/Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/8f4aabaf93cd/Spark-X2.6-4B-Q5_K_M.gguf --host 127.0.0.1 --port 8091 -c 16384 -np 4 -ngl 999 -fa on --jinja --seed 1234 --chat-template-kwargs "{\"enable_thinking\": false}" --no-webui -a quant 0.00.052.224 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.052.289 I srv llama_server: initializing ... 0.00.052.294 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.052.393 I srv init_listene: The UI is disabled 0.00.052.394 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.052.433 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) 0.00.054.115 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/8f4aabaf93cd/Spark-X2.6-4B-Q5_K_M.gguf' 0.00.511.685 I cmn init: llama threadpool init, n_threads = 8 0.00.621.169 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.00.630.474 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.630.487 I srv llama_server: model loaded 0.00.630.488 I srv llama_server: listening on http://127.0.0.1:8091 1.23.229.429 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 1.23.229.501 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 1.23.229.504 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 1.23.229.539 I slot launch_slot_: id 1 | task 1 | processing task, is_child = 0 1.23.229.542 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 1.23.229.570 I slot launch_slot_: id 2 | task 2 | processing task, is_child = 0 1.23.229.572 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 1.23.229.604 I slot launch_slot_: id 3 | task 3 | processing task, is_child = 0 1.24.571.411 I slot print_timing: id 0 | task 0 | prompt eval time = 1292.05 ms / 130 tokens ( 9.94 ms per token, 100.62 tokens per second) 1.24.571.416 I slot print_timing: id 0 | task 0 | eval time = 49.74 ms / 2 tokens ( 49.74 ms per token, 20.10 tokens per second) 1.24.571.417 I slot print_timing: id 0 | task 0 | total time = 1341.79 ms / 132 tokens 1.24.571.417 I slot print_timing: id 0 | task 0 | graphs reused = 1 1.24.571.418 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.571.445 I slot release: id 0 | task 0 | stop processing: n_tokens = 131, truncated = 0 1.24.575.347 I slot print_timing: id 2 | task 2 | prompt eval time = 1298.25 ms / 134 tokens ( 9.69 ms per token, 103.22 tokens per second) 1.24.575.350 I slot print_timing: id 2 | task 2 | eval time = 47.47 ms / 2 tokens ( 47.47 ms per token, 21.07 tokens per second) 1.24.575.351 I slot print_timing: id 2 | task 2 | total time = 1345.72 ms / 136 tokens 1.24.575.351 I slot print_timing: id 2 | task 2 | graphs reused = 1 1.24.575.352 I slot print_timing: id 2 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.575.370 I slot release: id 2 | task 2 | stop processing: n_tokens = 135, truncated = 0 1.24.577.174 I slot print_timing: id 3 | task 3 | prompt eval time = 1301.10 ms / 142 tokens ( 9.16 ms per token, 109.14 tokens per second) 1.24.577.179 I slot print_timing: id 3 | task 3 | eval time = 46.45 ms / 2 tokens ( 46.45 ms per token, 21.53 tokens per second) 1.24.577.180 I slot print_timing: id 3 | task 3 | total time = 1347.55 ms / 144 tokens 1.24.577.180 I slot print_timing: id 3 | task 3 | graphs reused = 1 1.24.577.181 I slot print_timing: id 3 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.577.203 I slot release: id 3 | task 3 | stop processing: n_tokens = 143, truncated = 0 1.24.603.580 I slot print_timing: id 1 | task 1 | prompt eval time = 1295.36 ms / 128 tokens ( 10.12 ms per token, 98.81 tokens per second) 1.24.603.583 I slot print_timing: id 1 | task 1 | eval time = 78.59 ms / 3 tokens ( 39.30 ms per token, 25.45 tokens per second) 1.24.603.584 I slot print_timing: id 1 | task 1 | total time = 1373.96 ms / 131 tokens 1.24.603.584 I slot print_timing: id 1 | task 1 | graphs reused = 1 1.24.603.585 I slot print_timing: id 1 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.603.601 I slot release: id 1 | task 1 | stop processing: n_tokens = 130, truncated = 0 1.24.603.607 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.282 1.24.607.135 I slot launch_slot_: id 0 | task 9 | processing task, is_child = 0 1.24.616.960 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.292 1.24.617.058 I slot launch_slot_: id 1 | task 10 | processing task, is_child = 0 1.24.617.124 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.274 1.24.617.199 I slot launch_slot_: id 2 | task 11 | processing task, is_child = 0 1.24.617.234 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 1.24.617.312 I slot launch_slot_: id 3 | task 12 | processing task, is_child = 0 1.26.091.516 I slot print_timing: id 0 | task 9 | prompt eval time = 1431.67 ms / 164 tokens ( 8.73 ms per token, 114.55 tokens per second) 1.26.091.520 I slot print_timing: id 0 | task 9 | eval time = 42.52 ms / 2 tokens ( 42.52 ms per token, 23.52 tokens per second) 1.26.091.521 I slot print_timing: id 0 | task 9 | total time = 1474.19 ms / 166 tokens 1.26.091.521 I slot print_timing: id 0 | task 9 | graphs reused = 1 1.26.091.522 I slot print_timing: id 0 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.091.548 I slot release: id 0 | task 9 | stop processing: n_tokens = 174, truncated = 0 1.26.094.481 I slot print_timing: id 2 | task 11 | prompt eval time = 1433.72 ms / 204 tokens ( 7.03 ms per token, 142.29 tokens per second) 1.26.094.487 I slot print_timing: id 2 | task 11 | eval time = 42.98 ms / 2 tokens ( 42.98 ms per token, 23.27 tokens per second) 1.26.094.487 I slot print_timing: id 2 | task 11 | total time = 1476.70 ms / 206 tokens 1.26.094.488 I slot print_timing: id 2 | task 11 | graphs reused = 1 1.26.094.488 I slot print_timing: id 2 | task 11 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.094.510 I slot release: id 2 | task 11 | stop processing: n_tokens = 214, truncated = 0 1.26.096.017 I slot print_timing: id 3 | task 12 | prompt eval time = 1434.61 ms / 110 tokens ( 13.04 ms per token, 76.68 tokens per second) 1.26.096.023 I slot print_timing: id 3 | task 12 | eval time = 43.40 ms / 2 tokens ( 43.40 ms per token, 23.04 tokens per second) 1.26.096.024 I slot print_timing: id 3 | task 12 | total time = 1478.00 ms / 112 tokens 1.26.096.024 I slot print_timing: id 3 | task 12 | graphs reused = 1 1.26.096.026 I slot print_timing: id 3 | task 12 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.096.038 I slot release: id 3 | task 12 | stop processing: n_tokens = 120, truncated = 0 1.26.096.044 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.297 (> 0.100 thold), f_keep = 0.317 1.26.098.490 I slot launch_slot_: id 3 | task 17 | processing task, is_child = 0 1.26.107.465 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.213 1.26.107.547 I slot launch_slot_: id 0 | task 18 | processing task, is_child = 0 1.26.107.587 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.173 1.26.107.658 I slot launch_slot_: id 2 | task 19 | processing task, is_child = 0 1.26.165.815 I slot print_timing: id 1 | task 10 | prompt eval time = 1432.79 ms / 159 tokens ( 9.01 ms per token, 110.97 tokens per second) 1.26.165.822 I slot print_timing: id 1 | task 10 | eval time = 115.47 ms / 3 tokens ( 57.73 ms per token, 17.32 tokens per second) 1.26.165.822 I slot print_timing: id 1 | task 10 | total time = 1548.25 ms / 162 tokens 1.26.165.822 I slot print_timing: id 1 | task 10 | graphs reused = 1 1.26.165.823 I slot print_timing: id 1 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.165.846 I slot release: id 1 | task 10 | stop processing: n_tokens = 170, truncated = 0 1.26.946.805 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.287 (> 0.100 thold), f_keep = 0.218 1.26.981.597 I slot launch_slot_: id 1 | task 22 | processing task, is_child = 0 1.27.419.988 I slot print_timing: id 2 | task 19 | prompt eval time = 984.79 ms / 127 tokens ( 7.75 ms per token, 128.96 tokens per second) 1.27.419.999 I slot print_timing: id 2 | task 19 | eval time = 327.36 ms / 2 tokens ( 327.36 ms per token, 3.05 tokens per second) 1.27.420.001 I slot print_timing: id 2 | task 19 | total time = 1312.15 ms / 129 tokens 1.27.420.003 I slot print_timing: id 2 | task 19 | graphs reused = 1 1.27.420.004 I slot print_timing: id 2 | task 19 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.420.098 I slot release: id 2 | task 19 | stop processing: n_tokens = 137, truncated = 0 1.27.423.044 I slot print_timing: id 3 | task 17 | prompt eval time = 986.55 ms / 119 tokens ( 8.29 ms per token, 120.62 tokens per second) 1.27.423.050 I slot print_timing: id 3 | task 17 | eval time = 328.52 ms / 2 tokens ( 328.52 ms per token, 3.04 tokens per second) 1.27.423.052 I slot print_timing: id 3 | task 17 | total time = 1315.08 ms / 121 tokens 1.27.423.054 I slot print_timing: id 3 | task 17 | graphs reused = 1 1.27.423.055 I slot print_timing: id 3 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.423.099 I slot release: id 3 | task 17 | stop processing: n_tokens = 129, truncated = 0 1.27.499.909 I slot print_timing: id 0 | task 18 | prompt eval time = 982.91 ms / 151 tokens ( 6.51 ms per token, 153.63 tokens per second) 1.27.499.923 I slot print_timing: id 0 | task 18 | eval time = 409.31 ms / 3 tokens ( 204.66 ms per token, 4.89 tokens per second) 1.27.499.924 I slot print_timing: id 0 | task 18 | total time = 1392.22 ms / 154 tokens 1.27.499.926 I slot print_timing: id 0 | task 18 | graphs reused = 1 1.27.499.929 I slot print_timing: id 0 | task 18 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.500.002 I slot release: id 0 | task 18 | stop processing: n_tokens = 162, truncated = 0 1.27.502.636 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.240 (> 0.100 thold), f_keep = 0.228 1.27.508.577 I slot launch_slot_: id 0 | task 26 | processing task, is_child = 0 1.27.520.612 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.270 1.27.520.746 I slot launch_slot_: id 2 | task 27 | processing task, is_child = 0 1.27.520.792 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.287 1.27.520.898 I slot launch_slot_: id 3 | task 28 | processing task, is_child = 0 1.27.581.911 I slot print_timing: id 1 | task 22 | prompt eval time = 520.40 ms / 120 tokens ( 4.34 ms per token, 230.59 tokens per second) 1.27.581.919 I slot print_timing: id 1 | task 22 | eval time = 79.29 ms / 2 tokens ( 79.29 ms per token, 12.61 tokens per second) 1.27.581.920 I slot print_timing: id 1 | task 22 | total time = 599.69 ms / 122 tokens 1.27.581.921 I slot print_timing: id 1 | task 22 | graphs reused = 1 1.27.581.922 I slot print_timing: id 1 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.581.948 I slot release: id 1 | task 22 | stop processing: n_tokens = 130, truncated = 0 1.28.430.414 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.285 1.28.566.585 I slot launch_slot_: id 1 | task 31 | processing task, is_child = 0 1.29.021.447 I slot print_timing: id 2 | task 27 | prompt eval time = 1171.10 ms / 184 tokens ( 6.36 ms per token, 157.12 tokens per second) 1.29.021.460 I slot print_timing: id 2 | task 27 | eval time = 329.14 ms / 2 tokens ( 329.14 ms per token, 3.04 tokens per second) 1.29.021.461 I slot print_timing: id 2 | task 27 | total time = 1500.23 ms / 186 tokens 1.29.021.464 I slot print_timing: id 2 | task 27 | graphs reused = 1 1.29.021.464 I slot print_timing: id 2 | task 27 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.021.565 I slot release: id 2 | task 27 | stop processing: n_tokens = 194, truncated = 0 1.29.023.824 I slot print_timing: id 3 | task 28 | prompt eval time = 1173.46 ms / 138 tokens ( 8.50 ms per token, 117.60 tokens per second) 1.29.023.831 I slot print_timing: id 3 | task 28 | eval time = 328.90 ms / 2 tokens ( 328.90 ms per token, 3.04 tokens per second) 1.29.023.832 I slot print_timing: id 3 | task 28 | total time = 1502.36 ms / 140 tokens 1.29.023.833 I slot print_timing: id 3 | task 28 | graphs reused = 1 1.29.023.834 I slot print_timing: id 3 | task 28 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.023.894 I slot release: id 3 | task 28 | stop processing: n_tokens = 148, truncated = 0 1.29.101.289 I slot print_timing: id 0 | task 26 | prompt eval time = 1168.91 ms / 145 tokens ( 8.06 ms per token, 124.05 tokens per second) 1.29.101.315 I slot print_timing: id 0 | task 26 | eval time = 411.44 ms / 3 tokens ( 205.72 ms per token, 4.86 tokens per second) 1.29.101.321 I slot print_timing: id 0 | task 26 | total time = 1580.35 ms / 148 tokens 1.29.101.322 I slot print_timing: id 0 | task 26 | graphs reused = 1 1.29.101.324 I slot print_timing: id 0 | task 26 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.101.402 I slot release: id 0 | task 26 | stop processing: n_tokens = 156, truncated = 0 1.29.103.815 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.237 1.29.112.685 I slot launch_slot_: id 0 | task 35 | processing task, is_child = 0 1.29.125.577 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.191 1.29.125.688 I slot launch_slot_: id 2 | task 36 | processing task, is_child = 0 1.29.125.730 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.250 1.29.125.820 I slot launch_slot_: id 3 | task 37 | processing task, is_child = 0 1.29.186.521 I slot print_timing: id 1 | task 31 | prompt eval time = 532.00 ms / 122 tokens ( 4.36 ms per token, 229.33 tokens per second) 1.29.186.528 I slot print_timing: id 1 | task 31 | eval time = 82.73 ms / 2 tokens ( 82.73 ms per token, 12.09 tokens per second) 1.29.186.529 I slot print_timing: id 1 | task 31 | total time = 614.72 ms / 124 tokens 1.29.186.530 I slot print_timing: id 1 | task 31 | graphs reused = 1 1.29.186.531 I slot print_timing: id 1 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.186.559 I slot release: id 1 | task 31 | stop processing: n_tokens = 132, truncated = 0 1.29.983.798 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.280 1.30.071.965 I slot launch_slot_: id 1 | task 40 | processing task, is_child = 0 1.30.526.782 I slot print_timing: id 3 | task 37 | prompt eval time = 1069.79 ms / 149 tokens ( 7.18 ms per token, 139.28 tokens per second) 1.30.526.795 I slot print_timing: id 3 | task 37 | eval time = 330.63 ms / 2 tokens ( 330.63 ms per token, 3.02 tokens per second) 1.30.526.796 I slot print_timing: id 3 | task 37 | total time = 1400.42 ms / 151 tokens 1.30.526.798 I slot print_timing: id 3 | task 37 | graphs reused = 1 1.30.526.799 I slot print_timing: id 3 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.526.911 I slot release: id 3 | task 37 | stop processing: n_tokens = 159, truncated = 0 1.30.626.999 I slot print_timing: id 0 | task 35 | prompt eval time = 1064.91 ms / 133 tokens ( 8.01 ms per token, 124.89 tokens per second) 1.30.627.005 I slot print_timing: id 0 | task 35 | eval time = 436.25 ms / 3 tokens ( 218.12 ms per token, 4.58 tokens per second) 1.30.627.011 I slot print_timing: id 0 | task 35 | total time = 1501.16 ms / 136 tokens 1.30.627.012 I slot print_timing: id 0 | task 35 | graphs reused = 1 1.30.627.013 I slot print_timing: id 0 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.627.040 I slot release: id 0 | task 35 | stop processing: n_tokens = 144, truncated = 0 1.30.632.251 I slot print_timing: id 2 | task 36 | prompt eval time = 1067.24 ms / 181 tokens ( 5.90 ms per token, 169.60 tokens per second) 1.30.632.258 I slot print_timing: id 2 | task 36 | eval time = 438.93 ms / 3 tokens ( 219.47 ms per token, 4.56 tokens per second) 1.30.632.259 I slot print_timing: id 2 | task 36 | total time = 1506.17 ms / 184 tokens 1.30.632.259 I slot print_timing: id 2 | task 36 | graphs reused = 1 1.30.632.260 I slot print_timing: id 2 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.632.292 I slot release: id 2 | task 36 | stop processing: n_tokens = 192, truncated = 0 1.30.632.301 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.298 (> 0.100 thold), f_keep = 0.257 1.30.637.429 I slot launch_slot_: id 0 | task 44 | processing task, is_child = 0 1.30.647.685 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.193 1.30.647.800 I slot launch_slot_: id 2 | task 45 | processing task, is_child = 0 1.30.647.845 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.233 1.30.647.946 I slot launch_slot_: id 3 | task 46 | processing task, is_child = 0 1.30.707.792 I slot print_timing: id 1 | task 40 | prompt eval time = 555.31 ms / 127 tokens ( 4.37 ms per token, 228.70 tokens per second) 1.30.707.799 I slot print_timing: id 1 | task 40 | eval time = 77.93 ms / 2 tokens ( 77.93 ms per token, 12.83 tokens per second) 1.30.707.800 I slot print_timing: id 1 | task 40 | total time = 633.24 ms / 129 tokens 1.30.707.800 I slot print_timing: id 1 | task 40 | graphs reused = 1 1.30.707.801 I slot print_timing: id 1 | task 40 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.707.823 I slot release: id 1 | task 40 | stop processing: n_tokens = 137, truncated = 0 1.31.503.699 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.290 (> 0.100 thold), f_keep = 0.277 1.31.537.125 I slot launch_slot_: id 1 | task 49 | processing task, is_child = 0 1.32.102.333 I slot print_timing: id 0 | task 44 | prompt eval time = 1008.58 ms / 115 tokens ( 8.77 ms per token, 114.02 tokens per second) 1.32.102.342 I slot print_timing: id 0 | task 44 | eval time = 445.79 ms / 3 tokens ( 222.90 ms per token, 4.49 tokens per second) 1.32.102.343 I slot print_timing: id 0 | task 44 | total time = 1454.37 ms / 118 tokens 1.32.102.343 I slot print_timing: id 0 | task 44 | graphs reused = 1 1.32.102.344 I slot print_timing: id 0 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.102.384 I slot release: id 0 | task 44 | stop processing: n_tokens = 126, truncated = 0 1.32.107.163 I slot print_timing: id 2 | task 45 | prompt eval time = 1011.18 ms / 144 tokens ( 7.02 ms per token, 142.41 tokens per second) 1.32.107.170 I slot print_timing: id 2 | task 45 | eval time = 447.84 ms / 3 tokens ( 223.92 ms per token, 4.47 tokens per second) 1.32.107.171 I slot print_timing: id 2 | task 45 | total time = 1459.02 ms / 147 tokens 1.32.107.172 I slot print_timing: id 2 | task 45 | graphs reused = 1 1.32.107.172 I slot print_timing: id 2 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.107.191 I slot release: id 2 | task 45 | stop processing: n_tokens = 155, truncated = 0 1.32.109.246 I slot print_timing: id 3 | task 46 | prompt eval time = 1013.90 ms / 148 tokens ( 6.85 ms per token, 145.97 tokens per second) 1.32.109.249 I slot print_timing: id 3 | task 46 | eval time = 447.01 ms / 3 tokens ( 223.51 ms per token, 4.47 tokens per second) 1.32.109.249 I slot print_timing: id 3 | task 46 | total time = 1460.91 ms / 151 tokens 1.32.109.250 I slot print_timing: id 3 | task 46 | graphs reused = 1 1.32.109.250 I slot print_timing: id 3 | task 46 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.109.267 I slot release: id 3 | task 46 | stop processing: n_tokens = 159, truncated = 0 1.32.109.274 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.301 (> 0.100 thold), f_keep = 0.294 1.32.112.840 I slot launch_slot_: id 0 | task 53 | processing task, is_child = 0 1.32.120.080 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.239 1.32.120.191 I slot launch_slot_: id 2 | task 54 | processing task, is_child = 0 1.32.120.234 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.233 1.32.120.331 I slot launch_slot_: id 3 | task 55 | processing task, is_child = 0 1.32.180.179 I slot print_timing: id 1 | task 49 | prompt eval time = 565.42 ms / 122 tokens ( 4.63 ms per token, 215.77 tokens per second) 1.32.180.183 I slot print_timing: id 1 | task 49 | eval time = 75.32 ms / 2 tokens ( 75.32 ms per token, 13.28 tokens per second) 1.32.180.184 I slot print_timing: id 1 | task 49 | total time = 640.74 ms / 124 tokens 1.32.180.184 I slot print_timing: id 1 | task 49 | graphs reused = 1 1.32.180.185 I slot print_timing: id 1 | task 49 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.180.207 I slot release: id 1 | task 49 | stop processing: n_tokens = 132, truncated = 0 1.32.911.284 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.308 (> 0.100 thold), f_keep = 0.280 1.32.995.713 I slot launch_slot_: id 1 | task 58 | processing task, is_child = 0 1.33.444.690 I slot print_timing: id 2 | task 54 | prompt eval time = 995.10 ms / 124 tokens ( 8.03 ms per token, 124.61 tokens per second) 1.33.444.708 I slot print_timing: id 2 | task 54 | eval time = 329.06 ms / 2 tokens ( 329.06 ms per token, 3.04 tokens per second) 1.33.444.709 I slot print_timing: id 2 | task 54 | total time = 1324.16 ms / 126 tokens 1.33.444.717 I slot print_timing: id 2 | task 54 | graphs reused = 1 1.33.444.718 I slot print_timing: id 2 | task 54 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.444.817 I slot release: id 2 | task 54 | stop processing: n_tokens = 134, truncated = 0 1.33.545.246 I slot print_timing: id 0 | task 53 | prompt eval time = 992.56 ms / 114 tokens ( 8.71 ms per token, 114.85 tokens per second) 1.33.545.256 I slot print_timing: id 0 | task 53 | eval time = 432.34 ms / 3 tokens ( 216.17 ms per token, 4.63 tokens per second) 1.33.545.257 I slot print_timing: id 0 | task 53 | total time = 1424.90 ms / 117 tokens 1.33.545.258 I slot print_timing: id 0 | task 53 | graphs reused = 1 1.33.545.259 I slot print_timing: id 0 | task 53 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.545.307 I slot release: id 0 | task 53 | stop processing: n_tokens = 125, truncated = 0 1.33.550.652 I slot print_timing: id 3 | task 55 | prompt eval time = 997.75 ms / 148 tokens ( 6.74 ms per token, 148.33 tokens per second) 1.33.550.656 I slot print_timing: id 3 | task 55 | eval time = 432.22 ms / 3 tokens ( 216.11 ms per token, 4.63 tokens per second) 1.33.550.657 I slot print_timing: id 3 | task 55 | total time = 1429.98 ms / 151 tokens 1.33.550.658 I slot print_timing: id 3 | task 55 | graphs reused = 1 1.33.550.658 I slot print_timing: id 3 | task 55 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.550.682 I slot release: id 3 | task 55 | stop processing: n_tokens = 159, truncated = 0 1.33.550.691 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.293 (> 0.100 thold), f_keep = 0.328 1.33.554.060 I slot launch_slot_: id 0 | task 62 | processing task, is_child = 0 1.33.563.309 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.276 1.33.563.459 I slot launch_slot_: id 2 | task 63 | processing task, is_child = 0 1.33.563.505 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.322 (> 0.100 thold), f_keep = 0.233 1.33.563.611 I slot launch_slot_: id 3 | task 64 | processing task, is_child = 0 1.33.623.882 I slot print_timing: id 1 | task 58 | prompt eval time = 550.65 ms / 111 tokens ( 4.96 ms per token, 201.58 tokens per second) 1.33.623.887 I slot print_timing: id 1 | task 58 | eval time = 75.63 ms / 2 tokens ( 75.63 ms per token, 13.22 tokens per second) 1.33.623.888 I slot print_timing: id 1 | task 58 | total time = 626.27 ms / 113 tokens 1.33.623.888 I slot print_timing: id 1 | task 58 | graphs reused = 1 1.33.623.889 I slot print_timing: id 1 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.623.915 I slot release: id 1 | task 58 | stop processing: n_tokens = 121, truncated = 0 1.34.306.586 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.306 1.34.391.139 I slot launch_slot_: id 1 | task 67 | processing task, is_child = 0 1.34.843.898 I slot print_timing: id 3 | task 64 | prompt eval time = 951.42 ms / 106 tokens ( 8.98 ms per token, 111.41 tokens per second) 1.34.843.918 I slot print_timing: id 3 | task 64 | eval time = 328.40 ms / 2 tokens ( 328.40 ms per token, 3.05 tokens per second) 1.34.843.920 I slot print_timing: id 3 | task 64 | total time = 1279.81 ms / 108 tokens 1.34.843.922 I slot print_timing: id 3 | task 64 | graphs reused = 1 1.34.843.923 I slot print_timing: id 3 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.844.027 I slot release: id 3 | task 64 | stop processing: n_tokens = 116, truncated = 0 1.34.941.884 I slot print_timing: id 0 | task 62 | prompt eval time = 946.40 ms / 131 tokens ( 7.22 ms per token, 138.42 tokens per second) 1.34.941.889 I slot print_timing: id 0 | task 62 | eval time = 431.86 ms / 3 tokens ( 215.93 ms per token, 4.63 tokens per second) 1.34.941.890 I slot print_timing: id 0 | task 62 | total time = 1378.26 ms / 134 tokens 1.34.941.891 I slot print_timing: id 0 | task 62 | graphs reused = 1 1.34.941.892 I slot print_timing: id 0 | task 62 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.941.920 I slot release: id 0 | task 62 | stop processing: n_tokens = 142, truncated = 0 1.34.946.433 I slot print_timing: id 2 | task 63 | prompt eval time = 949.08 ms / 138 tokens ( 6.88 ms per token, 145.40 tokens per second) 1.34.946.440 I slot print_timing: id 2 | task 63 | eval time = 433.51 ms / 3 tokens ( 216.75 ms per token, 4.61 tokens per second) 1.34.946.441 I slot print_timing: id 2 | task 63 | total time = 1382.58 ms / 141 tokens 1.34.946.441 I slot print_timing: id 2 | task 63 | graphs reused = 1 1.34.946.442 I slot print_timing: id 2 | task 63 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.946.463 I slot release: id 2 | task 63 | stop processing: n_tokens = 149, truncated = 0 1.34.946.475 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.261 1.34.951.786 I slot launch_slot_: id 0 | task 71 | processing task, is_child = 0 1.34.956.756 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.248 1.34.956.868 I slot launch_slot_: id 2 | task 72 | processing task, is_child = 0 1.34.956.907 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.319 1.34.956.999 I slot launch_slot_: id 3 | task 73 | processing task, is_child = 0 1.35.016.950 I slot print_timing: id 1 | task 67 | prompt eval time = 550.92 ms / 113 tokens ( 4.88 ms per token, 205.11 tokens per second) 1.35.016.955 I slot print_timing: id 1 | task 67 | eval time = 72.58 ms / 2 tokens ( 72.58 ms per token, 13.78 tokens per second) 1.35.016.956 I slot print_timing: id 1 | task 67 | total time = 623.50 ms / 115 tokens 1.35.016.957 I slot print_timing: id 1 | task 67 | graphs reused = 1 1.35.016.957 I slot print_timing: id 1 | task 67 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.016.979 I slot release: id 1 | task 67 | stop processing: n_tokens = 123, truncated = 0 1.35.934.481 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.301 1.36.069.221 I slot launch_slot_: id 1 | task 76 | processing task, is_child = 0 1.36.641.817 I slot print_timing: id 0 | task 71 | prompt eval time = 1233.89 ms / 194 tokens ( 6.36 ms per token, 157.23 tokens per second) 1.36.641.827 I slot print_timing: id 0 | task 71 | eval time = 450.88 ms / 2 tokens ( 450.88 ms per token, 2.22 tokens per second) 1.36.641.834 I slot print_timing: id 0 | task 71 | total time = 1684.78 ms / 196 tokens 1.36.641.837 I slot print_timing: id 0 | task 71 | graphs reused = 1 1.36.641.840 I slot print_timing: id 0 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.641.933 I slot release: id 0 | task 71 | stop processing: n_tokens = 204, truncated = 0 1.36.644.185 I slot print_timing: id 2 | task 72 | prompt eval time = 1236.43 ms / 181 tokens ( 6.83 ms per token, 146.39 tokens per second) 1.36.644.191 I slot print_timing: id 2 | task 72 | eval time = 450.55 ms / 2 tokens ( 450.55 ms per token, 2.22 tokens per second) 1.36.644.194 I slot print_timing: id 2 | task 72 | total time = 1686.99 ms / 183 tokens 1.36.644.195 I slot print_timing: id 2 | task 72 | graphs reused = 1 1.36.644.196 I slot print_timing: id 2 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.644.258 I slot release: id 2 | task 72 | stop processing: n_tokens = 191, truncated = 0 1.36.646.338 I slot print_timing: id 3 | task 73 | prompt eval time = 1239.01 ms / 134 tokens ( 9.25 ms per token, 108.15 tokens per second) 1.36.646.349 I slot print_timing: id 3 | task 73 | eval time = 449.95 ms / 2 tokens ( 449.95 ms per token, 2.22 tokens per second) 1.36.646.350 I slot print_timing: id 3 | task 73 | total time = 1688.96 ms / 136 tokens 1.36.646.350 I slot print_timing: id 3 | task 73 | graphs reused = 1 1.36.646.352 I slot print_timing: id 3 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.646.391 I slot release: id 3 | task 73 | stop processing: n_tokens = 144, truncated = 0 1.36.691.470 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 1.36.698.515 I slot launch_slot_: id 0 | task 80 | processing task, is_child = 0 1.36.709.135 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.194 1.36.710.075 I slot launch_slot_: id 2 | task 81 | processing task, is_child = 0 1.36.710.117 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.257 1.36.710.206 I slot launch_slot_: id 3 | task 82 | processing task, is_child = 0 1.37.791.537 I slot print_timing: id 1 | task 76 | prompt eval time = 616.44 ms / 168 tokens ( 3.67 ms per token, 272.53 tokens per second) 1.37.791.557 I slot print_timing: id 1 | task 76 | eval time = 1100.04 ms / 3 tokens ( 550.02 ms per token, 1.82 tokens per second) 1.37.791.559 I slot print_timing: id 1 | task 76 | total time = 1716.47 ms / 171 tokens 1.37.791.560 I slot print_timing: id 1 | task 76 | graphs reused = 1 1.37.791.561 I slot print_timing: id 1 | task 76 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.791.674 I slot release: id 1 | task 76 | stop processing: n_tokens = 179, truncated = 0 1.37.884.246 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.207 1.37.894.519 I slot launch_slot_: id 1 | task 86 | processing task, is_child = 0 1.37.968.905 I slot print_timing: id 0 | task 80 | prompt eval time = 1168.62 ms / 171 tokens ( 6.83 ms per token, 146.33 tokens per second) 1.37.968.922 I slot print_timing: id 0 | task 80 | eval time = 90.05 ms / 2 tokens ( 90.05 ms per token, 11.11 tokens per second) 1.37.968.923 I slot print_timing: id 0 | task 80 | total time = 1258.67 ms / 173 tokens 1.37.968.925 I slot print_timing: id 0 | task 80 | graphs reused = 1 1.37.968.925 I slot print_timing: id 0 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.968.999 I slot release: id 0 | task 80 | stop processing: n_tokens = 181, truncated = 0 1.37.970.894 I slot print_timing: id 2 | task 81 | prompt eval time = 1171.14 ms / 143 tokens ( 8.19 ms per token, 122.10 tokens per second) 1.37.970.902 I slot print_timing: id 2 | task 81 | eval time = 89.25 ms / 2 tokens ( 89.25 ms per token, 11.20 tokens per second) 1.37.970.903 I slot print_timing: id 2 | task 81 | total time = 1260.39 ms / 145 tokens 1.37.970.904 I slot print_timing: id 2 | task 81 | graphs reused = 1 1.37.970.905 I slot print_timing: id 2 | task 81 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.970.947 I slot release: id 2 | task 81 | stop processing: n_tokens = 153, truncated = 0 1.38.254.735 I slot print_timing: id 3 | task 82 | prompt eval time = 1173.43 ms / 152 tokens ( 7.72 ms per token, 129.53 tokens per second) 1.38.254.752 I slot print_timing: id 3 | task 82 | eval time = 370.49 ms / 3 tokens ( 185.24 ms per token, 5.40 tokens per second) 1.38.254.754 I slot print_timing: id 3 | task 82 | total time = 1543.92 ms / 155 tokens 1.38.254.756 I slot print_timing: id 3 | task 82 | graphs reused = 1 1.38.254.757 I slot print_timing: id 3 | task 82 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.254.872 I slot release: id 3 | task 82 | stop processing: n_tokens = 163, truncated = 0 1.38.254.911 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 1.38.263.274 I slot launch_slot_: id 0 | task 89 | processing task, is_child = 0 1.38.274.944 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.242 1.38.275.089 I slot launch_slot_: id 2 | task 90 | processing task, is_child = 0 1.38.275.141 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.314 (> 0.100 thold), f_keep = 0.227 1.38.276.572 I slot launch_slot_: id 3 | task 91 | processing task, is_child = 0 1.39.207.121 I slot print_timing: id 1 | task 86 | prompt eval time = 456.82 ms / 125 tokens ( 3.65 ms per token, 273.63 tokens per second) 1.39.207.132 I slot print_timing: id 1 | task 86 | eval time = 855.72 ms / 2 tokens ( 855.72 ms per token, 1.17 tokens per second) 1.39.207.133 I slot print_timing: id 1 | task 86 | total time = 1312.53 ms / 127 tokens 1.39.207.134 I slot print_timing: id 1 | task 86 | graphs reused = 1 1.39.207.135 I slot print_timing: id 1 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.207.228 I slot release: id 1 | task 86 | stop processing: n_tokens = 135, truncated = 0 1.39.298.260 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.225 (> 0.100 thold), f_keep = 0.281 1.39.301.540 I slot launch_slot_: id 1 | task 95 | processing task, is_child = 0 1.39.376.419 I slot print_timing: id 0 | task 89 | prompt eval time = 1017.42 ms / 130 tokens ( 7.83 ms per token, 127.77 tokens per second) 1.39.376.431 I slot print_timing: id 0 | task 89 | eval time = 82.40 ms / 2 tokens ( 82.40 ms per token, 12.14 tokens per second) 1.39.376.432 I slot print_timing: id 0 | task 89 | total time = 1099.82 ms / 132 tokens 1.39.376.433 I slot print_timing: id 0 | task 89 | graphs reused = 1 1.39.376.434 I slot print_timing: id 0 | task 89 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.376.503 I slot release: id 0 | task 89 | stop processing: n_tokens = 140, truncated = 0 1.39.378.654 I slot print_timing: id 2 | task 90 | prompt eval time = 1018.16 ms / 166 tokens ( 6.13 ms per token, 163.04 tokens per second) 1.39.378.668 I slot print_timing: id 2 | task 90 | eval time = 82.44 ms / 2 tokens ( 82.44 ms per token, 12.13 tokens per second) 1.39.378.669 I slot print_timing: id 2 | task 90 | total time = 1100.60 ms / 168 tokens 1.39.378.670 I slot print_timing: id 2 | task 90 | graphs reused = 1 1.39.378.671 I slot print_timing: id 2 | task 90 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.378.714 I slot release: id 2 | task 90 | stop processing: n_tokens = 176, truncated = 0 1.39.380.691 I slot print_timing: id 3 | task 91 | prompt eval time = 1019.93 ms / 109 tokens ( 9.36 ms per token, 106.87 tokens per second) 1.39.380.699 I slot print_timing: id 3 | task 91 | eval time = 82.46 ms / 2 tokens ( 82.46 ms per token, 12.13 tokens per second) 1.39.380.700 I slot print_timing: id 3 | task 91 | total time = 1102.39 ms / 111 tokens 1.39.380.701 I slot print_timing: id 3 | task 91 | graphs reused = 1 1.39.380.702 I slot print_timing: id 3 | task 91 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.380.736 I slot release: id 3 | task 91 | stop processing: n_tokens = 119, truncated = 0 1.39.736.106 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.264 1.39.739.289 I slot launch_slot_: id 0 | task 99 | processing task, is_child = 0 1.39.751.835 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.210 1.39.751.972 I slot launch_slot_: id 2 | task 100 | processing task, is_child = 0 1.39.752.012 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.311 1.39.752.103 I slot launch_slot_: id 3 | task 101 | processing task, is_child = 0 1.39.812.987 I slot print_timing: id 1 | task 95 | prompt eval time = 434.53 ms / 160 tokens ( 2.72 ms per token, 368.21 tokens per second) 1.39.812.993 I slot print_timing: id 1 | task 95 | eval time = 76.90 ms / 2 tokens ( 76.90 ms per token, 13.00 tokens per second) 1.39.812.994 I slot print_timing: id 1 | task 95 | total time = 511.43 ms / 162 tokens 1.39.812.994 I slot print_timing: id 1 | task 95 | graphs reused = 1 1.39.812.995 I slot print_timing: id 1 | task 95 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.813.023 I slot release: id 1 | task 95 | stop processing: n_tokens = 170, truncated = 0 1.40.712.781 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.317 (> 0.100 thold), f_keep = 0.224 1.40.745.551 I slot launch_slot_: id 1 | task 104 | processing task, is_child = 0 1.41.175.724 I slot print_timing: id 0 | task 99 | prompt eval time = 1102.49 ms / 113 tokens ( 9.76 ms per token, 102.50 tokens per second) 1.41.175.729 I slot print_timing: id 0 | task 99 | eval time = 321.11 ms / 2 tokens ( 321.11 ms per token, 3.11 tokens per second) 1.41.175.730 I slot print_timing: id 0 | task 99 | total time = 1423.60 ms / 115 tokens 1.41.175.730 I slot print_timing: id 0 | task 99 | graphs reused = 1 1.41.175.731 I slot print_timing: id 0 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.175.756 I slot release: id 0 | task 99 | stop processing: n_tokens = 123, truncated = 0 1.41.252.780 I slot print_timing: id 2 | task 100 | prompt eval time = 1103.47 ms / 170 tokens ( 6.49 ms per token, 154.06 tokens per second) 1.41.252.783 I slot print_timing: id 2 | task 100 | eval time = 396.89 ms / 3 tokens ( 198.44 ms per token, 5.04 tokens per second) 1.41.252.784 I slot print_timing: id 2 | task 100 | total time = 1500.36 ms / 173 tokens 1.41.252.784 I slot print_timing: id 2 | task 100 | graphs reused = 1 1.41.252.785 I slot print_timing: id 2 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.252.805 I slot release: id 2 | task 100 | stop processing: n_tokens = 181, truncated = 0 1.41.253.900 I slot print_timing: id 3 | task 101 | prompt eval time = 1104.43 ms / 167 tokens ( 6.61 ms per token, 151.21 tokens per second) 1.41.253.901 I slot print_timing: id 3 | task 101 | eval time = 396.77 ms / 3 tokens ( 198.39 ms per token, 5.04 tokens per second) 1.41.253.901 I slot print_timing: id 3 | task 101 | total time = 1501.21 ms / 170 tokens 1.41.253.902 I slot print_timing: id 3 | task 101 | graphs reused = 1 1.41.253.902 I slot print_timing: id 3 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.253.912 I slot release: id 3 | task 101 | stop processing: n_tokens = 178, truncated = 0 1.41.253.917 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.301 1.41.256.557 I slot launch_slot_: id 0 | task 108 | processing task, is_child = 0 1.41.263.546 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.204 1.41.263.616 I slot launch_slot_: id 2 | task 109 | processing task, is_child = 0 1.41.263.645 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.208 1.41.264.209 I slot launch_slot_: id 3 | task 110 | processing task, is_child = 0 1.41.321.776 I slot print_timing: id 1 | task 104 | prompt eval time = 505.63 ms / 111 tokens ( 4.56 ms per token, 219.53 tokens per second) 1.41.321.778 I slot print_timing: id 1 | task 104 | eval time = 70.10 ms / 2 tokens ( 70.10 ms per token, 14.27 tokens per second) 1.41.321.779 I slot print_timing: id 1 | task 104 | total time = 575.73 ms / 113 tokens 1.41.321.779 I slot print_timing: id 1 | task 104 | graphs reused = 1 1.41.321.780 I slot print_timing: id 1 | task 104 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.321.793 I slot release: id 1 | task 104 | stop processing: n_tokens = 121, truncated = 0 1.42.104.184 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.306 1.42.189.068 I slot launch_slot_: id 1 | task 113 | processing task, is_child = 0 1.42.621.892 I slot print_timing: id 0 | task 108 | prompt eval time = 1034.52 ms / 136 tokens ( 7.61 ms per token, 131.46 tokens per second) 1.42.621.895 I slot print_timing: id 0 | task 108 | eval time = 323.15 ms / 2 tokens ( 323.15 ms per token, 3.09 tokens per second) 1.42.621.896 I slot print_timing: id 0 | task 108 | total time = 1357.67 ms / 138 tokens 1.42.621.896 I slot print_timing: id 0 | task 108 | graphs reused = 1 1.42.621.897 I slot print_timing: id 0 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.621.942 I slot release: id 0 | task 108 | stop processing: n_tokens = 146, truncated = 0 1.42.623.073 I slot print_timing: id 2 | task 109 | prompt eval time = 1035.72 ms / 149 tokens ( 6.95 ms per token, 143.86 tokens per second) 1.42.623.076 I slot print_timing: id 2 | task 109 | eval time = 323.02 ms / 2 tokens ( 323.02 ms per token, 3.10 tokens per second) 1.42.623.077 I slot print_timing: id 2 | task 109 | total time = 1358.74 ms / 151 tokens 1.42.623.077 I slot print_timing: id 2 | task 109 | graphs reused = 1 1.42.623.077 I slot print_timing: id 2 | task 109 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.623.097 I slot release: id 2 | task 109 | stop processing: n_tokens = 159, truncated = 0 1.42.624.232 I slot print_timing: id 3 | task 110 | prompt eval time = 1036.90 ms / 126 tokens ( 8.23 ms per token, 121.52 tokens per second) 1.42.624.234 I slot print_timing: id 3 | task 110 | eval time = 322.88 ms / 2 tokens ( 322.88 ms per token, 3.10 tokens per second) 1.42.624.234 I slot print_timing: id 3 | task 110 | total time = 1359.79 ms / 128 tokens 1.42.624.235 I slot print_timing: id 3 | task 110 | graphs reused = 1 1.42.624.235 I slot print_timing: id 3 | task 110 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.624.251 I slot release: id 3 | task 110 | stop processing: n_tokens = 136, truncated = 0 1.42.663.584 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 1.42.667.575 I slot launch_slot_: id 0 | task 117 | processing task, is_child = 0 1.42.671.652 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.279 1.42.671.719 I slot launch_slot_: id 3 | task 118 | processing task, is_child = 0 1.42.671.748 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 1.42.672.301 I slot launch_slot_: id 2 | task 119 | processing task, is_child = 0 1.43.589.076 I slot print_timing: id 1 | task 113 | prompt eval time = 473.98 ms / 124 tokens ( 3.82 ms per token, 261.61 tokens per second) 1.43.589.084 I slot print_timing: id 1 | task 113 | eval time = 925.49 ms / 3 tokens ( 462.75 ms per token, 2.16 tokens per second) 1.43.589.084 I slot print_timing: id 1 | task 113 | total time = 1399.47 ms / 127 tokens 1.43.589.085 I slot print_timing: id 1 | task 113 | graphs reused = 1 1.43.589.085 I slot print_timing: id 1 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.589.118 I slot release: id 1 | task 113 | stop processing: n_tokens = 135, truncated = 0 1.43.669.618 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.274 1.43.671.358 I slot launch_slot_: id 1 | task 123 | processing task, is_child = 0 1.43.742.389 I slot print_timing: id 0 | task 117 | prompt eval time = 994.93 ms / 126 tokens ( 7.90 ms per token, 126.64 tokens per second) 1.43.742.391 I slot print_timing: id 0 | task 117 | eval time = 75.15 ms / 2 tokens ( 75.15 ms per token, 13.31 tokens per second) 1.43.742.392 I slot print_timing: id 0 | task 117 | total time = 1070.08 ms / 128 tokens 1.43.742.392 I slot print_timing: id 0 | task 117 | graphs reused = 1 1.43.742.393 I slot print_timing: id 0 | task 117 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.742.411 I slot release: id 0 | task 117 | stop processing: n_tokens = 136, truncated = 0 1.43.743.532 I slot print_timing: id 2 | task 119 | prompt eval time = 995.91 ms / 143 tokens ( 6.96 ms per token, 143.59 tokens per second) 1.43.743.535 I slot print_timing: id 2 | task 119 | eval time = 75.20 ms / 2 tokens ( 75.20 ms per token, 13.30 tokens per second) 1.43.743.537 I slot print_timing: id 2 | task 119 | total time = 1071.11 ms / 145 tokens 1.43.743.537 I slot print_timing: id 2 | task 119 | graphs reused = 1 1.43.743.537 I slot print_timing: id 2 | task 119 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.743.557 I slot release: id 2 | task 119 | stop processing: n_tokens = 153, truncated = 0 1.44.072.088 I slot print_timing: id 3 | task 118 | prompt eval time = 997.07 ms / 148 tokens ( 6.74 ms per token, 148.43 tokens per second) 1.44.072.091 I slot print_timing: id 3 | task 118 | eval time = 402.47 ms / 3 tokens ( 201.24 ms per token, 4.97 tokens per second) 1.44.072.091 I slot print_timing: id 3 | task 118 | total time = 1399.54 ms / 151 tokens 1.44.072.092 I slot print_timing: id 3 | task 118 | graphs reused = 1 1.44.072.092 I slot print_timing: id 3 | task 118 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.072.116 I slot release: id 3 | task 118 | stop processing: n_tokens = 159, truncated = 0 1.44.072.125 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.319 (> 0.100 thold), f_keep = 0.239 1.44.075.277 I slot launch_slot_: id 3 | task 127 | processing task, is_child = 0 1.44.080.512 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.287 (> 0.100 thold), f_keep = 0.272 1.44.081.069 I slot launch_slot_: id 0 | task 126 | processing task, is_child = 0 1.44.081.099 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.280 (> 0.100 thold), f_keep = 0.242 1.44.081.155 I slot launch_slot_: id 2 | task 128 | processing task, is_child = 0 1.44.933.791 I slot print_timing: id 1 | task 123 | prompt eval time = 480.05 ms / 136 tokens ( 3.53 ms per token, 283.30 tokens per second) 1.44.933.794 I slot print_timing: id 1 | task 123 | eval time = 782.37 ms / 2 tokens ( 782.37 ms per token, 1.28 tokens per second) 1.44.933.795 I slot print_timing: id 1 | task 123 | total time = 1262.42 ms / 138 tokens 1.44.933.796 I slot print_timing: id 1 | task 123 | graphs reused = 1 1.44.933.796 I slot print_timing: id 1 | task 123 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.933.824 I slot release: id 1 | task 123 | stop processing: n_tokens = 146, truncated = 0 1.45.013.538 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.253 1.45.016.346 I slot launch_slot_: id 1 | task 132 | processing task, is_child = 0 1.45.088.248 I slot print_timing: id 2 | task 128 | prompt eval time = 930.52 ms / 123 tokens ( 7.57 ms per token, 132.18 tokens per second) 1.45.088.254 I slot print_timing: id 2 | task 128 | eval time = 75.95 ms / 2 tokens ( 75.95 ms per token, 13.17 tokens per second) 1.45.088.254 I slot print_timing: id 2 | task 128 | total time = 1006.47 ms / 125 tokens 1.45.088.255 I slot print_timing: id 2 | task 128 | graphs reused = 1 1.45.088.255 I slot print_timing: id 2 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.088.277 I slot release: id 2 | task 128 | stop processing: n_tokens = 133, truncated = 0 1.45.089.373 I slot print_timing: id 3 | task 127 | prompt eval time = 931.64 ms / 110 tokens ( 8.47 ms per token, 118.07 tokens per second) 1.45.089.374 I slot print_timing: id 3 | task 127 | eval time = 75.84 ms / 2 tokens ( 75.84 ms per token, 13.19 tokens per second) 1.45.089.376 I slot print_timing: id 3 | task 127 | total time = 1007.47 ms / 112 tokens 1.45.089.376 I slot print_timing: id 3 | task 127 | graphs reused = 1 1.45.089.376 I slot print_timing: id 3 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.089.388 I slot release: id 3 | task 127 | stop processing: n_tokens = 120, truncated = 0 1.45.496.264 I slot print_timing: id 0 | task 126 | prompt eval time = 929.86 ms / 120 tokens ( 7.75 ms per token, 129.05 tokens per second) 1.45.496.267 I slot print_timing: id 0 | task 126 | eval time = 485.23 ms / 3 tokens ( 242.62 ms per token, 4.12 tokens per second) 1.45.496.267 I slot print_timing: id 0 | task 126 | total time = 1415.10 ms / 123 tokens 1.45.496.268 I slot print_timing: id 0 | task 126 | graphs reused = 1 1.45.496.268 I slot print_timing: id 0 | task 126 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.496.292 I slot release: id 0 | task 126 | stop processing: n_tokens = 131, truncated = 0 1.45.496.300 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.299 (> 0.100 thold), f_keep = 0.290 1.45.498.842 I slot launch_slot_: id 0 | task 135 | processing task, is_child = 0 1.45.503.690 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.145 (> 0.100 thold), f_keep = 0.278 1.45.503.759 I slot launch_slot_: id 2 | task 136 | processing task, is_child = 0 1.45.503.786 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.317 1.45.503.848 I slot launch_slot_: id 3 | task 137 | processing task, is_child = 0 1.46.762.901 I slot print_timing: id 1 | task 132 | prompt eval time = 559.06 ms / 175 tokens ( 3.19 ms per token, 313.02 tokens per second) 1.46.762.904 I slot print_timing: id 1 | task 132 | eval time = 1187.48 ms / 3 tokens ( 593.74 ms per token, 1.68 tokens per second) 1.46.762.904 I slot print_timing: id 1 | task 132 | total time = 1746.54 ms / 178 tokens 1.46.762.905 I slot print_timing: id 1 | task 132 | graphs reused = 1 1.46.762.905 I slot print_timing: id 1 | task 132 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.762.929 I slot release: id 1 | task 132 | stop processing: n_tokens = 186, truncated = 0 1.46.825.366 I slot print_timing: id 0 | task 135 | prompt eval time = 1257.98 ms / 118 tokens ( 10.66 ms per token, 93.80 tokens per second) 1.46.825.371 I slot print_timing: id 0 | task 135 | eval time = 63.52 ms / 2 tokens ( 63.52 ms per token, 15.74 tokens per second) 1.46.825.372 I slot print_timing: id 0 | task 135 | total time = 1321.50 ms / 120 tokens 1.46.825.373 I slot print_timing: id 0 | task 135 | graphs reused = 1 1.46.825.373 I slot print_timing: id 0 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.825.389 I slot release: id 0 | task 135 | stop processing: n_tokens = 128, truncated = 0 1.46.826.564 I slot print_timing: id 2 | task 136 | prompt eval time = 1258.64 ms / 247 tokens ( 5.10 ms per token, 196.24 tokens per second) 1.46.826.566 I slot print_timing: id 2 | task 136 | eval time = 62.41 ms / 2 tokens ( 62.41 ms per token, 16.02 tokens per second) 1.46.826.567 I slot print_timing: id 2 | task 136 | total time = 1321.05 ms / 249 tokens 1.46.826.567 I slot print_timing: id 2 | task 136 | graphs reused = 1 1.46.826.567 I slot print_timing: id 2 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.826.582 I slot release: id 2 | task 136 | stop processing: n_tokens = 257, truncated = 0 1.46.827.694 I slot print_timing: id 3 | task 137 | prompt eval time = 1259.84 ms / 138 tokens ( 9.13 ms per token, 109.54 tokens per second) 1.46.827.700 I slot print_timing: id 3 | task 137 | eval time = 62.21 ms / 2 tokens ( 62.21 ms per token, 16.07 tokens per second) 1.46.827.701 I slot print_timing: id 3 | task 137 | total time = 1322.05 ms / 140 tokens 1.46.827.701 I slot print_timing: id 3 | task 137 | graphs reused = 1 1.46.827.701 I slot print_timing: id 3 | task 137 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.827.713 I slot release: id 3 | task 137 | stop processing: n_tokens = 148, truncated = 0 1.46.827.718 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.289 1.46.829.835 I slot launch_slot_: id 0 | task 142 | processing task, is_child = 0 1.46.841.367 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.257 1.46.841.935 I slot launch_slot_: id 3 | task 143 | processing task, is_child = 0 1.46.841.997 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.240 (> 0.100 thold), f_keep = 0.199 1.46.842.507 I slot launch_slot_: id 1 | task 144 | processing task, is_child = 0 1.46.842.556 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.144 1.46.842.619 I slot launch_slot_: id 2 | task 145 | processing task, is_child = 0 1.48.351.833 I slot print_timing: id 1 | task 144 | prompt eval time = 1467.60 ms / 145 tokens ( 10.12 ms per token, 98.80 tokens per second) 1.48.351.836 I slot print_timing: id 1 | task 144 | eval time = 41.48 ms / 2 tokens ( 41.48 ms per token, 24.11 tokens per second) 1.48.351.836 I slot print_timing: id 1 | task 144 | total time = 1509.08 ms / 147 tokens 1.48.351.837 I slot print_timing: id 1 | task 144 | graphs reused = 1 1.48.351.837 I slot print_timing: id 1 | task 144 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.351.856 I slot release: id 1 | task 144 | stop processing: n_tokens = 155, truncated = 0 1.48.352.951 I slot print_timing: id 2 | task 145 | prompt eval time = 1468.52 ms / 162 tokens ( 9.06 ms per token, 110.31 tokens per second) 1.48.352.953 I slot print_timing: id 2 | task 145 | eval time = 41.55 ms / 2 tokens ( 41.55 ms per token, 24.07 tokens per second) 1.48.352.953 I slot print_timing: id 2 | task 145 | total time = 1510.08 ms / 164 tokens 1.48.352.953 I slot print_timing: id 2 | task 145 | graphs reused = 1 1.48.352.954 I slot print_timing: id 2 | task 145 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.352.965 I slot release: id 2 | task 145 | stop processing: n_tokens = 172, truncated = 0 1.48.354.069 I slot print_timing: id 3 | task 143 | prompt eval time = 1469.55 ms / 158 tokens ( 9.30 ms per token, 107.52 tokens per second) 1.48.354.071 I slot print_timing: id 3 | task 143 | eval time = 41.52 ms / 2 tokens ( 41.52 ms per token, 24.09 tokens per second) 1.48.354.071 I slot print_timing: id 3 | task 143 | total time = 1511.06 ms / 160 tokens 1.48.354.071 I slot print_timing: id 3 | task 143 | graphs reused = 1 1.48.354.072 I slot print_timing: id 3 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.354.091 I slot release: id 3 | task 143 | stop processing: n_tokens = 168, truncated = 0 1.48.379.165 I slot print_timing: id 0 | task 142 | prompt eval time = 1466.60 ms / 182 tokens ( 8.06 ms per token, 124.10 tokens per second) 1.48.379.168 I slot print_timing: id 0 | task 142 | eval time = 69.93 ms / 3 tokens ( 34.97 ms per token, 28.60 tokens per second) 1.48.379.168 I slot print_timing: id 0 | task 142 | total time = 1536.54 ms / 185 tokens 1.48.379.169 I slot print_timing: id 0 | task 142 | graphs reused = 1 1.48.379.169 I slot print_timing: id 0 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.379.184 I slot release: id 0 | task 142 | stop processing: n_tokens = 193, truncated = 0 1.48.379.196 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.192 1.48.382.044 I slot launch_slot_: id 0 | task 151 | processing task, is_child = 0 1.48.391.720 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.345 (> 0.100 thold), f_keep = 0.258 1.48.391.792 I slot launch_slot_: id 1 | task 152 | processing task, is_child = 0 1.48.391.847 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.185 (> 0.100 thold), f_keep = 0.215 1.48.392.483 I slot launch_slot_: id 2 | task 153 | processing task, is_child = 0 1.48.392.514 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.302 (> 0.100 thold), f_keep = 0.226 1.48.392.577 I slot launch_slot_: id 3 | task 154 | processing task, is_child = 0 1.49.858.311 I slot print_timing: id 1 | task 152 | prompt eval time = 1424.02 ms / 107 tokens ( 13.31 ms per token, 75.14 tokens per second) 1.49.858.313 I slot print_timing: id 1 | task 152 | eval time = 41.58 ms / 2 tokens ( 41.58 ms per token, 24.05 tokens per second) 1.49.858.314 I slot print_timing: id 1 | task 152 | total time = 1465.60 ms / 109 tokens 1.49.858.314 I slot print_timing: id 1 | task 152 | graphs reused = 1 1.49.858.315 I slot print_timing: id 1 | task 152 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.858.332 I slot release: id 1 | task 152 | stop processing: n_tokens = 117, truncated = 0 1.49.920.221 I slot print_timing: id 0 | task 151 | prompt eval time = 1423.02 ms / 229 tokens ( 6.21 ms per token, 160.93 tokens per second) 1.49.920.226 I slot print_timing: id 0 | task 151 | eval time = 104.62 ms / 3 tokens ( 52.31 ms per token, 19.12 tokens per second) 1.49.920.227 I slot print_timing: id 0 | task 151 | total time = 1527.64 ms / 232 tokens 1.49.920.227 I slot print_timing: id 0 | task 151 | graphs reused = 1 1.49.920.228 I slot print_timing: id 0 | task 151 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.920.248 I slot release: id 0 | task 151 | stop processing: n_tokens = 240, truncated = 0 1.49.921.364 I slot print_timing: id 2 | task 153 | prompt eval time = 1424.97 ms / 191 tokens ( 7.46 ms per token, 134.04 tokens per second) 1.49.921.367 I slot print_timing: id 2 | task 153 | eval time = 103.57 ms / 3 tokens ( 51.79 ms per token, 19.31 tokens per second) 1.49.921.367 I slot print_timing: id 2 | task 153 | total time = 1528.54 ms / 194 tokens 1.49.921.367 I slot print_timing: id 2 | task 153 | graphs reused = 1 1.49.921.368 I slot print_timing: id 2 | task 153 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.921.386 I slot release: id 2 | task 153 | stop processing: n_tokens = 202, truncated = 0 1.49.922.552 I slot print_timing: id 3 | task 154 | prompt eval time = 1426.01 ms / 117 tokens ( 12.19 ms per token, 82.05 tokens per second) 1.49.922.554 I slot print_timing: id 3 | task 154 | eval time = 103.61 ms / 3 tokens ( 51.80 ms per token, 19.30 tokens per second) 1.49.922.555 I slot print_timing: id 3 | task 154 | total time = 1529.62 ms / 120 tokens 1.49.922.555 I slot print_timing: id 3 | task 154 | graphs reused = 1 1.49.922.555 I slot print_timing: id 3 | task 154 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.922.567 I slot release: id 3 | task 154 | stop processing: n_tokens = 128, truncated = 0 1.49.922.572 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.154 1.49.927.161 I slot launch_slot_: id 0 | task 160 | processing task, is_child = 0 1.49.933.031 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.316 1.49.933.115 I slot launch_slot_: id 1 | task 161 | processing task, is_child = 0 1.49.933.170 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.183 1.49.933.235 I slot launch_slot_: id 2 | task 162 | processing task, is_child = 0 1.49.933.264 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.290 (> 0.100 thold), f_keep = 0.297 1.49.933.331 I slot launch_slot_: id 3 | task 163 | processing task, is_child = 0 1.51.296.476 I slot print_timing: id 3 | task 163 | prompt eval time = 1321.54 ms / 122 tokens ( 10.83 ms per token, 92.32 tokens per second) 1.51.296.482 I slot print_timing: id 3 | task 163 | eval time = 41.23 ms / 2 tokens ( 41.23 ms per token, 24.25 tokens per second) 1.51.296.482 I slot print_timing: id 3 | task 163 | total time = 1362.77 ms / 124 tokens 1.51.296.483 I slot print_timing: id 3 | task 163 | graphs reused = 1 1.51.296.483 I slot print_timing: id 3 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.296.505 I slot release: id 3 | task 163 | stop processing: n_tokens = 132, truncated = 0 1.51.334.040 I slot print_timing: id 0 | task 160 | prompt eval time = 1318.45 ms / 143 tokens ( 9.22 ms per token, 108.46 tokens per second) 1.51.334.046 I slot print_timing: id 0 | task 160 | eval time = 82.25 ms / 3 tokens ( 41.13 ms per token, 24.32 tokens per second) 1.51.334.046 I slot print_timing: id 0 | task 160 | total time = 1400.70 ms / 146 tokens 1.51.334.047 I slot print_timing: id 0 | task 160 | graphs reused = 1 1.51.334.047 I slot print_timing: id 0 | task 160 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.334.065 I slot release: id 0 | task 160 | stop processing: n_tokens = 154, truncated = 0 1.51.335.196 I slot print_timing: id 1 | task 161 | prompt eval time = 1319.40 ms / 140 tokens ( 9.42 ms per token, 106.11 tokens per second) 1.51.335.199 I slot print_timing: id 1 | task 161 | eval time = 82.32 ms / 3 tokens ( 41.16 ms per token, 24.30 tokens per second) 1.51.335.199 I slot print_timing: id 1 | task 161 | total time = 1401.71 ms / 143 tokens 1.51.335.200 I slot print_timing: id 1 | task 161 | graphs reused = 1 1.51.335.200 I slot print_timing: id 1 | task 161 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.335.210 I slot release: id 1 | task 161 | stop processing: n_tokens = 151, truncated = 0 1.51.336.289 I slot print_timing: id 2 | task 162 | prompt eval time = 1320.35 ms / 175 tokens ( 7.54 ms per token, 132.54 tokens per second) 1.51.336.290 I slot print_timing: id 2 | task 162 | eval time = 82.35 ms / 3 tokens ( 41.17 ms per token, 24.29 tokens per second) 1.51.336.291 I slot print_timing: id 2 | task 162 | total time = 1402.70 ms / 178 tokens 1.51.336.291 I slot print_timing: id 2 | task 162 | graphs reused = 1 1.51.336.291 I slot print_timing: id 2 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.336.303 I slot release: id 2 | task 162 | stop processing: n_tokens = 186, truncated = 0 1.51.336.308 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.314 (> 0.100 thold), f_keep = 0.288 1.51.337.501 I slot launch_slot_: id 3 | task 169 | processing task, is_child = 0 1.51.346.937 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.240 1.51.347.535 I slot launch_slot_: id 0 | task 170 | processing task, is_child = 0 1.51.347.598 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.253 (> 0.100 thold), f_keep = 0.245 1.51.347.656 I slot launch_slot_: id 1 | task 171 | processing task, is_child = 0 1.51.347.684 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.199 1.51.347.741 I slot launch_slot_: id 2 | task 172 | processing task, is_child = 0 1.52.643.515 I slot print_timing: id 1 | task 171 | prompt eval time = 1254.32 ms / 137 tokens ( 9.16 ms per token, 109.22 tokens per second) 1.52.643.517 I slot print_timing: id 1 | task 171 | eval time = 41.33 ms / 2 tokens ( 41.33 ms per token, 24.20 tokens per second) 1.52.643.518 I slot print_timing: id 1 | task 171 | total time = 1295.65 ms / 139 tokens 1.52.643.518 I slot print_timing: id 1 | task 171 | graphs reused = 1 1.52.643.519 I slot print_timing: id 1 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.643.537 I slot release: id 1 | task 171 | stop processing: n_tokens = 147, truncated = 0 1.52.644.629 I slot print_timing: id 2 | task 172 | prompt eval time = 1255.26 ms / 138 tokens ( 9.10 ms per token, 109.94 tokens per second) 1.52.644.631 I slot print_timing: id 2 | task 172 | eval time = 41.39 ms / 2 tokens ( 41.39 ms per token, 24.16 tokens per second) 1.52.644.631 I slot print_timing: id 2 | task 172 | total time = 1296.65 ms / 140 tokens 1.52.644.631 I slot print_timing: id 2 | task 172 | graphs reused = 1 1.52.644.632 I slot print_timing: id 2 | task 172 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.644.648 I slot release: id 2 | task 172 | stop processing: n_tokens = 148, truncated = 0 1.52.645.753 I slot print_timing: id 3 | task 169 | prompt eval time = 1256.30 ms / 112 tokens ( 11.22 ms per token, 89.15 tokens per second) 1.52.645.755 I slot print_timing: id 3 | task 169 | eval time = 41.37 ms / 2 tokens ( 41.37 ms per token, 24.17 tokens per second) 1.52.645.755 I slot print_timing: id 3 | task 169 | total time = 1297.66 ms / 114 tokens 1.52.645.755 I slot print_timing: id 3 | task 169 | graphs reused = 1 1.52.645.756 I slot print_timing: id 3 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.645.764 I slot release: id 3 | task 169 | stop processing: n_tokens = 122, truncated = 0 1.52.671.266 I slot print_timing: id 0 | task 170 | prompt eval time = 1253.34 ms / 162 tokens ( 7.74 ms per token, 129.25 tokens per second) 1.52.671.272 I slot print_timing: id 0 | task 170 | eval time = 70.18 ms / 3 tokens ( 35.09 ms per token, 28.50 tokens per second) 1.52.671.272 I slot print_timing: id 0 | task 170 | total time = 1323.52 ms / 165 tokens 1.52.671.273 I slot print_timing: id 0 | task 170 | graphs reused = 1 1.52.671.273 I slot print_timing: id 0 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.671.289 I slot release: id 0 | task 170 | stop processing: n_tokens = 173, truncated = 0 1.52.671.295 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 1.52.672.905 I slot launch_slot_: id 3 | task 178 | processing task, is_child = 0 1.52.681.953 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.214 1.52.682.031 I slot launch_slot_: id 0 | task 179 | processing task, is_child = 0 1.52.682.091 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 1.52.682.159 I slot launch_slot_: id 1 | task 180 | processing task, is_child = 0 1.52.682.190 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 1.52.682.256 I slot launch_slot_: id 2 | task 181 | processing task, is_child = 0 1.54.069.457 I slot print_timing: id 0 | task 179 | prompt eval time = 1345.60 ms / 132 tokens ( 10.19 ms per token, 98.10 tokens per second) 1.54.069.459 I slot print_timing: id 0 | task 179 | eval time = 41.59 ms / 2 tokens ( 41.59 ms per token, 24.04 tokens per second) 1.54.069.460 I slot print_timing: id 0 | task 179 | total time = 1387.19 ms / 134 tokens 1.54.069.461 I slot print_timing: id 0 | task 179 | graphs reused = 1 1.54.069.461 I slot print_timing: id 0 | task 179 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.069.486 I slot release: id 0 | task 179 | stop processing: n_tokens = 142, truncated = 0 1.54.071.634 I slot print_timing: id 2 | task 181 | prompt eval time = 1347.64 ms / 183 tokens ( 7.36 ms per token, 135.79 tokens per second) 1.54.071.636 I slot print_timing: id 2 | task 181 | eval time = 41.47 ms / 2 tokens ( 41.47 ms per token, 24.11 tokens per second) 1.54.071.636 I slot print_timing: id 2 | task 181 | total time = 1389.11 ms / 185 tokens 1.54.071.637 I slot print_timing: id 2 | task 181 | graphs reused = 1 1.54.071.637 I slot print_timing: id 2 | task 181 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.071.651 I slot release: id 2 | task 181 | stop processing: n_tokens = 193, truncated = 0 1.54.072.731 I slot print_timing: id 3 | task 178 | prompt eval time = 1348.74 ms / 122 tokens ( 11.06 ms per token, 90.45 tokens per second) 1.54.072.733 I slot print_timing: id 3 | task 178 | eval time = 41.34 ms / 2 tokens ( 41.34 ms per token, 24.19 tokens per second) 1.54.072.733 I slot print_timing: id 3 | task 178 | total time = 1390.08 ms / 124 tokens 1.54.072.733 I slot print_timing: id 3 | task 178 | graphs reused = 1 1.54.072.733 I slot print_timing: id 3 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.072.743 I slot release: id 3 | task 178 | stop processing: n_tokens = 132, truncated = 0 1.54.072.748 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.198 (> 0.100 thold), f_keep = 0.261 1.54.075.016 I slot launch_slot_: id 0 | task 186 | processing task, is_child = 0 1.54.081.416 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.192 1.54.082.019 I slot launch_slot_: id 2 | task 187 | processing task, is_child = 0 1.54.082.045 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.284 (> 0.100 thold), f_keep = 0.288 1.54.082.107 I slot launch_slot_: id 3 | task 188 | processing task, is_child = 0 1.54.139.785 I slot print_timing: id 1 | task 180 | prompt eval time = 1346.55 ms / 183 tokens ( 7.36 ms per token, 135.90 tokens per second) 1.54.139.788 I slot print_timing: id 1 | task 180 | eval time = 110.83 ms / 3 tokens ( 55.42 ms per token, 18.05 tokens per second) 1.54.139.788 I slot print_timing: id 1 | task 180 | total time = 1457.38 ms / 186 tokens 1.54.139.788 I slot print_timing: id 1 | task 180 | graphs reused = 1 1.54.139.789 I slot print_timing: id 1 | task 180 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.139.817 I slot release: id 1 | task 180 | stop processing: n_tokens = 194, truncated = 0 1.54.940.764 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.191 1.54.975.853 I slot launch_slot_: id 1 | task 191 | processing task, is_child = 0 1.55.427.341 I slot print_timing: id 0 | task 186 | prompt eval time = 1013.15 ms / 178 tokens ( 5.69 ms per token, 175.69 tokens per second) 1.55.427.357 I slot print_timing: id 0 | task 186 | eval time = 332.03 ms / 2 tokens ( 332.03 ms per token, 3.01 tokens per second) 1.55.427.359 I slot print_timing: id 0 | task 186 | total time = 1345.18 ms / 180 tokens 1.55.427.361 I slot print_timing: id 0 | task 186 | graphs reused = 1 1.55.427.362 I slot print_timing: id 0 | task 186 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.427.533 I slot release: id 0 | task 186 | stop processing: n_tokens = 188, truncated = 0 1.55.429.971 I slot print_timing: id 2 | task 187 | prompt eval time = 1016.44 ms / 117 tokens ( 8.69 ms per token, 115.11 tokens per second) 1.55.429.980 I slot print_timing: id 2 | task 187 | eval time = 331.27 ms / 2 tokens ( 331.27 ms per token, 3.02 tokens per second) 1.55.429.981 I slot print_timing: id 2 | task 187 | total time = 1347.72 ms / 119 tokens 1.55.429.983 I slot print_timing: id 2 | task 187 | graphs reused = 1 1.55.429.984 I slot print_timing: id 2 | task 187 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.430.032 I slot release: id 2 | task 187 | stop processing: n_tokens = 127, truncated = 0 1.55.432.188 I slot print_timing: id 3 | task 188 | prompt eval time = 1019.12 ms / 125 tokens ( 8.15 ms per token, 122.65 tokens per second) 1.55.432.196 I slot print_timing: id 3 | task 188 | eval time = 330.71 ms / 2 tokens ( 330.71 ms per token, 3.02 tokens per second) 1.55.432.197 I slot print_timing: id 3 | task 188 | total time = 1349.83 ms / 127 tokens 1.55.432.198 I slot print_timing: id 3 | task 188 | graphs reused = 1 1.55.432.199 I slot print_timing: id 3 | task 188 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.432.241 I slot release: id 3 | task 188 | stop processing: n_tokens = 135, truncated = 0 1.55.474.786 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.271 (> 0.100 thold), f_keep = 0.281 1.55.477.469 I slot launch_slot_: id 3 | task 195 | processing task, is_child = 0 1.55.484.651 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.197 1.55.485.387 I slot launch_slot_: id 0 | task 196 | processing task, is_child = 0 1.55.485.429 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.291 1.55.485.518 I slot launch_slot_: id 2 | task 197 | processing task, is_child = 0 1.55.545.396 I slot print_timing: id 1 | task 191 | prompt eval time = 493.25 ms / 125 tokens ( 3.95 ms per token, 253.42 tokens per second) 1.55.545.404 I slot print_timing: id 1 | task 191 | eval time = 70.61 ms / 2 tokens ( 70.61 ms per token, 14.16 tokens per second) 1.55.545.405 I slot print_timing: id 1 | task 191 | total time = 563.87 ms / 127 tokens 1.55.545.405 I slot print_timing: id 1 | task 191 | graphs reused = 1 1.55.545.406 I slot print_timing: id 1 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.545.438 I slot release: id 1 | task 191 | stop processing: n_tokens = 135, truncated = 0 1.56.279.369 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.274 1.56.354.938 I slot launch_slot_: id 1 | task 200 | processing task, is_child = 0 1.56.806.917 I slot print_timing: id 3 | task 195 | prompt eval time = 990.60 ms / 131 tokens ( 7.56 ms per token, 132.24 tokens per second) 1.56.806.932 I slot print_timing: id 3 | task 195 | eval time = 330.42 ms / 2 tokens ( 330.42 ms per token, 3.03 tokens per second) 1.56.806.933 I slot print_timing: id 3 | task 195 | total time = 1321.02 ms / 133 tokens 1.56.806.935 I slot print_timing: id 3 | task 195 | graphs reused = 1 1.56.806.936 I slot print_timing: id 3 | task 195 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.807.051 I slot release: id 3 | task 195 | stop processing: n_tokens = 141, truncated = 0 1.56.905.362 I slot print_timing: id 0 | task 196 | prompt eval time = 985.75 ms / 117 tokens ( 8.43 ms per token, 118.69 tokens per second) 1.56.905.379 I slot print_timing: id 0 | task 196 | eval time = 434.08 ms / 3 tokens ( 217.04 ms per token, 4.61 tokens per second) 1.56.905.380 I slot print_timing: id 0 | task 196 | total time = 1419.83 ms / 120 tokens 1.56.905.381 I slot print_timing: id 0 | task 196 | graphs reused = 1 1.56.905.381 I slot print_timing: id 0 | task 196 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.905.422 I slot release: id 0 | task 196 | stop processing: n_tokens = 128, truncated = 0 1.56.910.472 I slot print_timing: id 2 | task 197 | prompt eval time = 988.32 ms / 143 tokens ( 6.91 ms per token, 144.69 tokens per second) 1.56.910.476 I slot print_timing: id 2 | task 197 | eval time = 436.46 ms / 3 tokens ( 218.23 ms per token, 4.58 tokens per second) 1.56.910.477 I slot print_timing: id 2 | task 197 | total time = 1424.78 ms / 146 tokens 1.56.910.478 I slot print_timing: id 2 | task 197 | graphs reused = 1 1.56.910.478 I slot print_timing: id 2 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.910.500 I slot release: id 2 | task 197 | stop processing: n_tokens = 154, truncated = 0 1.56.910.508 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.289 1.56.914.437 I slot launch_slot_: id 0 | task 204 | processing task, is_child = 0 1.56.921.896 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.240 1.56.922.029 I slot launch_slot_: id 2 | task 205 | processing task, is_child = 0 1.56.922.073 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.262 1.56.922.174 I slot launch_slot_: id 3 | task 206 | processing task, is_child = 0 1.56.982.066 I slot print_timing: id 1 | task 200 | prompt eval time = 550.70 ms / 130 tokens ( 4.24 ms per token, 236.06 tokens per second) 1.56.982.070 I slot print_timing: id 1 | task 200 | eval time = 73.92 ms / 2 tokens ( 73.92 ms per token, 13.53 tokens per second) 1.56.982.071 I slot print_timing: id 1 | task 200 | total time = 624.62 ms / 132 tokens 1.56.982.071 I slot print_timing: id 1 | task 200 | graphs reused = 1 1.56.982.072 I slot print_timing: id 1 | task 200 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.982.097 I slot release: id 1 | task 200 | stop processing: n_tokens = 140, truncated = 0 1.57.714.730 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.325 (> 0.100 thold), f_keep = 0.264 1.57.749.281 I slot launch_slot_: id 1 | task 209 | processing task, is_child = 0 1.58.183.383 I slot print_timing: id 0 | task 204 | prompt eval time = 936.35 ms / 132 tokens ( 7.09 ms per token, 140.97 tokens per second) 1.58.183.396 I slot print_timing: id 0 | task 204 | eval time = 324.81 ms / 2 tokens ( 324.81 ms per token, 3.08 tokens per second) 1.58.183.397 I slot print_timing: id 0 | task 204 | total time = 1261.17 ms / 134 tokens 1.58.183.399 I slot print_timing: id 0 | task 204 | graphs reused = 1 1.58.183.400 I slot print_timing: id 0 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.183.501 I slot release: id 0 | task 204 | stop processing: n_tokens = 142, truncated = 0 1.58.188.047 I slot print_timing: id 3 | task 206 | prompt eval time = 939.73 ms / 131 tokens ( 7.17 ms per token, 139.40 tokens per second) 1.58.188.056 I slot print_timing: id 3 | task 206 | eval time = 325.77 ms / 2 tokens ( 325.77 ms per token, 3.07 tokens per second) 1.58.188.058 I slot print_timing: id 3 | task 206 | total time = 1265.50 ms / 133 tokens 1.58.188.059 I slot print_timing: id 3 | task 206 | graphs reused = 1 1.58.188.060 I slot print_timing: id 3 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.188.131 I slot release: id 3 | task 206 | stop processing: n_tokens = 141, truncated = 0 1.58.255.986 I slot print_timing: id 2 | task 205 | prompt eval time = 938.05 ms / 124 tokens ( 7.56 ms per token, 132.19 tokens per second) 1.58.255.995 I slot print_timing: id 2 | task 205 | eval time = 395.58 ms / 3 tokens ( 197.79 ms per token, 5.06 tokens per second) 1.58.255.996 I slot print_timing: id 2 | task 205 | total time = 1333.63 ms / 127 tokens 1.58.255.997 I slot print_timing: id 2 | task 205 | graphs reused = 1 1.58.255.997 I slot print_timing: id 2 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.256.059 I slot release: id 2 | task 205 | stop processing: n_tokens = 135, truncated = 0 1.58.256.075 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.261 1.58.260.625 I slot launch_slot_: id 0 | task 214 | processing task, is_child = 0 1.58.272.553 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.274 1.58.273.717 I slot launch_slot_: id 2 | task 213 | processing task, is_child = 0 1.58.273.771 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.262 1.58.273.902 I slot launch_slot_: id 3 | task 215 | processing task, is_child = 0 1.58.335.111 I slot print_timing: id 1 | task 209 | prompt eval time = 504.09 ms / 105 tokens ( 4.80 ms per token, 208.30 tokens per second) 1.58.335.116 I slot print_timing: id 1 | task 209 | eval time = 81.15 ms / 2 tokens ( 81.15 ms per token, 12.32 tokens per second) 1.58.335.118 I slot print_timing: id 1 | task 209 | total time = 585.24 ms / 107 tokens 1.58.335.119 I slot print_timing: id 1 | task 209 | graphs reused = 1 1.58.335.120 I slot print_timing: id 1 | task 209 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.335.146 I slot release: id 1 | task 209 | stop processing: n_tokens = 115, truncated = 0 1.59.184.404 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.322 1.59.270.010 I slot launch_slot_: id 1 | task 218 | processing task, is_child = 0 1.59.759.577 I slot print_timing: id 0 | task 214 | prompt eval time = 1106.49 ms / 160 tokens ( 6.92 ms per token, 144.60 tokens per second) 1.59.759.579 I slot print_timing: id 0 | task 214 | eval time = 379.16 ms / 2 tokens ( 379.16 ms per token, 2.64 tokens per second) 1.59.759.580 I slot print_timing: id 0 | task 214 | total time = 1485.65 ms / 162 tokens 1.59.759.580 I slot print_timing: id 0 | task 214 | graphs reused = 1 1.59.759.581 I slot print_timing: id 0 | task 214 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.759.611 I slot release: id 0 | task 214 | stop processing: n_tokens = 170, truncated = 0 1.59.760.740 I slot print_timing: id 2 | task 213 | prompt eval time = 1107.40 ms / 143 tokens ( 7.74 ms per token, 129.13 tokens per second) 1.59.760.743 I slot print_timing: id 2 | task 213 | eval time = 379.13 ms / 2 tokens ( 379.13 ms per token, 2.64 tokens per second) 1.59.760.743 I slot print_timing: id 2 | task 213 | total time = 1486.54 ms / 145 tokens 1.59.760.743 I slot print_timing: id 2 | task 213 | graphs reused = 1 1.59.760.744 I slot print_timing: id 2 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.760.761 I slot release: id 2 | task 213 | stop processing: n_tokens = 153, truncated = 0 1.59.761.893 I slot print_timing: id 3 | task 215 | prompt eval time = 1108.40 ms / 173 tokens ( 6.41 ms per token, 156.08 tokens per second) 1.59.761.896 I slot print_timing: id 3 | task 215 | eval time = 379.05 ms / 2 tokens ( 379.05 ms per token, 2.64 tokens per second) 1.59.761.896 I slot print_timing: id 3 | task 215 | total time = 1487.45 ms / 175 tokens 1.59.761.896 I slot print_timing: id 3 | task 215 | graphs reused = 1 1.59.761.897 I slot print_timing: id 3 | task 215 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.761.918 I slot release: id 3 | task 215 | stop processing: n_tokens = 183, truncated = 0 1.59.801.297 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.218 1.59.805.191 I slot launch_slot_: id 0 | task 222 | processing task, is_child = 0 1.59.810.951 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.306 (> 0.100 thold), f_keep = 0.242 1.59.811.024 I slot launch_slot_: id 2 | task 223 | processing task, is_child = 0 1.59.811.056 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.202 1.59.811.604 I slot launch_slot_: id 3 | task 224 | processing task, is_child = 0 1.59.870.477 I slot print_timing: id 1 | task 218 | prompt eval time = 530.62 ms / 161 tokens ( 3.30 ms per token, 303.42 tokens per second) 1.59.870.481 I slot print_timing: id 1 | task 218 | eval time = 69.18 ms / 2 tokens ( 69.18 ms per token, 14.45 tokens per second) 1.59.870.481 I slot print_timing: id 1 | task 218 | total time = 599.80 ms / 163 tokens 1.59.870.482 I slot print_timing: id 1 | task 218 | graphs reused = 1 1.59.870.483 I slot print_timing: id 1 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.870.510 I slot release: id 1 | task 218 | stop processing: n_tokens = 171, truncated = 0 2.00.546.350 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.216 2.00.682.454 I slot launch_slot_: id 1 | task 227 | processing task, is_child = 0 2.01.167.460 I slot print_timing: id 0 | task 222 | prompt eval time = 979.04 ms / 113 tokens ( 8.66 ms per token, 115.42 tokens per second) 2.01.167.468 I slot print_timing: id 0 | task 222 | eval time = 376.81 ms / 2 tokens ( 376.81 ms per token, 2.65 tokens per second) 2.01.167.469 I slot print_timing: id 0 | task 222 | total time = 1355.85 ms / 115 tokens 2.01.167.469 I slot print_timing: id 0 | task 222 | graphs reused = 1 2.01.167.470 I slot print_timing: id 0 | task 222 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.167.491 I slot release: id 0 | task 222 | stop processing: n_tokens = 123, truncated = 0 2.01.168.582 I slot print_timing: id 2 | task 223 | prompt eval time = 980.28 ms / 112 tokens ( 8.75 ms per token, 114.25 tokens per second) 2.01.168.585 I slot print_timing: id 2 | task 223 | eval time = 376.57 ms / 2 tokens ( 376.57 ms per token, 2.66 tokens per second) 2.01.168.585 I slot print_timing: id 2 | task 223 | total time = 1356.85 ms / 114 tokens 2.01.168.585 I slot print_timing: id 2 | task 223 | graphs reused = 1 2.01.168.586 I slot print_timing: id 2 | task 223 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.168.602 I slot release: id 2 | task 223 | stop processing: n_tokens = 122, truncated = 0 2.01.169.790 I slot print_timing: id 3 | task 224 | prompt eval time = 981.50 ms / 152 tokens ( 6.46 ms per token, 154.87 tokens per second) 2.01.169.795 I slot print_timing: id 3 | task 224 | eval time = 376.45 ms / 2 tokens ( 376.45 ms per token, 2.66 tokens per second) 2.01.169.796 I slot print_timing: id 3 | task 224 | total time = 1357.95 ms / 154 tokens 2.01.169.796 I slot print_timing: id 3 | task 224 | graphs reused = 1 2.01.169.796 I slot print_timing: id 3 | task 224 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.169.816 I slot release: id 3 | task 224 | stop processing: n_tokens = 162, truncated = 0 2.01.208.156 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.301 2.01.209.205 I slot launch_slot_: id 0 | task 231 | processing task, is_child = 0 2.01.212.578 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.306 (> 0.100 thold), f_keep = 0.303 2.01.213.106 I slot launch_slot_: id 2 | task 232 | processing task, is_child = 0 2.01.213.137 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.301 (> 0.100 thold), f_keep = 0.228 2.01.213.678 I slot launch_slot_: id 3 | task 233 | processing task, is_child = 0 2.01.271.463 I slot print_timing: id 1 | task 227 | prompt eval time = 525.18 ms / 140 tokens ( 3.75 ms per token, 266.57 tokens per second) 2.01.271.465 I slot print_timing: id 1 | task 227 | eval time = 63.31 ms / 2 tokens ( 63.31 ms per token, 15.80 tokens per second) 2.01.271.466 I slot print_timing: id 1 | task 227 | total time = 588.49 ms / 142 tokens 2.01.271.466 I slot print_timing: id 1 | task 227 | graphs reused = 1 2.01.271.467 I slot print_timing: id 1 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.271.487 I slot release: id 1 | task 227 | stop processing: n_tokens = 150, truncated = 0 2.02.003.783 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.247 2.02.036.168 I slot launch_slot_: id 1 | task 236 | processing task, is_child = 0 2.02.468.748 I slot print_timing: id 2 | task 232 | prompt eval time = 931.42 ms / 112 tokens ( 8.32 ms per token, 120.25 tokens per second) 2.02.468.752 I slot print_timing: id 2 | task 232 | eval time = 323.51 ms / 2 tokens ( 323.51 ms per token, 3.09 tokens per second) 2.02.468.754 I slot print_timing: id 2 | task 232 | total time = 1254.93 ms / 114 tokens 2.02.468.755 I slot print_timing: id 2 | task 232 | graphs reused = 1 2.02.468.755 I slot print_timing: id 2 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.468.788 I slot release: id 2 | task 232 | stop processing: n_tokens = 122, truncated = 0 2.02.469.942 I slot print_timing: id 3 | task 233 | prompt eval time = 932.39 ms / 114 tokens ( 8.18 ms per token, 122.27 tokens per second) 2.02.469.945 I slot print_timing: id 3 | task 233 | eval time = 323.63 ms / 2 tokens ( 323.63 ms per token, 3.09 tokens per second) 2.02.469.945 I slot print_timing: id 3 | task 233 | total time = 1256.03 ms / 116 tokens 2.02.469.946 I slot print_timing: id 3 | task 233 | graphs reused = 1 2.02.469.946 I slot print_timing: id 3 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.469.963 I slot release: id 3 | task 233 | stop processing: n_tokens = 124, truncated = 0 2.02.542.093 I slot print_timing: id 0 | task 231 | prompt eval time = 930.42 ms / 155 tokens ( 6.00 ms per token, 166.59 tokens per second) 2.02.542.096 I slot print_timing: id 0 | task 231 | eval time = 397.99 ms / 3 tokens ( 198.99 ms per token, 5.03 tokens per second) 2.02.542.097 I slot print_timing: id 0 | task 231 | total time = 1328.40 ms / 158 tokens 2.02.542.097 I slot print_timing: id 0 | task 231 | graphs reused = 1 2.02.542.098 I slot print_timing: id 0 | task 231 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.542.124 I slot release: id 0 | task 231 | stop processing: n_tokens = 166, truncated = 0 2.02.543.502 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.292 (> 0.100 thold), f_keep = 0.311 2.02.544.926 I slot launch_slot_: id 2 | task 240 | processing task, is_child = 0 2.02.549.341 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.223 2.02.549.413 I slot launch_slot_: id 0 | task 241 | processing task, is_child = 0 2.02.549.440 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.298 2.02.549.504 I slot launch_slot_: id 3 | task 242 | processing task, is_child = 0 2.03.504.320 I slot print_timing: id 1 | task 236 | prompt eval time = 506.61 ms / 134 tokens ( 3.78 ms per token, 264.50 tokens per second) 2.03.504.323 I slot print_timing: id 1 | task 236 | eval time = 960.82 ms / 3 tokens ( 480.41 ms per token, 2.08 tokens per second) 2.03.504.324 I slot print_timing: id 1 | task 236 | total time = 1467.43 ms / 137 tokens 2.03.504.324 I slot print_timing: id 1 | task 236 | graphs reused = 1 2.03.504.325 I slot print_timing: id 1 | task 236 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.504.355 I slot release: id 1 | task 236 | stop processing: n_tokens = 145, truncated = 0 2.03.586.690 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.255 2.03.589.134 I slot launch_slot_: id 1 | task 246 | processing task, is_child = 0 2.03.660.193 I slot print_timing: id 0 | task 241 | prompt eval time = 1034.88 ms / 125 tokens ( 8.28 ms per token, 120.79 tokens per second) 2.03.660.196 I slot print_timing: id 0 | task 241 | eval time = 75.80 ms / 2 tokens ( 75.80 ms per token, 13.19 tokens per second) 2.03.660.196 I slot print_timing: id 0 | task 241 | total time = 1110.68 ms / 127 tokens 2.03.660.197 I slot print_timing: id 0 | task 241 | graphs reused = 1 2.03.660.197 I slot print_timing: id 0 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.660.218 I slot release: id 0 | task 241 | stop processing: n_tokens = 135, truncated = 0 2.04.004.167 I slot print_timing: id 2 | task 240 | prompt eval time = 1035.88 ms / 121 tokens ( 8.56 ms per token, 116.81 tokens per second) 2.04.004.170 I slot print_timing: id 2 | task 240 | eval time = 418.64 ms / 3 tokens ( 209.32 ms per token, 4.78 tokens per second) 2.04.004.170 I slot print_timing: id 2 | task 240 | total time = 1454.52 ms / 124 tokens 2.04.004.171 I slot print_timing: id 2 | task 240 | graphs reused = 2 2.04.004.171 I slot print_timing: id 2 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.004.200 I slot release: id 2 | task 240 | stop processing: n_tokens = 132, truncated = 0 2.04.005.304 I slot print_timing: id 3 | task 242 | prompt eval time = 1036.91 ms / 170 tokens ( 6.10 ms per token, 163.95 tokens per second) 2.04.005.306 I slot print_timing: id 3 | task 242 | eval time = 418.62 ms / 3 tokens ( 209.31 ms per token, 4.78 tokens per second) 2.04.005.307 I slot print_timing: id 3 | task 242 | total time = 1455.53 ms / 173 tokens 2.04.005.307 I slot print_timing: id 3 | task 242 | graphs reused = 2 2.04.005.307 I slot print_timing: id 3 | task 242 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.005.320 I slot release: id 3 | task 242 | stop processing: n_tokens = 181, truncated = 0 2.04.005.328 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.274 2.04.007.862 I slot launch_slot_: id 0 | task 249 | processing task, is_child = 0 2.04.013.522 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.311 (> 0.100 thold), f_keep = 0.280 2.04.013.596 I slot launch_slot_: id 2 | task 250 | processing task, is_child = 0 2.04.013.630 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.204 2.04.013.707 I slot launch_slot_: id 3 | task 251 | processing task, is_child = 0 2.05.123.232 I slot print_timing: id 1 | task 246 | prompt eval time = 496.06 ms / 159 tokens ( 3.12 ms per token, 320.53 tokens per second) 2.05.123.237 I slot print_timing: id 1 | task 246 | eval time = 1038.03 ms / 3 tokens ( 519.01 ms per token, 1.93 tokens per second) 2.05.123.239 I slot print_timing: id 1 | task 246 | total time = 1534.09 ms / 162 tokens 2.05.123.240 I slot print_timing: id 1 | task 246 | graphs reused = 2 2.05.123.241 I slot print_timing: id 1 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.123.275 I slot release: id 1 | task 246 | stop processing: n_tokens = 170, truncated = 0 2.05.128.743 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.224 2.05.134.622 I slot launch_slot_: id 1 | task 255 | processing task, is_child = 0 2.05.210.682 I slot print_timing: id 2 | task 250 | prompt eval time = 1110.68 ms / 110 tokens ( 10.10 ms per token, 99.04 tokens per second) 2.05.210.690 I slot print_timing: id 2 | task 250 | eval time = 84.74 ms / 2 tokens ( 84.74 ms per token, 11.80 tokens per second) 2.05.210.691 I slot print_timing: id 2 | task 250 | total time = 1195.42 ms / 112 tokens 2.05.210.692 I slot print_timing: id 2 | task 250 | graphs reused = 2 2.05.210.692 I slot print_timing: id 2 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.210.720 I slot release: id 2 | task 250 | stop processing: n_tokens = 120, truncated = 0 2.05.581.294 I slot print_timing: id 0 | task 249 | prompt eval time = 1107.07 ms / 131 tokens ( 8.45 ms per token, 118.33 tokens per second) 2.05.581.309 I slot print_timing: id 0 | task 249 | eval time = 460.46 ms / 3 tokens ( 230.23 ms per token, 4.34 tokens per second) 2.05.581.311 I slot print_timing: id 0 | task 249 | total time = 1567.53 ms / 134 tokens 2.05.581.313 I slot print_timing: id 0 | task 249 | graphs reused = 2 2.05.581.314 I slot print_timing: id 0 | task 249 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.581.405 I slot release: id 0 | task 249 | stop processing: n_tokens = 142, truncated = 0 2.05.583.630 I slot print_timing: id 3 | task 251 | prompt eval time = 1113.37 ms / 188 tokens ( 5.92 ms per token, 168.86 tokens per second) 2.05.583.636 I slot print_timing: id 3 | task 251 | eval time = 454.88 ms / 3 tokens ( 227.44 ms per token, 4.40 tokens per second) 2.05.583.637 I slot print_timing: id 3 | task 251 | total time = 1568.24 ms / 191 tokens 2.05.583.638 I slot print_timing: id 3 | task 251 | graphs reused = 2 2.05.583.639 I slot print_timing: id 3 | task 251 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.583.700 I slot release: id 3 | task 251 | stop processing: n_tokens = 199, truncated = 0 2.05.583.731 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.261 2.05.591.415 I slot launch_slot_: id 0 | task 258 | processing task, is_child = 0 2.05.600.438 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.253 (> 0.100 thold), f_keep = 0.308 2.05.600.570 I slot launch_slot_: id 2 | task 259 | processing task, is_child = 0 2.05.600.626 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.186 2.05.601.569 I slot launch_slot_: id 3 | task 260 | processing task, is_child = 0 2.06.655.307 I slot print_timing: id 1 | task 255 | prompt eval time = 540.37 ms / 155 tokens ( 3.49 ms per token, 286.84 tokens per second) 2.06.655.321 I slot print_timing: id 1 | task 255 | eval time = 980.29 ms / 3 tokens ( 490.15 ms per token, 2.04 tokens per second) 2.06.655.322 I slot print_timing: id 1 | task 255 | total time = 1520.66 ms / 158 tokens 2.06.655.323 I slot print_timing: id 1 | task 255 | graphs reused = 2 2.06.655.323 I slot print_timing: id 1 | task 255 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.655.359 I slot release: id 1 | task 255 | stop processing: n_tokens = 166, truncated = 0 2.06.723.265 I slot print_timing: id 0 | task 258 | prompt eval time = 1050.90 ms / 148 tokens ( 7.10 ms per token, 140.83 tokens per second) 2.06.723.271 I slot print_timing: id 0 | task 258 | eval time = 70.78 ms / 2 tokens ( 70.78 ms per token, 14.13 tokens per second) 2.06.723.272 I slot print_timing: id 0 | task 258 | total time = 1121.68 ms / 150 tokens 2.06.723.273 I slot print_timing: id 0 | task 258 | graphs reused = 2 2.06.723.274 I slot print_timing: id 0 | task 258 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.723.309 I slot release: id 0 | task 258 | stop processing: n_tokens = 158, truncated = 0 2.06.728.619 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.234 2.06.733.771 I slot launch_slot_: id 0 | task 265 | processing task, is_child = 0 2.06.737.437 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.223 2.06.737.567 I slot launch_slot_: id 1 | task 266 | processing task, is_child = 0 2.06.808.292 I slot print_timing: id 2 | task 259 | prompt eval time = 1055.24 ms / 137 tokens ( 7.70 ms per token, 129.83 tokens per second) 2.06.808.303 I slot print_timing: id 2 | task 259 | eval time = 150.44 ms / 3 tokens ( 75.22 ms per token, 13.29 tokens per second) 2.06.808.304 I slot print_timing: id 2 | task 259 | total time = 1205.68 ms / 140 tokens 2.06.808.305 I slot print_timing: id 2 | task 259 | graphs reused = 3 2.06.808.306 I slot print_timing: id 2 | task 259 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.808.337 I slot release: id 2 | task 259 | stop processing: n_tokens = 148, truncated = 0 2.06.810.930 I slot print_timing: id 3 | task 260 | prompt eval time = 1057.69 ms / 117 tokens ( 9.04 ms per token, 110.62 tokens per second) 2.06.810.935 I slot print_timing: id 3 | task 260 | eval time = 150.45 ms / 3 tokens ( 75.23 ms per token, 13.29 tokens per second) 2.06.810.936 I slot print_timing: id 3 | task 260 | total time = 1208.14 ms / 120 tokens 2.06.810.937 I slot print_timing: id 3 | task 260 | graphs reused = 3 2.06.810.938 I slot print_timing: id 3 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.810.961 I slot release: id 3 | task 260 | stop processing: n_tokens = 128, truncated = 0 2.07.355.558 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.250 2.07.440.755 I slot launch_slot_: id 2 | task 269 | processing task, is_child = 0 2.07.445.737 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.286 (> 0.100 thold), f_keep = 0.297 2.07.448.957 I slot launch_slot_: id 3 | task 270 | processing task, is_child = 0 2.08.225.836 I slot print_timing: id 0 | task 265 | prompt eval time = 794.51 ms / 159 tokens ( 5.00 ms per token, 200.12 tokens per second) 2.08.225.854 I slot print_timing: id 0 | task 265 | eval time = 693.73 ms / 3 tokens ( 346.86 ms per token, 2.88 tokens per second) 2.08.225.858 I slot print_timing: id 0 | task 265 | total time = 1488.23 ms / 162 tokens 2.08.225.861 I slot print_timing: id 0 | task 265 | graphs reused = 3 2.08.225.861 I slot print_timing: id 0 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.225.954 I slot release: id 0 | task 265 | stop processing: n_tokens = 170, truncated = 0 2.08.228.240 I slot print_timing: id 1 | task 266 | prompt eval time = 796.33 ms / 136 tokens ( 5.86 ms per token, 170.78 tokens per second) 2.08.228.248 I slot print_timing: id 1 | task 266 | eval time = 694.13 ms / 3 tokens ( 347.07 ms per token, 2.88 tokens per second) 2.08.228.249 I slot print_timing: id 1 | task 266 | total time = 1490.46 ms / 139 tokens 2.08.228.266 I slot print_timing: id 1 | task 266 | graphs reused = 3 2.08.228.267 I slot print_timing: id 1 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.228.317 I slot release: id 1 | task 266 | stop processing: n_tokens = 147, truncated = 0 2.08.273.475 I slot print_timing: id 2 | task 269 | prompt eval time = 774.46 ms / 152 tokens ( 5.10 ms per token, 196.27 tokens per second) 2.08.273.480 I slot print_timing: id 2 | task 269 | eval time = 42.96 ms / 2 tokens ( 42.96 ms per token, 23.28 tokens per second) 2.08.273.481 I slot print_timing: id 2 | task 269 | total time = 817.41 ms / 154 tokens 2.08.273.482 I slot print_timing: id 2 | task 269 | graphs reused = 3 2.08.273.483 I slot print_timing: id 2 | task 269 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.273.508 I slot release: id 2 | task 269 | stop processing: n_tokens = 162, truncated = 0 2.08.275.781 I slot print_timing: id 3 | task 270 | prompt eval time = 776.32 ms / 124 tokens ( 6.26 ms per token, 159.73 tokens per second) 2.08.275.783 I slot print_timing: id 3 | task 270 | eval time = 42.87 ms / 2 tokens ( 42.87 ms per token, 23.32 tokens per second) 2.08.275.784 I slot print_timing: id 3 | task 270 | total time = 819.19 ms / 126 tokens 2.08.275.784 I slot print_timing: id 3 | task 270 | graphs reused = 3 2.08.275.785 I slot print_timing: id 3 | task 270 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.275.812 I slot release: id 3 | task 270 | stop processing: n_tokens = 134, truncated = 0 2.08.275.819 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.307 (> 0.100 thold), f_keep = 0.291 2.08.278.979 I slot launch_slot_: id 3 | task 275 | processing task, is_child = 0 2.08.291.344 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.218 2.08.291.451 I slot launch_slot_: id 0 | task 276 | processing task, is_child = 0 2.08.291.528 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.252 2.08.292.260 I slot launch_slot_: id 1 | task 277 | processing task, is_child = 0 2.08.292.301 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.228 2.08.292.389 I slot launch_slot_: id 2 | task 278 | processing task, is_child = 0 2.09.713.535 I slot print_timing: id 0 | task 276 | prompt eval time = 1371.95 ms / 159 tokens ( 8.63 ms per token, 115.89 tokens per second) 2.09.713.540 I slot print_timing: id 0 | task 276 | eval time = 49.18 ms / 2 tokens ( 49.18 ms per token, 20.33 tokens per second) 2.09.713.540 I slot print_timing: id 0 | task 276 | total time = 1421.13 ms / 161 tokens 2.09.713.541 I slot print_timing: id 0 | task 276 | graphs reused = 3 2.09.713.542 I slot print_timing: id 0 | task 276 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.713.576 I slot release: id 0 | task 276 | stop processing: n_tokens = 169, truncated = 0 2.09.715.423 I slot print_timing: id 1 | task 277 | prompt eval time = 1374.58 ms / 164 tokens ( 8.38 ms per token, 119.31 tokens per second) 2.09.715.426 I slot print_timing: id 1 | task 277 | eval time = 48.29 ms / 2 tokens ( 48.29 ms per token, 20.71 tokens per second) 2.09.715.426 I slot print_timing: id 1 | task 277 | total time = 1422.87 ms / 166 tokens 2.09.715.427 I slot print_timing: id 1 | task 277 | graphs reused = 3 2.09.715.427 I slot print_timing: id 1 | task 277 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.715.447 I slot release: id 1 | task 277 | stop processing: n_tokens = 174, truncated = 0 2.09.717.259 I slot print_timing: id 2 | task 278 | prompt eval time = 1377.38 ms / 152 tokens ( 9.06 ms per token, 110.35 tokens per second) 2.09.717.262 I slot print_timing: id 2 | task 278 | eval time = 47.19 ms / 2 tokens ( 47.19 ms per token, 21.19 tokens per second) 2.09.717.262 I slot print_timing: id 2 | task 278 | total time = 1424.57 ms / 154 tokens 2.09.717.263 I slot print_timing: id 2 | task 278 | graphs reused = 3 2.09.717.263 I slot print_timing: id 2 | task 278 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.717.279 I slot release: id 2 | task 278 | stop processing: n_tokens = 162, truncated = 0 2.09.719.080 I slot print_timing: id 3 | task 275 | prompt eval time = 1379.85 ms / 118 tokens ( 11.69 ms per token, 85.52 tokens per second) 2.09.719.084 I slot print_timing: id 3 | task 275 | eval time = 46.35 ms / 2 tokens ( 46.35 ms per token, 21.57 tokens per second) 2.09.719.085 I slot print_timing: id 3 | task 275 | total time = 1426.20 ms / 120 tokens 2.09.719.085 I slot print_timing: id 3 | task 275 | graphs reused = 3 2.09.719.085 I slot print_timing: id 3 | task 275 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.719.097 I slot release: id 3 | task 275 | stop processing: n_tokens = 128, truncated = 0 2.09.719.610 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.219 2.09.724.320 I slot launch_slot_: id 0 | task 283 | processing task, is_child = 0 2.09.733.777 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.213 2.09.733.878 I slot launch_slot_: id 1 | task 284 | processing task, is_child = 0 2.09.733.953 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.314 (> 0.100 thold), f_keep = 0.228 2.09.734.623 I slot launch_slot_: id 2 | task 285 | processing task, is_child = 0 2.09.734.664 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.289 2.09.734.741 I slot launch_slot_: id 3 | task 286 | processing task, is_child = 0 2.10.927.428 I slot print_timing: id 0 | task 283 | prompt eval time = 1150.95 ms / 154 tokens ( 7.47 ms per token, 133.80 tokens per second) 2.10.927.431 I slot print_timing: id 0 | task 283 | eval time = 41.73 ms / 2 tokens ( 41.73 ms per token, 23.97 tokens per second) 2.10.927.432 I slot print_timing: id 0 | task 283 | total time = 1192.67 ms / 156 tokens 2.10.927.432 I slot print_timing: id 0 | task 283 | graphs reused = 3 2.10.927.433 I slot print_timing: id 0 | task 283 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.927.456 I slot release: id 0 | task 283 | stop processing: n_tokens = 164, truncated = 0 2.10.928.570 I slot print_timing: id 1 | task 284 | prompt eval time = 1151.88 ms / 158 tokens ( 7.29 ms per token, 137.17 tokens per second) 2.10.928.572 I slot print_timing: id 1 | task 284 | eval time = 41.78 ms / 2 tokens ( 41.78 ms per token, 23.93 tokens per second) 2.10.928.572 I slot print_timing: id 1 | task 284 | total time = 1193.67 ms / 160 tokens 2.10.928.572 I slot print_timing: id 1 | task 284 | graphs reused = 3 2.10.928.573 I slot print_timing: id 1 | task 284 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.928.586 I slot release: id 1 | task 284 | stop processing: n_tokens = 168, truncated = 0 2.10.929.777 I slot print_timing: id 2 | task 285 | prompt eval time = 1152.85 ms / 109 tokens ( 10.58 ms per token, 94.55 tokens per second) 2.10.929.781 I slot print_timing: id 2 | task 285 | eval time = 41.88 ms / 2 tokens ( 41.88 ms per token, 23.87 tokens per second) 2.10.929.782 I slot print_timing: id 2 | task 285 | total time = 1194.74 ms / 111 tokens 2.10.929.782 I slot print_timing: id 2 | task 285 | graphs reused = 3 2.10.929.782 I slot print_timing: id 2 | task 285 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.929.791 I slot release: id 2 | task 285 | stop processing: n_tokens = 119, truncated = 0 2.10.930.956 I slot print_timing: id 3 | task 286 | prompt eval time = 1153.98 ms / 117 tokens ( 9.86 ms per token, 101.39 tokens per second) 2.10.930.961 I slot print_timing: id 3 | task 286 | eval time = 41.81 ms / 2 tokens ( 41.81 ms per token, 23.92 tokens per second) 2.10.930.961 I slot print_timing: id 3 | task 286 | total time = 1195.79 ms / 119 tokens 2.10.930.961 I slot print_timing: id 3 | task 286 | graphs reused = 3 2.10.930.962 I slot print_timing: id 3 | task 286 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.930.969 I slot release: id 3 | task 286 | stop processing: n_tokens = 127, truncated = 0 2.10.931.188 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.330 (> 0.100 thold), f_keep = 0.226 2.10.933.978 I slot launch_slot_: id 0 | task 291 | processing task, is_child = 0 2.10.938.969 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.220 2.10.939.034 I slot launch_slot_: id 1 | task 292 | processing task, is_child = 0 2.10.939.082 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.311 2.10.939.136 I slot launch_slot_: id 2 | task 293 | processing task, is_child = 0 2.10.939.162 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.291 2.10.939.663 I slot launch_slot_: id 3 | task 294 | processing task, is_child = 0 2.12.187.417 I slot print_timing: id 0 | task 291 | prompt eval time = 1206.27 ms / 103 tokens ( 11.71 ms per token, 85.39 tokens per second) 2.12.187.419 I slot print_timing: id 0 | task 291 | eval time = 41.48 ms / 2 tokens ( 41.48 ms per token, 24.11 tokens per second) 2.12.187.420 I slot print_timing: id 0 | task 291 | total time = 1247.74 ms / 105 tokens 2.12.187.420 I slot print_timing: id 0 | task 291 | graphs reused = 3 2.12.187.421 I slot print_timing: id 0 | task 291 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.187.441 I slot release: id 0 | task 291 | stop processing: n_tokens = 113, truncated = 0 2.12.188.533 I slot print_timing: id 1 | task 292 | prompt eval time = 1207.25 ms / 188 tokens ( 6.42 ms per token, 155.73 tokens per second) 2.12.188.536 I slot print_timing: id 1 | task 292 | eval time = 41.50 ms / 2 tokens ( 41.50 ms per token, 24.10 tokens per second) 2.12.188.536 I slot print_timing: id 1 | task 292 | total time = 1248.75 ms / 190 tokens 2.12.188.536 I slot print_timing: id 1 | task 292 | graphs reused = 3 2.12.188.537 I slot print_timing: id 1 | task 292 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.188.549 I slot release: id 1 | task 292 | stop processing: n_tokens = 198, truncated = 0 2.12.227.752 I slot print_timing: id 2 | task 293 | prompt eval time = 1208.21 ms / 125 tokens ( 9.67 ms per token, 103.46 tokens per second) 2.12.227.754 I slot print_timing: id 2 | task 293 | eval time = 79.65 ms / 3 tokens ( 39.82 ms per token, 25.11 tokens per second) 2.12.227.755 I slot print_timing: id 2 | task 293 | total time = 1287.86 ms / 128 tokens 2.12.227.755 I slot print_timing: id 2 | task 293 | graphs reused = 3 2.12.227.756 I slot print_timing: id 2 | task 293 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.227.770 I slot release: id 2 | task 293 | stop processing: n_tokens = 136, truncated = 0 2.12.228.917 I slot print_timing: id 3 | task 294 | prompt eval time = 1209.22 ms / 113 tokens ( 10.70 ms per token, 93.45 tokens per second) 2.12.228.919 I slot print_timing: id 3 | task 294 | eval time = 79.70 ms / 3 tokens ( 39.85 ms per token, 25.09 tokens per second) 2.12.228.920 I slot print_timing: id 3 | task 294 | total time = 1288.92 ms / 116 tokens 2.12.228.920 I slot print_timing: id 3 | task 294 | graphs reused = 3 2.12.228.920 I slot print_timing: id 3 | task 294 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.228.932 I slot release: id 3 | task 294 | stop processing: n_tokens = 124, truncated = 0 2.12.228.937 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.270 (> 0.100 thold), f_keep = 0.327 2.12.229.962 I slot launch_slot_: id 0 | task 300 | processing task, is_child = 0 2.12.237.774 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.187 2.12.237.858 I slot launch_slot_: id 1 | task 301 | processing task, is_child = 0 2.12.237.907 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.247 (> 0.100 thold), f_keep = 0.306 2.12.237.966 I slot launch_slot_: id 3 | task 302 | processing task, is_child = 0 2.12.237.992 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.272 2.12.238.051 I slot launch_slot_: id 2 | task 303 | processing task, is_child = 0 2.13.596.141 I slot print_timing: id 0 | task 300 | prompt eval time = 1316.08 ms / 128 tokens ( 10.28 ms per token, 97.26 tokens per second) 2.13.596.144 I slot print_timing: id 0 | task 300 | eval time = 42.00 ms / 2 tokens ( 42.00 ms per token, 23.81 tokens per second) 2.13.596.144 I slot print_timing: id 0 | task 300 | total time = 1358.08 ms / 130 tokens 2.13.596.145 I slot print_timing: id 0 | task 300 | graphs reused = 3 2.13.596.145 I slot print_timing: id 0 | task 300 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.596.167 I slot release: id 0 | task 300 | stop processing: n_tokens = 138, truncated = 0 2.13.598.357 I slot print_timing: id 2 | task 303 | prompt eval time = 1318.24 ms / 127 tokens ( 10.38 ms per token, 96.34 tokens per second) 2.13.598.363 I slot print_timing: id 2 | task 303 | eval time = 41.80 ms / 2 tokens ( 41.80 ms per token, 23.93 tokens per second) 2.13.598.363 I slot print_timing: id 2 | task 303 | total time = 1360.03 ms / 129 tokens 2.13.598.364 I slot print_timing: id 2 | task 303 | graphs reused = 3 2.13.598.364 I slot print_timing: id 2 | task 303 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.598.375 I slot release: id 2 | task 303 | stop processing: n_tokens = 137, truncated = 0 2.13.599.471 I slot print_timing: id 3 | task 302 | prompt eval time = 1319.40 ms / 145 tokens ( 9.10 ms per token, 109.90 tokens per second) 2.13.599.473 I slot print_timing: id 3 | task 302 | eval time = 41.63 ms / 2 tokens ( 41.63 ms per token, 24.02 tokens per second) 2.13.599.473 I slot print_timing: id 3 | task 302 | total time = 1361.03 ms / 147 tokens 2.13.599.474 I slot print_timing: id 3 | task 302 | graphs reused = 3 2.13.599.474 I slot print_timing: id 3 | task 302 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.599.483 I slot release: id 3 | task 302 | stop processing: n_tokens = 155, truncated = 0 2.13.599.488 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.245 2.13.603.321 I slot launch_slot_: id 3 | task 308 | processing task, is_child = 0 2.13.607.160 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.268 2.13.607.236 I slot launch_slot_: id 0 | task 309 | processing task, is_child = 0 2.13.607.268 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.270 2.13.607.798 I slot launch_slot_: id 2 | task 310 | processing task, is_child = 0 2.13.665.538 I slot print_timing: id 1 | task 301 | prompt eval time = 1317.08 ms / 166 tokens ( 7.93 ms per token, 126.04 tokens per second) 2.13.665.541 I slot print_timing: id 1 | task 301 | eval time = 110.26 ms / 3 tokens ( 55.13 ms per token, 18.14 tokens per second) 2.13.665.541 I slot print_timing: id 1 | task 301 | total time = 1427.34 ms / 169 tokens 2.13.665.541 I slot print_timing: id 1 | task 301 | graphs reused = 3 2.13.665.542 I slot print_timing: id 1 | task 301 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.665.562 I slot release: id 1 | task 301 | stop processing: n_tokens = 177, truncated = 0 2.14.454.414 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.209 2.14.539.879 I slot launch_slot_: id 1 | task 313 | processing task, is_child = 0 2.15.024.765 I slot print_timing: id 0 | task 309 | prompt eval time = 1040.96 ms / 124 tokens ( 8.39 ms per token, 119.12 tokens per second) 2.15.024.770 I slot print_timing: id 0 | task 309 | eval time = 376.00 ms / 2 tokens ( 376.00 ms per token, 2.66 tokens per second) 2.15.024.770 I slot print_timing: id 0 | task 309 | total time = 1416.96 ms / 126 tokens 2.15.024.771 I slot print_timing: id 0 | task 309 | graphs reused = 3 2.15.024.771 I slot print_timing: id 0 | task 309 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.024.791 I slot release: id 0 | task 309 | stop processing: n_tokens = 134, truncated = 0 2.15.026.992 I slot print_timing: id 3 | task 308 | prompt eval time = 1043.16 ms / 139 tokens ( 7.50 ms per token, 133.25 tokens per second) 2.15.026.994 I slot print_timing: id 3 | task 308 | eval time = 375.78 ms / 2 tokens ( 375.78 ms per token, 2.66 tokens per second) 2.15.026.994 I slot print_timing: id 3 | task 308 | total time = 1418.94 ms / 141 tokens 2.15.026.995 I slot print_timing: id 3 | task 308 | graphs reused = 3 2.15.026.995 I slot print_timing: id 3 | task 308 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.027.008 I slot release: id 3 | task 308 | stop processing: n_tokens = 149, truncated = 0 2.15.089.385 I slot print_timing: id 2 | task 310 | prompt eval time = 1042.05 ms / 161 tokens ( 6.47 ms per token, 154.50 tokens per second) 2.15.089.390 I slot print_timing: id 2 | task 310 | eval time = 439.40 ms / 3 tokens ( 219.70 ms per token, 4.55 tokens per second) 2.15.089.391 I slot print_timing: id 2 | task 310 | total time = 1481.45 ms / 164 tokens 2.15.089.391 I slot print_timing: id 2 | task 310 | graphs reused = 3 2.15.089.392 I slot print_timing: id 2 | task 310 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.089.411 I slot release: id 2 | task 310 | stop processing: n_tokens = 172, truncated = 0 2.15.089.418 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.276 2.15.090.900 I slot launch_slot_: id 0 | task 317 | processing task, is_child = 0 2.15.097.262 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.215 2.15.097.337 I slot launch_slot_: id 2 | task 318 | processing task, is_child = 0 2.15.097.367 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.248 2.15.097.933 I slot launch_slot_: id 3 | task 319 | processing task, is_child = 0 2.15.155.625 I slot print_timing: id 1 | task 313 | prompt eval time = 547.42 ms / 142 tokens ( 3.86 ms per token, 259.40 tokens per second) 2.15.155.631 I slot print_timing: id 1 | task 313 | eval time = 67.30 ms / 2 tokens ( 67.30 ms per token, 14.86 tokens per second) 2.15.155.632 I slot print_timing: id 1 | task 313 | total time = 614.71 ms / 144 tokens 2.15.155.632 I slot print_timing: id 1 | task 313 | graphs reused = 3 2.15.155.633 I slot print_timing: id 1 | task 313 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.155.651 I slot release: id 1 | task 313 | stop processing: n_tokens = 152, truncated = 0 2.16.056.561 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.243 2.16.142.082 I slot launch_slot_: id 1 | task 322 | processing task, is_child = 0 2.16.633.130 I slot print_timing: id 0 | task 317 | prompt eval time = 1155.89 ms / 122 tokens ( 9.47 ms per token, 105.55 tokens per second) 2.16.633.139 I slot print_timing: id 0 | task 317 | eval time = 379.29 ms / 2 tokens ( 379.29 ms per token, 2.64 tokens per second) 2.16.633.139 I slot print_timing: id 0 | task 317 | total time = 1535.18 ms / 124 tokens 2.16.633.140 I slot print_timing: id 0 | task 317 | graphs reused = 3 2.16.633.140 I slot print_timing: id 0 | task 317 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.633.181 I slot release: id 0 | task 317 | stop processing: n_tokens = 132, truncated = 0 2.16.634.334 I slot print_timing: id 2 | task 318 | prompt eval time = 1156.88 ms / 173 tokens ( 6.69 ms per token, 149.54 tokens per second) 2.16.634.338 I slot print_timing: id 2 | task 318 | eval time = 379.39 ms / 2 tokens ( 379.39 ms per token, 2.64 tokens per second) 2.16.634.338 I slot print_timing: id 2 | task 318 | total time = 1536.27 ms / 175 tokens 2.16.634.339 I slot print_timing: id 2 | task 318 | graphs reused = 3 2.16.634.339 I slot print_timing: id 2 | task 318 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.634.354 I slot release: id 2 | task 318 | stop processing: n_tokens = 183, truncated = 0 2.16.635.457 I slot print_timing: id 3 | task 319 | prompt eval time = 1157.81 ms / 190 tokens ( 6.09 ms per token, 164.10 tokens per second) 2.16.635.458 I slot print_timing: id 3 | task 319 | eval time = 379.44 ms / 2 tokens ( 379.44 ms per token, 2.64 tokens per second) 2.16.635.459 I slot print_timing: id 3 | task 319 | total time = 1537.25 ms / 192 tokens 2.16.635.459 I slot print_timing: id 3 | task 319 | graphs reused = 3 2.16.635.459 I slot print_timing: id 3 | task 319 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.635.472 I slot release: id 3 | task 319 | stop processing: n_tokens = 200, truncated = 0 2.16.673.934 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.280 2.16.676.487 I slot launch_slot_: id 0 | task 326 | processing task, is_child = 0 2.16.682.912 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.202 2.16.682.996 I slot launch_slot_: id 2 | task 327 | processing task, is_child = 0 2.16.683.033 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.325 (> 0.100 thold), f_keep = 0.185 2.16.683.108 I slot launch_slot_: id 3 | task 328 | processing task, is_child = 0 2.17.587.799 I slot print_timing: id 1 | task 322 | prompt eval time = 531.12 ms / 162 tokens ( 3.28 ms per token, 305.01 tokens per second) 2.17.587.805 I slot print_timing: id 1 | task 322 | eval time = 913.86 ms / 3 tokens ( 456.93 ms per token, 2.19 tokens per second) 2.17.587.805 I slot print_timing: id 1 | task 322 | total time = 1444.99 ms / 165 tokens 2.17.587.806 I slot print_timing: id 1 | task 322 | graphs reused = 3 2.17.587.806 I slot print_timing: id 1 | task 322 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.587.838 I slot release: id 1 | task 322 | stop processing: n_tokens = 173, truncated = 0 2.17.667.727 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.214 2.17.670.570 I slot launch_slot_: id 1 | task 332 | processing task, is_child = 0 2.17.741.574 I slot print_timing: id 0 | task 326 | prompt eval time = 982.12 ms / 136 tokens ( 7.22 ms per token, 138.48 tokens per second) 2.17.741.580 I slot print_timing: id 0 | task 326 | eval time = 76.33 ms / 2 tokens ( 76.33 ms per token, 13.10 tokens per second) 2.17.741.580 I slot print_timing: id 0 | task 326 | total time = 1058.46 ms / 138 tokens 2.17.741.581 I slot print_timing: id 0 | task 326 | graphs reused = 3 2.17.741.581 I slot print_timing: id 0 | task 326 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.741.602 I slot release: id 0 | task 326 | stop processing: n_tokens = 146, truncated = 0 2.17.742.709 I slot print_timing: id 2 | task 327 | prompt eval time = 983.21 ms / 126 tokens ( 7.80 ms per token, 128.15 tokens per second) 2.17.742.712 I slot print_timing: id 2 | task 327 | eval time = 76.26 ms / 2 tokens ( 76.26 ms per token, 13.11 tokens per second) 2.17.742.712 I slot print_timing: id 2 | task 327 | total time = 1059.47 ms / 128 tokens 2.17.742.712 I slot print_timing: id 2 | task 327 | graphs reused = 3 2.17.742.713 I slot print_timing: id 2 | task 327 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.742.729 I slot release: id 2 | task 327 | stop processing: n_tokens = 136, truncated = 0 2.17.743.831 I slot print_timing: id 3 | task 328 | prompt eval time = 984.37 ms / 105 tokens ( 9.37 ms per token, 106.67 tokens per second) 2.17.743.833 I slot print_timing: id 3 | task 328 | eval time = 76.11 ms / 2 tokens ( 76.11 ms per token, 13.14 tokens per second) 2.17.743.834 I slot print_timing: id 3 | task 328 | total time = 1060.48 ms / 107 tokens 2.17.743.834 I slot print_timing: id 3 | task 328 | graphs reused = 3 2.17.743.834 I slot print_timing: id 3 | task 328 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.743.843 I slot release: id 3 | task 328 | stop processing: n_tokens = 115, truncated = 0 2.18.137.613 I slot print_timing: id 1 | task 332 | prompt eval time = 417.11 ms / 146 tokens ( 2.86 ms per token, 350.03 tokens per second) 2.18.137.619 I slot print_timing: id 1 | task 332 | eval time = 49.92 ms / 3 tokens ( 24.96 ms per token, 40.06 tokens per second) 2.18.137.619 I slot print_timing: id 1 | task 332 | total time = 467.03 ms / 149 tokens 2.18.137.620 I slot print_timing: id 1 | task 332 | graphs reused = 4 2.18.137.621 I slot print_timing: id 1 | task 332 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.137.637 I slot release: id 1 | task 332 | stop processing: n_tokens = 157, truncated = 0 2.18.159.343 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 146, t_last = 323761939146 2.18.160.756 I slot launch_slot_: id 0 | task 338 | processing task, is_child = 0 2.18.168.644 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 136, t_last = 323761940272 2.18.168.703 I slot launch_slot_: id 2 | task 339 | processing task, is_child = 0 2.18.168.777 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 115, t_last = 323761941386 2.18.168.824 I slot launch_slot_: id 3 | task 340 | processing task, is_child = 0 2.18.168.862 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 157, t_last = 323762335180 2.18.168.916 I slot launch_slot_: id 1 | task 341 | processing task, is_child = 0 2.22.161.550 I slot print_timing: id 0 | task 338 | prompt processing, n_tokens = 674, progress = 0.57, t = 3.99 s / 168.81 tokens per second 2.22.238.470 I slot print_timing: id 1 | task 341 | prompt processing, n_tokens = 670, progress = 0.57, t = 3.99 s / 167.81 tokens per second 2.22.243.724 I slot print_timing: id 2 | task 339 | prompt processing, n_tokens = 683, progress = 0.57, t = 3.99 s / 171.08 tokens per second 2.22.248.237 I slot print_timing: id 3 | task 340 | prompt processing, n_tokens = 21, progress = 0.03, t = 3.99 s / 5.26 tokens per second 2.25.557.410 I slot print_timing: id 0 | task 338 | prompt processing, n_tokens = 1086, progress = 0.91, t = 7.39 s / 146.99 tokens per second 2.26.055.905 I slot print_timing: id 1 | task 341 | prompt processing, n_tokens = 1086, progress = 0.92, t = 7.39 s / 146.99 tokens per second 2.26.061.058 I slot print_timing: id 2 | task 339 | prompt processing, n_tokens = 1086, progress = 0.91, t = 7.39 s / 146.99 tokens per second 2.26.065.494 I slot print_timing: id 3 | task 340 | prompt processing, n_tokens = 655, progress = 0.56, t = 7.39 s / 88.66 tokens per second 2.26.957.337 I slot print_timing: id 0 | task 338 | prompt processing, n_tokens = 1186, progress = 1.00, t = 8.79 s / 134.95 tokens per second 2.27.648.666 I slot print_timing: id 1 | task 341 | prompt processing, n_tokens = 1182, progress = 1.00, t = 8.79 s / 134.50 tokens per second 2.27.660.514 I slot print_timing: id 2 | task 339 | prompt processing, n_tokens = 1195, progress = 1.00, t = 8.79 s / 135.98 tokens per second 2.27.671.549 I slot print_timing: id 3 | task 340 | prompt processing, n_tokens = 1086, progress = 0.93, t = 8.79 s / 123.58 tokens per second 2.27.981.543 I slot print_timing: id 3 | task 340 | prompt processing, n_tokens = 1167, progress = 1.00, t = 9.81 s / 118.97 tokens per second 2.31.026.769 I slot print_timing: id 3 | task 340 | prompt eval time = 9896.16 ms / 1171 tokens ( 8.45 ms per token, 118.33 tokens per second) 2.31.026.772 I slot print_timing: id 3 | task 340 | eval time = 2961.34 ms / 67 tokens ( 44.87 ms per token, 22.29 tokens per second) 2.31.026.773 I slot print_timing: id 3 | task 340 | total time = 12857.50 ms / 1238 tokens 2.31.026.774 I slot print_timing: id 3 | task 340 | graphs reused = 70 2.31.026.774 I slot print_timing: id 3 | task 340 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.026.827 I slot release: id 3 | task 340 | stop processing: n_tokens = 1246, truncated = 0 2.31.070.247 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.895 2.31.070.271 I slot launch_slot_: id 3 | task 414 | processing task, is_child = 0 2.31.776.722 I slot print_timing: id 1 | task 341 | prompt eval time = 9811.33 ms / 1186 tokens ( 8.27 ms per token, 120.88 tokens per second) 2.31.776.730 I slot print_timing: id 1 | task 341 | eval time = 3796.34 ms / 78 tokens ( 49.30 ms per token, 20.28 tokens per second) 2.31.776.731 I slot print_timing: id 1 | task 341 | total time = 13607.68 ms / 1264 tokens 2.31.776.731 I slot print_timing: id 1 | task 341 | graphs reused = 75 2.31.776.732 I slot print_timing: id 1 | task 341 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.776.789 I slot release: id 1 | task 341 | stop processing: n_tokens = 1272, truncated = 0 2.31.847.159 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.877 2.31.847.186 I slot launch_slot_: id 1 | task 425 | processing task, is_child = 0 2.33.180.296 I slot print_timing: id 0 | task 338 | n_gen = 100, tg = 19.03 t/s, tg_3s = 19.23 t/s 2.33.183.505 I slot print_timing: id 2 | task 339 | n_gen = 100, tg = 19.03 t/s, tg_3s = 19.22 t/s 2.36.185.953 I slot print_timing: id 0 | task 338 | n_gen = 167, tg = 20.23 t/s, tg_3s = 22.29 t/s 2.36.189.114 I slot print_timing: id 2 | task 339 | n_gen = 167, tg = 20.23 t/s, tg_3s = 22.29 t/s 2.36.325.344 I slot print_timing: id 3 | task 414 | n_gen = 100, tg = 20.36 t/s, tg_3s = 20.57 t/s 2.36.771.221 I slot print_timing: id 1 | task 425 | n_gen = 100, tg = 22.26 t/s, tg_3s = 22.48 t/s 2.37.444.711 I slot print_timing: id 0 | task 338 | prompt eval time = 9810.28 ms / 1190 tokens ( 8.24 ms per token, 121.30 tokens per second) 2.37.444.720 I slot print_timing: id 0 | task 338 | eval time = 9465.50 ms / 195 tokens ( 48.79 ms per token, 20.50 tokens per second) 2.37.444.721 I slot print_timing: id 0 | task 338 | total time = 19275.78 ms / 1385 tokens 2.37.444.722 I slot print_timing: id 0 | task 338 | graphs reused = 188 2.37.444.722 I slot print_timing: id 0 | task 338 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.444.787 I slot release: id 0 | task 338 | stop processing: n_tokens = 1393, truncated = 0 2.37.492.920 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.800 2.37.492.944 I slot launch_slot_: id 0 | task 543 | processing task, is_child = 0 2.38.702.988 I slot print_timing: id 3 | task 414 | prompt eval time = 392.65 ms / 107 tokens ( 3.67 ms per token, 272.50 tokens per second) 2.38.702.991 I slot print_timing: id 3 | task 414 | eval time = 7240.05 ms / 146 tokens ( 49.93 ms per token, 20.03 tokens per second) 2.38.702.992 I slot print_timing: id 3 | task 414 | total time = 7632.71 ms / 253 tokens 2.38.702.993 I slot print_timing: id 3 | task 414 | graphs reused = 206 2.38.702.993 I slot print_timing: id 3 | task 414 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.703.055 I slot release: id 3 | task 414 | stop processing: n_tokens = 1367, truncated = 0 2.38.746.503 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.816 2.38.746.526 I slot launch_slot_: id 3 | task 565 | processing task, is_child = 0 2.39.193.338 I slot print_timing: id 2 | task 339 | n_gen = 221, tg = 19.62 t/s, tg_3s = 17.97 t/s 2.39.775.511 I slot print_timing: id 1 | task 425 | n_gen = 154, tg = 20.53 t/s, tg_3s = 17.97 t/s 2.41.842.387 I slot print_timing: id 2 | task 339 | prompt eval time = 9812.39 ms / 1199 tokens ( 8.18 ms per token, 122.19 tokens per second) 2.41.842.394 I slot print_timing: id 2 | task 339 | eval time = 13860.85 ms / 280 tokens ( 49.68 ms per token, 20.13 tokens per second) 2.41.842.395 I slot print_timing: id 2 | task 339 | total time = 23673.24 ms / 1479 tokens 2.41.842.395 I slot print_timing: id 2 | task 339 | graphs reused = 266 2.41.842.396 I slot print_timing: id 2 | task 339 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.842.450 I slot release: id 2 | task 339 | stop processing: n_tokens = 1487, truncated = 0 2.41.910.497 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.750 2.41.910.526 I slot launch_slot_: id 2 | task 630 | processing task, is_child = 0 2.42.626.704 I slot print_timing: id 1 | task 425 | prompt eval time = 476.46 ms / 114 tokens ( 4.18 ms per token, 239.27 tokens per second) 2.42.626.711 I slot print_timing: id 1 | task 425 | eval time = 10303.05 ms / 209 tokens ( 49.53 ms per token, 20.19 tokens per second) 2.42.626.712 I slot print_timing: id 1 | task 425 | total time = 10779.51 ms / 323 tokens 2.42.626.713 I slot print_timing: id 1 | task 425 | graphs reused = 271 2.42.626.713 I slot print_timing: id 1 | task 425 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.626.774 I slot release: id 1 | task 425 | stop processing: n_tokens = 1437, truncated = 0 2.42.696.405 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.776 2.42.696.429 I slot launch_slot_: id 1 | task 640 | processing task, is_child = 0 2.43.435.365 I slot print_timing: id 0 | task 543 | n_gen = 100, tg = 17.84 t/s, tg_3s = 18.02 t/s 2.44.388.030 I slot print_timing: id 3 | task 565 | n_gen = 100, tg = 18.72 t/s, tg_3s = 18.90 t/s 2.45.963.202 I slot print_timing: id 3 | task 565 | prompt eval time = 351.70 ms / 89 tokens ( 3.95 ms per token, 253.06 tokens per second) 2.45.963.205 I slot print_timing: id 3 | task 565 | eval time = 6864.97 ms / 135 tokens ( 51.23 ms per token, 19.52 tokens per second) 2.45.963.206 I slot print_timing: id 3 | task 565 | total time = 7216.67 ms / 224 tokens 2.45.963.207 I slot print_timing: id 3 | task 565 | graphs reused = 331 2.45.963.207 I slot print_timing: id 3 | task 565 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.963.262 I slot release: id 3 | task 565 | stop processing: n_tokens = 1338, truncated = 0 2.46.006.612 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.833 2.46.006.635 I slot launch_slot_: id 3 | task 705 | processing task, is_child = 0 2.46.474.810 I slot print_timing: id 0 | task 543 | n_gen = 162, tg = 18.74 t/s, tg_3s = 20.40 t/s 2.47.522.111 I slot print_timing: id 2 | task 630 | n_gen = 100, tg = 19.14 t/s, tg_3s = 19.34 t/s 2.47.742.345 I slot print_timing: id 0 | task 543 | prompt eval time = 391.67 ms / 117 tokens ( 3.35 ms per token, 298.72 tokens per second) 2.47.742.349 I slot print_timing: id 0 | task 543 | eval time = 9857.72 ms / 190 tokens ( 52.16 ms per token, 19.17 tokens per second) 2.47.742.349 I slot print_timing: id 0 | task 543 | total time = 10249.39 ms / 307 tokens 2.47.742.350 I slot print_timing: id 0 | task 543 | graphs reused = 361 2.47.742.351 I slot print_timing: id 0 | task 543 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.742.415 I slot release: id 0 | task 543 | stop processing: n_tokens = 1421, truncated = 0 2.47.790.415 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.785 2.47.790.441 I slot launch_slot_: id 0 | task 740 | processing task, is_child = 0 2.48.162.757 I slot print_timing: id 1 | task 640 | n_gen = 100, tg = 20.00 t/s, tg_3s = 20.20 t/s 2.48.800.198 I slot print_timing: id 2 | task 630 | prompt eval time = 440.35 ms / 118 tokens ( 3.73 ms per token, 267.97 tokens per second) 2.48.800.205 I slot print_timing: id 2 | task 630 | eval time = 6449.31 ms / 123 tokens ( 52.86 ms per token, 18.92 tokens per second) 2.48.800.205 I slot print_timing: id 2 | task 630 | total time = 6889.66 ms / 241 tokens 2.48.800.206 I slot print_timing: id 2 | task 630 | graphs reused = 376 2.48.800.206 I slot print_timing: id 2 | task 630 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.800.264 I slot release: id 2 | task 630 | stop processing: n_tokens = 1355, truncated = 0 2.48.868.146 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.823 2.48.868.176 I slot launch_slot_: id 2 | task 759 | processing task, is_child = 0 2.51.189.953 I slot print_timing: id 1 | task 640 | n_gen = 160, tg = 19.93 t/s, tg_3s = 19.82 t/s 2.51.372.435 I slot print_timing: id 3 | task 705 | n_gen = 100, tg = 19.70 t/s, tg_3s = 19.90 t/s 2.51.912.883 I slot print_timing: id 3 | task 705 | prompt eval time = 340.29 ms / 100 tokens ( 3.40 ms per token, 293.87 tokens per second) 2.51.912.891 I slot print_timing: id 3 | task 705 | eval time = 5565.95 ms / 112 tokens ( 50.14 ms per token, 19.94 tokens per second) 2.51.912.892 I slot print_timing: id 3 | task 705 | total time = 5906.24 ms / 212 tokens 2.51.912.893 I slot print_timing: id 3 | task 705 | graphs reused = 434 2.51.912.893 I slot print_timing: id 3 | task 705 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.912.953 I slot release: id 3 | task 705 | stop processing: n_tokens = 1326, truncated = 0 2.51.956.573 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.841 2.51.956.593 I slot launch_slot_: id 3 | task 822 | processing task, is_child = 0 2.53.027.803 I slot print_timing: id 0 | task 740 | prompt eval time = 327.22 ms / 76 tokens ( 4.31 ms per token, 232.26 tokens per second) 2.53.027.807 I slot print_timing: id 0 | task 740 | eval time = 4910.13 ms / 97 tokens ( 51.15 ms per token, 19.55 tokens per second) 2.53.027.808 I slot print_timing: id 0 | task 740 | total time = 5237.36 ms / 173 tokens 2.53.027.809 I slot print_timing: id 0 | task 740 | graphs reused = 449 2.53.027.810 I slot print_timing: id 0 | task 740 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.027.870 I slot release: id 0 | task 740 | stop processing: n_tokens = 1287, truncated = 0 2.53.076.099 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.866 2.53.076.130 I slot launch_slot_: id 0 | task 842 | processing task, is_child = 0 2.54.199.429 I slot print_timing: id 1 | task 640 | n_gen = 215, tg = 19.48 t/s, tg_3s = 18.28 t/s 2.54.245.946 I slot print_timing: id 2 | task 759 | n_gen = 100, tg = 19.85 t/s, tg_3s = 20.05 t/s 2.54.650.400 I slot print_timing: id 2 | task 759 | prompt eval time = 389.82 ms / 76 tokens ( 5.13 ms per token, 194.96 tokens per second) 2.54.650.405 I slot print_timing: id 2 | task 759 | eval time = 5392.40 ms / 109 tokens ( 49.93 ms per token, 20.03 tokens per second) 2.54.650.405 I slot print_timing: id 2 | task 759 | total time = 5782.22 ms / 185 tokens 2.54.650.406 I slot print_timing: id 2 | task 759 | graphs reused = 476 2.54.650.406 I slot print_timing: id 2 | task 759 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.650.459 I slot release: id 2 | task 759 | stop processing: n_tokens = 1299, truncated = 0 2.54.718.547 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.858 2.54.718.575 I slot launch_slot_: id 2 | task 873 | processing task, is_child = 0 2.57.239.183 I slot print_timing: id 1 | task 640 | n_gen = 274, tg = 19.46 t/s, tg_3s = 19.41 t/s 2.57.423.018 I slot print_timing: id 3 | task 822 | n_gen = 100, tg = 19.34 t/s, tg_3s = 19.54 t/s 2.58.003.833 I slot print_timing: id 1 | task 640 | prompt eval time = 516.32 ms / 145 tokens ( 3.56 ms per token, 280.83 tokens per second) 2.58.003.837 I slot print_timing: id 1 | task 640 | eval time = 14791.07 ms / 291 tokens ( 51.00 ms per token, 19.61 tokens per second) 2.58.003.838 I slot print_timing: id 1 | task 640 | total time = 15307.39 ms / 436 tokens 2.58.003.839 I slot print_timing: id 1 | task 640 | graphs reused = 537 2.58.003.839 I slot print_timing: id 1 | task 640 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.003.898 I slot release: id 1 | task 640 | stop processing: n_tokens = 1550, truncated = 0 2.58.073.225 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.719 2.58.073.253 I slot launch_slot_: id 1 | task 940 | processing task, is_child = 0 2.58.545.092 I slot print_timing: id 0 | task 842 | n_gen = 100, tg = 19.33 t/s, tg_3s = 19.52 t/s 2.58.686.371 I slot print_timing: id 0 | task 842 | prompt eval time = 346.21 ms / 99 tokens ( 3.50 ms per token, 285.96 tokens per second) 2.58.686.375 I slot print_timing: id 0 | task 842 | eval time = 5264.03 ms / 103 tokens ( 51.61 ms per token, 19.38 tokens per second) 2.58.686.376 I slot print_timing: id 0 | task 842 | total time = 5610.23 ms / 202 tokens 2.58.686.377 I slot print_timing: id 0 | task 842 | graphs reused = 542 2.58.686.377 I slot print_timing: id 0 | task 842 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.686.442 I slot release: id 0 | task 842 | stop processing: n_tokens = 1316, truncated = 0 2.58.735.470 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.847 2.58.735.496 I slot launch_slot_: id 0 | task 950 | processing task, is_child = 0 3.00.203.353 I slot print_timing: id 2 | task 873 | n_gen = 100, tg = 19.67 t/s, tg_3s = 19.86 t/s 3.00.428.779 I slot print_timing: id 3 | task 822 | n_gen = 154, tg = 18.83 t/s, tg_3s = 17.97 t/s 3.01.464.870 I slot print_timing: id 3 | task 822 | prompt eval time = 348.06 ms / 72 tokens ( 4.83 ms per token, 206.86 tokens per second) 3.01.464.877 I slot print_timing: id 3 | task 822 | eval time = 9160.21 ms / 177 tokens ( 52.05 ms per token, 19.21 tokens per second) 3.01.464.878 I slot print_timing: id 3 | task 822 | total time = 9508.27 ms / 249 tokens 3.01.464.878 I slot print_timing: id 3 | task 822 | graphs reused = 594 3.01.464.879 I slot print_timing: id 3 | task 822 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.464.933 I slot release: id 3 | task 822 | stop processing: n_tokens = 1363, truncated = 0 3.01.508.365 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.818 3.01.508.395 I slot launch_slot_: id 3 | task 1006 | processing task, is_child = 0 3.03.235.894 I slot print_timing: id 2 | task 873 | n_gen = 162, tg = 19.96 t/s, tg_3s = 20.44 t/s 3.03.413.572 I slot print_timing: id 1 | task 940 | n_gen = 100, tg = 19.80 t/s, tg_3s = 20.00 t/s 3.03.816.234 I slot print_timing: id 0 | task 950 | n_gen = 100, tg = 21.09 t/s, tg_3s = 21.30 t/s 3.04.625.659 I slot print_timing: id 1 | task 940 | prompt eval time = 339.94 ms / 62 tokens ( 5.48 ms per token, 182.38 tokens per second) 3.04.625.666 I slot print_timing: id 1 | task 940 | eval time = 6212.45 ms / 127 tokens ( 49.31 ms per token, 20.28 tokens per second) 3.04.625.667 I slot print_timing: id 1 | task 940 | total time = 6552.40 ms / 189 tokens 3.04.625.667 I slot print_timing: id 1 | task 940 | graphs reused = 655 3.04.625.668 I slot print_timing: id 1 | task 940 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.625.723 I slot release: id 1 | task 940 | stop processing: n_tokens = 1303, truncated = 0 3.04.695.326 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.856 3.04.695.356 I slot launch_slot_: id 1 | task 1072 | processing task, is_child = 0 3.06.265.692 I slot print_timing: id 2 | task 873 | n_gen = 223, tg = 20.01 t/s, tg_3s = 20.13 t/s 3.06.267.261 I slot print_timing: id 3 | task 1006 | prompt eval time = 335.67 ms / 74 tokens ( 4.54 ms per token, 220.45 tokens per second) 3.06.267.264 I slot print_timing: id 3 | task 1006 | eval time = 4423.19 ms / 93 tokens ( 48.08 ms per token, 20.80 tokens per second) 3.06.267.265 I slot print_timing: id 3 | task 1006 | total time = 4758.86 ms / 167 tokens 3.06.267.265 I slot print_timing: id 3 | task 1006 | graphs reused = 681 3.06.267.266 I slot print_timing: id 3 | task 1006 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.267.321 I slot release: id 3 | task 1006 | stop processing: n_tokens = 1281, truncated = 0 3.06.310.743 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.870 3.06.310.765 I slot launch_slot_: id 3 | task 1103 | processing task, is_child = 0 3.06.842.636 I slot print_timing: id 0 | task 950 | n_gen = 155, tg = 19.95 t/s, tg_3s = 18.17 t/s 3.08.284.056 I slot print_timing: id 0 | task 950 | prompt eval time = 386.73 ms / 111 tokens ( 3.48 ms per token, 287.02 tokens per second) 3.08.284.059 I slot print_timing: id 0 | task 950 | eval time = 9161.82 ms / 187 tokens ( 49.26 ms per token, 20.30 tokens per second) 3.08.284.060 I slot print_timing: id 0 | task 950 | total time = 9548.55 ms / 298 tokens 3.08.284.061 I slot print_timing: id 0 | task 950 | graphs reused = 716 3.08.284.061 I slot print_timing: id 0 | task 950 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.284.124 I slot release: id 0 | task 950 | stop processing: n_tokens = 1412, truncated = 0 3.08.332.503 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.790 3.08.332.525 I slot launch_slot_: id 0 | task 1143 | processing task, is_child = 0 3.09.161.628 I slot print_timing: id 1 | task 1072 | prompt eval time = 349.56 ms / 59 tokens ( 5.92 ms per token, 168.78 tokens per second) 3.09.161.632 I slot print_timing: id 1 | task 1072 | eval time = 4116.70 ms / 81 tokens ( 51.46 ms per token, 19.43 tokens per second) 3.09.161.633 I slot print_timing: id 1 | task 1072 | total time = 4466.27 ms / 140 tokens 3.09.161.634 I slot print_timing: id 1 | task 1072 | graphs reused = 727 3.09.161.634 I slot print_timing: id 1 | task 1072 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.161.686 I slot release: id 1 | task 1072 | stop processing: n_tokens = 1254, truncated = 0 3.09.231.501 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.889 3.09.231.528 I slot launch_slot_: id 1 | task 1158 | processing task, is_child = 0 3.09.572.547 I slot print_timing: id 2 | task 873 | n_gen = 278, tg = 19.23 t/s, tg_3s = 16.63 t/s 3.11.497.156 I slot print_timing: id 2 | task 873 | prompt eval time = 450.77 ms / 125 tokens ( 3.61 ms per token, 277.30 tokens per second) 3.11.497.161 I slot print_timing: id 2 | task 873 | eval time = 16327.80 ms / 319 tokens ( 51.35 ms per token, 19.48 tokens per second) 3.11.497.162 I slot print_timing: id 2 | task 873 | total time = 16778.57 ms / 444 tokens 3.11.497.162 I slot print_timing: id 2 | task 873 | graphs reused = 765 3.11.497.163 I slot print_timing: id 2 | task 873 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.497.237 I slot release: id 2 | task 873 | stop processing: n_tokens = 1558, truncated = 0 3.11.565.451 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.716 3.11.565.479 I slot launch_slot_: id 2 | task 1202 | processing task, is_child = 0 3.12.015.170 I slot print_timing: id 3 | task 1103 | n_gen = 100, tg = 18.48 t/s, tg_3s = 18.67 t/s 3.12.736.325 I slot print_timing: id 0 | task 1143 | prompt eval time = 328.68 ms / 70 tokens ( 4.70 ms per token, 212.97 tokens per second) 3.12.736.332 I slot print_timing: id 0 | task 1143 | eval time = 4075.11 ms / 77 tokens ( 53.62 ms per token, 18.65 tokens per second) 3.12.736.332 I slot print_timing: id 0 | task 1143 | total time = 4403.79 ms / 147 tokens 3.12.736.333 I slot print_timing: id 0 | task 1143 | graphs reused = 783 3.12.736.333 I slot print_timing: id 0 | task 1143 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.736.389 I slot release: id 0 | task 1143 | stop processing: n_tokens = 1261, truncated = 0 3.12.784.375 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.884 3.12.784.400 I slot launch_slot_: id 0 | task 1225 | processing task, is_child = 0 3.13.250.283 I slot print_timing: id 3 | task 1103 | prompt eval time = 348.26 ms / 76 tokens ( 4.58 ms per token, 218.23 tokens per second) 3.13.250.290 I slot print_timing: id 3 | task 1103 | eval time = 6591.25 ms / 122 tokens ( 54.47 ms per token, 18.36 tokens per second) 3.13.250.291 I slot print_timing: id 3 | task 1103 | total time = 6939.51 ms / 198 tokens 3.13.250.292 I slot print_timing: id 3 | task 1103 | graphs reused = 786 3.13.250.292 I slot print_timing: id 3 | task 1103 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.250.357 I slot release: id 3 | task 1103 | stop processing: n_tokens = 1312, truncated = 0 3.13.295.811 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.850 3.13.295.841 I slot launch_slot_: id 3 | task 1232 | processing task, is_child = 0 3.14.819.468 I slot print_timing: id 1 | task 1158 | n_gen = 100, tg = 19.28 t/s, tg_3s = 19.48 t/s 3.16.749.888 I slot print_timing: id 2 | task 1202 | prompt eval time = 319.57 ms / 65 tokens ( 4.92 ms per token, 203.40 tokens per second) 3.16.749.895 I slot print_timing: id 2 | task 1202 | eval time = 4864.84 ms / 100 tokens ( 49.14 ms per token, 20.35 tokens per second) 3.16.749.896 I slot print_timing: id 2 | task 1202 | total time = 5184.40 ms / 165 tokens 3.16.749.896 I slot print_timing: id 2 | task 1202 | graphs reused = 856 3.16.749.897 I slot print_timing: id 2 | task 1202 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.749.950 I slot release: id 2 | task 1202 | stop processing: n_tokens = 1279, truncated = 0 3.16.817.817 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.873 3.16.817.845 I slot launch_slot_: id 2 | task 1307 | processing task, is_child = 0 3.17.839.360 I slot print_timing: id 1 | task 1158 | n_gen = 159, tg = 19.38 t/s, tg_3s = 19.54 t/s 3.18.107.112 I slot print_timing: id 0 | task 1225 | n_gen = 100, tg = 19.82 t/s, tg_3s = 20.02 t/s 3.18.381.306 I slot print_timing: id 3 | task 1232 | n_gen = 100, tg = 20.60 t/s, tg_3s = 20.80 t/s 3.18.555.298 I slot print_timing: id 0 | task 1225 | prompt eval time = 328.77 ms / 71 tokens ( 4.63 ms per token, 215.96 tokens per second) 3.18.555.302 I slot print_timing: id 0 | task 1225 | eval time = 5442.12 ms / 110 tokens ( 49.93 ms per token, 20.03 tokens per second) 3.18.555.302 I slot print_timing: id 0 | task 1225 | total time = 5770.89 ms / 181 tokens 3.18.555.303 I slot print_timing: id 0 | task 1225 | graphs reused = 884 3.18.555.304 I slot print_timing: id 0 | task 1225 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.555.361 I slot release: id 0 | task 1225 | stop processing: n_tokens = 1295, truncated = 0 3.18.603.404 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.861 3.18.603.429 I slot launch_slot_: id 0 | task 1340 | processing task, is_child = 0 3.19.851.569 I slot print_timing: id 3 | task 1232 | prompt eval time = 278.67 ms / 62 tokens ( 4.49 ms per token, 222.48 tokens per second) 3.19.851.576 I slot print_timing: id 3 | task 1232 | eval time = 6277.05 ms / 126 tokens ( 50.22 ms per token, 19.91 tokens per second) 3.19.851.577 I slot print_timing: id 3 | task 1232 | total time = 6555.72 ms / 188 tokens 3.19.851.578 I slot print_timing: id 3 | task 1232 | graphs reused = 903 3.19.851.578 I slot print_timing: id 3 | task 1232 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.851.637 I slot release: id 3 | task 1232 | stop processing: n_tokens = 1302, truncated = 0 3.19.894.580 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.856 3.19.894.602 I slot launch_slot_: id 3 | task 1363 | processing task, is_child = 0 3.20.876.403 I slot print_timing: id 1 | task 1158 | n_gen = 213, tg = 18.94 t/s, tg_3s = 17.78 t/s 3.22.317.006 I slot print_timing: id 2 | task 1307 | n_gen = 100, tg = 19.57 t/s, tg_3s = 19.76 t/s 3.23.483.742 I slot print_timing: id 1 | task 1158 | prompt eval time = 454.26 ms / 106 tokens ( 4.29 ms per token, 233.35 tokens per second) 3.23.483.749 I slot print_timing: id 1 | task 1158 | eval time = 13797.95 ms / 271 tokens ( 51.10 ms per token, 19.57 tokens per second) 3.23.483.750 I slot print_timing: id 1 | task 1158 | total time = 14252.21 ms / 377 tokens 3.23.483.750 I slot print_timing: id 1 | task 1158 | graphs reused = 973 3.23.483.751 I slot print_timing: id 1 | task 1158 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.483.805 I slot release: id 1 | task 1158 | stop processing: n_tokens = 1491, truncated = 0 3.23.553.365 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.748 3.23.553.394 I slot launch_slot_: id 1 | task 1438 | processing task, is_child = 0 3.24.027.296 I slot print_timing: id 0 | task 1340 | n_gen = 100, tg = 19.65 t/s, tg_3s = 19.85 t/s 3.25.027.466 I slot print_timing: id 3 | task 1363 | n_gen = 100, tg = 20.90 t/s, tg_3s = 21.11 t/s 3.25.340.486 I slot print_timing: id 2 | task 1307 | n_gen = 161, tg = 19.79 t/s, tg_3s = 20.18 t/s 3.27.045.681 I slot print_timing: id 0 | task 1340 | n_gen = 167, tg = 20.61 t/s, tg_3s = 22.20 t/s 3.27.273.909 I slot print_timing: id 2 | task 1307 | prompt eval time = 439.54 ms / 105 tokens ( 4.19 ms per token, 238.88 tokens per second) 3.27.273.915 I slot print_timing: id 2 | task 1307 | eval time = 10016.51 ms / 204 tokens ( 49.34 ms per token, 20.27 tokens per second) 3.27.273.916 I slot print_timing: id 2 | task 1307 | total time = 10456.06 ms / 309 tokens 3.27.273.916 I slot print_timing: id 2 | task 1307 | graphs reused = 1047 3.27.273.917 I slot print_timing: id 2 | task 1307 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.273.976 I slot release: id 2 | task 1307 | stop processing: n_tokens = 1424, truncated = 0 3.27.341.834 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.783 3.27.341.862 I slot launch_slot_: id 2 | task 1517 | processing task, is_child = 0 3.28.029.464 I slot print_timing: id 3 | task 1363 | n_gen = 161, tg = 20.67 t/s, tg_3s = 20.32 t/s 3.28.610.860 I slot print_timing: id 1 | task 1438 | n_gen = 100, tg = 21.00 t/s, tg_3s = 21.21 t/s 3.29.689.924 I slot print_timing: id 1 | task 1438 | prompt eval time = 342.28 ms / 68 tokens ( 5.03 ms per token, 198.67 tokens per second) 3.29.689.931 I slot print_timing: id 1 | task 1438 | eval time = 5794.24 ms / 124 tokens ( 47.11 ms per token, 21.23 tokens per second) 3.29.689.932 I slot print_timing: id 1 | task 1438 | total time = 6136.52 ms / 192 tokens 3.29.689.932 I slot print_timing: id 1 | task 1438 | graphs reused = 1091 3.29.689.933 I slot print_timing: id 1 | task 1438 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.689.989 I slot release: id 1 | task 1438 | stop processing: n_tokens = 1306, truncated = 0 3.29.759.705 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.854 3.29.759.733 I slot launch_slot_: id 1 | task 1566 | processing task, is_child = 0 3.30.158.763 I slot print_timing: id 0 | task 1340 | n_gen = 223, tg = 19.88 t/s, tg_3s = 17.99 t/s 3.30.935.682 I slot print_timing: id 2 | task 1517 | prompt eval time = 320.86 ms / 62 tokens ( 5.18 ms per token, 193.23 tokens per second) 3.30.935.687 I slot print_timing: id 2 | task 1517 | eval time = 3272.95 ms / 66 tokens ( 50.35 ms per token, 19.86 tokens per second) 3.30.935.688 I slot print_timing: id 2 | task 1517 | total time = 3593.81 ms / 128 tokens 3.30.935.689 I slot print_timing: id 2 | task 1517 | graphs reused = 1107 3.30.935.689 I slot print_timing: id 2 | task 1517 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.935.745 I slot release: id 2 | task 1517 | stop processing: n_tokens = 1242, truncated = 0 3.31.003.846 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.898 3.31.003.875 I slot launch_slot_: id 2 | task 1587 | processing task, is_child = 0 3.31.286.065 I slot print_timing: id 3 | task 1363 | n_gen = 220, tg = 19.92 t/s, tg_3s = 18.12 t/s 3.32.977.353 I slot print_timing: id 0 | task 1340 | prompt eval time = 386.61 ms / 111 tokens ( 3.48 ms per token, 287.11 tokens per second) 3.32.977.357 I slot print_timing: id 0 | task 1340 | eval time = 13987.31 ms / 278 tokens ( 50.50 ms per token, 19.80 tokens per second) 3.32.977.358 I slot print_timing: id 0 | task 1340 | total time = 14373.92 ms / 389 tokens 3.32.977.358 I slot print_timing: id 0 | task 1340 | graphs reused = 1141 3.32.977.359 I slot print_timing: id 0 | task 1340 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.977.418 I slot release: id 0 | task 1340 | stop processing: n_tokens = 1503, truncated = 0 3.33.025.698 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.742 3.33.025.724 I slot launch_slot_: id 0 | task 1626 | processing task, is_child = 0 3.34.191.091 I slot print_timing: id 1 | task 1566 | prompt eval time = 400.33 ms / 74 tokens ( 5.41 ms per token, 184.85 tokens per second) 3.34.191.098 I slot print_timing: id 1 | task 1566 | eval time = 4031.02 ms / 77 tokens ( 53.04 ms per token, 18.85 tokens per second) 3.34.191.099 I slot print_timing: id 1 | task 1566 | total time = 4431.35 ms / 151 tokens 3.34.191.099 I slot print_timing: id 1 | task 1566 | graphs reused = 1159 3.34.191.100 I slot print_timing: id 1 | task 1566 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.191.157 I slot release: id 1 | task 1566 | stop processing: n_tokens = 1265, truncated = 0 3.34.260.809 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.881 3.34.260.833 I slot launch_slot_: id 1 | task 1648 | processing task, is_child = 0 3.34.556.212 I slot print_timing: id 3 | task 1363 | n_gen = 279, tg = 19.49 t/s, tg_3s = 18.04 t/s 3.36.482.163 I slot print_timing: id 2 | task 1587 | n_gen = 100, tg = 19.47 t/s, tg_3s = 19.67 t/s 3.36.483.759 I slot print_timing: id 3 | task 1363 | prompt eval time = 395.39 ms / 128 tokens ( 3.09 ms per token, 323.73 tokens per second) 3.36.483.762 I slot print_timing: id 3 | task 1363 | eval time = 16193.76 ms / 320 tokens ( 50.76 ms per token, 19.70 tokens per second) 3.36.483.762 I slot print_timing: id 3 | task 1363 | total time = 16589.15 ms / 448 tokens 3.36.483.763 I slot print_timing: id 3 | task 1363 | graphs reused = 1197 3.36.483.764 I slot print_timing: id 3 | task 1363 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.483.824 I slot release: id 3 | task 1363 | stop processing: n_tokens = 1562, truncated = 0 3.36.527.156 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.714 3.36.527.180 I slot launch_slot_: id 3 | task 1692 | processing task, is_child = 0 3.38.431.515 I slot print_timing: id 0 | task 1626 | n_gen = 100, tg = 19.56 t/s, tg_3s = 19.76 t/s 3.39.376.964 I slot print_timing: id 1 | task 1648 | n_gen = 100, tg = 21.06 t/s, tg_3s = 21.27 t/s 3.39.513.373 I slot print_timing: id 2 | task 1587 | n_gen = 162, tg = 19.84 t/s, tg_3s = 20.45 t/s 3.39.827.996 I slot print_timing: id 2 | task 1587 | prompt eval time = 394.12 ms / 80 tokens ( 4.93 ms per token, 202.98 tokens per second) 3.39.828.000 I slot print_timing: id 2 | task 1587 | eval time = 8429.99 ms / 169 tokens ( 50.18 ms per token, 19.93 tokens per second) 3.39.828.001 I slot print_timing: id 2 | task 1587 | total time = 8824.11 ms / 249 tokens 3.39.828.001 I slot print_timing: id 2 | task 1587 | graphs reused = 1262 3.39.828.002 I slot print_timing: id 2 | task 1587 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.828.055 I slot release: id 2 | task 1587 | stop processing: n_tokens = 1363, truncated = 0 3.39.895.912 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.818 3.39.895.941 I slot launch_slot_: id 2 | task 1762 | processing task, is_child = 0 3.41.457.457 I slot print_timing: id 0 | task 1626 | n_gen = 160, tg = 19.66 t/s, tg_3s = 19.83 t/s 3.41.641.789 I slot print_timing: id 3 | task 1692 | n_gen = 100, tg = 20.71 t/s, tg_3s = 20.92 t/s 3.42.402.089 I slot print_timing: id 1 | task 1648 | n_gen = 160, tg = 20.58 t/s, tg_3s = 19.83 t/s 3.43.345.222 I slot print_timing: id 0 | task 1626 | prompt eval time = 344.77 ms / 88 tokens ( 3.92 ms per token, 255.24 tokens per second) 3.43.345.226 I slot print_timing: id 0 | task 1626 | eval time = 9974.72 ms / 202 tokens ( 49.63 ms per token, 20.15 tokens per second) 3.43.345.227 I slot print_timing: id 0 | task 1626 | total time = 10319.49 ms / 290 tokens 3.43.345.227 I slot print_timing: id 0 | task 1626 | graphs reused = 1329 3.43.345.228 I slot print_timing: id 0 | task 1626 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.345.283 I slot release: id 0 | task 1626 | stop processing: n_tokens = 1404, truncated = 0 3.43.393.610 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.794 3.43.393.633 I slot launch_slot_: id 0 | task 1834 | processing task, is_child = 0 3.44.649.784 I slot print_timing: id 3 | task 1692 | n_gen = 160, tg = 20.42 t/s, tg_3s = 19.95 t/s 3.45.051.386 I slot print_timing: id 1 | task 1648 | prompt eval time = 415.29 ms / 97 tokens ( 4.28 ms per token, 233.57 tokens per second) 3.45.051.393 I slot print_timing: id 1 | task 1648 | eval time = 10375.26 ms / 212 tokens ( 49.17 ms per token, 20.34 tokens per second) 3.45.051.394 I slot print_timing: id 1 | task 1648 | total time = 10790.55 ms / 309 tokens 3.45.051.394 I slot print_timing: id 1 | task 1648 | graphs reused = 1357 3.45.051.395 I slot print_timing: id 1 | task 1648 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.051.453 I slot release: id 1 | task 1648 | stop processing: n_tokens = 1423, truncated = 0 3.45.053.081 I slot print_timing: id 2 | task 1762 | n_gen = 100, tg = 20.79 t/s, tg_3s = 21.00 t/s 3.45.120.928 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.784 3.45.120.958 I slot launch_slot_: id 1 | task 1866 | processing task, is_child = 0 3.45.578.533 I slot print_timing: id 3 | task 1692 | prompt eval time = 334.38 ms / 71 tokens ( 4.71 ms per token, 212.33 tokens per second) 3.45.578.536 I slot print_timing: id 3 | task 1692 | eval time = 8716.96 ms / 172 tokens ( 50.98 ms per token, 19.62 tokens per second) 3.45.578.537 I slot print_timing: id 3 | task 1692 | total time = 9051.34 ms / 243 tokens 3.45.578.538 I slot print_timing: id 3 | task 1692 | graphs reused = 1357 3.45.578.538 I slot print_timing: id 3 | task 1692 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.578.589 I slot release: id 3 | task 1692 | stop processing: n_tokens = 1357, truncated = 0 3.45.622.394 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.822 3.45.622.424 I slot launch_slot_: id 3 | task 1870 | processing task, is_child = 0 3.48.094.472 I slot print_timing: id 2 | task 1762 | n_gen = 153, tg = 19.48 t/s, tg_3s = 17.43 t/s 3.48.899.893 I slot print_timing: id 0 | task 1834 | n_gen = 100, tg = 19.36 t/s, tg_3s = 19.55 t/s 3.49.621.817 I slot print_timing: id 2 | task 1762 | prompt eval time = 394.10 ms / 90 tokens ( 4.38 ms per token, 228.37 tokens per second) 3.49.621.823 I slot print_timing: id 2 | task 1762 | eval time = 9331.77 ms / 187 tokens ( 50.17 ms per token, 19.93 tokens per second) 3.49.621.824 I slot print_timing: id 2 | task 1762 | total time = 9725.87 ms / 277 tokens 3.49.621.824 I slot print_timing: id 2 | task 1762 | graphs reused = 1437 3.49.621.825 I slot print_timing: id 2 | task 1762 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.621.883 I slot release: id 2 | task 1762 | stop processing: n_tokens = 1391, truncated = 0 3.49.689.805 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.802 3.49.689.830 I slot launch_slot_: id 2 | task 1955 | processing task, is_child = 0 3.50.677.294 I slot print_timing: id 1 | task 1866 | n_gen = 100, tg = 19.41 t/s, tg_3s = 19.60 t/s 3.50.815.098 I slot print_timing: id 3 | task 1870 | n_gen = 100, tg = 20.46 t/s, tg_3s = 20.66 t/s 3.51.807.217 I slot print_timing: id 3 | task 1870 | prompt eval time = 353.53 ms / 94 tokens ( 3.76 ms per token, 265.89 tokens per second) 3.51.807.221 I slot print_timing: id 3 | task 1870 | eval time = 5831.25 ms / 122 tokens ( 48.19 ms per token, 20.75 tokens per second) 3.51.807.222 I slot print_timing: id 3 | task 1870 | total time = 6184.78 ms / 216 tokens 3.51.807.222 I slot print_timing: id 3 | task 1870 | graphs reused = 1473 3.51.807.223 I slot print_timing: id 3 | task 1870 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.807.282 I slot release: id 3 | task 1870 | stop processing: n_tokens = 1330, truncated = 0 3.51.851.187 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.838 3.51.851.210 I slot launch_slot_: id 3 | task 1996 | processing task, is_child = 0 3.52.160.308 I slot print_timing: id 0 | task 1834 | n_gen = 158, tg = 18.75 t/s, tg_3s = 17.79 t/s 3.53.686.237 I slot print_timing: id 1 | task 1866 | n_gen = 160, tg = 19.60 t/s, tg_3s = 19.94 t/s 3.54.452.141 I slot print_timing: id 1 | task 1866 | prompt eval time = 454.95 ms / 106 tokens ( 4.29 ms per token, 232.99 tokens per second) 3.54.452.144 I slot print_timing: id 1 | task 1866 | eval time = 8876.22 ms / 177 tokens ( 50.43 ms per token, 19.83 tokens per second) 3.54.452.145 I slot print_timing: id 1 | task 1866 | total time = 9331.17 ms / 283 tokens 3.54.452.146 I slot print_timing: id 1 | task 1866 | graphs reused = 1521 3.54.452.146 I slot print_timing: id 1 | task 1866 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.452.203 I slot release: id 1 | task 1866 | stop processing: n_tokens = 1397, truncated = 0 3.54.521.761 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.798 3.54.521.787 I slot launch_slot_: id 1 | task 2049 | processing task, is_child = 0 3.55.163.234 I slot print_timing: id 0 | task 1834 | n_gen = 216, tg = 18.90 t/s, tg_3s = 19.31 t/s 3.55.256.885 I slot print_timing: id 2 | task 1955 | n_gen = 100, tg = 19.33 t/s, tg_3s = 19.52 t/s 3.57.056.760 I slot print_timing: id 3 | task 1996 | n_gen = 100, tg = 20.57 t/s, tg_3s = 20.78 t/s 3.58.178.766 I slot print_timing: id 0 | task 1834 | n_gen = 283, tg = 19.59 t/s, tg_3s = 22.22 t/s 3.58.271.966 I slot print_timing: id 2 | task 1955 | n_gen = 167, tg = 20.40 t/s, tg_3s = 22.22 t/s 3.59.398.020 I slot print_timing: id 1 | task 2049 | n_gen = 100, tg = 22.17 t/s, tg_3s = 22.40 t/s 3.59.711.804 I slot print_timing: id 0 | task 1834 | prompt eval time = 391.35 ms / 125 tokens ( 3.13 ms per token, 319.41 tokens per second) 3.59.711.811 I slot print_timing: id 0 | task 1834 | eval time = 15926.82 ms / 317 tokens ( 50.40 ms per token, 19.84 tokens per second) 3.59.711.812 I slot print_timing: id 0 | task 1834 | total time = 16318.16 ms / 442 tokens 3.59.711.813 I slot print_timing: id 0 | task 1834 | graphs reused = 1625 3.59.711.813 I slot print_timing: id 0 | task 1834 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.711.872 I slot release: id 0 | task 1834 | stop processing: n_tokens = 1556, truncated = 0 3.59.760.122 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.717 3.59.760.144 I slot launch_slot_: id 0 | task 2159 | processing task, is_child = 0 4.00.095.331 I slot print_timing: id 3 | task 1996 | n_gen = 162, tg = 20.51 t/s, tg_3s = 20.40 t/s 4.00.639.327 I slot print_timing: id 1 | task 2049 | prompt eval time = 410.97 ms / 71 tokens ( 5.79 ms per token, 172.76 tokens per second) 4.00.639.334 I slot print_timing: id 1 | task 2049 | eval time = 5706.56 ms / 122 tokens ( 47.16 ms per token, 21.20 tokens per second) 4.00.639.335 I slot print_timing: id 1 | task 2049 | total time = 6117.53 ms / 193 tokens 4.00.639.335 I slot print_timing: id 1 | task 2049 | graphs reused = 1637 4.00.639.336 I slot print_timing: id 1 | task 2049 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.639.396 I slot release: id 1 | task 2049 | stop processing: n_tokens = 1307, truncated = 0 4.00.708.900 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.853 4.00.708.927 I slot launch_slot_: id 1 | task 2175 | processing task, is_child = 0 4.01.289.146 I slot print_timing: id 2 | task 1955 | n_gen = 221, tg = 19.72 t/s, tg_3s = 17.90 t/s 4.02.464.382 I slot print_timing: id 3 | task 1996 | prompt eval time = 392.74 ms / 114 tokens ( 3.45 ms per token, 290.27 tokens per second) 4.02.464.389 I slot print_timing: id 3 | task 1996 | eval time = 10220.42 ms / 207 tokens ( 49.61 ms per token, 20.16 tokens per second) 4.02.464.389 I slot print_timing: id 3 | task 1996 | total time = 10613.16 ms / 321 tokens 4.02.464.390 I slot print_timing: id 3 | task 1996 | graphs reused = 1666 4.02.464.391 I slot print_timing: id 3 | task 1996 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.464.447 I slot release: id 3 | task 1996 | stop processing: n_tokens = 1435, truncated = 0 4.02.507.907 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.777 4.02.507.937 I slot launch_slot_: id 3 | task 2209 | processing task, is_child = 0 4.03.291.924 I slot print_timing: id 2 | task 1955 | prompt eval time = 445.35 ms / 103 tokens ( 4.32 ms per token, 231.28 tokens per second) 4.03.291.928 I slot print_timing: id 2 | task 1955 | eval time = 13156.74 ms / 260 tokens ( 50.80 ms per token, 19.69 tokens per second) 4.03.291.929 I slot print_timing: id 2 | task 1955 | total time = 13602.08 ms / 363 tokens 4.03.291.929 I slot print_timing: id 2 | task 1955 | graphs reused = 1675 4.03.291.930 I slot print_timing: id 2 | task 1955 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.291.989 I slot release: id 2 | task 1955 | stop processing: n_tokens = 1477, truncated = 0 4.03.359.982 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.755 4.03.360.010 I slot launch_slot_: id 2 | task 2223 | processing task, is_child = 0 4.04.922.384 I slot print_timing: id 0 | task 2159 | prompt eval time = 331.77 ms / 81 tokens ( 4.10 ms per token, 244.14 tokens per second) 4.04.922.389 I slot print_timing: id 0 | task 2159 | eval time = 4830.46 ms / 88 tokens ( 55.52 ms per token, 18.01 tokens per second) 4.04.922.389 I slot print_timing: id 0 | task 2159 | total time = 5162.23 ms / 169 tokens 4.04.922.390 I slot print_timing: id 0 | task 2159 | graphs reused = 1699 4.04.922.391 I slot print_timing: id 0 | task 2159 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.922.448 I slot release: id 0 | task 2159 | stop processing: n_tokens = 1283, truncated = 0 4.04.970.520 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.869 4.04.970.542 I slot launch_slot_: id 0 | task 2253 | processing task, is_child = 0 4.06.387.652 I slot print_timing: id 1 | task 2175 | n_gen = 100, tg = 18.75 t/s, tg_3s = 18.94 t/s 4.06.611.799 I slot print_timing: id 1 | task 2175 | prompt eval time = 397.70 ms / 74 tokens ( 5.37 ms per token, 186.07 tokens per second) 4.06.611.806 I slot print_timing: id 1 | task 2175 | eval time = 5505.16 ms / 105 tokens ( 52.93 ms per token, 18.89 tokens per second) 4.06.611.808 I slot print_timing: id 1 | task 2175 | total time = 5902.86 ms / 179 tokens 4.06.611.809 I slot print_timing: id 1 | task 2175 | graphs reused = 1727 4.06.611.809 I slot print_timing: id 1 | task 2175 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.611.863 I slot release: id 1 | task 2175 | stop processing: n_tokens = 1293, truncated = 0 4.06.681.253 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.862 4.06.681.280 I slot launch_slot_: id 1 | task 2286 | processing task, is_child = 0 4.08.212.518 I slot print_timing: id 3 | task 2209 | n_gen = 100, tg = 18.43 t/s, tg_3s = 18.62 t/s 4.08.391.882 I slot print_timing: id 3 | task 2209 | prompt eval time = 333.70 ms / 77 tokens ( 4.33 ms per token, 230.75 tokens per second) 4.08.391.886 I slot print_timing: id 3 | task 2209 | eval time = 5550.24 ms / 104 tokens ( 53.89 ms per token, 18.56 tokens per second) 4.08.391.886 I slot print_timing: id 3 | task 2209 | total time = 5883.94 ms / 181 tokens 4.08.391.887 I slot print_timing: id 3 | task 2209 | graphs reused = 1754 4.08.391.887 I slot print_timing: id 3 | task 2209 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.391.951 I slot release: id 3 | task 2209 | stop processing: n_tokens = 1295, truncated = 0 4.08.435.243 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.861 4.08.435.264 I slot launch_slot_: id 3 | task 2319 | processing task, is_child = 0 4.09.045.924 I slot print_timing: id 2 | task 2223 | n_gen = 100, tg = 18.71 t/s, tg_3s = 18.90 t/s 4.10.347.042 I slot print_timing: id 0 | task 2253 | n_gen = 100, tg = 19.63 t/s, tg_3s = 19.83 t/s 4.10.796.180 I slot print_timing: id 0 | task 2253 | prompt eval time = 334.08 ms / 97 tokens ( 3.44 ms per token, 290.35 tokens per second) 4.10.796.183 I slot print_timing: id 0 | task 2253 | eval time = 5491.55 ms / 110 tokens ( 50.38 ms per token, 19.85 tokens per second) 4.10.796.184 I slot print_timing: id 0 | task 2253 | total time = 5825.63 ms / 207 tokens 4.10.796.184 I slot print_timing: id 0 | task 2253 | graphs reused = 1798 4.10.796.187 I slot print_timing: id 0 | task 2253 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.796.242 I slot release: id 0 | task 2253 | stop processing: n_tokens = 1321, truncated = 0 4.10.844.307 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.844 4.10.844.329 I slot launch_slot_: id 0 | task 2368 | processing task, is_child = 0 4.11.385.081 I slot print_timing: id 2 | task 2223 | prompt eval time = 393.85 ms / 86 tokens ( 4.58 ms per token, 218.36 tokens per second) 4.11.385.088 I slot print_timing: id 2 | task 2223 | eval time = 7631.21 ms / 148 tokens ( 51.91 ms per token, 19.26 tokens per second) 4.11.385.089 I slot print_timing: id 2 | task 2223 | total time = 8025.06 ms / 234 tokens 4.11.385.089 I slot print_timing: id 2 | task 2223 | graphs reused = 1804 4.11.385.090 I slot print_timing: id 2 | task 2223 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.385.150 I slot release: id 2 | task 2223 | stop processing: n_tokens = 1348, truncated = 0 4.11.453.964 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.827 4.11.453.992 I slot launch_slot_: id 2 | task 2378 | processing task, is_child = 0 4.12.288.219 I slot print_timing: id 1 | task 2286 | n_gen = 100, tg = 19.02 t/s, tg_3s = 19.21 t/s 4.13.726.962 I slot print_timing: id 3 | task 2319 | n_gen = 100, tg = 19.99 t/s, tg_3s = 20.19 t/s 4.14.530.093 I slot print_timing: id 0 | task 2368 | prompt eval time = 271.86 ms / 65 tokens ( 4.18 ms per token, 239.10 tokens per second) 4.14.530.099 I slot print_timing: id 0 | task 2368 | eval time = 3413.90 ms / 70 tokens ( 49.48 ms per token, 20.21 tokens per second) 4.14.530.101 I slot print_timing: id 0 | task 2368 | total time = 3685.76 ms / 135 tokens 4.14.530.101 I slot print_timing: id 0 | task 2368 | graphs reused = 1863 4.14.530.102 I slot print_timing: id 0 | task 2368 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.530.157 I slot release: id 0 | task 2368 | stop processing: n_tokens = 1249, truncated = 0 4.14.578.253 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.893 4.14.578.282 I slot launch_slot_: id 0 | task 2442 | processing task, is_child = 0 4.15.317.397 I slot print_timing: id 1 | task 2286 | n_gen = 162, tg = 19.55 t/s, tg_3s = 20.47 t/s 4.15.721.858 I slot print_timing: id 1 | task 2286 | prompt eval time = 400.63 ms / 101 tokens ( 3.97 ms per token, 252.10 tokens per second) 4.15.721.865 I slot print_timing: id 1 | task 2286 | eval time = 8639.94 ms / 171 tokens ( 50.82 ms per token, 19.68 tokens per second) 4.15.721.866 I slot print_timing: id 1 | task 2286 | total time = 9040.57 ms / 272 tokens 4.15.721.867 I slot print_timing: id 1 | task 2286 | graphs reused = 1881 4.15.721.867 I slot print_timing: id 1 | task 2286 | graph reallocs = 0 / 0 (same size) / (changed size) 4.15.721.924 I slot release: id 1 | task 2286 | stop processing: n_tokens = 1386, truncated = 0 4.15.791.397 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.804 4.15.791.425 I slot launch_slot_: id 1 | task 2464 | processing task, is_child = 0 4.16.733.491 I slot print_timing: id 3 | task 2319 | n_gen = 155, tg = 19.35 t/s, tg_3s = 18.29 t/s 4.16.821.656 I slot print_timing: id 2 | task 2378 | n_gen = 100, tg = 19.85 t/s, tg_3s = 20.05 t/s 4.19.647.700 I slot print_timing: id 0 | task 2442 | n_gen = 100, tg = 20.89 t/s, tg_3s = 21.10 t/s 4.19.742.179 I slot print_timing: id 3 | task 2319 | n_gen = 222, tg = 20.15 t/s, tg_3s = 22.27 t/s 4.19.830.610 I slot print_timing: id 2 | task 2378 | n_gen = 167, tg = 20.76 t/s, tg_3s = 22.27 t/s 4.20.593.097 I slot print_timing: id 1 | task 2464 | n_gen = 100, tg = 22.23 t/s, tg_3s = 22.46 t/s 4.20.952.378 I slot print_timing: id 1 | task 2464 | prompt eval time = 349.15 ms / 66 tokens ( 5.29 ms per token, 189.03 tokens per second) 4.20.952.382 I slot print_timing: id 1 | task 2464 | eval time = 4811.80 ms / 108 tokens ( 44.97 ms per token, 22.24 tokens per second) 4.20.952.383 I slot print_timing: id 1 | task 2464 | total time = 5160.94 ms / 174 tokens 4.20.952.384 I slot print_timing: id 1 | task 2464 | graphs reused = 1987 4.20.952.384 I slot print_timing: id 1 | task 2464 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.952.446 I slot release: id 1 | task 2464 | stop processing: n_tokens = 1288, truncated = 0 4.21.022.155 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.866 4.21.022.181 I slot launch_slot_: id 1 | task 2575 | processing task, is_child = 0 4.21.471.079 I slot print_timing: id 3 | task 2319 | prompt eval time = 338.36 ms / 86 tokens ( 3.93 ms per token, 254.17 tokens per second) 4.21.471.085 I slot print_timing: id 3 | task 2319 | eval time = 12697.45 ms / 253 tokens ( 50.39 ms per token, 19.85 tokens per second) 4.21.471.086 I slot print_timing: id 3 | task 2319 | total time = 13035.81 ms / 339 tokens 4.21.471.086 I slot print_timing: id 3 | task 2319 | graphs reused = 1987 4.21.471.087 I slot print_timing: id 3 | task 2319 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.471.130 I slot release: id 3 | task 2319 | stop processing: n_tokens = 1453, truncated = 0 4.21.513.633 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.767 4.21.513.654 I slot launch_slot_: id 3 | task 2580 | processing task, is_child = 0 4.21.766.643 I slot print_timing: id 0 | task 2442 | prompt eval time = 329.69 ms / 73 tokens ( 4.52 ms per token, 221.42 tokens per second) 4.21.766.648 I slot print_timing: id 0 | task 2442 | eval time = 6858.65 ms / 135 tokens ( 51.18 ms per token, 19.54 tokens per second) 4.21.766.648 I slot print_timing: id 0 | task 2442 | total time = 7188.34 ms / 208 tokens 4.21.766.649 I slot print_timing: id 0 | task 2442 | graphs reused = 1987 4.21.766.649 I slot print_timing: id 0 | task 2442 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.766.731 I slot release: id 0 | task 2442 | stop processing: n_tokens = 1322, truncated = 0 4.21.848.810 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.843 4.21.848.827 I slot launch_slot_: id 0 | task 2583 | processing task, is_child = 0 4.22.355.563 I slot print_timing: id 2 | task 2378 | prompt eval time = 379.35 ms / 81 tokens ( 4.68 ms per token, 213.53 tokens per second) 4.22.355.569 I slot print_timing: id 2 | task 2378 | eval time = 10522.22 ms / 205 tokens ( 51.58 ms per token, 19.39 tokens per second) 4.22.355.570 I slot print_timing: id 2 | task 2378 | total time = 10901.56 ms / 286 tokens 4.22.355.571 I slot print_timing: id 2 | task 2378 | graphs reused = 1990 4.22.355.572 I slot print_timing: id 2 | task 2378 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.355.636 I slot release: id 2 | task 2378 | stop processing: n_tokens = 1400, truncated = 0 4.22.426.934 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.796 4.22.426.965 I slot launch_slot_: id 2 | task 2591 | processing task, is_child = 0 4.25.754.263 I slot print_timing: id 1 | task 2575 | prompt eval time = 402.79 ms / 96 tokens ( 4.20 ms per token, 238.34 tokens per second) 4.25.754.270 I slot print_timing: id 1 | task 2575 | eval time = 4329.29 ms / 78 tokens ( 56.22 ms per token, 17.79 tokens per second) 4.25.754.270 I slot print_timing: id 1 | task 2575 | total time = 4732.07 ms / 174 tokens 4.25.754.271 I slot print_timing: id 1 | task 2575 | graphs reused = 2052 4.25.754.272 I slot print_timing: id 1 | task 2575 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.754.330 I slot release: id 1 | task 2575 | stop processing: n_tokens = 1288, truncated = 0 4.25.823.836 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.866 4.25.823.861 I slot launch_slot_: id 1 | task 2659 | processing task, is_child = 0 4.27.270.694 I slot print_timing: id 3 | task 2580 | n_gen = 100, tg = 18.26 t/s, tg_3s = 18.44 t/s 4.27.355.507 I slot print_timing: id 0 | task 2583 | n_gen = 100, tg = 19.12 t/s, tg_3s = 19.32 t/s 4.27.672.887 I slot print_timing: id 2 | task 2591 | n_gen = 100, tg = 20.65 t/s, tg_3s = 20.86 t/s 4.27.714.722 I slot print_timing: id 0 | task 2583 | prompt eval time = 329.42 ms / 70 tokens ( 4.71 ms per token, 212.49 tokens per second) 4.27.714.729 I slot print_timing: id 0 | task 2583 | eval time = 5536.47 ms / 108 tokens ( 51.74 ms per token, 19.33 tokens per second) 4.27.714.729 I slot print_timing: id 0 | task 2583 | total time = 5865.89 ms / 178 tokens 4.27.714.730 I slot print_timing: id 0 | task 2583 | graphs reused = 2084 4.27.714.730 I slot print_timing: id 0 | task 2583 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.714.790 I slot release: id 0 | task 2583 | stop processing: n_tokens = 1292, truncated = 0 4.27.719.550 I slot print_timing: id 3 | task 2580 | prompt eval time = 335.14 ms / 84 tokens ( 3.99 ms per token, 250.64 tokens per second) 4.27.719.556 I slot print_timing: id 3 | task 2580 | eval time = 5870.75 ms / 110 tokens ( 53.86 ms per token, 18.57 tokens per second) 4.27.719.556 I slot print_timing: id 3 | task 2580 | total time = 6205.89 ms / 194 tokens 4.27.719.557 I slot print_timing: id 3 | task 2580 | graphs reused = 2084 4.27.719.557 I slot print_timing: id 3 | task 2580 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.719.603 I slot release: id 3 | task 2580 | stop processing: n_tokens = 1308, truncated = 0 4.27.760.423 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.863 4.27.760.443 I slot launch_slot_: id 0 | task 2696 | processing task, is_child = 0 4.27.787.368 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.852 4.27.787.388 I slot launch_slot_: id 3 | task 2697 | processing task, is_child = 0 4.30.689.648 I slot print_timing: id 2 | task 2591 | n_gen = 153, tg = 19.46 t/s, tg_3s = 17.57 t/s 4.31.316.961 I slot print_timing: id 1 | task 2659 | n_gen = 100, tg = 19.45 t/s, tg_3s = 19.64 t/s 4.32.578.143 I slot print_timing: id 3 | task 2697 | prompt eval time = 695.02 ms / 93 tokens ( 7.47 ms per token, 133.81 tokens per second) 4.32.578.150 I slot print_timing: id 3 | task 2697 | eval time = 4093.75 ms / 92 tokens ( 44.99 ms per token, 22.23 tokens per second) 4.32.578.151 I slot print_timing: id 3 | task 2697 | total time = 4788.77 ms / 185 tokens 4.32.578.151 I slot print_timing: id 3 | task 2697 | graphs reused = 2174 4.32.578.152 I slot print_timing: id 3 | task 2697 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.578.207 I slot release: id 3 | task 2697 | stop processing: n_tokens = 1299, truncated = 0 4.32.621.661 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.858 4.32.621.682 I slot launch_slot_: id 3 | task 2792 | processing task, is_child = 0 4.33.234.560 I slot print_timing: id 0 | task 2696 | n_gen = 100, tg = 20.83 t/s, tg_3s = 21.04 t/s 4.33.689.821 I slot print_timing: id 2 | task 2591 | n_gen = 213, tg = 19.61 t/s, tg_3s = 20.00 t/s 4.34.317.822 I slot print_timing: id 1 | task 2659 | n_gen = 160, tg = 19.65 t/s, tg_3s = 19.99 t/s 4.36.251.467 I slot print_timing: id 0 | task 2696 | n_gen = 167, tg = 21.36 t/s, tg_3s = 22.21 t/s 4.36.253.068 I slot print_timing: id 1 | task 2659 | prompt eval time = 402.10 ms / 88 tokens ( 4.57 ms per token, 218.85 tokens per second) 4.36.253.071 I slot print_timing: id 1 | task 2659 | eval time = 10027.10 ms / 203 tokens ( 49.64 ms per token, 20.15 tokens per second) 4.36.253.072 I slot print_timing: id 1 | task 2659 | total time = 10429.20 ms / 291 tokens 4.36.253.073 I slot print_timing: id 1 | task 2659 | graphs reused = 2245 4.36.253.073 I slot print_timing: id 1 | task 2659 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.253.129 I slot release: id 1 | task 2659 | stop processing: n_tokens = 1405, truncated = 0 4.36.322.904 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.951 (> 0.100 thold), f_keep = 0.794 4.36.322.934 I slot launch_slot_: id 1 | task 2868 | processing task, is_child = 0 4.36.706.134 I slot print_timing: id 2 | task 2591 | n_gen = 274, tg = 19.74 t/s, tg_3s = 20.22 t/s 4.37.740.833 I slot print_timing: id 2 | task 2591 | prompt eval time = 452.13 ms / 119 tokens ( 3.80 ms per token, 263.20 tokens per second) 4.37.740.841 I slot print_timing: id 2 | task 2591 | eval time = 14861.73 ms / 297 tokens ( 50.21 ms per token, 19.92 tokens per second) 4.37.740.841 I slot print_timing: id 2 | task 2591 | total time = 15313.86 ms / 416 tokens 4.37.740.842 I slot print_timing: id 2 | task 2591 | graphs reused = 2268 4.37.740.842 I slot print_timing: id 2 | task 2591 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.740.897 I slot release: id 2 | task 2591 | stop processing: n_tokens = 1530, truncated = 0 4.37.742.514 I slot print_timing: id 3 | task 2792 | n_gen = 100, tg = 20.92 t/s, tg_3s = 21.14 t/s 4.37.808.978 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.729 4.37.809.007 I slot launch_slot_: id 2 | task 2896 | processing task, is_child = 0 4.39.265.530 I slot print_timing: id 0 | task 2696 | n_gen = 221, tg = 20.40 t/s, tg_3s = 17.92 t/s 4.39.762.160 I slot print_timing: id 1 | task 2868 | prompt eval time = 338.41 ms / 57 tokens ( 5.94 ms per token, 168.44 tokens per second) 4.39.762.167 I slot print_timing: id 1 | task 2868 | eval time = 3100.81 ms / 63 tokens ( 50.01 ms per token, 19.99 tokens per second) 4.39.762.167 I slot print_timing: id 1 | task 2868 | total time = 3439.22 ms / 120 tokens 4.39.762.168 I slot print_timing: id 1 | task 2868 | graphs reused = 2302 4.39.762.169 I slot print_timing: id 1 | task 2868 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.762.225 I slot release: id 1 | task 2868 | stop processing: n_tokens = 1234, truncated = 0 4.39.831.791 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.904 4.39.831.816 I slot launch_slot_: id 1 | task 2935 | processing task, is_child = 0 4.40.744.100 I slot print_timing: id 3 | task 2792 | n_gen = 152, tg = 19.53 t/s, tg_3s = 17.32 t/s 4.42.269.773 I slot print_timing: id 0 | task 2696 | n_gen = 280, tg = 20.23 t/s, tg_3s = 19.64 t/s 4.42.724.286 I slot print_timing: id 2 | task 2896 | prompt eval time = 379.15 ms / 79 tokens ( 4.80 ms per token, 208.36 tokens per second) 4.42.724.289 I slot print_timing: id 2 | task 2896 | eval time = 4536.12 ms / 94 tokens ( 48.78 ms per token, 20.50 tokens per second) 4.42.724.290 I slot print_timing: id 2 | task 2896 | total time = 4915.27 ms / 173 tokens 4.42.724.290 I slot print_timing: id 2 | task 2896 | graphs reused = 2355 4.42.724.291 I slot print_timing: id 2 | task 2896 | graph reallocs = 0 / 0 (same size) / (changed size) 4.42.724.348 I slot release: id 2 | task 2896 | stop processing: n_tokens = 1287, truncated = 0 4.42.792.268 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.866 4.42.792.291 I slot launch_slot_: id 2 | task 2994 | processing task, is_child = 0 4.43.777.641 I slot print_timing: id 3 | task 2792 | n_gen = 212, tg = 19.60 t/s, tg_3s = 19.78 t/s 4.45.035.414 I slot print_timing: id 1 | task 2935 | n_gen = 100, tg = 20.62 t/s, tg_3s = 20.83 t/s 4.45.304.819 I slot print_timing: id 0 | task 2696 | n_gen = 340, tg = 20.15 t/s, tg_3s = 19.77 t/s 4.45.983.138 I slot print_timing: id 1 | task 2935 | prompt eval time = 403.19 ms / 101 tokens ( 3.99 ms per token, 250.50 tokens per second) 4.45.983.145 I slot print_timing: id 1 | task 2935 | eval time = 5748.13 ms / 121 tokens ( 47.90 ms per token, 20.88 tokens per second) 4.45.983.146 I slot print_timing: id 1 | task 2935 | total time = 6151.31 ms / 222 tokens 4.45.983.147 I slot print_timing: id 1 | task 2935 | graphs reused = 2416 4.45.983.147 I slot print_timing: id 1 | task 2935 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.983.201 I slot release: id 1 | task 2935 | stop processing: n_tokens = 1336, truncated = 0 4.46.052.972 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.835 4.46.052.998 I slot launch_slot_: id 1 | task 3060 | processing task, is_child = 0 4.46.800.806 I slot print_timing: id 3 | task 2792 | n_gen = 270, tg = 19.51 t/s, tg_3s = 19.19 t/s 4.47.426.775 I slot print_timing: id 0 | task 2696 | prompt eval time = 693.77 ms / 133 tokens ( 5.22 ms per token, 191.71 tokens per second) 4.47.426.779 I slot print_timing: id 0 | task 2696 | eval time = 18945.61 ms / 378 tokens ( 50.25 ms per token, 19.90 tokens per second) 4.47.426.781 I slot print_timing: id 0 | task 2696 | total time = 19639.38 ms / 511 tokens 4.47.426.781 I slot print_timing: id 0 | task 2696 | graphs reused = 2435 4.47.426.782 I slot print_timing: id 0 | task 2696 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.426.852 I slot release: id 0 | task 2696 | stop processing: n_tokens = 1625, truncated = 0 4.47.475.196 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.686 4.47.475.219 I slot launch_slot_: id 0 | task 3084 | processing task, is_child = 0 4.48.310.250 I slot print_timing: id 2 | task 2994 | n_gen = 100, tg = 19.31 t/s, tg_3s = 19.51 t/s 4.49.841.637 I slot print_timing: id 3 | task 2792 | n_gen = 332, tg = 19.67 t/s, tg_3s = 20.39 t/s 4.50.605.448 I slot print_timing: id 3 | task 2792 | prompt eval time = 389.54 ms / 103 tokens ( 3.78 ms per token, 264.42 tokens per second) 4.50.605.455 I slot print_timing: id 3 | task 2792 | eval time = 17594.22 ms / 349 tokens ( 50.56 ms per token, 19.78 tokens per second) 4.50.605.456 I slot print_timing: id 3 | task 2792 | total time = 17983.76 ms / 452 tokens 4.50.605.456 I slot print_timing: id 3 | task 2792 | graphs reused = 2496 4.50.605.457 I slot print_timing: id 3 | task 2792 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.605.513 I slot release: id 3 | task 2792 | stop processing: n_tokens = 1566, truncated = 0 4.50.648.875 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.714 4.50.648.897 I slot launch_slot_: id 3 | task 3150 | processing task, is_child = 0 4.51.352.605 I slot print_timing: id 2 | task 2994 | n_gen = 162, tg = 19.71 t/s, tg_3s = 20.38 t/s 4.51.485.520 I slot print_timing: id 1 | task 3060 | n_gen = 100, tg = 19.94 t/s, tg_3s = 20.14 t/s 4.52.341.376 I slot print_timing: id 1 | task 3060 | prompt eval time = 466.40 ms / 103 tokens ( 4.53 ms per token, 220.84 tokens per second) 4.52.341.380 I slot print_timing: id 1 | task 3060 | eval time = 5821.97 ms / 119 tokens ( 49.34 ms per token, 20.27 tokens per second) 4.52.341.380 I slot print_timing: id 1 | task 3060 | total time = 6288.37 ms / 222 tokens 4.52.341.381 I slot print_timing: id 1 | task 3060 | graphs reused = 2525 4.52.341.382 I slot print_timing: id 1 | task 3060 | graph reallocs = 0 / 0 (same size) / (changed size) 4.52.341.438 I slot release: id 1 | task 3060 | stop processing: n_tokens = 1336, truncated = 0 4.52.411.043 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.835 4.52.411.068 I slot launch_slot_: id 1 | task 3184 | processing task, is_child = 0 4.52.867.531 I slot print_timing: id 0 | task 3084 | n_gen = 100, tg = 19.57 t/s, tg_3s = 19.77 t/s 4.54.220.967 I slot print_timing: id 2 | task 2994 | prompt eval time = 391.64 ms / 78 tokens ( 5.02 ms per token, 199.16 tokens per second) 4.54.220.971 I slot print_timing: id 2 | task 2994 | eval time = 11037.02 ms / 218 tokens ( 50.86 ms per token, 19.66 tokens per second) 4.54.220.971 I slot print_timing: id 2 | task 2994 | total time = 11428.67 ms / 296 tokens 4.54.220.972 I slot print_timing: id 2 | task 2994 | graphs reused = 2555 4.54.220.972 I slot print_timing: id 2 | task 2994 | graph reallocs = 0 / 0 (same size) / (changed size) 4.54.221.024 I slot release: id 2 | task 2994 | stop processing: n_tokens = 1410, truncated = 0 4.54.289.005 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.791 4.54.289.034 I slot launch_slot_: id 2 | task 3219 | processing task, is_child = 0 4.55.878.244 I slot print_timing: id 0 | task 3084 | n_gen = 157, tg = 19.33 t/s, tg_3s = 18.93 t/s 4.56.242.311 I slot print_timing: id 3 | task 3150 | n_gen = 100, tg = 18.84 t/s, tg_3s = 19.03 t/s 4.56.914.448 I slot print_timing: id 1 | task 3184 | prompt eval time = 408.99 ms / 77 tokens ( 5.31 ms per token, 188.27 tokens per second) 4.56.914.456 I slot print_timing: id 1 | task 3184 | eval time = 4094.38 ms / 82 tokens ( 50.55 ms per token, 19.78 tokens per second) 4.56.914.457 I slot print_timing: id 1 | task 3184 | total time = 4503.37 ms / 159 tokens 4.56.914.459 I slot print_timing: id 1 | task 3184 | graphs reused = 2601 4.56.914.459 I slot print_timing: id 1 | task 3184 | graph reallocs = 0 / 0 (same size) / (changed size) 4.56.914.543 I slot release: id 1 | task 3184 | stop processing: n_tokens = 1273, truncated = 0 4.56.984.191 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.876 4.56.984.216 I slot launch_slot_: id 1 | task 3270 | processing task, is_child = 0 4.58.103.303 I slot print_timing: id 3 | task 3150 | prompt eval time = 338.76 ms / 80 tokens ( 4.23 ms per token, 236.15 tokens per second) 4.58.103.307 I slot print_timing: id 3 | task 3150 | eval time = 7115.64 ms / 135 tokens ( 53.10 ms per token, 18.83 tokens per second) 4.58.103.308 I slot print_timing: id 3 | task 3150 | total time = 7454.40 ms / 215 tokens 4.58.103.308 I slot print_timing: id 3 | task 3150 | graphs reused = 2617 4.58.103.309 I slot print_timing: id 3 | task 3150 | graph reallocs = 0 / 0 (same size) / (changed size) 4.58.103.366 I slot release: id 3 | task 3150 | stop processing: n_tokens = 1332, truncated = 0 4.58.147.064 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.951 (> 0.100 thold), f_keep = 0.837 4.58.147.095 I slot launch_slot_: id 3 | task 3291 | processing task, is_child = 0 4.58.920.547 I slot print_timing: id 0 | task 3084 | n_gen = 214, tg = 19.17 t/s, tg_3s = 18.74 t/s 4.59.732.459 I slot print_timing: id 2 | task 3219 | n_gen = 100, tg = 20.06 t/s, tg_3s = 20.27 t/s 5.00.044.160 I slot print_timing: id 0 | task 3084 | prompt eval time = 332.93 ms / 100 tokens ( 3.33 ms per token, 300.37 tokens per second) 5.00.044.172 I slot print_timing: id 0 | task 3084 | eval time = 12236.01 ms / 239 tokens ( 51.41 ms per token, 19.45 tokens per second) 5.00.044.173 I slot print_timing: id 0 | task 3084 | total time = 12568.93 ms / 339 tokens 5.00.044.173 I slot print_timing: id 0 | task 3084 | graphs reused = 2652 5.00.044.174 I slot print_timing: id 0 | task 3084 | graph reallocs = 0 / 0 (same size) / (changed size) 5.00.044.231 I slot release: id 0 | task 3084 | stop processing: n_tokens = 1453, truncated = 0 5.00.092.227 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.767 5.00.092.253 I slot launch_slot_: id 0 | task 3331 | processing task, is_child = 0 5.00.580.899 I slot print_timing: id 2 | task 3219 | prompt eval time = 509.20 ms / 146 tokens ( 3.49 ms per token, 286.72 tokens per second) 5.00.580.908 I slot print_timing: id 2 | task 3219 | eval time = 5782.66 ms / 113 tokens ( 51.63 ms per token, 19.37 tokens per second) 5.00.580.908 I slot print_timing: id 2 | task 3219 | total time = 6291.86 ms / 259 tokens 5.00.580.909 I slot print_timing: id 2 | task 3219 | graphs reused = 2655 5.00.580.910 I slot print_timing: id 2 | task 3219 | graph reallocs = 0 / 0 (same size) / (changed size) 5.00.580.973 I slot release: id 2 | task 3219 | stop processing: n_tokens = 1373, truncated = 0 5.00.649.505 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.812 5.00.649.530 I slot launch_slot_: id 2 | task 3338 | processing task, is_child = 0 5.02.570.875 I slot print_timing: id 1 | task 3270 | n_gen = 100, tg = 18.88 t/s, tg_3s = 19.07 t/s 5.02.705.295 I slot print_timing: id 1 | task 3270 | prompt eval time = 342.27 ms / 67 tokens ( 5.11 ms per token, 195.75 tokens per second) 5.02.705.302 I slot print_timing: id 1 | task 3270 | eval time = 5378.80 ms / 103 tokens ( 52.73 ms per token, 18.96 tokens per second) 5.02.705.302 I slot print_timing: id 1 | task 3270 | total time = 5721.07 ms / 170 tokens 5.02.705.303 I slot print_timing: id 1 | task 3270 | graphs reused = 2690 5.02.705.303 I slot print_timing: id 1 | task 3270 | graph reallocs = 0 / 0 (same size) / (changed size) 5.02.705.357 I slot release: id 1 | task 3270 | stop processing: n_tokens = 1284, truncated = 0 5.02.774.824 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.868 5.02.774.852 I slot launch_slot_: id 1 | task 3379 | processing task, is_child = 0 5.03.178.270 I slot print_timing: id 3 | task 3291 | prompt eval time = 276.09 ms / 57 tokens ( 4.84 ms per token, 206.46 tokens per second) 5.03.178.274 I slot print_timing: id 3 | task 3291 | eval time = 4755.08 ms / 86 tokens ( 55.94 ms per token, 17.88 tokens per second) 5.03.178.284 I slot print_timing: id 3 | task 3291 | total time = 5031.16 ms / 143 tokens 5.03.178.286 I slot print_timing: id 3 | task 3291 | graphs reused = 2690 5.03.178.286 I slot print_timing: id 3 | task 3291 | graph reallocs = 0 / 0 (same size) / (changed size) 5.03.178.327 I slot release: id 3 | task 3291 | stop processing: n_tokens = 1257, truncated = 0 5.03.220.173 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.887 5.03.220.194 I slot launch_slot_: id 3 | task 3383 | processing task, is_child = 0 5.05.393.991 I slot print_timing: id 0 | task 3331 | prompt eval time = 341.71 ms / 89 tokens ( 3.84 ms per token, 260.46 tokens per second) 5.05.393.998 I slot print_timing: id 0 | task 3331 | eval time = 4960.02 ms / 91 tokens ( 55.11 ms per token, 18.15 tokens per second) 5.05.393.998 I slot print_timing: id 0 | task 3331 | total time = 5301.73 ms / 180 tokens 5.05.393.999 I slot print_timing: id 0 | task 3331 | graphs reused = 2729 5.05.393.999 I slot print_timing: id 0 | task 3331 | graph reallocs = 0 / 0 (same size) / (changed size) 5.05.394.056 I slot release: id 0 | task 3331 | stop processing: n_tokens = 1294, truncated = 0 5.05.442.176 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.862 5.05.442.201 I slot launch_slot_: id 0 | task 3428 | processing task, is_child = 0 5.06.275.407 I slot print_timing: id 2 | task 3338 | prompt eval time = 390.79 ms / 71 tokens ( 5.50 ms per token, 181.68 tokens per second) 5.06.275.414 I slot print_timing: id 2 | task 3338 | eval time = 5235.08 ms / 99 tokens ( 53.42 ms per token, 18.72 tokens per second) 5.06.275.415 I slot print_timing: id 2 | task 3338 | total time = 5625.87 ms / 170 tokens 5.06.275.416 I slot print_timing: id 2 | task 3338 | graphs reused = 2739 5.06.275.416 I slot print_timing: id 2 | task 3338 | graph reallocs = 0 / 0 (same size) / (changed size) 5.06.275.474 I slot release: id 2 | task 3338 | stop processing: n_tokens = 1284, truncated = 0 5.06.343.410 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.868 5.06.343.437 I slot launch_slot_: id 2 | task 3443 | processing task, is_child = 0 5.08.435.769 I slot print_timing: id 1 | task 3379 | n_gen = 100, tg = 18.82 t/s, tg_3s = 19.01 t/s 5.08.574.144 I slot print_timing: id 3 | task 3383 | n_gen = 100, tg = 19.72 t/s, tg_3s = 19.92 t/s 5.10.543.804 I slot print_timing: id 0 | task 3428 | n_gen = 100, tg = 20.76 t/s, tg_3s = 20.97 t/s 5.11.175.613 I slot print_timing: id 2 | task 3443 | n_gen = 100, tg = 22.25 t/s, tg_3s = 22.47 t/s 5.11.222.115 I slot print_timing: id 3 | task 3383 | prompt eval time = 333.90 ms / 72 tokens ( 4.64 ms per token, 215.63 tokens per second) 5.11.222.122 I slot print_timing: id 3 | task 3383 | eval time = 7668.01 ms / 159 tokens ( 48.53 ms per token, 20.61 tokens per second) 5.11.222.122 I slot print_timing: id 3 | task 3383 | total time = 8001.91 ms / 231 tokens 5.11.222.123 I slot print_timing: id 3 | task 3383 | graphs reused = 2837 5.11.222.123 I slot print_timing: id 3 | task 3383 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.222.176 I slot release: id 3 | task 3383 | stop processing: n_tokens = 1345, truncated = 0 5.11.265.485 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.829 5.11.265.508 I slot launch_slot_: id 3 | task 3547 | processing task, is_child = 0 5.11.575.021 I slot print_timing: id 1 | task 3379 | n_gen = 164, tg = 19.41 t/s, tg_3s = 20.39 t/s 5.12.470.288 I slot print_timing: id 1 | task 3379 | prompt eval time = 401.27 ms / 84 tokens ( 4.78 ms per token, 209.33 tokens per second) 5.12.470.295 I slot print_timing: id 1 | task 3379 | eval time = 9294.16 ms / 183 tokens ( 51.07 ms per token, 19.58 tokens per second) 5.12.470.296 I slot print_timing: id 1 | task 3379 | total time = 9695.43 ms / 267 tokens 5.12.470.297 I slot print_timing: id 1 | task 3379 | graphs reused = 2854 5.12.470.297 I slot print_timing: id 1 | task 3379 | graph reallocs = 0 / 0 (same size) / (changed size) 5.12.470.350 I slot release: id 1 | task 3379 | stop processing: n_tokens = 1381, truncated = 0 5.12.539.914 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.807 5.12.539.942 I slot launch_slot_: id 1 | task 3569 | processing task, is_child = 0 5.13.573.680 I slot print_timing: id 0 | task 3428 | n_gen = 153, tg = 19.49 t/s, tg_3s = 17.49 t/s 5.13.753.441 I slot print_timing: id 0 | task 3428 | prompt eval time = 332.57 ms / 88 tokens ( 3.78 ms per token, 264.61 tokens per second) 5.13.753.448 I slot print_timing: id 0 | task 3428 | eval time = 7978.66 ms / 157 tokens ( 51.15 ms per token, 19.55 tokens per second) 5.13.753.448 I slot print_timing: id 0 | task 3428 | total time = 8311.23 ms / 245 tokens 5.13.753.449 I slot print_timing: id 0 | task 3428 | graphs reused = 2871 5.13.753.449 I slot print_timing: id 0 | task 3428 | graph reallocs = 0 / 0 (same size) / (changed size) 5.13.753.503 I slot release: id 0 | task 3428 | stop processing: n_tokens = 1359, truncated = 0 5.13.801.775 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.820 5.13.801.801 I slot launch_slot_: id 0 | task 3591 | processing task, is_child = 0 5.14.177.218 I slot print_timing: id 2 | task 3443 | n_gen = 147, tg = 19.59 t/s, tg_3s = 15.66 t/s 5.14.541.502 I slot print_timing: id 2 | task 3443 | prompt eval time = 382.77 ms / 94 tokens ( 4.07 ms per token, 245.58 tokens per second) 5.14.541.509 I slot print_timing: id 2 | task 3443 | eval time = 7815.29 ms / 155 tokens ( 50.75 ms per token, 19.70 tokens per second) 5.14.541.510 I slot print_timing: id 2 | task 3443 | total time = 8198.06 ms / 249 tokens 5.14.541.510 I slot print_timing: id 2 | task 3443 | graphs reused = 2880 5.14.541.511 I slot print_timing: id 2 | task 3443 | graph reallocs = 0 / 0 (same size) / (changed size) 5.14.541.563 I slot release: id 2 | task 3443 | stop processing: n_tokens = 1363, truncated = 0 5.14.609.441 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.818 5.14.609.464 I slot launch_slot_: id 2 | task 3604 | processing task, is_child = 0 5.17.022.735 I slot print_timing: id 3 | task 3547 | n_gen = 100, tg = 18.46 t/s, tg_3s = 18.64 t/s 5.17.961.577 I slot print_timing: id 1 | task 3569 | n_gen = 100, tg = 19.73 t/s, tg_3s = 19.93 t/s 5.18.903.079 I slot print_timing: id 0 | task 3591 | n_gen = 100, tg = 20.75 t/s, tg_3s = 20.96 t/s 5.19.446.457 I slot print_timing: id 2 | task 3604 | n_gen = 100, tg = 22.26 t/s, tg_3s = 22.48 t/s 5.20.032.193 I slot print_timing: id 3 | task 3547 | n_gen = 167, tg = 19.83 t/s, tg_3s = 22.26 t/s 5.20.971.882 I slot print_timing: id 1 | task 3569 | n_gen = 167, tg = 20.68 t/s, tg_3s = 22.26 t/s 5.21.690.347 I slot print_timing: id 0 | task 3591 | prompt eval time = 329.52 ms / 84 tokens ( 3.92 ms per token, 254.91 tokens per second) 5.21.690.354 I slot print_timing: id 0 | task 3591 | eval time = 7559.01 ms / 162 tokens ( 46.95 ms per token, 21.30 tokens per second) 5.21.690.354 I slot print_timing: id 0 | task 3591 | total time = 7888.54 ms / 246 tokens 5.21.690.355 I slot print_timing: id 0 | task 3591 | graphs reused = 3028 5.21.690.356 I slot print_timing: id 0 | task 3591 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.690.408 I slot release: id 0 | task 3591 | stop processing: n_tokens = 1360, truncated = 0 5.21.738.712 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.820 5.21.738.737 I slot launch_slot_: id 0 | task 3757 | processing task, is_child = 0 5.22.479.550 I slot print_timing: id 2 | task 3604 | n_gen = 162, tg = 21.52 t/s, tg_3s = 20.44 t/s 5.23.065.930 I slot print_timing: id 3 | task 3547 | n_gen = 229, tg = 19.99 t/s, tg_3s = 20.44 t/s 5.23.695.871 I slot print_timing: id 3 | task 3547 | prompt eval time = 393.61 ms / 111 tokens ( 3.55 ms per token, 282.01 tokens per second) 5.23.695.876 I slot print_timing: id 3 | task 3547 | eval time = 12036.75 ms / 243 tokens ( 49.74 ms per token, 20.11 tokens per second) 5.23.695.876 I slot print_timing: id 3 | task 3547 | total time = 12430.35 ms / 354 tokens 5.23.695.877 I slot print_timing: id 3 | task 3547 | graphs reused = 3064 5.23.695.877 I slot print_timing: id 3 | task 3547 | graph reallocs = 0 / 0 (same size) / (changed size) 5.23.695.933 I slot release: id 3 | task 3547 | stop processing: n_tokens = 1468, truncated = 0 5.23.739.341 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.760 5.23.739.367 I slot launch_slot_: id 3 | task 3797 | processing task, is_child = 0 5.23.995.900 I slot print_timing: id 1 | task 3569 | n_gen = 224, tg = 20.18 t/s, tg_3s = 18.85 t/s 5.25.296.882 I slot print_timing: id 1 | task 3569 | prompt eval time = 403.34 ms / 88 tokens ( 4.58 ms per token, 218.18 tokens per second) 5.25.296.888 I slot print_timing: id 1 | task 3569 | eval time = 12353.59 ms / 252 tokens ( 49.22 ms per token, 20.32 tokens per second) 5.25.296.889 I slot print_timing: id 1 | task 3569 | total time = 12756.93 ms / 340 tokens 5.25.296.889 I slot print_timing: id 1 | task 3569 | graphs reused = 3090 5.25.296.890 I slot print_timing: id 1 | task 3569 | graph reallocs = 0 / 0 (same size) / (changed size) 5.25.296.943 I slot release: id 1 | task 3569 | stop processing: n_tokens = 1454, truncated = 0 5.25.366.383 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.767 5.25.366.408 I slot launch_slot_: id 1 | task 3828 | processing task, is_child = 0 5.25.768.518 I slot print_timing: id 2 | task 3604 | n_gen = 221, tg = 20.43 t/s, tg_3s = 17.94 t/s 5.26.697.972 I slot print_timing: id 2 | task 3604 | prompt eval time = 389.06 ms / 74 tokens ( 5.26 ms per token, 190.20 tokens per second) 5.26.697.978 I slot print_timing: id 2 | task 3604 | eval time = 11699.44 ms / 240 tokens ( 48.95 ms per token, 20.43 tokens per second) 5.26.697.979 I slot print_timing: id 2 | task 3604 | total time = 12088.50 ms / 314 tokens 5.26.697.980 I slot print_timing: id 2 | task 3604 | graphs reused = 3107 5.26.697.980 I slot print_timing: id 2 | task 3604 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.698.041 I slot release: id 2 | task 3604 | stop processing: n_tokens = 1428, truncated = 0 5.26.765.522 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.781 5.26.765.545 I slot launch_slot_: id 2 | task 3850 | processing task, is_child = 0 5.27.567.165 I slot print_timing: id 0 | task 3757 | n_gen = 100, tg = 18.01 t/s, tg_3s = 18.19 t/s 5.28.913.317 I slot print_timing: id 0 | task 3757 | prompt eval time = 330.19 ms / 73 tokens ( 4.52 ms per token, 221.09 tokens per second) 5.28.913.321 I slot print_timing: id 0 | task 3757 | eval time = 6844.39 ms / 130 tokens ( 53.06 ms per token, 18.85 tokens per second) 5.28.913.321 I slot print_timing: id 0 | task 3757 | total time = 7174.57 ms / 203 tokens 5.28.913.322 I slot print_timing: id 0 | task 3757 | graphs reused = 3144 5.28.913.323 I slot print_timing: id 0 | task 3757 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.913.393 I slot release: id 0 | task 3757 | stop processing: n_tokens = 1317, truncated = 0 5.28.961.610 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.847 5.28.961.635 I slot launch_slot_: id 0 | task 3893 | processing task, is_child = 0 5.29.568.544 I slot print_timing: id 3 | task 3797 | n_gen = 100, tg = 18.04 t/s, tg_3s = 18.22 t/s 5.30.913.883 I slot print_timing: id 1 | task 3828 | n_gen = 100, tg = 19.68 t/s, tg_3s = 19.88 t/s 5.31.859.430 I slot print_timing: id 2 | task 3850 | n_gen = 100, tg = 21.07 t/s, tg_3s = 21.28 t/s 5.32.580.706 I slot print_timing: id 3 | task 3797 | n_gen = 167, tg = 19.53 t/s, tg_3s = 22.24 t/s 5.33.744.845 I slot print_timing: id 0 | task 3893 | n_gen = 100, tg = 22.23 t/s, tg_3s = 22.46 t/s 5.33.925.812 I slot print_timing: id 1 | task 3828 | n_gen = 167, tg = 20.64 t/s, tg_3s = 22.24 t/s 5.33.972.429 I slot print_timing: id 2 | task 3850 | prompt eval time = 394.94 ms / 92 tokens ( 4.29 ms per token, 232.95 tokens per second) 5.33.972.433 I slot print_timing: id 2 | task 3850 | eval time = 6811.94 ms / 147 tokens ( 46.66 ms per token, 21.43 tokens per second) 5.33.972.433 I slot print_timing: id 2 | task 3850 | total time = 7206.88 ms / 239 tokens 5.33.972.434 I slot print_timing: id 2 | task 3850 | graphs reused = 3248 5.33.972.435 I slot print_timing: id 2 | task 3850 | graph reallocs = 0 / 0 (same size) / (changed size) 5.33.972.492 I slot release: id 2 | task 3850 | stop processing: n_tokens = 1353, truncated = 0 5.34.040.553 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.824 5.34.040.575 I slot launch_slot_: id 2 | task 4001 | processing task, is_child = 0 5.34.875.961 I slot print_timing: id 0 | task 3893 | prompt eval time = 330.17 ms / 79 tokens ( 4.18 ms per token, 239.27 tokens per second) 5.34.875.967 I slot print_timing: id 0 | task 3893 | eval time = 5584.15 ms / 118 tokens ( 47.73 ms per token, 20.95 tokens per second) 5.34.875.968 I slot print_timing: id 0 | task 3893 | total time = 5914.32 ms / 197 tokens 5.34.875.969 I slot print_timing: id 0 | task 3893 | graphs reused = 3257 5.34.875.969 I slot print_timing: id 0 | task 3893 | graph reallocs = 0 / 0 (same size) / (changed size) 5.34.876.023 I slot release: id 0 | task 3893 | stop processing: n_tokens = 1311, truncated = 0 5.34.924.251 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.850 5.34.924.276 I slot launch_slot_: id 0 | task 4015 | processing task, is_child = 0 5.35.603.252 I slot print_timing: id 3 | task 3797 | n_gen = 220, tg = 19.01 t/s, tg_3s = 17.53 t/s 5.36.232.479 I slot print_timing: id 3 | task 3797 | prompt eval time = 341.14 ms / 97 tokens ( 3.52 ms per token, 284.34 tokens per second) 5.36.232.486 I slot print_timing: id 3 | task 3797 | eval time = 12151.97 ms / 234 tokens ( 52.15 ms per token, 19.17 tokens per second) 5.36.232.487 I slot print_timing: id 3 | task 3797 | total time = 12493.10 ms / 331 tokens 5.36.232.488 I slot print_timing: id 3 | task 3797 | graphs reused = 3277 5.36.232.488 I slot print_timing: id 3 | task 3797 | graph reallocs = 0 / 0 (same size) / (changed size) 5.36.232.555 I slot release: id 3 | task 3797 | stop processing: n_tokens = 1445, truncated = 0 5.36.276.116 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.772 5.36.276.137 I slot launch_slot_: id 3 | task 4039 | processing task, is_child = 0 5.36.969.123 I slot print_timing: id 1 | task 3828 | n_gen = 215, tg = 19.30 t/s, tg_3s = 15.77 t/s 5.39.441.209 I slot print_timing: id 2 | task 4001 | n_gen = 100, tg = 19.73 t/s, tg_3s = 19.93 t/s 5.39.980.216 I slot print_timing: id 1 | task 3828 | n_gen = 282, tg = 19.93 t/s, tg_3s = 22.25 t/s 5.40.023.508 I slot print_timing: id 0 | task 4015 | n_gen = 100, tg = 21.04 t/s, tg_3s = 21.26 t/s 5.41.062.512 I slot print_timing: id 3 | task 4039 | n_gen = 100, tg = 22.26 t/s, tg_3s = 22.48 t/s 5.42.368.506 I slot print_timing: id 3 | task 4039 | prompt eval time = 338.24 ms / 88 tokens ( 3.84 ms per token, 260.17 tokens per second) 5.42.368.513 I slot print_timing: id 3 | task 4039 | eval time = 5754.12 ms / 129 tokens ( 44.95 ms per token, 22.24 tokens per second) 5.42.368.513 I slot print_timing: id 3 | task 4039 | total time = 6092.36 ms / 217 tokens 5.42.368.514 I slot print_timing: id 3 | task 4039 | graphs reused = 3403 5.42.368.515 I slot print_timing: id 3 | task 4039 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.368.568 I slot release: id 3 | task 4039 | stop processing: n_tokens = 1331, truncated = 0 5.42.411.974 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.838 5.42.411.999 I slot launch_slot_: id 3 | task 4171 | processing task, is_child = 0 5.42.668.160 I slot print_timing: id 2 | task 4001 | n_gen = 167, tg = 20.13 t/s, tg_3s = 20.76 t/s 5.42.929.357 I slot print_timing: id 2 | task 4001 | prompt eval time = 382.14 ms / 83 tokens ( 4.60 ms per token, 217.20 tokens per second) 5.42.929.366 I slot print_timing: id 2 | task 4001 | eval time = 8506.64 ms / 172 tokens ( 49.75 ms per token, 20.10 tokens per second) 5.42.929.367 I slot print_timing: id 2 | task 4001 | total time = 8888.77 ms / 255 tokens 5.42.929.368 I slot print_timing: id 2 | task 4001 | graphs reused = 3406 5.42.929.369 I slot print_timing: id 2 | task 4001 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.929.440 I slot release: id 2 | task 4001 | stop processing: n_tokens = 1369, truncated = 0 5.42.998.174 I slot print_timing: id 1 | task 3828 | n_gen = 343, tg = 19.98 t/s, tg_3s = 20.21 t/s 5.43.000.231 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.814 5.43.000.256 I slot launch_slot_: id 2 | task 4179 | processing task, is_child = 0 5.43.278.552 I slot print_timing: id 0 | task 4015 | n_gen = 161, tg = 20.10 t/s, tg_3s = 18.74 t/s 5.45.420.806 I slot print_timing: id 1 | task 3828 | prompt eval time = 517.17 ms / 142 tokens ( 3.64 ms per token, 274.57 tokens per second) 5.45.420.809 I slot print_timing: id 1 | task 3828 | eval time = 19537.22 ms / 390 tokens ( 50.22 ms per token, 19.91 tokens per second) 5.45.420.810 I slot print_timing: id 1 | task 3828 | total time = 20054.39 ms / 532 tokens 5.45.420.810 I slot print_timing: id 1 | task 3828 | graphs reused = 3450 5.45.420.811 I slot print_timing: id 1 | task 3828 | graph reallocs = 0 / 0 (same size) / (changed size) 5.45.420.867 I slot release: id 1 | task 3828 | stop processing: n_tokens = 1646, truncated = 0 5.45.490.378 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.677 5.45.490.406 I slot launch_slot_: id 1 | task 4228 | processing task, is_child = 0 5.46.304.741 I slot print_timing: id 0 | task 4015 | n_gen = 219, tg = 19.84 t/s, tg_3s = 19.17 t/s 5.47.884.430 I slot print_timing: id 3 | task 4171 | n_gen = 100, tg = 19.29 t/s, tg_3s = 19.48 t/s 5.48.198.124 I slot print_timing: id 2 | task 4179 | n_gen = 100, tg = 20.57 t/s, tg_3s = 20.78 t/s 5.48.334.962 I slot print_timing: id 3 | task 4171 | prompt eval time = 339.46 ms / 91 tokens ( 3.73 ms per token, 268.08 tokens per second) 5.48.334.968 I slot print_timing: id 3 | task 4171 | eval time = 5583.50 ms / 110 tokens ( 51.22 ms per token, 19.52 tokens per second) 5.48.334.970 I slot print_timing: id 3 | task 4171 | total time = 5922.95 ms / 201 tokens 5.48.334.971 I slot print_timing: id 3 | task 4171 | graphs reused = 3503 5.48.334.971 I slot print_timing: id 3 | task 4171 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.335.026 I slot release: id 3 | task 4171 | stop processing: n_tokens = 1315, truncated = 0 5.48.378.401 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.848 5.48.378.423 I slot launch_slot_: id 3 | task 4286 | processing task, is_child = 0 5.49.344.281 I slot print_timing: id 0 | task 4015 | n_gen = 281, tg = 19.96 t/s, tg_3s = 20.40 t/s 5.49.929.934 I slot print_timing: id 0 | task 4015 | prompt eval time = 394.97 ms / 108 tokens ( 3.66 ms per token, 273.44 tokens per second) 5.49.929.938 I slot print_timing: id 0 | task 4015 | eval time = 14610.68 ms / 294 tokens ( 49.87 ms per token, 20.05 tokens per second) 5.49.929.939 I slot print_timing: id 0 | task 4015 | total time = 15005.65 ms / 402 tokens 5.49.929.940 I slot print_timing: id 0 | task 4015 | graphs reused = 3529 5.49.929.940 I slot print_timing: id 0 | task 4015 | graph reallocs = 0 / 0 (same size) / (changed size) 5.49.930.001 I slot release: id 0 | task 4015 | stop processing: n_tokens = 1516, truncated = 0 5.49.978.340 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.735 5.49.978.365 I slot launch_slot_: id 0 | task 4317 | processing task, is_child = 0 5.50.863.321 I slot print_timing: id 1 | task 4228 | n_gen = 100, tg = 19.92 t/s, tg_3s = 20.13 t/s 5.51.223.206 I slot print_timing: id 2 | task 4179 | n_gen = 156, tg = 19.78 t/s, tg_3s = 18.51 t/s 5.53.425.655 I slot print_timing: id 3 | task 4286 | n_gen = 100, tg = 21.02 t/s, tg_3s = 21.23 t/s 5.53.872.044 I slot print_timing: id 1 | task 4228 | n_gen = 167, tg = 20.81 t/s, tg_3s = 22.27 t/s 5.54.006.737 I slot print_timing: id 1 | task 4228 | prompt eval time = 404.04 ms / 98 tokens ( 4.12 ms per token, 242.55 tokens per second) 5.54.006.744 I slot print_timing: id 1 | task 4228 | eval time = 8112.28 ms / 170 tokens ( 48.00 ms per token, 20.83 tokens per second) 5.54.006.746 I slot print_timing: id 1 | task 4228 | total time = 8516.33 ms / 268 tokens 5.54.006.746 I slot print_timing: id 1 | task 4228 | graphs reused = 3611 5.54.006.747 I slot print_timing: id 1 | task 4228 | graph reallocs = 0 / 0 (same size) / (changed size) 5.54.006.802 I slot release: id 1 | task 4228 | stop processing: n_tokens = 1381, truncated = 0 5.54.009.982 I slot print_timing: id 3 | task 4286 | prompt eval time = 337.04 ms / 78 tokens ( 4.32 ms per token, 231.43 tokens per second) 5.54.009.989 I slot print_timing: id 3 | task 4286 | eval time = 5294.51 ms / 113 tokens ( 47.27 ms per token, 21.15 tokens per second) 5.54.009.989 I slot print_timing: id 3 | task 4286 | total time = 5631.55 ms / 191 tokens 5.54.009.990 I slot print_timing: id 3 | task 4286 | graphs reused = 3611 5.54.009.990 I slot print_timing: id 3 | task 4286 | graph reallocs = 0 / 0 (same size) / (changed size) 5.54.010.035 I slot release: id 3 | task 4286 | stop processing: n_tokens = 1305, truncated = 0 5.54.061.791 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.807 5.54.061.814 I slot launch_slot_: id 1 | task 4403 | processing task, is_child = 0 5.54.091.927 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.854 5.54.091.951 I slot launch_slot_: id 3 | task 4404 | processing task, is_child = 0 5.54.586.654 I slot print_timing: id 2 | task 4179 | n_gen = 220, tg = 19.55 t/s, tg_3s = 19.03 t/s 5.55.375.290 I slot print_timing: id 0 | task 4317 | n_gen = 100, tg = 19.57 t/s, tg_3s = 19.77 t/s 5.55.692.676 I slot print_timing: id 2 | task 4179 | prompt eval time = 385.09 ms / 95 tokens ( 4.05 ms per token, 246.70 tokens per second) 5.55.692.683 I slot print_timing: id 2 | task 4179 | eval time = 12307.32 ms / 242 tokens ( 51.07 ms per token, 19.58 tokens per second) 5.55.692.683 I slot print_timing: id 2 | task 4179 | total time = 12692.41 ms / 337 tokens 5.55.692.684 I slot print_timing: id 2 | task 4179 | graphs reused = 3631 5.55.692.684 I slot print_timing: id 2 | task 4179 | graph reallocs = 0 / 0 (same size) / (changed size) 5.55.692.741 I slot release: id 2 | task 4179 | stop processing: n_tokens = 1451, truncated = 0 5.55.760.649 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.768 5.55.760.677 I slot launch_slot_: id 2 | task 4429 | processing task, is_child = 0 5.56.511.320 I slot print_timing: id 0 | task 4317 | prompt eval time = 338.49 ms / 95 tokens ( 3.56 ms per token, 280.66 tokens per second) 5.56.511.324 I slot print_timing: id 0 | task 4317 | eval time = 6194.46 ms / 118 tokens ( 52.94 ms per token, 18.89 tokens per second) 5.56.511.324 I slot print_timing: id 0 | task 4317 | total time = 6532.95 ms / 213 tokens 5.56.511.325 I slot print_timing: id 0 | task 4317 | graphs reused = 3638 5.56.511.325 I slot print_timing: id 0 | task 4317 | graph reallocs = 0 / 0 (same size) / (changed size) 5.56.511.389 I slot release: id 0 | task 4317 | stop processing: n_tokens = 1327, truncated = 0 5.56.559.473 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.841 5.56.559.497 I slot launch_slot_: id 0 | task 4441 | processing task, is_child = 0 5.59.171.405 I slot print_timing: id 3 | task 4404 | prompt eval time = 652.22 ms / 74 tokens ( 8.81 ms per token, 113.46 tokens per second) 5.59.171.408 I slot print_timing: id 3 | task 4404 | eval time = 4425.35 ms / 84 tokens ( 53.32 ms per token, 18.76 tokens per second) 5.59.171.409 I slot print_timing: id 3 | task 4404 | total time = 5077.57 ms / 158 tokens 5.59.171.410 I slot print_timing: id 3 | task 4404 | graphs reused = 3685 5.59.171.410 I slot print_timing: id 3 | task 4404 | graph reallocs = 0 / 0 (same size) / (changed size) 5.59.171.466 I slot release: id 3 | task 4404 | stop processing: n_tokens = 1272, truncated = 0 5.59.215.067 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.877 5.59.215.090 I slot launch_slot_: id 3 | task 4493 | processing task, is_child = 0 6.00.139.720 I slot print_timing: id 1 | task 4403 | n_gen = 100, tg = 18.33 t/s, tg_3s = 18.52 t/s 6.01.040.123 I slot print_timing: id 2 | task 4429 | prompt eval time = 389.93 ms / 75 tokens ( 5.20 ms per token, 192.34 tokens per second) 6.01.040.130 I slot print_timing: id 2 | task 4429 | eval time = 4889.51 ms / 96 tokens ( 51.47 ms per token, 19.43 tokens per second) 6.01.040.130 I slot print_timing: id 2 | task 4429 | total time = 5279.44 ms / 171 tokens 6.01.040.131 I slot print_timing: id 2 | task 4429 | graphs reused = 3717 6.01.040.132 I slot print_timing: id 2 | task 4429 | graph reallocs = 0 / 0 (same size) / (changed size) 6.01.040.189 I slot release: id 2 | task 4429 | stop processing: n_tokens = 1285, truncated = 0 6.01.108.260 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.868 6.01.108.289 I slot launch_slot_: id 2 | task 4530 | processing task, is_child = 0 6.02.034.271 I slot print_timing: id 0 | task 4441 | n_gen = 100, tg = 19.71 t/s, tg_3s = 19.91 t/s 6.02.574.396 I slot print_timing: id 1 | task 4403 | prompt eval time = 648.12 ms / 89 tokens ( 7.28 ms per token, 137.32 tokens per second) 6.02.574.403 I slot print_timing: id 1 | task 4403 | eval time = 7834.32 ms / 147 tokens ( 53.66 ms per token, 18.64 tokens per second) 6.02.574.403 I slot print_timing: id 1 | task 4403 | total time = 8482.44 ms / 236 tokens 6.02.574.404 I slot print_timing: id 1 | task 4403 | graphs reused = 3740 6.02.574.405 I slot print_timing: id 1 | task 4403 | graph reallocs = 0 / 0 (same size) / (changed size) 6.02.574.459 I slot release: id 1 | task 4403 | stop processing: n_tokens = 1350, truncated = 0 6.02.643.958 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.826 6.02.643.984 I slot launch_slot_: id 1 | task 4558 | processing task, is_child = 0 6.04.671.664 I slot print_timing: id 3 | task 4493 | n_gen = 100, tg = 19.35 t/s, tg_3s = 19.55 t/s 6.05.071.763 I slot print_timing: id 0 | task 4441 | n_gen = 160, tg = 19.72 t/s, tg_3s = 19.75 t/s 6.06.290.271 I slot print_timing: id 2 | task 4530 | n_gen = 100, tg = 20.62 t/s, tg_3s = 20.83 t/s 6.07.504.603 I slot print_timing: id 1 | task 4558 | n_gen = 100, tg = 22.20 t/s, tg_3s = 22.42 t/s 6.07.688.089 I slot print_timing: id 3 | task 4493 | n_gen = 167, tg = 20.41 t/s, tg_3s = 22.21 t/s 6.08.088.725 I slot print_timing: id 0 | task 4441 | n_gen = 227, tg = 20.40 t/s, tg_3s = 22.21 t/s 6.08.496.331 I slot print_timing: id 1 | task 4558 | prompt eval time = 400.81 ms / 81 tokens ( 4.95 ms per token, 202.09 tokens per second) 6.08.496.339 I slot print_timing: id 1 | task 4558 | eval time = 5451.52 ms / 122 tokens ( 45.05 ms per token, 22.20 tokens per second) 6.08.496.339 I slot print_timing: id 1 | task 4558 | total time = 5852.34 ms / 203 tokens 6.08.496.340 I slot print_timing: id 1 | task 4558 | graphs reused = 3860 6.08.496.340 I slot print_timing: id 1 | task 4558 | graph reallocs = 0 / 0 (same size) / (changed size) 6.08.496.398 I slot release: id 1 | task 4558 | stop processing: n_tokens = 1316, truncated = 0 6.08.566.128 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.847 6.08.566.153 I slot launch_slot_: id 1 | task 4683 | processing task, is_child = 0 6.09.290.586 I slot print_timing: id 2 | task 4530 | n_gen = 159, tg = 20.26 t/s, tg_3s = 19.66 t/s 6.10.692.932 I slot print_timing: id 3 | task 4493 | n_gen = 226, tg = 20.20 t/s, tg_3s = 19.63 t/s 6.11.094.937 I slot print_timing: id 0 | task 4441 | n_gen = 286, tg = 20.24 t/s, tg_3s = 19.63 t/s 6.11.280.456 I slot print_timing: id 3 | task 4493 | prompt eval time = 341.08 ms / 95 tokens ( 3.59 ms per token, 278.53 tokens per second) 6.11.280.462 I slot print_timing: id 3 | task 4493 | eval time = 11724.28 ms / 239 tokens ( 49.26 ms per token, 20.30 tokens per second) 6.11.280.463 I slot print_timing: id 3 | task 4493 | total time = 12065.36 ms / 334 tokens 6.11.280.464 I slot print_timing: id 3 | task 4493 | graphs reused = 3909 6.11.280.464 I slot print_timing: id 3 | task 4493 | graph reallocs = 0 / 0 (same size) / (changed size) 6.11.280.522 I slot release: id 3 | task 4493 | stop processing: n_tokens = 1448, truncated = 0 6.11.324.123 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.770 6.11.324.149 I slot launch_slot_: id 3 | task 4738 | processing task, is_child = 0 6.11.516.858 I slot print_timing: id 0 | task 4441 | prompt eval time = 450.96 ms / 150 tokens ( 3.01 ms per token, 332.62 tokens per second) 6.11.516.863 I slot print_timing: id 0 | task 4441 | eval time = 14506.39 ms / 292 tokens ( 49.85 ms per token, 20.06 tokens per second) 6.11.516.864 I slot print_timing: id 0 | task 4441 | total time = 14957.35 ms / 442 tokens 6.11.516.865 I slot print_timing: id 0 | task 4441 | graphs reused = 3909 6.11.516.866 I slot print_timing: id 0 | task 4441 | graph reallocs = 0 / 0 (same size) / (changed size) 6.11.516.959 I slot release: id 0 | task 4441 | stop processing: n_tokens = 1557, truncated = 0 6.11.600.386 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.716 6.11.600.405 I slot launch_slot_: id 0 | task 4741 | processing task, is_child = 0 6.12.306.832 I slot print_timing: id 2 | task 4530 | n_gen = 215, tg = 19.78 t/s, tg_3s = 18.57 t/s 6.13.429.054 I slot print_timing: id 2 | task 4530 | prompt eval time = 381.86 ms / 92 tokens ( 4.15 ms per token, 240.92 tokens per second) 6.13.429.058 I slot print_timing: id 2 | task 4530 | eval time = 11938.89 ms / 240 tokens ( 49.95 ms per token, 20.02 tokens per second) 6.13.429.059 I slot print_timing: id 2 | task 4530 | total time = 12320.76 ms / 332 tokens 6.13.429.059 I slot print_timing: id 2 | task 4530 | graphs reused = 3940 6.13.429.060 I slot print_timing: id 2 | task 4530 | graph reallocs = 0 / 0 (same size) / (changed size) 6.13.429.116 I slot release: id 2 | task 4530 | stop processing: n_tokens = 1446, truncated = 0 6.13.496.948 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.771 6.13.496.970 I slot launch_slot_: id 2 | task 4777 | processing task, is_child = 0 6.14.194.207 I slot print_timing: id 1 | task 4683 | n_gen = 100, tg = 18.94 t/s, tg_3s = 19.13 t/s 6.16.081.767 I slot print_timing: id 1 | task 4683 | prompt eval time = 401.94 ms / 95 tokens ( 4.23 ms per token, 236.35 tokens per second) 6.16.081.773 I slot print_timing: id 1 | task 4683 | eval time = 7113.66 ms / 142 tokens ( 50.45 ms per token, 19.82 tokens per second) 6.16.081.774 I slot print_timing: id 1 | task 4683 | total time = 7515.60 ms / 237 tokens 6.16.081.774 I slot print_timing: id 1 | task 4683 | graphs reused = 3989 6.16.081.775 I slot print_timing: id 1 | task 4683 | graph reallocs = 0 / 0 (same size) / (changed size) 6.16.081.828 I slot release: id 1 | task 4683 | stop processing: n_tokens = 1351, truncated = 0 6.16.151.261 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.825 6.16.151.284 I slot launch_slot_: id 1 | task 4831 | processing task, is_child = 0 6.17.035.702 I slot print_timing: id 3 | task 4738 | n_gen = 100, tg = 18.21 t/s, tg_3s = 18.40 t/s 6.17.120.714 I slot print_timing: id 0 | task 4741 | n_gen = 100, tg = 19.28 t/s, tg_3s = 19.48 t/s 6.18.112.526 I slot print_timing: id 3 | task 4738 | prompt eval time = 276.23 ms / 63 tokens ( 4.38 ms per token, 228.07 tokens per second) 6.18.112.531 I slot print_timing: id 3 | task 4738 | eval time = 6512.14 ms / 124 tokens ( 52.94 ms per token, 18.89 tokens per second) 6.18.112.531 I slot print_timing: id 3 | task 4738 | total time = 6788.37 ms / 187 tokens 6.18.112.532 I slot print_timing: id 3 | task 4738 | graphs reused = 4021 6.18.112.532 I slot print_timing: id 3 | task 4738 | graph reallocs = 0 / 0 (same size) / (changed size) 6.18.112.583 I slot release: id 3 | task 4738 | stop processing: n_tokens = 1301, truncated = 0 6.18.156.085 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.857 6.18.156.114 I slot launch_slot_: id 3 | task 4868 | processing task, is_child = 0 6.18.537.577 I slot print_timing: id 2 | task 4777 | prompt eval time = 331.83 ms / 62 tokens ( 5.35 ms per token, 186.84 tokens per second) 6.18.537.581 I slot print_timing: id 2 | task 4777 | eval time = 4708.77 ms / 91 tokens ( 52.32 ms per token, 19.11 tokens per second) 6.18.537.581 I slot print_timing: id 2 | task 4777 | total time = 5040.60 ms / 153 tokens 6.18.537.582 I slot print_timing: id 2 | task 4777 | graphs reused = 4021 6.18.537.582 I slot print_timing: id 2 | task 4777 | graph reallocs = 0 / 0 (same size) / (changed size) 6.18.537.637 I slot release: id 2 | task 4777 | stop processing: n_tokens = 1267, truncated = 0 6.18.608.663 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.880 6.18.608.699 I slot launch_slot_: id 2 | task 4873 | processing task, is_child = 0 6.19.945.612 I slot print_timing: id 0 | task 4741 | prompt eval time = 386.11 ms / 105 tokens ( 3.68 ms per token, 271.95 tokens per second) 6.19.945.622 I slot print_timing: id 0 | task 4741 | eval time = 7959.09 ms / 150 tokens ( 53.42 ms per token, 18.72 tokens per second) 6.19.945.623 I slot print_timing: id 0 | task 4741 | total time = 8345.20 ms / 255 tokens 6.19.945.624 I slot print_timing: id 0 | task 4741 | graphs reused = 4041 6.19.945.624 I slot print_timing: id 0 | task 4741 | graph reallocs = 0 / 0 (same size) / (changed size) 6.19.945.682 I slot release: id 0 | task 4741 | stop processing: n_tokens = 1369, truncated = 0 6.19.993.798 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.814 6.19.993.821 I slot launch_slot_: id 0 | task 4898 | processing task, is_child = 0 6.21.961.658 I slot print_timing: id 1 | task 4831 | n_gen = 100, tg = 18.54 t/s, tg_3s = 18.73 t/s 6.23.586.886 I slot print_timing: id 3 | task 4868 | n_gen = 100, tg = 19.44 t/s, tg_3s = 19.64 t/s 6.23.767.517 I slot print_timing: id 2 | task 4873 | n_gen = 100, tg = 20.77 t/s, tg_3s = 20.98 t/s 6.24.845.027 I slot print_timing: id 0 | task 4898 | n_gen = 100, tg = 22.18 t/s, tg_3s = 22.40 t/s 6.24.981.390 I slot print_timing: id 1 | task 4831 | n_gen = 167, tg = 19.86 t/s, tg_3s = 22.19 t/s 6.26.285.936 I slot print_timing: id 1 | task 4831 | prompt eval time = 470.35 ms / 133 tokens ( 3.54 ms per token, 282.77 tokens per second) 6.26.285.943 I slot print_timing: id 1 | task 4831 | eval time = 9664.29 ms / 196 tokens ( 49.56 ms per token, 20.18 tokens per second) 6.26.285.943 I slot print_timing: id 1 | task 4831 | total time = 10134.64 ms / 329 tokens 6.26.285.944 I slot print_timing: id 1 | task 4831 | graphs reused = 4172 6.26.285.945 I slot print_timing: id 1 | task 4831 | graph reallocs = 0 / 0 (same size) / (changed size) 6.26.286.005 I slot release: id 1 | task 4831 | stop processing: n_tokens = 1443, truncated = 0 6.26.355.722 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.773 6.26.355.750 I slot launch_slot_: id 1 | task 5033 | processing task, is_child = 0 6.26.698.557 I slot print_timing: id 3 | task 4868 | n_gen = 163, tg = 19.75 t/s, tg_3s = 20.25 t/s 6.26.784.023 I slot print_timing: id 2 | task 4873 | n_gen = 161, tg = 20.56 t/s, tg_3s = 20.22 t/s 6.27.686.117 I slot print_timing: id 0 | task 4898 | prompt eval time = 387.71 ms / 110 tokens ( 3.52 ms per token, 283.72 tokens per second) 6.27.686.123 I slot print_timing: id 0 | task 4898 | eval time = 7304.58 ms / 157 tokens ( 46.82 ms per token, 21.36 tokens per second) 6.27.686.123 I slot print_timing: id 0 | task 4898 | total time = 7692.29 ms / 267 tokens 6.27.686.124 I slot print_timing: id 0 | task 4898 | graphs reused = 4193 6.27.686.124 I slot print_timing: id 0 | task 4898 | graph reallocs = 0 / 0 (same size) / (changed size) 6.27.686.196 I slot release: id 0 | task 4898 | stop processing: n_tokens = 1381, truncated = 0 6.27.734.565 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.807 6.27.734.593 I slot launch_slot_: id 0 | task 5059 | processing task, is_child = 0 6.28.569.087 I slot print_timing: id 3 | task 4868 | prompt eval time = 338.19 ms / 94 tokens ( 3.60 ms per token, 277.95 tokens per second) 6.28.569.091 I slot print_timing: id 3 | task 4868 | eval time = 10074.77 ms / 199 tokens ( 50.88 ms per token, 19.65 tokens per second) 6.28.569.092 I slot print_timing: id 3 | task 4868 | total time = 10412.97 ms / 293 tokens 6.28.569.092 I slot print_timing: id 3 | task 4868 | graphs reused = 4204 6.28.569.093 I slot print_timing: id 3 | task 4868 | graph reallocs = 0 / 0 (same size) / (changed size) 6.28.569.148 I slot release: id 3 | task 4868 | stop processing: n_tokens = 1407, truncated = 0 6.28.612.512 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.792 6.28.612.535 I slot launch_slot_: id 3 | task 5074 | processing task, is_child = 0 6.29.828.105 I slot print_timing: id 2 | task 4873 | n_gen = 216, tg = 19.86 t/s, tg_3s = 18.07 t/s 6.30.500.780 I slot print_timing: id 1 | task 5033 | prompt eval time = 340.67 ms / 68 tokens ( 5.01 ms per token, 199.60 tokens per second) 6.30.500.784 I slot print_timing: id 1 | task 5033 | eval time = 3804.35 ms / 73 tokens ( 52.84 ms per token, 18.93 tokens per second) 6.30.500.785 I slot print_timing: id 1 | task 5033 | total time = 4145.02 ms / 141 tokens 6.30.500.785 I slot print_timing: id 1 | task 5033 | graphs reused = 4236 6.30.500.786 I slot print_timing: id 1 | task 5033 | graph reallocs = 0 / 0 (same size) / (changed size) 6.30.500.850 I slot release: id 1 | task 5033 | stop processing: n_tokens = 1255, truncated = 0 6.30.570.479 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.888 6.30.570.511 I slot launch_slot_: id 1 | task 5111 | processing task, is_child = 0 6.32.376.350 I slot print_timing: id 2 | task 4873 | prompt eval time = 392.77 ms / 85 tokens ( 4.62 ms per token, 216.41 tokens per second) 6.32.376.355 I slot print_timing: id 2 | task 4873 | eval time = 13374.87 ms / 265 tokens ( 50.66 ms per token, 19.74 tokens per second) 6.32.376.355 I slot print_timing: id 2 | task 4873 | total time = 13767.64 ms / 350 tokens 6.32.376.356 I slot print_timing: id 2 | task 4873 | graphs reused = 4266 6.32.376.356 I slot print_timing: id 2 | task 4873 | graph reallocs = 0 / 0 (same size) / (changed size) 6.32.376.410 I slot release: id 2 | task 4873 | stop processing: n_tokens = 1464, truncated = 0 6.32.444.294 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.762 6.32.444.320 I slot launch_slot_: id 2 | task 5146 | processing task, is_child = 0 6.33.510.432 I slot print_timing: id 0 | task 5059 | n_gen = 100, tg = 18.19 t/s, tg_3s = 18.37 t/s 6.34.143.365 I slot print_timing: id 3 | task 5074 | n_gen = 100, tg = 19.30 t/s, tg_3s = 19.50 t/s 6.34.273.061 I slot print_timing: id 0 | task 5059 | prompt eval time = 332.05 ms / 100 tokens ( 3.32 ms per token, 301.16 tokens per second) 6.34.273.067 I slot print_timing: id 0 | task 5059 | eval time = 6206.41 ms / 117 tokens ( 53.50 ms per token, 18.69 tokens per second) 6.34.273.068 I slot print_timing: id 0 | task 5059 | total time = 6538.46 ms / 217 tokens 6.34.273.069 I slot print_timing: id 0 | task 5059 | graphs reused = 4297 6.34.273.069 I slot print_timing: id 0 | task 5059 | graph reallocs = 0 / 0 (same size) / (changed size) 6.34.273.124 I slot release: id 0 | task 5059 | stop processing: n_tokens = 1331, truncated = 0 6.34.321.605 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.838 6.34.321.629 I slot launch_slot_: id 0 | task 5182 | processing task, is_child = 0 6.36.019.378 I slot print_timing: id 1 | task 5111 | n_gen = 100, tg = 19.64 t/s, tg_3s = 19.84 t/s 6.37.148.417 I slot print_timing: id 3 | task 5074 | n_gen = 161, tg = 19.67 t/s, tg_3s = 20.30 t/s 6.37.552.512 I slot print_timing: id 2 | task 5146 | n_gen = 100, tg = 20.98 t/s, tg_3s = 21.20 t/s 6.38.855.237 I slot print_timing: id 2 | task 5146 | prompt eval time = 390.25 ms / 73 tokens ( 5.35 ms per token, 187.06 tokens per second) 6.38.855.243 I slot print_timing: id 2 | task 5146 | eval time = 6020.66 ms / 129 tokens ( 47.04 ms per token, 21.26 tokens per second) 6.38.855.244 I slot print_timing: id 2 | task 5146 | total time = 6410.91 ms / 202 tokens 6.38.855.244 I slot print_timing: id 2 | task 5146 | graphs reused = 4390 6.38.855.245 I slot print_timing: id 2 | task 5146 | graph reallocs = 0 / 0 (same size) / (changed size) 6.38.855.302 I slot release: id 2 | task 5146 | stop processing: n_tokens = 1316, truncated = 0 6.38.923.561 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.847 6.38.923.586 I slot launch_slot_: id 2 | task 5279 | processing task, is_child = 0 6.39.255.463 I slot print_timing: id 1 | task 5111 | n_gen = 165, tg = 19.82 t/s, tg_3s = 20.09 t/s 6.39.503.659 I slot print_timing: id 0 | task 5182 | n_gen = 100, tg = 20.46 t/s, tg_3s = 20.67 t/s 6.40.183.185 I slot print_timing: id 3 | task 5074 | n_gen = 220, tg = 19.61 t/s, tg_3s = 19.44 t/s 6.42.292.431 I slot print_timing: id 1 | task 5111 | n_gen = 231, tg = 20.33 t/s, tg_3s = 21.73 t/s 6.42.515.822 I slot print_timing: id 0 | task 5182 | n_gen = 167, tg = 21.15 t/s, tg_3s = 22.24 t/s 6.43.195.864 I slot print_timing: id 3 | task 5074 | n_gen = 287, tg = 20.17 t/s, tg_3s = 22.24 t/s 6.43.687.842 I slot print_timing: id 1 | task 5111 | prompt eval time = 408.84 ms / 70 tokens ( 5.84 ms per token, 171.22 tokens per second) 6.43.687.848 I slot print_timing: id 1 | task 5111 | eval time = 12708.48 ms / 262 tokens ( 48.69 ms per token, 20.54 tokens per second) 6.43.687.848 I slot print_timing: id 1 | task 5111 | total time = 13117.32 ms / 332 tokens 6.43.687.849 I slot print_timing: id 1 | task 5111 | graphs reused = 4485 6.43.687.849 I slot print_timing: id 1 | task 5111 | graph reallocs = 0 / 0 (same size) / (changed size) 6.43.687.901 I slot release: id 1 | task 5111 | stop processing: n_tokens = 1446, truncated = 0 6.43.757.642 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.771 6.43.757.671 I slot launch_slot_: id 1 | task 5379 | processing task, is_child = 0 6.44.170.747 I slot print_timing: id 2 | task 5279 | n_gen = 100, tg = 20.61 t/s, tg_3s = 20.82 t/s 6.45.524.901 I slot print_timing: id 0 | task 5182 | n_gen = 226, tg = 20.72 t/s, tg_3s = 19.61 t/s 6.46.204.566 I slot print_timing: id 3 | task 5074 | n_gen = 346, tg = 20.07 t/s, tg_3s = 19.61 t/s 6.47.194.232 I slot print_timing: id 2 | task 5279 | n_gen = 167, tg = 21.21 t/s, tg_3s = 22.16 t/s 6.47.374.757 I slot print_timing: id 2 | task 5279 | prompt eval time = 443.68 ms / 105 tokens ( 4.23 ms per token, 236.65 tokens per second) 6.47.374.761 I slot print_timing: id 2 | task 5279 | eval time = 8007.48 ms / 171 tokens ( 47.10 ms per token, 21.23 tokens per second) 6.47.374.762 I slot print_timing: id 2 | task 5279 | total time = 8451.16 ms / 276 tokens 6.47.374.762 I slot print_timing: id 2 | task 5279 | graphs reused = 4554 6.47.374.763 I slot print_timing: id 2 | task 5279 | graph reallocs = 0 / 0 (same size) / (changed size) 6.47.374.819 I slot release: id 2 | task 5279 | stop processing: n_tokens = 1390, truncated = 0 6.47.442.891 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.802 6.47.442.914 I slot launch_slot_: id 2 | task 5454 | processing task, is_child = 0 6.47.880.432 I slot print_timing: id 0 | task 5182 | prompt eval time = 344.17 ms / 91 tokens ( 3.78 ms per token, 264.40 tokens per second) 6.47.880.439 I slot print_timing: id 0 | task 5182 | eval time = 13214.62 ms / 271 tokens ( 48.94 ms per token, 20.43 tokens per second) 6.47.880.440 I slot print_timing: id 0 | task 5182 | total time = 13558.79 ms / 362 tokens 6.47.880.441 I slot print_timing: id 0 | task 5182 | graphs reused = 4554 6.47.880.441 I slot print_timing: id 0 | task 5182 | graph reallocs = 0 / 0 (same size) / (changed size) 6.47.880.514 I slot release: id 0 | task 5182 | stop processing: n_tokens = 1476, truncated = 0 6.47.931.723 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.755 6.47.931.748 I slot launch_slot_: id 0 | task 5459 | processing task, is_child = 0 6.48.683.796 I slot print_timing: id 3 | task 5074 | prompt eval time = 402.32 ms / 106 tokens ( 3.80 ms per token, 263.47 tokens per second) 6.48.683.802 I slot print_timing: id 3 | task 5074 | eval time = 19668.93 ms / 387 tokens ( 50.96 ms per token, 19.62 tokens per second) 6.48.683.803 I slot print_timing: id 3 | task 5074 | total time = 20071.25 ms / 493 tokens 6.48.683.803 I slot print_timing: id 3 | task 5074 | graphs reused = 4562 6.48.683.804 I slot print_timing: id 3 | task 5074 | graph reallocs = 0 / 0 (same size) / (changed size) 6.48.683.857 I slot release: id 3 | task 5074 | stop processing: n_tokens = 1607, truncated = 0 6.48.727.152 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.694 6.48.727.177 I slot launch_slot_: id 3 | task 5471 | processing task, is_child = 0 6.49.517.273 I slot print_timing: id 1 | task 5379 | n_gen = 100, tg = 18.51 t/s, tg_3s = 18.70 t/s 6.50.505.329 I slot print_timing: id 1 | task 5379 | prompt eval time = 410.70 ms / 79 tokens ( 5.20 ms per token, 192.35 tokens per second) 6.50.505.333 I slot print_timing: id 1 | task 5379 | eval time = 6336.95 ms / 122 tokens ( 52.37 ms per token, 19.09 tokens per second) 6.50.505.333 I slot print_timing: id 1 | task 5379 | total time = 6747.65 ms / 201 tokens 6.50.505.334 I slot print_timing: id 1 | task 5379 | graphs reused = 4593 6.50.505.334 I slot print_timing: id 1 | task 5379 | graph reallocs = 0 / 0 (same size) / (changed size) 6.50.505.400 I slot release: id 1 | task 5379 | stop processing: n_tokens = 1315, truncated = 0 6.50.574.935 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.848 6.50.574.960 I slot launch_slot_: id 1 | task 5507 | processing task, is_child = 0 6.53.184.770 I slot print_timing: id 2 | task 5454 | n_gen = 100, tg = 18.51 t/s, tg_3s = 18.69 t/s 6.53.361.128 I slot print_timing: id 0 | task 5459 | n_gen = 100, tg = 19.62 t/s, tg_3s = 19.82 t/s 6.53.859.826 I slot print_timing: id 3 | task 5471 | n_gen = 100, tg = 20.66 t/s, tg_3s = 20.87 t/s 6.54.445.788 I slot print_timing: id 3 | task 5471 | prompt eval time = 340.09 ms / 98 tokens ( 3.47 ms per token, 288.16 tokens per second) 6.54.445.796 I slot print_timing: id 3 | task 5471 | eval time = 5378.52 ms / 113 tokens ( 48.02 ms per token, 20.82 tokens per second) 6.54.445.796 I slot print_timing: id 3 | task 5471 | total time = 5718.60 ms / 211 tokens 6.54.445.797 I slot print_timing: id 3 | task 5471 | graphs reused = 4668 6.54.445.798 I slot print_timing: id 3 | task 5471 | graph reallocs = 0 / 0 (same size) / (changed size) 6.54.445.854 I slot release: id 3 | task 5471 | stop processing: n_tokens = 1325, truncated = 0 6.54.489.264 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.842 6.54.489.288 I slot launch_slot_: id 3 | task 5588 | processing task, is_child = 0 6.55.696.032 I slot print_timing: id 1 | task 5507 | n_gen = 100, tg = 20.98 t/s, tg_3s = 21.19 t/s 6.56.191.637 I slot print_timing: id 2 | task 5454 | n_gen = 161, tg = 19.15 t/s, tg_3s = 20.29 t/s 6.56.368.035 I slot print_timing: id 0 | task 5459 | n_gen = 161, tg = 19.87 t/s, tg_3s = 20.29 t/s 6.58.708.232 I slot print_timing: id 1 | task 5507 | n_gen = 167, tg = 21.47 t/s, tg_3s = 22.24 t/s 6.59.204.905 I slot print_timing: id 2 | task 5454 | n_gen = 228, tg = 19.97 t/s, tg_3s = 22.24 t/s 6.59.296.474 I slot print_timing: id 3 | task 5588 | n_gen = 100, tg = 22.20 t/s, tg_3s = 22.43 t/s 6.59.381.973 I slot print_timing: id 0 | task 5459 | n_gen = 228, tg = 20.51 t/s, tg_3s = 22.23 t/s 6.59.833.631 I slot print_timing: id 1 | task 5507 | prompt eval time = 401.51 ms / 93 tokens ( 4.32 ms per token, 231.63 tokens per second) 6.59.833.637 I slot print_timing: id 1 | task 5507 | eval time = 8857.15 ms / 192 tokens ( 46.37 ms per token, 21.56 tokens per second) 6.59.833.638 I slot print_timing: id 1 | task 5507 | total time = 9258.66 ms / 285 tokens 6.59.833.639 I slot print_timing: id 1 | task 5507 | graphs reused = 4778 6.59.833.639 I slot print_timing: id 1 | task 5507 | graph reallocs = 0 / 0 (same size) / (changed size) 6.59.833.693 I slot release: id 1 | task 5507 | stop processing: n_tokens = 1399, truncated = 0 6.59.903.356 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.797 6.59.903.384 I slot launch_slot_: id 1 | task 5703 | processing task, is_child = 0 7.00.803.724 I slot print_timing: id 3 | task 5588 | prompt eval time = 347.98 ms / 76 tokens ( 4.58 ms per token, 218.41 tokens per second) 7.00.803.728 I slot print_timing: id 3 | task 5588 | eval time = 5966.45 ms / 126 tokens ( 47.73 ms per token, 20.95 tokens per second) 7.00.803.729 I slot print_timing: id 3 | task 5588 | total time = 6314.43 ms / 202 tokens 7.00.803.729 I slot print_timing: id 3 | task 5588 | graphs reused = 4788 7.00.803.730 I slot print_timing: id 3 | task 5588 | graph reallocs = 0 / 0 (same size) / (changed size) 7.00.803.782 I slot release: id 3 | task 5588 | stop processing: n_tokens = 1316, truncated = 0 7.00.847.376 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.847 7.00.847.404 I slot launch_slot_: id 3 | task 5718 | processing task, is_child = 0 7.01.161.600 I slot print_timing: id 2 | task 5454 | prompt eval time = 392.11 ms / 97 tokens ( 4.04 ms per token, 247.38 tokens per second) 7.01.161.607 I slot print_timing: id 2 | task 5454 | eval time = 13326.57 ms / 258 tokens ( 51.85 ms per token, 19.28 tokens per second) 7.01.161.608 I slot print_timing: id 2 | task 5454 | total time = 13718.68 ms / 355 tokens 7.01.161.608 I slot print_timing: id 2 | task 5454 | graphs reused = 4788 7.01.161.609 I slot print_timing: id 2 | task 5454 | graph reallocs = 0 / 0 (same size) / (changed size) 7.01.161.676 I slot release: id 2 | task 5454 | stop processing: n_tokens = 1469, truncated = 0 7.01.241.964 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.759 7.01.241.988 I slot launch_slot_: id 2 | task 5721 | processing task, is_child = 0 7.02.414.455 I slot print_timing: id 0 | task 5459 | n_gen = 276, tg = 19.50 t/s, tg_3s = 15.83 t/s 7.04.578.389 I slot print_timing: id 2 | task 5721 | prompt eval time = 318.00 ms / 64 tokens ( 4.97 ms per token, 201.26 tokens per second) 7.04.578.393 I slot print_timing: id 2 | task 5721 | eval time = 3018.39 ms / 68 tokens ( 45.05 ms per token, 22.20 tokens per second) 7.04.578.393 I slot print_timing: id 2 | task 5721 | total time = 3336.39 ms / 132 tokens 7.04.578.394 I slot print_timing: id 2 | task 5721 | graphs reused = 4853 7.04.578.395 I slot print_timing: id 2 | task 5721 | graph reallocs = 0 / 0 (same size) / (changed size) 7.04.578.449 I slot release: id 2 | task 5721 | stop processing: n_tokens = 1246, truncated = 0 7.04.646.498 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.895 7.04.646.522 I slot launch_slot_: id 2 | task 5792 | processing task, is_child = 0 7.05.438.850 I slot print_timing: id 0 | task 5459 | n_gen = 336, tg = 19.56 t/s, tg_3s = 19.84 t/s 7.05.620.677 I slot print_timing: id 1 | task 5703 | n_gen = 100, tg = 18.61 t/s, tg_3s = 18.80 t/s 7.06.254.416 I slot print_timing: id 3 | task 5718 | n_gen = 100, tg = 19.75 t/s, tg_3s = 19.95 t/s 7.06.522.116 I slot print_timing: id 1 | task 5703 | prompt eval time = 396.80 ms / 71 tokens ( 5.59 ms per token, 178.93 tokens per second) 7.06.522.120 I slot print_timing: id 1 | task 5703 | eval time = 6221.93 ms / 120 tokens ( 52.29 ms per token, 19.13 tokens per second) 7.06.522.121 I slot print_timing: id 1 | task 5703 | total time = 6618.73 ms / 191 tokens 7.06.522.122 I slot print_timing: id 1 | task 5703 | graphs reused = 4885 7.06.522.122 I slot print_timing: id 1 | task 5703 | graph reallocs = 0 / 0 (same size) / (changed size) 7.06.522.185 I slot release: id 1 | task 5703 | stop processing: n_tokens = 1305, truncated = 0 7.06.591.686 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.854 7.06.591.711 I slot launch_slot_: id 1 | task 5829 | processing task, is_child = 0 7.08.480.694 I slot print_timing: id 0 | task 5459 | n_gen = 397, tg = 19.64 t/s, tg_3s = 20.05 t/s 7.09.296.418 I slot print_timing: id 3 | task 5718 | n_gen = 161, tg = 19.86 t/s, tg_3s = 20.05 t/s 7.09.791.142 I slot print_timing: id 2 | task 5792 | n_gen = 100, tg = 20.78 t/s, tg_3s = 20.99 t/s 7.11.415.248 I slot print_timing: id 1 | task 5829 | prompt eval time = 351.32 ms / 69 tokens ( 5.09 ms per token, 196.40 tokens per second) 7.11.415.252 I slot print_timing: id 1 | task 5829 | eval time = 4472.21 ms / 100 tokens ( 45.17 ms per token, 22.14 tokens per second) 7.11.415.253 I slot print_timing: id 1 | task 5829 | total time = 4823.53 ms / 169 tokens 7.11.415.253 I slot print_timing: id 1 | task 5829 | graphs reused = 4983 7.11.415.254 I slot print_timing: id 1 | task 5829 | graph reallocs = 0 / 0 (same size) / (changed size) 7.11.415.311 I slot release: id 1 | task 5829 | stop processing: n_tokens = 1283, truncated = 0 7.11.481.468 I slot print_timing: id 0 | task 5459 | n_gen = 463, tg = 19.94 t/s, tg_3s = 21.99 t/s 7.11.485.019 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.869 7.11.485.042 I slot launch_slot_: id 1 | task 5932 | processing task, is_child = 0 7.12.316.232 I slot print_timing: id 3 | task 5718 | n_gen = 220, tg = 19.78 t/s, tg_3s = 19.54 t/s 7.12.810.527 I slot print_timing: id 2 | task 5792 | n_gen = 159, tg = 20.30 t/s, tg_3s = 19.54 t/s 7.14.522.655 I slot print_timing: id 0 | task 5459 | n_gen = 523, tg = 19.92 t/s, tg_3s = 19.73 t/s 7.14.751.580 I slot print_timing: id 2 | task 5792 | prompt eval time = 380.96 ms / 74 tokens ( 5.15 ms per token, 194.25 tokens per second) 7.14.751.583 I slot print_timing: id 2 | task 5792 | eval time = 9724.09 ms / 202 tokens ( 48.38 ms per token, 20.67 tokens per second) 7.14.751.584 I slot print_timing: id 2 | task 5792 | total time = 10105.05 ms / 276 tokens 7.14.751.585 I slot print_timing: id 2 | task 5792 | graphs reused = 5045 7.14.751.585 I slot print_timing: id 2 | task 5792 | graph reallocs = 0 / 0 (same size) / (changed size) 7.14.751.648 I slot release: id 2 | task 5792 | stop processing: n_tokens = 1390, truncated = 0 7.14.819.841 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.802 7.14.819.866 I slot launch_slot_: id 2 | task 5999 | processing task, is_child = 0 7.15.356.105 I slot print_timing: id 3 | task 5718 | n_gen = 280, tg = 19.77 t/s, tg_3s = 19.74 t/s 7.16.477.927 I slot print_timing: id 0 | task 5459 | prompt eval time = 383.64 ms / 108 tokens ( 3.55 ms per token, 281.51 tokens per second) 7.16.477.931 I slot print_timing: id 0 | task 5459 | eval time = 28162.53 ms / 559 tokens ( 50.47 ms per token, 19.81 tokens per second) 7.16.477.931 I slot print_timing: id 0 | task 5459 | total time = 28546.17 ms / 667 tokens 7.16.477.932 I slot print_timing: id 0 | task 5459 | graphs reused = 5072 7.16.477.933 I slot print_timing: id 0 | task 5459 | graph reallocs = 0 / 0 (same size) / (changed size) 7.16.477.993 I slot release: id 0 | task 5459 | stop processing: n_tokens = 1781, truncated = 0 7.16.526.241 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.626 7.16.526.268 I slot launch_slot_: id 0 | task 6031 | processing task, is_child = 0 7.16.885.681 I slot print_timing: id 1 | task 5932 | n_gen = 100, tg = 19.85 t/s, tg_3s = 20.05 t/s 7.18.019.918 I slot print_timing: id 1 | task 5932 | prompt eval time = 412.93 ms / 88 tokens ( 4.69 ms per token, 213.11 tokens per second) 7.18.019.922 I slot print_timing: id 1 | task 5932 | eval time = 6121.94 ms / 125 tokens ( 49.37 ms per token, 20.26 tokens per second) 7.18.019.923 I slot print_timing: id 1 | task 5932 | total time = 6534.87 ms / 213 tokens 7.18.019.923 I slot print_timing: id 1 | task 5932 | graphs reused = 5099 7.18.019.924 I slot print_timing: id 1 | task 5932 | graph reallocs = 0 / 0 (same size) / (changed size) 7.18.019.976 I slot release: id 1 | task 5932 | stop processing: n_tokens = 1327, truncated = 0 7.18.089.557 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.840 7.18.089.586 I slot launch_slot_: id 1 | task 6062 | processing task, is_child = 0 7.18.491.729 I slot print_timing: id 3 | task 5718 | n_gen = 337, tg = 19.48 t/s, tg_3s = 18.18 t/s 7.18.607.309 I slot print_timing: id 3 | task 5718 | prompt eval time = 394.55 ms / 127 tokens ( 3.11 ms per token, 321.88 tokens per second) 7.18.607.311 I slot print_timing: id 3 | task 5718 | eval time = 17365.35 ms / 338 tokens ( 51.53 ms per token, 19.41 tokens per second) 7.18.607.312 I slot print_timing: id 3 | task 5718 | total time = 17759.90 ms / 465 tokens 7.18.607.312 I slot print_timing: id 3 | task 5718 | graphs reused = 5099 7.18.607.312 I slot print_timing: id 3 | task 5718 | graph reallocs = 0 / 0 (same size) / (changed size) 7.18.607.369 I slot release: id 3 | task 5718 | stop processing: n_tokens = 1579, truncated = 0 7.18.649.286 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.706 7.18.649.310 I slot launch_slot_: id 3 | task 6066 | processing task, is_child = 0 7.20.562.589 I slot print_timing: id 2 | task 5999 | n_gen = 100, tg = 18.51 t/s, tg_3s = 18.70 t/s 7.20.694.514 I slot print_timing: id 0 | task 6031 | prompt eval time = 271.29 ms / 66 tokens ( 4.11 ms per token, 243.28 tokens per second) 7.20.694.518 I slot print_timing: id 0 | task 6031 | eval time = 3896.94 ms / 72 tokens ( 54.89 ms per token, 18.22 tokens per second) 7.20.694.519 I slot print_timing: id 0 | task 6031 | total time = 4168.23 ms / 138 tokens 7.20.694.522 I slot print_timing: id 0 | task 6031 | graphs reused = 5135 7.20.694.522 I slot print_timing: id 0 | task 6031 | graph reallocs = 0 / 0 (same size) / (changed size) 7.20.694.579 I slot release: id 0 | task 6031 | stop processing: n_tokens = 1251, truncated = 0 7.20.742.816 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.891 7.20.742.841 I slot launch_slot_: id 0 | task 6108 | processing task, is_child = 0 7.23.567.262 I slot print_timing: id 2 | task 5999 | n_gen = 160, tg = 19.04 t/s, tg_3s = 19.97 t/s 7.23.610.599 I slot print_timing: id 1 | task 6062 | n_gen = 100, tg = 19.78 t/s, tg_3s = 19.98 t/s 7.23.748.546 I slot print_timing: id 3 | task 6066 | n_gen = 100, tg = 20.79 t/s, tg_3s = 21.00 t/s 7.25.586.118 I slot print_timing: id 0 | task 6108 | n_gen = 100, tg = 22.23 t/s, tg_3s = 22.46 t/s 7.26.578.743 I slot print_timing: id 2 | task 5999 | n_gen = 227, tg = 19.89 t/s, tg_3s = 22.25 t/s 7.26.622.193 I slot print_timing: id 1 | task 6062 | n_gen = 167, tg = 20.71 t/s, tg_3s = 22.25 t/s 7.26.760.337 I slot print_timing: id 3 | task 6066 | n_gen = 167, tg = 21.35 t/s, tg_3s = 22.25 t/s 7.26.848.819 I slot print_timing: id 2 | task 5999 | prompt eval time = 394.68 ms / 95 tokens ( 4.15 ms per token, 240.70 tokens per second) 7.26.848.827 I slot print_timing: id 2 | task 5999 | eval time = 11634.27 ms / 233 tokens ( 50.15 ms per token, 19.94 tokens per second) 7.26.848.827 I slot print_timing: id 2 | task 5999 | total time = 12028.95 ms / 328 tokens 7.26.848.828 I slot print_timing: id 2 | task 5999 | graphs reused = 5262 7.26.848.829 I slot print_timing: id 2 | task 5999 | graph reallocs = 0 / 0 (same size) / (changed size) 7.26.848.885 I slot release: id 2 | task 5999 | stop processing: n_tokens = 1442, truncated = 0 7.26.916.931 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.773 7.26.916.961 I slot launch_slot_: id 2 | task 6239 | processing task, is_child = 0 7.28.612.834 I slot print_timing: id 0 | task 6108 | n_gen = 160, tg = 21.26 t/s, tg_3s = 19.82 t/s 7.29.649.993 I slot print_timing: id 1 | task 6062 | n_gen = 227, tg = 20.46 t/s, tg_3s = 19.82 t/s 7.29.788.208 I slot print_timing: id 3 | task 6066 | n_gen = 227, tg = 20.92 t/s, tg_3s = 19.82 t/s 7.31.182.525 I slot print_timing: id 2 | task 6239 | prompt eval time = 391.44 ms / 85 tokens ( 4.61 ms per token, 217.15 tokens per second) 7.31.182.531 I slot print_timing: id 2 | task 6239 | eval time = 3874.12 ms / 87 tokens ( 45.05 ms per token, 22.20 tokens per second) 7.31.182.532 I slot print_timing: id 2 | task 6239 | total time = 4265.56 ms / 172 tokens 7.31.182.533 I slot print_timing: id 2 | task 6239 | graphs reused = 5347 7.31.182.533 I slot print_timing: id 2 | task 6239 | graph reallocs = 0 / 0 (same size) / (changed size) 7.31.182.587 I slot release: id 2 | task 6239 | stop processing: n_tokens = 1286, truncated = 0 7.31.250.554 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.867 7.31.250.582 I slot launch_slot_: id 2 | task 6329 | processing task, is_child = 0 7.31.685.928 I slot print_timing: id 0 | task 6108 | n_gen = 220, tg = 20.75 t/s, tg_3s = 19.52 t/s 7.32.276.178 I slot print_timing: id 0 | task 6108 | prompt eval time = 390.04 ms / 123 tokens ( 3.17 ms per token, 315.35 tokens per second) 7.32.276.186 I slot print_timing: id 0 | task 6108 | eval time = 11143.29 ms / 233 tokens ( 48.03 ms per token, 20.82 tokens per second) 7.32.276.186 I slot print_timing: id 0 | task 6108 | total time = 11533.33 ms / 356 tokens 7.32.276.187 I slot print_timing: id 0 | task 6108 | graphs reused = 5359 7.32.276.188 I slot print_timing: id 0 | task 6108 | graph reallocs = 0 / 0 (same size) / (changed size) 7.32.276.242 I slot release: id 0 | task 6108 | stop processing: n_tokens = 1470, truncated = 0 7.32.324.666 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.759 7.32.324.688 I slot launch_slot_: id 0 | task 6346 | processing task, is_child = 0 7.32.657.575 I slot print_timing: id 1 | task 6062 | n_gen = 280, tg = 19.85 t/s, tg_3s = 17.62 t/s 7.32.790.945 I slot print_timing: id 3 | task 6066 | n_gen = 280, tg = 20.21 t/s, tg_3s = 17.65 t/s 7.32.881.747 I slot print_timing: id 1 | task 6062 | prompt eval time = 515.62 ms / 145 tokens ( 3.56 ms per token, 281.22 tokens per second) 7.32.881.751 I slot print_timing: id 1 | task 6062 | eval time = 14276.54 ms / 285 tokens ( 50.27 ms per token, 19.89 tokens per second) 7.32.881.752 I slot print_timing: id 1 | task 6062 | total time = 14792.15 ms / 430 tokens 7.32.881.753 I slot print_timing: id 1 | task 6062 | graphs reused = 5364 7.32.881.753 I slot print_timing: id 1 | task 6062 | graph reallocs = 0 / 0 (same size) / (changed size) 7.32.881.821 I slot release: id 1 | task 6062 | stop processing: n_tokens = 1544, truncated = 0 7.32.954.060 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.722 7.32.954.090 I slot launch_slot_: id 1 | task 6355 | processing task, is_child = 0 7.35.804.879 I slot print_timing: id 3 | task 6066 | n_gen = 338, tg = 20.04 t/s, tg_3s = 19.24 t/s 7.36.794.773 I slot print_timing: id 2 | task 6329 | n_gen = 100, tg = 19.39 t/s, tg_3s = 19.58 t/s 7.37.512.750 I slot print_timing: id 0 | task 6346 | n_gen = 100, tg = 20.39 t/s, tg_3s = 20.59 t/s 7.37.874.465 I slot print_timing: id 1 | task 6355 | n_gen = 100, tg = 22.18 t/s, tg_3s = 22.41 t/s 7.38.823.263 I slot print_timing: id 3 | task 6066 | n_gen = 405, tg = 20.37 t/s, tg_3s = 22.20 t/s 7.39.813.853 I slot print_timing: id 2 | task 6329 | n_gen = 167, tg = 20.43 t/s, tg_3s = 22.19 t/s 7.40.531.881 I slot print_timing: id 0 | task 6346 | n_gen = 167, tg = 21.08 t/s, tg_3s = 22.19 t/s 7.40.892.827 I slot print_timing: id 1 | task 6355 | n_gen = 167, tg = 22.19 t/s, tg_3s = 22.20 t/s 7.41.660.557 I slot print_timing: id 2 | task 6329 | prompt eval time = 437.70 ms / 120 tokens ( 3.65 ms per token, 274.16 tokens per second) 7.41.660.564 I slot print_timing: id 2 | task 6329 | eval time = 9972.27 ms / 208 tokens ( 48.18 ms per token, 20.76 tokens per second) 7.41.660.564 I slot print_timing: id 2 | task 6329 | total time = 10409.97 ms / 328 tokens 7.41.660.565 I slot print_timing: id 2 | task 6329 | graphs reused = 5545 7.41.660.566 I slot print_timing: id 2 | task 6329 | graph reallocs = 0 / 0 (same size) / (changed size) 7.41.660.625 I slot release: id 2 | task 6329 | stop processing: n_tokens = 1442, truncated = 0 7.41.728.802 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.773 7.41.728.827 I slot launch_slot_: id 2 | task 6542 | processing task, is_child = 0 7.42.013.511 I slot print_timing: id 3 | task 6066 | n_gen = 470, tg = 20.37 t/s, tg_3s = 20.37 t/s 7.43.570.289 I slot print_timing: id 0 | task 6346 | n_gen = 227, tg = 20.71 t/s, tg_3s = 19.75 t/s 7.43.932.723 I slot print_timing: id 1 | task 6355 | n_gen = 227, tg = 21.48 t/s, tg_3s = 19.74 t/s 7.44.158.093 I slot print_timing: id 1 | task 6355 | prompt eval time = 457.22 ms / 111 tokens ( 4.12 ms per token, 242.77 tokens per second) 7.44.158.098 I slot print_timing: id 1 | task 6355 | eval time = 10746.77 ms / 232 tokens ( 46.52 ms per token, 21.49 tokens per second) 7.44.158.101 I slot print_timing: id 1 | task 6355 | total time = 11203.99 ms / 343 tokens 7.44.158.101 I slot print_timing: id 1 | task 6355 | graphs reused = 5589 7.44.158.102 I slot print_timing: id 1 | task 6355 | graph reallocs = 0 / 0 (same size) / (changed size) 7.44.158.160 I slot release: id 1 | task 6355 | stop processing: n_tokens = 1457, truncated = 0 7.44.227.961 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.765 7.44.227.993 I slot launch_slot_: id 1 | task 6591 | processing task, is_child = 0 7.45.039.795 I slot print_timing: id 3 | task 6066 | n_gen = 528, tg = 20.23 t/s, tg_3s = 19.17 t/s 7.45.709.802 I slot print_timing: id 0 | task 6346 | prompt eval time = 331.79 ms / 85 tokens ( 3.90 ms per token, 256.19 tokens per second) 7.45.709.809 I slot print_timing: id 0 | task 6346 | eval time = 13053.32 ms / 267 tokens ( 49.07 ms per token, 20.38 tokens per second) 7.45.709.810 I slot print_timing: id 0 | task 6346 | total time = 13385.10 ms / 352 tokens 7.45.709.810 I slot print_timing: id 0 | task 6346 | graphs reused = 5612 7.45.709.811 I slot print_timing: id 0 | task 6346 | graph reallocs = 0 / 0 (same size) / (changed size) 7.45.709.866 I slot release: id 0 | task 6346 | stop processing: n_tokens = 1466, truncated = 0 7.45.758.168 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.761 7.45.758.191 I slot launch_slot_: id 0 | task 6619 | processing task, is_child = 0 7.47.175.857 I slot print_timing: id 2 | task 6542 | n_gen = 100, tg = 19.60 t/s, tg_3s = 19.80 t/s 7.48.077.802 I slot print_timing: id 3 | task 6066 | n_gen = 590, tg = 20.25 t/s, tg_3s = 20.41 t/s 7.49.339.880 I slot print_timing: id 1 | task 6591 | n_gen = 100, tg = 21.00 t/s, tg_3s = 21.21 t/s 7.50.199.837 I slot print_timing: id 2 | task 6542 | n_gen = 167, tg = 20.56 t/s, tg_3s = 22.16 t/s 7.50.380.397 I slot print_timing: id 2 | task 6542 | prompt eval time = 396.80 ms / 96 tokens ( 4.13 ms per token, 241.94 tokens per second) 7.50.380.402 I slot print_timing: id 2 | task 6542 | eval time = 8254.77 ms / 171 tokens ( 48.56 ms per token, 20.59 tokens per second) 7.50.380.403 I slot print_timing: id 2 | task 6542 | total time = 8651.56 ms / 267 tokens 7.50.380.403 I slot print_timing: id 2 | task 6542 | graphs reused = 5706 7.50.380.404 I slot print_timing: id 2 | task 6542 | graph reallocs = 0 / 0 (same size) / (changed size) 7.50.380.462 I slot release: id 2 | task 6542 | stop processing: n_tokens = 1381, truncated = 0 7.50.448.629 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.807 7.50.448.652 I slot launch_slot_: id 2 | task 6718 | processing task, is_child = 0 7.50.826.184 I slot print_timing: id 1 | task 6591 | prompt eval time = 397.24 ms / 71 tokens ( 5.59 ms per token, 178.73 tokens per second) 7.50.826.188 I slot print_timing: id 1 | task 6591 | eval time = 6200.95 ms / 126 tokens ( 49.61 ms per token, 20.16 tokens per second) 7.50.826.189 I slot print_timing: id 1 | task 6591 | total time = 6598.19 ms / 197 tokens 7.50.826.189 I slot print_timing: id 1 | task 6591 | graphs reused = 5706 7.50.826.190 I slot print_timing: id 1 | task 6591 | graph reallocs = 0 / 0 (same size) / (changed size) 7.50.826.234 I slot release: id 1 | task 6591 | stop processing: n_tokens = 1311, truncated = 0 7.50.890.227 I slot print_timing: id 0 | task 6619 | n_gen = 100, tg = 20.63 t/s, tg_3s = 20.83 t/s 7.50.892.393 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.850 7.50.892.411 I slot launch_slot_: id 1 | task 6722 | processing task, is_child = 0 7.51.178.350 I slot print_timing: id 3 | task 6066 | n_gen = 646, tg = 20.04 t/s, tg_3s = 18.06 t/s 7.53.903.721 I slot print_timing: id 0 | task 6619 | n_gen = 160, tg = 20.35 t/s, tg_3s = 19.91 t/s 7.54.179.222 I slot print_timing: id 3 | task 6066 | n_gen = 711, tg = 20.17 t/s, tg_3s = 21.66 t/s 7.55.528.005 I slot print_timing: id 0 | task 6619 | prompt eval time = 332.14 ms / 86 tokens ( 3.86 ms per token, 258.93 tokens per second) 7.55.528.017 I slot print_timing: id 0 | task 6619 | eval time = 9437.67 ms / 196 tokens ( 48.40 ms per token, 20.66 tokens per second) 7.55.528.017 I slot print_timing: id 0 | task 6619 | total time = 9769.81 ms / 282 tokens 7.55.528.018 I slot print_timing: id 0 | task 6619 | graphs reused = 5799 7.55.528.019 I slot print_timing: id 0 | task 6619 | graph reallocs = 0 / 0 (same size) / (changed size) 7.55.528.083 I slot release: id 0 | task 6619 | stop processing: n_tokens = 1396, truncated = 0 7.55.576.415 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.799 7.55.576.443 I slot launch_slot_: id 0 | task 6820 | processing task, is_child = 0 7.55.945.628 I slot print_timing: id 2 | task 6718 | n_gen = 100, tg = 19.34 t/s, tg_3s = 19.54 t/s 7.56.131.311 I slot print_timing: id 1 | task 6722 | n_gen = 100, tg = 20.45 t/s, tg_3s = 20.66 t/s 7.57.220.032 I slot print_timing: id 3 | task 6066 | n_gen = 770, tg = 20.11 t/s, tg_3s = 19.40 t/s 7.57.534.323 I slot print_timing: id 2 | task 6718 | prompt eval time = 378.74 ms / 76 tokens ( 4.98 ms per token, 200.66 tokens per second) 7.57.534.327 I slot print_timing: id 2 | task 6718 | eval time = 6706.92 ms / 134 tokens ( 50.43 ms per token, 19.83 tokens per second) 7.57.534.327 I slot print_timing: id 2 | task 6718 | total time = 7085.66 ms / 210 tokens 7.57.534.328 I slot print_timing: id 2 | task 6718 | graphs reused = 5832 7.57.534.328 I slot print_timing: id 2 | task 6718 | graph reallocs = 0 / 0 (same size) / (changed size) 7.57.534.381 I slot release: id 2 | task 6718 | stop processing: n_tokens = 1324, truncated = 0 7.57.602.631 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.842 7.57.602.654 I slot launch_slot_: id 2 | task 6857 | processing task, is_child = 0 7.59.167.992 I slot print_timing: id 1 | task 6722 | n_gen = 160, tg = 20.18 t/s, tg_3s = 19.76 t/s 8.00.252.651 I slot print_timing: id 3 | task 6066 | n_gen = 830, tg = 20.09 t/s, tg_3s = 19.78 t/s 8.00.835.023 I slot print_timing: id 0 | task 6820 | n_gen = 100, tg = 20.61 t/s, tg_3s = 20.82 t/s 8.00.836.615 I slot print_timing: id 1 | task 6722 | prompt eval time = 397.86 ms / 83 tokens ( 4.79 ms per token, 208.61 tokens per second) 8.00.836.618 I slot print_timing: id 1 | task 6722 | eval time = 9546.33 ms / 197 tokens ( 48.71 ms per token, 20.53 tokens per second) 8.00.836.619 I slot print_timing: id 1 | task 6722 | total time = 9944.20 ms / 280 tokens 8.00.836.620 I slot print_timing: id 1 | task 6722 | graphs reused = 5894 8.00.836.620 I slot print_timing: id 1 | task 6722 | graph reallocs = 0 / 0 (same size) / (changed size) 8.00.836.673 I slot release: id 1 | task 6722 | stop processing: n_tokens = 1394, truncated = 0 8.00.906.503 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.800 8.00.906.529 I slot launch_slot_: id 1 | task 6924 | processing task, is_child = 0 8.02.864.118 I slot print_timing: id 2 | task 6857 | n_gen = 100, tg = 20.34 t/s, tg_3s = 20.54 t/s 8.03.273.426 I slot print_timing: id 3 | task 6066 | n_gen = 888, tg = 20.03 t/s, tg_3s = 19.20 t/s 8.03.859.860 I slot print_timing: id 0 | task 6820 | n_gen = 158, tg = 20.06 t/s, tg_3s = 19.17 t/s 8.04.135.836 I slot print_timing: id 2 | task 6857 | prompt eval time = 393.80 ms / 86 tokens ( 4.58 ms per token, 218.39 tokens per second) 8.04.135.843 I slot print_timing: id 2 | task 6857 | eval time = 6139.38 ms / 128 tokens ( 48.34 ms per token, 20.69 tokens per second) 8.04.135.844 I slot print_timing: id 2 | task 6857 | total time = 6533.18 ms / 214 tokens 8.04.135.845 I slot print_timing: id 2 | task 6857 | graphs reused = 5953 8.04.135.845 I slot print_timing: id 2 | task 6857 | graph reallocs = 0 / 0 (same size) / (changed size) 8.04.135.904 I slot release: id 2 | task 6857 | stop processing: n_tokens = 1328, truncated = 0 8.04.204.100 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.840 8.04.204.126 I slot launch_slot_: id 2 | task 6989 | processing task, is_child = 0 8.06.177.880 I slot print_timing: id 1 | task 6924 | n_gen = 100, tg = 20.55 t/s, tg_3s = 20.75 t/s 8.06.316.857 I slot print_timing: id 3 | task 6066 | n_gen = 948, tg = 20.01 t/s, tg_3s = 19.71 t/s 8.06.900.649 I slot print_timing: id 0 | task 6820 | n_gen = 218, tg = 19.97 t/s, tg_3s = 19.73 t/s 8.07.988.851 I slot print_timing: id 1 | task 6924 | prompt eval time = 453.16 ms / 103 tokens ( 4.40 ms per token, 227.29 tokens per second) 8.07.988.857 I slot print_timing: id 1 | task 6924 | eval time = 6629.15 ms / 140 tokens ( 47.69 ms per token, 20.97 tokens per second) 8.07.988.858 I slot print_timing: id 1 | task 6924 | total time = 7082.32 ms / 243 tokens 8.07.988.859 I slot print_timing: id 1 | task 6924 | graphs reused = 6027 8.07.988.861 I slot print_timing: id 1 | task 6924 | graph reallocs = 0 / 0 (same size) / (changed size) 8.07.988.919 I slot release: id 1 | task 6924 | stop processing: n_tokens = 1357, truncated = 0 8.08.058.396 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.822 8.08.058.427 I slot launch_slot_: id 1 | task 7068 | processing task, is_child = 0 8.09.353.123 I slot print_timing: id 3 | task 6066 | n_gen = 1006, tg = 19.95 t/s, tg_3s = 19.10 t/s 8.09.487.688 I slot print_timing: id 2 | task 6989 | n_gen = 100, tg = 20.18 t/s, tg_3s = 20.39 t/s 8.09.529.938 I slot print_timing: id 0 | task 6820 | prompt eval time = 455.21 ms / 142 tokens ( 3.21 ms per token, 311.94 tokens per second) 8.09.529.945 I slot print_timing: id 0 | task 6820 | eval time = 13498.28 ms / 267 tokens ( 50.75 ms per token, 19.71 tokens per second) 8.09.529.945 I slot print_timing: id 0 | task 6820 | total time = 13953.49 ms / 409 tokens 8.09.529.946 I slot print_timing: id 0 | task 6820 | graphs reused = 6048 8.09.529.947 I slot print_timing: id 0 | task 6820 | graph reallocs = 0 / 0 (same size) / (changed size) 8.09.530.009 I slot release: id 0 | task 6820 | stop processing: n_tokens = 1523, truncated = 0 8.09.578.583 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.732 8.09.578.606 I slot launch_slot_: id 0 | task 7094 | processing task, is_child = 0 8.10.433.292 I slot print_timing: id 3 | task 6066 | prompt eval time = 336.80 ms / 82 tokens ( 4.11 ms per token, 243.47 tokens per second) 8.10.433.298 I slot print_timing: id 3 | task 6066 | eval time = 51447.18 ms / 1024 tokens ( 50.29 ms per token, 19.88 tokens per second) 8.10.433.299 I slot print_timing: id 3 | task 6066 | total time = 51783.97 ms / 1106 tokens 8.10.433.300 I slot print_timing: id 3 | task 6066 | graphs reused = 6059 8.10.433.306 I slot print_timing: id 3 | task 6066 | graph reallocs = 0 / 0 (same size) / (changed size) 8.10.433.365 I slot release: id 3 | task 6066 | stop processing: n_tokens = 2220, truncated = 0 8.10.645.083 I slot print_timing: id 2 | task 6989 | prompt eval time = 378.73 ms / 71 tokens ( 5.33 ms per token, 187.47 tokens per second) 8.10.645.090 I slot print_timing: id 2 | task 6989 | eval time = 6062.22 ms / 120 tokens ( 50.94 ms per token, 19.63 tokens per second) 8.10.645.091 I slot print_timing: id 2 | task 6989 | total time = 6440.95 ms / 191 tokens 8.10.645.091 I slot print_timing: id 2 | task 6989 | graphs reused = 6063 8.10.645.092 I slot print_timing: id 2 | task 6989 | graph reallocs = 0 / 0 (same size) / (changed size) 8.10.645.140 I slot release: id 2 | task 6989 | stop processing: n_tokens = 1305, truncated = 0 8.12.958.418 I slot print_timing: id 1 | task 7068 | n_gen = 100, tg = 22.34 t/s, tg_3s = 22.57 t/s 8.13.953.705 I slot print_timing: id 0 | task 7094 | n_gen = 100, tg = 24.53 t/s, tg_3s = 24.78 t/s 8.14.192.320 I slot print_timing: id 0 | task 7094 | prompt eval time = 339.56 ms / 71 tokens ( 4.78 ms per token, 209.10 tokens per second) 8.14.192.325 I slot print_timing: id 0 | task 7094 | eval time = 4274.15 ms / 106 tokens ( 40.71 ms per token, 24.57 tokens per second) 8.14.192.325 I slot print_timing: id 0 | task 7094 | total time = 4613.70 ms / 177 tokens 8.14.192.326 I slot print_timing: id 0 | task 7094 | graphs reused = 6150 8.14.192.327 I slot print_timing: id 0 | task 7094 | graph reallocs = 0 / 0 (same size) / (changed size) 8.14.192.380 I slot release: id 0 | task 7094 | stop processing: n_tokens = 1291, truncated = 0 8.15.970.947 I slot print_timing: id 1 | task 7068 | n_gen = 201, tg = 26.87 t/s, tg_3s = 33.53 t/s 8.16.300.154 I slot print_timing: id 1 | task 7068 | prompt eval time = 468.61 ms / 117 tokens ( 4.01 ms per token, 249.68 tokens per second) 8.16.300.160 I slot print_timing: id 1 | task 7068 | eval time = 7773.11 ms / 214 tokens ( 36.49 ms per token, 27.40 tokens per second) 8.16.300.161 I slot print_timing: id 1 | task 7068 | total time = 8241.72 ms / 331 tokens 8.16.300.162 I slot print_timing: id 1 | task 7068 | graphs reused = 6231 8.16.300.162 I slot print_timing: id 1 | task 7068 | graph reallocs = 0 / 0 (same size) / (changed size) 8.16.300.222 I slot release: id 1 | task 7068 | stop processing: n_tokens = 1445, truncated = 0 8.16.318.713 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2220, t_last = 324114630908 8.16.350.313 I slot launch_slot_: id 3 | task 7285 | processing task, is_child = 0 8.16.421.775 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1305, t_last = 324114842683 8.16.422.494 I slot launch_slot_: id 2 | task 7286 | processing task, is_child = 0 8.16.422.665 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1291, t_last = 324118389923 8.16.423.374 I slot launch_slot_: id 0 | task 7287 | processing task, is_child = 0 8.16.423.467 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1445, t_last = 324120497765 8.16.424.166 I slot launch_slot_: id 1 | task 7288 | processing task, is_child = 0 8.22.307.687 I slot print_timing: id 0 | task 7287 | prompt processing, n_tokens = 865, progress = 0.89, t = 5.88 s / 147.02 tokens per second 8.22.450.228 I slot print_timing: id 1 | task 7288 | prompt processing, n_tokens = 842, progress = 0.88, t = 5.88 s / 143.11 tokens per second 8.22.453.939 I slot print_timing: id 2 | task 7286 | prompt processing, n_tokens = 616, progress = 0.79, t = 5.88 s / 104.70 tokens per second 8.22.455.655 I slot print_timing: id 3 | task 7285 | prompt processing, n_tokens = 642, progress = 0.84, t = 5.88 s / 109.12 tokens per second 8.23.508.072 I slot print_timing: id 0 | task 7287 | prompt processing, n_tokens = 972, progress = 1.00, t = 7.08 s / 137.21 tokens per second 8.23.652.238 I slot print_timing: id 1 | task 7288 | prompt processing, n_tokens = 955, progress = 1.00, t = 7.08 s / 134.81 tokens per second 8.23.655.566 I slot print_timing: id 2 | task 7286 | prompt processing, n_tokens = 774, progress = 0.99, t = 7.08 s / 109.26 tokens per second 8.23.657.611 I slot print_timing: id 3 | task 7285 | prompt processing, n_tokens = 762, progress = 0.99, t = 7.08 s / 107.57 tokens per second 8.23.789.953 I slot print_timing: id 0 | task 7287 | prompt eval time = 7322.26 ms / 976 tokens ( 7.50 ms per token, 133.29 tokens per second) 8.23.789.956 I slot print_timing: id 0 | task 7287 | eval time = 43.52 ms / 2 tokens ( 43.52 ms per token, 22.98 tokens per second) 8.23.789.956 I slot print_timing: id 0 | task 7287 | total time = 7365.77 ms / 978 tokens 8.23.789.957 I slot print_timing: id 0 | task 7287 | graphs reused = 6232 8.23.789.957 I slot print_timing: id 0 | task 7287 | graph reallocs = 0 / 0 (same size) / (changed size) 8.23.790.009 I slot release: id 0 | task 7287 | stop processing: n_tokens = 986, truncated = 0 8.23.791.109 I slot print_timing: id 1 | task 7288 | prompt eval time = 7323.35 ms / 959 tokens ( 7.64 ms per token, 130.95 tokens per second) 8.23.791.110 I slot print_timing: id 1 | task 7288 | eval time = 43.50 ms / 2 tokens ( 43.50 ms per token, 22.99 tokens per second) 8.23.791.111 I slot print_timing: id 1 | task 7288 | total time = 7366.86 ms / 961 tokens 8.23.791.111 I slot print_timing: id 1 | task 7288 | graphs reused = 6232 8.23.791.111 I slot print_timing: id 1 | task 7288 | graph reallocs = 0 / 0 (same size) / (changed size) 8.23.791.143 I slot release: id 1 | task 7288 | stop processing: n_tokens = 969, truncated = 0 8.23.792.239 I slot print_timing: id 2 | task 7286 | prompt eval time = 7324.39 ms / 778 tokens ( 9.41 ms per token, 106.22 tokens per second) 8.23.792.244 I slot print_timing: id 2 | task 7286 | eval time = 43.54 ms / 2 tokens ( 43.54 ms per token, 22.97 tokens per second) 8.23.792.245 I slot print_timing: id 2 | task 7286 | total time = 7367.93 ms / 780 tokens 8.23.792.245 I slot print_timing: id 2 | task 7286 | graphs reused = 6232 8.23.792.245 I slot print_timing: id 2 | task 7286 | graph reallocs = 0 / 0 (same size) / (changed size) 8.23.792.276 I slot release: id 2 | task 7286 | stop processing: n_tokens = 788, truncated = 0 8.23.793.370 I slot print_timing: id 3 | task 7285 | prompt eval time = 7325.41 ms / 766 tokens ( 9.56 ms per token, 104.57 tokens per second) 8.23.793.372 I slot print_timing: id 3 | task 7285 | eval time = 43.60 ms / 2 tokens ( 43.60 ms per token, 22.94 tokens per second) 8.23.793.372 I slot print_timing: id 3 | task 7285 | total time = 7369.01 ms / 768 tokens 8.23.793.373 I slot print_timing: id 3 | task 7285 | graphs reused = 6232 8.23.793.373 I slot print_timing: id 3 | task 7285 | graph reallocs = 0 / 0 (same size) / (changed size) 8.23.793.391 I slot release: id 3 | task 7285 | stop processing: n_tokens = 776, truncated = 0 8.23.798.055 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 324127987552 8.23.812.390 I slot launch_slot_: id 0 | task 7294 | processing task, is_child = 0 8.23.867.130 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 969, t_last = 324127988686 8.23.867.281 I slot launch_slot_: id 1 | task 7295 | processing task, is_child = 0 8.23.867.405 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 788, t_last = 324127989819 8.23.867.502 I slot launch_slot_: id 2 | task 7296 | processing task, is_child = 0 8.23.867.568 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 776, t_last = 324127990935 8.23.867.662 I slot launch_slot_: id 3 | task 7297 | processing task, is_child = 0 8.29.292.001 I slot print_timing: id 0 | task 7294 | prompt processing, n_tokens = 690, progress = 0.87, t = 5.42 s / 127.20 tokens per second 8.29.325.748 I slot print_timing: id 1 | task 7295 | prompt processing, n_tokens = 690, progress = 0.87, t = 5.42 s / 127.21 tokens per second 8.29.329.451 I slot print_timing: id 2 | task 7296 | prompt processing, n_tokens = 690, progress = 0.82, t = 5.42 s / 127.21 tokens per second 8.29.331.313 I slot print_timing: id 3 | task 7297 | prompt processing, n_tokens = 690, progress = 0.81, t = 5.42 s / 127.22 tokens per second 8.30.395.126 I slot print_timing: id 0 | task 7294 | prompt processing, n_tokens = 792, progress = 1.00, t = 6.53 s / 121.33 tokens per second 8.30.432.494 I slot print_timing: id 1 | task 7295 | prompt processing, n_tokens = 794, progress = 1.00, t = 6.53 s / 121.64 tokens per second 8.30.435.552 I slot print_timing: id 2 | task 7296 | prompt processing, n_tokens = 837, progress = 1.00, t = 6.53 s / 128.24 tokens per second 8.30.437.294 I slot print_timing: id 3 | task 7297 | prompt processing, n_tokens = 845, progress = 1.00, t = 6.53 s / 129.46 tokens per second 8.30.569.483 I slot print_timing: id 0 | task 7294 | prompt eval time = 6658.35 ms / 796 tokens ( 8.36 ms per token, 119.55 tokens per second) 8.30.569.486 I slot print_timing: id 0 | task 7294 | eval time = 43.46 ms / 2 tokens ( 43.46 ms per token, 23.01 tokens per second) 8.30.569.486 I slot print_timing: id 0 | task 7294 | total time = 6701.81 ms / 798 tokens 8.30.569.487 I slot print_timing: id 0 | task 7294 | graphs reused = 6232 8.30.569.487 I slot print_timing: id 0 | task 7294 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.569.522 I slot release: id 0 | task 7294 | stop processing: n_tokens = 806, truncated = 0 8.30.570.627 I slot print_timing: id 1 | task 7295 | prompt eval time = 6659.26 ms / 798 tokens ( 8.34 ms per token, 119.83 tokens per second) 8.30.570.628 I slot print_timing: id 1 | task 7295 | eval time = 43.48 ms / 2 tokens ( 43.48 ms per token, 23.00 tokens per second) 8.30.570.628 I slot print_timing: id 1 | task 7295 | total time = 6702.74 ms / 800 tokens 8.30.570.629 I slot print_timing: id 1 | task 7295 | graphs reused = 6232 8.30.570.629 I slot print_timing: id 1 | task 7295 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.570.651 I slot release: id 1 | task 7295 | stop processing: n_tokens = 808, truncated = 0 8.30.571.749 I slot print_timing: id 2 | task 7296 | prompt eval time = 6660.24 ms / 841 tokens ( 7.92 ms per token, 126.27 tokens per second) 8.30.571.750 I slot print_timing: id 2 | task 7296 | eval time = 43.44 ms / 2 tokens ( 43.44 ms per token, 23.02 tokens per second) 8.30.571.750 I slot print_timing: id 2 | task 7296 | total time = 6703.68 ms / 843 tokens 8.30.571.751 I slot print_timing: id 2 | task 7296 | graphs reused = 6232 8.30.571.751 I slot print_timing: id 2 | task 7296 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.571.783 I slot release: id 2 | task 7296 | stop processing: n_tokens = 851, truncated = 0 8.30.572.864 I slot print_timing: id 3 | task 7297 | prompt eval time = 6661.25 ms / 849 tokens ( 7.85 ms per token, 127.45 tokens per second) 8.30.572.866 I slot print_timing: id 3 | task 7297 | eval time = 43.40 ms / 2 tokens ( 43.40 ms per token, 23.04 tokens per second) 8.30.572.866 I slot print_timing: id 3 | task 7297 | total time = 6704.65 ms / 851 tokens 8.30.572.866 I slot print_timing: id 3 | task 7297 | graphs reused = 6232 8.30.572.867 I slot print_timing: id 3 | task 7297 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.572.886 I slot release: id 3 | task 7297 | stop processing: n_tokens = 859, truncated = 0 8.30.577.368 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 8.30.577.435 I slot launch_slot_: id 0 | task 7303 | processing task, is_child = 0 8.30.638.535 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 808, t_last = 324134768194 8.30.638.689 I slot launch_slot_: id 1 | task 7304 | processing task, is_child = 0 8.30.638.838 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 851, t_last = 324134769326 8.30.638.940 I slot launch_slot_: id 2 | task 7305 | processing task, is_child = 0 8.30.639.010 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 859, t_last = 324134770429 8.30.639.120 I slot launch_slot_: id 3 | task 7306 | processing task, is_child = 0 8.35.607.678 I slot print_timing: id 1 | task 7304 | prompt processing, n_tokens = 739, progress = 0.85, t = 4.96 s / 148.90 tokens per second 8.35.615.186 I slot print_timing: id 2 | task 7305 | prompt processing, n_tokens = 739, progress = 0.84, t = 4.96 s / 148.90 tokens per second 8.35.619.400 I slot print_timing: id 3 | task 7306 | prompt processing, n_tokens = 817, progress = 0.86, t = 4.96 s / 164.62 tokens per second 8.36.491.165 I slot print_timing: id 0 | task 7303 | prompt eval time = 4968.47 ms / 105 tokens ( 47.32 ms per token, 21.13 tokens per second) 8.36.491.175 I slot print_timing: id 0 | task 7303 | eval time = 883.55 ms / 2 tokens ( 883.55 ms per token, 1.13 tokens per second) 8.36.491.176 I slot print_timing: id 0 | task 7303 | total time = 5852.03 ms / 107 tokens 8.36.491.177 I slot print_timing: id 0 | task 7303 | graphs reused = 6232 8.36.491.178 I slot print_timing: id 0 | task 7303 | graph reallocs = 0 / 0 (same size) / (changed size) 8.36.491.290 I slot release: id 0 | task 7303 | stop processing: n_tokens = 832, truncated = 0 8.36.491.316 I slot print_timing: id 1 | task 7304 | prompt processing, n_tokens = 864, progress = 1.00, t = 5.85 s / 147.76 tokens per second 8.36.495.670 I slot print_timing: id 2 | task 7305 | prompt processing, n_tokens = 874, progress = 1.00, t = 5.85 s / 149.48 tokens per second 8.36.499.538 I slot print_timing: id 3 | task 7306 | prompt processing, n_tokens = 945, progress = 1.00, t = 5.85 s / 161.62 tokens per second 8.36.599.923 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 832, t_last = 324140688833 8.36.637.141 I slot launch_slot_: id 0 | task 7311 | processing task, is_child = 0 8.37.572.385 I slot print_timing: id 1 | task 7304 | prompt eval time = 5954.88 ms / 868 tokens ( 6.86 ms per token, 145.76 tokens per second) 8.37.572.396 I slot print_timing: id 1 | task 7304 | eval time = 976.66 ms / 2 tokens ( 976.66 ms per token, 1.02 tokens per second) 8.37.572.397 I slot print_timing: id 1 | task 7304 | total time = 6931.54 ms / 870 tokens 8.37.572.398 I slot print_timing: id 1 | task 7304 | graphs reused = 6232 8.37.572.398 I slot print_timing: id 1 | task 7304 | graph reallocs = 0 / 0 (same size) / (changed size) 8.37.572.472 I slot release: id 1 | task 7304 | stop processing: n_tokens = 878, truncated = 0 8.37.573.633 I slot print_timing: id 2 | task 7305 | prompt eval time = 5956.80 ms / 878 tokens ( 6.78 ms per token, 147.39 tokens per second) 8.37.573.635 I slot print_timing: id 2 | task 7305 | eval time = 975.81 ms / 2 tokens ( 975.81 ms per token, 1.02 tokens per second) 8.37.573.636 I slot print_timing: id 2 | task 7305 | total time = 6932.61 ms / 880 tokens 8.37.573.636 I slot print_timing: id 2 | task 7305 | graphs reused = 6232 8.37.573.636 I slot print_timing: id 2 | task 7305 | graph reallocs = 0 / 0 (same size) / (changed size) 8.37.573.669 I slot release: id 2 | task 7305 | stop processing: n_tokens = 888, truncated = 0 8.37.574.856 I slot print_timing: id 3 | task 7306 | prompt eval time = 5958.73 ms / 949 tokens ( 6.28 ms per token, 159.26 tokens per second) 8.37.574.858 I slot print_timing: id 3 | task 7306 | eval time = 974.94 ms / 2 tokens ( 974.94 ms per token, 1.03 tokens per second) 8.37.574.858 I slot print_timing: id 3 | task 7306 | total time = 6933.67 ms / 951 tokens 8.37.574.858 I slot print_timing: id 3 | task 7306 | graphs reused = 6232 8.37.574.859 I slot print_timing: id 3 | task 7306 | graph reallocs = 0 / 0 (same size) / (changed size) 8.37.574.896 I slot release: id 3 | task 7306 | stop processing: n_tokens = 959, truncated = 0 8.38.388.535 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 878, t_last = 324141770015 8.38.388.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.306 MiB) 8.38.388.663 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.151 MiB) 8.38.388.667 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.216 MiB) 8.38.388.671 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.247 MiB) 8.38.660.227 I slot launch_slot_: id 1 | task 7315 | processing task, is_child = 0 8.38.660.310 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.770 MiB) 8.38.660.317 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 49.228 MiB) 8.38.660.320 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.631 MiB) 8.38.660.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.614 MiB) 8.38.660.325 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.524 MiB) 8.38.684.971 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.461 MiB) 8.38.684.976 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.508 MiB) 8.38.684.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 51.690 MiB) 8.38.684.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.490 MiB) 8.38.684.985 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.922 MiB) 8.38.684.988 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.431 MiB) 8.38.707.613 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 888, t_last = 324141771212 8.38.707.772 I slot launch_slot_: id 2 | task 7316 | processing task, is_child = 0 8.38.707.842 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 959, t_last = 324141772439 8.38.707.949 I slot launch_slot_: id 3 | task 7317 | processing task, is_child = 0 8.42.026.453 I slot print_timing: id 1 | task 7315 | prompt processing, n_tokens = 507, progress = 0.50, t = 3.31 s / 153.19 tokens per second 8.42.030.196 I slot print_timing: id 2 | task 7316 | prompt processing, n_tokens = 402, progress = 0.44, t = 3.31 s / 121.47 tokens per second 8.42.032.051 I slot print_timing: id 3 | task 7317 | prompt processing, n_tokens = 747, progress = 0.42, t = 3.31 s / 225.74 tokens per second 8.44.686.954 I slot print_timing: id 0 | task 7311 | prompt eval time = 5389.27 ms / 988 tokens ( 5.45 ms per token, 183.33 tokens per second) 8.44.686.961 I slot print_timing: id 0 | task 7311 | eval time = 2660.51 ms / 2 tokens ( 2660.51 ms per token, 0.38 tokens per second) 8.44.686.961 I slot print_timing: id 0 | task 7311 | total time = 8049.78 ms / 990 tokens 8.44.686.962 I slot print_timing: id 0 | task 7311 | graphs reused = 6232 8.44.686.962 I slot print_timing: id 0 | task 7311 | graph reallocs = 0 / 0 (same size) / (changed size) 8.44.687.035 I slot release: id 0 | task 7311 | stop processing: n_tokens = 998, truncated = 0 8.44.687.064 I slot print_timing: id 1 | task 7315 | prompt processing, n_tokens = 871, progress = 0.85, t = 5.97 s / 145.90 tokens per second 8.44.689.740 I slot print_timing: id 2 | task 7316 | prompt processing, n_tokens = 747, progress = 0.82, t = 5.97 s / 125.13 tokens per second 8.44.691.729 I slot print_timing: id 3 | task 7317 | prompt processing, n_tokens = 1294, progress = 0.72, t = 5.97 s / 216.76 tokens per second 8.45.739.688 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 998, t_last = 324148884578 8.45.739.819 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.029 MiB) 8.45.739.823 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.493 MiB) 8.45.739.826 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.798 MiB) 8.45.739.829 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.321 MiB) 8.45.739.831 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.923 MiB) 8.45.739.833 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.185 MiB) 8.46.463.456 I slot launch_slot_: id 0 | task 7321 | processing task, is_child = 0 8.46.464.001 I slot print_timing: id 1 | task 7315 | prompt processing, n_tokens = 1019, progress = 1.00, t = 7.02 s / 145.08 tokens per second 8.46.468.268 I slot print_timing: id 2 | task 7316 | prompt processing, n_tokens = 914, progress = 1.00, t = 7.02 s / 130.13 tokens per second 8.46.472.196 I slot print_timing: id 3 | task 7317 | prompt processing, n_tokens = 1806, progress = 1.00, t = 7.02 s / 257.14 tokens per second 8.48.087.891 I slot print_timing: id 1 | task 7315 | prompt eval time = 8627.87 ms / 1023 tokens ( 8.43 ms per token, 118.57 tokens per second) 8.48.087.906 I slot print_timing: id 1 | task 7315 | eval time = 744.19 ms / 2 tokens ( 744.19 ms per token, 1.34 tokens per second) 8.48.087.907 I slot print_timing: id 1 | task 7315 | total time = 9372.06 ms / 1025 tokens 8.48.087.909 I slot print_timing: id 1 | task 7315 | graphs reused = 6232 8.48.087.910 I slot print_timing: id 1 | task 7315 | graph reallocs = 0 / 0 (same size) / (changed size) 8.48.088.056 I slot release: id 1 | task 7315 | stop processing: n_tokens = 1033, truncated = 0 8.48.090.223 I slot print_timing: id 2 | task 7316 | prompt eval time = 8629.88 ms / 918 tokens ( 9.40 ms per token, 106.37 tokens per second) 8.48.090.228 I slot print_timing: id 2 | task 7316 | eval time = 744.34 ms / 2 tokens ( 744.34 ms per token, 1.34 tokens per second) 8.48.090.232 I slot print_timing: id 2 | task 7316 | total time = 9374.23 ms / 920 tokens 8.48.090.233 I slot print_timing: id 2 | task 7316 | graphs reused = 6232 8.48.090.234 I slot print_timing: id 2 | task 7316 | graph reallocs = 0 / 0 (same size) / (changed size) 8.48.090.344 I slot release: id 2 | task 7316 | stop processing: n_tokens = 928, truncated = 0 8.48.093.484 I slot print_timing: id 3 | task 7317 | prompt eval time = 8631.77 ms / 1810 tokens ( 4.77 ms per token, 209.69 tokens per second) 8.48.093.497 I slot print_timing: id 3 | task 7317 | eval time = 745.53 ms / 2 tokens ( 745.53 ms per token, 1.34 tokens per second) 8.48.093.498 I slot print_timing: id 3 | task 7317 | total time = 9377.30 ms / 1812 tokens 8.48.093.500 I slot print_timing: id 3 | task 7317 | graphs reused = 6232 8.48.093.501 I slot print_timing: id 3 | task 7317 | graph reallocs = 0 / 0 (same size) / (changed size) 8.48.093.675 I slot release: id 3 | task 7317 | stop processing: n_tokens = 1820, truncated = 0 8.48.113.530 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1033, t_last = 324152285599 8.48.113.672 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.614 MiB) 8.48.113.679 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.508 MiB) 8.48.113.683 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 8.48.113.686 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.414 MiB) 8.48.113.689 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.215 MiB) 8.48.113.738 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 47.154 MiB) 8.48.524.902 I slot launch_slot_: id 1 | task 7325 | processing task, is_child = 0 8.48.525.111 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.735 MiB) 8.48.525.562 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.877 MiB) 8.48.526.125 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.629 MiB) 8.48.526.831 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.814 MiB) 8.48.527.361 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.829 MiB) 8.48.564.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.445 MiB) 8.48.564.880 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 51.092 MiB) 8.48.565.426 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.278 MiB) 8.48.565.846 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 38.539 MiB) 8.48.566.247 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 47.154 MiB) 8.48.566.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.954 MiB) 8.48.591.993 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 324152287887 8.48.592.177 I slot launch_slot_: id 2 | task 7326 | processing task, is_child = 0 8.48.592.296 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1820, t_last = 324152291219 8.48.592.457 I slot launch_slot_: id 3 | task 7327 | processing task, is_child = 0 8.52.636.982 I slot print_timing: id 0 | task 7321 | prompt eval time = 3718.64 ms / 934 tokens ( 3.98 ms per token, 251.17 tokens per second) 8.52.636.993 I slot print_timing: id 0 | task 7321 | eval time = 2454.82 ms / 2 tokens ( 2454.82 ms per token, 0.41 tokens per second) 8.52.636.995 I slot print_timing: id 0 | task 7321 | total time = 6173.46 ms / 936 tokens 8.52.636.996 I slot print_timing: id 0 | task 7321 | graphs reused = 6233 8.52.636.997 I slot print_timing: id 0 | task 7321 | graph reallocs = 0 / 0 (same size) / (changed size) 8.52.637.165 I slot release: id 0 | task 7321 | stop processing: n_tokens = 944, truncated = 0 8.52.637.228 I slot print_timing: id 1 | task 7325 | prompt processing, n_tokens = 590, progress = 0.84, t = 4.03 s / 146.33 tokens per second 8.52.644.621 I slot print_timing: id 2 | task 7326 | prompt processing, n_tokens = 590, progress = 0.81, t = 4.03 s / 146.36 tokens per second 8.52.648.529 I slot print_timing: id 3 | task 7327 | prompt processing, n_tokens = 759, progress = 0.87, t = 4.03 s / 188.32 tokens per second 8.53.327.547 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 944, t_last = 324156834708 8.53.327.732 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.660 MiB) 8.53.327.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.907 MiB) 8.53.327.746 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.430 MiB) 8.53.327.750 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.982 MiB) 8.53.328.494 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 49.123 MiB) 8.53.329.169 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 8.53.419.697 I slot launch_slot_: id 0 | task 7331 | processing task, is_child = 0 8.53.420.189 I slot print_timing: id 1 | task 7325 | prompt processing, n_tokens = 696, progress = 0.99, t = 4.73 s / 147.26 tokens per second 8.53.424.049 I slot print_timing: id 2 | task 7326 | prompt processing, n_tokens = 724, progress = 0.99, t = 4.73 s / 153.21 tokens per second 8.53.427.880 I slot print_timing: id 3 | task 7327 | prompt processing, n_tokens = 868, progress = 1.00, t = 4.72 s / 183.72 tokens per second 8.54.722.729 I slot print_timing: id 1 | task 7325 | prompt eval time = 5288.85 ms / 700 tokens ( 7.56 ms per token, 132.35 tokens per second) 8.54.722.735 I slot print_timing: id 1 | task 7325 | eval time = 832.65 ms / 2 tokens ( 832.65 ms per token, 1.20 tokens per second) 8.54.722.736 I slot print_timing: id 1 | task 7325 | total time = 6121.50 ms / 702 tokens 8.54.722.737 I slot print_timing: id 1 | task 7325 | graphs reused = 6233 8.54.722.737 I slot print_timing: id 1 | task 7325 | graph reallocs = 0 / 0 (same size) / (changed size) 8.54.722.774 I slot release: id 1 | task 7325 | stop processing: n_tokens = 710, truncated = 0 8.54.723.868 I slot print_timing: id 2 | task 7326 | prompt eval time = 5289.21 ms / 728 tokens ( 7.27 ms per token, 137.64 tokens per second) 8.54.723.870 I slot print_timing: id 2 | task 7326 | eval time = 832.51 ms / 2 tokens ( 832.51 ms per token, 1.20 tokens per second) 8.54.723.870 I slot print_timing: id 2 | task 7326 | total time = 6121.72 ms / 730 tokens 8.54.723.871 I slot print_timing: id 2 | task 7326 | graphs reused = 6233 8.54.723.871 I slot print_timing: id 2 | task 7326 | graph reallocs = 0 / 0 (same size) / (changed size) 8.54.723.907 I slot release: id 2 | task 7326 | stop processing: n_tokens = 738, truncated = 0 8.54.725.056 I slot print_timing: id 3 | task 7327 | prompt eval time = 5289.62 ms / 872 tokens ( 6.07 ms per token, 164.85 tokens per second) 8.54.725.058 I slot print_timing: id 3 | task 7327 | eval time = 832.53 ms / 2 tokens ( 832.53 ms per token, 1.20 tokens per second) 8.54.725.059 I slot print_timing: id 3 | task 7327 | total time = 6122.15 ms / 874 tokens 8.54.725.059 I slot print_timing: id 3 | task 7327 | graphs reused = 6233 8.54.725.059 I slot print_timing: id 3 | task 7327 | graph reallocs = 0 / 0 (same size) / (changed size) 8.54.725.099 I slot release: id 3 | task 7327 | stop processing: n_tokens = 882, truncated = 0 8.55.032.340 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.882 8.55.032.420 I slot launch_slot_: id 1 | task 7336 | processing task, is_child = 0 8.55.032.506 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 47.752 MiB) 8.55.032.509 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 8.55.032.512 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.278 MiB) 8.55.032.637 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.184 MiB) 8.55.033.038 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.430 MiB) 8.55.033.376 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.184 MiB) 8.55.047.995 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.784 MiB) 8.55.048.157 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.321 MiB) 8.55.048.419 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 8.55.048.766 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.521 MiB) 8.55.049.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.568 MiB) 8.55.064.271 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.848 8.55.064.340 I slot launch_slot_: id 2 | task 7337 | processing task, is_child = 0 8.55.064.410 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 324158922642 8.55.064.510 I slot launch_slot_: id 3 | task 7338 | processing task, is_child = 0 8.56.225.164 I slot print_timing: id 0 | task 7331 | prompt eval time = 1612.62 ms / 703 tokens ( 2.29 ms per token, 435.94 tokens per second) 8.56.225.168 I slot print_timing: id 0 | task 7331 | eval time = 1192.83 ms / 2 tokens ( 1192.83 ms per token, 0.84 tokens per second) 8.56.225.169 I slot print_timing: id 0 | task 7331 | total time = 2805.44 ms / 705 tokens 8.56.225.170 I slot print_timing: id 0 | task 7331 | graphs reused = 6233 8.56.225.170 I slot print_timing: id 0 | task 7331 | graph reallocs = 0 / 0 (same size) / (changed size) 8.56.225.234 I slot release: id 0 | task 7331 | stop processing: n_tokens = 713, truncated = 0 8.57.113.610 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 713, t_last = 324160422777 8.57.113.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.753 MiB) 8.57.113.720 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.507 MiB) 8.57.114.022 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 8.57.114.462 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.507 MiB) 8.57.114.810 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.231 MiB) 8.57.115.231 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.999 MiB) 8.57.131.006 I slot launch_slot_: id 0 | task 7341 | processing task, is_child = 0 8.58.326.772 I slot print_timing: id 1 | task 7336 | prompt eval time = 2047.90 ms / 89 tokens ( 23.01 ms per token, 43.46 tokens per second) 8.58.326.775 I slot print_timing: id 1 | task 7336 | eval time = 1214.35 ms / 2 tokens ( 1214.35 ms per token, 0.82 tokens per second) 8.58.326.776 I slot print_timing: id 1 | task 7336 | total time = 3262.25 ms / 91 tokens 8.58.326.776 I slot print_timing: id 1 | task 7336 | graphs reused = 6233 8.58.326.777 I slot print_timing: id 1 | task 7336 | graph reallocs = 0 / 0 (same size) / (changed size) 8.58.326.819 I slot release: id 1 | task 7336 | stop processing: n_tokens = 716, truncated = 0 8.58.327.964 I slot print_timing: id 2 | task 7337 | prompt eval time = 2047.41 ms / 95 tokens ( 21.55 ms per token, 46.40 tokens per second) 8.58.327.967 I slot print_timing: id 2 | task 7337 | eval time = 1214.36 ms / 2 tokens ( 1214.36 ms per token, 0.82 tokens per second) 8.58.327.968 I slot print_timing: id 2 | task 7337 | total time = 3261.77 ms / 97 tokens 8.58.327.968 I slot print_timing: id 2 | task 7337 | graphs reused = 6233 8.58.327.968 I slot print_timing: id 2 | task 7337 | graph reallocs = 0 / 0 (same size) / (changed size) 8.58.328.003 I slot release: id 2 | task 7337 | stop processing: n_tokens = 722, truncated = 0 8.58.330.853 I slot print_timing: id 3 | task 7338 | prompt processing, n_tokens = 860, progress = 1.00, t = 3.26 s / 263.98 tokens per second 8.59.176.674 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 716, t_last = 324162524362 8.59.176.798 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.063 MiB) 8.59.176.804 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 8.59.177.385 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 33.863 MiB) 8.59.177.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.923 MiB) 8.59.178.388 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.216 MiB) 8.59.178.761 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.324 MiB) 8.59.179.049 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.015 MiB) 8.59.197.594 I slot launch_slot_: id 1 | task 7344 | processing task, is_child = 0 8.59.197.667 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.354 MiB) 8.59.197.827 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.368 MiB) 8.59.198.128 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.231 MiB) 8.59.198.350 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.801 MiB) 8.59.198.605 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 32.879 MiB) 8.59.198.814 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.461 MiB) 8.59.199.113 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.216 MiB) 8.59.216.900 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 722, t_last = 324162525546 8.59.217.043 I slot launch_slot_: id 2 | task 7345 | processing task, is_child = 0 9.01.407.274 I slot print_timing: id 3 | task 7338 | prompt eval time = 4108.81 ms / 864 tokens ( 4.76 ms per token, 210.28 tokens per second) 9.01.407.278 I slot print_timing: id 3 | task 7338 | eval time = 2230.60 ms / 2 tokens ( 2230.60 ms per token, 0.45 tokens per second) 9.01.407.278 I slot print_timing: id 3 | task 7338 | total time = 6339.41 ms / 866 tokens 9.01.407.279 I slot print_timing: id 3 | task 7338 | graphs reused = 6233 9.01.407.279 I slot print_timing: id 3 | task 7338 | graph reallocs = 0 / 0 (same size) / (changed size) 9.01.407.349 I slot release: id 3 | task 7338 | stop processing: n_tokens = 874, truncated = 0 9.01.407.388 I slot print_timing: id 0 | task 7341 | prompt processing, n_tokens = 977, progress = 1.00, t = 4.28 s / 228.53 tokens per second 9.02.963.859 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 874, t_last = 324165604892 9.02.964.006 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.555 MiB) 9.02.964.013 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 9.02.964.366 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.075 MiB) 9.02.964.877 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.306 MiB) 9.02.965.189 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 9.02.965.455 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.845 MiB) 9.02.976.200 I slot launch_slot_: id 3 | task 7348 | processing task, is_child = 0 9.02.976.212 I slot print_timing: id 1 | task 7344 | prompt processing, n_tokens = 850, progress = 0.86, t = 3.74 s / 227.19 tokens per second 9.02.980.545 I slot print_timing: id 2 | task 7345 | prompt processing, n_tokens = 850, progress = 0.83, t = 3.74 s / 227.22 tokens per second 9.04.649.141 I slot print_timing: id 0 | task 7341 | prompt eval time = 5832.82 ms / 981 tokens ( 5.95 ms per token, 168.19 tokens per second) 9.04.649.156 I slot print_timing: id 0 | task 7341 | eval time = 1685.26 ms / 2 tokens ( 1685.26 ms per token, 0.59 tokens per second) 9.04.649.158 I slot print_timing: id 0 | task 7341 | total time = 7518.08 ms / 983 tokens 9.04.649.160 I slot print_timing: id 0 | task 7341 | graphs reused = 6233 9.04.649.161 I slot print_timing: id 0 | task 7341 | graph reallocs = 0 / 0 (same size) / (changed size) 9.04.649.317 I slot release: id 0 | task 7341 | stop processing: n_tokens = 991, truncated = 0 9.04.649.384 I slot print_timing: id 1 | task 7344 | prompt processing, n_tokens = 991, progress = 1.00, t = 5.42 s / 182.70 tokens per second 9.04.656.925 I slot print_timing: id 2 | task 7345 | prompt processing, n_tokens = 1021, progress = 1.00, t = 5.42 s / 188.25 tokens per second 9.05.501.306 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 9.05.501.763 I slot launch_slot_: id 0 | task 7351 | processing task, is_child = 0 9.06.146.496 I slot print_timing: id 1 | task 7344 | prompt eval time = 6277.67 ms / 995 tokens ( 6.31 ms per token, 158.50 tokens per second) 9.06.146.507 I slot print_timing: id 1 | task 7344 | eval time = 647.49 ms / 2 tokens ( 647.49 ms per token, 1.54 tokens per second) 9.06.146.509 I slot print_timing: id 1 | task 7344 | total time = 6925.16 ms / 997 tokens 9.06.146.510 I slot print_timing: id 1 | task 7344 | graphs reused = 6233 9.06.146.512 I slot print_timing: id 1 | task 7344 | graph reallocs = 0 / 0 (same size) / (changed size) 9.06.146.663 I slot release: id 1 | task 7344 | stop processing: n_tokens = 1005, truncated = 0 9.06.148.902 I slot print_timing: id 2 | task 7345 | prompt eval time = 6279.38 ms / 1025 tokens ( 6.13 ms per token, 163.23 tokens per second) 9.06.148.908 I slot print_timing: id 2 | task 7345 | eval time = 647.63 ms / 2 tokens ( 647.63 ms per token, 1.54 tokens per second) 9.06.148.909 I slot print_timing: id 2 | task 7345 | total time = 6927.01 ms / 1027 tokens 9.06.148.910 I slot print_timing: id 2 | task 7345 | graphs reused = 6233 9.06.148.911 I slot print_timing: id 2 | task 7345 | graph reallocs = 0 / 0 (same size) / (changed size) 9.06.149.008 I slot release: id 2 | task 7345 | stop processing: n_tokens = 1035, truncated = 0 9.06.161.721 I slot print_timing: id 3 | task 7348 | prompt processing, n_tokens = 983, progress = 1.00, t = 3.16 s / 311.32 tokens per second 9.06.249.998 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1005, t_last = 324170344207 9.06.250.201 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.829 MiB) 9.06.250.208 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 32.738 MiB) 9.06.250.554 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.292 MiB) 9.06.251.154 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.213 MiB) 9.06.251.833 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.848 MiB) 9.06.252.386 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.894 MiB) 9.06.286.387 I slot launch_slot_: id 1 | task 7354 | processing task, is_child = 0 9.06.286.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.629 MiB) 9.06.286.805 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 35.199 MiB) 9.06.287.121 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.939 MiB) 9.06.287.408 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.461 MiB) 9.06.287.734 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.708 MiB) 9.06.288.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 38.153 MiB) 9.06.288.331 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 38.891 MiB) 9.06.310.299 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 324170346552 9.06.310.465 I slot launch_slot_: id 2 | task 7355 | processing task, is_child = 0 9.08.066.928 I slot print_timing: id 0 | task 7351 | prompt eval time = 745.65 ms / 105 tokens ( 7.10 ms per token, 140.82 tokens per second) 9.08.066.931 I slot print_timing: id 0 | task 7351 | eval time = 1819.47 ms / 2 tokens ( 1819.47 ms per token, 0.55 tokens per second) 9.08.066.932 I slot print_timing: id 0 | task 7351 | total time = 2565.12 ms / 107 tokens 9.08.066.932 I slot print_timing: id 0 | task 7351 | graphs reused = 6233 9.08.066.933 I slot print_timing: id 0 | task 7351 | graph reallocs = 0 / 0 (same size) / (changed size) 9.08.066.987 I slot release: id 0 | task 7351 | stop processing: n_tokens = 992, truncated = 0 9.08.068.085 I slot print_timing: id 3 | task 7348 | prompt eval time = 3265.20 ms / 987 tokens ( 3.31 ms per token, 302.28 tokens per second) 9.08.068.088 I slot print_timing: id 3 | task 7348 | eval time = 1818.09 ms / 2 tokens ( 1818.09 ms per token, 0.55 tokens per second) 9.08.068.088 I slot print_timing: id 3 | task 7348 | total time = 5083.29 ms / 989 tokens 9.08.068.088 I slot print_timing: id 3 | task 7348 | graphs reused = 6233 9.08.068.089 I slot print_timing: id 3 | task 7348 | graph reallocs = 0 / 0 (same size) / (changed size) 9.08.068.129 I slot release: id 3 | task 7348 | stop processing: n_tokens = 997, truncated = 0 9.09.154.172 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 992, t_last = 324172264530 9.09.154.268 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 33.969 MiB) 9.09.154.273 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.521 MiB) 9.09.154.621 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.705 MiB) 9.09.154.875 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.954 MiB) 9.09.155.166 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.414 MiB) 9.09.155.552 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.016 MiB) 9.09.155.821 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.953 MiB) 9.09.364.998 I slot launch_slot_: id 0 | task 7358 | processing task, is_child = 0 9.09.365.096 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.784 MiB) 9.09.365.100 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.038 MiB) 9.09.373.045 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 997, t_last = 324172265672 9.09.373.179 I slot launch_slot_: id 3 | task 7359 | processing task, is_child = 0 9.11.922.343 I slot print_timing: id 1 | task 7354 | prompt processing, n_tokens = 871, progress = 1.00, t = 5.12 s / 170.16 tokens per second 9.11.926.113 I slot print_timing: id 2 | task 7355 | prompt processing, n_tokens = 1010, progress = 1.00, t = 5.12 s / 197.34 tokens per second 9.13.382.390 I slot print_timing: id 0 | task 7358 | prompt processing, n_tokens = 768, progress = 0.86, t = 4.01 s / 191.67 tokens per second 9.13.384.383 I slot print_timing: id 3 | task 7359 | prompt processing, n_tokens = 768, progress = 0.77, t = 4.00 s / 191.84 tokens per second 9.14.196.520 I slot print_timing: id 1 | task 7354 | prompt eval time = 7070.79 ms / 875 tokens ( 8.08 ms per token, 123.75 tokens per second) 9.14.196.524 I slot print_timing: id 1 | task 7354 | eval time = 815.24 ms / 2 tokens ( 815.24 ms per token, 1.23 tokens per second) 9.14.196.524 I slot print_timing: id 1 | task 7354 | total time = 7886.04 ms / 877 tokens 9.14.196.525 I slot print_timing: id 1 | task 7354 | graphs reused = 6233 9.14.196.526 I slot print_timing: id 1 | task 7354 | graph reallocs = 0 / 0 (same size) / (changed size) 9.14.196.603 I slot release: id 1 | task 7354 | stop processing: n_tokens = 885, truncated = 0 9.14.197.753 I slot print_timing: id 2 | task 7355 | prompt eval time = 7071.15 ms / 1014 tokens ( 6.97 ms per token, 143.40 tokens per second) 9.14.197.761 I slot print_timing: id 2 | task 7355 | eval time = 815.38 ms / 2 tokens ( 815.38 ms per token, 1.23 tokens per second) 9.14.197.761 I slot print_timing: id 2 | task 7355 | total time = 7886.53 ms / 1016 tokens 9.14.197.761 I slot print_timing: id 2 | task 7355 | graphs reused = 6233 9.14.197.762 I slot print_timing: id 2 | task 7355 | graph reallocs = 0 / 0 (same size) / (changed size) 9.14.197.826 I slot release: id 2 | task 7355 | stop processing: n_tokens = 1024, truncated = 0 9.14.197.843 I slot print_timing: id 0 | task 7358 | prompt processing, n_tokens = 890, progress = 1.00, t = 4.82 s / 184.56 tokens per second 9.14.203.246 I slot print_timing: id 3 | task 7359 | prompt processing, n_tokens = 998, progress = 1.00, t = 4.82 s / 207.11 tokens per second 9.14.283.646 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.810 (> 0.100 thold), f_keep = 0.785 9.14.283.712 I slot launch_slot_: id 2 | task 7364 | processing task, is_child = 0 9.14.283.806 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.932 MiB) 9.14.290.227 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 885, t_last = 324178394146 9.14.290.340 I slot launch_slot_: id 1 | task 7365 | processing task, is_child = 0 9.15.516.771 I slot print_timing: id 0 | task 7358 | prompt eval time = 4909.28 ms / 894 tokens ( 5.49 ms per token, 182.10 tokens per second) 9.15.516.775 I slot print_timing: id 0 | task 7358 | eval time = 1234.28 ms / 2 tokens ( 1234.28 ms per token, 0.81 tokens per second) 9.15.516.775 I slot print_timing: id 0 | task 7358 | total time = 6143.57 ms / 896 tokens 9.15.516.776 I slot print_timing: id 0 | task 7358 | graphs reused = 6233 9.15.516.776 I slot print_timing: id 0 | task 7358 | graph reallocs = 0 / 0 (same size) / (changed size) 9.15.516.861 I slot release: id 0 | task 7358 | stop processing: n_tokens = 904, truncated = 0 9.15.518.039 I slot print_timing: id 3 | task 7359 | prompt eval time = 4906.83 ms / 1002 tokens ( 4.90 ms per token, 204.21 tokens per second) 9.15.518.041 I slot print_timing: id 3 | task 7359 | eval time = 1234.40 ms / 2 tokens ( 1234.40 ms per token, 0.81 tokens per second) 9.15.518.043 I slot print_timing: id 3 | task 7359 | total time = 6141.23 ms / 1004 tokens 9.15.518.043 I slot print_timing: id 3 | task 7359 | graphs reused = 6233 9.15.518.044 I slot print_timing: id 3 | task 7359 | graph reallocs = 0 / 0 (same size) / (changed size) 9.15.518.093 I slot release: id 3 | task 7359 | stop processing: n_tokens = 1012, truncated = 0 9.16.309.890 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 324179714404 9.16.310.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 350.111 MiB) 9.16.318.015 I slot launch_slot_: id 0 | task 7368 | processing task, is_child = 0 9.16.328.762 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.794 9.16.328.823 I slot launch_slot_: id 3 | task 7369 | processing task, is_child = 0 9.17.676.727 I slot print_timing: id 2 | task 7364 | prompt eval time = 2019.31 ms / 188 tokens ( 10.74 ms per token, 93.10 tokens per second) 9.17.676.738 I slot print_timing: id 2 | task 7364 | eval time = 1366.85 ms / 2 tokens ( 1366.85 ms per token, 0.73 tokens per second) 9.17.676.739 I slot print_timing: id 2 | task 7364 | total time = 3386.15 ms / 190 tokens 9.17.676.739 I slot print_timing: id 2 | task 7364 | graphs reused = 6233 9.17.676.740 I slot print_timing: id 2 | task 7364 | graph reallocs = 0 / 0 (same size) / (changed size) 9.17.676.854 I slot release: id 2 | task 7364 | stop processing: n_tokens = 993, truncated = 0 9.17.680.015 I slot print_timing: id 1 | task 7365 | prompt processing, n_tokens = 893, progress = 1.00, t = 3.39 s / 263.79 tokens per second 9.18.446.137 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 993, t_last = 324181874404 9.18.446.257 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.341 MiB) 9.18.455.763 I slot launch_slot_: id 2 | task 7372 | processing task, is_child = 0 9.19.630.880 I slot print_timing: id 1 | task 7365 | prompt eval time = 4154.50 ms / 897 tokens ( 4.63 ms per token, 215.91 tokens per second) 9.19.630.899 I slot print_timing: id 1 | task 7365 | eval time = 1185.99 ms / 2 tokens ( 1185.99 ms per token, 0.84 tokens per second) 9.19.630.900 I slot print_timing: id 1 | task 7365 | total time = 5340.49 ms / 899 tokens 9.19.630.902 I slot print_timing: id 1 | task 7365 | graphs reused = 6233 9.19.630.905 I slot print_timing: id 1 | task 7365 | graph reallocs = 0 / 0 (same size) / (changed size) 9.19.631.071 I slot release: id 1 | task 7365 | stop processing: n_tokens = 907, truncated = 0 9.19.633.445 I slot print_timing: id 3 | task 7369 | prompt eval time = 2115.41 ms / 81 tokens ( 26.12 ms per token, 38.29 tokens per second) 9.19.633.453 I slot print_timing: id 3 | task 7369 | eval time = 1187.30 ms / 2 tokens ( 1187.30 ms per token, 0.84 tokens per second) 9.19.633.454 I slot print_timing: id 3 | task 7369 | total time = 3302.71 ms / 83 tokens 9.19.633.455 I slot print_timing: id 3 | task 7369 | graphs reused = 6233 9.19.633.457 I slot print_timing: id 3 | task 7369 | graph reallocs = 0 / 0 (same size) / (changed size) 9.19.633.544 I slot release: id 3 | task 7369 | stop processing: n_tokens = 886, truncated = 0 9.19.633.598 I slot print_timing: id 0 | task 7368 | prompt processing, n_tokens = 927, progress = 1.00, t = 3.30 s / 281.10 tokens per second 9.20.482.492 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 907, t_last = 324183828614 9.20.482.810 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.546 MiB) 9.20.502.756 I slot launch_slot_: id 1 | task 7375 | processing task, is_child = 0 9.20.502.922 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.932 MiB) 9.20.516.147 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 886, t_last = 324183831087 9.20.516.320 I slot launch_slot_: id 3 | task 7376 | processing task, is_child = 0 9.23.259.610 I slot print_timing: id 0 | task 7368 | prompt eval time = 4153.59 ms / 931 tokens ( 4.46 ms per token, 224.14 tokens per second) 9.23.259.626 I slot print_timing: id 0 | task 7368 | eval time = 2777.14 ms / 2 tokens ( 2777.14 ms per token, 0.36 tokens per second) 9.23.259.628 I slot print_timing: id 0 | task 7368 | total time = 6930.73 ms / 933 tokens 9.23.259.630 I slot print_timing: id 0 | task 7368 | graphs reused = 6233 9.23.259.631 I slot print_timing: id 0 | task 7368 | graph reallocs = 0 / 0 (same size) / (changed size) 9.23.259.781 I slot release: id 0 | task 7368 | stop processing: n_tokens = 941, truncated = 0 9.23.265.191 I slot print_timing: id 2 | task 7372 | prompt processing, n_tokens = 880, progress = 1.00, t = 4.80 s / 183.43 tokens per second 9.24.675.469 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 324187457324 9.24.704.572 I slot launch_slot_: id 0 | task 7379 | processing task, is_child = 0 9.24.704.989 I slot print_timing: id 1 | task 7375 | prompt processing, n_tokens = 753, progress = 0.82, t = 4.16 s / 181.21 tokens per second 9.24.708.719 I slot print_timing: id 3 | task 7376 | prompt processing, n_tokens = 1148, progress = 0.85, t = 4.15 s / 276.43 tokens per second 9.27.173.564 I slot print_timing: id 2 | task 7372 | prompt eval time = 6217.97 ms / 884 tokens ( 7.03 ms per token, 142.17 tokens per second) 9.27.173.574 I slot print_timing: id 2 | task 7372 | eval time = 2498.12 ms / 2 tokens ( 2498.12 ms per token, 0.40 tokens per second) 9.27.173.575 I slot print_timing: id 2 | task 7372 | total time = 8716.09 ms / 886 tokens 9.27.173.578 I slot print_timing: id 2 | task 7372 | graphs reused = 6233 9.27.173.579 I slot print_timing: id 2 | task 7372 | graph reallocs = 0 / 0 (same size) / (changed size) 9.27.173.724 I slot release: id 2 | task 7372 | stop processing: n_tokens = 894, truncated = 0 9.27.180.707 I slot print_timing: id 1 | task 7375 | prompt processing, n_tokens = 914, progress = 1.00, t = 6.65 s / 137.37 tokens per second 9.27.184.882 I slot print_timing: id 3 | task 7376 | prompt processing, n_tokens = 1349, progress = 1.00, t = 6.65 s / 202.82 tokens per second 9.27.906.919 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 894, t_last = 324191371267 9.27.907.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 248.171 MiB) 9.27.924.700 I slot launch_slot_: id 2 | task 7382 | processing task, is_child = 0 9.27.924.730 I slot print_timing: id 0 | task 7379 | prompt processing, n_tokens = 1148, progress = 0.86, t = 3.20 s / 359.26 tokens per second 9.29.853.633 I slot print_timing: id 1 | task 7375 | prompt eval time = 7388.17 ms / 918 tokens ( 8.05 ms per token, 124.25 tokens per second) 9.29.853.645 I slot print_timing: id 1 | task 7375 | eval time = 1949.08 ms / 2 tokens ( 1949.08 ms per token, 0.51 tokens per second) 9.29.853.647 I slot print_timing: id 1 | task 7375 | total time = 9337.26 ms / 920 tokens 9.29.853.648 I slot print_timing: id 1 | task 7375 | graphs reused = 6233 9.29.853.649 I slot print_timing: id 1 | task 7375 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.853.810 I slot release: id 1 | task 7375 | stop processing: n_tokens = 928, truncated = 0 9.29.856.142 I slot print_timing: id 3 | task 7376 | prompt eval time = 7388.19 ms / 1353 tokens ( 5.46 ms per token, 183.13 tokens per second) 9.29.856.149 I slot print_timing: id 3 | task 7376 | eval time = 1949.24 ms / 2 tokens ( 1949.24 ms per token, 0.51 tokens per second) 9.29.856.150 I slot print_timing: id 3 | task 7376 | total time = 9337.43 ms / 1355 tokens 9.29.856.152 I slot print_timing: id 3 | task 7376 | graphs reused = 6233 9.29.856.153 I slot print_timing: id 3 | task 7376 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.856.294 I slot release: id 3 | task 7376 | stop processing: n_tokens = 1363, truncated = 0 9.29.856.348 I slot print_timing: id 0 | task 7379 | prompt processing, n_tokens = 1336, progress = 1.00, t = 5.14 s / 259.68 tokens per second 9.30.725.747 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 324194051353 9.30.726.275 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 245.780 MiB) 9.30.750.431 I slot launch_slot_: id 1 | task 7385 | processing task, is_child = 0 9.30.750.620 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.323 MiB) 9.30.773.682 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.869 9.30.773.763 I slot launch_slot_: id 3 | task 7386 | processing task, is_child = 0 9.31.898.893 I slot print_timing: id 0 | task 7379 | prompt eval time = 6021.08 ms / 1340 tokens ( 4.49 ms per token, 222.55 tokens per second) 9.31.898.904 I slot print_timing: id 0 | task 7379 | eval time = 1173.18 ms / 2 tokens ( 1173.18 ms per token, 0.85 tokens per second) 9.31.898.906 I slot print_timing: id 0 | task 7379 | total time = 7194.26 ms / 1342 tokens 9.31.898.907 I slot print_timing: id 0 | task 7379 | graphs reused = 6233 9.31.898.908 I slot print_timing: id 0 | task 7379 | graph reallocs = 0 / 0 (same size) / (changed size) 9.31.899.122 I slot release: id 0 | task 7379 | stop processing: n_tokens = 1350, truncated = 0 9.31.903.377 I slot print_timing: id 2 | task 7382 | prompt processing, n_tokens = 1251, progress = 1.00, t = 3.97 s / 315.40 tokens per second 9.32.796.978 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1350, t_last = 324196096665 9.32.797.330 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.635 MiB) 9.32.797.354 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 223.136 MiB) 9.32.835.076 I slot launch_slot_: id 0 | task 7389 | processing task, is_child = 0 9.33.695.157 I slot print_timing: id 2 | task 7382 | prompt eval time = 4865.91 ms / 1255 tokens ( 3.88 ms per token, 257.92 tokens per second) 9.33.695.162 I slot print_timing: id 2 | task 7382 | eval time = 900.64 ms / 2 tokens ( 900.64 ms per token, 1.11 tokens per second) 9.33.695.162 I slot print_timing: id 2 | task 7382 | total time = 5766.55 ms / 1257 tokens 9.33.695.163 I slot print_timing: id 2 | task 7382 | graphs reused = 6233 9.33.695.163 I slot print_timing: id 2 | task 7382 | graph reallocs = 0 / 0 (same size) / (changed size) 9.33.695.235 I slot release: id 2 | task 7382 | stop processing: n_tokens = 1265, truncated = 0 9.33.696.416 I slot print_timing: id 3 | task 7386 | prompt eval time = 2020.88 ms / 121 tokens ( 16.70 ms per token, 59.88 tokens per second) 9.33.696.418 I slot print_timing: id 3 | task 7386 | eval time = 899.48 ms / 2 tokens ( 899.48 ms per token, 1.11 tokens per second) 9.33.696.418 I slot print_timing: id 3 | task 7386 | total time = 2920.36 ms / 123 tokens 9.33.696.418 I slot print_timing: id 3 | task 7386 | graphs reused = 6233 9.33.696.419 I slot print_timing: id 3 | task 7386 | graph reallocs = 0 / 0 (same size) / (changed size) 9.33.696.471 I slot release: id 3 | task 7386 | stop processing: n_tokens = 1306, truncated = 0 9.34.480.168 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1265, t_last = 324197892778 9.34.480.275 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.184 MiB) 9.34.498.963 I slot launch_slot_: id 2 | task 7392 | processing task, is_child = 0 9.34.499.067 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 230.309 MiB) 9.34.520.517 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1306, t_last = 324197894014 9.34.520.664 I slot launch_slot_: id 3 | task 7393 | processing task, is_child = 0 9.36.237.145 I slot print_timing: id 1 | task 7385 | prompt eval time = 3706.39 ms / 782 tokens ( 4.74 ms per token, 210.99 tokens per second) 9.36.237.148 I slot print_timing: id 1 | task 7385 | eval time = 1756.98 ms / 2 tokens ( 1756.98 ms per token, 0.57 tokens per second) 9.36.237.149 I slot print_timing: id 1 | task 7385 | total time = 5463.37 ms / 784 tokens 9.36.237.149 I slot print_timing: id 1 | task 7385 | graphs reused = 6233 9.36.237.149 I slot print_timing: id 1 | task 7385 | graph reallocs = 0 / 0 (same size) / (changed size) 9.36.237.192 I slot release: id 1 | task 7385 | stop processing: n_tokens = 792, truncated = 0 9.36.237.211 I slot print_timing: id 0 | task 7389 | prompt processing, n_tokens = 797, progress = 1.00, t = 3.40 s / 234.35 tokens per second 9.37.798.723 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 792, t_last = 324200434735 9.37.798.870 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.776 MiB) 9.37.812.033 I slot launch_slot_: id 1 | task 7396 | processing task, is_child = 0 9.37.812.239 I slot print_timing: id 2 | task 7392 | prompt processing, n_tokens = 736, progress = 0.86, t = 3.28 s / 224.72 tokens per second 9.37.814.040 I slot print_timing: id 3 | task 7393 | prompt processing, n_tokens = 736, progress = 0.83, t = 3.27 s / 224.74 tokens per second 9.38.935.999 I slot print_timing: id 0 | task 7389 | prompt eval time = 4963.60 ms / 801 tokens ( 6.20 ms per token, 161.37 tokens per second) 9.38.936.002 I slot print_timing: id 0 | task 7389 | eval time = 1137.29 ms / 2 tokens ( 1137.29 ms per token, 0.88 tokens per second) 9.38.936.003 I slot print_timing: id 0 | task 7389 | total time = 6100.89 ms / 803 tokens 9.38.936.004 I slot print_timing: id 0 | task 7389 | graphs reused = 6233 9.38.936.004 I slot print_timing: id 0 | task 7389 | graph reallocs = 0 / 0 (same size) / (changed size) 9.38.936.050 I slot release: id 0 | task 7389 | stop processing: n_tokens = 811, truncated = 0 9.38.938.397 I slot print_timing: id 2 | task 7392 | prompt processing, n_tokens = 853, progress = 1.00, t = 4.41 s / 193.31 tokens per second 9.38.940.399 I slot print_timing: id 3 | task 7393 | prompt processing, n_tokens = 882, progress = 1.00, t = 4.41 s / 199.90 tokens per second 9.39.765.160 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 811, t_last = 324203133593 9.39.765.288 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 232.981 MiB) 9.39.775.182 I slot launch_slot_: id 0 | task 7399 | processing task, is_child = 0 9.40.802.104 I slot print_timing: id 2 | task 7392 | prompt eval time = 5241.48 ms / 857 tokens ( 6.12 ms per token, 163.50 tokens per second) 9.40.802.119 I slot print_timing: id 2 | task 7392 | eval time = 1038.20 ms / 2 tokens ( 1038.20 ms per token, 0.96 tokens per second) 9.40.802.121 I slot print_timing: id 2 | task 7392 | total time = 6279.67 ms / 859 tokens 9.40.802.123 I slot print_timing: id 2 | task 7392 | graphs reused = 6233 9.40.802.124 I slot print_timing: id 2 | task 7392 | graph reallocs = 0 / 0 (same size) / (changed size) 9.40.802.287 I slot release: id 2 | task 7392 | stop processing: n_tokens = 867, truncated = 0 9.40.804.462 I slot print_timing: id 3 | task 7393 | prompt eval time = 5242.54 ms / 886 tokens ( 5.92 ms per token, 169.00 tokens per second) 9.40.804.469 I slot print_timing: id 3 | task 7393 | eval time = 1039.30 ms / 2 tokens ( 1039.30 ms per token, 0.96 tokens per second) 9.40.804.471 I slot print_timing: id 3 | task 7393 | total time = 6281.84 ms / 888 tokens 9.40.804.472 I slot print_timing: id 3 | task 7393 | graphs reused = 6233 9.40.804.473 I slot print_timing: id 3 | task 7393 | graph reallocs = 0 / 0 (same size) / (changed size) 9.40.804.572 I slot release: id 3 | task 7393 | stop processing: n_tokens = 896, truncated = 0 9.41.480.983 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 867, t_last = 324204999830 9.41.481.299 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 234.388 MiB) 9.41.512.610 I slot launch_slot_: id 2 | task 7402 | processing task, is_child = 0 9.41.512.738 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 244.374 MiB) 9.41.534.916 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 896, t_last = 324205002115 9.41.535.052 I slot launch_slot_: id 3 | task 7403 | processing task, is_child = 0 9.42.996.348 I slot print_timing: id 1 | task 7396 | prompt eval time = 3668.89 ms / 778 tokens ( 4.72 ms per token, 212.05 tokens per second) 9.42.996.351 I slot print_timing: id 1 | task 7396 | eval time = 1515.41 ms / 2 tokens ( 1515.41 ms per token, 0.66 tokens per second) 9.42.996.351 I slot print_timing: id 1 | task 7396 | total time = 5184.29 ms / 780 tokens 9.42.996.352 I slot print_timing: id 1 | task 7396 | graphs reused = 6233 9.42.996.352 I slot print_timing: id 1 | task 7396 | graph reallocs = 0 / 0 (same size) / (changed size) 9.42.996.401 I slot release: id 1 | task 7396 | stop processing: n_tokens = 788, truncated = 0 9.42.996.416 I slot print_timing: id 0 | task 7399 | prompt processing, n_tokens = 839, progress = 1.00, t = 3.22 s / 260.56 tokens per second 9.44.608.561 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.849 (> 0.100 thold), f_keep = 0.862 9.44.608.703 I slot launch_slot_: id 1 | task 7406 | processing task, is_child = 0 9.44.612.138 I slot print_timing: id 2 | task 7402 | prompt processing, n_tokens = 643, progress = 0.85, t = 3.07 s / 209.41 tokens per second 9.44.613.974 I slot print_timing: id 3 | task 7403 | prompt processing, n_tokens = 643, progress = 0.84, t = 3.07 s / 209.43 tokens per second 9.45.412.965 I slot print_timing: id 0 | task 7399 | prompt eval time = 4833.36 ms / 843 tokens ( 5.73 ms per token, 174.41 tokens per second) 9.45.412.968 I slot print_timing: id 0 | task 7399 | eval time = 804.41 ms / 2 tokens ( 804.41 ms per token, 1.24 tokens per second) 9.45.412.969 I slot print_timing: id 0 | task 7399 | total time = 5637.77 ms / 845 tokens 9.45.412.969 I slot print_timing: id 0 | task 7399 | graphs reused = 6233 9.45.412.970 I slot print_timing: id 0 | task 7399 | graph reallocs = 0 / 0 (same size) / (changed size) 9.45.413.010 I slot release: id 0 | task 7399 | stop processing: n_tokens = 853, truncated = 0 9.45.415.230 I slot print_timing: id 2 | task 7402 | prompt processing, n_tokens = 758, progress = 0.99, t = 3.87 s / 195.62 tokens per second 9.45.417.301 I slot print_timing: id 3 | task 7403 | prompt processing, n_tokens = 764, progress = 0.99, t = 3.87 s / 197.18 tokens per second 9.45.503.285 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 853, t_last = 324209610553 9.45.503.368 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.859 MiB) 9.45.509.331 I slot launch_slot_: id 0 | task 7409 | processing task, is_child = 0 9.46.390.172 I slot print_timing: id 1 | task 7406 | prompt eval time = 892.31 ms / 121 tokens ( 7.37 ms per token, 135.60 tokens per second) 9.46.390.175 I slot print_timing: id 1 | task 7406 | eval time = 889.13 ms / 2 tokens ( 889.13 ms per token, 1.12 tokens per second) 9.46.390.176 I slot print_timing: id 1 | task 7406 | total time = 1781.44 ms / 123 tokens 9.46.390.177 I slot print_timing: id 1 | task 7406 | graphs reused = 6233 9.46.390.177 I slot print_timing: id 1 | task 7406 | graph reallocs = 0 / 0 (same size) / (changed size) 9.46.390.230 I slot release: id 1 | task 7406 | stop processing: n_tokens = 801, truncated = 0 9.46.391.367 I slot print_timing: id 2 | task 7402 | prompt eval time = 3965.29 ms / 762 tokens ( 5.20 ms per token, 192.17 tokens per second) 9.46.391.369 I slot print_timing: id 2 | task 7402 | eval time = 889.14 ms / 2 tokens ( 889.14 ms per token, 1.12 tokens per second) 9.46.391.370 I slot print_timing: id 2 | task 7402 | total time = 4854.43 ms / 764 tokens 9.46.391.370 I slot print_timing: id 2 | task 7402 | graphs reused = 6233 9.46.391.371 I slot print_timing: id 2 | task 7402 | graph reallocs = 0 / 0 (same size) / (changed size) 9.46.391.401 I slot release: id 2 | task 7402 | stop processing: n_tokens = 772, truncated = 0 9.46.392.556 I slot print_timing: id 3 | task 7403 | prompt eval time = 3966.07 ms / 768 tokens ( 5.16 ms per token, 193.64 tokens per second) 9.46.392.558 I slot print_timing: id 3 | task 7403 | eval time = 889.28 ms / 2 tokens ( 889.28 ms per token, 1.12 tokens per second) 9.46.392.559 I slot print_timing: id 3 | task 7403 | total time = 4855.35 ms / 770 tokens 9.46.392.559 I slot print_timing: id 3 | task 7403 | graphs reused = 6233 9.46.392.559 I slot print_timing: id 3 | task 7403 | graph reallocs = 0 / 0 (same size) / (changed size) 9.46.392.602 I slot release: id 3 | task 7403 | stop processing: n_tokens = 778, truncated = 0 9.47.148.236 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 801, t_last = 324210587773 9.47.148.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 254.360 MiB) 9.47.471.158 I slot launch_slot_: id 1 | task 7413 | processing task, is_child = 0 9.47.471.231 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 240.014 MiB) 9.47.479.685 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.037 MiB) 9.47.485.956 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 324210588944 9.47.486.079 I slot launch_slot_: id 2 | task 7414 | processing task, is_child = 0 9.47.486.142 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 324210590145 9.47.486.247 I slot launch_slot_: id 3 | task 7415 | processing task, is_child = 0 9.52.537.748 I slot print_timing: id 0 | task 7409 | prompt eval time = 4512.35 ms / 952 tokens ( 4.74 ms per token, 210.98 tokens per second) 9.52.537.754 I slot print_timing: id 0 | task 7409 | eval time = 2516.05 ms / 2 tokens ( 2516.05 ms per token, 0.40 tokens per second) 9.52.537.755 I slot print_timing: id 0 | task 7409 | total time = 7028.39 ms / 954 tokens 9.52.537.756 I slot print_timing: id 0 | task 7409 | graphs reused = 6233 9.52.537.756 I slot print_timing: id 0 | task 7409 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.537.828 I slot release: id 0 | task 7409 | stop processing: n_tokens = 962, truncated = 0 9.52.537.858 I slot print_timing: id 1 | task 7413 | prompt processing, n_tokens = 817, progress = 0.88, t = 5.05 s / 161.83 tokens per second 9.52.540.289 I slot print_timing: id 2 | task 7414 | prompt processing, n_tokens = 817, progress = 0.87, t = 5.05 s / 161.84 tokens per second 9.52.542.274 I slot print_timing: id 3 | task 7415 | prompt processing, n_tokens = 817, progress = 0.88, t = 5.05 s / 161.84 tokens per second 9.53.217.268 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.889 (> 0.100 thold), f_keep = 0.887 9.53.217.340 I slot launch_slot_: id 0 | task 7419 | processing task, is_child = 0 9.53.298.283 I slot print_timing: id 1 | task 7413 | prompt processing, n_tokens = 922, progress = 1.00, t = 5.73 s / 160.93 tokens per second 9.53.300.817 I slot print_timing: id 2 | task 7414 | prompt processing, n_tokens = 940, progress = 1.00, t = 5.73 s / 164.08 tokens per second 9.53.302.616 I slot print_timing: id 3 | task 7415 | prompt processing, n_tokens = 924, progress = 1.00, t = 5.73 s / 161.29 tokens per second 9.53.733.834 I slot print_timing: id 1 | task 7413 | prompt eval time = 6164.79 ms / 926 tokens ( 6.66 ms per token, 150.21 tokens per second) 9.53.733.837 I slot print_timing: id 1 | task 7413 | eval time = 80.97 ms / 2 tokens ( 80.97 ms per token, 12.35 tokens per second) 9.53.733.838 I slot print_timing: id 1 | task 7413 | total time = 6245.76 ms / 928 tokens 9.53.733.838 I slot print_timing: id 1 | task 7413 | graphs reused = 6233 9.53.733.839 I slot print_timing: id 1 | task 7413 | graph reallocs = 0 / 0 (same size) / (changed size) 9.53.733.879 I slot release: id 1 | task 7413 | stop processing: n_tokens = 936, truncated = 0 9.53.734.991 I slot print_timing: id 2 | task 7414 | prompt eval time = 6165.80 ms / 944 tokens ( 6.53 ms per token, 153.10 tokens per second) 9.53.734.993 I slot print_timing: id 2 | task 7414 | eval time = 80.93 ms / 2 tokens ( 80.93 ms per token, 12.36 tokens per second) 9.53.734.993 I slot print_timing: id 2 | task 7414 | total time = 6246.73 ms / 946 tokens 9.53.734.994 I slot print_timing: id 2 | task 7414 | graphs reused = 6233 9.53.734.994 I slot print_timing: id 2 | task 7414 | graph reallocs = 0 / 0 (same size) / (changed size) 9.53.735.018 I slot release: id 2 | task 7414 | stop processing: n_tokens = 954, truncated = 0 9.53.736.109 I slot print_timing: id 3 | task 7415 | prompt eval time = 6166.81 ms / 928 tokens ( 6.65 ms per token, 150.48 tokens per second) 9.53.736.111 I slot print_timing: id 3 | task 7415 | eval time = 80.88 ms / 2 tokens ( 80.88 ms per token, 12.36 tokens per second) 9.53.736.112 I slot print_timing: id 3 | task 7415 | total time = 6247.68 ms / 930 tokens 9.53.736.112 I slot print_timing: id 3 | task 7415 | graphs reused = 6233 9.53.736.112 I slot print_timing: id 3 | task 7415 | graph reallocs = 0 / 0 (same size) / (changed size) 9.53.736.144 I slot release: id 3 | task 7415 | stop processing: n_tokens = 938, truncated = 0 9.53.762.053 I slot print_timing: id 0 | task 7419 | prompt eval time = 515.37 ms / 107 tokens ( 4.82 ms per token, 207.62 tokens per second) 9.53.762.055 I slot print_timing: id 0 | task 7419 | eval time = 29.33 ms / 2 tokens ( 29.33 ms per token, 34.09 tokens per second) 9.53.762.056 I slot print_timing: id 0 | task 7419 | total time = 544.70 ms / 109 tokens 9.53.762.056 I slot print_timing: id 0 | task 7419 | graphs reused = 6233 9.53.762.057 I slot print_timing: id 0 | task 7419 | graph reallocs = 0 / 0 (same size) / (changed size) 9.53.762.098 I slot release: id 0 | task 7419 | stop processing: n_tokens = 961, truncated = 0 9.53.762.105 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 324217931422 9.53.762.200 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 242.264 MiB) 9.53.768.433 I slot launch_slot_: id 1 | task 7423 | processing task, is_child = 0 9.53.768.523 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.291 MiB) 9.53.775.923 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 233.544 MiB) 9.53.782.323 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 209.775 MiB) 9.53.788.904 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 324217932561 9.53.789.110 I slot launch_slot_: id 2 | task 7424 | processing task, is_child = 0 9.53.789.324 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 938, t_last = 324217933687 9.53.789.463 I slot launch_slot_: id 3 | task 7425 | processing task, is_child = 0 9.53.789.559 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 324217959641 9.53.789.696 I slot launch_slot_: id 0 | task 7426 | processing task, is_child = 0 9.59.647.686 I slot print_timing: id 0 | task 7426 | prompt processing, n_tokens = 818, progress = 0.87, t = 5.86 s / 139.64 tokens per second 9.59.744.056 I slot print_timing: id 1 | task 7423 | prompt processing, n_tokens = 668, progress = 0.85, t = 5.86 s / 114.04 tokens per second 9.59.749.273 I slot print_timing: id 2 | task 7424 | prompt processing, n_tokens = 818, progress = 0.85, t = 5.86 s / 139.65 tokens per second 9.59.753.156 I slot print_timing: id 3 | task 7425 | prompt processing, n_tokens = 668, progress = 0.85, t = 5.86 s / 114.05 tokens per second 10.00.736.622 I slot print_timing: id 0 | task 7426 | prompt processing, n_tokens = 943, progress = 1.00, t = 6.95 s / 135.74 tokens per second 10.00.834.115 I slot print_timing: id 1 | task 7423 | prompt processing, n_tokens = 785, progress = 0.99, t = 6.95 s / 113.00 tokens per second 10.00.839.595 I slot print_timing: id 2 | task 7424 | prompt processing, n_tokens = 963, progress = 1.00, t = 6.95 s / 138.63 tokens per second 10.00.843.661 I slot print_timing: id 3 | task 7425 | prompt processing, n_tokens = 785, progress = 0.99, t = 6.95 s / 113.01 tokens per second 10.00.987.749 I slot print_timing: id 0 | task 7426 | prompt eval time = 7148.40 ms / 947 tokens ( 7.55 ms per token, 132.48 tokens per second) 10.00.987.753 I slot print_timing: id 0 | task 7426 | eval time = 49.64 ms / 2 tokens ( 49.64 ms per token, 20.15 tokens per second) 10.00.987.754 I slot print_timing: id 0 | task 7426 | total time = 7198.04 ms / 949 tokens 10.00.987.755 I slot print_timing: id 0 | task 7426 | graphs reused = 6234 10.00.987.755 I slot print_timing: id 0 | task 7426 | graph reallocs = 0 / 0 (same size) / (changed size) 10.00.987.826 I slot release: id 0 | task 7426 | stop processing: n_tokens = 957, truncated = 0 10.00.989.925 I slot print_timing: id 1 | task 7423 | prompt eval time = 7150.73 ms / 789 tokens ( 9.06 ms per token, 110.34 tokens per second) 10.00.989.930 I slot print_timing: id 1 | task 7423 | eval time = 49.18 ms / 2 tokens ( 49.18 ms per token, 20.33 tokens per second) 10.00.989.931 I slot print_timing: id 1 | task 7423 | total time = 7199.92 ms / 791 tokens 10.00.989.931 I slot print_timing: id 1 | task 7423 | graphs reused = 6234 10.00.989.932 I slot print_timing: id 1 | task 7423 | graph reallocs = 0 / 0 (same size) / (changed size) 10.00.989.994 I slot release: id 1 | task 7423 | stop processing: n_tokens = 799, truncated = 0 10.00.992.003 I slot print_timing: id 2 | task 7424 | prompt eval time = 7152.92 ms / 967 tokens ( 7.40 ms per token, 135.19 tokens per second) 10.00.992.007 I slot print_timing: id 2 | task 7424 | eval time = 48.81 ms / 2 tokens ( 48.81 ms per token, 20.49 tokens per second) 10.00.992.008 I slot print_timing: id 2 | task 7424 | total time = 7201.73 ms / 969 tokens 10.00.992.008 I slot print_timing: id 2 | task 7424 | graphs reused = 6234 10.00.992.009 I slot print_timing: id 2 | task 7424 | graph reallocs = 0 / 0 (same size) / (changed size) 10.00.992.053 I slot release: id 2 | task 7424 | stop processing: n_tokens = 977, truncated = 0 10.00.993.853 I slot print_timing: id 3 | task 7425 | prompt eval time = 7155.03 ms / 789 tokens ( 9.07 ms per token, 110.27 tokens per second) 10.00.993.858 I slot print_timing: id 3 | task 7425 | eval time = 48.28 ms / 2 tokens ( 48.28 ms per token, 20.71 tokens per second) 10.00.993.859 I slot print_timing: id 3 | task 7425 | total time = 7203.31 ms / 791 tokens 10.00.993.859 I slot print_timing: id 3 | task 7425 | graphs reused = 6234 10.00.993.860 I slot print_timing: id 3 | task 7425 | graph reallocs = 0 / 0 (same size) / (changed size) 10.00.993.898 I slot release: id 3 | task 7425 | stop processing: n_tokens = 799, truncated = 0 10.01.001.299 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.892 10.01.001.388 I slot launch_slot_: id 0 | task 7432 | processing task, is_child = 0 10.01.001.513 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.570 MiB) 10.01.018.458 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 266.735 MiB) 10.01.034.497 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 232.419 MiB) 10.01.040.586 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 324225187537 10.01.040.758 I slot launch_slot_: id 1 | task 7433 | processing task, is_child = 0 10.01.040.927 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 324225189597 10.01.041.048 I slot launch_slot_: id 2 | task 7434 | processing task, is_child = 0 10.01.041.122 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 324225191441 10.01.041.230 I slot launch_slot_: id 3 | task 7435 | processing task, is_child = 0 10.05.963.023 I slot print_timing: id 1 | task 7433 | prompt processing, n_tokens = 771, progress = 0.87, t = 4.92 s / 156.76 tokens per second 10.05.966.076 I slot print_timing: id 2 | task 7434 | prompt processing, n_tokens = 771, progress = 0.84, t = 4.92 s / 156.76 tokens per second 10.05.968.032 I slot print_timing: id 3 | task 7435 | prompt processing, n_tokens = 771, progress = 0.86, t = 4.92 s / 156.77 tokens per second 10.06.829.689 I slot print_timing: id 0 | task 7432 | prompt eval time = 4921.74 ms / 108 tokens ( 45.57 ms per token, 21.94 tokens per second) 10.06.829.693 I slot print_timing: id 0 | task 7432 | eval time = 866.70 ms / 2 tokens ( 866.70 ms per token, 1.15 tokens per second) 10.06.829.694 I slot print_timing: id 0 | task 7432 | total time = 5788.44 ms / 110 tokens 10.06.829.694 I slot print_timing: id 0 | task 7432 | graphs reused = 6235 10.06.829.695 I slot print_timing: id 0 | task 7432 | graph reallocs = 0 / 0 (same size) / (changed size) 10.06.829.755 I slot release: id 0 | task 7432 | stop processing: n_tokens = 963, truncated = 0 10.06.829.776 I slot print_timing: id 1 | task 7433 | prompt processing, n_tokens = 886, progress = 1.00, t = 5.79 s / 153.15 tokens per second 10.06.833.979 I slot print_timing: id 2 | task 7434 | prompt processing, n_tokens = 917, progress = 1.00, t = 5.78 s / 158.52 tokens per second 10.06.835.845 I slot print_timing: id 3 | task 7435 | prompt processing, n_tokens = 890, progress = 1.00, t = 5.78 s / 153.85 tokens per second 10.06.921.937 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 963, t_last = 324231027298 10.06.922.032 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 250.844 MiB) 10.06.933.762 I slot launch_slot_: id 0 | task 7440 | processing task, is_child = 0 10.07.691.053 I slot print_timing: id 1 | task 7433 | prompt eval time = 5876.28 ms / 890 tokens ( 6.60 ms per token, 151.46 tokens per second) 10.07.691.057 I slot print_timing: id 1 | task 7433 | eval time = 771.46 ms / 2 tokens ( 771.46 ms per token, 1.30 tokens per second) 10.07.691.058 I slot print_timing: id 1 | task 7433 | total time = 6647.73 ms / 892 tokens 10.07.691.058 I slot print_timing: id 1 | task 7433 | graphs reused = 6235 10.07.691.058 I slot print_timing: id 1 | task 7433 | graph reallocs = 0 / 0 (same size) / (changed size) 10.07.691.102 I slot release: id 1 | task 7433 | stop processing: n_tokens = 900, truncated = 0 10.07.692.243 I slot print_timing: id 2 | task 7434 | prompt eval time = 5877.21 ms / 921 tokens ( 6.38 ms per token, 156.71 tokens per second) 10.07.692.245 I slot print_timing: id 2 | task 7434 | eval time = 771.48 ms / 2 tokens ( 771.48 ms per token, 1.30 tokens per second) 10.07.692.246 I slot print_timing: id 2 | task 7434 | total time = 6648.69 ms / 923 tokens 10.07.692.246 I slot print_timing: id 2 | task 7434 | graphs reused = 6235 10.07.692.246 I slot print_timing: id 2 | task 7434 | graph reallocs = 0 / 0 (same size) / (changed size) 10.07.692.273 I slot release: id 2 | task 7434 | stop processing: n_tokens = 931, truncated = 0 10.07.693.428 I slot print_timing: id 3 | task 7435 | prompt eval time = 5878.14 ms / 894 tokens ( 6.58 ms per token, 152.09 tokens per second) 10.07.693.430 I slot print_timing: id 3 | task 7435 | eval time = 771.50 ms / 2 tokens ( 771.50 ms per token, 1.30 tokens per second) 10.07.693.430 I slot print_timing: id 3 | task 7435 | total time = 6649.64 ms / 896 tokens 10.07.693.431 I slot print_timing: id 3 | task 7435 | graphs reused = 6235 10.07.693.431 I slot print_timing: id 3 | task 7435 | graph reallocs = 0 / 0 (same size) / (changed size) 10.07.693.457 I slot release: id 3 | task 7435 | stop processing: n_tokens = 904, truncated = 0 10.08.504.020 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.897 10.08.504.094 I slot launch_slot_: id 1 | task 7444 | processing task, is_child = 0 10.08.504.177 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 254.430 MiB) 10.08.772.611 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 302.916 MiB) 10.08.779.638 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 324231889816 10.08.779.806 I slot launch_slot_: id 2 | task 7445 | processing task, is_child = 0 10.08.779.890 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 324231891000 10.08.779.990 I slot launch_slot_: id 3 | task 7446 | processing task, is_child = 0 10.11.807.384 I slot print_timing: id 1 | task 7444 | prompt processing, n_tokens = 79, progress = 1.00, t = 3.02 s / 26.12 tokens per second 10.11.811.313 I slot print_timing: id 2 | task 7445 | prompt processing, n_tokens = 710, progress = 0.58, t = 3.02 s / 234.90 tokens per second 10.11.813.203 I slot print_timing: id 3 | task 7446 | prompt processing, n_tokens = 699, progress = 0.58, t = 3.02 s / 231.27 tokens per second 10.13.392.552 I slot print_timing: id 0 | task 7440 | prompt eval time = 4873.56 ms / 894 tokens ( 5.45 ms per token, 183.44 tokens per second) 10.13.392.562 I slot print_timing: id 0 | task 7440 | eval time = 1585.19 ms / 2 tokens ( 1585.19 ms per token, 0.63 tokens per second) 10.13.392.564 I slot print_timing: id 0 | task 7440 | total time = 6458.75 ms / 896 tokens 10.13.392.565 I slot print_timing: id 0 | task 7440 | graphs reused = 6235 10.13.392.566 I slot print_timing: id 0 | task 7440 | graph reallocs = 0 / 0 (same size) / (changed size) 10.13.392.736 I slot release: id 0 | task 7440 | stop processing: n_tokens = 904, truncated = 0 10.13.395.070 I slot print_timing: id 2 | task 7445 | prompt processing, n_tokens = 1051, progress = 0.86, t = 4.61 s / 228.21 tokens per second 10.13.401.324 I slot print_timing: id 3 | task 7446 | prompt processing, n_tokens = 1051, progress = 0.87, t = 4.61 s / 228.22 tokens per second 10.14.163.662 I slot print_timing: id 1 | task 7444 | prompt eval time = 4613.18 ms / 83 tokens ( 55.58 ms per token, 17.99 tokens per second) 10.14.163.676 I slot print_timing: id 1 | task 7444 | eval time = 768.60 ms / 2 tokens ( 768.60 ms per token, 1.30 tokens per second) 10.14.163.683 I slot print_timing: id 1 | task 7444 | total time = 5381.78 ms / 85 tokens 10.14.163.685 I slot print_timing: id 1 | task 7444 | graphs reused = 6235 10.14.163.686 I slot print_timing: id 1 | task 7444 | graph reallocs = 0 / 0 (same size) / (changed size) 10.14.163.851 I slot release: id 1 | task 7444 | stop processing: n_tokens = 891, truncated = 0 10.14.163.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 324237590279 10.14.164.156 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.719 MiB) 10.14.178.657 I slot launch_slot_: id 0 | task 7450 | processing task, is_child = 0 10.14.178.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 233.966 MiB) 10.14.192.161 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 324238361394 10.14.192.375 I slot launch_slot_: id 1 | task 7451 | processing task, is_child = 0 10.18.111.720 I slot print_timing: id 0 | task 7450 | prompt processing, n_tokens = 764, progress = 0.60, t = 3.92 s / 194.93 tokens per second 10.18.153.891 I slot print_timing: id 1 | task 7451 | prompt processing, n_tokens = 1284, progress = 0.48, t = 3.92 s / 327.64 tokens per second 10.18.154.041 I slot print_timing: id 2 | task 7445 | prompt processing, n_tokens = 1222, progress = 1.00, t = 5.38 s / 227.32 tokens per second 10.18.162.631 I slot print_timing: id 3 | task 7446 | prompt processing, n_tokens = 1211, progress = 1.00, t = 5.38 s / 225.28 tokens per second 10.20.593.292 I slot print_timing: id 0 | task 7450 | prompt processing, n_tokens = 1051, progress = 0.82, t = 6.40 s / 164.35 tokens per second 10.20.599.710 I slot print_timing: id 1 | task 7451 | prompt processing, n_tokens = 2146, progress = 0.81, t = 6.39 s / 335.59 tokens per second 10.21.570.109 I slot print_timing: id 2 | task 7445 | prompt eval time = 11807.25 ms / 1226 tokens ( 9.63 ms per token, 103.83 tokens per second) 10.21.570.118 I slot print_timing: id 2 | task 7445 | eval time = 979.26 ms / 2 tokens ( 979.26 ms per token, 1.02 tokens per second) 10.21.570.119 I slot print_timing: id 2 | task 7445 | total time = 12786.50 ms / 1228 tokens 10.21.570.121 I slot print_timing: id 2 | task 7445 | graphs reused = 6235 10.21.570.123 I slot print_timing: id 2 | task 7445 | graph reallocs = 0 / 0 (same size) / (changed size) 10.21.570.298 I slot release: id 2 | task 7445 | stop processing: n_tokens = 1236, truncated = 0 10.21.573.066 I slot print_timing: id 3 | task 7446 | prompt eval time = 11809.45 ms / 1215 tokens ( 9.72 ms per token, 102.88 tokens per second) 10.21.573.073 I slot print_timing: id 3 | task 7446 | eval time = 979.84 ms / 2 tokens ( 979.84 ms per token, 1.02 tokens per second) 10.21.573.077 I slot print_timing: id 3 | task 7446 | total time = 12789.28 ms / 1217 tokens 10.21.573.078 I slot print_timing: id 3 | task 7446 | graphs reused = 6235 10.21.573.079 I slot print_timing: id 3 | task 7446 | graph reallocs = 0 / 0 (same size) / (changed size) 10.21.573.199 I slot release: id 3 | task 7446 | stop processing: n_tokens = 1225, truncated = 0 10.21.573.253 I slot print_timing: id 0 | task 7450 | prompt processing, n_tokens = 1276, progress = 1.00, t = 7.37 s / 173.02 tokens per second 10.21.580.040 I slot print_timing: id 1 | task 7451 | prompt processing, n_tokens = 2353, progress = 0.88, t = 7.37 s / 319.07 tokens per second 10.22.287.832 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1236, t_last = 324245767841 10.22.288.227 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.638 MiB) 10.22.306.923 I slot launch_slot_: id 2 | task 7456 | processing task, is_child = 0 10.22.307.088 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 251.828 MiB) 10.22.330.781 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1225, t_last = 324245770742 10.22.331.009 I slot launch_slot_: id 3 | task 7457 | processing task, is_child = 0 10.22.331.024 I slot print_timing: id 1 | task 7451 | prompt processing, n_tokens = 2658, progress = 1.00, t = 8.09 s / 328.52 tokens per second 10.26.395.699 I slot print_timing: id 0 | task 7450 | prompt eval time = 8095.39 ms / 1280 tokens ( 6.32 ms per token, 158.11 tokens per second) 10.26.395.711 I slot print_timing: id 0 | task 7450 | eval time = 4107.89 ms / 2 tokens ( 4107.89 ms per token, 0.24 tokens per second) 10.26.395.713 I slot print_timing: id 0 | task 7450 | total time = 12203.28 ms / 1282 tokens 10.26.395.715 I slot print_timing: id 0 | task 7450 | graphs reused = 6235 10.26.395.716 I slot print_timing: id 0 | task 7450 | graph reallocs = 0 / 0 (same size) / (changed size) 10.26.395.912 I slot release: id 0 | task 7450 | stop processing: n_tokens = 1290, truncated = 0 10.26.398.515 I slot print_timing: id 2 | task 7456 | prompt processing, n_tokens = 2043, progress = 0.80, t = 4.06 s / 503.51 tokens per second 10.30.505.330 I slot print_timing: id 1 | task 7451 | prompt eval time = 12205.68 ms / 2662 tokens ( 4.59 ms per token, 218.10 tokens per second) 10.30.505.341 I slot print_timing: id 1 | task 7451 | eval time = 4106.86 ms / 2 tokens ( 4106.86 ms per token, 0.24 tokens per second) 10.30.505.346 I slot print_timing: id 1 | task 7451 | total time = 16312.53 ms / 2664 tokens 10.30.505.348 I slot print_timing: id 1 | task 7451 | graphs reused = 6235 10.30.505.352 I slot print_timing: id 1 | task 7451 | graph reallocs = 0 / 0 (same size) / (changed size) 10.30.505.811 I slot release: id 1 | task 7451 | stop processing: n_tokens = 2672, truncated = 0 10.30.505.857 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.897 10.30.506.149 I slot launch_slot_: id 1 | task 7460 | processing task, is_child = 0 10.30.506.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.432 MiB) 10.30.526.473 I slot print_timing: id 2 | task 7456 | prompt processing, n_tokens = 2052, progress = 0.80, t = 8.17 s / 251.26 tokens per second 10.30.530.395 I slot print_timing: id 3 | task 7457 | prompt processing, n_tokens = 2038, progress = 0.72, t = 4.10 s / 496.73 tokens per second 10.32.388.328 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1290, t_last = 324250593455 10.32.388.513 I slot launch_slot_: id 0 | task 7462 | processing task, is_child = 0 10.32.539.495 I slot print_timing: id 2 | task 7456 | prompt processing, n_tokens = 2353, progress = 0.92, t = 10.05 s / 234.04 tokens per second 10.32.541.267 I slot print_timing: id 3 | task 7457 | prompt processing, n_tokens = 2301, progress = 0.82, t = 5.99 s / 384.16 tokens per second 10.35.725.174 I slot print_timing: id 0 | task 7462 | prompt processing, n_tokens = 1294, progress = 0.72, t = 3.34 s / 387.96 tokens per second 10.35.728.081 I slot print_timing: id 2 | task 7456 | prompt processing, n_tokens = 2564, progress = 1.00, t = 13.39 s / 191.49 tokens per second 10.35.730.306 I slot print_timing: id 3 | task 7457 | prompt processing, n_tokens = 2353, progress = 0.84, t = 9.33 s / 252.32 tokens per second 10.37.174.102 I slot print_timing: id 1 | task 7460 | prompt eval time = 5202.48 ms / 340 tokens ( 15.30 ms per token, 65.35 tokens per second) 10.37.174.109 I slot print_timing: id 1 | task 7460 | eval time = 1448.97 ms / 2 tokens ( 1448.97 ms per token, 0.69 tokens per second) 10.37.174.109 I slot print_timing: id 1 | task 7460 | total time = 6651.45 ms / 342 tokens 10.37.174.109 I slot print_timing: id 1 | task 7460 | graphs reused = 6235 10.37.174.110 I slot print_timing: id 1 | task 7460 | graph reallocs = 0 / 0 (same size) / (changed size) 10.37.174.262 I slot release: id 1 | task 7460 | stop processing: n_tokens = 2739, truncated = 0 10.37.175.593 I slot print_timing: id 0 | task 7462 | prompt processing, n_tokens = 1467, progress = 0.81, t = 4.78 s / 306.62 tokens per second 10.37.178.956 I slot print_timing: id 3 | task 7457 | prompt processing, n_tokens = 2813, progress = 1.00, t = 10.77 s / 261.08 tokens per second 10.37.961.990 I slot print_timing: id 2 | task 7456 | prompt eval time = 14841.18 ms / 2568 tokens ( 5.78 ms per token, 173.03 tokens per second) 10.37.961.993 I slot print_timing: id 2 | task 7456 | eval time = 786.41 ms / 2 tokens ( 786.41 ms per token, 1.27 tokens per second) 10.37.961.995 I slot print_timing: id 2 | task 7456 | total time = 15627.58 ms / 2570 tokens 10.37.961.995 I slot print_timing: id 2 | task 7456 | graphs reused = 6235 10.37.961.996 I slot print_timing: id 2 | task 7456 | graph reallocs = 0 / 0 (same size) / (changed size) 10.37.962.144 I slot release: id 2 | task 7456 | stop processing: n_tokens = 2578, truncated = 0 10.37.963.416 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2739, t_last = 324261371806 10.37.963.624 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 237.060 MiB) 10.37.990.970 I slot launch_slot_: id 1 | task 7466 | processing task, is_child = 0 10.37.991.114 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 301.404 MiB) 10.38.013.928 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2578, t_last = 324262159689 10.38.014.130 I slot launch_slot_: id 2 | task 7467 | processing task, is_child = 0 10.38.014.140 I slot print_timing: id 0 | task 7462 | prompt processing, n_tokens = 1806, progress = 1.00, t = 5.57 s / 324.10 tokens per second 10.42.041.850 I slot print_timing: id 3 | task 7457 | prompt eval time = 11564.85 ms / 2817 tokens ( 4.11 ms per token, 243.58 tokens per second) 10.42.041.854 I slot print_timing: id 3 | task 7457 | eval time = 4078.43 ms / 2 tokens ( 4078.43 ms per token, 0.25 tokens per second) 10.42.041.855 I slot print_timing: id 3 | task 7457 | total time = 15643.29 ms / 2819 tokens 10.42.041.855 I slot print_timing: id 3 | task 7457 | graphs reused = 6235 10.42.041.856 I slot print_timing: id 3 | task 7457 | graph reallocs = 0 / 0 (same size) / (changed size) 10.42.042.045 I slot release: id 3 | task 7457 | stop processing: n_tokens = 2827, truncated = 0 10.42.042.082 I slot print_timing: id 1 | task 7466 | prompt processing, n_tokens = 1354, progress = 0.73, t = 4.02 s / 336.52 tokens per second 10.42.046.313 I slot print_timing: id 2 | task 7467 | prompt processing, n_tokens = 689, progress = 0.33, t = 4.02 s / 171.26 tokens per second 10.43.865.997 I slot print_timing: id 0 | task 7462 | prompt eval time = 9652.10 ms / 1810 tokens ( 5.33 ms per token, 187.52 tokens per second) 10.43.866.001 I slot print_timing: id 0 | task 7462 | eval time = 1825.36 ms / 2 tokens ( 1825.36 ms per token, 0.55 tokens per second) 10.43.866.002 I slot print_timing: id 0 | task 7462 | total time = 11477.45 ms / 1812 tokens 10.43.866.002 I slot print_timing: id 0 | task 7462 | graphs reused = 6235 10.43.866.002 I slot print_timing: id 0 | task 7462 | graph reallocs = 0 / 0 (same size) / (changed size) 10.43.866.118 I slot release: id 0 | task 7462 | stop processing: n_tokens = 1820, truncated = 0 10.43.866.135 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.799 (> 0.100 thold), f_keep = 0.831 10.43.866.252 I slot launch_slot_: id 0 | task 7470 | processing task, is_child = 0 10.43.866.447 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 241.842 MiB) 10.43.866.743 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 235.232 MiB) 10.43.892.140 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2827, t_last = 324266239590 10.43.892.367 I slot launch_slot_: id 3 | task 7471 | processing task, is_child = 0 10.43.896.348 I slot print_timing: id 1 | task 7466 | prompt processing, n_tokens = 1467, progress = 0.79, t = 5.85 s / 250.82 tokens per second 10.43.900.132 I slot print_timing: id 2 | task 7467 | prompt processing, n_tokens = 1467, progress = 0.71, t = 5.85 s / 250.84 tokens per second 10.47.932.589 I slot print_timing: id 0 | task 7470 | prompt processing, n_tokens = 377, progress = 1.00, t = 4.04 s / 93.31 tokens per second 10.48.080.119 I slot print_timing: id 1 | task 7466 | prompt processing, n_tokens = 1866, progress = 1.00, t = 9.92 s / 188.17 tokens per second 10.48.083.089 I slot print_timing: id 2 | task 7467 | prompt processing, n_tokens = 1565, progress = 0.75, t = 9.92 s / 157.82 tokens per second 10.48.084.884 I slot print_timing: id 3 | task 7471 | prompt processing, n_tokens = 1174, progress = 0.59, t = 4.03 s / 291.42 tokens per second 10.49.861.820 I slot print_timing: id 2 | task 7467 | prompt processing, n_tokens = 2077, progress = 1.00, t = 11.84 s / 175.38 tokens per second 10.49.864.687 I slot print_timing: id 3 | task 7471 | prompt processing, n_tokens = 1467, progress = 0.74, t = 5.96 s / 246.33 tokens per second 10.49.980.829 I slot print_timing: id 0 | task 7470 | prompt eval time = 5968.13 ms / 381 tokens ( 15.66 ms per token, 63.84 tokens per second) 10.49.980.832 I slot print_timing: id 0 | task 7470 | eval time = 120.31 ms / 2 tokens ( 120.31 ms per token, 8.31 tokens per second) 10.49.980.832 I slot print_timing: id 0 | task 7470 | total time = 6088.45 ms / 383 tokens 10.49.980.833 I slot print_timing: id 0 | task 7470 | graphs reused = 6235 10.49.980.833 I slot print_timing: id 0 | task 7470 | graph reallocs = 0 / 0 (same size) / (changed size) 10.49.980.921 I slot release: id 0 | task 7470 | stop processing: n_tokens = 1894, truncated = 0 10.49.982.045 I slot print_timing: id 1 | task 7466 | prompt eval time = 11845.77 ms / 1870 tokens ( 6.33 ms per token, 157.86 tokens per second) 10.49.982.049 I slot print_timing: id 1 | task 7466 | eval time = 120.25 ms / 2 tokens ( 120.25 ms per token, 8.32 tokens per second) 10.49.982.050 I slot print_timing: id 1 | task 7466 | total time = 11966.02 ms / 1872 tokens 10.49.982.050 I slot print_timing: id 1 | task 7466 | graphs reused = 6235 10.49.982.051 I slot print_timing: id 1 | task 7466 | graph reallocs = 0 / 0 (same size) / (changed size) 10.49.982.105 I slot release: id 1 | task 7466 | stop processing: n_tokens = 1880, truncated = 0 10.49.983.250 I slot print_timing: id 3 | task 7471 | prompt processing, n_tokens = 1475, progress = 0.74, t = 6.08 s / 242.77 tokens per second 10.51.042.826 I slot print_timing: id 2 | task 7467 | prompt eval time = 11966.82 ms / 2081 tokens ( 5.75 ms per token, 173.90 tokens per second) 10.51.042.829 I slot print_timing: id 2 | task 7467 | eval time = 1059.58 ms / 2 tokens ( 1059.58 ms per token, 0.94 tokens per second) 10.51.042.830 I slot print_timing: id 2 | task 7467 | total time = 13026.40 ms / 2083 tokens 10.51.042.830 I slot print_timing: id 2 | task 7467 | graphs reused = 6235 10.51.042.831 I slot print_timing: id 2 | task 7467 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.042.930 I slot release: id 2 | task 7467 | stop processing: n_tokens = 2091, truncated = 0 10.51.042.962 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1894, t_last = 324274178466 10.51.043.118 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 240.014 MiB) 10.51.069.978 I slot launch_slot_: id 0 | task 7476 | processing task, is_child = 0 10.51.070.092 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.965 MiB) 10.51.093.472 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.508 MiB) 10.51.117.976 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.834 (> 0.100 thold), f_keep = 0.804 10.51.118.055 I slot launch_slot_: id 1 | task 7477 | processing task, is_child = 0 10.51.118.174 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2091, t_last = 324275240474 10.51.118.316 I slot launch_slot_: id 2 | task 7478 | processing task, is_child = 0 10.51.121.155 I slot print_timing: id 3 | task 7471 | prompt processing, n_tokens = 1987, progress = 1.00, t = 7.14 s / 278.38 tokens per second 10.54.389.280 I slot print_timing: id 3 | task 7471 | prompt eval time = 8851.87 ms / 1991 tokens ( 4.45 ms per token, 224.92 tokens per second) 10.54.389.287 I slot print_timing: id 3 | task 7471 | eval time = 1633.38 ms / 2 tokens ( 1633.38 ms per token, 0.61 tokens per second) 10.54.389.288 I slot print_timing: id 3 | task 7471 | total time = 10485.25 ms / 1993 tokens 10.54.389.289 I slot print_timing: id 3 | task 7471 | graphs reused = 6235 10.54.389.289 I slot print_timing: id 3 | task 7471 | graph reallocs = 0 / 0 (same size) / (changed size) 10.54.389.433 I slot release: id 3 | task 7471 | stop processing: n_tokens = 2001, truncated = 0 10.54.389.461 I slot print_timing: id 0 | task 7476 | prompt processing, n_tokens = 602, progress = 0.84, t = 3.27 s / 184.18 tokens per second 10.54.392.638 I slot print_timing: id 2 | task 7478 | prompt processing, n_tokens = 602, progress = 0.82, t = 3.27 s / 184.32 tokens per second 10.54.958.633 I slot print_timing: id 1 | task 7477 | prompt eval time = 3269.39 ms / 301 tokens ( 10.86 ms per token, 92.07 tokens per second) 10.54.958.639 I slot print_timing: id 1 | task 7477 | eval time = 570.60 ms / 2 tokens ( 570.60 ms per token, 1.75 tokens per second) 10.54.958.639 I slot print_timing: id 1 | task 7477 | total time = 3839.99 ms / 303 tokens 10.54.958.640 I slot print_timing: id 1 | task 7477 | graphs reused = 6235 10.54.958.640 I slot print_timing: id 1 | task 7477 | graph reallocs = 0 / 0 (same size) / (changed size) 10.54.958.759 I slot release: id 1 | task 7477 | stop processing: n_tokens = 1814, truncated = 0 10.54.958.779 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2001, t_last = 324278586976 10.54.958.966 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 262.519 MiB) 10.54.982.390 I slot launch_slot_: id 3 | task 7482 | processing task, is_child = 0 10.54.982.503 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.967 MiB) 10.55.004.209 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1814, t_last = 324279156304 10.55.004.389 I slot launch_slot_: id 1 | task 7483 | processing task, is_child = 0 10.55.004.396 I slot print_timing: id 0 | task 7476 | prompt processing, n_tokens = 712, progress = 0.99, t = 3.84 s / 185.46 tokens per second 10.55.006.443 I slot print_timing: id 2 | task 7478 | prompt processing, n_tokens = 731, progress = 0.99, t = 3.84 s / 190.52 tokens per second 10.57.541.815 I slot print_timing: id 0 | task 7476 | prompt eval time = 4823.96 ms / 716 tokens ( 6.74 ms per token, 148.43 tokens per second) 10.57.541.819 I slot print_timing: id 0 | task 7476 | eval time = 1599.52 ms / 2 tokens ( 1599.52 ms per token, 0.63 tokens per second) 10.57.541.820 I slot print_timing: id 0 | task 7476 | total time = 6423.48 ms / 718 tokens 10.57.541.821 I slot print_timing: id 0 | task 7476 | graphs reused = 6235 10.57.541.821 I slot print_timing: id 0 | task 7476 | graph reallocs = 0 / 0 (same size) / (changed size) 10.57.541.866 I slot release: id 0 | task 7476 | stop processing: n_tokens = 726, truncated = 0 10.57.543.150 I slot print_timing: id 2 | task 7478 | prompt eval time = 4823.14 ms / 735 tokens ( 6.56 ms per token, 152.39 tokens per second) 10.57.543.153 I slot print_timing: id 2 | task 7478 | eval time = 1599.30 ms / 2 tokens ( 1599.30 ms per token, 0.63 tokens per second) 10.57.543.153 I slot print_timing: id 2 | task 7478 | total time = 6422.44 ms / 737 tokens 10.57.543.153 I slot print_timing: id 2 | task 7478 | graphs reused = 6235 10.57.543.154 I slot print_timing: id 2 | task 7478 | graph reallocs = 0 / 0 (same size) / (changed size) 10.57.543.189 I slot release: id 2 | task 7478 | stop processing: n_tokens = 745, truncated = 0 10.57.812.866 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 324281739409 10.57.812.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.886 MiB) 10.58.134.695 I slot launch_slot_: id 0 | task 7487 | processing task, is_child = 0 10.58.134.766 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 223.558 MiB) 10.58.140.122 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.856 10.58.140.171 I slot launch_slot_: id 2 | task 7488 | processing task, is_child = 0 10.59.760.555 I slot print_timing: id 1 | task 7483 | prompt eval time = 3976.04 ms / 712 tokens ( 5.58 ms per token, 179.07 tokens per second) 10.59.760.559 I slot print_timing: id 1 | task 7483 | eval time = 778.34 ms / 2 tokens ( 778.34 ms per token, 1.28 tokens per second) 10.59.760.559 I slot print_timing: id 1 | task 7483 | total time = 4754.38 ms / 714 tokens 10.59.760.560 I slot print_timing: id 1 | task 7483 | graphs reused = 6235 10.59.760.560 I slot print_timing: id 1 | task 7483 | graph reallocs = 0 / 0 (same size) / (changed size) 10.59.760.613 I slot release: id 1 | task 7483 | stop processing: n_tokens = 722, truncated = 0 10.59.763.096 I slot print_timing: id 3 | task 7482 | prompt eval time = 3975.14 ms / 748 tokens ( 5.31 ms per token, 188.17 tokens per second) 10.59.763.099 I slot print_timing: id 3 | task 7482 | eval time = 779.75 ms / 2 tokens ( 779.75 ms per token, 1.28 tokens per second) 10.59.763.100 I slot print_timing: id 3 | task 7482 | total time = 4754.89 ms / 750 tokens 10.59.763.100 I slot print_timing: id 3 | task 7482 | graphs reused = 6235 10.59.763.100 I slot print_timing: id 3 | task 7482 | graph reallocs = 0 / 0 (same size) / (changed size) 10.59.763.135 I slot release: id 3 | task 7482 | stop processing: n_tokens = 758, truncated = 0 11.00.181.147 I slot print_timing: id 2 | task 7488 | prompt eval time = 1619.80 ms / 101 tokens ( 16.04 ms per token, 62.35 tokens per second) 11.00.181.151 I slot print_timing: id 2 | task 7488 | eval time = 419.24 ms / 2 tokens ( 419.24 ms per token, 2.39 tokens per second) 11.00.181.152 I slot print_timing: id 2 | task 7488 | total time = 2039.04 ms / 103 tokens 11.00.181.152 I slot print_timing: id 2 | task 7488 | graphs reused = 6235 11.00.181.154 I slot print_timing: id 2 | task 7488 | graph reallocs = 0 / 0 (same size) / (changed size) 11.00.181.217 I slot release: id 2 | task 7488 | stop processing: n_tokens = 740, truncated = 0 11.00.181.233 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 722, t_last = 324283958156 11.00.181.379 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 231.434 MiB) 11.00.191.624 I slot launch_slot_: id 1 | task 7492 | processing task, is_child = 0 11.00.191.695 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 235.513 MiB) 11.00.198.220 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.465 MiB) 11.00.203.641 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 758, t_last = 324283960678 11.00.203.785 I slot launch_slot_: id 3 | task 7493 | processing task, is_child = 0 11.00.203.847 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 324284378760 11.00.203.943 I slot launch_slot_: id 2 | task 7494 | processing task, is_child = 0 11.04.841.308 I slot print_timing: id 0 | task 7487 | prompt eval time = 4261.82 ms / 796 tokens ( 5.35 ms per token, 186.77 tokens per second) 11.04.841.311 I slot print_timing: id 0 | task 7487 | eval time = 2439.30 ms / 2 tokens ( 2439.30 ms per token, 0.41 tokens per second) 11.04.841.311 I slot print_timing: id 0 | task 7487 | total time = 6701.12 ms / 798 tokens 11.04.841.312 I slot print_timing: id 0 | task 7487 | graphs reused = 6235 11.04.841.312 I slot print_timing: id 0 | task 7487 | graph reallocs = 0 / 0 (same size) / (changed size) 11.04.841.383 I slot release: id 0 | task 7487 | stop processing: n_tokens = 806, truncated = 0 11.04.841.410 I slot print_timing: id 1 | task 7492 | prompt processing, n_tokens = 672, progress = 0.84, t = 4.63 s / 145.00 tokens per second 11.04.845.000 I slot print_timing: id 2 | task 7494 | prompt processing, n_tokens = 672, progress = 0.85, t = 4.63 s / 145.01 tokens per second 11.04.846.720 I slot print_timing: id 3 | task 7493 | prompt processing, n_tokens = 891, progress = 0.86, t = 4.63 s / 192.27 tokens per second 11.05.616.467 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 324289038926 11.05.616.553 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.787 MiB) 11.05.710.250 I slot launch_slot_: id 0 | task 7498 | processing task, is_child = 0 11.05.710.462 I slot print_timing: id 1 | task 7492 | prompt processing, n_tokens = 799, progress = 1.00, t = 5.41 s / 147.67 tokens per second 11.05.712.709 I slot print_timing: id 2 | task 7494 | prompt processing, n_tokens = 789, progress = 1.00, t = 5.41 s / 145.83 tokens per second 11.05.714.530 I slot print_timing: id 3 | task 7493 | prompt processing, n_tokens = 1039, progress = 1.00, t = 5.41 s / 192.04 tokens per second 11.07.242.003 I slot print_timing: id 1 | task 7492 | prompt eval time = 6198.48 ms / 803 tokens ( 7.72 ms per token, 129.55 tokens per second) 11.07.242.014 I slot print_timing: id 1 | task 7492 | eval time = 837.78 ms / 2 tokens ( 837.78 ms per token, 1.19 tokens per second) 11.07.242.014 I slot print_timing: id 1 | task 7492 | total time = 7036.26 ms / 805 tokens 11.07.242.015 I slot print_timing: id 1 | task 7492 | graphs reused = 6235 11.07.242.015 I slot print_timing: id 1 | task 7492 | graph reallocs = 0 / 0 (same size) / (changed size) 11.07.242.090 I slot release: id 1 | task 7492 | stop processing: n_tokens = 813, truncated = 0 11.07.243.364 I slot print_timing: id 2 | task 7494 | prompt eval time = 6199.56 ms / 793 tokens ( 7.82 ms per token, 127.91 tokens per second) 11.07.243.369 I slot print_timing: id 2 | task 7494 | eval time = 837.90 ms / 2 tokens ( 837.90 ms per token, 1.19 tokens per second) 11.07.243.370 I slot print_timing: id 2 | task 7494 | total time = 7037.46 ms / 795 tokens 11.07.243.370 I slot print_timing: id 2 | task 7494 | graphs reused = 6235 11.07.243.370 I slot print_timing: id 2 | task 7494 | graph reallocs = 0 / 0 (same size) / (changed size) 11.07.243.408 I slot release: id 2 | task 7494 | stop processing: n_tokens = 803, truncated = 0 11.07.244.647 I slot print_timing: id 3 | task 7493 | prompt eval time = 6200.62 ms / 1043 tokens ( 5.94 ms per token, 168.21 tokens per second) 11.07.244.648 I slot print_timing: id 3 | task 7493 | eval time = 837.97 ms / 2 tokens ( 837.97 ms per token, 1.19 tokens per second) 11.07.244.649 I slot print_timing: id 3 | task 7493 | total time = 7038.59 ms / 1045 tokens 11.07.244.649 I slot print_timing: id 3 | task 7493 | graphs reused = 6235 11.07.244.649 I slot print_timing: id 3 | task 7493 | graph reallocs = 0 / 0 (same size) / (changed size) 11.07.244.680 I slot release: id 3 | task 7493 | stop processing: n_tokens = 1053, truncated = 0 11.07.552.972 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 813, t_last = 324291439633 11.07.553.052 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.073 MiB) 11.07.559.539 I slot launch_slot_: id 1 | task 7503 | processing task, is_child = 0 11.07.559.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.917 MiB) 11.07.565.216 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 241.139 MiB) 11.07.576.369 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 324291440951 11.07.576.507 I slot launch_slot_: id 2 | task 7504 | processing task, is_child = 0 11.07.576.584 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1053, t_last = 324291442223 11.07.576.688 I slot launch_slot_: id 3 | task 7505 | processing task, is_child = 0 11.09.798.195 I slot print_timing: id 0 | task 7498 | prompt eval time = 1842.70 ms / 836 tokens ( 2.20 ms per token, 453.68 tokens per second) 11.09.798.199 I slot print_timing: id 0 | task 7498 | eval time = 2245.21 ms / 2 tokens ( 2245.21 ms per token, 0.45 tokens per second) 11.09.798.199 I slot print_timing: id 0 | task 7498 | total time = 4087.92 ms / 838 tokens 11.09.798.200 I slot print_timing: id 0 | task 7498 | graphs reused = 6235 11.09.798.200 I slot print_timing: id 0 | task 7498 | graph reallocs = 0 / 0 (same size) / (changed size) 11.09.798.278 I slot release: id 0 | task 7498 | stop processing: n_tokens = 846, truncated = 0 11.11.791.911 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.869 (> 0.100 thold), f_keep = 0.884 11.11.792.000 I slot launch_slot_: id 0 | task 7508 | processing task, is_child = 0 11.11.996.379 I slot print_timing: id 1 | task 7503 | prompt processing, n_tokens = 712, progress = 0.79, t = 4.22 s / 168.91 tokens per second 11.11.998.419 I slot print_timing: id 2 | task 7504 | prompt processing, n_tokens = 712, progress = 0.86, t = 4.22 s / 168.92 tokens per second 11.12.000.328 I slot print_timing: id 3 | task 7505 | prompt processing, n_tokens = 712, progress = 0.80, t = 4.21 s / 168.93 tokens per second 11.13.369.829 I slot print_timing: id 1 | task 7503 | prompt processing, n_tokens = 895, progress = 1.00, t = 5.59 s / 160.20 tokens per second 11.13.373.092 I slot print_timing: id 2 | task 7504 | prompt processing, n_tokens = 824, progress = 1.00, t = 5.59 s / 147.50 tokens per second 11.13.374.884 I slot print_timing: id 3 | task 7505 | prompt processing, n_tokens = 889, progress = 1.00, t = 5.59 s / 159.14 tokens per second 11.13.507.396 I slot print_timing: id 0 | task 7508 | prompt eval time = 1671.71 ms / 113 tokens ( 14.79 ms per token, 67.60 tokens per second) 11.13.507.400 I slot print_timing: id 0 | task 7508 | eval time = 43.66 ms / 2 tokens ( 43.66 ms per token, 22.90 tokens per second) 11.13.507.400 I slot print_timing: id 0 | task 7508 | total time = 1715.38 ms / 115 tokens 11.13.507.401 I slot print_timing: id 0 | task 7508 | graphs reused = 6235 11.13.507.402 I slot print_timing: id 0 | task 7508 | graph reallocs = 0 / 0 (same size) / (changed size) 11.13.507.445 I slot release: id 0 | task 7508 | stop processing: n_tokens = 862, truncated = 0 11.13.508.648 I slot print_timing: id 1 | task 7503 | prompt eval time = 5888.15 ms / 899 tokens ( 6.55 ms per token, 152.68 tokens per second) 11.13.508.651 I slot print_timing: id 1 | task 7503 | eval time = 43.80 ms / 2 tokens ( 43.80 ms per token, 22.83 tokens per second) 11.13.508.651 I slot print_timing: id 1 | task 7503 | total time = 5931.95 ms / 901 tokens 11.13.508.651 I slot print_timing: id 1 | task 7503 | graphs reused = 6235 11.13.508.652 I slot print_timing: id 1 | task 7503 | graph reallocs = 0 / 0 (same size) / (changed size) 11.13.508.678 I slot release: id 1 | task 7503 | stop processing: n_tokens = 909, truncated = 0 11.13.509.810 I slot print_timing: id 2 | task 7504 | prompt eval time = 5889.01 ms / 828 tokens ( 7.11 ms per token, 140.60 tokens per second) 11.13.509.815 I slot print_timing: id 2 | task 7504 | eval time = 43.91 ms / 2 tokens ( 43.91 ms per token, 22.77 tokens per second) 11.13.509.815 I slot print_timing: id 2 | task 7504 | total time = 5932.92 ms / 830 tokens 11.13.509.816 I slot print_timing: id 2 | task 7504 | graphs reused = 6235 11.13.509.816 I slot print_timing: id 2 | task 7504 | graph reallocs = 0 / 0 (same size) / (changed size) 11.13.509.838 I slot release: id 2 | task 7504 | stop processing: n_tokens = 838, truncated = 0 11.13.510.995 I slot print_timing: id 3 | task 7505 | prompt eval time = 5889.97 ms / 893 tokens ( 6.60 ms per token, 151.61 tokens per second) 11.13.510.997 I slot print_timing: id 3 | task 7505 | eval time = 43.99 ms / 2 tokens ( 43.99 ms per token, 22.73 tokens per second) 11.13.510.997 I slot print_timing: id 3 | task 7505 | total time = 5933.96 ms / 895 tokens 11.13.510.998 I slot print_timing: id 3 | task 7505 | graphs reused = 6235 11.13.510.998 I slot print_timing: id 3 | task 7505 | graph reallocs = 0 / 0 (same size) / (changed size) 11.13.511.021 I slot release: id 3 | task 7505 | stop processing: n_tokens = 903, truncated = 0 11.13.515.749 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 862, t_last = 324297704988 11.13.515.838 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 298.767 MiB) 11.13.529.635 I slot launch_slot_: id 0 | task 7512 | processing task, is_child = 0 11.13.529.712 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 243.671 MiB) 11.13.539.914 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 241.420 MiB) 11.13.552.962 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.870 MiB) 11.13.576.299 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 909, t_last = 324297706221 11.13.576.454 I slot launch_slot_: id 1 | task 7513 | processing task, is_child = 0 11.13.576.584 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 838, t_last = 324297707381 11.13.576.678 I slot launch_slot_: id 2 | task 7514 | processing task, is_child = 0 11.13.576.749 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 324297708564 11.13.576.847 I slot launch_slot_: id 3 | task 7515 | processing task, is_child = 0 11.18.707.618 I slot print_timing: id 0 | task 7512 | prompt processing, n_tokens = 576, progress = 0.85, t = 5.13 s / 112.26 tokens per second 11.18.785.384 I slot print_timing: id 1 | task 7513 | prompt processing, n_tokens = 615, progress = 0.82, t = 5.13 s / 119.87 tokens per second 11.18.787.285 I slot print_timing: id 2 | task 7514 | prompt processing, n_tokens = 701, progress = 0.85, t = 5.13 s / 136.64 tokens per second 11.18.789.185 I slot print_timing: id 3 | task 7515 | prompt processing, n_tokens = 701, progress = 0.83, t = 5.13 s / 136.64 tokens per second 11.19.837.602 I slot print_timing: id 0 | task 7512 | prompt processing, n_tokens = 678, progress = 0.99, t = 6.26 s / 108.29 tokens per second 11.19.928.430 I slot print_timing: id 1 | task 7513 | prompt processing, n_tokens = 746, progress = 0.99, t = 6.26 s / 119.16 tokens per second 11.19.931.879 I slot print_timing: id 2 | task 7514 | prompt processing, n_tokens = 818, progress = 1.00, t = 6.26 s / 130.66 tokens per second 11.19.933.643 I slot print_timing: id 3 | task 7515 | prompt processing, n_tokens = 841, progress = 1.00, t = 6.26 s / 134.34 tokens per second 11.20.065.609 I slot print_timing: id 0 | task 7512 | prompt eval time = 6445.39 ms / 682 tokens ( 9.45 ms per token, 105.81 tokens per second) 11.20.065.614 I slot print_timing: id 0 | task 7512 | eval time = 43.36 ms / 2 tokens ( 43.36 ms per token, 23.06 tokens per second) 11.20.065.614 I slot print_timing: id 0 | task 7512 | total time = 6488.75 ms / 684 tokens 11.20.065.615 I slot print_timing: id 0 | task 7512 | graphs reused = 6235 11.20.065.615 I slot print_timing: id 0 | task 7512 | graph reallocs = 0 / 0 (same size) / (changed size) 11.20.065.650 I slot release: id 0 | task 7512 | stop processing: n_tokens = 692, truncated = 0 11.20.066.734 I slot print_timing: id 1 | task 7513 | prompt eval time = 6446.28 ms / 750 tokens ( 8.60 ms per token, 116.35 tokens per second) 11.20.066.735 I slot print_timing: id 1 | task 7513 | eval time = 43.39 ms / 2 tokens ( 43.39 ms per token, 23.04 tokens per second) 11.20.066.737 I slot print_timing: id 1 | task 7513 | total time = 6489.68 ms / 752 tokens 11.20.066.737 I slot print_timing: id 1 | task 7513 | graphs reused = 6235 11.20.066.737 I slot print_timing: id 1 | task 7513 | graph reallocs = 0 / 0 (same size) / (changed size) 11.20.066.763 I slot release: id 1 | task 7513 | stop processing: n_tokens = 760, truncated = 0 11.20.067.850 I slot print_timing: id 2 | task 7514 | prompt eval time = 6447.17 ms / 822 tokens ( 7.84 ms per token, 127.50 tokens per second) 11.20.067.852 I slot print_timing: id 2 | task 7514 | eval time = 43.44 ms / 2 tokens ( 43.44 ms per token, 23.02 tokens per second) 11.20.067.852 I slot print_timing: id 2 | task 7514 | total time = 6490.61 ms / 824 tokens 11.20.067.853 I slot print_timing: id 2 | task 7514 | graphs reused = 6235 11.20.067.853 I slot print_timing: id 2 | task 7514 | graph reallocs = 0 / 0 (same size) / (changed size) 11.20.067.884 I slot release: id 2 | task 7514 | stop processing: n_tokens = 832, truncated = 0 11.20.068.980 I slot print_timing: id 3 | task 7515 | prompt eval time = 6448.16 ms / 845 tokens ( 7.63 ms per token, 131.05 tokens per second) 11.20.068.982 I slot print_timing: id 3 | task 7515 | eval time = 43.42 ms / 2 tokens ( 43.42 ms per token, 23.03 tokens per second) 11.20.068.983 I slot print_timing: id 3 | task 7515 | total time = 6491.59 ms / 847 tokens 11.20.068.983 I slot print_timing: id 3 | task 7515 | graphs reused = 6235 11.20.068.983 I slot print_timing: id 3 | task 7515 | graph reallocs = 0 / 0 (same size) / (changed size) 11.20.069.009 I slot release: id 3 | task 7515 | stop processing: n_tokens = 855, truncated = 0 11.20.073.429 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 692, t_last = 324304263193 11.20.073.517 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 246.906 MiB) 11.20.086.505 I slot launch_slot_: id 0 | task 7521 | processing task, is_child = 0 11.20.086.572 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.870 MiB) 11.20.092.050 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 298.310 MiB) 11.20.109.392 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 240.436 MiB) 11.20.136.047 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 760, t_last = 324304264306 11.20.136.173 I slot launch_slot_: id 1 | task 7522 | processing task, is_child = 0 11.20.136.301 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 832, t_last = 324304265427 11.20.138.377 I slot launch_slot_: id 2 | task 7523 | processing task, is_child = 0 11.20.138.445 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 324304266552 11.20.138.553 I slot launch_slot_: id 3 | task 7524 | processing task, is_child = 0 11.23.413.626 I slot print_timing: id 0 | task 7521 | prompt processing, n_tokens = 590, progress = 0.84, t = 3.28 s / 180.15 tokens per second 11.23.975.922 I slot print_timing: id 1 | task 7522 | prompt processing, n_tokens = 590, progress = 0.82, t = 3.27 s / 180.16 tokens per second 11.23.979.199 I slot print_timing: id 2 | task 7523 | prompt processing, n_tokens = 118, progress = 0.99, t = 3.27 s / 36.03 tokens per second 11.23.981.192 I slot print_timing: id 3 | task 7524 | prompt processing, n_tokens = 590, progress = 0.84, t = 3.27 s / 180.32 tokens per second 11.24.863.674 I slot print_timing: id 0 | task 7521 | prompt processing, n_tokens = 697, progress = 0.99, t = 4.72 s / 147.55 tokens per second 11.24.867.491 I slot print_timing: id 1 | task 7522 | prompt processing, n_tokens = 719, progress = 0.99, t = 4.72 s / 152.21 tokens per second 11.24.870.485 I slot print_timing: id 3 | task 7524 | prompt processing, n_tokens = 702, progress = 0.99, t = 4.72 s / 148.70 tokens per second 11.24.986.733 I slot print_timing: id 2 | task 7523 | prompt eval time = 4724.77 ms / 122 tokens ( 38.73 ms per token, 25.82 tokens per second) 11.24.986.736 I slot print_timing: id 2 | task 7523 | eval time = 123.09 ms / 2 tokens ( 123.09 ms per token, 8.12 tokens per second) 11.24.986.737 I slot print_timing: id 2 | task 7523 | total time = 4847.86 ms / 124 tokens 11.24.986.737 I slot print_timing: id 2 | task 7523 | graphs reused = 6235 11.24.986.738 I slot print_timing: id 2 | task 7523 | graph reallocs = 0 / 0 (same size) / (changed size) 11.24.986.776 I slot release: id 2 | task 7523 | stop processing: n_tokens = 746, truncated = 0 11.25.049.164 I slot print_timing: id 0 | task 7521 | prompt eval time = 4845.94 ms / 701 tokens ( 6.91 ms per token, 144.66 tokens per second) 11.25.049.169 I slot print_timing: id 0 | task 7521 | eval time = 64.66 ms / 2 tokens ( 64.66 ms per token, 15.46 tokens per second) 11.25.049.169 I slot print_timing: id 0 | task 7521 | total time = 4910.60 ms / 703 tokens 11.25.049.170 I slot print_timing: id 0 | task 7521 | graphs reused = 6235 11.25.049.170 I slot print_timing: id 0 | task 7521 | graph reallocs = 0 / 0 (same size) / (changed size) 11.25.049.204 I slot release: id 0 | task 7521 | stop processing: n_tokens = 711, truncated = 0 11.25.050.360 I slot print_timing: id 1 | task 7522 | prompt eval time = 4846.93 ms / 723 tokens ( 6.70 ms per token, 149.17 tokens per second) 11.25.050.362 I slot print_timing: id 1 | task 7522 | eval time = 64.71 ms / 2 tokens ( 64.71 ms per token, 15.45 tokens per second) 11.25.050.362 I slot print_timing: id 1 | task 7522 | total time = 4911.64 ms / 725 tokens 11.25.050.363 I slot print_timing: id 1 | task 7522 | graphs reused = 6235 11.25.050.363 I slot print_timing: id 1 | task 7522 | graph reallocs = 0 / 0 (same size) / (changed size) 11.25.050.384 I slot release: id 1 | task 7522 | stop processing: n_tokens = 733, truncated = 0 11.25.051.526 I slot print_timing: id 3 | task 7524 | prompt eval time = 4846.23 ms / 706 tokens ( 6.86 ms per token, 145.68 tokens per second) 11.25.051.530 I slot print_timing: id 3 | task 7524 | eval time = 63.58 ms / 2 tokens ( 63.58 ms per token, 15.73 tokens per second) 11.25.051.532 I slot print_timing: id 3 | task 7524 | total time = 4909.82 ms / 708 tokens 11.25.051.532 I slot print_timing: id 3 | task 7524 | graphs reused = 6235 11.25.051.532 I slot print_timing: id 3 | task 7524 | graph reallocs = 0 / 0 (same size) / (changed size) 11.25.051.552 I slot release: id 3 | task 7524 | stop processing: n_tokens = 716, truncated = 0 11.25.051.558 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.880 11.25.051.626 I slot launch_slot_: id 0 | task 7530 | processing task, is_child = 0 11.25.068.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.638 MiB) 11.25.079.995 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.638 MiB) 11.25.085.218 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.854 11.25.085.300 I slot launch_slot_: id 1 | task 7531 | processing task, is_child = 0 11.25.085.419 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.874 11.25.085.456 I slot launch_slot_: id 3 | task 7532 | processing task, is_child = 0 11.25.085.518 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 324309184319 11.25.087.520 I slot launch_slot_: id 2 | task 7533 | processing task, is_child = 0 11.26.099.992 I slot print_timing: id 0 | task 7530 | prompt eval time = 908.86 ms / 82 tokens ( 11.08 ms per token, 90.22 tokens per second) 11.26.099.996 I slot print_timing: id 0 | task 7530 | eval time = 103.59 ms / 2 tokens ( 103.59 ms per token, 9.65 tokens per second) 11.26.099.997 I slot print_timing: id 0 | task 7530 | total time = 1012.45 ms / 84 tokens 11.26.099.998 I slot print_timing: id 0 | task 7530 | graphs reused = 6235 11.26.099.998 I slot print_timing: id 0 | task 7530 | graph reallocs = 0 / 0 (same size) / (changed size) 11.26.100.040 I slot release: id 0 | task 7530 | stop processing: n_tokens = 709, truncated = 0 11.26.101.592 I slot print_timing: id 1 | task 7531 | prompt eval time = 908.48 ms / 85 tokens ( 10.69 ms per token, 93.56 tokens per second) 11.26.101.594 I slot print_timing: id 1 | task 7531 | eval time = 103.88 ms / 2 tokens ( 103.88 ms per token, 9.63 tokens per second) 11.26.101.596 I slot print_timing: id 1 | task 7531 | total time = 1012.36 ms / 87 tokens 11.26.101.596 I slot print_timing: id 1 | task 7531 | graphs reused = 6235 11.26.101.597 I slot print_timing: id 1 | task 7531 | graph reallocs = 0 / 0 (same size) / (changed size) 11.26.101.621 I slot release: id 1 | task 7531 | stop processing: n_tokens = 712, truncated = 0 11.26.104.670 I slot print_timing: id 3 | task 7532 | prompt eval time = 904.50 ms / 79 tokens ( 11.45 ms per token, 87.34 tokens per second) 11.26.104.674 I slot print_timing: id 3 | task 7532 | eval time = 105.73 ms / 2 tokens ( 105.73 ms per token, 9.46 tokens per second) 11.26.104.675 I slot print_timing: id 3 | task 7532 | total time = 1010.24 ms / 81 tokens 11.26.104.675 I slot print_timing: id 3 | task 7532 | graphs reused = 6235 11.26.104.676 I slot print_timing: id 3 | task 7532 | graph reallocs = 0 / 0 (same size) / (changed size) 11.26.104.699 I slot release: id 3 | task 7532 | stop processing: n_tokens = 706, truncated = 0 11.26.131.083 I slot print_timing: id 2 | task 7533 | prompt eval time = 1012.30 ms / 105 tokens ( 9.64 ms per token, 103.72 tokens per second) 11.26.131.086 I slot print_timing: id 2 | task 7533 | eval time = 27.88 ms / 2 tokens ( 27.88 ms per token, 35.87 tokens per second) 11.26.131.088 I slot print_timing: id 2 | task 7533 | total time = 1040.17 ms / 107 tokens 11.26.131.088 I slot print_timing: id 2 | task 7533 | graphs reused = 6235 11.26.131.089 I slot print_timing: id 2 | task 7533 | graph reallocs = 0 / 0 (same size) / (changed size) 11.26.131.123 I slot release: id 2 | task 7533 | stop processing: n_tokens = 704, truncated = 0 11.26.131.131 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 11.26.131.201 I slot launch_slot_: id 2 | task 7538 | processing task, is_child = 0 11.26.152.717 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 289.766 MiB) 11.26.165.237 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.499 MiB) 11.26.173.284 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.891 11.26.173.393 I slot launch_slot_: id 3 | task 7539 | processing task, is_child = 0 11.26.173.555 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.838 (> 0.100 thold), f_keep = 0.883 11.26.173.602 I slot launch_slot_: id 0 | task 7540 | processing task, is_child = 0 11.26.173.677 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.879 11.26.173.718 I slot launch_slot_: id 1 | task 7541 | processing task, is_child = 0 11.27.170.801 I slot print_timing: id 0 | task 7540 | prompt eval time = 953.64 ms / 121 tokens ( 7.88 ms per token, 126.88 tokens per second) 11.27.170.803 I slot print_timing: id 0 | task 7540 | eval time = 43.43 ms / 2 tokens ( 43.43 ms per token, 23.03 tokens per second) 11.27.170.803 I slot print_timing: id 0 | task 7540 | total time = 997.07 ms / 123 tokens 11.27.170.804 I slot print_timing: id 0 | task 7540 | graphs reused = 6235 11.27.170.804 I slot print_timing: id 0 | task 7540 | graph reallocs = 0 / 0 (same size) / (changed size) 11.27.170.849 I slot release: id 0 | task 7540 | stop processing: n_tokens = 748, truncated = 0 11.27.171.955 I slot print_timing: id 1 | task 7541 | prompt eval time = 952.06 ms / 80 tokens ( 11.90 ms per token, 84.03 tokens per second) 11.27.171.956 I slot print_timing: id 1 | task 7541 | eval time = 43.44 ms / 2 tokens ( 43.44 ms per token, 23.02 tokens per second) 11.27.171.956 I slot print_timing: id 1 | task 7541 | total time = 995.50 ms / 82 tokens 11.27.171.957 I slot print_timing: id 1 | task 7541 | graphs reused = 6235 11.27.171.957 I slot print_timing: id 1 | task 7541 | graph reallocs = 0 / 0 (same size) / (changed size) 11.27.171.978 I slot release: id 1 | task 7541 | stop processing: n_tokens = 707, truncated = 0 11.27.173.079 I slot print_timing: id 2 | task 7538 | prompt eval time = 950.92 ms / 86 tokens ( 11.06 ms per token, 90.44 tokens per second) 11.27.173.086 I slot print_timing: id 2 | task 7538 | eval time = 43.49 ms / 2 tokens ( 43.49 ms per token, 22.99 tokens per second) 11.27.173.086 I slot print_timing: id 2 | task 7538 | total time = 994.41 ms / 88 tokens 11.27.173.086 I slot print_timing: id 2 | task 7538 | graphs reused = 6235 11.27.173.087 I slot print_timing: id 2 | task 7538 | graph reallocs = 0 / 0 (same size) / (changed size) 11.27.173.107 I slot release: id 2 | task 7538 | stop processing: n_tokens = 714, truncated = 0 11.27.174.189 I slot print_timing: id 3 | task 7539 | prompt eval time = 949.99 ms / 86 tokens ( 11.05 ms per token, 90.53 tokens per second) 11.27.174.196 I slot print_timing: id 3 | task 7539 | eval time = 43.49 ms / 2 tokens ( 43.49 ms per token, 22.99 tokens per second) 11.27.174.196 I slot print_timing: id 3 | task 7539 | total time = 993.48 ms / 88 tokens 11.27.174.196 I slot print_timing: id 3 | task 7539 | graphs reused = 6235 11.27.174.196 I slot print_timing: id 3 | task 7539 | graph reallocs = 0 / 0 (same size) / (changed size) 11.27.174.217 I slot release: id 3 | task 7539 | stop processing: n_tokens = 716, truncated = 0 11.27.178.322 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 324311368393 11.27.178.405 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.112 MiB) 11.27.184.909 I slot launch_slot_: id 0 | task 7545 | processing task, is_child = 0 11.27.184.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.398 MiB) 11.27.203.554 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 368.363 MiB) 11.27.215.758 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.694 MiB) 11.27.241.744 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 324311369521 11.27.241.873 I slot launch_slot_: id 1 | task 7546 | processing task, is_child = 0 11.27.241.991 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 324311370650 11.27.242.088 I slot launch_slot_: id 2 | task 7547 | processing task, is_child = 0 11.27.242.157 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 716, t_last = 324311371760 11.27.242.247 I slot launch_slot_: id 3 | task 7548 | processing task, is_child = 0 11.30.932.955 I slot print_timing: id 0 | task 7545 | prompt processing, n_tokens = 380, progress = 0.43, t = 3.69 s / 102.96 tokens per second 11.31.005.463 I slot print_timing: id 1 | task 7546 | prompt processing, n_tokens = 363, progress = 0.42, t = 3.69 s / 98.36 tokens per second 11.31.008.468 I slot print_timing: id 2 | task 7547 | prompt processing, n_tokens = 573, progress = 0.53, t = 3.69 s / 155.27 tokens per second 11.31.011.299 I slot print_timing: id 3 | task 7548 | prompt processing, n_tokens = 583, progress = 0.53, t = 3.69 s / 157.99 tokens per second 11.33.867.594 I slot print_timing: id 0 | task 7545 | prompt processing, n_tokens = 761, progress = 0.85, t = 6.63 s / 114.86 tokens per second 11.33.957.381 I slot print_timing: id 1 | task 7546 | prompt processing, n_tokens = 761, progress = 0.87, t = 6.63 s / 114.87 tokens per second 11.33.959.579 I slot print_timing: id 2 | task 7547 | prompt processing, n_tokens = 909, progress = 0.84, t = 6.62 s / 137.21 tokens per second 11.33.961.577 I slot print_timing: id 3 | task 7548 | prompt processing, n_tokens = 909, progress = 0.83, t = 6.62 s / 137.21 tokens per second 11.35.260.257 I slot print_timing: id 0 | task 7545 | prompt processing, n_tokens = 892, progress = 1.00, t = 8.02 s / 111.25 tokens per second 11.35.334.269 I slot print_timing: id 1 | task 7546 | prompt processing, n_tokens = 875, progress = 1.00, t = 8.02 s / 109.13 tokens per second 11.35.338.053 I slot print_timing: id 2 | task 7547 | prompt processing, n_tokens = 1085, progress = 1.00, t = 8.02 s / 135.33 tokens per second 11.35.339.895 I slot print_timing: id 3 | task 7548 | prompt processing, n_tokens = 1095, progress = 1.00, t = 8.02 s / 136.58 tokens per second 11.35.472.725 I slot print_timing: id 0 | task 7545 | prompt eval time = 8186.80 ms / 896 tokens ( 9.14 ms per token, 109.44 tokens per second) 11.35.472.728 I slot print_timing: id 0 | task 7545 | eval time = 43.67 ms / 2 tokens ( 43.67 ms per token, 22.90 tokens per second) 11.35.472.729 I slot print_timing: id 0 | task 7545 | total time = 8230.47 ms / 898 tokens 11.35.472.729 I slot print_timing: id 0 | task 7545 | graphs reused = 6235 11.35.472.730 I slot print_timing: id 0 | task 7545 | graph reallocs = 0 / 0 (same size) / (changed size) 11.35.472.771 I slot release: id 0 | task 7545 | stop processing: n_tokens = 906, truncated = 0 11.35.473.847 I slot print_timing: id 1 | task 7546 | prompt eval time = 8187.72 ms / 879 tokens ( 9.31 ms per token, 107.36 tokens per second) 11.35.473.849 I slot print_timing: id 1 | task 7546 | eval time = 43.65 ms / 2 tokens ( 43.65 ms per token, 22.91 tokens per second) 11.35.473.849 I slot print_timing: id 1 | task 7546 | total time = 8231.37 ms / 881 tokens 11.35.473.849 I slot print_timing: id 1 | task 7546 | graphs reused = 6235 11.35.473.850 I slot print_timing: id 1 | task 7546 | graph reallocs = 0 / 0 (same size) / (changed size) 11.35.473.874 I slot release: id 1 | task 7546 | stop processing: n_tokens = 889, truncated = 0 11.35.474.951 I slot print_timing: id 2 | task 7547 | prompt eval time = 8188.68 ms / 1089 tokens ( 7.52 ms per token, 132.99 tokens per second) 11.35.474.953 I slot print_timing: id 2 | task 7547 | eval time = 43.64 ms / 2 tokens ( 43.64 ms per token, 22.91 tokens per second) 11.35.474.958 I slot print_timing: id 2 | task 7547 | total time = 8232.32 ms / 1091 tokens 11.35.474.959 I slot print_timing: id 2 | task 7547 | graphs reused = 6235 11.35.474.959 I slot print_timing: id 2 | task 7547 | graph reallocs = 0 / 0 (same size) / (changed size) 11.35.474.995 I slot release: id 2 | task 7547 | stop processing: n_tokens = 1099, truncated = 0 11.35.476.085 I slot print_timing: id 3 | task 7548 | prompt eval time = 8189.64 ms / 1099 tokens ( 7.45 ms per token, 134.19 tokens per second) 11.35.476.087 I slot print_timing: id 3 | task 7548 | eval time = 43.68 ms / 2 tokens ( 43.68 ms per token, 22.89 tokens per second) 11.35.476.087 I slot print_timing: id 3 | task 7548 | total time = 8233.31 ms / 1101 tokens 11.35.476.088 I slot print_timing: id 3 | task 7548 | graphs reused = 6235 11.35.476.088 I slot print_timing: id 3 | task 7548 | graph reallocs = 0 / 0 (same size) / (changed size) 11.35.476.113 I slot release: id 3 | task 7548 | stop processing: n_tokens = 1109, truncated = 0 11.35.482.060 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.894 11.35.482.101 I slot launch_slot_: id 3 | task 7554 | processing task, is_child = 0 11.35.482.173 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.451 MiB) 11.35.507.164 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 338.646 MiB) 11.35.513.555 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.901 11.35.513.623 I slot launch_slot_: id 2 | task 7555 | processing task, is_child = 0 11.35.513.760 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 906, t_last = 324319670314 11.35.516.167 I slot launch_slot_: id 0 | task 7556 | processing task, is_child = 0 11.35.516.246 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 889, t_last = 324319671417 11.35.516.344 I slot launch_slot_: id 1 | task 7557 | processing task, is_child = 0 11.38.764.413 I slot print_timing: id 2 | task 7555 | prompt eval time = 2765.62 ms / 97 tokens ( 28.51 ms per token, 35.07 tokens per second) 11.38.764.416 I slot print_timing: id 2 | task 7555 | eval time = 479.35 ms / 2 tokens ( 479.35 ms per token, 2.09 tokens per second) 11.38.764.417 I slot print_timing: id 2 | task 7555 | total time = 3244.97 ms / 99 tokens 11.38.764.418 I slot print_timing: id 2 | task 7555 | graphs reused = 6235 11.38.764.418 I slot print_timing: id 2 | task 7555 | graph reallocs = 0 / 0 (same size) / (changed size) 11.38.764.486 I slot release: id 2 | task 7555 | stop processing: n_tokens = 1088, truncated = 0 11.38.765.714 I slot print_timing: id 3 | task 7554 | prompt eval time = 2765.20 ms / 110 tokens ( 25.14 ms per token, 39.78 tokens per second) 11.38.765.725 I slot print_timing: id 3 | task 7554 | eval time = 479.40 ms / 2 tokens ( 479.40 ms per token, 2.09 tokens per second) 11.38.765.726 I slot print_timing: id 3 | task 7554 | total time = 3244.60 ms / 112 tokens 11.38.765.726 I slot print_timing: id 3 | task 7554 | graphs reused = 6235 11.38.765.727 I slot print_timing: id 3 | task 7554 | graph reallocs = 0 / 0 (same size) / (changed size) 11.38.765.761 I slot release: id 3 | task 7554 | stop processing: n_tokens = 1102, truncated = 0 11.38.765.779 I slot print_timing: id 1 | task 7557 | prompt processing, n_tokens = 1083, progress = 1.00, t = 3.24 s / 333.97 tokens per second 11.38.841.611 I slot print_timing: id 0 | task 7556 | prompt eval time = 3246.85 ms / 179 tokens ( 18.14 ms per token, 55.13 tokens per second) 11.38.841.614 I slot print_timing: id 0 | task 7556 | eval time = 78.41 ms / 2 tokens ( 78.41 ms per token, 12.75 tokens per second) 11.38.841.615 I slot print_timing: id 0 | task 7556 | total time = 3325.26 ms / 181 tokens 11.38.841.628 I slot print_timing: id 0 | task 7556 | graphs reused = 6235 11.38.841.628 I slot print_timing: id 0 | task 7556 | graph reallocs = 0 / 0 (same size) / (changed size) 11.38.841.666 I slot release: id 0 | task 7556 | stop processing: n_tokens = 1097, truncated = 0 11.38.842.890 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.903 11.38.842.970 I slot launch_slot_: id 0 | task 7562 | processing task, is_child = 0 11.38.863.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.147 MiB) 11.38.870.668 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.911 11.38.870.744 I slot launch_slot_: id 2 | task 7563 | processing task, is_child = 0 11.38.870.823 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.899 11.38.870.860 I slot launch_slot_: id 3 | task 7564 | processing task, is_child = 0 11.39.614.849 I slot print_timing: id 1 | task 7557 | prompt eval time = 3323.66 ms / 1087 tokens ( 3.06 ms per token, 327.05 tokens per second) 11.39.614.854 I slot print_timing: id 1 | task 7557 | eval time = 771.95 ms / 2 tokens ( 771.95 ms per token, 1.30 tokens per second) 11.39.614.854 I slot print_timing: id 1 | task 7557 | total time = 4095.61 ms / 1089 tokens 11.39.614.855 I slot print_timing: id 1 | task 7557 | graphs reused = 6235 11.39.614.855 I slot print_timing: id 1 | task 7557 | graph reallocs = 0 / 0 (same size) / (changed size) 11.39.614.939 I slot release: id 1 | task 7557 | stop processing: n_tokens = 1097, truncated = 0 11.39.706.334 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 11.39.706.410 I slot launch_slot_: id 1 | task 7567 | processing task, is_child = 0 11.40.044.607 I slot print_timing: id 0 | task 7562 | prompt eval time = 833.12 ms / 98 tokens ( 8.50 ms per token, 117.63 tokens per second) 11.40.044.612 I slot print_timing: id 0 | task 7562 | eval time = 340.61 ms / 2 tokens ( 340.61 ms per token, 2.94 tokens per second) 11.40.044.612 I slot print_timing: id 0 | task 7562 | total time = 1173.73 ms / 100 tokens 11.40.044.613 I slot print_timing: id 0 | task 7562 | graphs reused = 6235 11.40.044.613 I slot print_timing: id 0 | task 7562 | graph reallocs = 0 / 0 (same size) / (changed size) 11.40.044.676 I slot release: id 0 | task 7562 | stop processing: n_tokens = 1090, truncated = 0 11.40.045.819 I slot print_timing: id 2 | task 7563 | prompt eval time = 832.59 ms / 107 tokens ( 7.78 ms per token, 128.52 tokens per second) 11.40.045.823 I slot print_timing: id 2 | task 7563 | eval time = 340.65 ms / 2 tokens ( 340.65 ms per token, 2.94 tokens per second) 11.40.045.824 I slot print_timing: id 2 | task 7563 | total time = 1173.24 ms / 109 tokens 11.40.045.824 I slot print_timing: id 2 | task 7563 | graphs reused = 6235 11.40.045.824 I slot print_timing: id 2 | task 7563 | graph reallocs = 0 / 0 (same size) / (changed size) 11.40.045.859 I slot release: id 2 | task 7563 | stop processing: n_tokens = 1099, truncated = 0 11.40.047.030 I slot print_timing: id 3 | task 7564 | prompt eval time = 831.90 ms / 114 tokens ( 7.30 ms per token, 137.04 tokens per second) 11.40.047.033 I slot print_timing: id 3 | task 7564 | eval time = 340.70 ms / 2 tokens ( 340.70 ms per token, 2.94 tokens per second) 11.40.047.034 I slot print_timing: id 3 | task 7564 | total time = 1172.60 ms / 116 tokens 11.40.047.034 I slot print_timing: id 3 | task 7564 | graphs reused = 6235 11.40.047.034 I slot print_timing: id 3 | task 7564 | graph reallocs = 0 / 0 (same size) / (changed size) 11.40.047.073 I slot release: id 3 | task 7564 | stop processing: n_tokens = 1106, truncated = 0 11.40.089.118 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.909 11.40.089.210 I slot launch_slot_: id 0 | task 7570 | processing task, is_child = 0 11.40.089.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.567 MiB) 11.40.089.338 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 288.402 MiB) 11.40.098.564 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.832 MiB) 11.40.126.963 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.902 11.40.127.050 I slot launch_slot_: id 2 | task 7571 | processing task, is_child = 0 11.40.127.151 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.896 11.40.127.191 I slot launch_slot_: id 3 | task 7572 | processing task, is_child = 0 11.40.865.863 I slot print_timing: id 1 | task 7567 | prompt eval time = 382.69 ms / 108 tokens ( 3.54 ms per token, 282.21 tokens per second) 11.40.865.866 I slot print_timing: id 1 | task 7567 | eval time = 776.74 ms / 2 tokens ( 776.74 ms per token, 1.29 tokens per second) 11.40.865.866 I slot print_timing: id 1 | task 7567 | total time = 1159.44 ms / 110 tokens 11.40.865.867 I slot print_timing: id 1 | task 7567 | graphs reused = 6235 11.40.865.867 I slot print_timing: id 1 | task 7567 | graph reallocs = 0 / 0 (same size) / (changed size) 11.40.865.924 I slot release: id 1 | task 7567 | stop processing: n_tokens = 1100, truncated = 0 11.40.954.069 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 11.40.954.175 I slot launch_slot_: id 1 | task 7575 | processing task, is_child = 0 11.41.294.641 I slot print_timing: id 0 | task 7570 | prompt eval time = 824.55 ms / 105 tokens ( 7.85 ms per token, 127.34 tokens per second) 11.41.294.660 I slot print_timing: id 0 | task 7570 | eval time = 342.83 ms / 2 tokens ( 342.83 ms per token, 2.92 tokens per second) 11.41.294.662 I slot print_timing: id 0 | task 7570 | total time = 1167.39 ms / 107 tokens 11.41.294.663 I slot print_timing: id 0 | task 7570 | graphs reused = 6235 11.41.294.664 I slot print_timing: id 0 | task 7570 | graph reallocs = 0 / 0 (same size) / (changed size) 11.41.294.825 I slot release: id 0 | task 7570 | stop processing: n_tokens = 1097, truncated = 0 11.41.297.005 I slot print_timing: id 2 | task 7571 | prompt eval time = 823.69 ms / 102 tokens ( 8.08 ms per token, 123.83 tokens per second) 11.41.297.011 I slot print_timing: id 2 | task 7571 | eval time = 344.05 ms / 2 tokens ( 344.05 ms per token, 2.91 tokens per second) 11.41.297.013 I slot print_timing: id 2 | task 7571 | total time = 1167.74 ms / 104 tokens 11.41.297.014 I slot print_timing: id 2 | task 7571 | graphs reused = 6235 11.41.297.015 I slot print_timing: id 2 | task 7571 | graph reallocs = 0 / 0 (same size) / (changed size) 11.41.297.094 I slot release: id 2 | task 7571 | stop processing: n_tokens = 1094, truncated = 0 11.41.299.174 I slot print_timing: id 3 | task 7572 | prompt eval time = 822.90 ms / 100 tokens ( 8.23 ms per token, 121.52 tokens per second) 11.41.299.180 I slot print_timing: id 3 | task 7572 | eval time = 345.09 ms / 2 tokens ( 345.09 ms per token, 2.90 tokens per second) 11.41.299.181 I slot print_timing: id 3 | task 7572 | total time = 1167.98 ms / 102 tokens 11.41.299.183 I slot print_timing: id 3 | task 7572 | graphs reused = 6235 11.41.299.184 I slot print_timing: id 3 | task 7572 | graph reallocs = 0 / 0 (same size) / (changed size) 11.41.299.275 I slot release: id 3 | task 7572 | stop processing: n_tokens = 1092, truncated = 0 11.41.345.671 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.903 11.41.345.757 I slot launch_slot_: id 0 | task 7578 | processing task, is_child = 0 11.41.345.919 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.603 MiB) 11.41.362.620 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.275 MiB) 11.41.375.862 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1094, t_last = 324325494637 11.41.376.091 I slot launch_slot_: id 2 | task 7579 | processing task, is_child = 0 11.41.376.188 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1092, t_last = 324325496818 11.41.376.337 I slot launch_slot_: id 3 | task 7580 | processing task, is_child = 0 11.43.618.410 I slot print_timing: id 1 | task 7575 | prompt eval time = 391.48 ms / 104 tokens ( 3.76 ms per token, 265.66 tokens per second) 11.43.618.422 I slot print_timing: id 1 | task 7575 | eval time = 2272.71 ms / 2 tokens ( 2272.71 ms per token, 0.44 tokens per second) 11.43.618.424 I slot print_timing: id 1 | task 7575 | total time = 2664.19 ms / 106 tokens 11.43.618.425 I slot print_timing: id 1 | task 7575 | graphs reused = 6235 11.43.618.427 I slot print_timing: id 1 | task 7575 | graph reallocs = 0 / 0 (same size) / (changed size) 11.43.618.570 I slot release: id 1 | task 7575 | stop processing: n_tokens = 1096, truncated = 0 11.45.205.990 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1096, t_last = 324327816114 11.45.206.340 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.040 MiB) 11.45.206.359 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.106 MiB) 11.45.229.921 I slot launch_slot_: id 1 | task 7583 | processing task, is_child = 0 11.45.230.382 I slot print_timing: id 2 | task 7579 | prompt processing, n_tokens = 861, progress = 0.86, t = 3.82 s / 225.21 tokens per second 11.45.234.285 I slot print_timing: id 3 | task 7580 | prompt processing, n_tokens = 861, progress = 0.84, t = 3.82 s / 225.23 tokens per second 11.47.021.922 I slot print_timing: id 0 | task 7578 | prompt eval time = 3829.60 ms / 103 tokens ( 37.18 ms per token, 26.90 tokens per second) 11.47.021.935 I slot print_timing: id 0 | task 7578 | eval time = 1815.94 ms / 2 tokens ( 1815.94 ms per token, 0.55 tokens per second) 11.47.021.936 I slot print_timing: id 0 | task 7578 | total time = 5645.54 ms / 105 tokens 11.47.021.938 I slot print_timing: id 0 | task 7578 | graphs reused = 6235 11.47.021.939 I slot print_timing: id 0 | task 7578 | graph reallocs = 0 / 0 (same size) / (changed size) 11.47.022.076 I slot release: id 0 | task 7578 | stop processing: n_tokens = 1095, truncated = 0 11.47.030.313 I slot print_timing: id 2 | task 7579 | prompt processing, n_tokens = 996, progress = 1.00, t = 5.64 s / 176.56 tokens per second 11.47.034.423 I slot print_timing: id 3 | task 7580 | prompt processing, n_tokens = 1017, progress = 1.00, t = 5.64 s / 180.29 tokens per second 11.47.699.668 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1095, t_last = 324331219620 11.47.699.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.104 MiB) 11.47.728.058 I slot launch_slot_: id 0 | task 7586 | processing task, is_child = 0 11.49.302.125 I slot print_timing: id 2 | task 7579 | prompt eval time = 6318.95 ms / 1000 tokens ( 6.32 ms per token, 158.25 tokens per second) 11.49.302.138 I slot print_timing: id 2 | task 7579 | eval time = 1604.81 ms / 2 tokens ( 1604.81 ms per token, 0.62 tokens per second) 11.49.302.140 I slot print_timing: id 2 | task 7579 | total time = 7923.76 ms / 1002 tokens 11.49.302.142 I slot print_timing: id 2 | task 7579 | graphs reused = 6235 11.49.302.143 I slot print_timing: id 2 | task 7579 | graph reallocs = 0 / 0 (same size) / (changed size) 11.49.302.328 I slot release: id 2 | task 7579 | stop processing: n_tokens = 1010, truncated = 0 11.49.304.799 I slot print_timing: id 3 | task 7580 | prompt eval time = 6320.97 ms / 1021 tokens ( 6.19 ms per token, 161.53 tokens per second) 11.49.304.806 I slot print_timing: id 3 | task 7580 | eval time = 1605.16 ms / 2 tokens ( 1605.16 ms per token, 0.62 tokens per second) 11.49.304.807 I slot print_timing: id 3 | task 7580 | total time = 7926.13 ms / 1023 tokens 11.49.304.808 I slot print_timing: id 3 | task 7580 | graphs reused = 6235 11.49.304.809 I slot print_timing: id 3 | task 7580 | graph reallocs = 0 / 0 (same size) / (changed size) 11.49.304.918 I slot release: id 3 | task 7580 | stop processing: n_tokens = 1031, truncated = 0 11.49.309.378 I slot print_timing: id 1 | task 7583 | prompt processing, n_tokens = 1087, progress = 1.00, t = 4.07 s / 267.22 tokens per second 11.49.990.707 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.888 11.49.991.131 I slot launch_slot_: id 2 | task 7589 | processing task, is_child = 0 11.49.991.480 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 222.855 MiB) 11.50.018.506 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.870 11.50.018.656 I slot launch_slot_: id 3 | task 7590 | processing task, is_child = 0 11.51.060.375 I slot print_timing: id 1 | task 7583 | prompt eval time = 4760.69 ms / 1091 tokens ( 4.36 ms per token, 229.17 tokens per second) 11.51.060.388 I slot print_timing: id 1 | task 7583 | eval time = 1069.73 ms / 2 tokens ( 1069.73 ms per token, 0.93 tokens per second) 11.51.060.389 I slot print_timing: id 1 | task 7583 | total time = 5830.42 ms / 1093 tokens 11.51.060.389 I slot print_timing: id 1 | task 7583 | graphs reused = 6235 11.51.060.390 I slot print_timing: id 1 | task 7583 | graph reallocs = 0 / 0 (same size) / (changed size) 11.51.060.441 I slot release: id 1 | task 7583 | stop processing: n_tokens = 1101, truncated = 0 11.51.060.455 I slot print_timing: id 0 | task 7586 | prompt processing, n_tokens = 1051, progress = 1.00, t = 3.33 s / 315.50 tokens per second 11.51.148.947 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1101, t_last = 324335257984 11.51.149.041 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 223.839 MiB) 11.51.149.046 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 222.433 MiB) 11.51.159.151 I slot launch_slot_: id 1 | task 7593 | processing task, is_child = 0 11.51.708.796 I slot print_timing: id 0 | task 7586 | prompt eval time = 3418.65 ms / 1055 tokens ( 3.24 ms per token, 308.60 tokens per second) 11.51.708.803 I slot print_timing: id 0 | task 7586 | eval time = 562.05 ms / 2 tokens ( 562.05 ms per token, 1.78 tokens per second) 11.51.708.805 I slot print_timing: id 0 | task 7586 | total time = 3980.69 ms / 1057 tokens 11.51.708.805 I slot print_timing: id 0 | task 7586 | graphs reused = 6235 11.51.708.806 I slot print_timing: id 0 | task 7586 | graph reallocs = 0 / 0 (same size) / (changed size) 11.51.708.900 I slot release: id 0 | task 7586 | stop processing: n_tokens = 1065, truncated = 0 11.51.710.200 I slot print_timing: id 2 | task 7589 | prompt eval time = 1125.47 ms / 143 tokens ( 7.87 ms per token, 127.06 tokens per second) 11.51.710.202 I slot print_timing: id 2 | task 7589 | eval time = 562.36 ms / 2 tokens ( 562.36 ms per token, 1.78 tokens per second) 11.51.710.203 I slot print_timing: id 2 | task 7589 | total time = 1687.83 ms / 145 tokens 11.51.710.203 I slot print_timing: id 2 | task 7589 | graphs reused = 6235 11.51.710.203 I slot print_timing: id 2 | task 7589 | graph reallocs = 0 / 0 (same size) / (changed size) 11.51.710.243 I slot release: id 2 | task 7589 | stop processing: n_tokens = 1041, truncated = 0 11.51.711.467 I slot print_timing: id 3 | task 7590 | prompt eval time = 1124.52 ms / 122 tokens ( 9.22 ms per token, 108.49 tokens per second) 11.51.711.477 I slot print_timing: id 3 | task 7590 | eval time = 562.52 ms / 2 tokens ( 562.52 ms per token, 1.78 tokens per second) 11.51.711.477 I slot print_timing: id 3 | task 7590 | total time = 1687.04 ms / 124 tokens 11.51.711.478 I slot print_timing: id 3 | task 7590 | graphs reused = 6235 11.51.711.478 I slot print_timing: id 3 | task 7590 | graph reallocs = 0 / 0 (same size) / (changed size) 11.51.711.517 I slot release: id 3 | task 7590 | stop processing: n_tokens = 1020, truncated = 0 11.52.455.121 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1065, t_last = 324335906454 11.52.455.211 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.063 MiB) 11.52.774.347 I slot launch_slot_: id 0 | task 7597 | processing task, is_child = 0 11.52.774.432 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.050 MiB) 11.52.782.127 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 237.342 MiB) 11.52.790.731 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1041, t_last = 324335907786 11.52.790.877 I slot launch_slot_: id 2 | task 7598 | processing task, is_child = 0 11.52.790.948 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1020, t_last = 324335909060 11.52.791.058 I slot launch_slot_: id 3 | task 7599 | processing task, is_child = 0 11.56.671.395 I slot print_timing: id 1 | task 7593 | prompt eval time = 3107.57 ms / 745 tokens ( 4.17 ms per token, 239.74 tokens per second) 11.56.671.409 I slot print_timing: id 1 | task 7593 | eval time = 2404.63 ms / 2 tokens ( 2404.63 ms per token, 0.42 tokens per second) 11.56.671.411 I slot print_timing: id 1 | task 7593 | total time = 5512.20 ms / 747 tokens 11.56.671.413 I slot print_timing: id 1 | task 7593 | graphs reused = 6235 11.56.671.415 I slot print_timing: id 1 | task 7593 | graph reallocs = 0 / 0 (same size) / (changed size) 11.56.671.597 I slot release: id 1 | task 7593 | stop processing: n_tokens = 755, truncated = 0 11.56.671.678 I slot print_timing: id 0 | task 7597 | prompt processing, n_tokens = 612, progress = 0.84, t = 3.88 s / 157.86 tokens per second 11.56.679.244 I slot print_timing: id 2 | task 7598 | prompt processing, n_tokens = 612, progress = 0.78, t = 3.87 s / 157.94 tokens per second 11.56.683.286 I slot print_timing: id 3 | task 7599 | prompt processing, n_tokens = 612, progress = 0.86, t = 3.87 s / 157.95 tokens per second 11.57.405.195 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.858 11.57.405.400 I slot launch_slot_: id 1 | task 7603 | processing task, is_child = 0 11.57.405.413 I slot print_timing: id 0 | task 7597 | prompt processing, n_tokens = 726, progress = 0.99, t = 4.61 s / 157.34 tokens per second 11.57.618.969 I slot print_timing: id 2 | task 7598 | prompt processing, n_tokens = 783, progress = 0.99, t = 4.61 s / 169.77 tokens per second 11.57.622.996 I slot print_timing: id 3 | task 7599 | prompt processing, n_tokens = 713, progress = 0.99, t = 4.61 s / 154.60 tokens per second 11.58.046.260 I slot print_timing: id 0 | task 7597 | prompt eval time = 5134.76 ms / 730 tokens ( 7.03 ms per token, 142.17 tokens per second) 11.58.046.273 I slot print_timing: id 0 | task 7597 | eval time = 120.42 ms / 2 tokens ( 120.42 ms per token, 8.30 tokens per second) 11.58.046.274 I slot print_timing: id 0 | task 7597 | total time = 5255.18 ms / 732 tokens 11.58.046.276 I slot print_timing: id 0 | task 7597 | graphs reused = 6235 11.58.046.277 I slot print_timing: id 0 | task 7597 | graph reallocs = 0 / 0 (same size) / (changed size) 11.58.046.352 I slot release: id 0 | task 7597 | stop processing: n_tokens = 740, truncated = 0 11.58.051.687 I slot print_timing: id 2 | task 7598 | prompt eval time = 5135.09 ms / 787 tokens ( 6.52 ms per token, 153.26 tokens per second) 11.58.051.694 I slot print_timing: id 2 | task 7598 | eval time = 123.56 ms / 2 tokens ( 123.56 ms per token, 8.09 tokens per second) 11.58.051.695 I slot print_timing: id 2 | task 7598 | total time = 5258.65 ms / 789 tokens 11.58.051.696 I slot print_timing: id 2 | task 7598 | graphs reused = 6235 11.58.051.697 I slot print_timing: id 2 | task 7598 | graph reallocs = 0 / 0 (same size) / (changed size) 11.58.051.758 I slot release: id 2 | task 7598 | stop processing: n_tokens = 797, truncated = 0 11.58.054.236 I slot print_timing: id 3 | task 7599 | prompt eval time = 5136.97 ms / 717 tokens ( 7.16 ms per token, 139.58 tokens per second) 11.58.054.240 I slot print_timing: id 3 | task 7599 | eval time = 124.03 ms / 2 tokens ( 124.03 ms per token, 8.06 tokens per second) 11.58.054.241 I slot print_timing: id 3 | task 7599 | total time = 5261.00 ms / 719 tokens 11.58.054.241 I slot print_timing: id 3 | task 7599 | graphs reused = 6235 11.58.054.242 I slot print_timing: id 3 | task 7599 | graph reallocs = 0 / 0 (same size) / (changed size) 11.58.054.277 I slot release: id 3 | task 7599 | stop processing: n_tokens = 727, truncated = 0 11.58.081.666 I slot print_timing: id 1 | task 7603 | prompt eval time = 434.82 ms / 97 tokens ( 4.48 ms per token, 223.08 tokens per second) 11.58.081.670 I slot print_timing: id 1 | task 7603 | eval time = 32.44 ms / 2 tokens ( 32.44 ms per token, 30.82 tokens per second) 11.58.081.670 I slot print_timing: id 1 | task 7603 | total time = 467.26 ms / 99 tokens 11.58.081.671 I slot print_timing: id 1 | task 7603 | graphs reused = 6235 11.58.081.671 I slot print_timing: id 1 | task 7603 | graph reallocs = 0 / 0 (same size) / (changed size) 11.58.081.708 I slot release: id 1 | task 7603 | stop processing: n_tokens = 746, truncated = 0 11.58.081.718 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.878 11.58.081.788 I slot launch_slot_: id 0 | task 7607 | processing task, is_child = 0 11.58.081.899 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 227.356 MiB) 11.58.089.733 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.498 MiB) 11.58.095.908 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 206.821 MiB) 11.58.101.473 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.869 11.58.101.531 I slot launch_slot_: id 1 | task 7608 | processing task, is_child = 0 11.58.101.698 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.861 (> 0.100 thold), f_keep = 0.813 11.58.101.744 I slot launch_slot_: id 2 | task 7609 | processing task, is_child = 0 11.58.101.825 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.891 11.58.101.870 I slot launch_slot_: id 3 | task 7610 | processing task, is_child = 0 11.59.045.791 I slot print_timing: id 0 | task 7607 | prompt eval time = 900.31 ms / 87 tokens ( 10.35 ms per token, 96.63 tokens per second) 11.59.045.793 I slot print_timing: id 0 | task 7607 | eval time = 43.60 ms / 2 tokens ( 43.60 ms per token, 22.94 tokens per second) 11.59.045.794 I slot print_timing: id 0 | task 7607 | total time = 943.91 ms / 89 tokens 11.59.045.794 I slot print_timing: id 0 | task 7607 | graphs reused = 6235 11.59.045.795 I slot print_timing: id 0 | task 7607 | graph reallocs = 0 / 0 (same size) / (changed size) 11.59.045.831 I slot release: id 0 | task 7607 | stop processing: n_tokens = 738, truncated = 0 11.59.046.946 I slot print_timing: id 1 | task 7608 | prompt eval time = 899.67 ms / 84 tokens ( 10.71 ms per token, 93.37 tokens per second) 11.59.046.951 I slot print_timing: id 1 | task 7608 | eval time = 43.57 ms / 2 tokens ( 43.57 ms per token, 22.95 tokens per second) 11.59.046.951 I slot print_timing: id 1 | task 7608 | total time = 943.24 ms / 86 tokens 11.59.046.952 I slot print_timing: id 1 | task 7608 | graphs reused = 6235 11.59.046.952 I slot print_timing: id 1 | task 7608 | graph reallocs = 0 / 0 (same size) / (changed size) 11.59.046.974 I slot release: id 1 | task 7608 | stop processing: n_tokens = 733, truncated = 0 11.59.048.121 I slot print_timing: id 2 | task 7609 | prompt eval time = 898.90 ms / 105 tokens ( 8.56 ms per token, 116.81 tokens per second) 11.59.048.126 I slot print_timing: id 2 | task 7609 | eval time = 43.61 ms / 2 tokens ( 43.61 ms per token, 22.93 tokens per second) 11.59.048.127 I slot print_timing: id 2 | task 7609 | total time = 942.51 ms / 107 tokens 11.59.048.127 I slot print_timing: id 2 | task 7609 | graphs reused = 6235 11.59.048.127 I slot print_timing: id 2 | task 7609 | graph reallocs = 0 / 0 (same size) / (changed size) 11.59.048.150 I slot release: id 2 | task 7609 | stop processing: n_tokens = 754, truncated = 0 11.59.049.247 I slot print_timing: id 3 | task 7610 | prompt eval time = 898.09 ms / 100 tokens ( 8.98 ms per token, 111.35 tokens per second) 11.59.049.250 I slot print_timing: id 3 | task 7610 | eval time = 43.63 ms / 2 tokens ( 43.63 ms per token, 22.92 tokens per second) 11.59.049.250 I slot print_timing: id 3 | task 7610 | total time = 941.71 ms / 102 tokens 11.59.049.250 I slot print_timing: id 3 | task 7610 | graphs reused = 6235 11.59.049.250 I slot print_timing: id 3 | task 7610 | graph reallocs = 0 / 0 (same size) / (changed size) 11.59.049.268 I slot release: id 3 | task 7610 | stop processing: n_tokens = 749, truncated = 0 11.59.053.964 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 324343243374 11.59.054.037 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 226.512 MiB) 11.59.063.247 I slot launch_slot_: id 0 | task 7614 | processing task, is_child = 0 11.59.063.318 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.747 MiB) 11.59.074.795 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.794 MiB) 11.59.083.197 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 210.197 MiB) 11.59.083.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.429 MiB) 11.59.092.553 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 733, t_last = 324343244517 11.59.092.704 I slot launch_slot_: id 1 | task 7615 | processing task, is_child = 0 11.59.092.833 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 324343245693 11.59.092.927 I slot launch_slot_: id 2 | task 7616 | processing task, is_child = 0 11.59.092.991 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 749, t_last = 324343246811 11.59.093.082 I slot launch_slot_: id 3 | task 7617 | processing task, is_child = 0 12.02.671.174 I slot print_timing: id 0 | task 7614 | prompt processing, n_tokens = 469, progress = 0.48, t = 3.58 s / 131.08 tokens per second 12.02.875.842 I slot print_timing: id 1 | task 7615 | prompt processing, n_tokens = 434, progress = 0.46, t = 3.58 s / 121.30 tokens per second 12.02.877.559 I slot print_timing: id 2 | task 7616 | prompt processing, n_tokens = 451, progress = 0.47, t = 3.58 s / 126.06 tokens per second 12.02.879.317 I slot print_timing: id 3 | task 7617 | prompt processing, n_tokens = 527, progress = 0.51, t = 3.58 s / 147.31 tokens per second 12.05.671.534 I slot print_timing: id 0 | task 7614 | prompt processing, n_tokens = 812, progress = 0.83, t = 6.58 s / 123.43 tokens per second 12.05.766.172 I slot print_timing: id 1 | task 7615 | prompt processing, n_tokens = 812, progress = 0.86, t = 6.58 s / 123.44 tokens per second 12.05.771.585 I slot print_timing: id 2 | task 7616 | prompt processing, n_tokens = 812, progress = 0.84, t = 6.58 s / 123.44 tokens per second 12.05.775.659 I slot print_timing: id 3 | task 7617 | prompt processing, n_tokens = 812, progress = 0.78, t = 6.58 s / 123.44 tokens per second 12.07.172.007 I slot print_timing: id 0 | task 7614 | prompt processing, n_tokens = 981, progress = 1.00, t = 8.08 s / 121.43 tokens per second 12.07.384.896 I slot print_timing: id 1 | task 7615 | prompt processing, n_tokens = 946, progress = 1.00, t = 8.08 s / 117.10 tokens per second 12.07.390.462 I slot print_timing: id 2 | task 7616 | prompt processing, n_tokens = 963, progress = 1.00, t = 8.08 s / 119.20 tokens per second 12.07.394.600 I slot print_timing: id 3 | task 7617 | prompt processing, n_tokens = 1039, progress = 1.00, t = 8.08 s / 128.62 tokens per second 12.07.538.028 I slot print_timing: id 0 | task 7614 | prompt eval time = 8395.86 ms / 985 tokens ( 8.52 ms per token, 117.32 tokens per second) 12.07.538.035 I slot print_timing: id 0 | task 7614 | eval time = 49.07 ms / 2 tokens ( 49.07 ms per token, 20.38 tokens per second) 12.07.538.037 I slot print_timing: id 0 | task 7614 | total time = 8444.94 ms / 987 tokens 12.07.538.037 I slot print_timing: id 0 | task 7614 | graphs reused = 6236 12.07.538.038 I slot print_timing: id 0 | task 7614 | graph reallocs = 0 / 0 (same size) / (changed size) 12.07.538.099 I slot release: id 0 | task 7614 | stop processing: n_tokens = 995, truncated = 0 12.07.539.911 I slot print_timing: id 1 | task 7615 | prompt eval time = 8398.19 ms / 950 tokens ( 8.84 ms per token, 113.12 tokens per second) 12.07.539.914 I slot print_timing: id 1 | task 7615 | eval time = 48.44 ms / 2 tokens ( 48.44 ms per token, 20.64 tokens per second) 12.07.539.914 I slot print_timing: id 1 | task 7615 | total time = 8446.64 ms / 952 tokens 12.07.539.915 I slot print_timing: id 1 | task 7615 | graphs reused = 6236 12.07.539.915 I slot print_timing: id 1 | task 7615 | graph reallocs = 0 / 0 (same size) / (changed size) 12.07.539.953 I slot release: id 1 | task 7615 | stop processing: n_tokens = 960, truncated = 0 12.07.541.721 I slot print_timing: id 2 | task 7616 | prompt eval time = 8400.41 ms / 967 tokens ( 8.69 ms per token, 115.11 tokens per second) 12.07.541.723 I slot print_timing: id 2 | task 7616 | eval time = 47.86 ms / 2 tokens ( 47.86 ms per token, 20.89 tokens per second) 12.07.541.724 I slot print_timing: id 2 | task 7616 | total time = 8448.27 ms / 969 tokens 12.07.541.724 I slot print_timing: id 2 | task 7616 | graphs reused = 6236 12.07.541.725 I slot print_timing: id 2 | task 7616 | graph reallocs = 0 / 0 (same size) / (changed size) 12.07.541.764 I slot release: id 2 | task 7616 | stop processing: n_tokens = 977, truncated = 0 12.07.543.423 I slot print_timing: id 3 | task 7617 | prompt eval time = 8402.40 ms / 1043 tokens ( 8.06 ms per token, 124.13 tokens per second) 12.07.543.431 I slot print_timing: id 3 | task 7617 | eval time = 47.40 ms / 2 tokens ( 47.40 ms per token, 21.10 tokens per second) 12.07.543.431 I slot print_timing: id 3 | task 7617 | total time = 8449.80 ms / 1045 tokens 12.07.543.432 I slot print_timing: id 3 | task 7617 | graphs reused = 6236 12.07.543.432 I slot print_timing: id 3 | task 7617 | graph reallocs = 0 / 0 (same size) / (changed size) 12.07.543.467 I slot release: id 3 | task 7617 | stop processing: n_tokens = 1053, truncated = 0 12.07.549.890 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 995, t_last = 324351735643 12.07.549.997 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.856 MiB) 12.07.557.435 I slot launch_slot_: id 0 | task 7623 | processing task, is_child = 0 12.07.557.540 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.851 MiB) 12.07.570.481 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 264.801 MiB) 12.07.578.857 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 960, t_last = 324351737496 12.07.578.995 I slot launch_slot_: id 1 | task 7624 | processing task, is_child = 0 12.07.579.139 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 324351739307 12.07.579.241 I slot launch_slot_: id 2 | task 7625 | processing task, is_child = 0 12.07.579.316 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1053, t_last = 324351741010 12.07.579.426 I slot launch_slot_: id 3 | task 7626 | processing task, is_child = 0 12.11.232.479 I slot print_timing: id 0 | task 7623 | prompt processing, n_tokens = 611, progress = 0.55, t = 3.65 s / 167.26 tokens per second 12.11.556.713 I slot print_timing: id 1 | task 7624 | prompt processing, n_tokens = 643, progress = 0.56, t = 3.65 s / 176.03 tokens per second 12.11.559.183 I slot print_timing: id 2 | task 7625 | prompt processing, n_tokens = 794, progress = 0.38, t = 3.65 s / 217.38 tokens per second 12.15.051.971 I slot print_timing: id 0 | task 7623 | prompt processing, n_tokens = 975, progress = 0.87, t = 7.47 s / 130.48 tokens per second 12.15.634.698 I slot print_timing: id 1 | task 7624 | prompt processing, n_tokens = 975, progress = 0.84, t = 7.47 s / 130.48 tokens per second 12.15.638.352 I slot print_timing: id 2 | task 7625 | prompt processing, n_tokens = 1613, progress = 0.76, t = 7.47 s / 215.87 tokens per second 12.15.640.230 I slot print_timing: id 3 | task 7626 | prompt processing, n_tokens = 533, progress = 0.25, t = 3.49 s / 152.60 tokens per second 12.18.104.118 I slot print_timing: id 0 | task 7623 | prompt processing, n_tokens = 1123, progress = 1.00, t = 10.52 s / 106.70 tokens per second 12.18.925.796 I slot print_timing: id 1 | task 7624 | prompt processing, n_tokens = 1155, progress = 1.00, t = 10.52 s / 109.74 tokens per second 12.18.931.419 I slot print_timing: id 2 | task 7625 | prompt processing, n_tokens = 1795, progress = 0.84, t = 10.52 s / 170.56 tokens per second 12.18.935.323 I slot print_timing: id 3 | task 7626 | prompt processing, n_tokens = 1616, progress = 0.76, t = 6.54 s / 246.91 tokens per second 12.20.076.376 I slot print_timing: id 2 | task 7625 | prompt processing, n_tokens = 2125, progress = 1.00, t = 12.49 s / 170.10 tokens per second 12.20.080.520 I slot print_timing: id 3 | task 7626 | prompt processing, n_tokens = 1795, progress = 0.84, t = 8.51 s / 210.85 tokens per second 12.20.880.065 I slot print_timing: id 1 | task 7624 | prompt eval time = 12496.66 ms / 1159 tokens ( 10.78 ms per token, 92.74 tokens per second) 12.20.880.075 I slot print_timing: id 1 | task 7624 | eval time = 803.71 ms / 2 tokens ( 803.71 ms per token, 1.24 tokens per second) 12.20.880.077 I slot print_timing: id 1 | task 7624 | total time = 13300.37 ms / 1161 tokens 12.20.880.079 I slot print_timing: id 1 | task 7624 | graphs reused = 6236 12.20.880.080 I slot print_timing: id 1 | task 7624 | graph reallocs = 0 / 0 (same size) / (changed size) 12.20.880.265 I slot release: id 1 | task 7624 | stop processing: n_tokens = 1169, truncated = 0 12.20.882.456 I slot print_timing: id 3 | task 7626 | prompt processing, n_tokens = 2128, progress = 1.00, t = 9.31 s / 228.47 tokens per second 12.20.986.998 I slot print_timing: id 0 | task 7623 | prompt eval time = 12494.75 ms / 1127 tokens ( 11.09 ms per token, 90.20 tokens per second) 12.20.987.003 I slot print_timing: id 0 | task 7623 | eval time = 912.81 ms / 3 tokens ( 456.40 ms per token, 2.19 tokens per second) 12.20.987.004 I slot print_timing: id 0 | task 7623 | total time = 13407.56 ms / 1130 tokens 12.20.987.005 I slot print_timing: id 0 | task 7623 | graphs reused = 6236 12.20.987.006 I slot print_timing: id 0 | task 7623 | graph reallocs = 0 / 0 (same size) / (changed size) 12.20.987.080 I slot release: id 0 | task 7623 | stop processing: n_tokens = 1138, truncated = 0 12.20.989.364 I slot print_timing: id 2 | task 7625 | prompt eval time = 13302.54 ms / 2129 tokens ( 6.25 ms per token, 160.04 tokens per second) 12.20.989.367 I slot print_timing: id 2 | task 7625 | eval time = 106.95 ms / 2 tokens ( 106.95 ms per token, 9.35 tokens per second) 12.20.989.368 I slot print_timing: id 2 | task 7625 | total time = 13409.50 ms / 2131 tokens 12.20.989.369 I slot print_timing: id 2 | task 7625 | graphs reused = 6236 12.20.989.369 I slot print_timing: id 2 | task 7625 | graph reallocs = 0 / 0 (same size) / (changed size) 12.20.989.481 I slot release: id 2 | task 7625 | stop processing: n_tokens = 2139, truncated = 0 12.20.991.563 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.856 12.20.991.678 I slot launch_slot_: id 2 | task 7633 | processing task, is_child = 0 12.20.991.840 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.680 MiB) 12.21.000.167 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.827 MiB) 12.21.007.948 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1169, t_last = 324365077809 12.21.008.146 I slot launch_slot_: id 1 | task 7634 | processing task, is_child = 0 12.21.008.258 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1138, t_last = 324365184623 12.21.008.419 I slot launch_slot_: id 0 | task 7635 | processing task, is_child = 0 12.25.047.746 I slot print_timing: id 3 | task 7626 | prompt eval time = 9432.35 ms / 2132 tokens ( 4.42 ms per token, 226.03 tokens per second) 12.25.047.761 I slot print_timing: id 3 | task 7626 | eval time = 4056.15 ms / 2 tokens ( 4056.15 ms per token, 0.25 tokens per second) 12.25.047.763 I slot print_timing: id 3 | task 7626 | total time = 13488.50 ms / 2134 tokens 12.25.047.764 I slot print_timing: id 3 | task 7626 | graphs reused = 6236 12.25.047.765 I slot print_timing: id 3 | task 7626 | graph reallocs = 0 / 0 (same size) / (changed size) 12.25.048.047 I slot release: id 3 | task 7626 | stop processing: n_tokens = 2142, truncated = 0 12.25.048.144 I slot print_timing: id 0 | task 7635 | prompt processing, n_tokens = 1627, progress = 0.76, t = 4.04 s / 402.99 tokens per second 12.25.056.481 I slot print_timing: id 1 | task 7634 | prompt processing, n_tokens = 420, progress = 0.21, t = 4.04 s / 104.04 tokens per second 12.27.535.952 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.842 (> 0.100 thold), f_keep = 0.855 12.27.536.195 I slot launch_slot_: id 3 | task 7638 | processing task, is_child = 0 12.27.536.219 I slot print_timing: id 0 | task 7635 | prompt processing, n_tokens = 1795, progress = 0.84, t = 6.53 s / 274.99 tokens per second 12.28.297.322 I slot print_timing: id 1 | task 7634 | prompt processing, n_tokens = 1560, progress = 0.75, t = 6.53 s / 239.00 tokens per second 12.30.342.205 I slot print_timing: id 0 | task 7635 | prompt processing, n_tokens = 2139, progress = 1.00, t = 9.33 s / 229.27 tokens per second 12.30.349.448 I slot print_timing: id 1 | task 7634 | prompt processing, n_tokens = 1795, progress = 0.87, t = 9.33 s / 192.41 tokens per second 12.31.062.777 I slot print_timing: id 1 | task 7634 | prompt processing, n_tokens = 2072, progress = 1.00, t = 10.05 s / 206.16 tokens per second 12.31.175.847 I slot print_timing: id 0 | task 7635 | prompt eval time = 10052.07 ms / 2143 tokens ( 4.69 ms per token, 213.19 tokens per second) 12.31.175.856 I slot print_timing: id 0 | task 7635 | eval time = 115.34 ms / 2 tokens ( 115.34 ms per token, 8.67 tokens per second) 12.31.175.857 I slot print_timing: id 0 | task 7635 | total time = 10167.41 ms / 2145 tokens 12.31.175.857 I slot print_timing: id 0 | task 7635 | graphs reused = 6236 12.31.175.858 I slot print_timing: id 0 | task 7635 | graph reallocs = 0 / 0 (same size) / (changed size) 12.31.175.953 I slot release: id 0 | task 7635 | stop processing: n_tokens = 2153, truncated = 0 12.31.178.202 I slot print_timing: id 2 | task 7633 | prompt eval time = 5285.55 ms / 273 tokens ( 19.36 ms per token, 51.65 tokens per second) 12.31.178.204 I slot print_timing: id 2 | task 7633 | eval time = 836.09 ms / 3 tokens ( 418.04 ms per token, 2.39 tokens per second) 12.31.178.205 I slot print_timing: id 2 | task 7633 | total time = 6121.64 ms / 276 tokens 12.31.178.205 I slot print_timing: id 2 | task 7633 | graphs reused = 6236 12.31.178.205 I slot print_timing: id 2 | task 7633 | graph reallocs = 0 / 0 (same size) / (changed size) 12.31.178.269 I slot release: id 2 | task 7633 | stop processing: n_tokens = 2107, truncated = 0 12.31.179.436 I slot print_timing: id 3 | task 7638 | prompt eval time = 2755.28 ms / 344 tokens ( 8.01 ms per token, 124.85 tokens per second) 12.31.179.441 I slot print_timing: id 3 | task 7638 | eval time = 116.67 ms / 2 tokens ( 116.67 ms per token, 8.57 tokens per second) 12.31.179.442 I slot print_timing: id 3 | task 7638 | total time = 2871.94 ms / 346 tokens 12.31.179.442 I slot print_timing: id 3 | task 7638 | graphs reused = 6236 12.31.179.442 I slot print_timing: id 3 | task 7638 | graph reallocs = 0 / 0 (same size) / (changed size) 12.31.179.499 I slot release: id 3 | task 7638 | stop processing: n_tokens = 2177, truncated = 0 12.31.205.366 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.869 (> 0.100 thold), f_keep = 0.850 12.31.205.441 I slot launch_slot_: id 0 | task 7643 | processing task, is_child = 0 12.31.205.586 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.210 MiB) 12.31.224.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.920 MiB) 12.31.224.289 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 234.529 MiB) 12.31.253.569 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.838 (> 0.100 thold), f_keep = 0.869 12.31.253.666 I slot launch_slot_: id 2 | task 7644 | processing task, is_child = 0 12.31.253.807 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.806 (> 0.100 thold), f_keep = 0.842 12.31.253.851 I slot launch_slot_: id 3 | task 7645 | processing task, is_child = 0 12.33.530.648 I slot print_timing: id 1 | task 7634 | prompt eval time = 10168.30 ms / 2076 tokens ( 4.90 ms per token, 204.16 tokens per second) 12.33.530.653 I slot print_timing: id 1 | task 7634 | eval time = 2353.50 ms / 3 tokens ( 1176.75 ms per token, 0.85 tokens per second) 12.33.530.653 I slot print_timing: id 1 | task 7634 | total time = 12521.80 ms / 2079 tokens 12.33.530.654 I slot print_timing: id 1 | task 7634 | graphs reused = 6236 12.33.530.655 I slot print_timing: id 1 | task 7634 | graph reallocs = 0 / 0 (same size) / (changed size) 12.33.530.810 I slot release: id 1 | task 7634 | stop processing: n_tokens = 2087, truncated = 0 12.33.622.330 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.878 12.33.622.419 I slot launch_slot_: id 1 | task 7648 | processing task, is_child = 0 12.34.102.000 I slot print_timing: id 0 | task 7643 | prompt eval time = 2366.15 ms / 276 tokens ( 8.57 ms per token, 116.65 tokens per second) 12.34.102.007 I slot print_timing: id 0 | task 7643 | eval time = 481.97 ms / 2 tokens ( 481.97 ms per token, 2.07 tokens per second) 12.34.102.007 I slot print_timing: id 0 | task 7643 | total time = 2848.12 ms / 278 tokens 12.34.102.008 I slot print_timing: id 0 | task 7643 | graphs reused = 6236 12.34.102.008 I slot print_timing: id 0 | task 7643 | graph reallocs = 0 / 0 (same size) / (changed size) 12.34.102.148 I slot release: id 0 | task 7643 | stop processing: n_tokens = 2108, truncated = 0 12.34.186.174 I slot print_timing: id 2 | task 7644 | prompt eval time = 2365.13 ms / 353 tokens ( 6.70 ms per token, 149.25 tokens per second) 12.34.186.177 I slot print_timing: id 2 | task 7644 | eval time = 564.99 ms / 3 tokens ( 282.50 ms per token, 3.54 tokens per second) 12.34.186.177 I slot print_timing: id 2 | task 7644 | total time = 2930.13 ms / 356 tokens 12.34.186.178 I slot print_timing: id 2 | task 7644 | graphs reused = 6236 12.34.186.178 I slot print_timing: id 2 | task 7644 | graph reallocs = 0 / 0 (same size) / (changed size) 12.34.186.253 I slot release: id 2 | task 7644 | stop processing: n_tokens = 2187, truncated = 0 12.34.187.395 I slot print_timing: id 3 | task 7645 | prompt eval time = 2364.42 ms / 441 tokens ( 5.36 ms per token, 186.51 tokens per second) 12.34.187.400 I slot print_timing: id 3 | task 7645 | eval time = 565.07 ms / 3 tokens ( 282.53 ms per token, 3.54 tokens per second) 12.34.187.401 I slot print_timing: id 3 | task 7645 | total time = 2929.49 ms / 444 tokens 12.34.187.401 I slot print_timing: id 3 | task 7645 | graphs reused = 6236 12.34.187.401 I slot print_timing: id 3 | task 7645 | graph reallocs = 0 / 0 (same size) / (changed size) 12.34.187.460 I slot release: id 3 | task 7645 | stop processing: n_tokens = 2274, truncated = 0 12.34.187.468 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.838 12.34.187.553 I slot launch_slot_: id 2 | task 7651 | processing task, is_child = 0 12.34.187.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.301 MiB) 12.34.214.571 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.793 MiB) 12.34.245.780 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.806 12.34.245.856 I slot launch_slot_: id 3 | task 7652 | processing task, is_child = 0 12.34.245.976 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.869 12.34.246.011 I slot launch_slot_: id 0 | task 7653 | processing task, is_child = 0 12.35.990.402 I slot print_timing: id 1 | task 7648 | prompt eval time = 562.64 ms / 189 tokens ( 2.98 ms per token, 335.92 tokens per second) 12.35.990.405 I slot print_timing: id 1 | task 7648 | eval time = 1805.34 ms / 3 tokens ( 902.67 ms per token, 1.11 tokens per second) 12.35.990.406 I slot print_timing: id 1 | task 7648 | total time = 2367.97 ms / 192 tokens 12.35.990.406 I slot print_timing: id 1 | task 7648 | graphs reused = 6236 12.35.990.407 I slot print_timing: id 1 | task 7648 | graph reallocs = 0 / 0 (same size) / (changed size) 12.35.990.489 I slot release: id 1 | task 7648 | stop processing: n_tokens = 2023, truncated = 0 12.36.055.093 I slot print_timing: id 0 | task 7653 | prompt eval time = 1743.27 ms / 226 tokens ( 7.71 ms per token, 129.64 tokens per second) 12.36.055.096 I slot print_timing: id 0 | task 7653 | eval time = 65.80 ms / 2 tokens ( 65.80 ms per token, 15.20 tokens per second) 12.36.055.097 I slot print_timing: id 0 | task 7653 | total time = 1809.07 ms / 228 tokens 12.36.055.097 I slot print_timing: id 0 | task 7653 | graphs reused = 6236 12.36.055.098 I slot print_timing: id 0 | task 7653 | graph reallocs = 0 / 0 (same size) / (changed size) 12.36.055.165 I slot release: id 0 | task 7653 | stop processing: n_tokens = 2058, truncated = 0 12.36.056.361 I slot print_timing: id 2 | task 7651 | prompt eval time = 1740.85 ms / 232 tokens ( 7.50 ms per token, 133.27 tokens per second) 12.36.056.365 I slot print_timing: id 2 | task 7651 | eval time = 64.71 ms / 2 tokens ( 64.71 ms per token, 15.45 tokens per second) 12.36.056.365 I slot print_timing: id 2 | task 7651 | total time = 1805.56 ms / 234 tokens 12.36.056.366 I slot print_timing: id 2 | task 7651 | graphs reused = 6236 12.36.056.366 I slot print_timing: id 2 | task 7651 | graph reallocs = 0 / 0 (same size) / (changed size) 12.36.056.413 I slot release: id 2 | task 7651 | stop processing: n_tokens = 2064, truncated = 0 12.36.057.556 I slot print_timing: id 3 | task 7652 | prompt eval time = 1736.68 ms / 280 tokens ( 6.20 ms per token, 161.23 tokens per second) 12.36.057.558 I slot print_timing: id 3 | task 7652 | eval time = 64.72 ms / 2 tokens ( 64.72 ms per token, 15.45 tokens per second) 12.36.057.559 I slot print_timing: id 3 | task 7652 | total time = 1801.40 ms / 282 tokens 12.36.057.559 I slot print_timing: id 3 | task 7652 | graphs reused = 6236 12.36.057.559 I slot print_timing: id 3 | task 7652 | graph reallocs = 0 / 0 (same size) / (changed size) 12.36.057.612 I slot release: id 3 | task 7652 | stop processing: n_tokens = 2113, truncated = 0 12.36.057.622 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.852 (> 0.100 thold), f_keep = 0.906 12.36.057.692 I slot launch_slot_: id 1 | task 7657 | processing task, is_child = 0 12.36.057.821 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 364.694 MiB) 12.36.095.005 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.934 MiB) 12.36.095.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 364.518 MiB) 12.36.120.890 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.441 MiB) 12.36.149.920 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.845 (> 0.100 thold), f_keep = 0.888 12.36.150.004 I slot launch_slot_: id 2 | task 7658 | processing task, is_child = 0 12.36.150.247 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.890 12.36.150.285 I slot launch_slot_: id 0 | task 7659 | processing task, is_child = 0 12.36.150.398 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.864 (> 0.100 thold), f_keep = 0.867 12.36.150.432 I slot launch_slot_: id 3 | task 7660 | processing task, is_child = 0 12.38.687.562 I slot print_timing: id 0 | task 7659 | prompt eval time = 2491.68 ms / 193 tokens ( 12.91 ms per token, 77.46 tokens per second) 12.38.687.564 I slot print_timing: id 0 | task 7659 | eval time = 45.43 ms / 2 tokens ( 45.43 ms per token, 22.01 tokens per second) 12.38.687.564 I slot print_timing: id 0 | task 7659 | total time = 2537.11 ms / 195 tokens 12.38.687.565 I slot print_timing: id 0 | task 7659 | graphs reused = 6236 12.38.687.565 I slot print_timing: id 0 | task 7659 | graph reallocs = 0 / 0 (same size) / (changed size) 12.38.687.634 I slot release: id 0 | task 7659 | stop processing: n_tokens = 2025, truncated = 0 12.38.688.718 I slot print_timing: id 1 | task 7657 | prompt eval time = 2491.08 ms / 318 tokens ( 7.83 ms per token, 127.66 tokens per second) 12.38.688.724 I slot print_timing: id 1 | task 7657 | eval time = 45.44 ms / 2 tokens ( 45.44 ms per token, 22.01 tokens per second) 12.38.688.724 I slot print_timing: id 1 | task 7657 | total time = 2536.53 ms / 320 tokens 12.38.688.724 I slot print_timing: id 1 | task 7657 | graphs reused = 6236 12.38.688.724 I slot print_timing: id 1 | task 7657 | graph reallocs = 0 / 0 (same size) / (changed size) 12.38.688.774 I slot release: id 1 | task 7657 | stop processing: n_tokens = 2151, truncated = 0 12.38.689.903 I slot print_timing: id 2 | task 7658 | prompt eval time = 2490.50 ms / 336 tokens ( 7.41 ms per token, 134.91 tokens per second) 12.38.689.906 I slot print_timing: id 2 | task 7658 | eval time = 45.48 ms / 2 tokens ( 45.48 ms per token, 21.99 tokens per second) 12.38.689.906 I slot print_timing: id 2 | task 7658 | total time = 2535.98 ms / 338 tokens 12.38.689.906 I slot print_timing: id 2 | task 7658 | graphs reused = 6236 12.38.689.907 I slot print_timing: id 2 | task 7658 | graph reallocs = 0 / 0 (same size) / (changed size) 12.38.689.950 I slot release: id 2 | task 7658 | stop processing: n_tokens = 2169, truncated = 0 12.38.691.040 I slot print_timing: id 3 | task 7660 | prompt eval time = 2489.89 ms / 289 tokens ( 8.62 ms per token, 116.07 tokens per second) 12.38.691.042 I slot print_timing: id 3 | task 7660 | eval time = 45.50 ms / 2 tokens ( 45.50 ms per token, 21.98 tokens per second) 12.38.691.043 I slot print_timing: id 3 | task 7660 | total time = 2535.39 ms / 291 tokens 12.38.691.043 I slot print_timing: id 3 | task 7660 | graphs reused = 6236 12.38.691.043 I slot print_timing: id 3 | task 7660 | graph reallocs = 0 / 0 (same size) / (changed size) 12.38.691.087 I slot release: id 3 | task 7660 | stop processing: n_tokens = 2121, truncated = 0 12.38.700.751 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.852 12.38.700.821 I slot launch_slot_: id 1 | task 7664 | processing task, is_child = 0 12.38.700.955 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.582 MiB) 12.38.723.269 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 364.448 MiB) 12.38.753.486 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 254.290 MiB) 12.38.785.773 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.904 12.38.785.862 I slot launch_slot_: id 0 | task 7665 | processing task, is_child = 0 12.38.786.097 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 12.38.786.143 I slot launch_slot_: id 2 | task 7666 | processing task, is_child = 0 12.38.786.258 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.821 (> 0.100 thold), f_keep = 0.863 12.38.786.290 I slot launch_slot_: id 3 | task 7667 | processing task, is_child = 0 12.41.579.755 I slot print_timing: id 0 | task 7665 | prompt eval time = 2748.19 ms / 387 tokens ( 7.10 ms per token, 140.82 tokens per second) 12.41.579.758 I slot print_timing: id 0 | task 7665 | eval time = 45.26 ms / 2 tokens ( 45.26 ms per token, 22.09 tokens per second) 12.41.579.758 I slot print_timing: id 0 | task 7665 | total time = 2793.45 ms / 389 tokens 12.41.579.758 I slot print_timing: id 0 | task 7665 | graphs reused = 6236 12.41.579.759 I slot print_timing: id 0 | task 7665 | graph reallocs = 0 / 0 (same size) / (changed size) 12.41.579.842 I slot release: id 0 | task 7665 | stop processing: n_tokens = 2219, truncated = 0 12.41.581.898 I slot print_timing: id 2 | task 7666 | prompt eval time = 2745.38 ms / 249 tokens ( 11.03 ms per token, 90.70 tokens per second) 12.41.581.900 I slot print_timing: id 2 | task 7666 | eval time = 45.25 ms / 2 tokens ( 45.25 ms per token, 22.10 tokens per second) 12.41.581.901 I slot print_timing: id 2 | task 7666 | total time = 2790.63 ms / 251 tokens 12.41.581.901 I slot print_timing: id 2 | task 7666 | graphs reused = 6236 12.41.581.901 I slot print_timing: id 2 | task 7666 | graph reallocs = 0 / 0 (same size) / (changed size) 12.41.581.949 I slot release: id 2 | task 7666 | stop processing: n_tokens = 2081, truncated = 0 12.41.583.020 I slot print_timing: id 3 | task 7667 | prompt eval time = 2744.69 ms / 399 tokens ( 6.88 ms per token, 145.37 tokens per second) 12.41.583.022 I slot print_timing: id 3 | task 7667 | eval time = 45.24 ms / 2 tokens ( 45.24 ms per token, 22.10 tokens per second) 12.41.583.023 I slot print_timing: id 3 | task 7667 | total time = 2789.93 ms / 401 tokens 12.41.583.023 I slot print_timing: id 3 | task 7667 | graphs reused = 6236 12.41.583.023 I slot print_timing: id 3 | task 7667 | graph reallocs = 0 / 0 (same size) / (changed size) 12.41.583.069 I slot release: id 3 | task 7667 | stop processing: n_tokens = 2231, truncated = 0 12.41.609.816 I slot print_timing: id 1 | task 7664 | prompt eval time = 2747.32 ms / 190 tokens ( 14.46 ms per token, 69.16 tokens per second) 12.41.609.818 I slot print_timing: id 1 | task 7664 | eval time = 74.24 ms / 3 tokens ( 37.12 ms per token, 26.94 tokens per second) 12.41.609.819 I slot print_timing: id 1 | task 7664 | total time = 2821.56 ms / 193 tokens 12.41.609.819 I slot print_timing: id 1 | task 7664 | graphs reused = 6236 12.41.609.819 I slot print_timing: id 1 | task 7664 | graph reallocs = 0 / 0 (same size) / (changed size) 12.41.609.869 I slot release: id 1 | task 7664 | stop processing: n_tokens = 2023, truncated = 0 12.41.609.877 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.825 12.41.609.941 I slot launch_slot_: id 0 | task 7672 | processing task, is_child = 0 12.41.610.070 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 256.751 MiB) 12.41.610.077 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.485 MiB) 12.41.647.592 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.644 MiB) 12.41.676.540 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.909 MiB) 12.41.703.998 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.906 12.41.704.096 I slot launch_slot_: id 1 | task 7673 | processing task, is_child = 0 12.41.704.327 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.880 12.41.704.366 I slot launch_slot_: id 2 | task 7674 | processing task, is_child = 0 12.41.704.481 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 12.41.704.514 I slot launch_slot_: id 3 | task 7675 | processing task, is_child = 0 12.43.558.431 I slot print_timing: id 0 | task 7672 | prompt eval time = 1808.47 ms / 213 tokens ( 8.49 ms per token, 117.78 tokens per second) 12.43.558.434 I slot print_timing: id 0 | task 7672 | eval time = 45.43 ms / 2 tokens ( 45.43 ms per token, 22.01 tokens per second) 12.43.558.434 I slot print_timing: id 0 | task 7672 | total time = 1853.90 ms / 215 tokens 12.43.558.435 I slot print_timing: id 0 | task 7672 | graphs reused = 6236 12.43.558.435 I slot print_timing: id 0 | task 7672 | graph reallocs = 0 / 0 (same size) / (changed size) 12.43.558.701 I slot release: id 0 | task 7672 | stop processing: n_tokens = 2044, truncated = 0 12.43.560.804 I slot print_timing: id 2 | task 7674 | prompt eval time = 1806.05 ms / 123 tokens ( 14.68 ms per token, 68.10 tokens per second) 12.43.560.807 I slot print_timing: id 2 | task 7674 | eval time = 45.32 ms / 2 tokens ( 45.32 ms per token, 22.06 tokens per second) 12.43.560.807 I slot print_timing: id 2 | task 7674 | total time = 1851.37 ms / 125 tokens 12.43.560.807 I slot print_timing: id 2 | task 7674 | graphs reused = 6236 12.43.560.808 I slot print_timing: id 2 | task 7674 | graph reallocs = 0 / 0 (same size) / (changed size) 12.43.560.855 I slot release: id 2 | task 7674 | stop processing: n_tokens = 1955, truncated = 0 12.43.612.863 I slot print_timing: id 1 | task 7673 | prompt eval time = 1806.63 ms / 238 tokens ( 7.59 ms per token, 131.74 tokens per second) 12.43.612.865 I slot print_timing: id 1 | task 7673 | eval time = 98.63 ms / 3 tokens ( 49.32 ms per token, 20.28 tokens per second) 12.43.612.867 I slot print_timing: id 1 | task 7673 | total time = 1905.27 ms / 241 tokens 12.43.612.867 I slot print_timing: id 1 | task 7673 | graphs reused = 6236 12.43.612.867 I slot print_timing: id 1 | task 7673 | graph reallocs = 0 / 0 (same size) / (changed size) 12.43.612.929 I slot release: id 1 | task 7673 | stop processing: n_tokens = 2072, truncated = 0 12.43.613.984 I slot print_timing: id 3 | task 7675 | prompt eval time = 1804.99 ms / 208 tokens ( 8.68 ms per token, 115.24 tokens per second) 12.43.613.988 I slot print_timing: id 3 | task 7675 | eval time = 97.33 ms / 3 tokens ( 48.67 ms per token, 20.55 tokens per second) 12.43.613.988 I slot print_timing: id 3 | task 7675 | total time = 1902.32 ms / 211 tokens 12.43.613.989 I slot print_timing: id 3 | task 7675 | graphs reused = 6236 12.43.613.989 I slot print_timing: id 3 | task 7675 | graph reallocs = 0 / 0 (same size) / (changed size) 12.43.614.041 I slot release: id 3 | task 7675 | stop processing: n_tokens = 2042, truncated = 0 12.43.614.045 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2044, t_last = 324387756244 12.43.614.190 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.372 MiB) 12.43.614.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.589 MiB) 12.43.646.866 I slot launch_slot_: id 0 | task 7680 | processing task, is_child = 0 12.43.646.998 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.744 MiB) 12.43.691.771 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.508 MiB) 12.43.691.786 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.915 MiB) 12.43.701.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.083 MiB) 12.43.728.359 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.884 12.43.728.440 I slot launch_slot_: id 1 | task 7681 | processing task, is_child = 0 12.43.728.658 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1955, t_last = 324387758398 12.43.728.795 I slot launch_slot_: id 2 | task 7682 | processing task, is_child = 0 12.43.728.902 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2042, t_last = 324387811584 12.43.729.037 I slot launch_slot_: id 3 | task 7683 | processing task, is_child = 0 12.47.238.486 I slot print_timing: id 0 | task 7680 | prompt processing, n_tokens = 950, progress = 0.65, t = 3.51 s / 270.70 tokens per second 12.47.746.431 I slot print_timing: id 1 | task 7681 | prompt processing, n_tokens = 168, progress = 1.00, t = 3.51 s / 47.87 tokens per second 12.47.748.624 I slot print_timing: id 2 | task 7682 | prompt processing, n_tokens = 930, progress = 0.61, t = 3.51 s / 265.21 tokens per second 12.50.958.063 I slot print_timing: id 0 | task 7680 | prompt processing, n_tokens = 1264, progress = 0.86, t = 7.23 s / 174.88 tokens per second 12.50.961.449 I slot print_timing: id 2 | task 7682 | prompt processing, n_tokens = 1021, progress = 0.67, t = 7.23 s / 141.31 tokens per second 12.50.963.226 I slot print_timing: id 3 | task 7683 | prompt processing, n_tokens = 1155, progress = 0.69, t = 3.21 s / 360.01 tokens per second 12.52.235.983 I slot print_timing: id 1 | task 7681 | prompt eval time = 7228.71 ms / 172 tokens ( 42.03 ms per token, 23.79 tokens per second) 12.52.235.989 I slot print_timing: id 1 | task 7681 | eval time = 1277.94 ms / 2 tokens ( 1277.94 ms per token, 0.78 tokens per second) 12.52.235.990 I slot print_timing: id 1 | task 7681 | total time = 8506.65 ms / 174 tokens 12.52.235.990 I slot print_timing: id 1 | task 7681 | graphs reused = 6236 12.52.235.991 I slot print_timing: id 1 | task 7681 | graph reallocs = 0 / 0 (same size) / (changed size) 12.52.236.191 I slot release: id 1 | task 7681 | stop processing: n_tokens = 2004, truncated = 0 12.52.236.222 I slot print_timing: id 0 | task 7680 | prompt processing, n_tokens = 1462, progress = 1.00, t = 8.51 s / 171.88 tokens per second 12.52.239.936 I slot print_timing: id 2 | task 7682 | prompt processing, n_tokens = 1264, progress = 0.82, t = 8.50 s / 148.65 tokens per second 12.52.241.702 I slot print_timing: id 3 | task 7683 | prompt processing, n_tokens = 1264, progress = 0.76, t = 4.49 s / 281.75 tokens per second 12.53.714.391 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2004, t_last = 324396433736 12.53.714.586 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 266.524 MiB) 12.53.755.747 I slot launch_slot_: id 1 | task 7688 | processing task, is_child = 0 12.53.756.107 I slot print_timing: id 2 | task 7682 | prompt processing, n_tokens = 1533, progress = 1.00, t = 9.98 s / 153.59 tokens per second 12.53.757.927 I slot print_timing: id 3 | task 7683 | prompt processing, n_tokens = 1667, progress = 1.00, t = 5.96 s / 279.48 tokens per second 12.54.770.121 I slot print_timing: id 0 | task 7680 | prompt eval time = 9985.34 ms / 1466 tokens ( 6.81 ms per token, 146.82 tokens per second) 12.54.770.125 I slot print_timing: id 0 | task 7680 | eval time = 1055.73 ms / 2 tokens ( 1055.73 ms per token, 0.95 tokens per second) 12.54.770.127 I slot print_timing: id 0 | task 7680 | total time = 11041.07 ms / 1468 tokens 12.54.770.128 I slot print_timing: id 0 | task 7680 | graphs reused = 6236 12.54.770.128 I slot print_timing: id 0 | task 7680 | graph reallocs = 0 / 0 (same size) / (changed size) 12.54.770.323 I slot release: id 0 | task 7680 | stop processing: n_tokens = 1476, truncated = 0 12.55.559.765 I slot print_timing: id 2 | task 7682 | prompt eval time = 11039.78 ms / 1537 tokens ( 7.18 ms per token, 139.22 tokens per second) 12.55.559.770 I slot print_timing: id 2 | task 7682 | eval time = 788.09 ms / 2 tokens ( 788.09 ms per token, 1.27 tokens per second) 12.55.559.770 I slot print_timing: id 2 | task 7682 | total time = 11827.87 ms / 1539 tokens 12.55.559.771 I slot print_timing: id 2 | task 7682 | graphs reused = 6236 12.55.559.772 I slot print_timing: id 2 | task 7682 | graph reallocs = 0 / 0 (same size) / (changed size) 12.55.559.904 I slot release: id 2 | task 7682 | stop processing: n_tokens = 1547, truncated = 0 12.55.561.133 I slot print_timing: id 3 | task 7683 | prompt eval time = 7024.78 ms / 1671 tokens ( 4.20 ms per token, 237.87 tokens per second) 12.55.561.137 I slot print_timing: id 3 | task 7683 | eval time = 787.72 ms / 2 tokens ( 787.72 ms per token, 1.27 tokens per second) 12.55.561.139 I slot print_timing: id 3 | task 7683 | total time = 7812.50 ms / 1673 tokens 12.55.561.142 I slot print_timing: id 3 | task 7683 | graphs reused = 6236 12.55.561.143 I slot print_timing: id 3 | task 7683 | graph reallocs = 0 / 0 (same size) / (changed size) 12.55.561.244 I slot release: id 3 | task 7683 | stop processing: n_tokens = 1681, truncated = 0 12.55.561.258 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 324398967867 12.55.561.397 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.437 MiB) 12.55.587.183 I slot launch_slot_: id 0 | task 7691 | processing task, is_child = 0 12.55.587.288 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 244.515 MiB) 12.55.587.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 246.906 MiB) 12.55.617.687 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.063 MiB) 12.55.642.807 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1547, t_last = 324399757448 12.55.642.994 I slot launch_slot_: id 2 | task 7692 | processing task, is_child = 0 12.55.643.088 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1681, t_last = 324399758788 12.55.643.220 I slot launch_slot_: id 3 | task 7693 | processing task, is_child = 0 12.58.671.233 I slot print_timing: id 1 | task 7688 | prompt processing, n_tokens = 991, progress = 1.00, t = 4.83 s / 205.04 tokens per second 13.01.186.760 I slot print_timing: id 0 | task 7691 | prompt processing, n_tokens = 848, progress = 0.86, t = 5.54 s / 153.05 tokens per second 13.01.191.007 I slot print_timing: id 2 | task 7692 | prompt processing, n_tokens = 848, progress = 0.89, t = 5.54 s / 153.10 tokens per second 13.01.194.823 I slot print_timing: id 3 | task 7693 | prompt processing, n_tokens = 848, progress = 0.87, t = 5.54 s / 153.13 tokens per second 13.02.097.823 I slot print_timing: id 1 | task 7688 | prompt eval time = 7430.87 ms / 995 tokens ( 7.47 ms per token, 133.90 tokens per second) 13.02.097.840 I slot print_timing: id 1 | task 7688 | eval time = 911.14 ms / 2 tokens ( 911.14 ms per token, 1.10 tokens per second) 13.02.097.841 I slot print_timing: id 1 | task 7688 | total time = 8342.02 ms / 997 tokens 13.02.097.843 I slot print_timing: id 1 | task 7688 | graphs reused = 6236 13.02.097.844 I slot print_timing: id 1 | task 7688 | graph reallocs = 0 / 0 (same size) / (changed size) 13.02.098.046 I slot release: id 1 | task 7688 | stop processing: n_tokens = 1005, truncated = 0 13.02.098.098 I slot print_timing: id 0 | task 7691 | prompt processing, n_tokens = 981, progress = 1.00, t = 6.45 s / 152.06 tokens per second 13.02.106.266 I slot print_timing: id 2 | task 7692 | prompt processing, n_tokens = 954, progress = 1.00, t = 6.45 s / 147.92 tokens per second 13.02.110.546 I slot print_timing: id 3 | task 7693 | prompt processing, n_tokens = 969, progress = 1.00, t = 6.45 s / 150.28 tokens per second 13.02.199.867 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.880 13.02.200.094 I slot launch_slot_: id 1 | task 7698 | processing task, is_child = 0 13.02.543.799 I slot print_timing: id 0 | task 7691 | prompt eval time = 6552.14 ms / 985 tokens ( 6.65 ms per token, 150.33 tokens per second) 13.02.543.813 I slot print_timing: id 0 | task 7691 | eval time = 348.39 ms / 2 tokens ( 348.39 ms per token, 2.87 tokens per second) 13.02.543.814 I slot print_timing: id 0 | task 7691 | total time = 6900.53 ms / 987 tokens 13.02.543.819 I slot print_timing: id 0 | task 7691 | graphs reused = 6236 13.02.543.820 I slot print_timing: id 0 | task 7691 | graph reallocs = 0 / 0 (same size) / (changed size) 13.02.544.034 I slot release: id 0 | task 7691 | stop processing: n_tokens = 995, truncated = 0 13.02.546.206 I slot print_timing: id 2 | task 7692 | prompt eval time = 6552.64 ms / 958 tokens ( 6.84 ms per token, 146.20 tokens per second) 13.02.546.212 I slot print_timing: id 2 | task 7692 | eval time = 348.40 ms / 2 tokens ( 348.40 ms per token, 2.87 tokens per second) 13.02.546.213 I slot print_timing: id 2 | task 7692 | total time = 6901.04 ms / 960 tokens 13.02.546.215 I slot print_timing: id 2 | task 7692 | graphs reused = 6236 13.02.546.216 I slot print_timing: id 2 | task 7692 | graph reallocs = 0 / 0 (same size) / (changed size) 13.02.546.317 I slot release: id 2 | task 7692 | stop processing: n_tokens = 968, truncated = 0 13.02.548.322 I slot print_timing: id 3 | task 7693 | prompt eval time = 6553.41 ms / 973 tokens ( 6.74 ms per token, 148.47 tokens per second) 13.02.548.333 I slot print_timing: id 3 | task 7693 | eval time = 348.47 ms / 2 tokens ( 348.47 ms per token, 2.87 tokens per second) 13.02.548.334 I slot print_timing: id 3 | task 7693 | total time = 6901.88 ms / 975 tokens 13.02.548.335 I slot print_timing: id 3 | task 7693 | graphs reused = 6236 13.02.548.336 I slot print_timing: id 3 | task 7693 | graph reallocs = 0 / 0 (same size) / (changed size) 13.02.548.428 I slot release: id 3 | task 7693 | stop processing: n_tokens = 983, truncated = 0 13.02.593.896 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 995, t_last = 324406741577 13.02.594.057 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 258.053 MiB) 13.02.639.588 I slot launch_slot_: id 0 | task 7701 | processing task, is_child = 0 13.02.639.687 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.143 MiB) 13.02.698.065 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 346.137 MiB) 13.02.744.187 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.913 13.02.744.268 I slot launch_slot_: id 2 | task 7702 | processing task, is_child = 0 13.02.744.343 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.899 13.02.744.379 I slot launch_slot_: id 3 | task 7703 | processing task, is_child = 0 13.03.822.967 I slot print_timing: id 1 | task 7698 | prompt eval time = 393.77 ms / 103 tokens ( 3.82 ms per token, 261.57 tokens per second) 13.03.822.978 I slot print_timing: id 1 | task 7698 | eval time = 1229.03 ms / 2 tokens ( 1229.03 ms per token, 0.81 tokens per second) 13.03.822.979 I slot print_timing: id 1 | task 7698 | total time = 1622.80 ms / 105 tokens 13.03.822.982 I slot print_timing: id 1 | task 7698 | graphs reused = 6236 13.03.822.983 I slot print_timing: id 1 | task 7698 | graph reallocs = 0 / 0 (same size) / (changed size) 13.03.823.147 I slot release: id 1 | task 7698 | stop processing: n_tokens = 988, truncated = 0 13.04.697.314 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 324408020690 13.04.791.122 I slot launch_slot_: id 1 | task 7706 | processing task, is_child = 0 13.07.318.706 I slot print_timing: id 2 | task 7702 | prompt eval time = 1950.26 ms / 93 tokens ( 20.97 ms per token, 47.69 tokens per second) 13.07.318.718 I slot print_timing: id 2 | task 7702 | eval time = 2623.77 ms / 2 tokens ( 2623.77 ms per token, 0.38 tokens per second) 13.07.318.719 I slot print_timing: id 2 | task 7702 | total time = 4574.03 ms / 95 tokens 13.07.318.721 I slot print_timing: id 2 | task 7702 | graphs reused = 6236 13.07.318.723 I slot print_timing: id 2 | task 7702 | graph reallocs = 0 / 0 (same size) / (changed size) 13.07.318.894 I slot release: id 2 | task 7702 | stop processing: n_tokens = 978, truncated = 0 13.07.321.351 I slot print_timing: id 3 | task 7703 | prompt eval time = 1950.81 ms / 98 tokens ( 19.91 ms per token, 50.24 tokens per second) 13.07.321.358 I slot print_timing: id 3 | task 7703 | eval time = 2624.06 ms / 2 tokens ( 2624.06 ms per token, 0.38 tokens per second) 13.07.321.359 I slot print_timing: id 3 | task 7703 | total time = 4574.86 ms / 100 tokens 13.07.321.360 I slot print_timing: id 3 | task 7703 | graphs reused = 6236 13.07.321.361 I slot print_timing: id 3 | task 7703 | graph reallocs = 0 / 0 (same size) / (changed size) 13.07.321.454 I slot release: id 3 | task 7703 | stop processing: n_tokens = 983, truncated = 0 13.07.321.515 I slot print_timing: id 0 | task 7701 | prompt processing, n_tokens = 810, progress = 1.00, t = 4.57 s / 177.25 tokens per second 13.07.890.590 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 978, t_last = 324411516437 13.07.890.887 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 348.598 MiB) 13.07.960.493 I slot launch_slot_: id 2 | task 7709 | processing task, is_child = 0 13.07.960.592 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 346.172 MiB) 13.08.000.128 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 983, t_last = 324411518998 13.08.000.291 I slot launch_slot_: id 3 | task 7710 | processing task, is_child = 0 13.08.000.301 I slot print_timing: id 1 | task 7706 | prompt processing, n_tokens = 1388, progress = 0.84, t = 3.08 s / 449.99 tokens per second 13.12.052.735 I slot print_timing: id 0 | task 7701 | prompt eval time = 5146.14 ms / 814 tokens ( 6.32 ms per token, 158.18 tokens per second) 13.12.052.749 I slot print_timing: id 0 | task 7701 | eval time = 4162.16 ms / 2 tokens ( 4162.16 ms per token, 0.24 tokens per second) 13.12.052.751 I slot print_timing: id 0 | task 7701 | total time = 9308.31 ms / 816 tokens 13.12.052.753 I slot print_timing: id 0 | task 7701 | graphs reused = 6236 13.12.052.753 I slot print_timing: id 0 | task 7701 | graph reallocs = 0 / 0 (same size) / (changed size) 13.12.052.920 I slot release: id 0 | task 7701 | stop processing: n_tokens = 824, truncated = 0 13.12.053.000 I slot print_timing: id 1 | task 7706 | prompt processing, n_tokens = 1643, progress = 1.00, t = 7.25 s / 226.77 tokens per second 13.12.060.628 I slot print_timing: id 2 | task 7709 | prompt processing, n_tokens = 1086, progress = 0.68, t = 4.05 s / 268.36 tokens per second 13.12.064.805 I slot print_timing: id 3 | task 7710 | prompt processing, n_tokens = 706, progress = 0.44, t = 4.05 s / 174.47 tokens per second 13.13.629.506 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 324416250463 13.13.629.798 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 405.911 MiB) 13.13.655.382 I slot launch_slot_: id 0 | task 7713 | processing task, is_child = 0 13.13.655.797 I slot print_timing: id 2 | task 7709 | prompt processing, n_tokens = 1388, progress = 0.87, t = 5.62 s / 246.89 tokens per second 13.13.659.630 I slot print_timing: id 3 | task 7710 | prompt processing, n_tokens = 1114, progress = 0.69, t = 5.62 s / 198.16 tokens per second 13.16.964.921 I slot print_timing: id 0 | task 7713 | prompt processing, n_tokens = 1140, progress = 0.69, t = 3.31 s / 344.89 tokens per second 13.16.991.983 I slot print_timing: id 2 | task 7709 | prompt processing, n_tokens = 1598, progress = 1.00, t = 8.96 s / 178.38 tokens per second 13.16.996.429 I slot print_timing: id 3 | task 7710 | prompt processing, n_tokens = 1388, progress = 0.85, t = 8.96 s / 154.94 tokens per second 13.18.106.058 I slot print_timing: id 1 | task 7706 | prompt eval time = 8825.50 ms / 1647 tokens ( 5.36 ms per token, 186.62 tokens per second) 13.18.106.069 I slot print_timing: id 1 | task 7706 | eval time = 4476.56 ms / 3 tokens ( 2238.28 ms per token, 0.45 tokens per second) 13.18.106.071 I slot print_timing: id 1 | task 7706 | total time = 13302.06 ms / 1650 tokens 13.18.106.074 I slot print_timing: id 1 | task 7706 | graphs reused = 6236 13.18.106.075 I slot print_timing: id 1 | task 7706 | graph reallocs = 0 / 0 (same size) / (changed size) 13.18.106.386 I slot release: id 1 | task 7706 | stop processing: n_tokens = 1658, truncated = 0 13.18.108.672 I slot print_timing: id 0 | task 7713 | prompt processing, n_tokens = 1388, progress = 0.84, t = 4.45 s / 312.11 tokens per second 13.18.114.983 I slot print_timing: id 3 | task 7710 | prompt processing, n_tokens = 1626, progress = 1.00, t = 10.10 s / 160.99 tokens per second 13.18.776.489 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.814 (> 0.100 thold), f_keep = 0.859 13.18.776.768 I slot launch_slot_: id 1 | task 7717 | processing task, is_child = 0 13.18.776.795 I slot print_timing: id 0 | task 7713 | prompt processing, n_tokens = 1652, progress = 1.00, t = 5.11 s / 323.00 tokens per second 13.19.517.111 I slot print_timing: id 2 | task 7709 | prompt eval time = 10106.17 ms / 1602 tokens ( 6.31 ms per token, 158.52 tokens per second) 13.19.517.122 I slot print_timing: id 2 | task 7709 | eval time = 1408.47 ms / 3 tokens ( 704.23 ms per token, 1.42 tokens per second) 13.19.517.123 I slot print_timing: id 2 | task 7709 | total time = 11514.64 ms / 1605 tokens 13.19.517.125 I slot print_timing: id 2 | task 7709 | graphs reused = 6236 13.19.517.126 I slot print_timing: id 2 | task 7709 | graph reallocs = 0 / 0 (same size) / (changed size) 13.19.517.373 I slot release: id 2 | task 7709 | stop processing: n_tokens = 1613, truncated = 0 13.19.520.512 I slot print_timing: id 3 | task 7710 | prompt eval time = 10773.74 ms / 1630 tokens ( 6.61 ms per token, 151.29 tokens per second) 13.19.520.520 I slot print_timing: id 3 | task 7710 | eval time = 744.05 ms / 2 tokens ( 744.05 ms per token, 1.34 tokens per second) 13.19.520.526 I slot print_timing: id 3 | task 7710 | total time = 11517.79 ms / 1632 tokens 13.19.520.528 I slot print_timing: id 3 | task 7710 | graphs reused = 6236 13.19.520.529 I slot print_timing: id 3 | task 7710 | graph reallocs = 0 / 0 (same size) / (changed size) 13.19.520.713 I slot release: id 3 | task 7710 | stop processing: n_tokens = 1640, truncated = 0 13.19.601.463 I slot print_timing: id 0 | task 7713 | prompt eval time = 5859.42 ms / 1656 tokens ( 3.54 ms per token, 282.62 tokens per second) 13.19.601.473 I slot print_timing: id 0 | task 7713 | eval time = 86.63 ms / 2 tokens ( 86.63 ms per token, 11.54 tokens per second) 13.19.601.474 I slot print_timing: id 0 | task 7713 | total time = 5946.05 ms / 1658 tokens 13.19.601.475 I slot print_timing: id 0 | task 7713 | graphs reused = 6236 13.19.601.476 I slot print_timing: id 0 | task 7713 | graph reallocs = 0 / 0 (same size) / (changed size) 13.19.601.617 I slot release: id 0 | task 7713 | stop processing: n_tokens = 1666, truncated = 0 13.19.604.218 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1613, t_last = 324423714917 13.19.614.874 I slot launch_slot_: id 2 | task 7720 | processing task, is_child = 0 13.19.615.043 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 344.413 MiB) 13.19.625.815 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 398.525 MiB) 13.19.634.932 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1640, t_last = 324423718259 13.19.635.131 I slot launch_slot_: id 3 | task 7721 | processing task, is_child = 0 13.19.635.276 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1666, t_last = 324423799163 13.19.635.452 I slot launch_slot_: id 0 | task 7722 | processing task, is_child = 0 13.21.622.839 I slot print_timing: id 1 | task 7717 | prompt eval time = 821.46 ms / 325 tokens ( 2.53 ms per token, 395.64 tokens per second) 13.21.622.851 I slot print_timing: id 1 | task 7717 | eval time = 2018.59 ms / 2 tokens ( 2018.59 ms per token, 0.50 tokens per second) 13.21.622.852 I slot print_timing: id 1 | task 7717 | total time = 2840.04 ms / 327 tokens 13.21.622.855 I slot print_timing: id 1 | task 7717 | graphs reused = 6236 13.21.622.857 I slot print_timing: id 1 | task 7717 | graph reallocs = 0 / 0 (same size) / (changed size) 13.21.623.160 I slot release: id 1 | task 7717 | stop processing: n_tokens = 1750, truncated = 0 13.23.925.832 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1750, t_last = 324425820705 13.23.926.214 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 400.249 MiB) 13.24.017.528 I slot launch_slot_: id 1 | task 7725 | processing task, is_child = 0 13.24.017.555 I slot print_timing: id 0 | task 7722 | prompt processing, n_tokens = 714, progress = 0.85, t = 4.29 s / 166.42 tokens per second 13.24.021.900 I slot print_timing: id 2 | task 7720 | prompt processing, n_tokens = 721, progress = 0.86, t = 4.29 s / 168.07 tokens per second 13.24.025.777 I slot print_timing: id 3 | task 7721 | prompt processing, n_tokens = 721, progress = 0.84, t = 4.29 s / 168.08 tokens per second 13.25.437.511 I slot print_timing: id 0 | task 7722 | prompt processing, n_tokens = 836, progress = 1.00, t = 5.80 s / 144.09 tokens per second 13.25.536.592 I slot print_timing: id 2 | task 7720 | prompt processing, n_tokens = 831, progress = 1.00, t = 5.80 s / 143.24 tokens per second 13.25.540.804 I slot print_timing: id 3 | task 7721 | prompt processing, n_tokens = 858, progress = 1.00, t = 5.80 s / 147.90 tokens per second 13.26.784.422 I slot print_timing: id 0 | task 7722 | prompt eval time = 6740.90 ms / 840 tokens ( 8.02 ms per token, 124.61 tokens per second) 13.26.784.435 I slot print_timing: id 0 | task 7722 | eval time = 408.03 ms / 2 tokens ( 408.03 ms per token, 2.45 tokens per second) 13.26.784.437 I slot print_timing: id 0 | task 7722 | total time = 7148.92 ms / 842 tokens 13.26.784.439 I slot print_timing: id 0 | task 7722 | graphs reused = 6236 13.26.784.440 I slot print_timing: id 0 | task 7722 | graph reallocs = 0 / 0 (same size) / (changed size) 13.26.784.620 I slot release: id 0 | task 7722 | stop processing: n_tokens = 850, truncated = 0 13.26.787.202 I slot print_timing: id 2 | task 7720 | prompt eval time = 6742.94 ms / 835 tokens ( 8.08 ms per token, 123.83 tokens per second) 13.26.787.211 I slot print_timing: id 2 | task 7720 | eval time = 408.39 ms / 2 tokens ( 408.39 ms per token, 2.45 tokens per second) 13.26.787.212 I slot print_timing: id 2 | task 7720 | total time = 7151.34 ms / 837 tokens 13.26.787.213 I slot print_timing: id 2 | task 7720 | graphs reused = 6236 13.26.787.215 I slot print_timing: id 2 | task 7720 | graph reallocs = 0 / 0 (same size) / (changed size) 13.26.787.340 I slot release: id 2 | task 7720 | stop processing: n_tokens = 845, truncated = 0 13.26.789.595 I slot print_timing: id 3 | task 7721 | prompt eval time = 6744.84 ms / 862 tokens ( 7.82 ms per token, 127.80 tokens per second) 13.26.789.607 I slot print_timing: id 3 | task 7721 | eval time = 408.51 ms / 2 tokens ( 408.51 ms per token, 2.45 tokens per second) 13.26.789.609 I slot print_timing: id 3 | task 7721 | total time = 7153.36 ms / 864 tokens 13.26.789.610 I slot print_timing: id 3 | task 7721 | graphs reused = 6236 13.26.789.612 I slot print_timing: id 3 | task 7721 | graph reallocs = 0 / 0 (same size) / (changed size) 13.26.789.711 I slot release: id 3 | task 7721 | stop processing: n_tokens = 872, truncated = 0 13.26.835.316 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 850, t_last = 324430982164 13.26.843.442 I slot launch_slot_: id 0 | task 7730 | processing task, is_child = 0 13.26.843.574 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 343.253 MiB) 13.26.851.028 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 402.218 MiB) 13.26.879.139 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 845, t_last = 324430984884 13.26.879.340 I slot launch_slot_: id 2 | task 7731 | processing task, is_child = 0 13.26.879.421 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 872, t_last = 324430987254 13.26.882.694 I slot launch_slot_: id 3 | task 7732 | processing task, is_child = 0 13.27.836.406 I slot print_timing: id 1 | task 7725 | prompt eval time = 2813.98 ms / 859 tokens ( 3.28 ms per token, 305.26 tokens per second) 13.27.836.422 I slot print_timing: id 1 | task 7725 | eval time = 1001.05 ms / 2 tokens ( 1001.05 ms per token, 1.00 tokens per second) 13.27.836.424 I slot print_timing: id 1 | task 7725 | total time = 3815.03 ms / 861 tokens 13.27.836.426 I slot print_timing: id 1 | task 7725 | graphs reused = 6236 13.27.836.427 I slot print_timing: id 1 | task 7725 | graph reallocs = 0 / 0 (same size) / (changed size) 13.27.836.606 I slot release: id 1 | task 7725 | stop processing: n_tokens = 869, truncated = 0 13.29.338.312 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 324432034149 13.29.783.277 I slot launch_slot_: id 1 | task 7735 | processing task, is_child = 0 13.30.775.445 I slot print_timing: id 0 | task 7730 | prompt processing, n_tokens = 729, progress = 0.99, t = 3.89 s / 187.33 tokens per second 13.30.782.587 I slot print_timing: id 2 | task 7731 | prompt processing, n_tokens = 758, progress = 0.99, t = 3.89 s / 194.80 tokens per second 13.31.682.631 I slot print_timing: id 3 | task 7732 | prompt eval time = 3892.24 ms / 171 tokens ( 22.76 ms per token, 43.93 tokens per second) 13.31.682.648 I slot print_timing: id 3 | task 7732 | eval time = 907.19 ms / 2 tokens ( 907.19 ms per token, 1.10 tokens per second) 13.31.682.650 I slot print_timing: id 3 | task 7732 | total time = 4799.44 ms / 173 tokens 13.31.682.652 I slot print_timing: id 3 | task 7732 | graphs reused = 6236 13.31.682.653 I slot print_timing: id 3 | task 7732 | graph reallocs = 0 / 0 (same size) / (changed size) 13.31.682.813 I slot release: id 3 | task 7732 | stop processing: n_tokens = 894, truncated = 0 13.32.015.911 I slot print_timing: id 0 | task 7730 | prompt eval time = 4795.46 ms / 733 tokens ( 6.54 ms per token, 152.85 tokens per second) 13.32.015.920 I slot print_timing: id 0 | task 7730 | eval time = 337.70 ms / 2 tokens ( 337.70 ms per token, 2.96 tokens per second) 13.32.015.922 I slot print_timing: id 0 | task 7730 | total time = 5133.16 ms / 735 tokens 13.32.015.924 I slot print_timing: id 0 | task 7730 | graphs reused = 6236 13.32.015.925 I slot print_timing: id 0 | task 7730 | graph reallocs = 0 / 0 (same size) / (changed size) 13.32.016.210 I slot release: id 0 | task 7730 | stop processing: n_tokens = 743, truncated = 0 13.32.019.025 I slot print_timing: id 2 | task 7731 | prompt eval time = 4797.53 ms / 762 tokens ( 6.30 ms per token, 158.83 tokens per second) 13.32.019.033 I slot print_timing: id 2 | task 7731 | eval time = 338.51 ms / 2 tokens ( 338.51 ms per token, 2.95 tokens per second) 13.32.019.038 I slot print_timing: id 2 | task 7731 | total time = 5136.05 ms / 764 tokens 13.32.019.040 I slot print_timing: id 2 | task 7731 | graphs reused = 6236 13.32.019.044 I slot print_timing: id 2 | task 7731 | graph reallocs = 0 / 0 (same size) / (changed size) 13.32.019.263 I slot release: id 2 | task 7731 | stop processing: n_tokens = 772, truncated = 0 13.32.019.303 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 894, t_last = 324435880356 13.32.051.965 I slot launch_slot_: id 3 | task 7739 | processing task, is_child = 0 13.32.052.081 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 346.523 MiB) 13.32.070.424 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 397.084 MiB) 13.32.093.029 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 743, t_last = 324436213753 13.32.093.210 I slot launch_slot_: id 0 | task 7740 | processing task, is_child = 0 13.34.392.740 I slot print_timing: id 1 | task 7735 | prompt eval time = 3035.59 ms / 688 tokens ( 4.41 ms per token, 226.64 tokens per second) 13.34.392.751 I slot print_timing: id 1 | task 7735 | eval time = 1572.07 ms / 2 tokens ( 1572.07 ms per token, 0.64 tokens per second) 13.34.392.759 I slot print_timing: id 1 | task 7735 | total time = 4607.66 ms / 690 tokens 13.34.392.761 I slot print_timing: id 1 | task 7735 | graphs reused = 6236 13.34.392.766 I slot print_timing: id 1 | task 7735 | graph reallocs = 0 / 0 (same size) / (changed size) 13.34.392.917 I slot release: id 1 | task 7735 | stop processing: n_tokens = 698, truncated = 0 13.35.134.675 I slot print_timing: id 0 | task 7740 | prompt eval time = 2986.23 ms / 673 tokens ( 4.44 ms per token, 225.37 tokens per second) 13.35.134.693 I slot print_timing: id 0 | task 7740 | eval time = 55.11 ms / 2 tokens ( 55.11 ms per token, 18.14 tokens per second) 13.35.134.697 I slot print_timing: id 0 | task 7740 | total time = 3041.35 ms / 675 tokens 13.35.134.698 I slot print_timing: id 0 | task 7740 | graphs reused = 6236 13.35.134.700 I slot print_timing: id 0 | task 7740 | graph reallocs = 0 / 0 (same size) / (changed size) 13.35.134.814 I slot release: id 0 | task 7740 | stop processing: n_tokens = 683, truncated = 0 13.35.137.080 I slot print_timing: id 3 | task 7739 | prompt eval time = 2986.23 ms / 707 tokens ( 4.22 ms per token, 236.75 tokens per second) 13.35.137.086 I slot print_timing: id 3 | task 7739 | eval time = 54.80 ms / 2 tokens ( 54.80 ms per token, 18.25 tokens per second) 13.35.137.087 I slot print_timing: id 3 | task 7739 | total time = 3041.03 ms / 709 tokens 13.35.137.089 I slot print_timing: id 3 | task 7739 | graphs reused = 6236 13.35.137.090 I slot print_timing: id 3 | task 7739 | graph reallocs = 0 / 0 (same size) / (changed size) 13.35.137.164 I slot release: id 3 | task 7739 | stop processing: n_tokens = 717, truncated = 0 13.38.046.705 I srv operator(): operator(): cleaning up before exit...