id 1 | task 8543 | total time = 5097.85 ms / 703 tokens 10.35.130.891 I slot print_timing: id 1 | task 8543 | graphs reused = 7277 10.35.130.891 I slot print_timing: id 1 | task 8543 | graph reallocs = 0 / 0 (same size) / (changed size) 10.35.130.939 I slot release: id 1 | task 8543 | stop processing: n_tokens = 711, truncated = 0 10.35.132.119 I slot print_timing: id 3 | task 8544 | prompt eval time = 4376.37 ms / 736 tokens ( 5.95 ms per token, 168.18 tokens per second) 10.35.132.122 I slot print_timing: id 3 | task 8544 | eval time = 720.87 ms / 2 tokens ( 720.87 ms per token, 1.39 tokens per second) 10.35.132.123 I slot print_timing: id 3 | task 8544 | total time = 5097.24 ms / 738 tokens 10.35.132.123 I slot print_timing: id 3 | task 8544 | graphs reused = 7277 10.35.132.124 I slot print_timing: id 3 | task 8544 | graph reallocs = 0 / 0 (same size) / (changed size) 10.35.132.180 I slot release: id 3 | task 8544 | stop processing: n_tokens = 746, truncated = 0 10.35.917.020 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.880 10.35.917.126 I slot launch_slot_: id 1 | task 8553 | processing task, is_child = 0 10.35.925.153 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 331582128022 10.35.925.260 I slot launch_slot_: id 3 | task 8554 | processing task, is_child = 0 10.36.808.279 I slot print_timing: id 0 | task 8547 | prompt eval time = 3225.17 ms / 723 tokens ( 4.46 ms per token, 224.17 tokens per second) 10.36.808.281 I slot print_timing: id 0 | task 8547 | eval time = 891.27 ms / 2 tokens ( 891.27 ms per token, 1.12 tokens per second) 10.36.808.282 I slot print_timing: id 0 | task 8547 | total time = 4116.44 ms / 725 tokens 10.36.808.282 I slot print_timing: id 0 | task 8547 | graphs reused = 7277 10.36.808.283 I slot print_timing: id 0 | task 8547 | graph reallocs = 0 / 0 (same size) / (changed size) 10.36.808.357 I slot release: id 0 | task 8547 | stop processing: n_tokens = 733, truncated = 0 10.37.619.903 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.854 10.37.620.055 I slot launch_slot_: id 0 | task 8557 | processing task, is_child = 0 10.38.104.293 I slot print_timing: id 1 | task 8553 | prompt eval time = 1693.37 ms / 82 tokens ( 20.65 ms per token, 48.42 tokens per second) 10.38.104.300 I slot print_timing: id 1 | task 8553 | eval time = 485.64 ms / 2 tokens ( 485.64 ms per token, 2.06 tokens per second) 10.38.104.300 I slot print_timing: id 1 | task 8553 | total time = 2179.02 ms / 84 tokens 10.38.104.301 I slot print_timing: id 1 | task 8553 | graphs reused = 7277 10.38.104.301 I slot print_timing: id 1 | task 8553 | graph reallocs = 0 / 0 (same size) / (changed size) 10.38.104.363 I slot release: id 1 | task 8553 | stop processing: n_tokens = 709, truncated = 0 10.38.105.499 I slot print_timing: id 2 | task 8550 | prompt eval time = 3197.98 ms / 706 tokens ( 4.53 ms per token, 220.76 tokens per second) 10.38.105.503 I slot print_timing: id 2 | task 8550 | eval time = 485.61 ms / 2 tokens ( 485.61 ms per token, 2.06 tokens per second) 10.38.105.503 I slot print_timing: id 2 | task 8550 | total time = 3683.58 ms / 708 tokens 10.38.105.504 I slot print_timing: id 2 | task 8550 | graphs reused = 7277 10.38.105.504 I slot print_timing: id 2 | task 8550 | graph reallocs = 0 / 0 (same size) / (changed size) 10.38.105.543 I slot release: id 2 | task 8550 | stop processing: n_tokens = 716, truncated = 0 10.38.180.014 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.886 10.38.180.104 I slot launch_slot_: id 1 | task 8560 | processing task, is_child = 0 10.38.180.176 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.638 MiB) 10.38.185.617 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.874 10.38.185.665 I slot launch_slot_: id 2 | task 8561 | processing task, is_child = 0 10.38.598.517 I slot print_timing: id 0 | task 8557 | prompt eval time = 558.70 ms / 79 tokens ( 7.07 ms per token, 141.40 tokens per second) 10.38.598.520 I slot print_timing: id 0 | task 8557 | eval time = 419.75 ms / 2 tokens ( 419.75 ms per token, 2.38 tokens per second) 10.38.598.520 I slot print_timing: id 0 | task 8557 | total time = 978.44 ms / 81 tokens 10.38.598.521 I slot print_timing: id 0 | task 8557 | graphs reused = 7277 10.38.598.521 I slot print_timing: id 0 | task 8557 | graph reallocs = 0 / 0 (same size) / (changed size) 10.38.598.586 I slot release: id 0 | task 8557 | stop processing: n_tokens = 706, truncated = 0 10.38.599.742 I slot print_timing: id 3 | task 8554 | prompt eval time = 2251.36 ms / 702 tokens ( 3.21 ms per token, 311.81 tokens per second) 10.38.599.748 I slot print_timing: id 3 | task 8554 | eval time = 419.73 ms / 2 tokens ( 419.73 ms per token, 2.38 tokens per second) 10.38.599.748 I slot print_timing: id 3 | task 8554 | total time = 2671.09 ms / 704 tokens 10.38.599.749 I slot print_timing: id 3 | task 8554 | graphs reused = 7277 10.38.599.749 I slot print_timing: id 3 | task 8554 | graph reallocs = 0 / 0 (same size) / (changed size) 10.38.599.780 I slot release: id 3 | task 8554 | stop processing: n_tokens = 712, truncated = 0 10.38.647.683 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.887 10.38.647.726 I slot launch_slot_: id 0 | task 8564 | processing task, is_child = 0 10.38.647.798 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 240.436 MiB) 10.38.652.991 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.838 (> 0.100 thold), f_keep = 0.879 10.38.653.029 I slot launch_slot_: id 3 | task 8565 | processing task, is_child = 0 10.39.137.613 I slot print_timing: id 1 | task 8560 | prompt eval time = 460.85 ms / 87 tokens ( 5.30 ms per token, 188.78 tokens per second) 10.39.137.615 I slot print_timing: id 1 | task 8560 | eval time = 491.09 ms / 2 tokens ( 491.09 ms per token, 2.04 tokens per second) 10.39.137.617 I slot print_timing: id 1 | task 8560 | total time = 951.93 ms / 89 tokens 10.39.137.618 I slot print_timing: id 1 | task 8560 | graphs reused = 7277 10.39.137.618 I slot print_timing: id 1 | task 8560 | graph reallocs = 0 / 0 (same size) / (changed size) 10.39.137.674 I slot release: id 1 | task 8560 | stop processing: n_tokens = 716, truncated = 0 10.39.138.777 I slot print_timing: id 2 | task 8561 | prompt eval time = 460.31 ms / 77 tokens ( 5.98 ms per token, 167.28 tokens per second) 10.39.138.781 I slot print_timing: id 2 | task 8561 | eval time = 491.10 ms / 2 tokens ( 491.10 ms per token, 2.04 tokens per second) 10.39.138.781 I slot print_timing: id 2 | task 8561 | total time = 951.40 ms / 79 tokens 10.39.138.782 I slot print_timing: id 2 | task 8561 | graphs reused = 7277 10.39.138.782 I slot print_timing: id 2 | task 8561 | graph reallocs = 0 / 0 (same size) / (changed size) 10.39.138.809 I slot release: id 2 | task 8561 | stop processing: n_tokens = 704, truncated = 0 10.39.213.136 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.874 10.39.213.193 I slot launch_slot_: id 1 | task 8568 | processing task, is_child = 0 10.39.213.265 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.638 MiB) 10.39.219.803 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 704, t_last = 331586134651 10.39.219.906 I slot launch_slot_: id 2 | task 8569 | processing task, is_child = 0 10.40.148.174 I slot print_timing: id 0 | task 8564 | prompt eval time = 559.03 ms / 87 tokens ( 6.43 ms per token, 155.63 tokens per second) 10.40.148.178 I slot print_timing: id 0 | task 8564 | eval time = 936.09 ms / 2 tokens ( 936.09 ms per token, 1.07 tokens per second) 10.40.148.178 I slot print_timing: id 0 | task 8564 | total time = 1495.13 ms / 89 tokens 10.40.148.179 I slot print_timing: id 0 | task 8564 | graphs reused = 7277 10.40.148.179 I slot print_timing: id 0 | task 8564 | graph reallocs = 0 / 0 (same size) / (changed size) 10.40.148.251 I slot release: id 0 | task 8564 | stop processing: n_tokens = 714, truncated = 0 10.40.149.411 I slot print_timing: id 3 | task 8565 | prompt eval time = 558.38 ms / 121 tokens ( 4.61 ms per token, 216.70 tokens per second) 10.40.149.414 I slot print_timing: id 3 | task 8565 | eval time = 936.28 ms / 2 tokens ( 936.28 ms per token, 1.07 tokens per second) 10.40.149.414 I slot print_timing: id 3 | task 8565 | total time = 1494.66 ms / 123 tokens 10.40.149.415 I slot print_timing: id 3 | task 8565 | graphs reused = 7277 10.40.149.415 I slot print_timing: id 3 | task 8565 | graph reallocs = 0 / 0 (same size) / (changed size) 10.40.149.448 I slot release: id 3 | task 8565 | stop processing: n_tokens = 748, truncated = 0 10.40.900.378 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 331587144093 10.40.900.490 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 289.766 MiB) 10.40.910.488 I slot launch_slot_: id 0 | task 8572 | processing task, is_child = 0 10.40.910.559 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.499 MiB) 10.40.916.833 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 331587145290 10.40.916.946 I slot launch_slot_: id 3 | task 8573 | processing task, is_child = 0 10.43.017.774 I slot print_timing: id 1 | task 8568 | prompt eval time = 1680.46 ms / 80 tokens ( 21.01 ms per token, 47.61 tokens per second) 10.43.017.777 I slot print_timing: id 1 | task 8568 | eval time = 2117.40 ms / 2 tokens ( 2117.40 ms per token, 0.47 tokens per second) 10.43.017.778 I slot print_timing: id 1 | task 8568 | total time = 3797.85 ms / 82 tokens 10.43.017.778 I slot print_timing: id 1 | task 8568 | graphs reused = 7277 10.43.017.778 I slot print_timing: id 1 | task 8568 | graph reallocs = 0 / 0 (same size) / (changed size) 10.43.017.820 I slot release: id 1 | task 8568 | stop processing: n_tokens = 707, truncated = 0 10.43.019.397 I slot print_timing: id 2 | task 8569 | prompt processing, n_tokens = 892, progress = 1.00, t = 3.79 s / 235.59 tokens per second 10.44.470.621 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 331590013662 10.44.470.744 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.112 MiB) 10.44.479.362 I slot launch_slot_: id 1 | task 8576 | processing task, is_child = 0 10.44.479.377 I slot print_timing: id 0 | task 8572 | prompt processing, n_tokens = 761, progress = 0.87, t = 3.55 s / 214.22 tokens per second 10.44.481.304 I slot print_timing: id 3 | task 8573 | prompt processing, n_tokens = 909, progress = 0.83, t = 3.55 s / 256.01 tokens per second 10.46.217.275 I slot print_timing: id 2 | task 8569 | prompt eval time = 5248.97 ms / 896 tokens ( 5.86 ms per token, 170.70 tokens per second) 10.46.217.278 I slot print_timing: id 2 | task 8569 | eval time = 1746.66 ms / 2 tokens ( 1746.66 ms per token, 0.57 tokens per second) 10.46.217.278 I slot print_timing: id 2 | task 8569 | total time = 6995.63 ms / 898 tokens 10.46.217.279 I slot print_timing: id 2 | task 8569 | graphs reused = 7277 10.46.217.279 I slot print_timing: id 2 | task 8569 | graph reallocs = 0 / 0 (same size) / (changed size) 10.46.217.361 I slot release: id 2 | task 8569 | stop processing: n_tokens = 906, truncated = 0 10.46.217.390 I slot print_timing: id 0 | task 8572 | prompt processing, n_tokens = 875, progress = 1.00, t = 5.30 s / 165.12 tokens per second 10.46.223.626 I slot print_timing: id 3 | task 8573 | prompt processing, n_tokens = 1095, progress = 1.00, t = 5.30 s / 206.71 tokens per second 10.46.950.855 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 906, t_last = 331593213203 10.46.950.976 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.398 MiB) 10.46.959.833 I slot launch_slot_: id 2 | task 8579 | processing task, is_child = 0 10.48.404.543 I slot print_timing: id 0 | task 8572 | prompt eval time = 6032.59 ms / 879 tokens ( 6.86 ms per token, 145.71 tokens per second) 10.48.404.562 I slot print_timing: id 0 | task 8572 | eval time = 1454.99 ms / 2 tokens ( 1454.99 ms per token, 0.69 tokens per second) 10.48.404.562 I slot print_timing: id 0 | task 8572 | total time = 7487.58 ms / 881 tokens 10.48.404.563 I slot print_timing: id 0 | task 8572 | graphs reused = 7277 10.48.404.563 I slot print_timing: id 0 | task 8572 | graph reallocs = 0 / 0 (same size) / (changed size) 10.48.404.639 I slot release: id 0 | task 8572 | stop processing: n_tokens = 889, truncated = 0 10.48.405.794 I slot print_timing: id 3 | task 8573 | prompt eval time = 6032.02 ms / 1099 tokens ( 5.49 ms per token, 182.19 tokens per second) 10.48.405.799 I slot print_timing: id 3 | task 8573 | eval time = 1454.94 ms / 2 tokens ( 1454.94 ms per token, 0.69 tokens per second) 10.48.405.800 I slot print_timing: id 3 | task 8573 | total time = 7486.97 ms / 1101 tokens 10.48.405.800 I slot print_timing: id 3 | task 8573 | graphs reused = 7277 10.48.405.801 I slot print_timing: id 3 | task 8573 | graph reallocs = 0 / 0 (same size) / (changed size) 10.48.405.846 I slot release: id 3 | task 8573 | stop processing: n_tokens = 1109, truncated = 0 10.48.405.863 I slot print_timing: id 1 | task 8576 | prompt processing, n_tokens = 1085, progress = 1.00, t = 3.92 s / 276.62 tokens per second 10.49.101.751 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.894 10.49.101.844 I slot launch_slot_: id 3 | task 8582 | processing task, is_child = 0 10.49.101.951 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 368.363 MiB) 10.49.111.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 889, t_last = 331595400481 10.49.111.669 I slot launch_slot_: id 0 | task 8583 | processing task, is_child = 0 10.50.759.316 I slot print_timing: id 1 | task 8576 | prompt eval time = 4620.61 ms / 1089 tokens ( 4.24 ms per token, 235.68 tokens per second) 10.50.759.326 I slot print_timing: id 1 | task 8576 | eval time = 1657.56 ms / 2 tokens ( 1657.56 ms per token, 0.60 tokens per second) 10.50.759.329 I slot print_timing: id 1 | task 8576 | total time = 6278.17 ms / 1091 tokens 10.50.759.331 I slot print_timing: id 1 | task 8576 | graphs reused = 7277 10.50.759.332 I slot print_timing: id 1 | task 8576 | graph reallocs = 0 / 0 (same size) / (changed size) 10.50.759.399 I slot release: id 1 | task 8576 | stop processing: n_tokens = 1099, truncated = 0 10.50.762.999 I slot print_timing: id 2 | task 8579 | prompt processing, n_tokens = 1088, progress = 1.00, t = 3.80 s / 286.58 tokens per second 10.51.463.452 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.901 10.51.463.584 I slot launch_slot_: id 1 | task 8586 | processing task, is_child = 0 10.52.125.896 I slot print_timing: id 2 | task 8579 | prompt eval time = 4500.40 ms / 1092 tokens ( 4.12 ms per token, 242.65 tokens per second) 10.52.125.899 I slot print_timing: id 2 | task 8579 | eval time = 663.80 ms / 2 tokens ( 663.80 ms per token, 1.51 tokens per second) 10.52.125.899 I slot print_timing: id 2 | task 8579 | total time = 5164.20 ms / 1094 tokens 10.52.125.900 I slot print_timing: id 2 | task 8579 | graphs reused = 7277 10.52.125.900 I slot print_timing: id 2 | task 8579 | graph reallocs = 0 / 0 (same size) / (changed size) 10.52.125.951 I slot release: id 2 | task 8579 | stop processing: n_tokens = 1102, truncated = 0 10.52.127.085 I slot print_timing: id 3 | task 8582 | prompt eval time = 2349.85 ms / 96 tokens ( 24.48 ms per token, 40.85 tokens per second) 10.52.127.088 I slot print_timing: id 3 | task 8582 | eval time = 663.64 ms / 2 tokens ( 663.64 ms per token, 1.51 tokens per second) 10.52.127.090 I slot print_timing: id 3 | task 8582 | total time = 3013.49 ms / 98 tokens 10.52.127.090 I slot print_timing: id 3 | task 8582 | graphs reused = 7277 10.52.127.090 I slot print_timing: id 3 | task 8582 | graph reallocs = 0 / 0 (same size) / (changed size) 10.52.127.123 I slot release: id 3 | task 8582 | stop processing: n_tokens = 1088, truncated = 0 10.52.127.139 I slot print_timing: id 0 | task 8583 | prompt processing, n_tokens = 1083, progress = 1.00, t = 3.01 s / 359.43 tokens per second 10.52.182.062 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.899 10.52.182.132 I slot launch_slot_: id 2 | task 8589 | processing task, is_child = 0 10.52.182.232 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.451 MiB) 10.52.192.624 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.911 10.52.192.678 I slot launch_slot_: id 3 | task 8590 | processing task, is_child = 0 10.52.662.362 I slot print_timing: id 0 | task 8583 | prompt eval time = 3069.13 ms / 1087 tokens ( 2.82 ms per token, 354.17 tokens per second) 10.52.662.366 I slot print_timing: id 0 | task 8583 | eval time = 481.52 ms / 2 tokens ( 481.52 ms per token, 2.08 tokens per second) 10.52.662.366 I slot print_timing: id 0 | task 8583 | total time = 3550.65 ms / 1089 tokens 10.52.662.367 I slot print_timing: id 0 | task 8583 | graphs reused = 7277 10.52.662.367 I slot print_timing: id 0 | task 8583 | graph reallocs = 0 / 0 (same size) / (changed size) 10.52.662.453 I slot release: id 0 | task 8583 | stop processing: n_tokens = 1097, truncated = 0 10.52.663.638 I slot print_timing: id 1 | task 8586 | prompt eval time = 714.70 ms / 106 tokens ( 6.74 ms per token, 148.31 tokens per second) 10.52.663.641 I slot print_timing: id 1 | task 8586 | eval time = 481.58 ms / 2 tokens ( 481.58 ms per token, 2.08 tokens per second) 10.52.663.641 I slot print_timing: id 1 | task 8586 | total time = 1196.28 ms / 108 tokens 10.52.663.642 I slot print_timing: id 1 | task 8586 | graphs reused = 7277 10.52.663.642 I slot print_timing: id 1 | task 8586 | graph reallocs = 0 / 0 (same size) / (changed size) 10.52.663.682 I slot release: id 1 | task 8586 | stop processing: n_tokens = 1097, truncated = 0 10.52.715.034 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.903 10.52.715.109 I slot launch_slot_: id 0 | task 8593 | processing task, is_child = 0 10.52.715.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.694 MiB) 10.52.726.121 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.903 10.52.726.177 I slot launch_slot_: id 1 | task 8594 | processing task, is_child = 0 10.53.227.255 I slot print_timing: id 2 | task 8589 | prompt eval time = 521.17 ms / 98 tokens ( 5.32 ms per token, 188.04 tokens per second) 10.53.227.258 I slot print_timing: id 2 | task 8589 | eval time = 513.38 ms / 2 tokens ( 513.38 ms per token, 1.95 tokens per second) 10.53.227.258 I slot print_timing: id 2 | task 8589 | total time = 1034.56 ms / 100 tokens 10.53.227.259 I slot print_timing: id 2 | task 8589 | graphs reused = 7277 10.53.227.259 I slot print_timing: id 2 | task 8589 | graph reallocs = 0 / 0 (same size) / (changed size) 10.53.227.321 I slot release: id 2 | task 8589 | stop processing: n_tokens = 1090, truncated = 0 10.53.228.454 I slot print_timing: id 3 | task 8590 | prompt eval time = 520.62 ms / 107 tokens ( 4.87 ms per token, 205.52 tokens per second) 10.53.228.457 I slot print_timing: id 3 | task 8590 | eval time = 513.42 ms / 2 tokens ( 513.42 ms per token, 1.95 tokens per second) 10.53.228.457 I slot print_timing: id 3 | task 8590 | total time = 1034.04 ms / 109 tokens 10.53.228.458 I slot print_timing: id 3 | task 8590 | graphs reused = 7277 10.53.228.458 I slot print_timing: id 3 | task 8590 | graph reallocs = 0 / 0 (same size) / (changed size) 10.53.228.501 I slot release: id 3 | task 8590 | stop processing: n_tokens = 1099, truncated = 0 10.53.283.235 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.909 10.53.283.301 I slot launch_slot_: id 2 | task 8597 | processing task, is_child = 0 10.53.283.393 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.147 MiB) 10.53.294.116 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.902 10.53.294.171 I slot launch_slot_: id 3 | task 8598 | processing task, is_child = 0 10.53.743.866 I slot print_timing: id 0 | task 8593 | prompt eval time = 555.92 ms / 114 tokens ( 4.88 ms per token, 205.07 tokens per second) 10.53.743.867 I slot print_timing: id 0 | task 8593 | eval time = 461.76 ms / 2 tokens ( 461.76 ms per token, 2.17 tokens per second) 10.53.743.868 I slot print_timing: id 0 | task 8593 | total time = 1017.68 ms / 116 tokens 10.53.743.868 I slot print_timing: id 0 | task 8593 | graphs reused = 7277 10.53.743.869 I slot print_timing: id 0 | task 8593 | graph reallocs = 0 / 0 (same size) / (changed size) 10.53.743.915 I slot release: id 0 | task 8593 | stop processing: n_tokens = 1106, truncated = 0 10.53.745.052 I slot print_timing: id 1 | task 8594 | prompt eval time = 555.34 ms / 108 tokens ( 5.14 ms per token, 194.47 tokens per second) 10.53.745.054 I slot print_timing: id 1 | task 8594 | eval time = 461.82 ms / 2 tokens ( 461.82 ms per token, 2.17 tokens per second) 10.53.745.055 I slot print_timing: id 1 | task 8594 | total time = 1017.17 ms / 110 tokens 10.53.745.055 I slot print_timing: id 1 | task 8594 | graphs reused = 7277 10.53.745.055 I slot print_timing: id 1 | task 8594 | graph reallocs = 0 / 0 (same size) / (changed size) 10.53.745.095 I slot release: id 1 | task 8594 | stop processing: n_tokens = 1100, truncated = 0 10.53.793.524 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.896 10.53.793.573 I slot launch_slot_: id 0 | task 8601 | processing task, is_child = 0 10.53.793.662 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 342.409 MiB) 10.53.805.062 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.901 10.53.805.111 I slot launch_slot_: id 1 | task 8602 | processing task, is_child = 0 10.54.293.851 I slot print_timing: id 2 | task 8597 | prompt eval time = 498.17 ms / 100 tokens ( 4.98 ms per token, 200.73 tokens per second) 10.54.293.856 I slot print_timing: id 2 | task 8597 | eval time = 501.50 ms / 2 tokens ( 501.50 ms per token, 1.99 tokens per second) 10.54.293.856 I slot print_timing: id 2 | task 8597 | total time = 999.67 ms / 102 tokens 10.54.293.857 I slot print_timing: id 2 | task 8597 | graphs reused = 7277 10.54.293.857 I slot print_timing: id 2 | task 8597 | graph reallocs = 0 / 0 (same size) / (changed size) 10.54.293.904 I slot release: id 2 | task 8597 | stop processing: n_tokens = 1092, truncated = 0 10.54.295.133 I slot print_timing: id 3 | task 8598 | prompt eval time = 497.64 ms / 102 tokens ( 4.88 ms per token, 204.97 tokens per second) 10.54.295.136 I slot print_timing: id 3 | task 8598 | eval time = 501.61 ms / 2 tokens ( 501.61 ms per token, 1.99 tokens per second) 10.54.295.136 I slot print_timing: id 3 | task 8598 | total time = 999.26 ms / 104 tokens 10.54.295.136 I slot print_timing: id 3 | task 8598 | graphs reused = 7277 10.54.295.137 I slot print_timing: id 3 | task 8598 | graph reallocs = 0 / 0 (same size) / (changed size) 10.54.295.172 I slot release: id 3 | task 8598 | stop processing: n_tokens = 1094, truncated = 0 10.54.343.675 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1092, t_last = 331601289746 10.54.343.767 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.639 MiB) 10.54.354.216 I slot launch_slot_: id 2 | task 8605 | processing task, is_child = 0 10.54.354.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.720 MiB) 10.54.367.259 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.906 10.54.367.311 I slot launch_slot_: id 3 | task 8606 | processing task, is_child = 0 10.55.561.165 I slot print_timing: id 0 | task 8601 | prompt eval time = 537.39 ms / 105 tokens ( 5.12 ms per token, 195.39 tokens per second) 10.55.561.168 I slot print_timing: id 0 | task 8601 | eval time = 1218.65 ms / 2 tokens ( 1218.65 ms per token, 0.82 tokens per second) 10.55.561.169 I slot print_timing: id 0 | task 8601 | total time = 1756.04 ms / 107 tokens 10.55.561.169 I slot print_timing: id 0 | task 8601 | graphs reused = 7277 10.55.561.170 I slot print_timing: id 0 | task 8601 | graph reallocs = 0 / 0 (same size) / (changed size) 10.55.561.243 I slot release: id 0 | task 8601 | stop processing: n_tokens = 1097, truncated = 0 10.55.562.518 I slot print_timing: id 1 | task 8602 | prompt eval time = 536.83 ms / 104 tokens ( 5.16 ms per token, 193.73 tokens per second) 10.55.562.521 I slot print_timing: id 1 | task 8602 | eval time = 1218.84 ms / 2 tokens ( 1218.84 ms per token, 0.82 tokens per second) 10.55.562.521 I slot print_timing: id 1 | task 8602 | total time = 1755.67 ms / 106 tokens 10.55.562.521 I slot print_timing: id 1 | task 8602 | graphs reused = 7277 10.55.562.522 I slot print_timing: id 1 | task 8602 | graph reallocs = 0 / 0 (same size) / (changed size) 10.55.562.561 I slot release: id 1 | task 8602 | stop processing: n_tokens = 1096, truncated = 0 10.56.317.364 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1097, t_last = 331602557085 10.56.317.507 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.275 MiB) 10.56.328.175 I slot launch_slot_: id 0 | task 8609 | processing task, is_child = 0 10.56.328.261 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.469 MiB) 10.56.328.267 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.104 MiB) 10.56.336.742 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1096, t_last = 331602558403 10.56.336.870 I slot launch_slot_: id 1 | task 8610 | processing task, is_child = 0 10.58.662.355 I slot print_timing: id 3 | task 8606 | prompt eval time = 1949.81 ms / 103 tokens ( 18.93 ms per token, 52.83 tokens per second) 10.58.662.358 I slot print_timing: id 3 | task 8606 | eval time = 2344.99 ms / 2 tokens ( 2344.99 ms per token, 0.43 tokens per second) 10.58.662.358 I slot print_timing: id 3 | task 8606 | total time = 4294.80 ms / 105 tokens 10.58.662.359 I slot print_timing: id 3 | task 8606 | graphs reused = 7277 10.58.662.360 I slot print_timing: id 3 | task 8606 | graph reallocs = 0 / 0 (same size) / (changed size) 10.58.662.433 I slot release: id 3 | task 8606 | stop processing: n_tokens = 1095, truncated = 0 10.58.668.111 I slot print_timing: id 2 | task 8605 | prompt processing, n_tokens = 996, progress = 1.00, t = 4.29 s / 231.96 tokens per second 10.59.990.527 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1095, t_last = 331605658275 10.59.990.624 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.572 MiB) 10.59.998.656 I slot launch_slot_: id 3 | task 8613 | processing task, is_child = 0 10.59.998.667 I slot print_timing: id 0 | task 8609 | prompt processing, n_tokens = 861, progress = 0.84, t = 3.65 s / 235.73 tokens per second 11.00.000.346 I slot print_timing: id 1 | task 8610 | prompt processing, n_tokens = 861, progress = 0.79, t = 3.65 s / 235.74 tokens per second 11.01.813.325 I slot print_timing: id 2 | task 8605 | prompt eval time = 5623.20 ms / 1000 tokens ( 5.62 ms per token, 177.83 tokens per second) 11.01.813.330 I slot print_timing: id 2 | task 8605 | eval time = 1822.78 ms / 2 tokens ( 1822.78 ms per token, 0.55 tokens per second) 11.01.813.330 I slot print_timing: id 2 | task 8605 | total time = 7445.99 ms / 1002 tokens 11.01.813.331 I slot print_timing: id 2 | task 8605 | graphs reused = 7277 11.01.813.331 I slot print_timing: id 2 | task 8605 | graph reallocs = 0 / 0 (same size) / (changed size) 11.01.813.421 I slot release: id 2 | task 8605 | stop processing: n_tokens = 1010, truncated = 0 11.01.813.448 I slot print_timing: id 0 | task 8609 | prompt processing, n_tokens = 1017, progress = 1.00, t = 5.48 s / 185.74 tokens per second 11.01.817.277 I slot print_timing: id 1 | task 8610 | prompt processing, n_tokens = 1087, progress = 1.00, t = 5.48 s / 198.54 tokens per second 11.02.512.014 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.888 11.02.512.135 I slot launch_slot_: id 2 | task 8616 | processing task, is_child = 0 11.03.231.019 I slot print_timing: id 0 | task 8609 | prompt eval time = 6173.73 ms / 1021 tokens ( 6.05 ms per token, 165.38 tokens per second) 11.03.231.022 I slot print_timing: id 0 | task 8609 | eval time = 720.41 ms / 2 tokens ( 720.41 ms per token, 1.39 tokens per second) 11.03.231.022 I slot print_timing: id 0 | task 8609 | total time = 6894.14 ms / 1023 tokens 11.03.231.023 I slot print_timing: id 0 | task 8609 | graphs reused = 7277 11.03.231.023 I slot print_timing: id 0 | task 8609 | graph reallocs = 0 / 0 (same size) / (changed size) 11.03.231.069 I slot release: id 0 | task 8609 | stop processing: n_tokens = 1031, truncated = 0 11.03.232.265 I slot print_timing: id 1 | task 8610 | prompt eval time = 6174.91 ms / 1091 tokens ( 5.66 ms per token, 176.68 tokens per second) 11.03.232.268 I slot print_timing: id 1 | task 8610 | eval time = 720.25 ms / 2 tokens ( 720.25 ms per token, 1.39 tokens per second) 11.03.232.268 I slot print_timing: id 1 | task 8610 | total time = 6895.16 ms / 1093 tokens 11.03.232.268 I slot print_timing: id 1 | task 8610 | graphs reused = 7277 11.03.232.269 I slot print_timing: id 1 | task 8610 | graph reallocs = 0 / 0 (same size) / (changed size) 11.03.232.316 I slot release: id 1 | task 8610 | stop processing: n_tokens = 1101, truncated = 0 11.03.236.459 I slot print_timing: id 3 | task 8613 | prompt processing, n_tokens = 1051, progress = 1.00, t = 3.23 s / 325.60 tokens per second 11.03.281.911 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1031, t_last = 331610226911 11.03.282.008 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 223.839 MiB) 11.03.293.755 I slot launch_slot_: id 0 | task 8619 | processing task, is_child = 0 11.03.293.841 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 222.855 MiB) 11.03.305.848 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.815 11.03.305.904 I slot launch_slot_: id 1 | task 8620 | processing task, is_child = 0 11.04.060.423 I slot print_timing: id 2 | task 8616 | prompt eval time = 768.57 ms / 122 tokens ( 6.30 ms per token, 158.74 tokens per second) 11.04.060.433 I slot print_timing: id 2 | task 8616 | eval time = 779.69 ms / 2 tokens ( 779.69 ms per token, 1.28 tokens per second) 11.04.060.434 I slot print_timing: id 2 | task 8616 | total time = 1548.27 ms / 124 tokens 11.04.060.435 I slot print_timing: id 2 | task 8616 | graphs reused = 7277 11.04.060.435 I slot print_timing: id 2 | task 8616 | graph reallocs = 0 / 0 (same size) / (changed size) 11.04.060.517 I slot release: id 2 | task 8616 | stop processing: n_tokens = 1020, truncated = 0 11.04.061.646 I slot print_timing: id 3 | task 8613 | prompt eval time = 3279.89 ms / 1055 tokens ( 3.11 ms per token, 321.66 tokens per second) 11.04.061.652 I slot print_timing: id 3 | task 8613 | eval time = 779.74 ms / 2 tokens ( 779.74 ms per token, 1.28 tokens per second) 11.04.061.653 I slot print_timing: id 3 | task 8613 | total time = 4059.62 ms / 1057 tokens 11.04.061.653 I slot print_timing: id 3 | task 8613 | graphs reused = 7277 11.04.061.653 I slot print_timing: id 3 | task 8613 | graph reallocs = 0 / 0 (same size) / (changed size) 11.04.061.699 I slot release: id 3 | task 8613 | stop processing: n_tokens = 1065, truncated = 0 11.04.803.542 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1020, t_last = 331611056359 11.04.803.683 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.063 MiB) 11.04.803.695 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 222.433 MiB) 11.04.814.014 I slot launch_slot_: id 2 | task 8623 | processing task, is_child = 0 11.04.814.096 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.498 MiB) 11.04.820.354 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1065, t_last = 331611057541 11.04.820.473 I slot launch_slot_: id 3 | task 8624 | processing task, is_child = 0 11.06.066.264 I slot print_timing: id 1 | task 8620 | prompt eval time = 1497.40 ms / 143 tokens ( 10.47 ms per token, 95.50 tokens per second) 11.06.066.268 I slot print_timing: id 1 | task 8620 | eval time = 1262.72 ms / 2 tokens ( 1262.72 ms per token, 0.79 tokens per second) 11.06.066.269 I slot print_timing: id 1 | task 8620 | total time = 2760.12 ms / 145 tokens 11.06.066.270 I slot print_timing: id 1 | task 8620 | graphs reused = 7277 11.06.066.270 I slot print_timing: id 1 | task 8620 | graph reallocs = 0 / 0 (same size) / (changed size) 11.06.066.370 I slot release: id 1 | task 8620 | stop processing: n_tokens = 1041, truncated = 0 11.07.571.888 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1041, t_last = 331613062215 11.07.572.019 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 227.356 MiB) 11.07.587.599 I slot launch_slot_: id 1 | task 8627 | processing task, is_child = 0 11.08.643.049 I slot print_timing: id 0 | task 8619 | prompt eval time = 4265.96 ms / 745 tokens ( 5.73 ms per token, 174.64 tokens per second) 11.08.643.053 I slot print_timing: id 0 | task 8619 | eval time = 1071.17 ms / 2 tokens ( 1071.17 ms per token, 0.93 tokens per second) 11.08.643.053 I slot print_timing: id 0 | task 8619 | total time = 5337.13 ms / 747 tokens 11.08.643.053 I slot print_timing: id 0 | task 8619 | graphs reused = 7277 11.08.643.054 I slot print_timing: id 0 | task 8619 | graph reallocs = 0 / 0 (same size) / (changed size) 11.08.643.120 I slot release: id 0 | task 8619 | stop processing: n_tokens = 755, truncated = 0 11.08.645.106 I slot print_timing: id 2 | task 8623 | prompt processing, n_tokens = 713, progress = 0.99, t = 3.82 s / 186.66 tokens per second 11.08.648.131 I slot print_timing: id 3 | task 8624 | prompt processing, n_tokens = 783, progress = 0.99, t = 3.82 s / 205.00 tokens per second 11.09.457.975 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.858 11.09.458.124 I slot launch_slot_: id 0 | task 8630 | processing task, is_child = 0 11.09.956.128 I slot print_timing: id 2 | task 8623 | prompt eval time = 4634.40 ms / 717 tokens ( 6.46 ms per token, 154.71 tokens per second) 11.09.956.135 I slot print_timing: id 2 | task 8623 | eval time = 499.56 ms / 2 tokens ( 499.56 ms per token, 2.00 tokens per second) 11.09.956.136 I slot print_timing: id 2 | task 8623 | total time = 5133.96 ms / 719 tokens 11.09.956.136 I slot print_timing: id 2 | task 8623 | graphs reused = 7277 11.09.956.137 I slot print_timing: id 2 | task 8623 | graph reallocs = 0 / 0 (same size) / (changed size) 11.09.956.197 I slot release: id 2 | task 8623 | stop processing: n_tokens = 727, truncated = 0 11.09.957.391 I slot print_timing: id 3 | task 8624 | prompt eval time = 4635.59 ms / 787 tokens ( 5.89 ms per token, 169.77 tokens per second) 11.09.957.394 I slot print_timing: id 3 | task 8624 | eval time = 499.43 ms / 2 tokens ( 499.43 ms per token, 2.00 tokens per second) 11.09.957.396 I slot print_timing: id 3 | task 8624 | total time = 5135.02 ms / 789 tokens 11.09.957.396 I slot print_timing: id 3 | task 8624 | graphs reused = 7277 11.09.957.397 I slot print_timing: id 3 | task 8624 | graph reallocs = 0 / 0 (same size) / (changed size) 11.09.957.441 I slot release: id 3 | task 8624 | stop processing: n_tokens = 797, truncated = 0 11.10.004.786 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.891 11.10.004.849 I slot launch_slot_: id 2 | task 8633 | processing task, is_child = 0 11.10.004.935 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 228.481 MiB) 11.10.010.445 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.813 11.10.010.490 I slot launch_slot_: id 3 | task 8634 | processing task, is_child = 0 11.10.392.043 I slot print_timing: id 0 | task 8630 | prompt eval time = 545.28 ms / 97 tokens ( 5.62 ms per token, 177.89 tokens per second) 11.10.392.045 I slot print_timing: id 0 | task 8630 | eval time = 388.61 ms / 2 tokens ( 388.61 ms per token, 2.57 tokens per second) 11.10.392.045 I slot print_timing: id 0 | task 8630 | total time = 933.90 ms / 99 tokens 11.10.392.046 I slot print_timing: id 0 | task 8630 | graphs reused = 7277 11.10.392.046 I slot print_timing: id 0 | task 8630 | graph reallocs = 0 / 0 (same size) / (changed size) 11.10.392.102 I slot release: id 0 | task 8630 | stop processing: n_tokens = 746, truncated = 0 11.10.393.323 I slot print_timing: id 1 | task 8627 | prompt eval time = 2417.17 ms / 730 tokens ( 3.31 ms per token, 302.01 tokens per second) 11.10.393.327 I slot print_timing: id 1 | task 8627 | eval time = 388.54 ms / 2 tokens ( 388.54 ms per token, 2.57 tokens per second) 11.10.393.327 I slot print_timing: id 1 | task 8627 | total time = 2805.71 ms / 732 tokens 11.10.393.327 I slot print_timing: id 1 | task 8627 | graphs reused = 7277 11.10.393.328 I slot print_timing: id 1 | task 8627 | graph reallocs = 0 / 0 (same size) / (changed size) 11.10.393.367 I slot release: id 1 | task 8627 | stop processing: n_tokens = 740, truncated = 0 11.10.441.196 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.869 11.10.441.241 I slot launch_slot_: id 0 | task 8637 | processing task, is_child = 0 11.10.441.317 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 237.342 MiB) 11.10.446.544 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.861 (> 0.100 thold), f_keep = 0.876 11.10.446.585 I slot launch_slot_: id 1 | task 8638 | processing task, is_child = 0 11.10.884.750 I slot print_timing: id 2 | task 8633 | prompt eval time = 429.52 ms / 89 tokens ( 4.83 ms per token, 207.21 tokens per second) 11.10.884.753 I slot print_timing: id 2 | task 8633 | eval time = 444.73 ms / 2 tokens ( 444.73 ms per token, 2.25 tokens per second) 11.10.884.753 I slot print_timing: id 2 | task 8633 | total time = 874.25 ms / 91 tokens 11.10.884.754 I slot print_timing: id 2 | task 8633 | graphs reused = 7277 11.10.884.754 I slot print_timing: id 2 | task 8633 | graph reallocs = 0 / 0 (same size) / (changed size) 11.10.884.824 I slot release: id 2 | task 8633 | stop processing: n_tokens = 738, truncated = 0 11.10.886.007 I slot print_timing: id 3 | task 8634 | prompt eval time = 428.99 ms / 84 tokens ( 5.11 ms per token, 195.81 tokens per second) 11.10.886.015 I slot print_timing: id 3 | task 8634 | eval time = 444.81 ms / 2 tokens ( 444.81 ms per token, 2.25 tokens per second) 11.10.886.015 I slot print_timing: id 3 | task 8634 | total time = 873.80 ms / 86 tokens 11.10.886.015 I slot print_timing: id 3 | task 8634 | graphs reused = 7277 11.10.886.016 I slot print_timing: id 3 | task 8634 | graph reallocs = 0 / 0 (same size) / (changed size) 11.10.886.061 I slot release: id 3 | task 8634 | stop processing: n_tokens = 733, truncated = 0 11.10.934.679 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 331617880666 11.10.934.755 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.206 MiB) 11.10.942.517 I slot launch_slot_: id 2 | task 8641 | processing task, is_child = 0 11.10.942.586 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 206.821 MiB) 11.10.949.085 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 733, t_last = 331617881903 11.10.949.195 I slot launch_slot_: id 3 | task 8642 | processing task, is_child = 0 11.12.694.409 I slot print_timing: id 0 | task 8637 | prompt eval time = 486.85 ms / 100 tokens ( 4.87 ms per token, 205.40 tokens per second) 11.12.694.412 I slot print_timing: id 0 | task 8637 | eval time = 1760.96 ms / 2 tokens ( 1760.96 ms per token, 0.57 tokens per second) 11.12.694.412 I slot print_timing: id 0 | task 8637 | total time = 2247.81 ms / 102 tokens 11.12.694.413 I slot print_timing: id 0 | task 8637 | graphs reused = 7277 11.12.694.413 I slot print_timing: id 0 | task 8637 | graph reallocs = 0 / 0 (same size) / (changed size) 11.12.694.460 I slot release: id 0 | task 8637 | stop processing: n_tokens = 749, truncated = 0 11.12.695.685 I slot print_timing: id 1 | task 8638 | prompt eval time = 486.39 ms / 105 tokens ( 4.63 ms per token, 215.88 tokens per second) 11.12.695.688 I slot print_timing: id 1 | task 8638 | eval time = 1761.01 ms / 2 tokens ( 1761.01 ms per token, 0.57 tokens per second) 11.12.695.689 I slot print_timing: id 1 | task 8638 | total time = 2247.40 ms / 107 tokens 11.12.695.689 I slot print_timing: id 1 | task 8638 | graphs reused = 7277 11.12.695.690 I slot print_timing: id 1 | task 8638 | graph reallocs = 0 / 0 (same size) / (changed size) 11.12.695.727 I slot release: id 1 | task 8638 | stop processing: n_tokens = 754, truncated = 0 11.14.000.742 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 749, t_last = 331619690302 11.14.000.826 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 226.512 MiB) 11.14.088.467 I slot launch_slot_: id 0 | task 8645 | processing task, is_child = 0 11.14.088.546 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.747 MiB) 11.14.095.307 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 331619691569 11.14.095.420 I slot launch_slot_: id 1 | task 8646 | processing task, is_child = 0 11.14.095.807 I slot print_timing: id 2 | task 8641 | prompt processing, n_tokens = 812, progress = 0.83, t = 3.05 s / 266.10 tokens per second 11.14.097.481 I slot print_timing: id 3 | task 8642 | prompt processing, n_tokens = 812, progress = 0.84, t = 3.05 s / 266.11 tokens per second 11.16.536.440 I slot print_timing: id 2 | task 8641 | prompt processing, n_tokens = 981, progress = 1.00, t = 5.39 s / 181.99 tokens per second 11.16.538.542 I slot print_timing: id 3 | task 8642 | prompt processing, n_tokens = 963, progress = 1.00, t = 5.39 s / 178.66 tokens per second 11.17.868.909 I slot print_timing: id 0 | task 8645 | prompt processing, n_tokens = 812, progress = 0.78, t = 3.77 s / 215.33 tokens per second 11.17.872.475 I slot print_timing: id 1 | task 8646 | prompt processing, n_tokens = 812, progress = 0.86, t = 3.77 s / 215.34 tokens per second 11.18.648.133 I slot print_timing: id 2 | task 8641 | prompt eval time = 6918.31 ms / 985 tokens ( 7.02 ms per token, 142.38 tokens per second) 11.18.648.137 I slot print_timing: id 2 | task 8641 | eval time = 780.61 ms / 2 tokens ( 780.61 ms per token, 1.28 tokens per second) 11.18.648.137 I slot print_timing: id 2 | task 8641 | total time = 7698.92 ms / 987 tokens 11.18.648.138 I slot print_timing: id 2 | task 8641 | graphs reused = 7277 11.18.648.138 I slot print_timing: id 2 | task 8641 | graph reallocs = 0 / 0 (same size) / (changed size) 11.18.648.200 I slot release: id 2 | task 8641 | stop processing: n_tokens = 995, truncated = 0 11.18.649.407 I slot print_timing: id 3 | task 8642 | prompt eval time = 6919.51 ms / 967 tokens ( 7.16 ms per token, 139.75 tokens per second) 11.18.649.410 I slot print_timing: id 3 | task 8642 | eval time = 780.52 ms / 2 tokens ( 780.52 ms per token, 1.28 tokens per second) 11.18.649.410 I slot print_timing: id 3 | task 8642 | total time = 7700.03 ms / 969 tokens 11.18.649.411 I slot print_timing: id 3 | task 8642 | graphs reused = 7277 11.18.649.411 I slot print_timing: id 3 | task 8642 | graph reallocs = 0 / 0 (same size) / (changed size) 11.18.649.455 I slot release: id 3 | task 8642 | stop processing: n_tokens = 977, truncated = 0 11.18.649.472 I slot print_timing: id 0 | task 8645 | prompt processing, n_tokens = 1039, progress = 1.00, t = 4.55 s / 228.27 tokens per second 11.18.653.296 I slot print_timing: id 1 | task 8646 | prompt processing, n_tokens = 946, progress = 1.00, t = 4.55 s / 207.85 tokens per second 11.18.698.728 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 995, t_last = 331625644042 11.18.698.813 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.385 MiB) 11.18.698.817 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.416 MiB) 11.18.705.018 I slot launch_slot_: id 2 | task 8651 | processing task, is_child = 0 11.18.705.103 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 210.197 MiB) 11.18.711.436 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 331625645297 11.18.711.550 I slot launch_slot_: id 3 | task 8652 | processing task, is_child = 0 11.21.043.739 I slot print_timing: id 0 | task 8645 | prompt eval time = 4602.05 ms / 1043 tokens ( 4.41 ms per token, 226.64 tokens per second) 11.21.043.742 I slot print_timing: id 0 | task 8645 | eval time = 2346.25 ms / 2 tokens ( 2346.25 ms per token, 0.43 tokens per second) 11.21.043.743 I slot print_timing: id 0 | task 8645 | total time = 6948.31 ms / 1045 tokens 11.21.043.743 I slot print_timing: id 0 | task 8645 | graphs reused = 7277 11.21.043.744 I slot print_timing: id 0 | task 8645 | graph reallocs = 0 / 0 (same size) / (changed size) 11.21.043.842 I slot release: id 0 | task 8645 | stop processing: n_tokens = 1053, truncated = 0 11.21.045.097 I slot print_timing: id 1 | task 8646 | prompt eval time = 4603.09 ms / 950 tokens ( 4.85 ms per token, 206.38 tokens per second) 11.21.045.100 I slot print_timing: id 1 | task 8646 | eval time = 2346.37 ms / 2 tokens ( 2346.37 ms per token, 0.43 tokens per second) 11.21.045.101 I slot print_timing: id 1 | task 8646 | total time = 6949.46 ms / 952 tokens 11.21.045.101 I slot print_timing: id 1 | task 8646 | graphs reused = 7277 11.21.045.101 I slot print_timing: id 1 | task 8646 | graph reallocs = 0 / 0 (same size) / (changed size) 11.21.045.145 I slot release: id 1 | task 8646 | stop processing: n_tokens = 960, truncated = 0 11.22.293.823 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1053, t_last = 331628039684 11.22.293.913 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 209.634 MiB) 11.22.381.515 I slot launch_slot_: id 0 | task 8655 | processing task, is_child = 0 11.22.381.599 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.781 MiB) 11.22.388.078 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 960, t_last = 331628040987 11.22.388.197 I slot launch_slot_: id 1 | task 8656 | processing task, is_child = 0 11.25.766.242 I slot print_timing: id 0 | task 8655 | prompt processing, n_tokens = 1616, progress = 0.76, t = 3.38 s / 478.39 tokens per second 11.26.078.421 I slot print_timing: id 1 | task 8656 | prompt processing, n_tokens = 432, progress = 0.21, t = 3.38 s / 127.89 tokens per second 11.26.078.453 I slot print_timing: id 2 | task 8651 | prompt processing, n_tokens = 975, progress = 0.84, t = 3.58 s / 272.17 tokens per second 11.26.082.040 I slot print_timing: id 3 | task 8652 | prompt processing, n_tokens = 975, progress = 0.87, t = 3.58 s / 272.19 tokens per second 11.28.391.896 I slot print_timing: id 0 | task 8655 | prompt processing, n_tokens = 1795, progress = 0.84, t = 6.00 s / 298.98 tokens per second 11.29.346.331 I slot print_timing: id 1 | task 8656 | prompt processing, n_tokens = 1613, progress = 0.76, t = 6.00 s / 268.68 tokens per second 11.29.349.132 I slot print_timing: id 2 | task 8651 | prompt processing, n_tokens = 1155, progress = 1.00, t = 9.68 s / 119.31 tokens per second 11.29.351.185 I slot print_timing: id 3 | task 8652 | prompt processing, n_tokens = 1123, progress = 1.00, t = 9.68 s / 116.01 tokens per second 11.30.464.138 I slot print_timing: id 0 | task 8655 | prompt processing, n_tokens = 2128, progress = 1.00, t = 8.07 s / 263.58 tokens per second 11.30.468.143 I slot print_timing: id 1 | task 8656 | prompt processing, n_tokens = 1795, progress = 0.84, t = 8.07 s / 222.34 tokens per second 11.31.215.102 I slot print_timing: id 2 | task 8651 | prompt eval time = 11751.31 ms / 1159 tokens ( 10.14 ms per token, 98.63 tokens per second) 11.31.215.105 I slot print_timing: id 2 | task 8651 | eval time = 752.23 ms / 2 tokens ( 752.23 ms per token, 1.33 tokens per second) 11.31.215.106 I slot print_timing: id 2 | task 8651 | total time = 12503.54 ms / 1161 tokens 11.31.215.107 I slot print_timing: id 2 | task 8651 | graphs reused = 7277 11.31.215.107 I slot print_timing: id 2 | task 8651 | graph reallocs = 0 / 0 (same size) / (changed size) 11.31.215.190 I slot release: id 2 | task 8651 | stop processing: n_tokens = 1169, truncated = 0 11.31.216.377 I slot print_timing: id 3 | task 8652 | prompt eval time = 11752.33 ms / 1127 tokens ( 10.43 ms per token, 95.90 tokens per second) 11.31.216.381 I slot print_timing: id 3 | task 8652 | eval time = 752.26 ms / 2 tokens ( 752.26 ms per token, 1.33 tokens per second) 11.31.216.381 I slot print_timing: id 3 | task 8652 | total time = 12504.59 ms / 1129 tokens 11.31.216.381 I slot print_timing: id 3 | task 8652 | graphs reused = 7277 11.31.216.382 I slot print_timing: id 3 | task 8652 | graph reallocs = 0 / 0 (same size) / (changed size) 11.31.216.431 I slot release: id 3 | task 8652 | stop processing: n_tokens = 1137, truncated = 0 11.31.216.446 I slot print_timing: id 1 | task 8656 | prompt processing, n_tokens = 2125, progress = 1.00, t = 8.82 s / 240.81 tokens per second 11.31.286.617 I slot print_timing: id 0 | task 8655 | prompt eval time = 8825.75 ms / 2132 tokens ( 4.14 ms per token, 241.57 tokens per second) 11.31.286.619 I slot print_timing: id 0 | task 8655 | eval time = 72.66 ms / 2 tokens ( 72.66 ms per token, 13.76 tokens per second) 11.31.286.620 I slot print_timing: id 0 | task 8655 | total time = 8898.41 ms / 2134 tokens 11.31.286.620 I slot print_timing: id 0 | task 8655 | graphs reused = 7277 11.31.286.621 I slot print_timing: id 0 | task 8655 | graph reallocs = 0 / 0 (same size) / (changed size) 11.31.286.698 I slot release: id 0 | task 8655 | stop processing: n_tokens = 2142, truncated = 0 11.31.288.009 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.855 11.31.288.103 I slot launch_slot_: id 0 | task 8662 | processing task, is_child = 0 11.31.288.204 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.926 MiB) 11.31.295.340 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 264.906 MiB) 11.31.301.932 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1169, t_last = 331638211032 11.31.302.096 I slot launch_slot_: id 2 | task 8663 | processing task, is_child = 0 11.31.302.189 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1137, t_last = 331638212273 11.31.302.307 I slot launch_slot_: id 3 | task 8664 | processing task, is_child = 0 11.35.136.348 I slot print_timing: id 1 | task 8656 | prompt eval time = 8899.57 ms / 2129 tokens ( 4.18 ms per token, 239.23 tokens per second) 11.35.136.351 I slot print_timing: id 1 | task 8656 | eval time = 3848.34 ms / 2 tokens ( 3848.34 ms per token, 0.26 tokens per second) 11.35.136.351 I slot print_timing: id 1 | task 8656 | total time = 12747.91 ms / 2131 tokens 11.35.136.352 I slot print_timing: id 1 | task 8656 | graphs reused = 7277 11.35.136.352 I slot print_timing: id 1 | task 8656 | graph reallocs = 0 / 0 (same size) / (changed size) 11.35.136.451 I slot release: id 1 | task 8656 | stop processing: n_tokens = 2139, truncated = 0 11.35.136.474 I slot print_timing: id 0 | task 8662 | prompt processing, n_tokens = 249, progress = 1.00, t = 3.83 s / 64.96 tokens per second 11.35.139.538 I slot print_timing: id 2 | task 8663 | prompt processing, n_tokens = 1580, progress = 0.75, t = 3.83 s / 412.41 tokens per second 11.35.141.547 I slot print_timing: id 3 | task 8664 | prompt processing, n_tokens = 218, progress = 0.11, t = 3.83 s / 56.91 tokens per second 11.38.252.958 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.842 (> 0.100 thold), f_keep = 0.856 11.38.253.110 I slot launch_slot_: id 1 | task 8667 | processing task, is_child = 0 11.38.256.922 I slot print_timing: id 2 | task 8663 | prompt processing, n_tokens = 1795, progress = 0.86, t = 6.95 s / 258.36 tokens per second 11.38.258.845 I slot print_timing: id 3 | task 8664 | prompt processing, n_tokens = 1627, progress = 0.76, t = 6.95 s / 234.19 tokens per second 11.39.972.922 I slot print_timing: id 0 | task 8662 | prompt eval time = 6950.62 ms / 253 tokens ( 27.47 ms per token, 36.40 tokens per second) 11.39.972.928 I slot print_timing: id 0 | task 8662 | eval time = 1719.98 ms / 2 tokens ( 1719.98 ms per token, 0.58 tokens per second) 11.39.972.928 I slot print_timing: id 0 | task 8662 | total time = 8670.60 ms / 255 tokens 11.39.972.929 I slot print_timing: id 0 | task 8662 | graphs reused = 7277 11.39.972.929 I slot print_timing: id 0 | task 8662 | graph reallocs = 0 / 0 (same size) / (changed size) 11.39.973.060 I slot release: id 0 | task 8662 | stop processing: n_tokens = 2086, truncated = 0 11.39.976.401 I slot print_timing: id 2 | task 8663 | prompt processing, n_tokens = 2092, progress = 1.00, t = 8.67 s / 241.36 tokens per second 11.39.978.603 I slot print_timing: id 3 | task 8664 | prompt processing, n_tokens = 1795, progress = 0.84, t = 8.67 s / 207.10 tokens per second 11.40.715.864 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.869 (> 0.100 thold), f_keep = 0.878 11.40.715.978 I slot launch_slot_: id 0 | task 8670 | processing task, is_child = 0 11.40.719.772 I slot print_timing: id 3 | task 8664 | prompt processing, n_tokens = 2139, progress = 1.00, t = 9.41 s / 227.33 tokens per second 11.41.346.165 I slot print_timing: id 1 | task 8667 | prompt eval time = 2461.51 ms / 344 tokens ( 7.16 ms per token, 139.75 tokens per second) 11.41.346.168 I slot print_timing: id 1 | task 8667 | eval time = 631.52 ms / 2 tokens ( 631.52 ms per token, 1.58 tokens per second) 11.41.346.168 I slot print_timing: id 1 | task 8667 | total time = 3093.03 ms / 346 tokens 11.41.346.173 I slot print_timing: id 1 | task 8667 | graphs reused = 7277 11.41.346.174 I slot print_timing: id 1 | task 8667 | graph reallocs = 0 / 0 (same size) / (changed size) 11.41.346.267 I slot release: id 1 | task 8667 | stop processing: n_tokens = 2177, truncated = 0 11.41.347.492 I slot print_timing: id 2 | task 8663 | prompt eval time = 9411.68 ms / 2096 tokens ( 4.49 ms per token, 222.70 tokens per second) 11.41.347.494 I slot print_timing: id 2 | task 8663 | eval time = 631.65 ms / 2 tokens ( 631.65 ms per token, 1.58 tokens per second) 11.41.347.495 I slot print_timing: id 2 | task 8663 | total time = 10043.34 ms / 2098 tokens 11.41.347.495 I slot print_timing: id 2 | task 8663 | graphs reused = 7277 11.41.347.496 I slot print_timing: id 2 | task 8663 | graph reallocs = 0 / 0 (same size) / (changed size) 11.41.347.559 I slot release: id 2 | task 8663 | stop processing: n_tokens = 2106, truncated = 0 11.41.411.546 I slot print_timing: id 3 | task 8664 | prompt eval time = 10044.39 ms / 2143 tokens ( 4.69 ms per token, 213.35 tokens per second) 11.41.411.551 I slot print_timing: id 3 | task 8664 | eval time = 62.76 ms / 2 tokens ( 62.76 ms per token, 15.93 tokens per second) 11.41.411.552 I slot print_timing: id 3 | task 8664 | total time = 10107.15 ms / 2145 tokens 11.41.411.552 I slot print_timing: id 3 | task 8664 | graphs reused = 7277 11.41.411.552 I slot print_timing: id 3 | task 8664 | graph reallocs = 0 / 0 (same size) / (changed size) 11.41.411.625 I slot release: id 3 | task 8664 | stop processing: n_tokens = 2153, truncated = 0 11.41.411.633 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.806 (> 0.100 thold), f_keep = 0.842 11.41.411.685 I slot launch_slot_: id 1 | task 8673 | processing task, is_child = 0 11.41.411.805 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.359 MiB) 11.41.427.329 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.920 MiB) 11.41.434.773 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.838 (> 0.100 thold), f_keep = 0.870 11.41.434.861 I slot launch_slot_: id 2 | task 8674 | processing task, is_child = 0 11.41.434.980 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.851 11.41.435.020 I slot launch_slot_: id 3 | task 8675 | processing task, is_child = 0 11.43.483.475 I slot print_timing: id 0 | task 8670 | prompt eval time = 694.48 ms / 276 tokens ( 2.52 ms per token, 397.42 tokens per second) 11.43.483.479 I slot print_timing: id 0 | task 8670 | eval time = 2072.99 ms / 2 tokens ( 2072.99 ms per token, 0.48 tokens per second) 11.43.483.479 I slot print_timing: id 0 | task 8670 | total time = 2767.47 ms / 278 tokens 11.43.483.480 I slot print_timing: id 0 | task 8670 | graphs reused = 7277 11.43.483.480 I slot print_timing: id 0 | task 8670 | graph reallocs = 0 / 0 (same size) / (changed size) 11.43.483.641 I slot release: id 0 | task 8670 | stop processing: n_tokens = 2108, truncated = 0 11.43.555.659 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.869 11.43.555.728 I slot launch_slot_: id 0 | task 8678 | processing task, is_child = 0 11.44.088.863 I slot print_timing: id 1 | task 8673 | prompt eval time = 2118.36 ms / 441 tokens ( 4.80 ms per token, 208.18 tokens per second) 11.44.088.866 I slot print_timing: id 1 | task 8673 | eval time = 535.47 ms / 2 tokens ( 535.47 ms per token, 1.87 tokens per second) 11.44.088.866 I slot print_timing: id 1 | task 8673 | total time = 2653.83 ms / 443 tokens 11.44.088.867 I slot print_timing: id 1 | task 8673 | graphs reused = 7277 11.44.088.867 I slot print_timing: id 1 | task 8673 | graph reallocs = 0 / 0 (same size) / (changed size) 11.44.088.966 I slot release: id 1 | task 8673 | stop processing: n_tokens = 2273, truncated = 0 11.44.090.200 I slot print_timing: id 2 | task 8674 | prompt eval time = 2116.53 ms / 353 tokens ( 6.00 ms per token, 166.78 tokens per second) 11.44.090.203 I slot print_timing: id 2 | task 8674 | eval time = 535.65 ms / 2 tokens ( 535.65 ms per token, 1.87 tokens per second) 11.44.090.203 I slot print_timing: id 2 | task 8674 | total time = 2652.18 ms / 355 tokens 11.44.090.203 I slot print_timing: id 2 | task 8674 | graphs reused = 7277 11.44.090.204 I slot print_timing: id 2 | task 8674 | graph reallocs = 0 / 0 (same size) / (changed size) 11.44.090.276 I slot release: id 2 | task 8674 | stop processing: n_tokens = 2186, truncated = 0 11.44.091.499 I slot print_timing: id 3 | task 8675 | prompt eval time = 2115.90 ms / 189 tokens ( 11.20 ms per token, 89.32 tokens per second) 11.44.091.507 I slot print_timing: id 3 | task 8675 | eval time = 535.85 ms / 2 tokens ( 535.85 ms per token, 1.87 tokens per second) 11.44.091.508 I slot print_timing: id 3 | task 8675 | total time = 2651.75 ms / 191 tokens 11.44.091.510 I slot print_timing: id 3 | task 8675 | graphs reused = 7277 11.44.091.511 I slot print_timing: id 3 | task 8675 | graph reallocs = 0 / 0 (same size) / (changed size) 11.44.091.570 I slot release: id 3 | task 8675 | stop processing: n_tokens = 2022, truncated = 0 11.44.130.782 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.806 11.44.130.840 I slot launch_slot_: id 1 | task 8681 | processing task, is_child = 0 11.44.130.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 234.529 MiB) 11.44.130.971 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.301 MiB) 11.44.139.686 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.617 MiB) 11.44.148.092 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.838 11.44.148.157 I slot launch_slot_: id 2 | task 8682 | processing task, is_child = 0 11.44.148.267 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.852 (> 0.100 thold), f_keep = 0.906 11.44.148.306 I slot launch_slot_: id 3 | task 8683 | processing task, is_child = 0 11.45.897.200 I slot print_timing: id 0 | task 8678 | prompt eval time = 575.04 ms / 232 tokens ( 2.48 ms per token, 403.45 tokens per second) 11.45.897.207 I slot print_timing: id 0 | task 8678 | eval time = 1766.42 ms / 2 tokens ( 1766.42 ms per token, 0.57 tokens per second) 11.45.897.209 I slot print_timing: id 0 | task 8678 | total time = 2341.45 ms / 234 tokens 11.45.897.210 I slot print_timing: id 0 | task 8678 | graphs reused = 7277 11.45.897.210 I slot print_timing: id 0 | task 8678 | graph reallocs = 0 / 0 (same size) / (changed size) 11.45.897.355 I slot release: id 0 | task 8678 | stop processing: n_tokens = 2064, truncated = 0 11.45.969.140 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.887 11.45.969.198 I slot launch_slot_: id 0 | task 8686 | processing task, is_child = 0 11.46.395.626 I slot print_timing: id 1 | task 8681 | prompt eval time = 1818.65 ms / 226 tokens ( 8.05 ms per token, 124.27 tokens per second) 11.46.395.632 I slot print_timing: id 1 | task 8681 | eval time = 428.66 ms / 2 tokens ( 428.66 ms per token, 2.33 tokens per second) 11.46.395.632 I slot print_timing: id 1 | task 8681 | total time = 2247.31 ms / 228 tokens 11.46.395.633 I slot print_timing: id 1 | task 8681 | graphs reused = 7277 11.46.395.633 I slot print_timing: id 1 | task 8681 | graph reallocs = 0 / 0 (same size) / (changed size) 11.46.395.737 I slot release: id 1 | task 8681 | stop processing: n_tokens = 2058, truncated = 0 11.46.396.964 I slot print_timing: id 2 | task 8682 | prompt eval time = 1817.97 ms / 281 tokens ( 6.47 ms per token, 154.57 tokens per second) 11.46.396.968 I slot print_timing: id 2 | task 8682 | eval time = 428.90 ms / 2 tokens ( 428.90 ms per token, 2.33 tokens per second) 11.46.396.969 I slot print_timing: id 2 | task 8682 | total time = 2246.88 ms / 283 tokens 11.46.396.969 I slot print_timing: id 2 | task 8682 | graphs reused = 7277 11.46.396.970 I slot print_timing: id 2 | task 8682 | graph reallocs = 0 / 0 (same size) / (changed size) 11.46.397.050 I slot release: id 2 | task 8682 | stop processing: n_tokens = 2113, truncated = 0 11.46.398.295 I slot print_timing: id 3 | task 8683 | prompt eval time = 1816.10 ms / 318 tokens ( 5.71 ms per token, 175.10 tokens per second) 11.46.398.299 I slot print_timing: id 3 | task 8683 | eval time = 429.16 ms / 2 tokens ( 429.16 ms per token, 2.33 tokens per second) 11.46.398.300 I slot print_timing: id 3 | task 8683 | total time = 2245.26 ms / 320 tokens 11.46.398.300 I slot print_timing: id 3 | task 8683 | graphs reused = 7277 11.46.398.300 I slot print_timing: id 3 | task 8683 | graph reallocs = 0 / 0 (same size) / (changed size) 11.46.398.365 I slot release: id 3 | task 8683 | stop processing: n_tokens = 2151, truncated = 0 11.46.437.619 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.845 (> 0.100 thold), f_keep = 0.867 11.46.437.666 I slot launch_slot_: id 2 | task 8689 | processing task, is_child = 0 11.46.437.804 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.688 MiB) 11.46.447.188 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 364.729 MiB) 11.46.464.497 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.864 (> 0.100 thold), f_keep = 0.890 11.46.464.563 I slot launch_slot_: id 1 | task 8690 | processing task, is_child = 0 11.46.464.677 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.851 11.46.464.713 I slot launch_slot_: id 3 | task 8691 | processing task, is_child = 0 11.48.510.485 I slot print_timing: id 0 | task 8686 | prompt eval time = 468.41 ms / 193 tokens ( 2.43 ms per token, 412.03 tokens per second) 11.48.510.491 I slot print_timing: id 0 | task 8686 | eval time = 2072.86 ms / 2 tokens ( 2072.86 ms per token, 0.48 tokens per second) 11.48.510.492 I slot print_timing: id 0 | task 8686 | total time = 2541.27 ms / 195 tokens 11.48.510.493 I slot print_timing: id 0 | task 8686 | graphs reused = 7277 11.48.510.493 I slot print_timing: id 0 | task 8686 | graph reallocs = 0 / 0 (same size) / (changed size) 11.48.510.639 I slot release: id 0 | task 8686 | stop processing: n_tokens = 2025, truncated = 0 11.48.581.392 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.904 11.48.581.459 I slot launch_slot_: id 0 | task 8694 | processing task, is_child = 0 11.49.007.620 I slot print_timing: id 1 | task 8690 | prompt eval time = 2114.44 ms / 289 tokens ( 7.32 ms per token, 136.68 tokens per second) 11.49.007.623 I slot print_timing: id 1 | task 8690 | eval time = 428.46 ms / 2 tokens ( 428.46 ms per token, 2.33 tokens per second) 11.49.007.623 I slot print_timing: id 1 | task 8690 | total time = 2542.89 ms / 291 tokens 11.49.007.624 I slot print_timing: id 1 | task 8690 | graphs reused = 7277 11.49.007.624 I slot print_timing: id 1 | task 8690 | graph reallocs = 0 / 0 (same size) / (changed size) 11.49.007.772 I slot release: id 1 | task 8690 | stop processing: n_tokens = 2121, truncated = 0 11.49.008.946 I slot print_timing: id 2 | task 8689 | prompt eval time = 2113.87 ms / 336 tokens ( 6.29 ms per token, 158.95 tokens per second) 11.49.008.949 I slot print_timing: id 2 | task 8689 | eval time = 428.64 ms / 2 tokens ( 428.64 ms per token, 2.33 tokens per second) 11.49.008.950 I slot print_timing: id 2 | task 8689 | total time = 2542.51 ms / 338 tokens 11.49.008.950 I slot print_timing: id 2 | task 8689 | graphs reused = 7277 11.49.008.950 I slot print_timing: id 2 | task 8689 | graph reallocs = 0 / 0 (same size) / (changed size) 11.49.009.022 I slot release: id 2 | task 8689 | stop processing: n_tokens = 2169, truncated = 0 11.49.010.231 I slot print_timing: id 3 | task 8691 | prompt eval time = 2113.25 ms / 387 tokens ( 5.46 ms per token, 183.13 tokens per second) 11.49.010.233 I slot print_timing: id 3 | task 8691 | eval time = 428.84 ms / 2 tokens ( 428.84 ms per token, 2.33 tokens per second) 11.49.010.234 I slot print_timing: id 3 | task 8691 | total time = 2542.09 ms / 389 tokens 11.49.010.234 I slot print_timing: id 3 | task 8691 | graphs reused = 7277 11.49.010.235 I slot print_timing: id 3 | task 8691 | graph reallocs = 0 / 0 (same size) / (changed size) 11.49.010.298 I slot release: id 3 | task 8691 | stop processing: n_tokens = 2219, truncated = 0 11.49.049.715 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.863 11.49.049.775 I slot launch_slot_: id 1 | task 8697 | processing task, is_child = 0 11.49.049.918 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.441 MiB) 11.49.073.207 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.512 MiB) 11.49.097.555 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.844 11.49.097.632 I slot launch_slot_: id 2 | task 8698 | processing task, is_child = 0 11.49.097.753 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.821 (> 0.100 thold), f_keep = 0.825 11.49.097.791 I slot launch_slot_: id 3 | task 8699 | processing task, is_child = 0 11.50.889.639 I slot print_timing: id 0 | task 8694 | prompt eval time = 468.25 ms / 190 tokens ( 2.46 ms per token, 405.77 tokens per second) 11.50.889.646 I slot print_timing: id 0 | task 8694 | eval time = 1839.92 ms / 2 tokens ( 1839.92 ms per token, 0.54 tokens per second) 11.50.889.647 I slot print_timing: id 0 | task 8694 | total time = 2308.16 ms / 192 tokens 11.50.889.647 I slot print_timing: id 0 | task 8694 | graphs reused = 7277 11.50.889.648 I slot print_timing: id 0 | task 8694 | graph reallocs = 0 / 0 (same size) / (changed size) 11.50.889.795 I slot release: id 0 | task 8694 | stop processing: n_tokens = 2022, truncated = 0 11.50.960.628 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.906 11.50.960.719 I slot launch_slot_: id 0 | task 8702 | processing task, is_child = 0 11.51.496.110 I slot print_timing: id 1 | task 8697 | prompt eval time = 1860.57 ms / 212 tokens ( 8.78 ms per token, 113.94 tokens per second) 11.51.496.112 I slot print_timing: id 1 | task 8697 | eval time = 537.74 ms / 2 tokens ( 537.74 ms per token, 1.86 tokens per second) 11.51.496.113 I slot print_timing: id 1 | task 8697 | total time = 2398.31 ms / 214 tokens 11.51.496.113 I slot print_timing: id 1 | task 8697 | graphs reused = 7277 11.51.496.113 I slot print_timing: id 1 | task 8697 | graph reallocs = 0 / 0 (same size) / (changed size) 11.51.496.229 I slot release: id 1 | task 8697 | stop processing: n_tokens = 2044, truncated = 0 11.51.497.484 I slot print_timing: id 2 | task 8698 | prompt eval time = 1859.95 ms / 249 tokens ( 7.47 ms per token, 133.87 tokens per second) 11.51.497.488 I slot print_timing: id 2 | task 8698 | eval time = 537.98 ms / 2 tokens ( 537.98 ms per token, 1.86 tokens per second) 11.51.497.488 I slot print_timing: id 2 | task 8698 | total time = 2397.93 ms / 251 tokens 11.51.497.488 I slot print_timing: id 2 | task 8698 | graphs reused = 7277 11.51.497.489 I slot print_timing: id 2 | task 8698 | graph reallocs = 0 / 0 (same size) / (changed size) 11.51.497.565 I slot release: id 2 | task 8698 | stop processing: n_tokens = 2081, truncated = 0 11.51.498.795 I slot print_timing: id 3 | task 8699 | prompt eval time = 1859.36 ms / 399 tokens ( 4.66 ms per token, 214.59 tokens per second) 11.51.498.797 I slot print_timing: id 3 | task 8699 | eval time = 538.17 ms / 2 tokens ( 538.17 ms per token, 1.86 tokens per second) 11.51.498.798 I slot print_timing: id 3 | task 8699 | total time = 2397.53 ms / 401 tokens 11.51.498.798 I slot print_timing: id 3 | task 8699 | graphs reused = 7277 11.51.498.798 I slot print_timing: id 3 | task 8699 | graph reallocs = 0 / 0 (same size) / (changed size) 11.51.498.868 I slot release: id 3 | task 8699 | stop processing: n_tokens = 2231, truncated = 0 11.51.538.423 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.821 11.51.538.468 I slot launch_slot_: id 3 | task 8705 | processing task, is_child = 0 11.51.538.599 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.617 MiB) 11.51.547.272 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 364.589 MiB) 11.51.555.787 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.896 11.51.555.849 I slot launch_slot_: id 1 | task 8706 | processing task, is_child = 0 11.51.555.968 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.880 11.51.556.002 I slot launch_slot_: id 2 | task 8707 | processing task, is_child = 0 11.52.718.656 I slot print_timing: id 0 | task 8702 | prompt eval time = 577.69 ms / 238 tokens ( 2.43 ms per token, 411.99 tokens per second) 11.52.718.663 I slot print_timing: id 0 | task 8702 | eval time = 1180.23 ms / 2 tokens ( 1180.23 ms per token, 0.85 tokens per second) 11.52.718.663 I slot print_timing: id 0 | task 8702 | total time = 1757.92 ms / 240 tokens 11.52.718.664 I slot print_timing: id 0 | task 8702 | graphs reused = 7277 11.52.718.664 I slot print_timing: id 0 | task 8702 | graph reallocs = 0 / 0 (same size) / (changed size) 11.52.718.827 I slot release: id 0 | task 8702 | stop processing: n_tokens = 2071, truncated = 0 11.52.789.474 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2071, t_last = 331659714670 11.52.789.608 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.547 MiB) 11.52.789.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 254.290 MiB) 11.52.799.820 I slot launch_slot_: id 0 | task 8710 | processing task, is_child = 0 11.54.562.078 I slot print_timing: id 1 | task 8706 | prompt eval time = 1231.27 ms / 123 tokens ( 10.01 ms per token, 99.90 tokens per second) 11.54.562.085 I slot print_timing: id 1 | task 8706 | eval time = 1774.79 ms / 2 tokens ( 1774.79 ms per token, 0.56 tokens per second) 11.54.562.086 I slot print_timing: id 1 | task 8706 | total time = 3006.06 ms / 125 tokens 11.54.562.086 I slot print_timing: id 1 | task 8706 | graphs reused = 7277 11.54.562.087 I slot print_timing: id 1 | task 8706 | graph reallocs = 0 / 0 (same size) / (changed size) 11.54.562.230 I slot release: id 1 | task 8706 | stop processing: n_tokens = 1955, truncated = 0 11.54.563.422 I slot print_timing: id 2 | task 8707 | prompt eval time = 1230.67 ms / 172 tokens ( 7.16 ms per token, 139.76 tokens per second) 11.54.563.427 I slot print_timing: id 2 | task 8707 | eval time = 1775.02 ms / 2 tokens ( 1775.02 ms per token, 0.56 tokens per second) 11.54.563.427 I slot print_timing: id 2 | task 8707 | total time = 3005.69 ms / 174 tokens 11.54.563.428 I slot print_timing: id 2 | task 8707 | graphs reused = 7277 11.54.563.428 I slot print_timing: id 2 | task 8707 | graph reallocs = 0 / 0 (same size) / (changed size) 11.54.563.498 I slot release: id 2 | task 8707 | stop processing: n_tokens = 2004, truncated = 0 11.54.564.727 I slot print_timing: id 3 | task 8705 | prompt eval time = 1229.99 ms / 208 tokens ( 5.91 ms per token, 169.11 tokens per second) 11.54.564.729 I slot print_timing: id 3 | task 8705 | eval time = 1775.26 ms / 2 tokens ( 1775.26 ms per token, 0.56 tokens per second) 11.54.564.730 I slot print_timing: id 3 | task 8705 | total time = 3005.24 ms / 210 tokens 11.54.564.730 I slot print_timing: id 3 | task 8705 | graphs reused = 7277 11.54.564.731 I slot print_timing: id 3 | task 8705 | graph reallocs = 0 / 0 (same size) / (changed size) 11.54.564.790 I slot release: id 3 | task 8705 | stop processing: n_tokens = 2041, truncated = 0 11.55.179.596 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1955, t_last = 331661558073 11.55.179.752 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 256.751 MiB) 11.55.614.219 I slot launch_slot_: id 1 | task 8714 | processing task, is_child = 0 11.55.614.358 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 305.905 MiB) 11.55.634.493 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.485 MiB) 11.55.634.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.648 MiB) 11.55.656.334 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2004, t_last = 331661559340 11.55.656.523 I slot launch_slot_: id 2 | task 8715 | processing task, is_child = 0 11.55.656.633 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2041, t_last = 331661560633 11.55.656.772 I slot launch_slot_: id 3 | task 8716 | processing task, is_child = 0 11.59.524.039 I slot print_timing: id 1 | task 8714 | prompt processing, n_tokens = 479, progress = 0.49, t = 3.86 s / 123.96 tokens per second 11.59.527.594 I slot print_timing: id 2 | task 8715 | prompt processing, n_tokens = 1155, progress = 0.69, t = 3.86 s / 298.92 tokens per second 11.59.530.172 I slot print_timing: id 3 | task 8716 | prompt processing, n_tokens = 410, progress = 0.27, t = 3.86 s / 106.12 tokens per second 12.01.690.569 I slot print_timing: id 0 | task 8710 | prompt eval time = 6724.19 ms / 1466 tokens ( 4.59 ms per token, 218.02 tokens per second) 12.01.690.578 I slot print_timing: id 0 | task 8710 | eval time = 2166.52 ms / 2 tokens ( 2166.52 ms per token, 0.46 tokens per second) 12.01.690.579 I slot print_timing: id 0 | task 8710 | total time = 8890.71 ms / 1468 tokens 12.01.690.579 I slot print_timing: id 0 | task 8710 | graphs reused = 7277 12.01.690.580 I slot print_timing: id 0 | task 8710 | graph reallocs = 0 / 0 (same size) / (changed size) 12.01.690.687 I slot release: id 0 | task 8710 | stop processing: n_tokens = 1476, truncated = 0 12.01.690.713 I slot print_timing: id 1 | task 8714 | prompt processing, n_tokens = 848, progress = 0.85, t = 6.03 s / 140.61 tokens per second 12.01.694.324 I slot print_timing: id 2 | task 8715 | prompt processing, n_tokens = 1264, progress = 0.76, t = 6.03 s / 209.60 tokens per second 12.01.696.301 I slot print_timing: id 3 | task 8716 | prompt processing, n_tokens = 1021, progress = 0.67, t = 6.03 s / 169.31 tokens per second 12.02.972.854 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 331668686530 12.03.288.425 I slot launch_slot_: id 0 | task 8720 | processing task, is_child = 0 12.03.288.708 I slot print_timing: id 1 | task 8714 | prompt processing, n_tokens = 991, progress = 1.00, t = 7.31 s / 135.49 tokens per second 12.03.290.464 I slot print_timing: id 2 | task 8715 | prompt processing, n_tokens = 1667, progress = 1.00, t = 7.31 s / 227.92 tokens per second 12.03.292.275 I slot print_timing: id 3 | task 8716 | prompt processing, n_tokens = 1264, progress = 0.82, t = 7.31 s / 172.83 tokens per second 12.04.753.375 I slot print_timing: id 3 | task 8716 | prompt processing, n_tokens = 1533, progress = 1.00, t = 9.09 s / 168.68 tokens per second 12.05.534.494 I slot print_timing: id 1 | task 8714 | prompt eval time = 9089.97 ms / 995 tokens ( 9.14 ms per token, 109.46 tokens per second) 12.05.534.497 I slot print_timing: id 1 | task 8714 | eval time = 785.85 ms / 2 tokens ( 785.85 ms per token, 1.27 tokens per second) 12.05.534.497 I slot print_timing: id 1 | task 8714 | total time = 9875.82 ms / 997 tokens 12.05.534.498 I slot print_timing: id 1 | task 8714 | graphs reused = 7277 12.05.534.498 I slot print_timing: id 1 | task 8714 | graph reallocs = 0 / 0 (same size) / (changed size) 12.05.534.586 I slot release: id 1 | task 8714 | stop processing: n_tokens = 1005, truncated = 0 12.05.535.792 I slot print_timing: id 2 | task 8715 | prompt eval time = 9090.87 ms / 1671 tokens ( 5.44 ms per token, 183.81 tokens per second) 12.05.535.796 I slot print_timing: id 2 | task 8715 | eval time = 785.99 ms / 2 tokens ( 785.99 ms per token, 1.27 tokens per second) 12.05.535.796 I slot print_timing: id 2 | task 8715 | total time = 9876.86 ms / 1673 tokens 12.05.535.796 I slot print_timing: id 2 | task 8715 | graphs reused = 7277 12.05.535.797 I slot print_timing: id 2 | task 8715 | graph reallocs = 0 / 0 (same size) / (changed size) 12.05.535.912 I slot release: id 2 | task 8715 | stop processing: n_tokens = 1681, truncated = 0 12.05.870.081 I slot print_timing: id 3 | task 8716 | prompt eval time = 9877.96 ms / 1537 tokens ( 6.43 ms per token, 155.60 tokens per second) 12.05.870.084 I slot print_timing: id 3 | task 8716 | eval time = 332.93 ms / 2 tokens ( 332.93 ms per token, 3.00 tokens per second) 12.05.870.084 I slot print_timing: id 3 | task 8716 | total time = 10210.89 ms / 1539 tokens 12.05.870.085 I slot print_timing: id 3 | task 8716 | graphs reused = 7277 12.05.870.085 I slot print_timing: id 3 | task 8716 | graph reallocs = 0 / 0 (same size) / (changed size) 12.05.870.193 I slot release: id 3 | task 8716 | stop processing: n_tokens = 1547, truncated = 0 12.05.870.208 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.881 12.05.870.296 I slot launch_slot_: id 1 | task 8724 | processing task, is_child = 0 12.05.870.428 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.589 MiB) 12.05.870.437 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.572 MiB) 12.05.879.681 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 266.137 MiB) 12.05.899.281 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1681, t_last = 331672531756 12.05.899.465 I slot launch_slot_: id 2 | task 8725 | processing task, is_child = 0 12.05.899.562 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1547, t_last = 331672866036 12.05.899.686 I slot launch_slot_: id 3 | task 8726 | processing task, is_child = 0 12.09.311.830 I slot print_timing: id 0 | task 8720 | prompt eval time = 4487.28 ms / 985 tokens ( 4.56 ms per token, 219.51 tokens per second) 12.09.311.834 I slot print_timing: id 0 | task 8720 | eval time = 1536.09 ms / 2 tokens ( 1536.09 ms per token, 0.65 tokens per second) 12.09.311.834 I slot print_timing: id 0 | task 8720 | total time = 6023.37 ms / 987 tokens 12.09.311.835 I slot print_timing: id 0 | task 8720 | graphs reused = 7277 12.09.311.835 I slot print_timing: id 0 | task 8720 | graph reallocs = 0 / 0 (same size) / (changed size) 12.09.311.935 I slot release: id 0 | task 8720 | stop processing: n_tokens = 995, truncated = 0 12.09.313.243 I slot print_timing: id 2 | task 8725 | prompt processing, n_tokens = 848, progress = 0.87, t = 3.41 s / 248.89 tokens per second 12.09.316.284 I slot print_timing: id 3 | task 8726 | prompt processing, n_tokens = 848, progress = 0.87, t = 3.41 s / 248.91 tokens per second 12.09.866.897 I slot print_timing: id 1 | task 8724 | prompt eval time = 3411.61 ms / 82 tokens ( 41.61 ms per token, 24.04 tokens per second) 12.09.866.900 I slot print_timing: id 1 | task 8724 | eval time = 553.68 ms / 2 tokens ( 553.68 ms per token, 1.81 tokens per second) 12.09.866.901 I slot print_timing: id 1 | task 8724 | total time = 3965.30 ms / 84 tokens 12.09.866.902 I slot print_timing: id 1 | task 8724 | graphs reused = 7277 12.09.866.902 I slot print_timing: id 1 | task 8724 | graph reallocs = 0 / 0 (same size) / (changed size) 12.09.866.977 I slot release: id 1 | task 8724 | stop processing: n_tokens = 968, truncated = 0 12.09.866.994 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.888 12.09.867.169 I slot launch_slot_: id 0 | task 8730 | processing task, is_child = 0 12.09.867.268 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.345 MiB) 12.09.877.424 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.913 12.09.877.495 I slot launch_slot_: id 1 | task 8731 | processing task, is_child = 0 12.09.880.973 I slot print_timing: id 2 | task 8725 | prompt processing, n_tokens = 969, progress = 1.00, t = 3.96 s / 244.56 tokens per second 12.09.882.719 I slot print_timing: id 3 | task 8726 | prompt processing, n_tokens = 974, progress = 1.00, t = 3.96 s / 245.84 tokens per second 12.10.436.726 I slot print_timing: id 2 | task 8725 | prompt eval time = 4450.22 ms / 973 tokens ( 4.57 ms per token, 218.64 tokens per second) 12.10.436.728 I slot print_timing: id 2 | task 8725 | eval time = 82.90 ms / 2 tokens ( 82.90 ms per token, 12.06 tokens per second) 12.10.436.729 I slot print_timing: id 2 | task 8725 | total time = 4533.13 ms / 975 tokens 12.10.436.729 I slot print_timing: id 2 | task 8725 | graphs reused = 7277 12.10.436.730 I slot print_timing: id 2 | task 8725 | graph reallocs = 0 / 0 (same size) / (changed size) 12.10.436.776 I slot release: id 2 | task 8725 | stop processing: n_tokens = 983, truncated = 0 12.10.437.860 I slot print_timing: id 3 | task 8726 | prompt eval time = 4451.22 ms / 978 tokens ( 4.55 ms per token, 219.72 tokens per second) 12.10.437.864 I slot print_timing: id 3 | task 8726 | eval time = 82.77 ms / 2 tokens ( 82.77 ms per token, 12.08 tokens per second) 12.10.437.864 I slot print_timing: id 3 | task 8726 | total time = 4533.99 ms / 980 tokens 12.10.437.864 I slot print_timing: id 3 | task 8726 | graphs reused = 7277 12.10.437.865 I slot print_timing: id 3 | task 8726 | graph reallocs = 0 / 0 (same size) / (changed size) 12.10.437.899 I slot release: id 3 | task 8726 | stop processing: n_tokens = 988, truncated = 0 12.10.472.441 I slot print_timing: id 0 | task 8730 | prompt eval time = 557.07 ms / 93 tokens ( 5.99 ms per token, 166.94 tokens per second) 12.10.472.447 I slot print_timing: id 0 | task 8730 | eval time = 37.87 ms / 2 tokens ( 37.87 ms per token, 26.41 tokens per second) 12.10.472.447 I slot print_timing: id 0 | task 8730 | total time = 594.94 ms / 95 tokens 12.10.472.448 I slot print_timing: id 0 | task 8730 | graphs reused = 7277 12.10.472.451 I slot print_timing: id 0 | task 8730 | graph reallocs = 0 / 0 (same size) / (changed size) 12.10.472.482 I slot release: id 0 | task 8730 | stop processing: n_tokens = 978, truncated = 0 12.10.473.620 I slot print_timing: id 1 | task 8731 | prompt eval time = 556.43 ms / 98 tokens ( 5.68 ms per token, 176.12 tokens per second) 12.10.473.622 I slot print_timing: id 1 | task 8731 | eval time = 37.94 ms / 2 tokens ( 37.94 ms per token, 26.36 tokens per second) 12.10.473.624 I slot print_timing: id 1 | task 8731 | total time = 594.37 ms / 100 tokens 12.10.473.624 I slot print_timing: id 1 | task 8731 | graphs reused = 7277 12.10.473.624 I slot print_timing: id 1 | task 8731 | graph reallocs = 0 / 0 (same size) / (changed size) 12.10.473.653 I slot release: id 1 | task 8731 | stop processing: n_tokens = 983, truncated = 0 12.10.473.658 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 983, t_last = 331677432618 12.10.473.743 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.477 MiB) 12.10.480.004 I slot launch_slot_: id 2 | task 8735 | processing task, is_child = 0 12.10.480.083 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.071 MiB) 12.10.488.463 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.437 MiB) 12.10.495.745 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 246.906 MiB) 12.10.502.944 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 331677433741 12.10.503.083 I slot launch_slot_: id 3 | task 8736 | processing task, is_child = 0 12.10.503.239 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 978, t_last = 331677468325 12.10.503.344 I slot launch_slot_: id 0 | task 8737 | processing task, is_child = 0 12.10.503.423 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 983, t_last = 331677469495 12.10.503.533 I slot launch_slot_: id 1 | task 8738 | processing task, is_child = 0 12.13.987.251 I slot print_timing: id 0 | task 8737 | prompt processing, n_tokens = 1086, progress = 0.68, t = 3.48 s / 311.74 tokens per second 12.14.244.610 I slot print_timing: id 1 | task 8738 | prompt processing, n_tokens = 962, progress = 0.59, t = 3.48 s / 276.16 tokens per second 12.17.148.487 I slot print_timing: id 0 | task 8737 | prompt processing, n_tokens = 1388, progress = 0.87, t = 6.64 s / 208.88 tokens per second 12.17.800.543 I slot print_timing: id 1 | task 8738 | prompt processing, n_tokens = 1114, progress = 0.69, t = 6.64 s / 167.65 tokens per second 12.19.859.114 I slot print_timing: id 0 | task 8737 | prompt processing, n_tokens = 1598, progress = 1.00, t = 9.36 s / 170.81 tokens per second 12.20.111.720 I slot print_timing: id 1 | task 8738 | prompt processing, n_tokens = 1388, progress = 0.85, t = 9.36 s / 148.36 tokens per second 12.20.115.252 I slot print_timing: id 2 | task 8735 | prompt processing, n_tokens = 695, progress = 0.86, t = 5.61 s / 123.79 tokens per second 12.20.116.953 I slot print_timing: id 3 | task 8736 | prompt processing, n_tokens = 1388, progress = 0.84, t = 5.61 s / 247.23 tokens per second 12.21.410.897 I slot print_timing: id 1 | task 8738 | prompt processing, n_tokens = 1626, progress = 1.00, t = 10.91 s / 149.09 tokens per second 12.21.414.923 I slot print_timing: id 2 | task 8735 | prompt processing, n_tokens = 810, progress = 1.00, t = 7.16 s / 113.05 tokens per second 12.21.417.137 I slot print_timing: id 3 | task 8736 | prompt processing, n_tokens = 1643, progress = 1.00, t = 7.16 s / 229.32 tokens per second 12.21.509.135 I slot print_timing: id 0 | task 8737 | prompt eval time = 10907.33 ms / 1602 tokens ( 6.81 ms per token, 146.87 tokens per second) 12.21.509.138 I slot print_timing: id 0 | task 8737 | eval time = 98.27 ms / 2 tokens ( 98.27 ms per token, 10.18 tokens per second) 12.21.509.139 I slot print_timing: id 0 | task 8737 | total time = 11005.59 ms / 1604 tokens 12.21.509.139 I slot print_timing: id 0 | task 8737 | graphs reused = 7277 12.21.509.140 I slot print_timing: id 0 | task 8737 | graph reallocs = 0 / 0 (same size) / (changed size) 12.21.509.222 I slot release: id 0 | task 8737 | stop processing: n_tokens = 1612, truncated = 0 12.21.549.367 I slot print_timing: id 1 | task 8738 | prompt eval time = 11006.74 ms / 1630 tokens ( 6.75 ms per token, 148.09 tokens per second) 12.21.549.370 I slot print_timing: id 1 | task 8738 | eval time = 38.85 ms / 2 tokens ( 38.85 ms per token, 25.74 tokens per second) 12.21.549.370 I slot print_timing: id 1 | task 8738 | total time = 11045.58 ms / 1632 tokens 12.21.549.370 I slot print_timing: id 1 | task 8738 | graphs reused = 7277 12.21.549.371 I slot print_timing: id 1 | task 8738 | graph reallocs = 0 / 0 (same size) / (changed size) 12.21.549.426 I slot release: id 1 | task 8738 | stop processing: n_tokens = 1640, truncated = 0 12.21.550.559 I slot print_timing: id 2 | task 8735 | prompt eval time = 7267.17 ms / 814 tokens ( 8.93 ms per token, 112.01 tokens per second) 12.21.550.561 I slot print_timing: id 2 | task 8735 | eval time = 38.77 ms / 2 tokens ( 38.77 ms per token, 25.80 tokens per second) 12.21.550.562 I slot print_timing: id 2 | task 8735 | total time = 7305.93 ms / 816 tokens 12.21.550.562 I slot print_timing: id 2 | task 8735 | graphs reused = 7277 12.21.550.562 I slot print_timing: id 2 | task 8735 | graph reallocs = 0 / 0 (same size) / (changed size) 12.21.550.588 I slot release: id 2 | task 8735 | stop processing: n_tokens = 824, truncated = 0 12.21.551.691 I slot print_timing: id 3 | task 8736 | prompt eval time = 7268.16 ms / 1647 tokens ( 4.41 ms per token, 226.60 tokens per second) 12.21.551.693 I slot print_timing: id 3 | task 8736 | eval time = 38.61 ms / 2 tokens ( 38.61 ms per token, 25.90 tokens per second) 12.21.551.693 I slot print_timing: id 3 | task 8736 | total time = 7306.78 ms / 1649 tokens 12.21.551.693 I slot print_timing: id 3 | task 8736 | graphs reused = 7277 12.21.551.693 I slot print_timing: id 3 | task 8736 | graph reallocs = 0 / 0 (same size) / (changed size) 12.21.551.736 I slot release: id 3 | task 8736 | stop processing: n_tokens = 1657, truncated = 0 12.21.551.743 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.855 (> 0.100 thold), f_keep = 0.883 12.21.551.811 I slot launch_slot_: id 0 | task 8745 | processing task, is_child = 0 12.21.551.915 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.063 MiB) 12.21.564.681 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 244.515 MiB) 12.21.570.300 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.143 MiB) 12.21.582.736 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1640, t_last = 331688545268 12.21.582.932 I slot launch_slot_: id 1 | task 8746 | processing task, is_child = 0 12.21.583.087 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 331688546430 12.21.583.183 I slot launch_slot_: id 2 | task 8747 | processing task, is_child = 0 12.21.583.282 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.814 (> 0.100 thold), f_keep = 0.859 12.21.583.317 I slot launch_slot_: id 3 | task 8748 | processing task, is_child = 0 12.25.475.328 I slot print_timing: id 1 | task 8746 | prompt processing, n_tokens = 721, progress = 0.86, t = 3.89 s / 185.45 tokens per second 12.25.479.059 I slot print_timing: id 2 | task 8747 | prompt processing, n_tokens = 721, progress = 0.84, t = 3.89 s / 185.46 tokens per second 12.26.056.211 I slot print_timing: id 0 | task 8745 | prompt eval time = 3890.79 ms / 241 tokens ( 16.14 ms per token, 61.94 tokens per second) 12.26.056.214 I slot print_timing: id 0 | task 8745 | eval time = 582.09 ms / 2 tokens ( 582.09 ms per token, 1.72 tokens per second) 12.26.056.214 I slot print_timing: id 0 | task 8745 | total time = 4472.88 ms / 243 tokens 12.26.056.215 I slot print_timing: id 0 | task 8745 | graphs reused = 7277 12.26.056.215 I slot print_timing: id 0 | task 8745 | graph reallocs = 0 / 0 (same size) / (changed size) 12.26.056.338 I slot release: id 0 | task 8745 | stop processing: n_tokens = 1666, truncated = 0 12.26.057.484 I slot print_timing: id 3 | task 8748 | prompt eval time = 3889.77 ms / 325 tokens ( 11.97 ms per token, 83.55 tokens per second) 12.26.057.486 I slot print_timing: id 3 | task 8748 | eval time = 582.18 ms / 2 tokens ( 582.18 ms per token, 1.72 tokens per second) 12.26.057.487 I slot print_timing: id 3 | task 8748 | total time = 4471.95 ms / 327 tokens 12.26.057.487 I slot print_timing: id 3 | task 8748 | graphs reused = 7277 12.26.057.487 I slot print_timing: id 3 | task 8748 | graph reallocs = 0 / 0 (same size) / (changed size) 12.26.057.555 I slot release: id 3 | task 8748 | stop processing: n_tokens = 1750, truncated = 0 12.26.057.566 I slot print_timing: id 1 | task 8746 | prompt processing, n_tokens = 831, progress = 1.00, t = 4.47 s / 185.91 tokens per second 12.26.060.445 I slot print_timing: id 2 | task 8747 | prompt processing, n_tokens = 858, progress = 1.00, t = 4.47 s / 191.96 tokens per second 12.26.105.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1666, t_last = 331693052181 12.26.105.665 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 258.017 MiB) 12.26.105.672 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 292.095 MiB) 12.26.114.663 I slot launch_slot_: id 0 | task 8753 | processing task, is_child = 0 12.26.114.770 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 293.748 MiB) 12.26.122.822 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1750, t_last = 331693053398 12.26.122.965 I slot launch_slot_: id 3 | task 8754 | processing task, is_child = 0 12.27.397.931 I slot print_timing: id 1 | task 8746 | prompt eval time = 4519.32 ms / 835 tokens ( 5.41 ms per token, 184.76 tokens per second) 12.27.397.935 I slot print_timing: id 1 | task 8746 | eval time = 1293.47 ms / 2 tokens ( 1293.47 ms per token, 0.77 tokens per second) 12.27.397.936 I slot print_timing: id 1 | task 8746 | total time = 5812.79 ms / 837 tokens 12.27.397.936 I slot print_timing: id 1 | task 8746 | graphs reused = 7277 12.27.397.937 I slot print_timing: id 1 | task 8746 | graph reallocs = 0 / 0 (same size) / (changed size) 12.27.398.019 I slot release: id 1 | task 8746 | stop processing: n_tokens = 845, truncated = 0 12.27.399.170 I slot print_timing: id 2 | task 8747 | prompt eval time = 4520.17 ms / 862 tokens ( 5.24 ms per token, 190.70 tokens per second) 12.27.399.174 I slot print_timing: id 2 | task 8747 | eval time = 1293.61 ms / 2 tokens ( 1293.61 ms per token, 0.77 tokens per second) 12.27.399.174 I slot print_timing: id 2 | task 8747 | total time = 5813.79 ms / 864 tokens 12.27.399.174 I slot print_timing: id 2 | task 8747 | graphs reused = 7277 12.27.399.175 I slot print_timing: id 2 | task 8747 | graph reallocs = 0 / 0 (same size) / (changed size) 12.27.399.222 I slot release: id 2 | task 8747 | stop processing: n_tokens = 872, truncated = 0 12.28.160.057 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 845, t_last = 331694393861 12.28.160.142 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 348.915 MiB) 12.28.861.409 I slot launch_slot_: id 1 | task 8757 | processing task, is_child = 0 12.28.867.123 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 872, t_last = 331694395064 12.28.867.245 I slot launch_slot_: id 2 | task 8758 | processing task, is_child = 0 12.30.350.255 I slot print_timing: id 0 | task 8753 | prompt processing, n_tokens = 836, progress = 1.00, t = 4.23 s / 197.76 tokens per second 12.30.600.340 I slot print_timing: id 3 | task 8754 | prompt processing, n_tokens = 855, progress = 1.00, t = 4.23 s / 202.27 tokens per second 12.32.030.334 I slot print_timing: id 1 | task 8757 | prompt processing, n_tokens = 613, progress = 0.81, t = 3.16 s / 194.05 tokens per second 12.32.033.504 I slot print_timing: id 2 | task 8758 | prompt processing, n_tokens = 714, progress = 0.81, t = 3.16 s / 226.04 tokens per second 12.32.710.469 I slot print_timing: id 0 | task 8753 | prompt eval time = 5906.00 ms / 840 tokens ( 7.03 ms per token, 142.23 tokens per second) 12.32.710.474 I slot print_timing: id 0 | task 8753 | eval time = 681.49 ms / 2 tokens ( 681.49 ms per token, 1.47 tokens per second) 12.32.710.475 I slot print_timing: id 0 | task 8753 | total time = 6587.49 ms / 842 tokens 12.32.710.476 I slot print_timing: id 0 | task 8753 | graphs reused = 7277 12.32.710.476 I slot print_timing: id 0 | task 8753 | graph reallocs = 0 / 0 (same size) / (changed size) 12.32.710.556 I slot release: id 0 | task 8753 | stop processing: n_tokens = 850, truncated = 0 12.32.711.721 I slot print_timing: id 3 | task 8754 | prompt eval time = 5907.07 ms / 859 tokens ( 6.88 ms per token, 145.42 tokens per second) 12.32.711.726 I slot print_timing: id 3 | task 8754 | eval time = 681.41 ms / 2 tokens ( 681.41 ms per token, 1.47 tokens per second) 12.32.711.727 I slot print_timing: id 3 | task 8754 | total time = 6588.48 ms / 861 tokens 12.32.711.727 I slot print_timing: id 3 | task 8754 | graphs reused = 7277 12.32.711.727 I slot print_timing: id 3 | task 8754 | graph reallocs = 0 / 0 (same size) / (changed size) 12.32.711.765 I slot release: id 3 | task 8754 | stop processing: n_tokens = 869, truncated = 0 12.32.711.776 I slot print_timing: id 1 | task 8757 | prompt processing, n_tokens = 758, progress = 0.99, t = 3.84 s / 197.37 tokens per second 12.32.715.850 I slot print_timing: id 2 | task 8758 | prompt processing, n_tokens = 880, progress = 1.00, t = 3.84 s / 229.15 tokens per second 12.32.760.944 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 850, t_last = 331699706398 12.32.761.050 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 343.147 MiB) 12.32.767.204 I slot launch_slot_: id 0 | task 8763 | processing task, is_child = 0 12.32.767.278 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 344.308 MiB) 12.32.772.977 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 331699707607 12.32.773.096 I slot launch_slot_: id 3 | task 8764 | processing task, is_child = 0 12.33.564.275 I slot print_timing: id 1 | task 8757 | prompt eval time = 3890.67 ms / 762 tokens ( 5.11 ms per token, 195.85 tokens per second) 12.33.564.277 I slot print_timing: id 1 | task 8757 | eval time = 804.63 ms / 2 tokens ( 804.63 ms per token, 1.24 tokens per second) 12.33.564.278 I slot print_timing: id 1 | task 8757 | total time = 4695.30 ms / 764 tokens 12.33.564.278 I slot print_timing: id 1 | task 8757 | graphs reused = 7277 12.33.564.279 I slot print_timing: id 1 | task 8757 | graph reallocs = 0 / 0 (same size) / (changed size) 12.33.564.345 I slot release: id 1 | task 8757 | stop processing: n_tokens = 772, truncated = 0 12.33.565.518 I slot print_timing: id 2 | task 8758 | prompt eval time = 3891.80 ms / 884 tokens ( 4.40 ms per token, 227.14 tokens per second) 12.33.565.521 I slot print_timing: id 2 | task 8758 | eval time = 804.58 ms / 2 tokens ( 804.58 ms per token, 1.24 tokens per second) 12.33.565.522 I slot print_timing: id 2 | task 8758 | total time = 4696.38 ms / 886 tokens 12.33.565.522 I slot print_timing: id 2 | task 8758 | graphs reused = 7277 12.33.565.522 I slot print_timing: id 2 | task 8758 | graph reallocs = 0 / 0 (same size) / (changed size) 12.33.565.573 I slot release: id 2 | task 8758 | stop processing: n_tokens = 894, truncated = 0 12.34.317.721 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 331700560187 12.35.068.402 I slot launch_slot_: id 1 | task 8767 | processing task, is_child = 0 12.35.068.487 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 347.684 MiB) 12.35.074.263 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 894, t_last = 331700561415 12.35.074.381 I slot launch_slot_: id 2 | task 8768 | processing task, is_child = 0 12.36.168.641 I slot print_timing: id 0 | task 8763 | prompt processing, n_tokens = 684, progress = 0.99, t = 3.40 s / 201.44 tokens per second 12.36.301.166 I slot print_timing: id 3 | task 8764 | prompt processing, n_tokens = 729, progress = 0.99, t = 3.40 s / 214.71 tokens per second 12.38.493.055 I slot print_timing: id 0 | task 8763 | prompt eval time = 5099.49 ms / 688 tokens ( 7.41 ms per token, 134.92 tokens per second) 12.38.493.060 I slot print_timing: id 0 | task 8763 | eval time = 620.46 ms / 2 tokens ( 620.46 ms per token, 1.61 tokens per second) 12.38.493.061 I slot print_timing: id 0 | task 8763 | total time = 5719.95 ms / 690 tokens 12.38.493.061 I slot print_timing: id 0 | task 8763 | graphs reused = 7277 12.38.493.062 I slot print_timing: id 0 | task 8763 | graph reallocs = 0 / 0 (same size) / (changed size) 12.38.493.107 I slot release: id 0 | task 8763 | stop processing: n_tokens = 698, truncated = 0 12.38.494.220 I slot print_timing: id 3 | task 8764 | prompt eval time = 5100.56 ms / 733 tokens ( 6.96 ms per token, 143.71 tokens per second) 12.38.494.221 I slot print_timing: id 3 | task 8764 | eval time = 620.36 ms / 2 tokens ( 620.36 ms per token, 1.61 tokens per second) 12.38.494.222 I slot print_timing: id 3 | task 8764 | total time = 5720.92 ms / 735 tokens 12.38.494.222 I slot print_timing: id 3 | task 8764 | graphs reused = 7277 12.38.494.222 I slot print_timing: id 3 | task 8764 | graph reallocs = 0 / 0 (same size) / (changed size) 12.38.494.261 I slot release: id 3 | task 8764 | stop processing: n_tokens = 743, truncated = 0 12.38.494.272 I slot print_timing: id 1 | task 8767 | prompt processing, n_tokens = 703, progress = 0.99, t = 3.42 s / 205.80 tokens per second 12.38.497.819 I slot print_timing: id 2 | task 8768 | prompt processing, n_tokens = 669, progress = 0.99, t = 3.42 s / 195.86 tokens per second 12.38.577.541 I slot print_timing: id 1 | task 8767 | prompt eval time = 3465.55 ms / 707 tokens ( 4.90 ms per token, 204.01 tokens per second) 12.38.577.545 I slot print_timing: id 1 | task 8767 | eval time = 35.91 ms / 2 tokens ( 35.91 ms per token, 27.84 tokens per second) 12.38.577.545 I slot print_timing: id 1 | task 8767 | total time = 3501.46 ms / 709 tokens 12.38.577.546 I slot print_timing: id 1 | task 8767 | graphs reused = 7277 12.38.577.546 I slot print_timing: id 1 | task 8767 | graph reallocs = 0 / 0 (same size) / (changed size) 12.38.577.580 I slot release: id 1 | task 8767 | stop processing: n_tokens = 717, truncated = 0 12.38.578.928 I slot print_timing: id 2 | task 8768 | prompt eval time = 3466.63 ms / 673 tokens ( 5.15 ms per token, 194.14 tokens per second) 12.38.578.930 I slot print_timing: id 2 | task 8768 | eval time = 36.05 ms / 2 tokens ( 36.05 ms per token, 27.74 tokens per second) 12.38.578.930 I slot print_timing: id 2 | task 8768 | total time = 3502.68 ms / 675 tokens 12.38.578.931 I slot print_timing: id 2 | task 8768 | graphs reused = 7277 12.38.578.931 I slot print_timing: id 2 | task 8768 | graph reallocs = 0 / 0 (same size) / (changed size) 12.38.578.948 I slot release: id 2 | task 8768 | stop processing: n_tokens = 683, truncated = 0 12.41.600.307 I srv operator(): operator(): cleaning up before exit...