/Users/minipro/quantdiff/work/llama-b11869/src/build/bin/llama-server -m /Users/minipro/quantdiff/models/campaign/91b8d85ab6ff/flint-UD-Q3_K_XL.gguf --host 127.0.0.1 --port 8091 -c 16384 -np 4 -ngl 999 -fa on --jinja --seed 1234 --chat-template-kwargs "{\"enable_thinking\": false}" --no-webui -a quant 0.00.049.951 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.050.001 I srv llama_server: initializing ... 0.00.050.007 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.050.092 I srv init_listene: The UI is disabled 0.00.050.093 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.050.130 W srv server_setup: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.051.798 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/91b8d85ab6ff/flint-UD-Q3_K_XL.gguf' 0.01.097.411 I cmn init: llama threadpool init, n_threads = 8 0.01.190.432 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.01.199.761 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.199.771 I srv server_run_i: model loaded 0.01.199.776 I srv server_on_li: listening on http://127.0.0.1:8091 0.30.906.405 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.30.906.455 I slot launch_slot_: id 0 | task 1 | processing task, is_child = 0 0.30.906.458 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.30.906.494 I slot launch_slot_: id 1 | task 3 | processing task, is_child = 0 0.30.906.496 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.30.906.532 I slot launch_slot_: id 2 | task 0 | processing task, is_child = 0 0.30.906.533 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.30.906.569 I slot launch_slot_: id 3 | task 2 | processing task, is_child = 0 0.32.019.433 I slot print_timing: id 0 | task 1 | prompt eval time = 1072.44 ms / 107 tokens ( 10.02 ms per token, 99.77 tokens per second) 0.32.019.437 I slot print_timing: id 0 | task 1 | eval time = 40.41 ms / 2 tokens ( 40.41 ms per token, 24.75 tokens per second) 0.32.019.438 I slot print_timing: id 0 | task 1 | total time = 1112.85 ms / 109 tokens 0.32.019.438 I slot print_timing: id 0 | task 1 | graphs reused = 1 0.32.019.439 I slot print_timing: id 0 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.019.458 I slot release: id 0 | task 1 | stop processing: n_tokens = 108, truncated = 0 0.32.019.555 I slot print_timing: id 1 | task 3 | prompt eval time = 1072.62 ms / 122 tokens ( 8.79 ms per token, 113.74 tokens per second) 0.32.019.557 I slot print_timing: id 1 | task 3 | eval time = 40.34 ms / 2 tokens ( 40.34 ms per token, 24.79 tokens per second) 0.32.019.557 I slot print_timing: id 1 | task 3 | total time = 1112.97 ms / 124 tokens 0.32.019.558 I slot print_timing: id 1 | task 3 | graphs reused = 1 0.32.019.558 I slot print_timing: id 1 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.019.569 I slot release: id 1 | task 3 | stop processing: n_tokens = 123, truncated = 0 0.32.019.665 I slot print_timing: id 2 | task 0 | prompt eval time = 1072.80 ms / 102 tokens ( 10.52 ms per token, 95.08 tokens per second) 0.32.019.667 I slot print_timing: id 2 | task 0 | eval time = 40.27 ms / 2 tokens ( 40.27 ms per token, 24.83 tokens per second) 0.32.019.668 I slot print_timing: id 2 | task 0 | total time = 1113.07 ms / 104 tokens 0.32.019.668 I slot print_timing: id 2 | task 0 | graphs reused = 1 0.32.019.668 I slot print_timing: id 2 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.019.676 I slot release: id 2 | task 0 | stop processing: n_tokens = 103, truncated = 0 0.32.019.785 I slot print_timing: id 3 | task 2 | prompt eval time = 1072.98 ms / 115 tokens ( 9.33 ms per token, 107.18 tokens per second) 0.32.019.787 I slot print_timing: id 3 | task 2 | eval time = 40.21 ms / 2 tokens ( 40.21 ms per token, 24.87 tokens per second) 0.32.019.788 I slot print_timing: id 3 | task 2 | total time = 1113.19 ms / 117 tokens 0.32.019.788 I slot print_timing: id 3 | task 2 | graphs reused = 1 0.32.019.788 I slot print_timing: id 3 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.019.798 I slot release: id 3 | task 2 | stop processing: n_tokens = 116, truncated = 0 0.32.028.453 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.250 0.32.030.022 I slot launch_slot_: id 0 | task 7 | processing task, is_child = 0 0.32.034.278 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.220 0.32.034.353 I slot launch_slot_: id 1 | task 8 | processing task, is_child = 0 0.32.034.395 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.252 0.32.034.451 I slot launch_slot_: id 2 | task 9 | processing task, is_child = 0 0.32.034.474 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.138 (> 0.100 thold), f_keep = 0.224 0.32.034.528 I slot launch_slot_: id 3 | task 10 | processing task, is_child = 0 0.33.553.820 I slot print_timing: id 0 | task 7 | prompt eval time = 1478.57 ms / 99 tokens ( 14.94 ms per token, 66.96 tokens per second) 0.33.553.821 I slot print_timing: id 0 | task 7 | eval time = 40.71 ms / 2 tokens ( 40.71 ms per token, 24.57 tokens per second) 0.33.553.822 I slot print_timing: id 0 | task 7 | total time = 1519.28 ms / 101 tokens 0.33.553.822 I slot print_timing: id 0 | task 7 | graphs reused = 1 0.33.553.823 I slot print_timing: id 0 | task 7 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.553.840 I slot release: id 0 | task 7 | stop processing: n_tokens = 100, truncated = 0 0.33.553.938 I slot print_timing: id 1 | task 8 | prompt eval time = 1478.73 ms / 140 tokens ( 10.56 ms per token, 94.68 tokens per second) 0.33.553.942 I slot print_timing: id 1 | task 8 | eval time = 40.65 ms / 2 tokens ( 40.65 ms per token, 24.60 tokens per second) 0.33.553.942 I slot print_timing: id 1 | task 8 | total time = 1519.38 ms / 142 tokens 0.33.553.943 I slot print_timing: id 1 | task 8 | graphs reused = 1 0.33.553.943 I slot print_timing: id 1 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.553.954 I slot release: id 1 | task 8 | stop processing: n_tokens = 141, truncated = 0 0.33.554.052 I slot print_timing: id 2 | task 9 | prompt eval time = 1478.89 ms / 149 tokens ( 9.93 ms per token, 100.75 tokens per second) 0.33.554.056 I slot print_timing: id 2 | task 9 | eval time = 40.59 ms / 2 tokens ( 40.59 ms per token, 24.64 tokens per second) 0.33.554.056 I slot print_timing: id 2 | task 9 | total time = 1519.48 ms / 151 tokens 0.33.554.056 I slot print_timing: id 2 | task 9 | graphs reused = 1 0.33.554.056 I slot print_timing: id 2 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.554.069 I slot release: id 2 | task 9 | stop processing: n_tokens = 150, truncated = 0 0.33.554.170 I slot print_timing: id 3 | task 10 | prompt eval time = 1479.06 ms / 189 tokens ( 7.83 ms per token, 127.78 tokens per second) 0.33.554.172 I slot print_timing: id 3 | task 10 | eval time = 40.53 ms / 2 tokens ( 40.53 ms per token, 24.67 tokens per second) 0.33.554.173 I slot print_timing: id 3 | task 10 | total time = 1519.58 ms / 191 tokens 0.33.554.173 I slot print_timing: id 3 | task 10 | graphs reused = 1 0.33.554.173 I slot print_timing: id 3 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.554.193 I slot release: id 3 | task 10 | stop processing: n_tokens = 190, truncated = 0 0.33.559.357 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.270 0.33.560.439 I slot launch_slot_: id 0 | task 14 | processing task, is_child = 0 0.33.566.712 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.184 0.33.566.794 I slot launch_slot_: id 1 | task 15 | processing task, is_child = 0 0.33.566.847 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.173 0.33.566.915 I slot launch_slot_: id 2 | task 16 | processing task, is_child = 0 0.33.566.947 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.137 0.33.567.007 I slot launch_slot_: id 3 | task 17 | processing task, is_child = 0 0.34.658.149 I slot print_timing: id 0 | task 14 | prompt eval time = 1050.91 ms / 107 tokens ( 9.82 ms per token, 101.82 tokens per second) 0.34.658.151 I slot print_timing: id 0 | task 14 | eval time = 40.22 ms / 2 tokens ( 40.22 ms per token, 24.86 tokens per second) 0.34.658.152 I slot print_timing: id 0 | task 14 | total time = 1091.13 ms / 109 tokens 0.34.658.152 I slot print_timing: id 0 | task 14 | graphs reused = 1 0.34.658.153 I slot print_timing: id 0 | task 14 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.658.173 I slot release: id 0 | task 14 | stop processing: n_tokens = 108, truncated = 0 0.34.658.263 I slot print_timing: id 1 | task 15 | prompt eval time = 1050.98 ms / 117 tokens ( 8.98 ms per token, 111.32 tokens per second) 0.34.658.265 I slot print_timing: id 1 | task 15 | eval time = 40.25 ms / 2 tokens ( 40.25 ms per token, 24.85 tokens per second) 0.34.658.266 I slot print_timing: id 1 | task 15 | total time = 1091.23 ms / 119 tokens 0.34.658.266 I slot print_timing: id 1 | task 15 | graphs reused = 1 0.34.658.266 I slot print_timing: id 1 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.658.278 I slot release: id 1 | task 15 | stop processing: n_tokens = 118, truncated = 0 0.34.658.361 I slot print_timing: id 2 | task 16 | prompt eval time = 1051.06 ms / 138 tokens ( 7.62 ms per token, 131.30 tokens per second) 0.34.658.364 I slot print_timing: id 2 | task 16 | eval time = 40.24 ms / 2 tokens ( 40.24 ms per token, 24.85 tokens per second) 0.34.658.364 I slot print_timing: id 2 | task 16 | total time = 1091.31 ms / 140 tokens 0.34.658.365 I slot print_timing: id 2 | task 16 | graphs reused = 1 0.34.658.365 I slot print_timing: id 2 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.658.374 I slot release: id 2 | task 16 | stop processing: n_tokens = 139, truncated = 0 0.34.658.467 I slot print_timing: id 3 | task 17 | prompt eval time = 1051.14 ms / 109 tokens ( 9.64 ms per token, 103.70 tokens per second) 0.34.658.469 I slot print_timing: id 3 | task 17 | eval time = 40.25 ms / 2 tokens ( 40.25 ms per token, 24.85 tokens per second) 0.34.658.469 I slot print_timing: id 3 | task 17 | total time = 1091.39 ms / 111 tokens 0.34.658.469 I slot print_timing: id 3 | task 17 | graphs reused = 1 0.34.658.470 I slot print_timing: id 3 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.658.480 I slot release: id 3 | task 17 | stop processing: n_tokens = 110, truncated = 0 0.34.664.602 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.241 0.34.665.747 I slot launch_slot_: id 0 | task 21 | processing task, is_child = 0 0.34.670.547 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.220 0.34.670.618 I slot launch_slot_: id 1 | task 22 | processing task, is_child = 0 0.34.670.668 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.187 0.34.670.726 I slot launch_slot_: id 2 | task 23 | processing task, is_child = 0 0.34.670.748 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.150 (> 0.100 thold), f_keep = 0.236 0.34.670.804 I slot launch_slot_: id 3 | task 24 | processing task, is_child = 0 0.36.096.108 I slot print_timing: id 0 | task 21 | prompt eval time = 1384.89 ms / 110 tokens ( 12.59 ms per token, 79.43 tokens per second) 0.36.096.110 I slot print_timing: id 0 | task 21 | eval time = 40.40 ms / 2 tokens ( 40.40 ms per token, 24.75 tokens per second) 0.36.096.111 I slot print_timing: id 0 | task 21 | total time = 1425.29 ms / 112 tokens 0.36.096.111 I slot print_timing: id 0 | task 21 | graphs reused = 1 0.36.096.112 I slot print_timing: id 0 | task 21 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.096.133 I slot release: id 0 | task 21 | stop processing: n_tokens = 111, truncated = 0 0.36.096.223 I slot print_timing: id 1 | task 22 | prompt eval time = 1384.97 ms / 128 tokens ( 10.82 ms per token, 92.42 tokens per second) 0.36.096.225 I slot print_timing: id 1 | task 22 | eval time = 40.42 ms / 2 tokens ( 40.42 ms per token, 24.74 tokens per second) 0.36.096.226 I slot print_timing: id 1 | task 22 | total time = 1425.39 ms / 130 tokens 0.36.096.226 I slot print_timing: id 1 | task 22 | graphs reused = 1 0.36.096.226 I slot print_timing: id 1 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.096.237 I slot release: id 1 | task 22 | stop processing: n_tokens = 129, truncated = 0 0.36.096.331 I slot print_timing: id 2 | task 23 | prompt eval time = 1385.06 ms / 135 tokens ( 10.26 ms per token, 97.47 tokens per second) 0.36.096.333 I slot print_timing: id 2 | task 23 | eval time = 40.42 ms / 2 tokens ( 40.42 ms per token, 24.74 tokens per second) 0.36.096.334 I slot print_timing: id 2 | task 23 | total time = 1425.48 ms / 137 tokens 0.36.096.338 I slot print_timing: id 2 | task 23 | graphs reused = 1 0.36.096.338 I slot print_timing: id 2 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.096.351 I slot release: id 2 | task 23 | stop processing: n_tokens = 136, truncated = 0 0.36.096.449 I slot print_timing: id 3 | task 24 | prompt eval time = 1385.14 ms / 173 tokens ( 8.01 ms per token, 124.90 tokens per second) 0.36.096.451 I slot print_timing: id 3 | task 24 | eval time = 40.45 ms / 2 tokens ( 40.45 ms per token, 24.72 tokens per second) 0.36.096.451 I slot print_timing: id 3 | task 24 | total time = 1425.58 ms / 175 tokens 0.36.096.452 I slot print_timing: id 3 | task 24 | graphs reused = 1 0.36.096.452 I slot print_timing: id 3 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.096.460 I slot release: id 3 | task 24 | stop processing: n_tokens = 174, truncated = 0 0.36.101.962 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.234 0.36.103.521 I slot launch_slot_: id 0 | task 28 | processing task, is_child = 0 0.36.108.718 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.202 0.36.109.050 I slot launch_slot_: id 1 | task 29 | processing task, is_child = 0 0.36.109.099 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.191 0.36.109.157 I slot launch_slot_: id 2 | task 30 | processing task, is_child = 0 0.36.109.184 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.149 0.36.109.243 I slot launch_slot_: id 3 | task 31 | processing task, is_child = 0 0.37.394.838 I slot print_timing: id 0 | task 28 | prompt eval time = 1245.34 ms / 115 tokens ( 10.83 ms per token, 92.34 tokens per second) 0.37.394.840 I slot print_timing: id 0 | task 28 | eval time = 40.24 ms / 2 tokens ( 40.24 ms per token, 24.85 tokens per second) 0.37.394.841 I slot print_timing: id 0 | task 28 | total time = 1285.59 ms / 117 tokens 0.37.394.841 I slot print_timing: id 0 | task 28 | graphs reused = 1 0.37.394.841 I slot print_timing: id 0 | task 28 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.394.864 I slot release: id 0 | task 28 | stop processing: n_tokens = 116, truncated = 0 0.37.394.954 I slot print_timing: id 1 | task 29 | prompt eval time = 1245.42 ms / 119 tokens ( 10.47 ms per token, 95.55 tokens per second) 0.37.394.956 I slot print_timing: id 1 | task 29 | eval time = 40.26 ms / 2 tokens ( 40.26 ms per token, 24.84 tokens per second) 0.37.394.956 I slot print_timing: id 1 | task 29 | total time = 1285.69 ms / 121 tokens 0.37.394.957 I slot print_timing: id 1 | task 29 | graphs reused = 1 0.37.394.957 I slot print_timing: id 1 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.394.968 I slot release: id 1 | task 29 | stop processing: n_tokens = 120, truncated = 0 0.37.395.062 I slot print_timing: id 2 | task 30 | prompt eval time = 1245.52 ms / 130 tokens ( 9.58 ms per token, 104.37 tokens per second) 0.37.395.064 I slot print_timing: id 2 | task 30 | eval time = 40.27 ms / 2 tokens ( 40.27 ms per token, 24.83 tokens per second) 0.37.395.064 I slot print_timing: id 2 | task 30 | total time = 1285.78 ms / 132 tokens 0.37.395.065 I slot print_timing: id 2 | task 30 | graphs reused = 1 0.37.395.065 I slot print_timing: id 2 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.395.079 I slot release: id 2 | task 30 | stop processing: n_tokens = 131, truncated = 0 0.37.395.174 I slot print_timing: id 3 | task 31 | prompt eval time = 1245.60 ms / 165 tokens ( 7.55 ms per token, 132.47 tokens per second) 0.37.395.176 I slot print_timing: id 3 | task 31 | eval time = 40.27 ms / 2 tokens ( 40.27 ms per token, 24.83 tokens per second) 0.37.395.177 I slot print_timing: id 3 | task 31 | total time = 1285.88 ms / 167 tokens 0.37.395.177 I slot print_timing: id 3 | task 31 | graphs reused = 1 0.37.395.177 I slot print_timing: id 3 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.395.186 I slot release: id 3 | task 31 | stop processing: n_tokens = 166, truncated = 0 0.37.400.549 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.233 0.37.401.775 I slot launch_slot_: id 0 | task 35 | processing task, is_child = 0 0.37.407.383 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.163 0.37.407.466 I slot launch_slot_: id 3 | task 36 | processing task, is_child = 0 0.37.407.518 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.217 0.37.407.578 I slot launch_slot_: id 1 | task 37 | processing task, is_child = 0 0.37.407.609 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.198 0.37.407.678 I slot launch_slot_: id 2 | task 38 | processing task, is_child = 0 0.38.589.396 I slot print_timing: id 0 | task 35 | prompt eval time = 1141.52 ms / 108 tokens ( 10.57 ms per token, 94.61 tokens per second) 0.38.589.398 I slot print_timing: id 0 | task 35 | eval time = 40.19 ms / 2 tokens ( 40.19 ms per token, 24.88 tokens per second) 0.38.589.399 I slot print_timing: id 0 | task 35 | total time = 1181.71 ms / 110 tokens 0.38.589.399 I slot print_timing: id 0 | task 35 | graphs reused = 1 0.38.589.399 I slot print_timing: id 0 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.589.417 I slot release: id 0 | task 35 | stop processing: n_tokens = 109, truncated = 0 0.38.589.506 I slot print_timing: id 1 | task 37 | prompt eval time = 1141.59 ms / 134 tokens ( 8.52 ms per token, 117.38 tokens per second) 0.38.589.507 I slot print_timing: id 1 | task 37 | eval time = 40.20 ms / 2 tokens ( 40.20 ms per token, 24.87 tokens per second) 0.38.589.508 I slot print_timing: id 1 | task 37 | total time = 1181.80 ms / 136 tokens 0.38.589.508 I slot print_timing: id 1 | task 37 | graphs reused = 1 0.38.589.508 I slot print_timing: id 1 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.589.523 I slot release: id 1 | task 37 | stop processing: n_tokens = 135, truncated = 0 0.38.589.608 I slot print_timing: id 2 | task 38 | prompt eval time = 1141.67 ms / 104 tokens ( 10.98 ms per token, 91.09 tokens per second) 0.38.589.610 I slot print_timing: id 2 | task 38 | eval time = 40.21 ms / 2 tokens ( 40.21 ms per token, 24.87 tokens per second) 0.38.589.611 I slot print_timing: id 2 | task 38 | total time = 1181.88 ms / 106 tokens 0.38.589.611 I slot print_timing: id 2 | task 38 | graphs reused = 1 0.38.589.611 I slot print_timing: id 2 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.589.619 I slot release: id 2 | task 38 | stop processing: n_tokens = 105, truncated = 0 0.38.589.703 I slot print_timing: id 3 | task 36 | prompt eval time = 1141.75 ms / 135 tokens ( 8.46 ms per token, 118.24 tokens per second) 0.38.589.705 I slot print_timing: id 3 | task 36 | eval time = 40.20 ms / 2 tokens ( 40.20 ms per token, 24.87 tokens per second) 0.38.589.706 I slot print_timing: id 3 | task 36 | total time = 1181.95 ms / 137 tokens 0.38.589.706 I slot print_timing: id 3 | task 36 | graphs reused = 1 0.38.589.706 I slot print_timing: id 3 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.589.715 I slot release: id 3 | task 36 | stop processing: n_tokens = 136, truncated = 0 0.38.595.346 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.268 (> 0.100 thold), f_keep = 0.239 0.38.596.306 I slot launch_slot_: id 0 | task 42 | processing task, is_child = 0 0.38.600.800 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.193 0.38.601.147 I slot launch_slot_: id 1 | task 43 | processing task, is_child = 0 0.38.601.192 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.248 0.38.601.247 I slot launch_slot_: id 2 | task 44 | processing task, is_child = 0 0.38.601.271 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.191 0.38.601.327 I slot launch_slot_: id 3 | task 45 | processing task, is_child = 0 0.39.761.542 I slot print_timing: id 0 | task 42 | prompt eval time = 1120.26 ms / 97 tokens ( 11.55 ms per token, 86.59 tokens per second) 0.39.761.548 I slot print_timing: id 0 | task 42 | eval time = 39.95 ms / 2 tokens ( 39.95 ms per token, 25.03 tokens per second) 0.39.761.548 I slot print_timing: id 0 | task 42 | total time = 1160.21 ms / 99 tokens 0.39.761.548 I slot print_timing: id 0 | task 42 | graphs reused = 1 0.39.761.549 I slot print_timing: id 0 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.761.567 I slot release: id 0 | task 42 | stop processing: n_tokens = 98, truncated = 0 0.39.761.657 I slot print_timing: id 1 | task 43 | prompt eval time = 1120.34 ms / 104 tokens ( 10.77 ms per token, 92.83 tokens per second) 0.39.761.658 I slot print_timing: id 1 | task 43 | eval time = 39.97 ms / 2 tokens ( 39.97 ms per token, 25.02 tokens per second) 0.39.761.659 I slot print_timing: id 1 | task 43 | total time = 1160.31 ms / 106 tokens 0.39.761.659 I slot print_timing: id 1 | task 43 | graphs reused = 1 0.39.761.660 I slot print_timing: id 1 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.761.670 I slot release: id 1 | task 43 | stop processing: n_tokens = 105, truncated = 0 0.39.761.759 I slot print_timing: id 2 | task 44 | prompt eval time = 1120.43 ms / 113 tokens ( 9.92 ms per token, 100.85 tokens per second) 0.39.761.761 I slot print_timing: id 2 | task 44 | eval time = 39.97 ms / 2 tokens ( 39.97 ms per token, 25.02 tokens per second) 0.39.761.762 I slot print_timing: id 2 | task 44 | total time = 1160.40 ms / 115 tokens 0.39.761.762 I slot print_timing: id 2 | task 44 | graphs reused = 1 0.39.761.762 I slot print_timing: id 2 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.761.776 I slot release: id 2 | task 44 | stop processing: n_tokens = 114, truncated = 0 0.39.761.869 I slot print_timing: id 3 | task 45 | prompt eval time = 1120.52 ms / 135 tokens ( 8.30 ms per token, 120.48 tokens per second) 0.39.761.871 I slot print_timing: id 3 | task 45 | eval time = 39.98 ms / 2 tokens ( 39.98 ms per token, 25.01 tokens per second) 0.39.761.871 I slot print_timing: id 3 | task 45 | total time = 1160.50 ms / 137 tokens 0.39.761.872 I slot print_timing: id 3 | task 45 | graphs reused = 1 0.39.761.872 I slot print_timing: id 3 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.761.879 I slot release: id 3 | task 45 | stop processing: n_tokens = 136, truncated = 0 0.39.767.351 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.257 0.39.767.992 I slot launch_slot_: id 1 | task 49 | processing task, is_child = 0 0.39.771.959 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.265 0.39.772.024 I slot launch_slot_: id 0 | task 50 | processing task, is_child = 0 0.39.772.072 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.228 0.39.772.407 I slot launch_slot_: id 2 | task 51 | processing task, is_child = 0 0.39.772.431 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.202 (> 0.100 thold), f_keep = 0.191 0.39.772.491 I slot launch_slot_: id 3 | task 52 | processing task, is_child = 0 0.40.891.155 I slot print_timing: id 0 | task 50 | prompt eval time = 1078.58 ms / 95 tokens ( 11.35 ms per token, 88.08 tokens per second) 0.40.891.157 I slot print_timing: id 0 | task 50 | eval time = 40.08 ms / 2 tokens ( 40.08 ms per token, 24.95 tokens per second) 0.40.891.158 I slot print_timing: id 0 | task 50 | total time = 1118.65 ms / 97 tokens 0.40.891.158 I slot print_timing: id 0 | task 50 | graphs reused = 1 0.40.891.159 I slot print_timing: id 0 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.891.180 I slot release: id 0 | task 50 | stop processing: n_tokens = 96, truncated = 0 0.40.891.269 I slot print_timing: id 1 | task 49 | prompt eval time = 1078.66 ms / 98 tokens ( 11.01 ms per token, 90.85 tokens per second) 0.40.891.270 I slot print_timing: id 1 | task 49 | eval time = 40.10 ms / 2 tokens ( 40.10 ms per token, 24.94 tokens per second) 0.40.891.271 I slot print_timing: id 1 | task 49 | total time = 1118.76 ms / 100 tokens 0.40.891.271 I slot print_timing: id 1 | task 49 | graphs reused = 1 0.40.891.271 I slot print_timing: id 1 | task 49 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.891.280 I slot release: id 1 | task 49 | stop processing: n_tokens = 99, truncated = 0 0.40.891.371 I slot print_timing: id 2 | task 51 | prompt eval time = 1078.75 ms / 120 tokens ( 8.99 ms per token, 111.24 tokens per second) 0.40.891.373 I slot print_timing: id 2 | task 51 | eval time = 40.10 ms / 2 tokens ( 40.10 ms per token, 24.94 tokens per second) 0.40.891.374 I slot print_timing: id 2 | task 51 | total time = 1118.85 ms / 122 tokens 0.40.891.374 I slot print_timing: id 2 | task 51 | graphs reused = 1 0.40.891.374 I slot print_timing: id 2 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.891.382 I slot release: id 2 | task 51 | stop processing: n_tokens = 121, truncated = 0 0.40.891.487 I slot print_timing: id 3 | task 52 | prompt eval time = 1078.84 ms / 129 tokens ( 8.36 ms per token, 119.57 tokens per second) 0.40.891.490 I slot print_timing: id 3 | task 52 | eval time = 40.11 ms / 2 tokens ( 40.11 ms per token, 24.93 tokens per second) 0.40.891.491 I slot print_timing: id 3 | task 52 | total time = 1118.95 ms / 131 tokens 0.40.891.491 I slot print_timing: id 3 | task 52 | graphs reused = 1 0.40.891.491 I slot print_timing: id 3 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.891.499 I slot release: id 3 | task 52 | stop processing: n_tokens = 130, truncated = 0 0.40.897.296 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.271 0.40.898.430 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.40.902.567 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.263 0.40.902.635 I slot launch_slot_: id 1 | task 57 | processing task, is_child = 0 0.40.902.681 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.215 0.40.902.738 I slot launch_slot_: id 2 | task 58 | processing task, is_child = 0 0.40.902.763 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.200 0.40.902.819 I slot launch_slot_: id 3 | task 59 | processing task, is_child = 0 0.42.299.762 I slot print_timing: id 0 | task 56 | prompt eval time = 1356.84 ms / 125 tokens ( 10.85 ms per token, 92.13 tokens per second) 0.42.299.763 I slot print_timing: id 0 | task 56 | eval time = 40.10 ms / 2 tokens ( 40.10 ms per token, 24.94 tokens per second) 0.42.299.764 I slot print_timing: id 0 | task 56 | total time = 1396.93 ms / 127 tokens 0.42.299.765 I slot print_timing: id 0 | task 56 | graphs reused = 1 0.42.299.765 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.299.783 I slot release: id 0 | task 56 | stop processing: n_tokens = 126, truncated = 0 0.42.299.883 I slot print_timing: id 1 | task 57 | prompt eval time = 1356.91 ms / 158 tokens ( 8.59 ms per token, 116.44 tokens per second) 0.42.299.885 I slot print_timing: id 1 | task 57 | eval time = 40.12 ms / 2 tokens ( 40.12 ms per token, 24.92 tokens per second) 0.42.299.885 I slot print_timing: id 1 | task 57 | total time = 1397.04 ms / 160 tokens 0.42.299.885 I slot print_timing: id 1 | task 57 | graphs reused = 1 0.42.299.886 I slot print_timing: id 1 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.299.896 I slot release: id 1 | task 57 | stop processing: n_tokens = 159, truncated = 0 0.42.299.984 I slot print_timing: id 2 | task 58 | prompt eval time = 1356.99 ms / 165 tokens ( 8.22 ms per token, 121.59 tokens per second) 0.42.299.987 I slot print_timing: id 2 | task 58 | eval time = 40.13 ms / 2 tokens ( 40.13 ms per token, 24.92 tokens per second) 0.42.299.987 I slot print_timing: id 2 | task 58 | total time = 1397.12 ms / 167 tokens 0.42.299.988 I slot print_timing: id 2 | task 58 | graphs reused = 1 0.42.299.988 I slot print_timing: id 2 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.300.000 I slot release: id 2 | task 58 | stop processing: n_tokens = 166, truncated = 0 0.42.300.085 I slot print_timing: id 3 | task 59 | prompt eval time = 1357.08 ms / 174 tokens ( 7.80 ms per token, 128.22 tokens per second) 0.42.300.088 I slot print_timing: id 3 | task 59 | eval time = 40.13 ms / 2 tokens ( 40.13 ms per token, 24.92 tokens per second) 0.42.300.088 I slot print_timing: id 3 | task 59 | total time = 1397.21 ms / 176 tokens 0.42.300.088 I slot print_timing: id 3 | task 59 | graphs reused = 1 0.42.300.089 I slot print_timing: id 3 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.300.102 I slot release: id 3 | task 59 | stop processing: n_tokens = 175, truncated = 0 0.42.305.140 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.206 0.42.306.803 I slot launch_slot_: id 0 | task 63 | processing task, is_child = 0 0.42.313.035 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.164 0.42.313.381 I slot launch_slot_: id 1 | task 64 | processing task, is_child = 0 0.42.313.433 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.157 0.42.313.494 I slot launch_slot_: id 2 | task 65 | processing task, is_child = 0 0.42.313.522 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.149 0.42.313.582 I slot launch_slot_: id 3 | task 66 | processing task, is_child = 0 0.43.652.672 I slot print_timing: id 0 | task 63 | prompt eval time = 1298.77 ms / 114 tokens ( 11.39 ms per token, 87.78 tokens per second) 0.43.652.674 I slot print_timing: id 0 | task 63 | eval time = 40.31 ms / 2 tokens ( 40.31 ms per token, 24.81 tokens per second) 0.43.652.674 I slot print_timing: id 0 | task 63 | total time = 1339.08 ms / 116 tokens 0.43.652.675 I slot print_timing: id 0 | task 63 | graphs reused = 1 0.43.652.675 I slot print_timing: id 0 | task 63 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.652.697 I slot release: id 0 | task 63 | stop processing: n_tokens = 115, truncated = 0 0.43.652.788 I slot print_timing: id 1 | task 64 | prompt eval time = 1298.84 ms / 133 tokens ( 9.77 ms per token, 102.40 tokens per second) 0.43.652.789 I slot print_timing: id 1 | task 64 | eval time = 40.33 ms / 2 tokens ( 40.33 ms per token, 24.80 tokens per second) 0.43.652.789 I slot print_timing: id 1 | task 64 | total time = 1339.17 ms / 135 tokens 0.43.652.790 I slot print_timing: id 1 | task 64 | graphs reused = 1 0.43.652.790 I slot print_timing: id 1 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.652.803 I slot release: id 1 | task 64 | stop processing: n_tokens = 134, truncated = 0 0.43.652.895 I slot print_timing: id 2 | task 65 | prompt eval time = 1298.93 ms / 140 tokens ( 9.28 ms per token, 107.78 tokens per second) 0.43.652.897 I slot print_timing: id 2 | task 65 | eval time = 40.33 ms / 2 tokens ( 40.33 ms per token, 24.80 tokens per second) 0.43.652.897 I slot print_timing: id 2 | task 65 | total time = 1339.26 ms / 142 tokens 0.43.652.897 I slot print_timing: id 2 | task 65 | graphs reused = 1 0.43.652.897 I slot print_timing: id 2 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.652.906 I slot release: id 2 | task 65 | stop processing: n_tokens = 141, truncated = 0 0.43.652.999 I slot print_timing: id 3 | task 66 | prompt eval time = 1299.01 ms / 158 tokens ( 8.22 ms per token, 121.63 tokens per second) 0.43.653.001 I slot print_timing: id 3 | task 66 | eval time = 40.34 ms / 2 tokens ( 40.34 ms per token, 24.79 tokens per second) 0.43.653.001 I slot print_timing: id 3 | task 66 | total time = 1339.35 ms / 160 tokens 0.43.653.002 I slot print_timing: id 3 | task 66 | graphs reused = 1 0.43.653.002 I slot print_timing: id 3 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.653.013 I slot release: id 3 | task 66 | stop processing: n_tokens = 159, truncated = 0 0.43.658.338 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.235 0.43.659.002 I slot launch_slot_: id 0 | task 70 | processing task, is_child = 0 0.43.664.842 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.194 0.43.664.919 I slot launch_slot_: id 1 | task 71 | processing task, is_child = 0 0.43.664.976 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.263 (> 0.100 thold), f_keep = 0.184 0.43.665.036 I slot launch_slot_: id 2 | task 72 | processing task, is_child = 0 0.43.665.064 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.164 0.43.665.126 I slot launch_slot_: id 3 | task 73 | processing task, is_child = 0 0.44.962.958 I slot print_timing: id 0 | task 70 | prompt eval time = 1257.76 ms / 156 tokens ( 8.06 ms per token, 124.03 tokens per second) 0.44.962.960 I slot print_timing: id 0 | task 70 | eval time = 40.06 ms / 2 tokens ( 40.06 ms per token, 24.96 tokens per second) 0.44.962.960 I slot print_timing: id 0 | task 70 | total time = 1297.82 ms / 158 tokens 0.44.962.960 I slot print_timing: id 0 | task 70 | graphs reused = 1 0.44.962.961 I slot print_timing: id 0 | task 70 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.962.980 I slot release: id 0 | task 70 | stop processing: n_tokens = 157, truncated = 0 0.44.963.067 I slot print_timing: id 1 | task 71 | prompt eval time = 1257.83 ms / 148 tokens ( 8.50 ms per token, 117.66 tokens per second) 0.44.963.074 I slot print_timing: id 1 | task 71 | eval time = 40.08 ms / 2 tokens ( 40.08 ms per token, 24.95 tokens per second) 0.44.963.075 I slot print_timing: id 1 | task 71 | total time = 1297.91 ms / 150 tokens 0.44.963.075 I slot print_timing: id 1 | task 71 | graphs reused = 1 0.44.963.075 I slot print_timing: id 1 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.963.089 I slot release: id 1 | task 71 | stop processing: n_tokens = 149, truncated = 0 0.44.963.174 I slot print_timing: id 2 | task 72 | prompt eval time = 1257.91 ms / 99 tokens ( 12.71 ms per token, 78.70 tokens per second) 0.44.963.176 I slot print_timing: id 2 | task 72 | eval time = 40.09 ms / 2 tokens ( 40.09 ms per token, 24.94 tokens per second) 0.44.963.177 I slot print_timing: id 2 | task 72 | total time = 1298.00 ms / 101 tokens 0.44.963.177 I slot print_timing: id 2 | task 72 | graphs reused = 1 0.44.963.177 I slot print_timing: id 2 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.963.186 I slot release: id 2 | task 72 | stop processing: n_tokens = 100, truncated = 0 0.44.963.271 I slot print_timing: id 3 | task 73 | prompt eval time = 1257.98 ms / 119 tokens ( 10.57 ms per token, 94.60 tokens per second) 0.44.963.275 I slot print_timing: id 3 | task 73 | eval time = 40.09 ms / 2 tokens ( 40.09 ms per token, 24.94 tokens per second) 0.44.963.275 I slot print_timing: id 3 | task 73 | total time = 1298.08 ms / 121 tokens 0.44.963.276 I slot print_timing: id 3 | task 73 | graphs reused = 1 0.44.963.276 I slot print_timing: id 3 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.963.285 I slot release: id 3 | task 73 | stop processing: n_tokens = 120, truncated = 0 0.44.968.466 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.267 (> 0.100 thold), f_keep = 0.172 0.44.970.533 I slot launch_slot_: id 0 | task 77 | processing task, is_child = 0 0.44.974.589 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.174 0.44.974.660 I slot launch_slot_: id 1 | task 78 | processing task, is_child = 0 0.44.974.705 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.260 0.44.974.763 I slot launch_slot_: id 2 | task 79 | processing task, is_child = 0 0.44.974.787 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.217 0.44.974.845 I slot launch_slot_: id 3 | task 80 | processing task, is_child = 0 0.46.170.371 I slot print_timing: id 0 | task 77 | prompt eval time = 1155.06 ms / 101 tokens ( 11.44 ms per token, 87.44 tokens per second) 0.46.170.374 I slot print_timing: id 0 | task 77 | eval time = 40.45 ms / 2 tokens ( 40.45 ms per token, 24.72 tokens per second) 0.46.170.375 I slot print_timing: id 0 | task 77 | total time = 1195.51 ms / 103 tokens 0.46.170.375 I slot print_timing: id 0 | task 77 | graphs reused = 1 0.46.170.376 I slot print_timing: id 0 | task 77 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.170.393 I slot release: id 0 | task 77 | stop processing: n_tokens = 102, truncated = 0 0.46.170.480 I slot print_timing: id 1 | task 78 | prompt eval time = 1155.14 ms / 101 tokens ( 11.44 ms per token, 87.44 tokens per second) 0.46.170.482 I slot print_timing: id 1 | task 78 | eval time = 40.47 ms / 2 tokens ( 40.47 ms per token, 24.71 tokens per second) 0.46.170.482 I slot print_timing: id 1 | task 78 | total time = 1195.61 ms / 103 tokens 0.46.170.482 I slot print_timing: id 1 | task 78 | graphs reused = 1 0.46.170.483 I slot print_timing: id 1 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.170.493 I slot release: id 1 | task 78 | stop processing: n_tokens = 102, truncated = 0 0.46.170.582 I slot print_timing: id 2 | task 79 | prompt eval time = 1155.31 ms / 158 tokens ( 7.31 ms per token, 136.76 tokens per second) 0.46.170.585 I slot print_timing: id 2 | task 79 | eval time = 40.38 ms / 2 tokens ( 40.38 ms per token, 24.77 tokens per second) 0.46.170.586 I slot print_timing: id 2 | task 79 | total time = 1195.69 ms / 160 tokens 0.46.170.586 I slot print_timing: id 2 | task 79 | graphs reused = 1 0.46.170.586 I slot print_timing: id 2 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.170.596 I slot release: id 2 | task 79 | stop processing: n_tokens = 159, truncated = 0 0.46.170.680 I slot print_timing: id 3 | task 80 | prompt eval time = 1155.39 ms / 156 tokens ( 7.41 ms per token, 135.02 tokens per second) 0.46.170.681 I slot print_timing: id 3 | task 80 | eval time = 40.38 ms / 2 tokens ( 40.38 ms per token, 24.77 tokens per second) 0.46.170.682 I slot print_timing: id 3 | task 80 | total time = 1195.77 ms / 158 tokens 0.46.170.682 I slot print_timing: id 3 | task 80 | graphs reused = 1 0.46.170.682 I slot print_timing: id 3 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.170.691 I slot release: id 3 | task 80 | stop processing: n_tokens = 157, truncated = 0 0.46.176.212 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.255 0.46.177.176 I slot launch_slot_: id 0 | task 85 | processing task, is_child = 0 0.46.182.386 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.255 0.46.182.460 I slot launch_slot_: id 1 | task 86 | processing task, is_child = 0 0.46.182.514 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.164 0.46.182.579 I slot launch_slot_: id 2 | task 84 | processing task, is_child = 0 0.46.182.606 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.166 0.46.182.669 I slot launch_slot_: id 3 | task 87 | processing task, is_child = 0 0.47.265.486 I slot print_timing: id 0 | task 85 | prompt eval time = 1042.65 ms / 114 tokens ( 9.15 ms per token, 109.34 tokens per second) 0.47.265.489 I slot print_timing: id 0 | task 85 | eval time = 40.15 ms / 2 tokens ( 40.15 ms per token, 24.90 tokens per second) 0.47.265.489 I slot print_timing: id 0 | task 85 | total time = 1082.81 ms / 116 tokens 0.47.265.490 I slot print_timing: id 0 | task 85 | graphs reused = 1 0.47.265.490 I slot print_timing: id 0 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.265.511 I slot release: id 0 | task 85 | stop processing: n_tokens = 115, truncated = 0 0.47.265.598 I slot print_timing: id 1 | task 86 | prompt eval time = 1042.73 ms / 113 tokens ( 9.23 ms per token, 108.37 tokens per second) 0.47.265.598 I slot print_timing: id 1 | task 86 | eval time = 40.17 ms / 2 tokens ( 40.17 ms per token, 24.89 tokens per second) 0.47.265.599 I slot print_timing: id 1 | task 86 | total time = 1082.90 ms / 115 tokens 0.47.265.599 I slot print_timing: id 1 | task 86 | graphs reused = 1 0.47.265.599 I slot print_timing: id 1 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.265.609 I slot release: id 1 | task 86 | stop processing: n_tokens = 114, truncated = 0 0.47.265.693 I slot print_timing: id 2 | task 84 | prompt eval time = 1042.81 ms / 134 tokens ( 7.78 ms per token, 128.50 tokens per second) 0.47.265.695 I slot print_timing: id 2 | task 84 | eval time = 40.17 ms / 2 tokens ( 40.17 ms per token, 24.89 tokens per second) 0.47.265.695 I slot print_timing: id 2 | task 84 | total time = 1082.99 ms / 136 tokens 0.47.265.695 I slot print_timing: id 2 | task 84 | graphs reused = 1 0.47.265.696 I slot print_timing: id 2 | task 84 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.265.705 I slot release: id 2 | task 84 | stop processing: n_tokens = 135, truncated = 0 0.47.265.790 I slot print_timing: id 3 | task 87 | prompt eval time = 1042.90 ms / 124 tokens ( 8.41 ms per token, 118.90 tokens per second) 0.47.265.792 I slot print_timing: id 3 | task 87 | eval time = 40.16 ms / 2 tokens ( 40.16 ms per token, 24.90 tokens per second) 0.47.265.792 I slot print_timing: id 3 | task 87 | total time = 1083.06 ms / 126 tokens 0.47.265.793 I slot print_timing: id 3 | task 87 | graphs reused = 1 0.47.265.793 I slot print_timing: id 3 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.265.800 I slot release: id 3 | task 87 | stop processing: n_tokens = 125, truncated = 0 0.47.270.880 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.225 (> 0.100 thold), f_keep = 0.235 0.47.272.423 I slot launch_slot_: id 0 | task 91 | processing task, is_child = 0 0.47.277.068 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.228 0.47.277.135 I slot launch_slot_: id 1 | task 92 | processing task, is_child = 0 0.47.277.182 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.193 0.47.277.515 I slot launch_slot_: id 2 | task 93 | processing task, is_child = 0 0.47.277.540 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.208 0.47.277.597 I slot launch_slot_: id 3 | task 94 | processing task, is_child = 0 0.48.387.637 I slot print_timing: id 0 | task 91 | prompt eval time = 1069.68 ms / 120 tokens ( 8.91 ms per token, 112.18 tokens per second) 0.48.387.640 I slot print_timing: id 0 | task 91 | eval time = 40.35 ms / 2 tokens ( 40.35 ms per token, 24.78 tokens per second) 0.48.387.640 I slot print_timing: id 0 | task 91 | total time = 1110.03 ms / 122 tokens 0.48.387.641 I slot print_timing: id 0 | task 91 | graphs reused = 1 0.48.387.641 I slot print_timing: id 0 | task 91 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.387.663 I slot release: id 0 | task 91 | stop processing: n_tokens = 121, truncated = 0 0.48.387.753 I slot print_timing: id 1 | task 92 | prompt eval time = 1069.77 ms / 113 tokens ( 9.47 ms per token, 105.63 tokens per second) 0.48.387.754 I slot print_timing: id 1 | task 92 | eval time = 40.37 ms / 2 tokens ( 40.37 ms per token, 24.77 tokens per second) 0.48.387.755 I slot print_timing: id 1 | task 92 | total time = 1110.13 ms / 115 tokens 0.48.387.755 I slot print_timing: id 1 | task 92 | graphs reused = 1 0.48.387.755 I slot print_timing: id 1 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.387.767 I slot release: id 1 | task 92 | stop processing: n_tokens = 114, truncated = 0 0.48.387.859 I slot print_timing: id 2 | task 93 | prompt eval time = 1069.87 ms / 133 tokens ( 8.04 ms per token, 124.31 tokens per second) 0.48.387.860 I slot print_timing: id 2 | task 93 | eval time = 40.36 ms / 2 tokens ( 40.36 ms per token, 24.78 tokens per second) 0.48.387.861 I slot print_timing: id 2 | task 93 | total time = 1110.22 ms / 135 tokens 0.48.387.861 I slot print_timing: id 2 | task 93 | graphs reused = 1 0.48.387.861 I slot print_timing: id 2 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.387.872 I slot release: id 2 | task 93 | stop processing: n_tokens = 134, truncated = 0 0.48.387.958 I slot print_timing: id 3 | task 94 | prompt eval time = 1069.95 ms / 133 tokens ( 8.04 ms per token, 124.30 tokens per second) 0.48.387.961 I slot print_timing: id 3 | task 94 | eval time = 40.36 ms / 2 tokens ( 40.36 ms per token, 24.78 tokens per second) 0.48.387.961 I slot print_timing: id 3 | task 94 | total time = 1110.31 ms / 135 tokens 0.48.387.962 I slot print_timing: id 3 | task 94 | graphs reused = 1 0.48.387.962 I slot print_timing: id 3 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.387.972 I slot release: id 3 | task 94 | stop processing: n_tokens = 134, truncated = 0 0.48.393.036 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.223 0.48.394.243 I slot launch_slot_: id 0 | task 100 | processing task, is_child = 0 0.48.398.534 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.201 0.48.398.606 I slot launch_slot_: id 3 | task 99 | processing task, is_child = 0 0.48.398.658 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.228 0.48.398.720 I slot launch_slot_: id 1 | task 98 | processing task, is_child = 0 0.48.398.745 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.201 0.48.398.804 I slot launch_slot_: id 2 | task 101 | processing task, is_child = 0 0.49.710.991 I slot print_timing: id 0 | task 100 | prompt eval time = 1271.82 ms / 99 tokens ( 12.85 ms per token, 77.84 tokens per second) 0.49.710.993 I slot print_timing: id 0 | task 100 | eval time = 40.35 ms / 2 tokens ( 40.35 ms per token, 24.78 tokens per second) 0.49.710.994 I slot print_timing: id 0 | task 100 | total time = 1312.18 ms / 101 tokens 0.49.710.994 I slot print_timing: id 0 | task 100 | graphs reused = 1 0.49.710.994 I slot print_timing: id 0 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.711.011 I slot release: id 0 | task 100 | stop processing: n_tokens = 100, truncated = 0 0.49.711.101 I slot print_timing: id 1 | task 98 | prompt eval time = 1271.90 ms / 113 tokens ( 11.26 ms per token, 88.84 tokens per second) 0.49.711.102 I slot print_timing: id 1 | task 98 | eval time = 40.37 ms / 2 tokens ( 40.37 ms per token, 24.77 tokens per second) 0.49.711.103 I slot print_timing: id 1 | task 98 | total time = 1312.27 ms / 115 tokens 0.49.711.103 I slot print_timing: id 1 | task 98 | graphs reused = 1 0.49.711.103 I slot print_timing: id 1 | task 98 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.711.113 I slot release: id 1 | task 98 | stop processing: n_tokens = 114, truncated = 0 0.49.711.203 I slot print_timing: id 2 | task 101 | prompt eval time = 1271.98 ms / 162 tokens ( 7.85 ms per token, 127.36 tokens per second) 0.49.711.206 I slot print_timing: id 2 | task 101 | eval time = 40.37 ms / 2 tokens ( 40.37 ms per token, 24.77 tokens per second) 0.49.711.206 I slot print_timing: id 2 | task 101 | total time = 1312.36 ms / 164 tokens 0.49.711.206 I slot print_timing: id 2 | task 101 | graphs reused = 1 0.49.711.207 I slot print_timing: id 2 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.711.216 I slot release: id 2 | task 101 | stop processing: n_tokens = 163, truncated = 0 0.49.711.307 I slot print_timing: id 3 | task 99 | prompt eval time = 1272.06 ms / 110 tokens ( 11.56 ms per token, 86.47 tokens per second) 0.49.711.309 I slot print_timing: id 3 | task 99 | eval time = 40.38 ms / 2 tokens ( 40.38 ms per token, 24.77 tokens per second) 0.49.711.310 I slot print_timing: id 3 | task 99 | total time = 1312.44 ms / 112 tokens 0.49.711.310 I slot print_timing: id 3 | task 99 | graphs reused = 1 0.49.711.310 I slot print_timing: id 3 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.711.317 I slot release: id 3 | task 99 | stop processing: n_tokens = 111, truncated = 0 0.49.716.648 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.270 0.49.717.228 I slot launch_slot_: id 0 | task 105 | processing task, is_child = 0 0.49.722.165 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.243 0.49.722.231 I slot launch_slot_: id 3 | task 106 | processing task, is_child = 0 0.49.722.283 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.228 0.49.722.344 I slot launch_slot_: id 1 | task 107 | processing task, is_child = 0 0.49.722.372 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.160 0.49.722.433 I slot launch_slot_: id 2 | task 108 | processing task, is_child = 0 0.51.397.789 I slot print_timing: id 0 | task 105 | prompt eval time = 1635.11 ms / 107 tokens ( 15.28 ms per token, 65.44 tokens per second) 0.51.397.792 I slot print_timing: id 0 | task 105 | eval time = 40.23 ms / 2 tokens ( 40.23 ms per token, 24.85 tokens per second) 0.51.397.793 I slot print_timing: id 0 | task 105 | total time = 1675.35 ms / 109 tokens 0.51.397.794 I slot print_timing: id 0 | task 105 | graphs reused = 1 0.51.397.794 I slot print_timing: id 0 | task 105 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.397.814 I slot release: id 0 | task 105 | stop processing: n_tokens = 108, truncated = 0 0.51.397.907 I slot print_timing: id 1 | task 107 | prompt eval time = 1635.19 ms / 165 tokens ( 9.91 ms per token, 100.91 tokens per second) 0.51.397.909 I slot print_timing: id 1 | task 107 | eval time = 40.26 ms / 2 tokens ( 40.26 ms per token, 24.84 tokens per second) 0.51.397.909 I slot print_timing: id 1 | task 107 | total time = 1675.45 ms / 167 tokens 0.51.397.910 I slot print_timing: id 1 | task 107 | graphs reused = 1 0.51.397.910 I slot print_timing: id 1 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.397.924 I slot release: id 1 | task 107 | stop processing: n_tokens = 166, truncated = 0 0.51.398.023 I slot print_timing: id 2 | task 108 | prompt eval time = 1635.28 ms / 214 tokens ( 7.64 ms per token, 130.86 tokens per second) 0.51.398.025 I slot print_timing: id 2 | task 108 | eval time = 40.27 ms / 2 tokens ( 40.27 ms per token, 24.83 tokens per second) 0.51.398.026 I slot print_timing: id 2 | task 108 | total time = 1675.54 ms / 216 tokens 0.51.398.026 I slot print_timing: id 2 | task 108 | graphs reused = 1 0.51.398.026 I slot print_timing: id 2 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.398.040 I slot release: id 2 | task 108 | stop processing: n_tokens = 215, truncated = 0 0.51.398.135 I slot print_timing: id 3 | task 106 | prompt eval time = 1635.36 ms / 127 tokens ( 12.88 ms per token, 77.66 tokens per second) 0.51.398.137 I slot print_timing: id 3 | task 106 | eval time = 40.27 ms / 2 tokens ( 40.27 ms per token, 24.83 tokens per second) 0.51.398.138 I slot print_timing: id 3 | task 106 | total time = 1675.63 ms / 129 tokens 0.51.398.138 I slot print_timing: id 3 | task 106 | graphs reused = 1 0.51.398.138 I slot print_timing: id 3 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.398.147 I slot release: id 3 | task 106 | stop processing: n_tokens = 128, truncated = 0 0.51.403.108 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.269 0.51.403.727 I slot launch_slot_: id 0 | task 112 | processing task, is_child = 0 0.51.410.829 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.157 0.51.410.905 I slot launch_slot_: id 1 | task 113 | processing task, is_child = 0 0.51.410.959 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.211 0.51.411.306 I slot launch_slot_: id 3 | task 114 | processing task, is_child = 0 0.51.411.336 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.121 0.51.411.399 I slot launch_slot_: id 2 | task 115 | processing task, is_child = 0 0.52.929.137 I slot print_timing: id 0 | task 112 | prompt eval time = 1477.33 ms / 133 tokens ( 11.11 ms per token, 90.03 tokens per second) 0.52.929.140 I slot print_timing: id 0 | task 112 | eval time = 40.40 ms / 2 tokens ( 40.40 ms per token, 24.75 tokens per second) 0.52.929.140 I slot print_timing: id 0 | task 112 | total time = 1517.73 ms / 135 tokens 0.52.929.140 I slot print_timing: id 0 | task 112 | graphs reused = 1 0.52.929.141 I slot print_timing: id 0 | task 112 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.929.158 I slot release: id 0 | task 112 | stop processing: n_tokens = 134, truncated = 0 0.52.929.246 I slot print_timing: id 1 | task 113 | prompt eval time = 1477.43 ms / 148 tokens ( 9.98 ms per token, 100.17 tokens per second) 0.52.929.248 I slot print_timing: id 1 | task 113 | eval time = 40.39 ms / 2 tokens ( 40.39 ms per token, 24.76 tokens per second) 0.52.929.249 I slot print_timing: id 1 | task 113 | total time = 1517.83 ms / 150 tokens 0.52.929.249 I slot print_timing: id 1 | task 113 | graphs reused = 1 0.52.929.249 I slot print_timing: id 1 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.929.260 I slot release: id 1 | task 113 | stop processing: n_tokens = 149, truncated = 0 0.52.929.352 I slot print_timing: id 2 | task 115 | prompt eval time = 1477.53 ms / 213 tokens ( 6.94 ms per token, 144.16 tokens per second) 0.52.929.355 I slot print_timing: id 2 | task 115 | eval time = 40.37 ms / 2 tokens ( 40.37 ms per token, 24.77 tokens per second) 0.52.929.355 I slot print_timing: id 2 | task 115 | total time = 1517.91 ms / 215 tokens 0.52.929.355 I slot print_timing: id 2 | task 115 | graphs reused = 1 0.52.929.356 I slot print_timing: id 2 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.929.372 I slot release: id 2 | task 115 | stop processing: n_tokens = 214, truncated = 0 0.52.929.455 I slot print_timing: id 3 | task 114 | prompt eval time = 1477.63 ms / 148 tokens ( 9.98 ms per token, 100.16 tokens per second) 0.52.929.457 I slot print_timing: id 3 | task 114 | eval time = 40.35 ms / 2 tokens ( 40.35 ms per token, 24.78 tokens per second) 0.52.929.457 I slot print_timing: id 3 | task 114 | total time = 1517.98 ms / 150 tokens 0.52.929.458 I slot print_timing: id 3 | task 114 | graphs reused = 1 0.52.929.458 I slot print_timing: id 3 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.929.470 I slot release: id 3 | task 114 | stop processing: n_tokens = 149, truncated = 0 0.52.934.853 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.299 (> 0.100 thold), f_keep = 0.216 0.52.936.922 I slot launch_slot_: id 0 | task 119 | processing task, is_child = 0 0.52.944.212 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.174 0.52.944.288 I slot launch_slot_: id 1 | task 120 | processing task, is_child = 0 0.52.944.348 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.260 (> 0.100 thold), f_keep = 0.181 0.52.944.422 I slot launch_slot_: id 3 | task 121 | processing task, is_child = 0 0.52.944.454 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.148 (> 0.100 thold), f_keep = 0.121 0.52.944.825 I slot launch_slot_: id 2 | task 122 | processing task, is_child = 0 0.54.382.353 I slot print_timing: id 0 | task 119 | prompt eval time = 1397.20 ms / 97 tokens ( 14.40 ms per token, 69.42 tokens per second) 0.54.382.355 I slot print_timing: id 0 | task 119 | eval time = 40.32 ms / 2 tokens ( 40.32 ms per token, 24.80 tokens per second) 0.54.382.355 I slot print_timing: id 0 | task 119 | total time = 1437.52 ms / 99 tokens 0.54.382.355 I slot print_timing: id 0 | task 119 | graphs reused = 1 0.54.382.356 I slot print_timing: id 0 | task 119 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.382.372 I slot release: id 0 | task 119 | stop processing: n_tokens = 98, truncated = 0 0.54.382.468 I slot print_timing: id 1 | task 120 | prompt eval time = 1397.30 ms / 132 tokens ( 10.59 ms per token, 94.47 tokens per second) 0.54.382.470 I slot print_timing: id 1 | task 120 | eval time = 40.31 ms / 2 tokens ( 40.31 ms per token, 24.81 tokens per second) 0.54.382.470 I slot print_timing: id 1 | task 120 | total time = 1437.61 ms / 134 tokens 0.54.382.470 I slot print_timing: id 1 | task 120 | graphs reused = 1 0.54.382.471 I slot print_timing: id 1 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.382.483 I slot release: id 1 | task 120 | stop processing: n_tokens = 133, truncated = 0 0.54.382.586 I slot print_timing: id 2 | task 122 | prompt eval time = 1397.40 ms / 176 tokens ( 7.94 ms per token, 125.95 tokens per second) 0.54.382.591 I slot print_timing: id 2 | task 122 | eval time = 40.31 ms / 2 tokens ( 40.31 ms per token, 24.81 tokens per second) 0.54.382.591 I slot print_timing: id 2 | task 122 | total time = 1437.71 ms / 178 tokens 0.54.382.592 I slot print_timing: id 2 | task 122 | graphs reused = 1 0.54.382.592 I slot print_timing: id 2 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.382.602 I slot release: id 2 | task 122 | stop processing: n_tokens = 177, truncated = 0 0.54.382.719 I slot print_timing: id 3 | task 121 | prompt eval time = 1397.51 ms / 104 tokens ( 13.44 ms per token, 74.42 tokens per second) 0.54.382.720 I slot print_timing: id 3 | task 121 | eval time = 40.31 ms / 2 tokens ( 40.31 ms per token, 24.81 tokens per second) 0.54.382.720 I slot print_timing: id 3 | task 121 | total time = 1437.82 ms / 106 tokens 0.54.382.720 I slot print_timing: id 3 | task 121 | graphs reused = 1 0.54.382.720 I slot print_timing: id 3 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.382.727 I slot release: id 3 | task 121 | stop processing: n_tokens = 105, truncated = 0 0.54.387.917 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.276 0.54.388.562 I slot launch_slot_: id 0 | task 126 | processing task, is_child = 0 0.54.393.455 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.270 (> 0.100 thold), f_keep = 0.257 0.54.393.525 I slot launch_slot_: id 3 | task 127 | processing task, is_child = 0 0.54.393.581 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.205 (> 0.100 thold), f_keep = 0.195 0.54.393.642 I slot launch_slot_: id 1 | task 128 | processing task, is_child = 0 0.54.393.670 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.159 (> 0.100 thold), f_keep = 0.147 0.54.393.738 I slot launch_slot_: id 2 | task 129 | processing task, is_child = 0 0.55.798.831 I slot print_timing: id 0 | task 126 | prompt eval time = 1364.67 ms / 110 tokens ( 12.41 ms per token, 80.61 tokens per second) 0.55.798.834 I slot print_timing: id 0 | task 126 | eval time = 40.41 ms / 2 tokens ( 40.41 ms per token, 24.74 tokens per second) 0.55.798.835 I slot print_timing: id 0 | task 126 | total time = 1405.09 ms / 112 tokens 0.55.798.835 I slot print_timing: id 0 | task 126 | graphs reused = 1 0.55.798.836 I slot print_timing: id 0 | task 126 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.798.857 I slot release: id 0 | task 126 | stop processing: n_tokens = 111, truncated = 0 0.55.798.946 I slot print_timing: id 1 | task 128 | prompt eval time = 1364.78 ms / 127 tokens ( 10.75 ms per token, 93.06 tokens per second) 0.55.798.949 I slot print_timing: id 1 | task 128 | eval time = 40.41 ms / 2 tokens ( 40.41 ms per token, 24.75 tokens per second) 0.55.798.949 I slot print_timing: id 1 | task 128 | total time = 1405.18 ms / 129 tokens 0.55.798.949 I slot print_timing: id 1 | task 128 | graphs reused = 1 0.55.798.950 I slot print_timing: id 1 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.798.961 I slot release: id 1 | task 128 | stop processing: n_tokens = 128, truncated = 0 0.55.799.057 I slot print_timing: id 2 | task 129 | prompt eval time = 1364.88 ms / 164 tokens ( 8.32 ms per token, 120.16 tokens per second) 0.55.799.060 I slot print_timing: id 2 | task 129 | eval time = 40.40 ms / 2 tokens ( 40.40 ms per token, 24.75 tokens per second) 0.55.799.061 I slot print_timing: id 2 | task 129 | total time = 1405.28 ms / 166 tokens 0.55.799.061 I slot print_timing: id 2 | task 129 | graphs reused = 1 0.55.799.061 I slot print_timing: id 2 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.799.075 I slot release: id 2 | task 129 | stop processing: n_tokens = 165, truncated = 0 0.55.799.162 I slot print_timing: id 3 | task 127 | prompt eval time = 1364.99 ms / 100 tokens ( 13.65 ms per token, 73.26 tokens per second) 0.55.799.164 I slot print_timing: id 3 | task 127 | eval time = 40.37 ms / 2 tokens ( 40.37 ms per token, 24.77 tokens per second) 0.55.799.164 I slot print_timing: id 3 | task 127 | total time = 1405.36 ms / 102 tokens 0.55.799.165 I slot print_timing: id 3 | task 127 | graphs reused = 1 0.55.799.165 I slot print_timing: id 3 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.799.173 I slot release: id 3 | task 127 | stop processing: n_tokens = 101, truncated = 0 0.55.804.981 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.234 0.55.806.637 I slot launch_slot_: id 0 | task 133 | processing task, is_child = 0 0.55.812.342 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.267 0.55.812.677 I slot launch_slot_: id 3 | task 134 | processing task, is_child = 0 0.55.812.732 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.203 0.55.812.794 I slot launch_slot_: id 1 | task 135 | processing task, is_child = 0 0.55.812.821 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.158 0.55.812.885 I slot launch_slot_: id 2 | task 136 | processing task, is_child = 0 0.57.048.615 I slot print_timing: id 0 | task 133 | prompt eval time = 1195.17 ms / 124 tokens ( 9.64 ms per token, 103.75 tokens per second) 0.57.048.617 I slot print_timing: id 0 | task 133 | eval time = 40.55 ms / 2 tokens ( 40.55 ms per token, 24.66 tokens per second) 0.57.048.617 I slot print_timing: id 0 | task 133 | total time = 1235.72 ms / 126 tokens 0.57.048.618 I slot print_timing: id 0 | task 133 | graphs reused = 1 0.57.048.618 I slot print_timing: id 0 | task 133 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.048.635 I slot release: id 0 | task 133 | stop processing: n_tokens = 125, truncated = 0 0.57.048.721 I slot print_timing: id 1 | task 135 | prompt eval time = 1195.28 ms / 124 tokens ( 9.64 ms per token, 103.74 tokens per second) 0.57.048.723 I slot print_timing: id 1 | task 135 | eval time = 40.54 ms / 2 tokens ( 40.54 ms per token, 24.67 tokens per second) 0.57.048.723 I slot print_timing: id 1 | task 135 | total time = 1235.81 ms / 126 tokens 0.57.048.724 I slot print_timing: id 1 | task 135 | graphs reused = 1 0.57.048.724 I slot print_timing: id 1 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.048.735 I slot release: id 1 | task 135 | stop processing: n_tokens = 125, truncated = 0 0.57.048.826 I slot print_timing: id 2 | task 136 | prompt eval time = 1195.39 ms / 151 tokens ( 7.92 ms per token, 126.32 tokens per second) 0.57.048.831 I slot print_timing: id 2 | task 136 | eval time = 40.51 ms / 2 tokens ( 40.51 ms per token, 24.69 tokens per second) 0.57.048.831 I slot print_timing: id 2 | task 136 | total time = 1235.90 ms / 153 tokens 0.57.048.832 I slot print_timing: id 2 | task 136 | graphs reused = 1 0.57.048.832 I slot print_timing: id 2 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.048.841 I slot release: id 2 | task 136 | stop processing: n_tokens = 152, truncated = 0 0.57.048.935 I slot print_timing: id 3 | task 134 | prompt eval time = 1195.49 ms / 111 tokens ( 10.77 ms per token, 92.85 tokens per second) 0.57.048.937 I slot print_timing: id 3 | task 134 | eval time = 40.49 ms / 2 tokens ( 40.49 ms per token, 24.70 tokens per second) 0.57.048.937 I slot print_timing: id 3 | task 134 | total time = 1235.98 ms / 113 tokens 0.57.048.938 I slot print_timing: id 3 | task 134 | graphs reused = 1 0.57.048.938 I slot print_timing: id 3 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.048.948 I slot release: id 3 | task 134 | stop processing: n_tokens = 112, truncated = 0 0.57.054.256 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.208 0.57.055.426 I slot launch_slot_: id 0 | task 140 | processing task, is_child = 0 0.57.060.936 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.208 0.57.061.003 I slot launch_slot_: id 1 | task 141 | processing task, is_child = 0 0.57.061.055 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.161 (> 0.100 thold), f_keep = 0.171 0.57.061.119 I slot launch_slot_: id 2 | task 142 | processing task, is_child = 0 0.57.061.143 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.232 0.57.061.200 I slot launch_slot_: id 3 | task 143 | processing task, is_child = 0 0.58.442.495 I slot print_timing: id 0 | task 140 | prompt eval time = 1340.68 ms / 117 tokens ( 11.46 ms per token, 87.27 tokens per second) 0.58.442.497 I slot print_timing: id 0 | task 140 | eval time = 40.61 ms / 2 tokens ( 40.61 ms per token, 24.63 tokens per second) 0.58.442.498 I slot print_timing: id 0 | task 140 | total time = 1381.29 ms / 119 tokens 0.58.442.498 I slot print_timing: id 0 | task 140 | graphs reused = 1 0.58.442.499 I slot print_timing: id 0 | task 140 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.442.523 I slot release: id 0 | task 140 | stop processing: n_tokens = 118, truncated = 0 0.58.442.610 I slot print_timing: id 1 | task 141 | prompt eval time = 1340.78 ms / 167 tokens ( 8.03 ms per token, 124.55 tokens per second) 0.58.442.612 I slot print_timing: id 1 | task 141 | eval time = 40.60 ms / 2 tokens ( 40.60 ms per token, 24.63 tokens per second) 0.58.442.612 I slot print_timing: id 1 | task 141 | total time = 1381.38 ms / 169 tokens 0.58.442.613 I slot print_timing: id 1 | task 141 | graphs reused = 1 0.58.442.613 I slot print_timing: id 1 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.442.626 I slot release: id 1 | task 141 | stop processing: n_tokens = 168, truncated = 0 0.58.442.712 I slot print_timing: id 2 | task 142 | prompt eval time = 1340.88 ms / 161 tokens ( 8.33 ms per token, 120.07 tokens per second) 0.58.442.715 I slot print_timing: id 2 | task 142 | eval time = 40.58 ms / 2 tokens ( 40.58 ms per token, 24.64 tokens per second) 0.58.442.715 I slot print_timing: id 2 | task 142 | total time = 1381.46 ms / 163 tokens 0.58.442.716 I slot print_timing: id 2 | task 142 | graphs reused = 1 0.58.442.716 I slot print_timing: id 2 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.442.725 I slot release: id 2 | task 142 | stop processing: n_tokens = 162, truncated = 0 0.58.442.805 I slot print_timing: id 3 | task 143 | prompt eval time = 1340.99 ms / 171 tokens ( 7.84 ms per token, 127.52 tokens per second) 0.58.442.807 I slot print_timing: id 3 | task 143 | eval time = 40.54 ms / 2 tokens ( 40.54 ms per token, 24.67 tokens per second) 0.58.442.808 I slot print_timing: id 3 | task 143 | total time = 1381.53 ms / 173 tokens 0.58.442.808 I slot print_timing: id 3 | task 143 | graphs reused = 1 0.58.442.808 I slot print_timing: id 3 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.442.825 I slot release: id 3 | task 143 | stop processing: n_tokens = 172, truncated = 0 0.58.448.177 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.241 (> 0.100 thold), f_keep = 0.220 0.58.449.609 I slot launch_slot_: id 0 | task 147 | processing task, is_child = 0 0.58.457.620 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.155 0.58.457.694 I slot launch_slot_: id 1 | task 148 | processing task, is_child = 0 0.58.457.750 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.160 0.58.458.098 I slot launch_slot_: id 2 | task 149 | processing task, is_child = 0 0.58.458.127 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.151 0.58.458.476 I slot launch_slot_: id 3 | task 150 | processing task, is_child = 0 0.59.413.397 I slot print_timing: id 0 | task 147 | prompt eval time = 910.44 ms / 108 tokens ( 8.43 ms per token, 118.62 tokens per second) 0.59.413.401 I slot print_timing: id 0 | task 147 | eval time = 44.47 ms / 2 tokens ( 44.47 ms per token, 22.49 tokens per second) 0.59.413.403 I slot print_timing: id 0 | task 147 | total time = 954.90 ms / 110 tokens 0.59.413.403 I slot print_timing: id 0 | task 147 | graphs reused = 1 0.59.413.404 I slot print_timing: id 0 | task 147 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.413.434 I slot release: id 0 | task 147 | stop processing: n_tokens = 109, truncated = 0 0.59.413.613 I slot print_timing: id 1 | task 148 | prompt eval time = 910.67 ms / 115 tokens ( 7.92 ms per token, 126.28 tokens per second) 0.59.413.617 I slot print_timing: id 1 | task 148 | eval time = 44.44 ms / 2 tokens ( 44.44 ms per token, 22.50 tokens per second) 0.59.413.618 I slot print_timing: id 1 | task 148 | total time = 955.11 ms / 117 tokens 0.59.413.618 I slot print_timing: id 1 | task 148 | graphs reused = 1 0.59.413.619 I slot print_timing: id 1 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.413.641 I slot release: id 1 | task 148 | stop processing: n_tokens = 116, truncated = 0 0.59.413.816 I slot print_timing: id 2 | task 149 | prompt eval time = 910.90 ms / 106 tokens ( 8.59 ms per token, 116.37 tokens per second) 0.59.413.822 I slot print_timing: id 2 | task 149 | eval time = 44.40 ms / 2 tokens ( 44.40 ms per token, 22.52 tokens per second) 0.59.413.823 I slot print_timing: id 2 | task 149 | total time = 955.29 ms / 108 tokens 0.59.413.824 I slot print_timing: id 2 | task 149 | graphs reused = 1 0.59.413.824 I slot print_timing: id 2 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.413.841 I slot release: id 2 | task 149 | stop processing: n_tokens = 107, truncated = 0 0.59.414.014 I slot print_timing: id 3 | task 150 | prompt eval time = 911.14 ms / 110 tokens ( 8.28 ms per token, 120.73 tokens per second) 0.59.414.017 I slot print_timing: id 3 | task 150 | eval time = 44.34 ms / 2 tokens ( 44.34 ms per token, 22.56 tokens per second) 0.59.414.017 I slot print_timing: id 3 | task 150 | total time = 955.48 ms / 112 tokens 0.59.414.018 I slot print_timing: id 3 | task 150 | graphs reused = 1 0.59.414.018 I slot print_timing: id 3 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.414.033 I slot release: id 3 | task 150 | stop processing: n_tokens = 111, truncated = 0 0.59.422.803 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.280 0.59.423.706 I slot launch_slot_: id 2 | task 154 | processing task, is_child = 0 0.59.429.481 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.239 0.59.429.956 I slot launch_slot_: id 0 | task 155 | processing task, is_child = 0 0.59.430.035 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.224 0.59.430.135 I slot launch_slot_: id 1 | task 156 | processing task, is_child = 0 0.59.430.176 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.234 0.59.430.277 I slot launch_slot_: id 3 | task 157 | processing task, is_child = 0 1.00.484.099 I slot print_timing: id 0 | task 155 | prompt eval time = 1012.54 ms / 119 tokens ( 8.51 ms per token, 117.53 tokens per second) 1.00.484.101 I slot print_timing: id 0 | task 155 | eval time = 41.27 ms / 2 tokens ( 41.27 ms per token, 24.23 tokens per second) 1.00.484.102 I slot print_timing: id 0 | task 155 | total time = 1053.81 ms / 121 tokens 1.00.484.102 I slot print_timing: id 0 | task 155 | graphs reused = 1 1.00.484.103 I slot print_timing: id 0 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.484.122 I slot release: id 0 | task 155 | stop processing: n_tokens = 120, truncated = 0 1.00.484.219 I slot print_timing: id 1 | task 156 | prompt eval time = 1012.63 ms / 123 tokens ( 8.23 ms per token, 121.47 tokens per second) 1.00.484.221 I slot print_timing: id 1 | task 156 | eval time = 41.28 ms / 2 tokens ( 41.28 ms per token, 24.22 tokens per second) 1.00.484.221 I slot print_timing: id 1 | task 156 | total time = 1053.91 ms / 125 tokens 1.00.484.222 I slot print_timing: id 1 | task 156 | graphs reused = 1 1.00.484.222 I slot print_timing: id 1 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.484.231 I slot release: id 1 | task 156 | stop processing: n_tokens = 124, truncated = 0 1.00.484.333 I slot print_timing: id 2 | task 154 | prompt eval time = 1012.72 ms / 120 tokens ( 8.44 ms per token, 118.49 tokens per second) 1.00.484.335 I slot print_timing: id 2 | task 154 | eval time = 41.28 ms / 2 tokens ( 41.28 ms per token, 24.23 tokens per second) 1.00.484.335 I slot print_timing: id 2 | task 154 | total time = 1054.00 ms / 122 tokens 1.00.484.335 I slot print_timing: id 2 | task 154 | graphs reused = 1 1.00.484.336 I slot print_timing: id 2 | task 154 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.484.343 I slot release: id 2 | task 154 | stop processing: n_tokens = 121, truncated = 0 1.00.484.451 I slot print_timing: id 3 | task 157 | prompt eval time = 1012.81 ms / 133 tokens ( 7.62 ms per token, 131.32 tokens per second) 1.00.484.455 I slot print_timing: id 3 | task 157 | eval time = 41.27 ms / 2 tokens ( 41.27 ms per token, 24.23 tokens per second) 1.00.484.456 I slot print_timing: id 3 | task 157 | total time = 1054.08 ms / 135 tokens 1.00.484.456 I slot print_timing: id 3 | task 157 | graphs reused = 1 1.00.484.456 I slot print_timing: id 3 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.484.464 I slot release: id 3 | task 157 | stop processing: n_tokens = 134, truncated = 0 1.00.489.709 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.284 (> 0.100 thold), f_keep = 0.223 1.00.491.556 I slot launch_slot_: id 2 | task 161 | processing task, is_child = 0 1.00.496.909 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.217 1.00.496.978 I slot launch_slot_: id 0 | task 162 | processing task, is_child = 0 1.00.497.029 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.210 1.00.497.089 I slot launch_slot_: id 1 | task 163 | processing task, is_child = 0 1.00.497.114 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.194 1.00.497.190 I slot launch_slot_: id 3 | task 164 | processing task, is_child = 0 1.01.793.265 I slot print_timing: id 0 | task 162 | prompt eval time = 1255.46 ms / 114 tokens ( 11.01 ms per token, 90.80 tokens per second) 1.01.793.270 I slot print_timing: id 0 | task 162 | eval time = 40.60 ms / 2 tokens ( 40.60 ms per token, 24.63 tokens per second) 1.01.793.271 I slot print_timing: id 0 | task 162 | total time = 1296.06 ms / 116 tokens 1.01.793.271 I slot print_timing: id 0 | task 162 | graphs reused = 1 1.01.793.272 I slot print_timing: id 0 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.793.289 I slot release: id 0 | task 162 | stop processing: n_tokens = 115, truncated = 0 1.01.793.376 I slot print_timing: id 1 | task 163 | prompt eval time = 1255.57 ms / 121 tokens ( 10.38 ms per token, 96.37 tokens per second) 1.01.793.378 I slot print_timing: id 1 | task 163 | eval time = 40.59 ms / 2 tokens ( 40.59 ms per token, 24.64 tokens per second) 1.01.793.378 I slot print_timing: id 1 | task 163 | total time = 1296.16 ms / 123 tokens 1.01.793.378 I slot print_timing: id 1 | task 163 | graphs reused = 1 1.01.793.379 I slot print_timing: id 1 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.793.388 I slot release: id 1 | task 163 | stop processing: n_tokens = 122, truncated = 0 1.01.793.478 I slot print_timing: id 2 | task 161 | prompt eval time = 1255.67 ms / 95 tokens ( 13.22 ms per token, 75.66 tokens per second) 1.01.793.480 I slot print_timing: id 2 | task 161 | eval time = 40.57 ms / 2 tokens ( 40.57 ms per token, 24.65 tokens per second) 1.01.793.480 I slot print_timing: id 2 | task 161 | total time = 1296.24 ms / 97 tokens 1.01.793.480 I slot print_timing: id 2 | task 161 | graphs reused = 1 1.01.793.481 I slot print_timing: id 2 | task 161 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.793.488 I slot release: id 2 | task 161 | stop processing: n_tokens = 96, truncated = 0 1.01.793.581 I slot print_timing: id 3 | task 164 | prompt eval time = 1255.78 ms / 145 tokens ( 8.66 ms per token, 115.47 tokens per second) 1.01.793.584 I slot print_timing: id 3 | task 164 | eval time = 40.55 ms / 2 tokens ( 40.55 ms per token, 24.66 tokens per second) 1.01.793.584 I slot print_timing: id 3 | task 164 | total time = 1296.33 ms / 147 tokens 1.01.793.584 I slot print_timing: id 3 | task 164 | graphs reused = 1 1.01.793.584 I slot print_timing: id 3 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.793.597 I slot release: id 3 | task 164 | stop processing: n_tokens = 146, truncated = 0 1.01.798.875 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.281 1.01.799.612 I slot launch_slot_: id 2 | task 168 | processing task, is_child = 0 1.01.804.663 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.226 1.01.805.012 I slot launch_slot_: id 0 | task 169 | processing task, is_child = 0 1.01.805.063 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.213 1.01.805.122 I slot launch_slot_: id 1 | task 170 | processing task, is_child = 0 1.01.805.148 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.178 1.01.805.207 I slot launch_slot_: id 3 | task 171 | processing task, is_child = 0 1.03.232.177 I slot print_timing: id 0 | task 169 | prompt eval time = 1386.30 ms / 130 tokens ( 10.66 ms per token, 93.77 tokens per second) 1.03.232.179 I slot print_timing: id 0 | task 169 | eval time = 40.66 ms / 2 tokens ( 40.66 ms per token, 24.59 tokens per second) 1.03.232.180 I slot print_timing: id 0 | task 169 | total time = 1426.96 ms / 132 tokens 1.03.232.180 I slot print_timing: id 0 | task 169 | graphs reused = 1 1.03.232.181 I slot print_timing: id 0 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.232.200 I slot release: id 0 | task 169 | stop processing: n_tokens = 131, truncated = 0 1.03.232.289 I slot print_timing: id 1 | task 170 | prompt eval time = 1386.42 ms / 146 tokens ( 9.50 ms per token, 105.31 tokens per second) 1.03.232.292 I slot print_timing: id 1 | task 170 | eval time = 40.65 ms / 2 tokens ( 40.65 ms per token, 24.60 tokens per second) 1.03.232.292 I slot print_timing: id 1 | task 170 | total time = 1427.06 ms / 148 tokens 1.03.232.293 I slot print_timing: id 1 | task 170 | graphs reused = 1 1.03.232.293 I slot print_timing: id 1 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.232.307 I slot release: id 1 | task 170 | stop processing: n_tokens = 147, truncated = 0 1.03.232.394 I slot print_timing: id 2 | task 168 | prompt eval time = 1386.52 ms / 102 tokens ( 13.59 ms per token, 73.57 tokens per second) 1.03.232.396 I slot print_timing: id 2 | task 168 | eval time = 40.63 ms / 2 tokens ( 40.63 ms per token, 24.61 tokens per second) 1.03.232.396 I slot print_timing: id 2 | task 168 | total time = 1427.15 ms / 104 tokens 1.03.232.396 I slot print_timing: id 2 | task 168 | graphs reused = 1 1.03.232.397 I slot print_timing: id 2 | task 168 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.232.404 I slot release: id 2 | task 168 | stop processing: n_tokens = 103, truncated = 0 1.03.232.494 I slot print_timing: id 3 | task 171 | prompt eval time = 1386.63 ms / 154 tokens ( 9.00 ms per token, 111.06 tokens per second) 1.03.232.496 I slot print_timing: id 3 | task 171 | eval time = 40.60 ms / 2 tokens ( 40.60 ms per token, 24.63 tokens per second) 1.03.232.496 I slot print_timing: id 3 | task 171 | total time = 1427.23 ms / 156 tokens 1.03.232.496 I slot print_timing: id 3 | task 171 | graphs reused = 1 1.03.232.496 I slot print_timing: id 3 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.232.507 I slot release: id 3 | task 171 | stop processing: n_tokens = 155, truncated = 0 1.03.237.956 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.260 (> 0.100 thold), f_keep = 0.198 1.03.239.580 I slot launch_slot_: id 0 | task 175 | processing task, is_child = 0 1.03.246.143 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.262 1.03.246.213 I slot launch_slot_: id 2 | task 176 | processing task, is_child = 0 1.03.246.266 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.202 (> 0.100 thold), f_keep = 0.177 1.03.246.327 I slot launch_slot_: id 1 | task 177 | processing task, is_child = 0 1.03.246.353 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.168 1.03.246.425 I slot launch_slot_: id 3 | task 178 | processing task, is_child = 0 1.04.444.210 I slot print_timing: id 0 | task 175 | prompt eval time = 1157.07 ms / 100 tokens ( 11.57 ms per token, 86.42 tokens per second) 1.04.444.213 I slot print_timing: id 0 | task 175 | eval time = 40.70 ms / 2 tokens ( 40.70 ms per token, 24.57 tokens per second) 1.04.444.213 I slot print_timing: id 0 | task 175 | total time = 1197.78 ms / 102 tokens 1.04.444.213 I slot print_timing: id 0 | task 175 | graphs reused = 1 1.04.444.214 I slot print_timing: id 0 | task 175 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.444.235 I slot release: id 0 | task 175 | stop processing: n_tokens = 101, truncated = 0 1.04.444.330 I slot print_timing: id 1 | task 177 | prompt eval time = 1157.18 ms / 129 tokens ( 8.97 ms per token, 111.48 tokens per second) 1.04.444.332 I slot print_timing: id 1 | task 177 | eval time = 40.70 ms / 2 tokens ( 40.70 ms per token, 24.57 tokens per second) 1.04.444.332 I slot print_timing: id 1 | task 177 | total time = 1197.88 ms / 131 tokens 1.04.444.332 I slot print_timing: id 1 | task 177 | graphs reused = 1 1.04.444.333 I slot print_timing: id 1 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.444.343 I slot release: id 1 | task 177 | stop processing: n_tokens = 130, truncated = 0 1.04.444.453 I slot print_timing: id 2 | task 176 | prompt eval time = 1157.28 ms / 102 tokens ( 11.35 ms per token, 88.14 tokens per second) 1.04.444.454 I slot print_timing: id 2 | task 176 | eval time = 40.70 ms / 2 tokens ( 40.70 ms per token, 24.57 tokens per second) 1.04.444.455 I slot print_timing: id 2 | task 176 | total time = 1197.98 ms / 104 tokens 1.04.444.455 I slot print_timing: id 2 | task 176 | graphs reused = 1 1.04.444.455 I slot print_timing: id 2 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.444.465 I slot release: id 2 | task 176 | stop processing: n_tokens = 103, truncated = 0 1.04.444.573 I slot print_timing: id 3 | task 178 | prompt eval time = 1157.39 ms / 138 tokens ( 8.39 ms per token, 119.23 tokens per second) 1.04.444.575 I slot print_timing: id 3 | task 178 | eval time = 40.70 ms / 2 tokens ( 40.70 ms per token, 24.57 tokens per second) 1.04.444.576 I slot print_timing: id 3 | task 178 | total time = 1198.09 ms / 140 tokens 1.04.444.576 I slot print_timing: id 3 | task 178 | graphs reused = 1 1.04.444.576 I slot print_timing: id 3 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.444.586 I slot release: id 3 | task 178 | stop processing: n_tokens = 139, truncated = 0 1.04.449.606 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.257 1.04.450.571 I slot launch_slot_: id 0 | task 182 | processing task, is_child = 0 1.04.455.735 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.262 1.04.455.811 I slot launch_slot_: id 2 | task 183 | processing task, is_child = 0 1.04.455.864 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.200 1.04.456.237 I slot launch_slot_: id 1 | task 184 | processing task, is_child = 0 1.04.456.267 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.187 1.04.456.331 I slot launch_slot_: id 3 | task 185 | processing task, is_child = 0 1.05.699.508 I slot print_timing: id 0 | task 182 | prompt eval time = 1202.39 ms / 115 tokens ( 10.46 ms per token, 95.64 tokens per second) 1.05.699.509 I slot print_timing: id 0 | task 182 | eval time = 40.76 ms / 2 tokens ( 40.76 ms per token, 24.53 tokens per second) 1.05.699.510 I slot print_timing: id 0 | task 182 | total time = 1243.16 ms / 117 tokens 1.05.699.510 I slot print_timing: id 0 | task 182 | graphs reused = 1 1.05.699.510 I slot print_timing: id 0 | task 182 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.699.530 I slot release: id 0 | task 182 | stop processing: n_tokens = 116, truncated = 0 1.05.699.627 I slot print_timing: id 1 | task 184 | prompt eval time = 1202.51 ms / 121 tokens ( 9.94 ms per token, 100.62 tokens per second) 1.05.699.629 I slot print_timing: id 1 | task 184 | eval time = 40.77 ms / 2 tokens ( 40.77 ms per token, 24.53 tokens per second) 1.05.699.629 I slot print_timing: id 1 | task 184 | total time = 1243.27 ms / 123 tokens 1.05.699.629 I slot print_timing: id 1 | task 184 | graphs reused = 1 1.05.699.630 I slot print_timing: id 1 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.699.638 I slot release: id 1 | task 184 | stop processing: n_tokens = 122, truncated = 0 1.05.699.733 I slot print_timing: id 2 | task 183 | prompt eval time = 1202.60 ms / 103 tokens ( 11.68 ms per token, 85.65 tokens per second) 1.05.699.735 I slot print_timing: id 2 | task 183 | eval time = 40.75 ms / 2 tokens ( 40.75 ms per token, 24.54 tokens per second) 1.05.699.735 I slot print_timing: id 2 | task 183 | total time = 1243.35 ms / 105 tokens 1.05.699.735 I slot print_timing: id 2 | task 183 | graphs reused = 1 1.05.699.736 I slot print_timing: id 2 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.699.743 I slot release: id 2 | task 183 | stop processing: n_tokens = 104, truncated = 0 1.05.699.837 I slot print_timing: id 3 | task 185 | prompt eval time = 1202.71 ms / 145 tokens ( 8.29 ms per token, 120.56 tokens per second) 1.05.699.840 I slot print_timing: id 3 | task 185 | eval time = 40.73 ms / 2 tokens ( 40.73 ms per token, 24.55 tokens per second) 1.05.699.841 I slot print_timing: id 3 | task 185 | total time = 1243.44 ms / 147 tokens 1.05.699.841 I slot print_timing: id 3 | task 185 | graphs reused = 1 1.05.699.841 I slot print_timing: id 3 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.699.849 I slot release: id 3 | task 185 | stop processing: n_tokens = 146, truncated = 0 1.05.705.634 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.225 (> 0.100 thold), f_keep = 0.221 1.05.707.045 I slot launch_slot_: id 1 | task 189 | processing task, is_child = 0 1.05.712.121 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.260 1.05.712.189 I slot launch_slot_: id 2 | task 190 | processing task, is_child = 0 1.05.712.238 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.224 1.05.712.297 I slot launch_slot_: id 0 | task 191 | processing task, is_child = 0 1.05.712.324 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.178 1.05.712.383 I slot launch_slot_: id 3 | task 192 | processing task, is_child = 0 1.07.109.980 I slot print_timing: id 0 | task 191 | prompt eval time = 1356.94 ms / 150 tokens ( 9.05 ms per token, 110.54 tokens per second) 1.07.109.983 I slot print_timing: id 0 | task 191 | eval time = 40.64 ms / 2 tokens ( 40.64 ms per token, 24.61 tokens per second) 1.07.109.983 I slot print_timing: id 0 | task 191 | total time = 1397.59 ms / 152 tokens 1.07.109.984 I slot print_timing: id 0 | task 191 | graphs reused = 1 1.07.109.984 I slot print_timing: id 0 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.110.006 I slot release: id 0 | task 191 | stop processing: n_tokens = 151, truncated = 0 1.07.110.089 I slot print_timing: id 1 | task 189 | prompt eval time = 1357.05 ms / 120 tokens ( 11.31 ms per token, 88.43 tokens per second) 1.07.110.090 I slot print_timing: id 1 | task 189 | eval time = 40.63 ms / 2 tokens ( 40.63 ms per token, 24.61 tokens per second) 1.07.110.090 I slot print_timing: id 1 | task 189 | total time = 1397.68 ms / 122 tokens 1.07.110.090 I slot print_timing: id 1 | task 189 | graphs reused = 1 1.07.110.091 I slot print_timing: id 1 | task 189 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.110.101 I slot release: id 1 | task 189 | stop processing: n_tokens = 121, truncated = 0 1.07.110.188 I slot print_timing: id 2 | task 190 | prompt eval time = 1357.16 ms / 107 tokens ( 12.68 ms per token, 78.84 tokens per second) 1.07.110.189 I slot print_timing: id 2 | task 190 | eval time = 40.60 ms / 2 tokens ( 40.60 ms per token, 24.63 tokens per second) 1.07.110.190 I slot print_timing: id 2 | task 190 | total time = 1397.76 ms / 109 tokens 1.07.110.190 I slot print_timing: id 2 | task 190 | graphs reused = 1 1.07.110.190 I slot print_timing: id 2 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.110.200 I slot release: id 2 | task 190 | stop processing: n_tokens = 108, truncated = 0 1.07.110.290 I slot print_timing: id 3 | task 192 | prompt eval time = 1357.27 ms / 156 tokens ( 8.70 ms per token, 114.94 tokens per second) 1.07.110.292 I slot print_timing: id 3 | task 192 | eval time = 40.58 ms / 2 tokens ( 40.58 ms per token, 24.64 tokens per second) 1.07.110.293 I slot print_timing: id 3 | task 192 | total time = 1397.85 ms / 158 tokens 1.07.110.293 I slot print_timing: id 3 | task 192 | graphs reused = 1 1.07.110.293 I slot print_timing: id 3 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.110.303 I slot release: id 3 | task 192 | stop processing: n_tokens = 157, truncated = 0 1.07.115.380 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.263 (> 0.100 thold), f_keep = 0.172 1.07.117.712 I slot launch_slot_: id 0 | task 196 | processing task, is_child = 0 1.07.122.626 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.215 1.07.122.693 I slot launch_slot_: id 1 | task 197 | processing task, is_child = 0 1.07.122.742 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.241 1.07.122.801 I slot launch_slot_: id 2 | task 198 | processing task, is_child = 0 1.07.122.828 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.166 1.07.122.888 I slot launch_slot_: id 3 | task 199 | processing task, is_child = 0 1.08.588.395 I slot print_timing: id 0 | task 196 | prompt eval time = 1424.80 ms / 99 tokens ( 14.39 ms per token, 69.48 tokens per second) 1.08.588.397 I slot print_timing: id 0 | task 196 | eval time = 40.70 ms / 2 tokens ( 40.70 ms per token, 24.57 tokens per second) 1.08.588.398 I slot print_timing: id 0 | task 196 | total time = 1465.50 ms / 101 tokens 1.08.588.398 I slot print_timing: id 0 | task 196 | graphs reused = 1 1.08.588.399 I slot print_timing: id 0 | task 196 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.588.419 I slot release: id 0 | task 196 | stop processing: n_tokens = 100, truncated = 0 1.08.588.509 I slot print_timing: id 1 | task 197 | prompt eval time = 1424.91 ms / 125 tokens ( 11.40 ms per token, 87.73 tokens per second) 1.08.588.512 I slot print_timing: id 1 | task 197 | eval time = 40.69 ms / 2 tokens ( 40.69 ms per token, 24.58 tokens per second) 1.08.588.512 I slot print_timing: id 1 | task 197 | total time = 1465.59 ms / 127 tokens 1.08.588.512 I slot print_timing: id 1 | task 197 | graphs reused = 1 1.08.588.513 I slot print_timing: id 1 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.588.528 I slot release: id 1 | task 197 | stop processing: n_tokens = 126, truncated = 0 1.08.588.614 I slot print_timing: id 2 | task 198 | prompt eval time = 1425.02 ms / 145 tokens ( 9.83 ms per token, 101.75 tokens per second) 1.08.588.617 I slot print_timing: id 2 | task 198 | eval time = 40.66 ms / 2 tokens ( 40.66 ms per token, 24.59 tokens per second) 1.08.588.618 I slot print_timing: id 2 | task 198 | total time = 1465.68 ms / 147 tokens 1.08.588.618 I slot print_timing: id 2 | task 198 | graphs reused = 1 1.08.588.618 I slot print_timing: id 2 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.588.627 I slot release: id 2 | task 198 | stop processing: n_tokens = 146, truncated = 0 1.08.588.716 I slot print_timing: id 3 | task 199 | prompt eval time = 1425.13 ms / 165 tokens ( 8.64 ms per token, 115.78 tokens per second) 1.08.588.718 I slot print_timing: id 3 | task 199 | eval time = 40.64 ms / 2 tokens ( 40.64 ms per token, 24.61 tokens per second) 1.08.588.719 I slot print_timing: id 3 | task 199 | total time = 1465.77 ms / 167 tokens 1.08.588.719 I slot print_timing: id 3 | task 199 | graphs reused = 1 1.08.588.719 I slot print_timing: id 3 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.588.731 I slot release: id 3 | task 199 | stop processing: n_tokens = 166, truncated = 0 1.08.593.759 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.260 1.08.595.416 I slot launch_slot_: id 0 | task 203 | processing task, is_child = 0 1.08.601.887 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.206 1.08.601.967 I slot launch_slot_: id 1 | task 204 | processing task, is_child = 0 1.08.602.028 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.205 (> 0.100 thold), f_keep = 0.178 1.08.602.101 I slot launch_slot_: id 2 | task 205 | processing task, is_child = 0 1.08.602.130 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.157 1.08.602.207 I slot launch_slot_: id 3 | task 206 | processing task, is_child = 0 1.09.860.959 I slot print_timing: id 0 | task 203 | prompt eval time = 1218.18 ms / 107 tokens ( 11.38 ms per token, 87.84 tokens per second) 1.09.860.964 I slot print_timing: id 0 | task 203 | eval time = 40.56 ms / 2 tokens ( 40.56 ms per token, 24.66 tokens per second) 1.09.860.964 I slot print_timing: id 0 | task 203 | total time = 1258.74 ms / 109 tokens 1.09.860.965 I slot print_timing: id 0 | task 203 | graphs reused = 1 1.09.860.965 I slot print_timing: id 0 | task 203 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.860.983 I slot release: id 0 | task 203 | stop processing: n_tokens = 108, truncated = 0 1.09.861.071 I slot print_timing: id 1 | task 204 | prompt eval time = 1218.28 ms / 124 tokens ( 9.82 ms per token, 101.78 tokens per second) 1.09.861.073 I slot print_timing: id 1 | task 204 | eval time = 40.55 ms / 2 tokens ( 40.55 ms per token, 24.66 tokens per second) 1.09.861.073 I slot print_timing: id 1 | task 204 | total time = 1258.84 ms / 126 tokens 1.09.861.073 I slot print_timing: id 1 | task 204 | graphs reused = 1 1.09.861.074 I slot print_timing: id 1 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.861.084 I slot release: id 1 | task 204 | stop processing: n_tokens = 125, truncated = 0 1.09.861.175 I slot print_timing: id 2 | task 205 | prompt eval time = 1218.39 ms / 127 tokens ( 9.59 ms per token, 104.24 tokens per second) 1.09.861.178 I slot print_timing: id 2 | task 205 | eval time = 40.53 ms / 2 tokens ( 40.53 ms per token, 24.67 tokens per second) 1.09.861.178 I slot print_timing: id 2 | task 205 | total time = 1258.92 ms / 129 tokens 1.09.861.178 I slot print_timing: id 2 | task 205 | graphs reused = 1 1.09.861.179 I slot print_timing: id 2 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.861.187 I slot release: id 2 | task 205 | stop processing: n_tokens = 128, truncated = 0 1.09.861.277 I slot print_timing: id 3 | task 206 | prompt eval time = 1218.49 ms / 149 tokens ( 8.18 ms per token, 122.28 tokens per second) 1.09.861.282 I slot print_timing: id 3 | task 206 | eval time = 40.51 ms / 2 tokens ( 40.51 ms per token, 24.68 tokens per second) 1.09.861.282 I slot print_timing: id 3 | task 206 | total time = 1259.00 ms / 151 tokens 1.09.861.282 I slot print_timing: id 3 | task 206 | graphs reused = 1 1.09.861.283 I slot print_timing: id 3 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.861.292 I slot release: id 3 | task 206 | stop processing: n_tokens = 150, truncated = 0 1.09.866.890 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.250 1.09.868.581 I slot launch_slot_: id 0 | task 210 | processing task, is_child = 0 1.09.874.197 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.208 1.09.875.197 I slot launch_slot_: id 1 | task 211 | processing task, is_child = 0 1.09.875.250 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.203 1.09.875.311 I slot launch_slot_: id 2 | task 212 | processing task, is_child = 0 1.09.875.337 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.173 1.09.875.398 I slot launch_slot_: id 3 | task 213 | processing task, is_child = 0 1.11.144.357 I slot print_timing: id 0 | task 210 | prompt eval time = 1228.09 ms / 105 tokens ( 11.70 ms per token, 85.50 tokens per second) 1.11.144.359 I slot print_timing: id 0 | task 210 | eval time = 40.86 ms / 2 tokens ( 40.86 ms per token, 24.47 tokens per second) 1.11.144.360 I slot print_timing: id 0 | task 210 | total time = 1268.95 ms / 107 tokens 1.11.144.360 I slot print_timing: id 0 | task 210 | graphs reused = 1 1.11.144.361 I slot print_timing: id 0 | task 210 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.144.381 I slot release: id 0 | task 210 | stop processing: n_tokens = 106, truncated = 0 1.11.144.472 I slot print_timing: id 1 | task 211 | prompt eval time = 1228.20 ms / 114 tokens ( 10.77 ms per token, 92.82 tokens per second) 1.11.144.474 I slot print_timing: id 1 | task 211 | eval time = 40.85 ms / 2 tokens ( 40.85 ms per token, 24.48 tokens per second) 1.11.144.475 I slot print_timing: id 1 | task 211 | total time = 1269.05 ms / 116 tokens 1.11.144.475 I slot print_timing: id 1 | task 211 | graphs reused = 1 1.11.144.475 I slot print_timing: id 1 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.144.486 I slot release: id 1 | task 211 | stop processing: n_tokens = 115, truncated = 0 1.11.144.583 I slot print_timing: id 2 | task 212 | prompt eval time = 1228.32 ms / 149 tokens ( 8.24 ms per token, 121.30 tokens per second) 1.11.144.585 I slot print_timing: id 2 | task 212 | eval time = 40.84 ms / 2 tokens ( 40.84 ms per token, 24.49 tokens per second) 1.11.144.585 I slot print_timing: id 2 | task 212 | total time = 1269.15 ms / 151 tokens 1.11.144.585 I slot print_timing: id 2 | task 212 | graphs reused = 1 1.11.144.586 I slot print_timing: id 2 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.144.601 I slot release: id 2 | task 212 | stop processing: n_tokens = 150, truncated = 0 1.11.144.693 I slot print_timing: id 3 | task 213 | prompt eval time = 1228.43 ms / 142 tokens ( 8.65 ms per token, 115.59 tokens per second) 1.11.144.695 I slot print_timing: id 3 | task 213 | eval time = 40.82 ms / 2 tokens ( 40.82 ms per token, 24.50 tokens per second) 1.11.144.695 I slot print_timing: id 3 | task 213 | total time = 1269.25 ms / 144 tokens 1.11.144.696 I slot print_timing: id 3 | task 213 | graphs reused = 1 1.11.144.696 I slot print_timing: id 3 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.144.714 I slot release: id 3 | task 213 | stop processing: n_tokens = 143, truncated = 0 1.11.150.311 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.245 1.11.151.445 I slot launch_slot_: id 0 | task 217 | processing task, is_child = 0 1.11.156.713 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.226 1.11.156.781 I slot launch_slot_: id 1 | task 218 | processing task, is_child = 0 1.11.156.831 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.173 1.11.156.892 I slot launch_slot_: id 2 | task 219 | processing task, is_child = 0 1.11.156.919 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.182 1.11.156.978 I slot launch_slot_: id 3 | task 220 | processing task, is_child = 0 1.12.397.269 I slot print_timing: id 0 | task 217 | prompt eval time = 1199.46 ms / 139 tokens ( 8.63 ms per token, 115.89 tokens per second) 1.12.397.272 I slot print_timing: id 0 | task 217 | eval time = 40.82 ms / 2 tokens ( 40.82 ms per token, 24.50 tokens per second) 1.12.397.272 I slot print_timing: id 0 | task 217 | total time = 1240.28 ms / 141 tokens 1.12.397.273 I slot print_timing: id 0 | task 217 | graphs reused = 1 1.12.397.273 I slot print_timing: id 0 | task 217 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.397.294 I slot release: id 0 | task 217 | stop processing: n_tokens = 140, truncated = 0 1.12.397.380 I slot print_timing: id 1 | task 218 | prompt eval time = 1199.57 ms / 149 tokens ( 8.05 ms per token, 124.21 tokens per second) 1.12.397.383 I slot print_timing: id 1 | task 218 | eval time = 40.81 ms / 2 tokens ( 40.81 ms per token, 24.50 tokens per second) 1.12.397.383 I slot print_timing: id 1 | task 218 | total time = 1240.38 ms / 151 tokens 1.12.397.384 I slot print_timing: id 1 | task 218 | graphs reused = 1 1.12.397.384 I slot print_timing: id 1 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.397.394 I slot release: id 1 | task 218 | stop processing: n_tokens = 150, truncated = 0 1.12.397.491 I slot print_timing: id 2 | task 219 | prompt eval time = 1199.68 ms / 143 tokens ( 8.39 ms per token, 119.20 tokens per second) 1.12.397.493 I slot print_timing: id 2 | task 219 | eval time = 40.79 ms / 2 tokens ( 40.79 ms per token, 24.52 tokens per second) 1.12.397.493 I slot print_timing: id 2 | task 219 | total time = 1240.47 ms / 145 tokens 1.12.397.493 I slot print_timing: id 2 | task 219 | graphs reused = 1 1.12.397.494 I slot print_timing: id 2 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.397.507 I slot release: id 2 | task 219 | stop processing: n_tokens = 144, truncated = 0 1.12.397.598 I slot print_timing: id 3 | task 220 | prompt eval time = 1199.79 ms / 144 tokens ( 8.33 ms per token, 120.02 tokens per second) 1.12.397.600 I slot print_timing: id 3 | task 220 | eval time = 40.77 ms / 2 tokens ( 40.77 ms per token, 24.53 tokens per second) 1.12.397.600 I slot print_timing: id 3 | task 220 | total time = 1240.56 ms / 146 tokens 1.12.397.600 I slot print_timing: id 3 | task 220 | graphs reused = 1 1.12.397.600 I slot print_timing: id 3 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.397.607 I slot release: id 3 | task 220 | stop processing: n_tokens = 145, truncated = 0 1.12.402.275 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.186 1.12.404.513 I slot launch_slot_: id 0 | task 224 | processing task, is_child = 0 1.12.411.475 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.280 (> 0.100 thold), f_keep = 0.173 1.12.411.845 I slot launch_slot_: id 1 | task 225 | processing task, is_child = 0 1.12.411.895 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.181 1.12.411.961 I slot launch_slot_: id 2 | task 226 | processing task, is_child = 0 1.12.411.987 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.179 1.12.412.047 I slot launch_slot_: id 3 | task 227 | processing task, is_child = 0 1.13.673.690 I slot print_timing: id 0 | task 224 | prompt eval time = 1221.05 ms / 98 tokens ( 12.46 ms per token, 80.26 tokens per second) 1.13.673.693 I slot print_timing: id 0 | task 224 | eval time = 40.59 ms / 2 tokens ( 40.59 ms per token, 24.64 tokens per second) 1.13.673.694 I slot print_timing: id 0 | task 224 | total time = 1261.63 ms / 100 tokens 1.13.673.695 I slot print_timing: id 0 | task 224 | graphs reused = 1 1.13.673.695 I slot print_timing: id 0 | task 224 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.673.711 I slot release: id 0 | task 224 | stop processing: n_tokens = 99, truncated = 0 1.13.673.800 I slot print_timing: id 1 | task 225 | prompt eval time = 1221.15 ms / 93 tokens ( 13.13 ms per token, 76.16 tokens per second) 1.13.673.801 I slot print_timing: id 1 | task 225 | eval time = 40.58 ms / 2 tokens ( 40.58 ms per token, 24.64 tokens per second) 1.13.673.802 I slot print_timing: id 1 | task 225 | total time = 1261.73 ms / 95 tokens 1.13.673.802 I slot print_timing: id 1 | task 225 | graphs reused = 1 1.13.673.802 I slot print_timing: id 1 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.673.811 I slot release: id 1 | task 225 | stop processing: n_tokens = 94, truncated = 0 1.13.673.899 I slot print_timing: id 2 | task 226 | prompt eval time = 1221.26 ms / 106 tokens ( 11.52 ms per token, 86.80 tokens per second) 1.13.673.901 I slot print_timing: id 2 | task 226 | eval time = 40.54 ms / 2 tokens ( 40.54 ms per token, 24.67 tokens per second) 1.13.673.901 I slot print_timing: id 2 | task 226 | total time = 1261.80 ms / 108 tokens 1.13.673.901 I slot print_timing: id 2 | task 226 | graphs reused = 1 1.13.673.902 I slot print_timing: id 2 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.673.910 I slot release: id 2 | task 226 | stop processing: n_tokens = 107, truncated = 0 1.13.673.996 I slot print_timing: id 3 | task 227 | prompt eval time = 1221.36 ms / 178 tokens ( 6.86 ms per token, 145.74 tokens per second) 1.13.673.999 I slot print_timing: id 3 | task 227 | eval time = 40.52 ms / 2 tokens ( 40.52 ms per token, 24.68 tokens per second) 1.13.674.000 I slot print_timing: id 3 | task 227 | total time = 1261.88 ms / 180 tokens 1.13.674.000 I slot print_timing: id 3 | task 227 | graphs reused = 1 1.13.674.000 I slot print_timing: id 3 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.674.010 I slot release: id 3 | task 227 | stop processing: n_tokens = 179, truncated = 0 1.13.679.181 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.287 1.13.679.895 I slot launch_slot_: id 1 | task 231 | processing task, is_child = 0 1.13.684.091 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.263 1.13.684.180 I slot launch_slot_: id 0 | task 232 | processing task, is_child = 0 1.13.684.235 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.243 1.13.684.304 I slot launch_slot_: id 2 | task 233 | processing task, is_child = 0 1.13.684.334 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.145 1.13.684.407 I slot launch_slot_: id 3 | task 234 | processing task, is_child = 0 1.14.953.981 I slot print_timing: id 0 | task 232 | prompt eval time = 1228.95 ms / 118 tokens ( 10.41 ms per token, 96.02 tokens per second) 1.14.953.983 I slot print_timing: id 0 | task 232 | eval time = 40.62 ms / 2 tokens ( 40.62 ms per token, 24.62 tokens per second) 1.14.953.983 I slot print_timing: id 0 | task 232 | total time = 1269.57 ms / 120 tokens 1.14.953.984 I slot print_timing: id 0 | task 232 | graphs reused = 1 1.14.953.984 I slot print_timing: id 0 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.954.002 I slot release: id 0 | task 232 | stop processing: n_tokens = 119, truncated = 0 1.14.954.088 I slot print_timing: id 1 | task 231 | prompt eval time = 1229.04 ms / 102 tokens ( 12.05 ms per token, 82.99 tokens per second) 1.14.954.091 I slot print_timing: id 1 | task 231 | eval time = 40.60 ms / 2 tokens ( 40.60 ms per token, 24.63 tokens per second) 1.14.954.091 I slot print_timing: id 1 | task 231 | total time = 1269.65 ms / 104 tokens 1.14.954.092 I slot print_timing: id 1 | task 231 | graphs reused = 1 1.14.954.092 I slot print_timing: id 1 | task 231 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.954.102 I slot release: id 1 | task 231 | stop processing: n_tokens = 103, truncated = 0 1.14.954.194 I slot print_timing: id 2 | task 233 | prompt eval time = 1229.14 ms / 148 tokens ( 8.31 ms per token, 120.41 tokens per second) 1.14.954.196 I slot print_timing: id 2 | task 233 | eval time = 40.59 ms / 2 tokens ( 40.59 ms per token, 24.63 tokens per second) 1.14.954.196 I slot print_timing: id 2 | task 233 | total time = 1269.74 ms / 150 tokens 1.14.954.197 I slot print_timing: id 2 | task 233 | graphs reused = 1 1.14.954.197 I slot print_timing: id 2 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.954.207 I slot release: id 2 | task 233 | stop processing: n_tokens = 149, truncated = 0 1.14.954.299 I slot print_timing: id 3 | task 234 | prompt eval time = 1229.23 ms / 114 tokens ( 10.78 ms per token, 92.74 tokens per second) 1.14.954.301 I slot print_timing: id 3 | task 234 | eval time = 40.58 ms / 2 tokens ( 40.58 ms per token, 24.64 tokens per second) 1.14.954.302 I slot print_timing: id 3 | task 234 | total time = 1269.82 ms / 116 tokens 1.14.954.302 I slot print_timing: id 3 | task 234 | graphs reused = 1 1.14.954.302 I slot print_timing: id 3 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.954.315 I slot release: id 3 | task 234 | stop processing: n_tokens = 115, truncated = 0 1.14.959.598 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.218 1.14.961.402 I slot launch_slot_: id 0 | task 238 | processing task, is_child = 0 1.14.966.891 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.252 1.14.966.961 I slot launch_slot_: id 1 | task 239 | processing task, is_child = 0 1.14.967.011 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.174 1.14.967.515 I slot launch_slot_: id 2 | task 240 | processing task, is_child = 0 1.14.967.541 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.226 1.14.967.975 I slot launch_slot_: id 3 | task 241 | processing task, is_child = 0 1.16.033.238 I slot print_timing: id 0 | task 238 | prompt eval time = 1024.45 ms / 113 tokens ( 9.07 ms per token, 110.30 tokens per second) 1.16.033.243 I slot print_timing: id 0 | task 238 | eval time = 40.80 ms / 2 tokens ( 40.80 ms per token, 24.51 tokens per second) 1.16.033.243 I slot print_timing: id 0 | task 238 | total time = 1065.25 ms / 115 tokens 1.16.033.244 I slot print_timing: id 0 | task 238 | graphs reused = 1 1.16.033.244 I slot print_timing: id 0 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.033.261 I slot release: id 0 | task 238 | stop processing: n_tokens = 114, truncated = 0 1.16.033.351 I slot print_timing: id 1 | task 239 | prompt eval time = 1024.55 ms / 115 tokens ( 8.91 ms per token, 112.24 tokens per second) 1.16.033.356 I slot print_timing: id 1 | task 239 | eval time = 40.80 ms / 2 tokens ( 40.80 ms per token, 24.51 tokens per second) 1.16.033.356 I slot print_timing: id 1 | task 239 | total time = 1065.35 ms / 117 tokens 1.16.033.356 I slot print_timing: id 1 | task 239 | graphs reused = 1 1.16.033.357 I slot print_timing: id 1 | task 239 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.033.365 I slot release: id 1 | task 239 | stop processing: n_tokens = 116, truncated = 0 1.16.033.457 I slot print_timing: id 2 | task 240 | prompt eval time = 1024.67 ms / 128 tokens ( 8.01 ms per token, 124.92 tokens per second) 1.16.033.459 I slot print_timing: id 2 | task 240 | eval time = 40.77 ms / 2 tokens ( 40.77 ms per token, 24.52 tokens per second) 1.16.033.459 I slot print_timing: id 2 | task 240 | total time = 1065.45 ms / 130 tokens 1.16.033.459 I slot print_timing: id 2 | task 240 | graphs reused = 1 1.16.033.460 I slot print_timing: id 2 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.033.470 I slot release: id 2 | task 240 | stop processing: n_tokens = 129, truncated = 0 1.16.033.563 I slot print_timing: id 3 | task 241 | prompt eval time = 1024.78 ms / 126 tokens ( 8.13 ms per token, 122.95 tokens per second) 1.16.033.565 I slot print_timing: id 3 | task 241 | eval time = 40.76 ms / 2 tokens ( 40.76 ms per token, 24.54 tokens per second) 1.16.033.566 I slot print_timing: id 3 | task 241 | total time = 1065.53 ms / 128 tokens 1.16.033.566 I slot print_timing: id 3 | task 241 | graphs reused = 1 1.16.033.566 I slot print_timing: id 3 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.033.573 I slot release: id 3 | task 241 | stop processing: n_tokens = 127, truncated = 0 1.16.038.926 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.228 1.16.040.137 I slot launch_slot_: id 0 | task 245 | processing task, is_child = 0 1.16.045.343 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.224 1.16.045.415 I slot launch_slot_: id 1 | task 246 | processing task, is_child = 0 1.16.045.467 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.202 1.16.045.811 I slot launch_slot_: id 2 | task 247 | processing task, is_child = 0 1.16.045.845 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.205 1.16.045.911 I slot launch_slot_: id 3 | task 248 | processing task, is_child = 0 1.17.464.468 I slot print_timing: id 0 | task 245 | prompt eval time = 1377.92 ms / 113 tokens ( 12.19 ms per token, 82.01 tokens per second) 1.17.464.470 I slot print_timing: id 0 | task 245 | eval time = 40.62 ms / 2 tokens ( 40.62 ms per token, 24.62 tokens per second) 1.17.464.470 I slot print_timing: id 0 | task 245 | total time = 1418.55 ms / 115 tokens 1.17.464.471 I slot print_timing: id 0 | task 245 | graphs reused = 1 1.17.464.471 I slot print_timing: id 0 | task 245 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.464.488 I slot release: id 0 | task 245 | stop processing: n_tokens = 114, truncated = 0 1.17.464.575 I slot print_timing: id 1 | task 246 | prompt eval time = 1378.03 ms / 132 tokens ( 10.44 ms per token, 95.79 tokens per second) 1.17.464.577 I slot print_timing: id 1 | task 246 | eval time = 40.61 ms / 2 tokens ( 40.61 ms per token, 24.62 tokens per second) 1.17.464.577 I slot print_timing: id 1 | task 246 | total time = 1418.64 ms / 134 tokens 1.17.464.578 I slot print_timing: id 1 | task 246 | graphs reused = 1 1.17.464.578 I slot print_timing: id 1 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.464.588 I slot release: id 1 | task 246 | stop processing: n_tokens = 133, truncated = 0 1.17.464.679 I slot print_timing: id 2 | task 247 | prompt eval time = 1378.13 ms / 151 tokens ( 9.13 ms per token, 109.57 tokens per second) 1.17.464.680 I slot print_timing: id 2 | task 247 | eval time = 40.59 ms / 2 tokens ( 40.59 ms per token, 24.64 tokens per second) 1.17.464.681 I slot print_timing: id 2 | task 247 | total time = 1418.72 ms / 153 tokens 1.17.464.681 I slot print_timing: id 2 | task 247 | graphs reused = 1 1.17.464.681 I slot print_timing: id 2 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.464.692 I slot release: id 2 | task 247 | stop processing: n_tokens = 152, truncated = 0 1.17.464.783 I slot print_timing: id 3 | task 248 | prompt eval time = 1378.24 ms / 160 tokens ( 8.61 ms per token, 116.09 tokens per second) 1.17.464.785 I slot print_timing: id 3 | task 248 | eval time = 40.57 ms / 2 tokens ( 40.57 ms per token, 24.65 tokens per second) 1.17.464.785 I slot print_timing: id 3 | task 248 | total time = 1418.81 ms / 162 tokens 1.17.464.785 I slot print_timing: id 3 | task 248 | graphs reused = 1 1.17.464.786 I slot print_timing: id 3 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.464.794 I slot release: id 3 | task 248 | stop processing: n_tokens = 161, truncated = 0 1.17.469.638 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.228 1.17.471.411 I slot launch_slot_: id 0 | task 252 | processing task, is_child = 0 1.17.478.025 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.271 (> 0.100 thold), f_keep = 0.195 1.17.478.106 I slot launch_slot_: id 1 | task 253 | processing task, is_child = 0 1.17.478.157 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.171 1.17.478.220 I slot launch_slot_: id 2 | task 254 | processing task, is_child = 0 1.17.478.247 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.161 1.17.478.309 I slot launch_slot_: id 3 | task 255 | processing task, is_child = 0 1.18.917.196 I slot print_timing: id 0 | task 252 | prompt eval time = 1398.10 ms / 126 tokens ( 11.10 ms per token, 90.12 tokens per second) 1.18.917.198 I slot print_timing: id 0 | task 252 | eval time = 40.77 ms / 2 tokens ( 40.77 ms per token, 24.53 tokens per second) 1.18.917.199 I slot print_timing: id 0 | task 252 | total time = 1438.88 ms / 128 tokens 1.18.917.199 I slot print_timing: id 0 | task 252 | graphs reused = 1 1.18.917.200 I slot print_timing: id 0 | task 252 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.917.218 I slot release: id 0 | task 252 | stop processing: n_tokens = 127, truncated = 0 1.18.917.316 I slot print_timing: id 1 | task 253 | prompt eval time = 1398.21 ms / 96 tokens ( 14.56 ms per token, 68.66 tokens per second) 1.18.917.318 I slot print_timing: id 1 | task 253 | eval time = 40.78 ms / 2 tokens ( 40.78 ms per token, 24.52 tokens per second) 1.18.917.319 I slot print_timing: id 1 | task 253 | total time = 1438.98 ms / 98 tokens 1.18.917.319 I slot print_timing: id 1 | task 253 | graphs reused = 1 1.18.917.319 I slot print_timing: id 1 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.917.331 I slot release: id 1 | task 253 | stop processing: n_tokens = 97, truncated = 0 1.18.917.420 I slot print_timing: id 2 | task 254 | prompt eval time = 1398.31 ms / 175 tokens ( 7.99 ms per token, 125.15 tokens per second) 1.18.917.422 I slot print_timing: id 2 | task 254 | eval time = 40.76 ms / 2 tokens ( 40.76 ms per token, 24.54 tokens per second) 1.18.917.422 I slot print_timing: id 2 | task 254 | total time = 1439.06 ms / 177 tokens 1.18.917.423 I slot print_timing: id 2 | task 254 | graphs reused = 1 1.18.917.423 I slot print_timing: id 2 | task 254 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.917.435 I slot release: id 2 | task 254 | stop processing: n_tokens = 176, truncated = 0 1.18.917.517 I slot print_timing: id 3 | task 255 | prompt eval time = 1398.40 ms / 144 tokens ( 9.71 ms per token, 102.97 tokens per second) 1.18.917.519 I slot print_timing: id 3 | task 255 | eval time = 40.74 ms / 2 tokens ( 40.74 ms per token, 24.55 tokens per second) 1.18.917.520 I slot print_timing: id 3 | task 255 | total time = 1439.14 ms / 146 tokens 1.18.917.520 I slot print_timing: id 3 | task 255 | graphs reused = 1 1.18.917.520 I slot print_timing: id 3 | task 255 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.917.529 I slot release: id 3 | task 255 | stop processing: n_tokens = 145, truncated = 0 1.18.922.503 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.205 1.18.924.023 I slot launch_slot_: id 0 | task 260 | processing task, is_child = 0 1.18.929.295 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.268 1.18.929.368 I slot launch_slot_: id 1 | task 259 | processing task, is_child = 0 1.19.588.326 I slot print_timing: id 0 | task 260 | prompt eval time = 627.53 ms / 115 tokens ( 5.46 ms per token, 183.26 tokens per second) 1.19.588.331 I slot print_timing: id 0 | task 260 | eval time = 31.37 ms / 2 tokens ( 31.37 ms per token, 31.88 tokens per second) 1.19.588.332 I slot print_timing: id 0 | task 260 | total time = 658.90 ms / 117 tokens 1.19.588.332 I slot print_timing: id 0 | task 260 | graphs reused = 1 1.19.588.333 I slot print_timing: id 0 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.588.348 I slot release: id 0 | task 260 | stop processing: n_tokens = 116, truncated = 0 1.19.588.433 I slot print_timing: id 1 | task 259 | prompt eval time = 627.60 ms / 128 tokens ( 4.90 ms per token, 203.95 tokens per second) 1.19.588.435 I slot print_timing: id 1 | task 259 | eval time = 31.38 ms / 2 tokens ( 31.38 ms per token, 31.87 tokens per second) 1.19.588.435 I slot print_timing: id 1 | task 259 | total time = 658.98 ms / 130 tokens 1.19.588.435 I slot print_timing: id 1 | task 259 | graphs reused = 1 1.19.588.436 I slot print_timing: id 1 | task 259 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.588.443 I slot release: id 1 | task 259 | stop processing: n_tokens = 129, truncated = 0 1.19.605.690 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 176, t_last = 349087664430 1.19.605.797 I slot launch_slot_: id 2 | task 264 | processing task, is_child = 0 1.19.609.313 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 145, t_last = 349087664524 1.19.609.352 I slot launch_slot_: id 3 | task 265 | processing task, is_child = 0 1.19.609.403 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 116, t_last = 349088335343 1.19.609.437 I slot launch_slot_: id 0 | task 267 | processing task, is_child = 0 1.19.609.463 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 129, t_last = 349088335438 1.19.609.496 I slot launch_slot_: id 1 | task 266 | processing task, is_child = 0 1.22.983.322 I slot print_timing: id 0 | task 267 | prompt processing, n_tokens = 532, progress = 0.51, t = 3.37 s / 157.69 tokens per second 1.23.132.818 I slot print_timing: id 1 | task 266 | prompt processing, n_tokens = 525, progress = 0.50, t = 3.37 s / 155.61 tokens per second 1.23.137.160 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 513, progress = 0.50, t = 3.37 s / 152.06 tokens per second 1.23.140.679 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 540, progress = 0.51, t = 3.37 s / 160.06 tokens per second 1.26.177.087 I slot print_timing: id 0 | task 267 | prompt processing, n_tokens = 953, progress = 0.91, t = 6.57 s / 145.11 tokens per second 1.26.254.288 I slot print_timing: id 1 | task 266 | prompt processing, n_tokens = 953, progress = 0.92, t = 6.57 s / 145.11 tokens per second 1.26.258.308 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 953, progress = 0.93, t = 6.57 s / 145.11 tokens per second 1.26.261.811 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 953, progress = 0.90, t = 6.57 s / 145.11 tokens per second 1.27.068.435 I slot print_timing: id 0 | task 267 | prompt processing, n_tokens = 1044, progress = 1.00, t = 7.46 s / 139.97 tokens per second 1.27.221.395 I slot print_timing: id 1 | task 266 | prompt processing, n_tokens = 1037, progress = 1.00, t = 7.46 s / 139.03 tokens per second 1.27.225.854 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 1025, progress = 1.00, t = 7.46 s / 137.42 tokens per second 1.27.229.308 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 1052, progress = 1.00, t = 7.46 s / 141.04 tokens per second 1.31.289.190 I slot print_timing: id 0 | task 267 | n_gen = 100, tg = 25.06 t/s, tg_3s = 25.31 t/s 1.31.289.366 I slot print_timing: id 1 | task 266 | n_gen = 100, tg = 25.06 t/s, tg_3s = 25.31 t/s 1.31.289.537 I slot print_timing: id 2 | task 264 | n_gen = 100, tg = 25.06 t/s, tg_3s = 25.31 t/s 1.31.289.708 I slot print_timing: id 3 | task 265 | n_gen = 100, tg = 25.06 t/s, tg_3s = 25.31 t/s 1.32.529.000 I slot print_timing: id 1 | task 266 | prompt eval time = 7729.04 ms / 1041 tokens ( 7.42 ms per token, 134.69 tokens per second) 1.32.529.008 I slot print_timing: id 1 | task 266 | eval time = 5190.43 ms / 131 tokens ( 39.93 ms per token, 25.05 tokens per second) 1.32.529.009 I slot print_timing: id 1 | task 266 | total time = 12919.47 ms / 1172 tokens 1.32.529.010 I slot print_timing: id 1 | task 266 | graphs reused = 132 1.32.529.011 I slot print_timing: id 1 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.529.083 I slot release: id 1 | task 266 | stop processing: n_tokens = 1171, truncated = 0 1.32.586.633 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.829 1.32.586.671 I slot launch_slot_: id 1 | task 405 | processing task, is_child = 0 1.34.303.581 I slot print_timing: id 0 | task 267 | n_gen = 164, tg = 23.40 t/s, tg_3s = 21.23 t/s 1.34.303.931 I slot print_timing: id 2 | task 264 | n_gen = 164, tg = 23.40 t/s, tg_3s = 21.23 t/s 1.34.304.108 I slot print_timing: id 3 | task 265 | n_gen = 164, tg = 23.40 t/s, tg_3s = 21.23 t/s 1.35.862.327 I slot print_timing: id 2 | task 264 | prompt eval time = 7729.14 ms / 1029 tokens ( 7.51 ms per token, 133.13 tokens per second) 1.35.862.335 I slot print_timing: id 2 | task 264 | eval time = 8523.64 ms / 203 tokens ( 42.20 ms per token, 23.70 tokens per second) 1.35.862.336 I slot print_timing: id 2 | task 264 | total time = 16252.78 ms / 1232 tokens 1.35.862.336 I slot print_timing: id 2 | task 264 | graphs reused = 200 1.35.862.337 I slot print_timing: id 2 | task 264 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.862.410 I slot release: id 2 | task 264 | stop processing: n_tokens = 1231, truncated = 0 1.35.920.760 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.789 1.35.920.793 I slot launch_slot_: id 2 | task 478 | processing task, is_child = 0 1.37.309.273 I slot print_timing: id 0 | task 267 | n_gen = 227, tg = 22.67 t/s, tg_3s = 20.96 t/s 1.37.309.710 I slot print_timing: id 3 | task 265 | n_gen = 227, tg = 22.67 t/s, tg_3s = 20.96 t/s 1.37.548.852 I slot print_timing: id 1 | task 405 | n_gen = 100, tg = 22.25 t/s, tg_3s = 22.47 t/s 1.39.628.833 I slot print_timing: id 0 | task 267 | prompt eval time = 7728.94 ms / 1048 tokens ( 7.37 ms per token, 135.59 tokens per second) 1.39.628.841 I slot print_timing: id 0 | task 267 | eval time = 12290.39 ms / 285 tokens ( 43.28 ms per token, 23.11 tokens per second) 1.39.628.842 I slot print_timing: id 0 | task 267 | total time = 20019.33 ms / 1333 tokens 1.39.628.843 I slot print_timing: id 0 | task 267 | graphs reused = 277 1.39.628.844 I slot print_timing: id 0 | task 267 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.628.917 I slot release: id 0 | task 267 | stop processing: n_tokens = 1332, truncated = 0 1.39.670.420 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.729 1.39.670.446 I slot launch_slot_: id 0 | task 561 | processing task, is_child = 0 1.40.321.829 I slot print_timing: id 3 | task 265 | n_gen = 292, tg = 22.41 t/s, tg_3s = 21.58 t/s 1.40.566.250 I slot print_timing: id 1 | task 405 | n_gen = 165, tg = 21.96 t/s, tg_3s = 21.54 t/s 1.40.846.551 I slot print_timing: id 2 | task 478 | n_gen = 100, tg = 22.55 t/s, tg_3s = 22.78 t/s 1.43.329.960 I slot print_timing: id 3 | task 265 | n_gen = 367, tg = 22.89 t/s, tg_3s = 24.93 t/s 1.43.570.745 I slot print_timing: id 1 | task 405 | n_gen = 240, tg = 22.82 t/s, tg_3s = 24.96 t/s 1.43.852.250 I slot print_timing: id 2 | task 478 | n_gen = 175, tg = 23.53 t/s, tg_3s = 24.95 t/s 1.44.132.616 I slot print_timing: id 0 | task 561 | n_gen = 100, tg = 24.92 t/s, tg_3s = 25.17 t/s 1.46.344.896 I slot print_timing: id 3 | task 265 | n_gen = 442, tg = 23.20 t/s, tg_3s = 24.88 t/s 1.46.586.973 I slot print_timing: id 1 | task 405 | n_gen = 315, tg = 23.28 t/s, tg_3s = 24.87 t/s 1.46.869.205 I slot print_timing: id 2 | task 478 | n_gen = 250, tg = 23.91 t/s, tg_3s = 24.86 t/s 1.47.150.414 I slot print_timing: id 0 | task 561 | n_gen = 175, tg = 24.89 t/s, tg_3s = 24.85 t/s 1.47.471.669 I slot print_timing: id 2 | task 478 | prompt eval time = 536.23 ms / 104 tokens ( 5.16 ms per token, 193.95 tokens per second) 1.47.471.676 I slot print_timing: id 2 | task 478 | eval time = 11014.64 ms / 265 tokens ( 41.72 ms per token, 23.97 tokens per second) 1.47.471.678 I slot print_timing: id 2 | task 478 | total time = 11550.86 ms / 369 tokens 1.47.471.679 I slot print_timing: id 2 | task 478 | graphs reused = 459 1.47.471.679 I slot print_timing: id 2 | task 478 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.471.757 I slot release: id 2 | task 478 | stop processing: n_tokens = 1339, truncated = 0 1.47.529.975 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.725 1.47.530.003 I slot launch_slot_: id 2 | task 747 | processing task, is_child = 0 1.49.348.364 I slot print_timing: id 3 | task 265 | n_gen = 506, tg = 22.94 t/s, tg_3s = 21.31 t/s 1.49.588.763 I slot print_timing: id 1 | task 405 | n_gen = 379, tg = 22.92 t/s, tg_3s = 21.32 t/s 1.50.152.501 I slot print_timing: id 0 | task 561 | n_gen = 239, tg = 23.82 t/s, tg_3s = 21.32 t/s 1.52.001.629 I slot print_timing: id 2 | task 747 | n_gen = 100, tg = 24.79 t/s, tg_3s = 25.04 t/s 1.52.363.938 I slot print_timing: id 3 | task 265 | n_gen = 581, tg = 23.18 t/s, tg_3s = 24.87 t/s 1.52.604.362 I slot print_timing: id 1 | task 405 | n_gen = 454, tg = 23.22 t/s, tg_3s = 24.87 t/s 1.53.167.995 I slot print_timing: id 0 | task 561 | n_gen = 314, tg = 24.06 t/s, tg_3s = 24.87 t/s 1.55.019.716 I slot print_timing: id 2 | task 747 | n_gen = 175, tg = 24.81 t/s, tg_3s = 24.85 t/s 1.55.059.649 I slot print_timing: id 0 | task 561 | prompt eval time = 489.38 ms / 105 tokens ( 4.66 ms per token, 214.56 tokens per second) 1.55.059.652 I slot print_timing: id 0 | task 561 | eval time = 14899.82 ms / 361 tokens ( 41.39 ms per token, 24.16 tokens per second) 1.55.059.654 I slot print_timing: id 0 | task 561 | total time = 15389.19 ms / 466 tokens 1.55.059.655 I slot print_timing: id 0 | task 561 | graphs reused = 632 1.55.059.656 I slot print_timing: id 0 | task 561 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.059.732 I slot release: id 0 | task 561 | stop processing: n_tokens = 1436, truncated = 0 1.55.101.472 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.676 1.55.101.500 I slot launch_slot_: id 0 | task 926 | processing task, is_child = 0 1.55.522.516 I slot print_timing: id 3 | task 265 | n_gen = 650, tg = 23.03 t/s, tg_3s = 21.85 t/s 1.55.645.486 I slot print_timing: id 1 | task 405 | n_gen = 519, tg = 22.97 t/s, tg_3s = 21.37 t/s 1.56.498.557 I slot print_timing: id 2 | task 747 | prompt eval time = 477.75 ms / 80 tokens ( 5.97 ms per token, 167.45 tokens per second) 1.56.498.564 I slot print_timing: id 2 | task 747 | eval time = 8490.79 ms / 201 tokens ( 42.45 ms per token, 23.55 tokens per second) 1.56.498.565 I slot print_timing: id 2 | task 747 | total time = 8968.54 ms / 281 tokens 1.56.498.566 I slot print_timing: id 2 | task 747 | graphs reused = 654 1.56.498.567 I slot print_timing: id 2 | task 747 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.498.638 I slot release: id 2 | task 747 | stop processing: n_tokens = 1251, truncated = 0 1.56.556.929 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.776 1.56.556.954 I slot launch_slot_: id 2 | task 952 | processing task, is_child = 0 1.57.403.210 I slot print_timing: id 1 | task 405 | prompt eval time = 511.90 ms / 97 tokens ( 5.28 ms per token, 189.49 tokens per second) 1.57.403.217 I slot print_timing: id 1 | task 405 | eval time = 24304.63 ms / 550 tokens ( 44.27 ms per token, 22.59 tokens per second) 1.57.403.218 I slot print_timing: id 1 | task 405 | total time = 24816.53 ms / 647 tokens 1.57.403.219 I slot print_timing: id 1 | task 405 | graphs reused = 660 1.57.403.220 I slot print_timing: id 1 | task 405 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.403.289 I slot release: id 1 | task 405 | stop processing: n_tokens = 1617, truncated = 0 1.57.460.132 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.600 1.57.460.164 I slot launch_slot_: id 1 | task 963 | processing task, is_child = 0 1.58.532.519 I slot print_timing: id 3 | task 265 | n_gen = 700, tg = 22.41 t/s, tg_3s = 16.61 t/s 2.00.539.396 I slot print_timing: id 0 | task 926 | n_gen = 100, tg = 20.05 t/s, tg_3s = 20.25 t/s 2.01.542.099 I slot print_timing: id 2 | task 952 | n_gen = 100, tg = 22.39 t/s, tg_3s = 22.61 t/s 2.01.542.280 I slot print_timing: id 3 | task 265 | n_gen = 775, tg = 22.63 t/s, tg_3s = 24.92 t/s 2.01.943.326 I slot print_timing: id 1 | task 963 | n_gen = 100, tg = 24.88 t/s, tg_3s = 25.13 t/s 2.03.547.367 I slot print_timing: id 0 | task 926 | n_gen = 175, tg = 21.90 t/s, tg_3s = 24.93 t/s 2.04.552.206 I slot print_timing: id 2 | task 952 | n_gen = 175, tg = 23.41 t/s, tg_3s = 24.92 t/s 2.04.552.388 I slot print_timing: id 3 | task 265 | n_gen = 850, tg = 22.81 t/s, tg_3s = 24.92 t/s 2.04.954.601 I slot print_timing: id 1 | task 963 | n_gen = 175, tg = 24.89 t/s, tg_3s = 24.91 t/s 2.06.561.465 I slot print_timing: id 0 | task 926 | n_gen = 250, tg = 22.72 t/s, tg_3s = 24.88 t/s 2.06.843.695 I slot print_timing: id 1 | task 963 | prompt eval time = 503.92 ms / 92 tokens ( 5.48 ms per token, 182.57 tokens per second) 2.06.843.702 I slot print_timing: id 1 | task 963 | eval time = 8879.60 ms / 222 tokens ( 40.18 ms per token, 24.89 tokens per second) 2.06.843.703 I slot print_timing: id 1 | task 963 | total time = 9383.52 ms / 314 tokens 2.06.843.704 I slot print_timing: id 1 | task 963 | graphs reused = 879 2.06.843.705 I slot print_timing: id 1 | task 963 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.843.780 I slot release: id 1 | task 963 | stop processing: n_tokens = 1284, truncated = 0 2.06.901.363 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.756 2.06.901.392 I slot launch_slot_: id 1 | task 1188 | processing task, is_child = 0 2.07.563.048 I slot print_timing: id 2 | task 952 | n_gen = 240, tg = 22.89 t/s, tg_3s = 21.59 t/s 2.07.563.220 I slot print_timing: id 3 | task 265 | n_gen = 915, tg = 22.72 t/s, tg_3s = 21.59 t/s 2.08.689.716 I slot print_timing: id 0 | task 926 | prompt eval time = 500.77 ms / 110 tokens ( 4.55 ms per token, 219.66 tokens per second) 2.08.689.721 I slot print_timing: id 0 | task 926 | eval time = 13087.43 ms / 293 tokens ( 44.82 ms per token, 22.31 tokens per second) 2.08.689.722 I slot print_timing: id 0 | task 926 | total time = 13588.20 ms / 403 tokens 2.08.689.723 I slot print_timing: id 0 | task 926 | graphs reused = 911 2.08.689.724 I slot print_timing: id 0 | task 926 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.689.805 I slot release: id 0 | task 926 | stop processing: n_tokens = 1372, truncated = 0 2.08.731.604 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.708 2.08.731.638 I slot launch_slot_: id 0 | task 1225 | processing task, is_child = 0 2.10.593.040 I slot print_timing: id 2 | task 952 | n_gen = 307, tg = 22.71 t/s, tg_3s = 22.11 t/s 2.10.593.216 I slot print_timing: id 3 | task 265 | n_gen = 982, tg = 22.68 t/s, tg_3s = 22.11 t/s 2.11.739.818 I slot print_timing: id 1 | task 1188 | n_gen = 100, tg = 22.57 t/s, tg_3s = 22.80 t/s 2.12.348.603 I slot print_timing: id 3 | task 265 | prompt eval time = 7729.24 ms / 1056 tokens ( 7.32 ms per token, 136.62 tokens per second) 2.12.348.608 I slot print_timing: id 3 | task 265 | eval time = 45009.78 ms / 1024 tokens ( 44.00 ms per token, 22.73 tokens per second) 2.12.348.609 I slot print_timing: id 3 | task 265 | total time = 52739.03 ms / 2080 tokens 2.12.348.610 I slot print_timing: id 3 | task 265 | graphs reused = 988 2.12.348.610 I slot print_timing: id 3 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.348.689 I slot release: id 3 | task 265 | stop processing: n_tokens = 2079, truncated = 0 2.12.389.849 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.467 2.12.418.535 I slot launch_slot_: id 3 | task 1307 | processing task, is_child = 0 2.13.581.933 I slot print_timing: id 0 | task 1225 | n_gen = 100, tg = 22.32 t/s, tg_3s = 22.55 t/s 2.13.622.089 I slot print_timing: id 2 | task 952 | n_gen = 371, tg = 22.42 t/s, tg_3s = 21.13 t/s 2.14.775.414 I slot print_timing: id 1 | task 1188 | n_gen = 166, tg = 22.23 t/s, tg_3s = 21.74 t/s 2.15.451.541 I slot print_timing: id 1 | task 1188 | prompt eval time = 453.01 ms / 70 tokens ( 6.47 ms per token, 154.52 tokens per second) 2.15.451.548 I slot print_timing: id 1 | task 1188 | eval time = 8097.13 ms / 183 tokens ( 44.49 ms per token, 22.48 tokens per second) 2.15.451.549 I slot print_timing: id 1 | task 1188 | total time = 8550.14 ms / 253 tokens 2.15.451.550 I slot print_timing: id 1 | task 1188 | graphs reused = 1052 2.15.451.551 I slot print_timing: id 1 | task 1188 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.451.627 I slot release: id 1 | task 1188 | stop processing: n_tokens = 1223, truncated = 0 2.15.507.370 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.794 2.15.507.396 I slot launch_slot_: id 1 | task 1376 | processing task, is_child = 0 2.16.605.483 I slot print_timing: id 0 | task 1225 | n_gen = 165, tg = 21.99 t/s, tg_3s = 21.50 t/s 2.16.645.676 I slot print_timing: id 2 | task 952 | n_gen = 436, tg = 22.28 t/s, tg_3s = 21.50 t/s 2.17.283.648 I slot print_timing: id 3 | task 1307 | n_gen = 100, tg = 22.60 t/s, tg_3s = 22.83 t/s 2.17.881.166 I slot print_timing: id 2 | task 952 | prompt eval time = 562.64 ms / 136 tokens ( 4.14 ms per token, 241.72 tokens per second) 2.17.881.171 I slot print_timing: id 2 | task 952 | eval time = 20761.56 ms / 467 tokens ( 44.55 ms per token, 22.45 tokens per second) 2.17.881.172 I slot print_timing: id 2 | task 952 | total time = 21324.20 ms / 603 tokens 2.17.881.173 I slot print_timing: id 2 | task 952 | graphs reused = 1097 2.17.881.174 I slot print_timing: id 2 | task 952 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.881.250 I slot release: id 2 | task 952 | stop processing: n_tokens = 1573, truncated = 0 2.17.938.610 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.617 2.17.938.638 I slot launch_slot_: id 2 | task 1427 | processing task, is_child = 0 2.19.643.520 I slot print_timing: id 0 | task 1225 | n_gen = 229, tg = 21.72 t/s, tg_3s = 21.07 t/s 2.20.288.325 I slot print_timing: id 3 | task 1307 | n_gen = 163, tg = 21.94 t/s, tg_3s = 20.97 t/s 2.20.447.516 I slot print_timing: id 1 | task 1376 | n_gen = 100, tg = 22.24 t/s, tg_3s = 22.46 t/s 2.22.441.867 I slot print_timing: id 2 | task 1427 | n_gen = 100, tg = 24.98 t/s, tg_3s = 25.23 t/s 2.22.680.033 I slot print_timing: id 0 | task 1225 | n_gen = 305, tg = 22.46 t/s, tg_3s = 25.03 t/s 2.23.320.307 I slot print_timing: id 3 | task 1307 | n_gen = 239, tg = 22.85 t/s, tg_3s = 25.07 t/s 2.23.479.276 I slot print_timing: id 1 | task 1376 | n_gen = 176, tg = 23.38 t/s, tg_3s = 25.07 t/s 2.25.476.530 I slot print_timing: id 2 | task 1427 | n_gen = 176, tg = 25.01 t/s, tg_3s = 25.04 t/s 2.25.715.805 I slot print_timing: id 0 | task 1225 | n_gen = 381, tg = 22.93 t/s, tg_3s = 25.03 t/s 2.25.716.321 I slot print_timing: id 3 | task 1307 | prompt eval time = 484.50 ms / 82 tokens ( 5.91 ms per token, 169.25 tokens per second) 2.25.716.325 I slot print_timing: id 3 | task 1307 | eval time = 12813.28 ms / 299 tokens ( 43.00 ms per token, 23.26 tokens per second) 2.25.716.325 I slot print_timing: id 3 | task 1307 | total time = 13297.77 ms / 381 tokens 2.25.716.326 I slot print_timing: id 3 | task 1307 | graphs reused = 1276 2.25.716.327 I slot print_timing: id 3 | task 1307 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.716.402 I slot release: id 3 | task 1307 | stop processing: n_tokens = 1332, truncated = 0 2.25.757.239 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.729 2.25.757.265 I slot launch_slot_: id 3 | task 1612 | processing task, is_child = 0 2.26.496.759 I slot print_timing: id 1 | task 1376 | n_gen = 244, tg = 23.14 t/s, tg_3s = 22.54 t/s 2.27.825.573 I slot print_timing: id 0 | task 1225 | prompt eval time = 415.21 ms / 69 tokens ( 6.02 ms per token, 166.18 tokens per second) 2.27.825.580 I slot print_timing: id 0 | task 1225 | eval time = 18678.71 ms / 426 tokens ( 43.95 ms per token, 22.75 tokens per second) 2.27.825.581 I slot print_timing: id 0 | task 1225 | total time = 19093.93 ms / 495 tokens 2.27.825.582 I slot print_timing: id 0 | task 1225 | graphs reused = 1317 2.27.825.583 I slot print_timing: id 0 | task 1225 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.825.664 I slot release: id 0 | task 1225 | stop processing: n_tokens = 1465, truncated = 0 2.27.866.687 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.663 2.27.866.719 I slot launch_slot_: id 0 | task 1658 | processing task, is_child = 0 2.28.487.289 I slot print_timing: id 2 | task 1427 | n_gen = 234, tg = 23.28 t/s, tg_3s = 19.26 t/s 2.28.771.730 I slot print_timing: id 1 | task 1376 | prompt eval time = 487.91 ms / 88 tokens ( 5.54 ms per token, 180.36 tokens per second) 2.28.771.737 I slot print_timing: id 1 | task 1376 | eval time = 12776.42 ms / 291 tokens ( 44.06 ms per token, 22.70 tokens per second) 2.28.771.738 I slot print_timing: id 1 | task 1376 | total time = 13264.32 ms / 379 tokens 2.28.771.739 I slot print_timing: id 1 | task 1376 | graphs reused = 1328 2.28.771.740 I slot print_timing: id 1 | task 1376 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.771.828 I slot release: id 1 | task 1376 | stop processing: n_tokens = 1349, truncated = 0 2.28.829.406 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.720 2.28.829.435 I slot launch_slot_: id 1 | task 1673 | processing task, is_child = 0 2.30.864.478 I slot print_timing: id 3 | task 1612 | n_gen = 100, tg = 20.95 t/s, tg_3s = 21.16 t/s 2.31.500.755 I slot print_timing: id 2 | task 1427 | n_gen = 300, tg = 22.96 t/s, tg_3s = 21.90 t/s 2.32.655.032 I slot print_timing: id 0 | task 1658 | n_gen = 100, tg = 22.87 t/s, tg_3s = 23.10 t/s 2.33.213.629 I slot print_timing: id 1 | task 1673 | n_gen = 100, tg = 25.09 t/s, tg_3s = 25.34 t/s 2.33.492.850 I slot print_timing: id 3 | task 1612 | prompt eval time = 381.00 ms / 54 tokens ( 7.06 ms per token, 141.73 tokens per second) 2.33.492.858 I slot print_timing: id 3 | task 1612 | eval time = 7354.58 ms / 166 tokens ( 44.57 ms per token, 22.43 tokens per second) 2.33.492.859 I slot print_timing: id 3 | task 1612 | total time = 7735.58 ms / 220 tokens 2.33.492.859 I slot print_timing: id 3 | task 1612 | graphs reused = 1433 2.33.492.860 I slot print_timing: id 3 | task 1612 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.492.937 I slot release: id 3 | task 1612 | stop processing: n_tokens = 1190, truncated = 0 2.33.533.883 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.816 2.33.533.913 I slot launch_slot_: id 3 | task 1783 | processing task, is_child = 0 2.34.506.701 I slot print_timing: id 2 | task 1427 | n_gen = 368, tg = 22.90 t/s, tg_3s = 22.62 t/s 2.35.661.418 I slot print_timing: id 0 | task 1658 | n_gen = 168, tg = 22.77 t/s, tg_3s = 22.62 t/s 2.35.946.302 I slot print_timing: id 1 | task 1673 | prompt eval time = 437.70 ms / 66 tokens ( 6.63 ms per token, 150.79 tokens per second) 2.35.946.306 I slot print_timing: id 1 | task 1673 | eval time = 6679.16 ms / 161 tokens ( 41.74 ms per token, 23.96 tokens per second) 2.35.946.307 I slot print_timing: id 1 | task 1673 | total time = 7116.86 ms / 227 tokens 2.35.946.308 I slot print_timing: id 1 | task 1673 | graphs reused = 1482 2.35.946.309 I slot print_timing: id 1 | task 1673 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.946.375 I slot release: id 1 | task 1673 | stop processing: n_tokens = 1197, truncated = 0 2.36.003.112 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.811 2.36.003.141 I slot launch_slot_: id 1 | task 1838 | processing task, is_child = 0 2.36.551.182 I slot print_timing: id 0 | task 1658 | prompt eval time = 459.55 ms / 96 tokens ( 4.79 ms per token, 208.90 tokens per second) 2.36.551.185 I slot print_timing: id 0 | task 1658 | eval time = 8224.91 ms / 180 tokens ( 45.95 ms per token, 21.76 tokens per second) 2.36.551.186 I slot print_timing: id 0 | task 1658 | total time = 8684.45 ms / 276 tokens 2.36.551.186 I slot print_timing: id 0 | task 1658 | graphs reused = 1483 2.36.551.186 I slot print_timing: id 0 | task 1658 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.551.233 I slot release: id 0 | task 1658 | stop processing: n_tokens = 1246, truncated = 0 2.36.589.341 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.779 2.36.589.365 I slot launch_slot_: id 0 | task 1844 | processing task, is_child = 0 2.37.508.111 I slot print_timing: id 2 | task 1427 | n_gen = 425, tg = 22.28 t/s, tg_3s = 18.99 t/s 2.38.385.973 I slot print_timing: id 3 | task 1783 | prompt eval time = 366.65 ms / 51 tokens ( 7.19 ms per token, 139.10 tokens per second) 2.38.385.979 I slot print_timing: id 3 | task 1783 | eval time = 4485.40 ms / 95 tokens ( 47.72 ms per token, 20.96 tokens per second) 2.38.385.980 I slot print_timing: id 3 | task 1783 | total time = 4852.05 ms / 146 tokens 2.38.385.981 I slot print_timing: id 3 | task 1783 | graphs reused = 1518 2.38.385.982 I slot print_timing: id 3 | task 1783 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.386.049 I slot release: id 3 | task 1783 | stop processing: n_tokens = 1116, truncated = 0 2.38.427.196 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.870 2.38.427.221 I slot launch_slot_: id 3 | task 1883 | processing task, is_child = 0 2.40.531.490 I slot print_timing: id 2 | task 1427 | n_gen = 491, tg = 22.22 t/s, tg_3s = 21.83 t/s 2.41.131.506 I slot print_timing: id 1 | task 1838 | n_gen = 100, tg = 21.23 t/s, tg_3s = 21.45 t/s 2.41.331.666 I slot print_timing: id 0 | task 1844 | n_gen = 100, tg = 22.79 t/s, tg_3s = 23.02 t/s 2.41.411.528 I slot print_timing: id 0 | task 1844 | prompt eval time = 397.97 ms / 63 tokens ( 6.32 ms per token, 158.30 tokens per second) 2.41.411.535 I slot print_timing: id 0 | task 1844 | eval time = 4424.19 ms / 102 tokens ( 43.80 ms per token, 22.83 tokens per second) 2.41.411.536 I slot print_timing: id 0 | task 1844 | total time = 4822.16 ms / 165 tokens 2.41.411.537 I slot print_timing: id 0 | task 1844 | graphs reused = 1579 2.41.411.538 I slot print_timing: id 0 | task 1844 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.411.611 I slot release: id 0 | task 1844 | stop processing: n_tokens = 1135, truncated = 0 2.41.453.299 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.856 2.41.453.322 I slot launch_slot_: id 0 | task 1950 | processing task, is_child = 0 2.43.148.897 I slot print_timing: id 3 | task 1883 | n_gen = 100, tg = 23.22 t/s, tg_3s = 23.46 t/s 2.43.548.982 I slot print_timing: id 2 | task 1427 | n_gen = 559, tg = 22.26 t/s, tg_3s = 22.54 t/s 2.44.149.486 I slot print_timing: id 1 | task 1838 | n_gen = 168, tg = 21.74 t/s, tg_3s = 22.53 t/s 2.44.669.563 I slot print_timing: id 1 | task 1838 | prompt eval time = 466.18 ms / 70 tokens ( 6.66 ms per token, 150.16 tokens per second) 2.44.669.568 I slot print_timing: id 1 | task 1838 | eval time = 8200.23 ms / 181 tokens ( 45.56 ms per token, 21.95 tokens per second) 2.44.669.569 I slot print_timing: id 1 | task 1838 | total time = 8666.41 ms / 251 tokens 2.44.669.570 I slot print_timing: id 1 | task 1838 | graphs reused = 1650 2.44.669.571 I slot print_timing: id 1 | task 1838 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.669.645 I slot release: id 1 | task 1838 | stop processing: n_tokens = 1221, truncated = 0 2.44.726.943 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.795 2.44.726.972 I slot launch_slot_: id 1 | task 2025 | processing task, is_child = 0 2.46.161.825 I slot print_timing: id 0 | task 1950 | n_gen = 100, tg = 22.78 t/s, tg_3s = 23.01 t/s 2.46.162.345 I slot print_timing: id 3 | task 1883 | n_gen = 166, tg = 22.68 t/s, tg_3s = 21.90 t/s 2.46.560.787 I slot print_timing: id 2 | task 1427 | n_gen = 625, tg = 22.22 t/s, tg_3s = 21.91 t/s 2.48.204.699 I slot print_timing: id 0 | task 1950 | prompt eval time = 363.07 ms / 56 tokens ( 6.48 ms per token, 154.24 tokens per second) 2.48.204.707 I slot print_timing: id 0 | task 1950 | eval time = 6388.30 ms / 151 tokens ( 42.59 ms per token, 23.48 tokens per second) 2.48.204.708 I slot print_timing: id 0 | task 1950 | total time = 6751.37 ms / 207 tokens 2.48.204.708 I slot print_timing: id 0 | task 1950 | graphs reused = 1725 2.48.204.709 I slot print_timing: id 0 | task 1950 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.204.776 I slot release: id 0 | task 1950 | stop processing: n_tokens = 1177, truncated = 0 2.48.246.262 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.825 2.48.246.285 I slot launch_slot_: id 0 | task 2105 | processing task, is_child = 0 2.49.188.541 I slot print_timing: id 3 | task 1883 | n_gen = 234, tg = 22.62 t/s, tg_3s = 22.47 t/s 2.49.429.381 I slot print_timing: id 1 | task 2025 | n_gen = 100, tg = 23.17 t/s, tg_3s = 23.40 t/s 2.49.588.800 I slot print_timing: id 2 | task 1427 | n_gen = 693, tg = 22.24 t/s, tg_3s = 22.46 t/s 2.50.316.661 I slot print_timing: id 2 | task 1427 | prompt eval time = 539.43 ms / 115 tokens ( 4.69 ms per token, 213.19 tokens per second) 2.50.316.667 I slot print_timing: id 2 | task 1427 | eval time = 31838.58 ms / 711 tokens ( 44.84 ms per token, 22.30 tokens per second) 2.50.316.669 I slot print_timing: id 2 | task 1427 | total time = 32378.01 ms / 826 tokens 2.50.316.669 I slot print_timing: id 2 | task 1427 | graphs reused = 1766 2.50.316.670 I slot print_timing: id 2 | task 1427 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.316.737 I slot release: id 2 | task 1427 | stop processing: n_tokens = 1795, truncated = 0 2.50.374.147 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.541 2.50.374.176 I slot launch_slot_: id 2 | task 2151 | processing task, is_child = 0 2.52.204.906 I slot print_timing: id 3 | task 1883 | n_gen = 298, tg = 22.30 t/s, tg_3s = 21.22 t/s 2.52.443.890 I slot print_timing: id 1 | task 2025 | n_gen = 164, tg = 22.37 t/s, tg_3s = 21.23 t/s 2.52.642.969 I slot print_timing: id 1 | task 2025 | prompt eval time = 429.41 ms / 63 tokens ( 6.82 ms per token, 146.71 tokens per second) 2.52.642.976 I slot print_timing: id 1 | task 2025 | eval time = 7486.58 ms / 169 tokens ( 44.56 ms per token, 22.44 tokens per second) 2.52.642.977 I slot print_timing: id 1 | task 2025 | total time = 7915.99 ms / 232 tokens 2.52.642.978 I slot print_timing: id 1 | task 2025 | graphs reused = 1809 2.52.642.979 I slot print_timing: id 1 | task 2025 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.643.042 I slot release: id 1 | task 2025 | stop processing: n_tokens = 1202, truncated = 0 2.52.699.853 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.808 2.52.699.879 I slot launch_slot_: id 1 | task 2199 | processing task, is_child = 0 2.53.491.007 I slot print_timing: id 0 | task 2105 | n_gen = 100, tg = 20.31 t/s, tg_3s = 20.52 t/s 2.53.770.532 I slot print_timing: id 3 | task 1883 | prompt eval time = 458.56 ms / 98 tokens ( 4.68 ms per token, 213.71 tokens per second) 2.53.770.539 I slot print_timing: id 3 | task 1883 | eval time = 14884.74 ms / 326 tokens ( 45.80 ms per token, 21.83 tokens per second) 2.53.770.540 I slot print_timing: id 3 | task 1883 | total time = 15343.30 ms / 424 tokens 2.53.770.541 I slot print_timing: id 3 | task 1883 | graphs reused = 1822 2.53.770.542 I slot print_timing: id 3 | task 1883 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.770.616 I slot release: id 3 | task 1883 | stop processing: n_tokens = 1394, truncated = 0 2.53.811.158 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.697 2.53.811.183 I slot launch_slot_: id 3 | task 2217 | processing task, is_child = 0 2.55.716.386 I slot print_timing: id 2 | task 2151 | n_gen = 100, tg = 20.47 t/s, tg_3s = 20.67 t/s 2.56.073.507 I slot print_timing: id 0 | task 2105 | prompt eval time = 370.66 ms / 55 tokens ( 6.74 ms per token, 148.38 tokens per second) 2.56.073.514 I slot print_timing: id 0 | task 2105 | eval time = 7456.55 ms / 154 tokens ( 48.74 ms per token, 20.52 tokens per second) 2.56.073.515 I slot print_timing: id 0 | task 2105 | total time = 7827.21 ms / 209 tokens 2.56.073.516 I slot print_timing: id 0 | task 2105 | graphs reused = 1865 2.56.073.517 I slot print_timing: id 0 | task 2105 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.073.590 I slot release: id 0 | task 2105 | stop processing: n_tokens = 1179, truncated = 0 2.56.114.765 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.824 2.56.114.792 I slot launch_slot_: id 0 | task 2265 | processing task, is_child = 0 2.57.898.379 I slot print_timing: id 1 | task 2199 | n_gen = 100, tg = 21.10 t/s, tg_3s = 21.31 t/s 2.58.576.721 I slot print_timing: id 3 | task 2217 | n_gen = 100, tg = 23.25 t/s, tg_3s = 23.48 t/s 2.58.736.084 I slot print_timing: id 2 | task 2151 | n_gen = 168, tg = 21.25 t/s, tg_3s = 22.52 t/s 3.00.448.540 I slot print_timing: id 0 | task 2265 | n_gen = 100, tg = 25.05 t/s, tg_3s = 25.30 t/s 3.00.933.017 I slot print_timing: id 1 | task 2199 | n_gen = 176, tg = 22.65 t/s, tg_3s = 25.04 t/s 3.01.610.189 I slot print_timing: id 3 | task 2217 | n_gen = 176, tg = 24.00 t/s, tg_3s = 25.05 t/s 3.01.649.715 I slot print_timing: id 0 | task 2265 | prompt eval time = 381.47 ms / 63 tokens ( 6.06 ms per token, 165.15 tokens per second) 3.01.649.723 I slot print_timing: id 0 | task 2265 | eval time = 5153.44 ms / 130 tokens ( 39.95 ms per token, 25.03 tokens per second) 3.01.649.724 I slot print_timing: id 0 | task 2265 | total time = 5534.92 ms / 193 tokens 3.01.649.725 I slot print_timing: id 0 | task 2265 | graphs reused = 1993 3.01.649.726 I slot print_timing: id 0 | task 2265 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.649.805 I slot release: id 0 | task 2265 | stop processing: n_tokens = 1163, truncated = 0 3.01.691.412 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.835 3.01.691.437 I slot launch_slot_: id 0 | task 2398 | processing task, is_child = 0 3.01.982.728 I slot print_timing: id 2 | task 2151 | n_gen = 243, tg = 21.79 t/s, tg_3s = 23.10 t/s 3.03.945.882 I slot print_timing: id 1 | task 2199 | n_gen = 244, tg = 22.63 t/s, tg_3s = 22.57 t/s 3.04.624.099 I slot print_timing: id 3 | task 2217 | n_gen = 244, tg = 23.58 t/s, tg_3s = 22.56 t/s 3.04.983.729 I slot print_timing: id 2 | task 2151 | n_gen = 317, tg = 22.40 t/s, tg_3s = 24.66 t/s 3.06.021.497 I slot print_timing: id 0 | task 2398 | n_gen = 100, tg = 24.99 t/s, tg_3s = 25.25 t/s 3.06.460.981 I slot print_timing: id 0 | task 2398 | prompt eval time = 369.09 ms / 57 tokens ( 6.48 ms per token, 154.43 tokens per second) 3.06.460.990 I slot print_timing: id 0 | task 2398 | eval time = 4400.44 ms / 111 tokens ( 40.00 ms per token, 25.00 tokens per second) 3.06.460.991 I slot print_timing: id 0 | task 2398 | total time = 4769.53 ms / 168 tokens 3.06.460.992 I slot print_timing: id 0 | task 2398 | graphs reused = 2103 3.06.460.992 I slot print_timing: id 0 | task 2398 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.461.066 I slot release: id 0 | task 2398 | stop processing: n_tokens = 1138, truncated = 0 3.06.502.470 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.853 3.06.502.493 I slot launch_slot_: id 0 | task 2512 | processing task, is_child = 0 3.06.968.386 I slot print_timing: id 1 | task 2199 | n_gen = 312, tg = 22.60 t/s, tg_3s = 22.50 t/s 3.07.656.358 I slot print_timing: id 3 | task 2217 | n_gen = 312, tg = 23.32 t/s, tg_3s = 22.43 t/s 3.08.016.536 I slot print_timing: id 2 | task 2151 | n_gen = 385, tg = 22.41 t/s, tg_3s = 22.42 t/s 3.09.985.388 I slot print_timing: id 1 | task 2199 | n_gen = 387, tg = 23.01 t/s, tg_3s = 24.86 t/s 3.10.665.880 I slot print_timing: id 3 | task 2217 | n_gen = 387, tg = 23.61 t/s, tg_3s = 24.92 t/s 3.10.866.137 I slot print_timing: id 0 | task 2512 | n_gen = 100, tg = 24.87 t/s, tg_3s = 25.12 t/s 3.11.026.942 I slot print_timing: id 2 | task 2151 | n_gen = 460, tg = 22.78 t/s, tg_3s = 24.91 t/s 3.11.594.284 I slot print_timing: id 3 | task 2217 | prompt eval time = 506.65 ms / 114 tokens ( 4.44 ms per token, 225.01 tokens per second) 3.11.594.292 I slot print_timing: id 3 | task 2217 | eval time = 17276.44 ms / 410 tokens ( 42.24 ms per token, 23.67 tokens per second) 3.11.594.293 I slot print_timing: id 3 | task 2217 | total time = 17783.09 ms / 524 tokens 3.11.594.294 I slot print_timing: id 3 | task 2217 | graphs reused = 2218 3.11.594.295 I slot print_timing: id 3 | task 2217 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.594.384 I slot release: id 3 | task 2217 | stop processing: n_tokens = 1494, truncated = 0 3.11.635.347 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.650 3.11.635.372 I slot launch_slot_: id 3 | task 2633 | processing task, is_child = 0 3.12.995.918 I slot print_timing: id 1 | task 2199 | n_gen = 453, tg = 22.84 t/s, tg_3s = 21.92 t/s 3.13.874.508 I slot print_timing: id 0 | task 2512 | n_gen = 166, tg = 23.61 t/s, tg_3s = 21.94 t/s 3.14.035.009 I slot print_timing: id 2 | task 2151 | n_gen = 526, tg = 22.67 t/s, tg_3s = 21.94 t/s 3.15.596.141 I slot print_timing: id 0 | task 2512 | prompt eval time = 383.40 ms / 61 tokens ( 6.29 ms per token, 159.10 tokens per second) 3.15.596.149 I slot print_timing: id 0 | task 2512 | eval time = 8710.23 ms / 209 tokens ( 41.88 ms per token, 23.88 tokens per second) 3.15.596.150 I slot print_timing: id 0 | task 2512 | total time = 9093.63 ms / 270 tokens 3.15.596.151 I slot print_timing: id 0 | task 2512 | graphs reused = 2305 3.15.596.152 I slot print_timing: id 0 | task 2512 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.596.245 I slot release: id 0 | task 2512 | stop processing: n_tokens = 1240, truncated = 0 3.15.637.649 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.783 3.15.637.674 I slot launch_slot_: id 0 | task 2725 | processing task, is_child = 0 3.16.068.660 I slot print_timing: id 1 | task 2199 | n_gen = 521, tg = 22.74 t/s, tg_3s = 22.13 t/s 3.16.389.792 I slot print_timing: id 3 | task 2633 | n_gen = 100, tg = 22.92 t/s, tg_3s = 23.15 t/s 3.17.073.161 I slot print_timing: id 2 | task 2151 | n_gen = 593, tg = 22.60 t/s, tg_3s = 22.05 t/s 3.19.078.112 I slot print_timing: id 1 | task 2199 | n_gen = 596, tg = 23.00 t/s, tg_3s = 24.92 t/s 3.19.399.383 I slot print_timing: id 3 | task 2633 | n_gen = 175, tg = 23.74 t/s, tg_3s = 24.92 t/s 3.20.041.063 I slot print_timing: id 0 | task 2725 | n_gen = 100, tg = 24.92 t/s, tg_3s = 25.17 t/s 3.20.081.555 I slot print_timing: id 2 | task 2151 | n_gen = 668, tg = 22.84 t/s, tg_3s = 24.93 t/s 3.20.562.660 I slot print_timing: id 3 | task 2633 | prompt eval time = 434.35 ms / 73 tokens ( 5.95 ms per token, 168.07 tokens per second) 3.20.562.666 I slot print_timing: id 3 | task 2633 | eval time = 8492.92 ms / 204 tokens ( 41.84 ms per token, 23.90 tokens per second) 3.20.562.667 I slot print_timing: id 3 | task 2633 | total time = 8927.28 ms / 277 tokens 3.20.562.668 I slot print_timing: id 3 | task 2633 | graphs reused = 2417 3.20.562.669 I slot print_timing: id 3 | task 2633 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.562.745 I slot release: id 3 | task 2633 | stop processing: n_tokens = 1247, truncated = 0 3.20.603.938 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.779 3.20.603.969 I slot launch_slot_: id 3 | task 2841 | processing task, is_child = 0 3.22.096.826 I slot print_timing: id 1 | task 2199 | n_gen = 662, tg = 22.88 t/s, tg_3s = 21.86 t/s 3.23.065.666 I slot print_timing: id 0 | task 2725 | n_gen = 166, tg = 23.58 t/s, tg_3s = 21.82 t/s 3.23.105.801 I slot print_timing: id 2 | task 2151 | n_gen = 734, tg = 22.75 t/s, tg_3s = 21.82 t/s 3.25.032.365 I slot print_timing: id 3 | task 2841 | n_gen = 100, tg = 24.84 t/s, tg_3s = 25.09 t/s 3.25.112.617 I slot print_timing: id 1 | task 2199 | n_gen = 737, tg = 23.07 t/s, tg_3s = 24.87 t/s 3.26.078.666 I slot print_timing: id 0 | task 2725 | n_gen = 241, tg = 23.98 t/s, tg_3s = 24.89 t/s 3.26.119.173 I slot print_timing: id 2 | task 2151 | n_gen = 809, tg = 22.93 t/s, tg_3s = 24.89 t/s 3.27.810.590 I slot print_timing: id 0 | task 2725 | prompt eval time = 430.90 ms / 79 tokens ( 5.45 ms per token, 183.34 tokens per second) 3.27.810.599 I slot print_timing: id 0 | task 2725 | eval time = 11742.01 ms / 284 tokens ( 41.49 ms per token, 24.10 tokens per second) 3.27.810.600 I slot print_timing: id 0 | task 2725 | total time = 12172.91 ms / 363 tokens 3.27.810.601 I slot print_timing: id 0 | task 2725 | graphs reused = 2583 3.27.810.601 I slot print_timing: id 0 | task 2725 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.810.676 I slot release: id 0 | task 2725 | stop processing: n_tokens = 1333, truncated = 0 3.27.852.558 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.728 3.27.852.585 I slot launch_slot_: id 0 | task 3013 | processing task, is_child = 0 3.28.160.242 I slot print_timing: id 1 | task 2199 | n_gen = 806, tg = 23.03 t/s, tg_3s = 22.64 t/s 3.28.160.469 I slot print_timing: id 3 | task 2841 | n_gen = 171, tg = 23.90 t/s, tg_3s = 22.70 t/s 3.29.124.899 I slot print_timing: id 2 | task 2151 | n_gen = 876, tg = 22.88 t/s, tg_3s = 22.29 t/s 3.29.647.947 I slot print_timing: id 3 | task 2841 | prompt eval time = 442.52 ms / 90 tokens ( 4.92 ms per token, 203.38 tokens per second) 3.29.647.955 I slot print_timing: id 3 | task 2841 | eval time = 8601.45 ms / 207 tokens ( 41.75 ms per token, 23.95 tokens per second) 3.29.647.956 I slot print_timing: id 3 | task 2841 | total time = 9043.97 ms / 297 tokens 3.29.647.957 I slot print_timing: id 3 | task 2841 | graphs reused = 2618 3.29.647.958 I slot print_timing: id 3 | task 2841 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.648.046 I slot release: id 3 | task 2841 | stop processing: n_tokens = 1267, truncated = 0 3.29.689.374 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.766 3.29.689.400 I slot launch_slot_: id 3 | task 3052 | processing task, is_child = 0 3.31.199.339 I slot print_timing: id 1 | task 2199 | n_gen = 871, tg = 22.90 t/s, tg_3s = 21.39 t/s 3.32.164.021 I slot print_timing: id 2 | task 2151 | n_gen = 942, tg = 22.79 t/s, tg_3s = 21.72 t/s 3.32.605.819 I slot print_timing: id 0 | task 3013 | n_gen = 100, tg = 22.67 t/s, tg_3s = 22.90 t/s 3.34.147.007 I slot print_timing: id 3 | task 3052 | n_gen = 100, tg = 24.72 t/s, tg_3s = 24.97 t/s 3.34.227.420 I slot print_timing: id 1 | task 2199 | n_gen = 946, tg = 23.04 t/s, tg_3s = 24.77 t/s 3.35.201.672 I slot print_timing: id 2 | task 2151 | n_gen = 1017, tg = 22.92 t/s, tg_3s = 24.69 t/s 3.35.486.260 I slot print_timing: id 2 | task 2151 | prompt eval time = 504.76 ms / 100 tokens ( 5.05 ms per token, 198.11 tokens per second) 3.35.486.268 I slot print_timing: id 2 | task 2151 | eval time = 44607.31 ms / 1024 tokens ( 43.60 ms per token, 22.93 tokens per second) 3.35.486.269 I slot print_timing: id 2 | task 2151 | total time = 45112.08 ms / 1124 tokens 3.35.486.270 I slot print_timing: id 2 | task 2151 | graphs reused = 2748 3.35.486.271 I slot print_timing: id 2 | task 2151 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.486.344 I slot release: id 2 | task 2151 | stop processing: n_tokens = 2092, truncated = 0 3.35.543.969 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.464 3.35.576.274 I slot launch_slot_: id 2 | task 3188 | processing task, is_child = 0 3.36.011.238 I slot print_timing: id 0 | task 3013 | n_gen = 173, tg = 22.13 t/s, tg_3s = 21.44 t/s 3.37.163.221 I slot print_timing: id 3 | task 3052 | n_gen = 162, tg = 22.93 t/s, tg_3s = 20.56 t/s 3.37.243.870 I slot print_timing: id 1 | task 2199 | n_gen = 1008, tg = 22.87 t/s, tg_3s = 20.55 t/s 3.37.891.934 I slot print_timing: id 1 | task 2199 | prompt eval time = 506.58 ms / 100 tokens ( 5.07 ms per token, 197.40 tokens per second) 3.37.891.942 I slot print_timing: id 1 | task 2199 | eval time = 44685.47 ms / 1024 tokens ( 43.68 ms per token, 22.89 tokens per second) 3.37.891.943 I slot print_timing: id 1 | task 2199 | total time = 45192.05 ms / 1124 tokens 3.37.891.944 I slot print_timing: id 1 | task 2199 | graphs reused = 2791 3.37.891.944 I slot print_timing: id 1 | task 2199 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.892.015 I slot release: id 1 | task 2199 | stop processing: n_tokens = 2094, truncated = 0 3.37.949.308 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.464 3.37.978.084 I slot launch_slot_: id 1 | task 3236 | processing task, is_child = 0 3.39.011.876 I slot print_timing: id 0 | task 3013 | n_gen = 234, tg = 21.63 t/s, tg_3s = 20.33 t/s 3.40.175.999 I slot print_timing: id 3 | task 3052 | n_gen = 225, tg = 22.32 t/s, tg_3s = 20.91 t/s 3.40.416.002 I slot print_timing: id 3 | task 3052 | prompt eval time = 452.91 ms / 80 tokens ( 5.66 ms per token, 176.64 tokens per second) 3.40.416.008 I slot print_timing: id 3 | task 3052 | eval time = 10273.68 ms / 231 tokens ( 44.67 ms per token, 22.39 tokens per second) 3.40.416.009 I slot print_timing: id 3 | task 3052 | total time = 10726.59 ms / 311 tokens 3.40.416.009 I slot print_timing: id 3 | task 3052 | graphs reused = 2837 3.40.416.010 I slot print_timing: id 3 | task 3052 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.416.095 I slot release: id 3 | task 3052 | stop processing: n_tokens = 1281, truncated = 0 3.40.457.020 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.758 3.40.457.044 I slot launch_slot_: id 3 | task 3288 | processing task, is_child = 0 3.40.943.679 I slot print_timing: id 2 | task 3188 | n_gen = 100, tg = 20.46 t/s, tg_3s = 20.67 t/s 3.42.026.961 I slot print_timing: id 0 | task 3013 | n_gen = 300, tg = 21.69 t/s, tg_3s = 21.89 t/s 3.42.824.850 I slot print_timing: id 1 | task 3236 | n_gen = 100, tg = 22.83 t/s, tg_3s = 23.06 t/s 3.43.982.059 I slot print_timing: id 2 | task 3188 | n_gen = 176, tg = 22.22 t/s, tg_3s = 25.01 t/s 3.44.860.913 I slot print_timing: id 3 | task 3288 | n_gen = 100, tg = 25.00 t/s, tg_3s = 25.25 t/s 3.45.060.025 I slot print_timing: id 0 | task 3013 | n_gen = 376, tg = 22.29 t/s, tg_3s = 25.06 t/s 3.45.858.295 I slot print_timing: id 1 | task 3236 | n_gen = 176, tg = 23.74 t/s, tg_3s = 25.05 t/s 3.47.018.015 I slot print_timing: id 2 | task 3188 | n_gen = 252, tg = 23.00 t/s, tg_3s = 25.03 t/s 3.47.218.247 I slot print_timing: id 3 | task 3288 | prompt eval time = 443.97 ms / 83 tokens ( 5.35 ms per token, 186.95 tokens per second) 3.47.218.254 I slot print_timing: id 3 | task 3288 | eval time = 6317.23 ms / 159 tokens ( 39.98 ms per token, 25.01 tokens per second) 3.47.218.256 I slot print_timing: id 3 | task 3288 | total time = 6761.19 ms / 242 tokens 3.47.218.257 I slot print_timing: id 3 | task 3288 | graphs reused = 2994 3.47.218.258 I slot print_timing: id 3 | task 3288 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.218.327 I slot release: id 3 | task 3288 | stop processing: n_tokens = 1212, truncated = 0 3.47.259.515 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.801 3.47.259.539 I slot launch_slot_: id 3 | task 3450 | processing task, is_child = 0 3.48.082.396 I slot print_timing: id 0 | task 3013 | n_gen = 442, tg = 22.22 t/s, tg_3s = 21.84 t/s 3.48.896.010 I slot print_timing: id 1 | task 3236 | n_gen = 242, tg = 23.15 t/s, tg_3s = 21.73 t/s 3.50.056.102 I slot print_timing: id 2 | task 3188 | n_gen = 318, tg = 22.72 t/s, tg_3s = 21.72 t/s 3.51.102.748 I slot print_timing: id 0 | task 3013 | n_gen = 517, tg = 22.57 t/s, tg_3s = 24.83 t/s 3.51.704.286 I slot print_timing: id 3 | task 3450 | n_gen = 100, tg = 24.88 t/s, tg_3s = 25.13 t/s 3.51.904.320 I slot print_timing: id 1 | task 3236 | n_gen = 317, tg = 23.55 t/s, tg_3s = 24.93 t/s 3.53.067.664 I slot print_timing: id 2 | task 3188 | n_gen = 393, tg = 23.11 t/s, tg_3s = 24.90 t/s 3.54.112.863 I slot print_timing: id 0 | task 3013 | n_gen = 592, tg = 22.84 t/s, tg_3s = 24.92 t/s 3.54.715.547 I slot print_timing: id 3 | task 3450 | n_gen = 175, tg = 24.89 t/s, tg_3s = 24.91 t/s 3.54.916.717 I slot print_timing: id 1 | task 3236 | n_gen = 392, tg = 23.80 t/s, tg_3s = 24.90 t/s 3.56.084.881 I slot print_timing: id 2 | task 3188 | n_gen = 468, tg = 23.37 t/s, tg_3s = 24.86 t/s 3.57.130.297 I slot print_timing: id 0 | task 3013 | n_gen = 667, tg = 23.05 t/s, tg_3s = 24.86 t/s 3.57.735.095 I slot print_timing: id 3 | task 3450 | n_gen = 250, tg = 24.87 t/s, tg_3s = 24.84 t/s 3.57.936.524 I slot print_timing: id 1 | task 3236 | n_gen = 467, tg = 23.96 t/s, tg_3s = 24.84 t/s 3.58.906.143 I slot print_timing: id 2 | task 3188 | prompt eval time = 529.77 ms / 116 tokens ( 4.57 ms per token, 218.96 tokens per second) 3.58.906.148 I slot print_timing: id 2 | task 3188 | eval time = 22800.09 ms / 538 tokens ( 42.46 ms per token, 23.55 tokens per second) 3.58.906.150 I slot print_timing: id 2 | task 3188 | total time = 23329.85 ms / 654 tokens 3.58.906.151 I slot print_timing: id 2 | task 3188 | graphs reused = 3269 3.58.906.152 I slot print_timing: id 2 | task 3188 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.906.228 I slot release: id 2 | task 3188 | stop processing: n_tokens = 1621, truncated = 0 3.58.964.429 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.599 3.58.964.460 I slot launch_slot_: id 2 | task 3732 | processing task, is_child = 0 4.00.153.314 I slot print_timing: id 0 | task 3013 | n_gen = 730, tg = 22.84 t/s, tg_3s = 20.84 t/s 4.00.756.701 I slot print_timing: id 3 | task 3450 | n_gen = 313, tg = 23.94 t/s, tg_3s = 20.85 t/s 4.00.957.371 I slot print_timing: id 1 | task 3236 | n_gen = 530, tg = 23.54 t/s, tg_3s = 20.86 t/s 4.03.176.929 I slot print_timing: id 0 | task 3013 | n_gen = 805, tg = 23.01 t/s, tg_3s = 24.80 t/s 4.03.500.676 I slot print_timing: id 2 | task 3732 | n_gen = 100, tg = 24.76 t/s, tg_3s = 25.01 t/s 4.03.782.874 I slot print_timing: id 3 | task 3450 | n_gen = 388, tg = 24.10 t/s, tg_3s = 24.78 t/s 4.03.984.519 I slot print_timing: id 1 | task 3236 | n_gen = 605, tg = 23.69 t/s, tg_3s = 24.78 t/s 4.06.201.207 I slot print_timing: id 0 | task 3013 | n_gen = 880, tg = 23.15 t/s, tg_3s = 24.80 t/s 4.06.524.167 I slot print_timing: id 2 | task 3732 | n_gen = 175, tg = 24.78 t/s, tg_3s = 24.81 t/s 4.06.766.390 I slot print_timing: id 1 | task 3236 | prompt eval time = 509.59 ms / 100 tokens ( 5.10 ms per token, 196.24 tokens per second) 4.06.766.395 I slot print_timing: id 1 | task 3236 | eval time = 28278.70 ms / 674 tokens ( 42.02 ms per token, 23.80 tokens per second) 4.06.766.396 I slot print_timing: id 1 | task 3236 | total time = 28788.29 ms / 774 tokens 4.06.766.396 I slot print_timing: id 1 | task 3236 | graphs reused = 3447 4.06.766.397 I slot print_timing: id 1 | task 3236 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.766.473 I slot release: id 1 | task 3236 | stop processing: n_tokens = 1743, truncated = 0 4.06.824.162 I slot print_timing: id 3 | task 3450 | n_gen = 463, tg = 24.19 t/s, tg_3s = 24.66 t/s 4.06.824.173 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.557 4.06.824.199 I slot launch_slot_: id 1 | task 3916 | processing task, is_child = 0 4.09.237.042 I slot print_timing: id 0 | task 3013 | n_gen = 946, tg = 23.05 t/s, tg_3s = 21.74 t/s 4.09.560.045 I slot print_timing: id 2 | task 3732 | n_gen = 241, tg = 23.86 t/s, tg_3s = 21.74 t/s 4.09.842.130 I slot print_timing: id 3 | task 3450 | n_gen = 529, tg = 23.87 t/s, tg_3s = 21.87 t/s 4.10.850.513 I slot print_timing: id 2 | task 3732 | prompt eval time = 537.86 ms / 106 tokens ( 5.07 ms per token, 197.08 tokens per second) 4.10.850.521 I slot print_timing: id 2 | task 3732 | eval time = 11348.19 ms / 273 tokens ( 41.72 ms per token, 23.97 tokens per second) 4.10.850.523 I slot print_timing: id 2 | task 3732 | total time = 11886.05 ms / 379 tokens 4.10.850.524 I slot print_timing: id 2 | task 3732 | graphs reused = 3535 4.10.850.524 I slot print_timing: id 2 | task 3732 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.850.598 I slot release: id 2 | task 3732 | stop processing: n_tokens = 1349, truncated = 0 4.10.908.939 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.720 4.10.908.967 I slot launch_slot_: id 2 | task 4009 | processing task, is_child = 0 4.11.655.484 I slot print_timing: id 1 | task 3916 | n_gen = 100, tg = 22.49 t/s, tg_3s = 22.72 t/s 4.12.260.263 I slot print_timing: id 0 | task 3013 | n_gen = 1011, tg = 22.94 t/s, tg_3s = 21.50 t/s 4.12.793.307 I slot print_timing: id 0 | task 3013 | prompt eval time = 386.40 ms / 62 tokens ( 6.23 ms per token, 160.45 tokens per second) 4.12.793.313 I slot print_timing: id 0 | task 3013 | eval time = 44554.31 ms / 1024 tokens ( 43.55 ms per token, 22.96 tokens per second) 4.12.793.314 I slot print_timing: id 0 | task 3013 | total time = 44940.71 ms / 1086 tokens 4.12.793.314 I slot print_timing: id 0 | task 3013 | graphs reused = 3568 4.12.793.315 I slot print_timing: id 0 | task 3013 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.793.390 I slot release: id 0 | task 3013 | stop processing: n_tokens = 2056, truncated = 0 4.12.834.748 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.472 4.12.865.910 I slot launch_slot_: id 0 | task 4048 | processing task, is_child = 0 4.13.187.096 I slot print_timing: id 3 | task 3450 | n_gen = 594, tg = 23.29 t/s, tg_3s = 19.43 t/s 4.14.670.264 I slot print_timing: id 1 | task 3916 | n_gen = 166, tg = 22.25 t/s, tg_3s = 21.89 t/s 4.15.269.289 I slot print_timing: id 1 | task 3916 | prompt eval time = 430.19 ms / 66 tokens ( 6.52 ms per token, 153.42 tokens per second) 4.15.269.296 I slot print_timing: id 1 | task 3916 | eval time = 8014.89 ms / 181 tokens ( 44.53 ms per token, 22.46 tokens per second) 4.15.269.296 I slot print_timing: id 1 | task 3916 | total time = 8445.08 ms / 247 tokens 4.15.269.297 I slot print_timing: id 1 | task 3916 | graphs reused = 3618 4.15.269.298 I slot print_timing: id 1 | task 3916 | graph reallocs = 0 / 0 (same size) / (changed size) 4.15.269.365 I slot release: id 1 | task 3916 | stop processing: n_tokens = 1215, truncated = 0 4.15.325.452 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.799 4.15.325.477 I slot launch_slot_: id 1 | task 4102 | processing task, is_child = 0 4.16.102.218 I slot print_timing: id 2 | task 4009 | n_gen = 100, tg = 20.90 t/s, tg_3s = 21.12 t/s 4.16.222.246 I slot print_timing: id 3 | task 3450 | n_gen = 659, tg = 23.09 t/s, tg_3s = 21.42 t/s 4.17.622.485 I slot print_timing: id 0 | task 4048 | n_gen = 100, tg = 22.72 t/s, tg_3s = 22.95 t/s 4.17.903.196 I slot print_timing: id 2 | task 4009 | prompt eval time = 457.42 ms / 70 tokens ( 6.53 ms per token, 153.03 tokens per second) 4.17.903.203 I slot print_timing: id 2 | task 4009 | eval time = 6536.80 ms / 145 tokens ( 45.39 ms per token, 22.03 tokens per second) 4.17.903.204 I slot print_timing: id 2 | task 4009 | total time = 6994.22 ms / 215 tokens 4.17.903.204 I slot print_timing: id 2 | task 4009 | graphs reused = 3670 4.17.903.205 I slot print_timing: id 2 | task 4009 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.903.273 I slot release: id 2 | task 4009 | stop processing: n_tokens = 1185, truncated = 0 4.17.960.925 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.819 4.17.960.951 I slot launch_slot_: id 2 | task 4159 | processing task, is_child = 0 4.19.235.457 I slot print_timing: id 3 | task 3450 | n_gen = 724, tg = 22.94 t/s, tg_3s = 21.57 t/s 4.20.162.238 I slot print_timing: id 1 | task 4102 | n_gen = 100, tg = 22.56 t/s, tg_3s = 22.79 t/s 4.20.641.957 I slot print_timing: id 0 | task 4048 | n_gen = 165, tg = 22.23 t/s, tg_3s = 21.53 t/s 4.21.925.023 I slot print_timing: id 1 | task 4102 | prompt eval time = 448.32 ms / 69 tokens ( 6.50 ms per token, 153.91 tokens per second) 4.21.925.030 I slot print_timing: id 1 | task 4102 | eval time = 6151.21 ms / 144 tokens ( 43.02 ms per token, 23.25 tokens per second) 4.21.925.031 I slot print_timing: id 1 | task 4102 | total time = 6599.53 ms / 213 tokens 4.21.925.032 I slot print_timing: id 1 | task 4102 | graphs reused = 3755 4.21.925.032 I slot print_timing: id 1 | task 4102 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.925.103 I slot release: id 1 | task 4102 | stop processing: n_tokens = 1183, truncated = 0 4.21.982.531 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.821 4.21.982.564 I slot launch_slot_: id 1 | task 4250 | processing task, is_child = 0 4.22.377.036 I slot print_timing: id 3 | task 3450 | n_gen = 793, tg = 22.86 t/s, tg_3s = 21.96 t/s 4.22.474.632 I slot print_timing: id 0 | task 4048 | prompt eval time = 399.23 ms / 68 tokens ( 5.87 ms per token, 170.33 tokens per second) 4.22.474.637 I slot print_timing: id 0 | task 4048 | eval time = 9209.48 ms / 200 tokens ( 46.28 ms per token, 21.61 tokens per second) 4.22.474.638 I slot print_timing: id 0 | task 4048 | total time = 9608.71 ms / 268 tokens 4.22.474.639 I slot print_timing: id 0 | task 4048 | graphs reused = 3755 4.22.474.639 I slot print_timing: id 0 | task 4048 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.474.687 I slot release: id 0 | task 4048 | stop processing: n_tokens = 1237, truncated = 0 4.22.513.776 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.785 4.22.513.797 I slot launch_slot_: id 0 | task 4254 | processing task, is_child = 0 4.23.206.263 I slot print_timing: id 2 | task 4159 | n_gen = 100, tg = 20.70 t/s, tg_3s = 20.90 t/s 4.25.380.406 I slot print_timing: id 3 | task 3450 | n_gen = 857, tg = 22.73 t/s, tg_3s = 21.31 t/s 4.26.221.868 I slot print_timing: id 2 | task 4159 | n_gen = 175, tg = 22.31 t/s, tg_3s = 24.87 t/s 4.26.823.650 I slot print_timing: id 1 | task 4250 | n_gen = 100, tg = 22.77 t/s, tg_3s = 22.99 t/s 4.26.863.981 I slot print_timing: id 2 | task 4159 | prompt eval time = 461.58 ms / 74 tokens ( 6.24 ms per token, 160.32 tokens per second) 4.26.863.987 I slot print_timing: id 2 | task 4159 | eval time = 8441.43 ms / 191 tokens ( 44.43 ms per token, 22.51 tokens per second) 4.26.863.988 I slot print_timing: id 2 | task 4159 | total time = 8903.02 ms / 265 tokens 4.26.863.989 I slot print_timing: id 2 | task 4159 | graphs reused = 3852 4.26.863.990 I slot print_timing: id 2 | task 4159 | graph reallocs = 0 / 0 (same size) / (changed size) 4.26.864.062 I slot release: id 2 | task 4159 | stop processing: n_tokens = 1235, truncated = 0 4.26.921.857 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.786 4.26.921.883 I slot launch_slot_: id 2 | task 4355 | processing task, is_child = 0 4.27.291.692 I slot print_timing: id 0 | task 4254 | n_gen = 100, tg = 22.88 t/s, tg_3s = 23.11 t/s 4.28.394.548 I slot print_timing: id 3 | task 3450 | n_gen = 922, tg = 22.65 t/s, tg_3s = 21.56 t/s 4.29.836.347 I slot print_timing: id 1 | task 4250 | n_gen = 165, tg = 22.28 t/s, tg_3s = 21.58 t/s 4.30.317.128 I slot print_timing: id 0 | task 4254 | n_gen = 174, tg = 23.53 t/s, tg_3s = 24.46 t/s 4.31.004.467 I slot print_timing: id 0 | task 4254 | prompt eval time = 450.44 ms / 90 tokens ( 5.00 ms per token, 199.80 tokens per second) 4.31.004.474 I slot print_timing: id 0 | task 4254 | eval time = 8040.22 ms / 191 tokens ( 42.32 ms per token, 23.63 tokens per second) 4.31.004.475 I slot print_timing: id 0 | task 4254 | total time = 8490.66 ms / 281 tokens 4.31.004.476 I slot print_timing: id 0 | task 4254 | graphs reused = 3940 4.31.004.476 I slot print_timing: id 0 | task 4254 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.004.544 I slot release: id 0 | task 4254 | stop processing: n_tokens = 1251, truncated = 0 4.31.045.746 I slot print_timing: id 1 | task 4250 | prompt eval time = 492.30 ms / 91 tokens ( 5.41 ms per token, 184.85 tokens per second) 4.31.045.749 I slot print_timing: id 1 | task 4250 | eval time = 8570.87 ms / 195 tokens ( 44.18 ms per token, 22.63 tokens per second) 4.31.045.750 I slot print_timing: id 1 | task 4250 | total time = 9063.17 ms / 286 tokens 4.31.045.751 I slot print_timing: id 1 | task 4250 | graphs reused = 3940 4.31.045.751 I slot print_timing: id 1 | task 4250 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.045.806 I slot release: id 1 | task 4250 | stop processing: n_tokens = 1256, truncated = 0 4.31.046.115 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.776 4.31.046.139 I slot launch_slot_: id 0 | task 4449 | processing task, is_child = 0 4.31.075.717 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.773 4.31.075.736 I slot launch_slot_: id 1 | task 4450 | processing task, is_child = 0 4.31.618.402 I slot print_timing: id 3 | task 3450 | n_gen = 989, tg = 22.51 t/s, tg_3s = 20.78 t/s 4.31.956.174 I slot print_timing: id 2 | task 4355 | n_gen = 100, tg = 21.66 t/s, tg_3s = 21.88 t/s 4.33.099.914 I slot print_timing: id 3 | task 3450 | prompt eval time = 465.06 ms / 94 tokens ( 4.95 ms per token, 202.13 tokens per second) 4.33.099.922 I slot print_timing: id 3 | task 3450 | eval time = 45375.31 ms / 1024 tokens ( 44.36 ms per token, 22.55 tokens per second) 4.33.099.923 I slot print_timing: id 3 | task 3450 | total time = 45840.36 ms / 1118 tokens 4.33.099.924 I slot print_timing: id 3 | task 3450 | graphs reused = 3973 4.33.099.925 I slot print_timing: id 3 | task 3450 | graph reallocs = 0 / 0 (same size) / (changed size) 4.33.099.996 I slot release: id 3 | task 3450 | stop processing: n_tokens = 2088, truncated = 0 4.33.140.603 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.465 4.33.171.187 I slot launch_slot_: id 3 | task 4488 | processing task, is_child = 0 4.34.971.408 I slot print_timing: id 2 | task 4355 | n_gen = 166, tg = 21.75 t/s, tg_3s = 21.89 t/s 4.36.048.495 I slot print_timing: id 0 | task 4449 | n_gen = 100, tg = 22.83 t/s, tg_3s = 23.06 t/s 4.36.048.685 I slot print_timing: id 1 | task 4450 | n_gen = 100, tg = 22.83 t/s, tg_3s = 23.06 t/s 4.37.481.183 I slot print_timing: id 2 | task 4355 | prompt eval time = 464.22 ms / 75 tokens ( 6.19 ms per token, 161.56 tokens per second) 4.37.481.191 I slot print_timing: id 2 | task 4355 | eval time = 10095.07 ms / 229 tokens ( 44.28 ms per token, 22.59 tokens per second) 4.37.481.192 I slot print_timing: id 2 | task 4355 | total time = 10559.29 ms / 304 tokens 4.37.481.193 I slot print_timing: id 2 | task 4355 | graphs reused = 4069 4.37.481.194 I slot print_timing: id 2 | task 4355 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.481.267 I slot release: id 2 | task 4355 | stop processing: n_tokens = 1274, truncated = 0 4.37.538.371 I slot print_timing: id 3 | task 4488 | n_gen = 100, tg = 24.95 t/s, tg_3s = 25.20 t/s 4.37.538.381 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.762 4.37.538.403 I slot launch_slot_: id 2 | task 4590 | processing task, is_child = 0 4.39.069.206 I slot print_timing: id 0 | task 4449 | n_gen = 167, tg = 22.56 t/s, tg_3s = 22.18 t/s 4.39.069.379 I slot print_timing: id 1 | task 4450 | n_gen = 167, tg = 22.56 t/s, tg_3s = 22.18 t/s 4.40.545.813 I slot print_timing: id 3 | task 4488 | n_gen = 167, tg = 23.80 t/s, tg_3s = 22.28 t/s 4.41.905.584 I slot print_timing: id 2 | task 4590 | n_gen = 100, tg = 25.02 t/s, tg_3s = 25.27 t/s 4.42.105.187 I slot print_timing: id 0 | task 4449 | n_gen = 243, tg = 23.28 t/s, tg_3s = 25.03 t/s 4.42.105.362 I slot print_timing: id 1 | task 4450 | n_gen = 243, tg = 23.28 t/s, tg_3s = 25.03 t/s 4.42.385.060 I slot print_timing: id 3 | task 4488 | prompt eval time = 399.29 ms / 66 tokens ( 6.05 ms per token, 165.29 tokens per second) 4.42.385.068 I slot print_timing: id 3 | task 4488 | eval time = 8814.57 ms / 213 tokens ( 41.58 ms per token, 24.05 tokens per second) 4.42.385.068 I slot print_timing: id 3 | task 4488 | total time = 9213.86 ms / 279 tokens 4.42.385.069 I slot print_timing: id 3 | task 4488 | graphs reused = 4177 4.42.385.070 I slot print_timing: id 3 | task 4488 | graph reallocs = 0 / 0 (same size) / (changed size) 4.42.385.148 I slot release: id 3 | task 4488 | stop processing: n_tokens = 1248, truncated = 0 4.42.426.107 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.778 4.42.426.141 I slot launch_slot_: id 3 | task 4705 | processing task, is_child = 0 4.43.330.447 I slot print_timing: id 0 | task 4449 | prompt eval time = 636.05 ms / 56 tokens ( 11.36 ms per token, 88.04 tokens per second) 4.43.330.455 I slot print_timing: id 0 | task 4449 | eval time = 11618.65 ms / 264 tokens ( 44.18 ms per token, 22.64 tokens per second) 4.43.330.456 I slot print_timing: id 0 | task 4449 | total time = 12254.70 ms / 320 tokens 4.43.330.457 I slot print_timing: id 0 | task 4449 | graphs reused = 4187 4.43.330.458 I slot print_timing: id 0 | task 4449 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.330.529 I slot release: id 0 | task 4449 | stop processing: n_tokens = 1290, truncated = 0 4.43.372.709 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.753 4.43.372.736 I slot launch_slot_: id 0 | task 4720 | processing task, is_child = 0 4.44.918.790 I slot print_timing: id 2 | task 4590 | n_gen = 157, tg = 22.38 t/s, tg_3s = 18.92 t/s 4.45.117.932 I slot print_timing: id 1 | task 4450 | n_gen = 300, tg = 22.30 t/s, tg_3s = 18.92 t/s 4.45.953.703 I slot print_timing: id 2 | task 4590 | prompt eval time = 410.38 ms / 59 tokens ( 6.96 ms per token, 143.77 tokens per second) 4.45.953.711 I slot print_timing: id 2 | task 4590 | eval time = 8004.91 ms / 183 tokens ( 43.98 ms per token, 22.74 tokens per second) 4.45.953.712 I slot print_timing: id 2 | task 4590 | total time = 8415.29 ms / 242 tokens 4.45.953.713 I slot print_timing: id 2 | task 4590 | graphs reused = 4241 4.45.953.714 I slot print_timing: id 2 | task 4590 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.953.786 I slot release: id 2 | task 4590 | stop processing: n_tokens = 1212, truncated = 0 4.46.011.679 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.801 4.46.011.704 I slot launch_slot_: id 2 | task 4778 | processing task, is_child = 0 4.47.553.999 I slot print_timing: id 3 | task 4705 | n_gen = 100, tg = 21.20 t/s, tg_3s = 21.41 t/s 4.48.109.851 I slot print_timing: id 0 | task 4720 | n_gen = 100, tg = 22.93 t/s, tg_3s = 23.16 t/s 4.48.149.817 I slot print_timing: id 1 | task 4450 | n_gen = 367, tg = 22.27 t/s, tg_3s = 22.10 t/s 4.50.381.898 I slot print_timing: id 2 | task 4778 | n_gen = 100, tg = 25.09 t/s, tg_3s = 25.34 t/s 4.50.581.478 I slot print_timing: id 3 | task 4705 | n_gen = 176, tg = 22.73 t/s, tg_3s = 25.10 t/s 4.50.820.473 I slot print_timing: id 3 | task 4705 | prompt eval time = 457.60 ms / 86 tokens ( 5.32 ms per token, 187.94 tokens per second) 4.50.820.478 I slot print_timing: id 3 | task 4705 | eval time = 7936.72 ms / 182 tokens ( 43.85 ms per token, 22.81 tokens per second) 4.50.820.479 I slot print_timing: id 3 | task 4705 | total time = 8394.32 ms / 268 tokens 4.50.820.479 I slot print_timing: id 3 | task 4705 | graphs reused = 4350 4.50.820.480 I slot print_timing: id 3 | task 4705 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.820.558 I slot release: id 3 | task 4705 | stop processing: n_tokens = 1238, truncated = 0 4.50.861.377 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.784 4.50.861.402 I slot launch_slot_: id 3 | task 4892 | processing task, is_child = 0 4.51.277.255 I slot print_timing: id 0 | task 4720 | prompt eval time = 419.89 ms / 70 tokens ( 6.00 ms per token, 166.71 tokens per second) 4.51.277.258 I slot print_timing: id 0 | task 4720 | eval time = 7484.61 ms / 170 tokens ( 44.29 ms per token, 22.58 tokens per second) 4.51.277.258 I slot print_timing: id 0 | task 4720 | total time = 7904.51 ms / 240 tokens 4.51.277.259 I slot print_timing: id 0 | task 4720 | graphs reused = 4350 4.51.277.259 I slot print_timing: id 0 | task 4720 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.277.302 I slot release: id 0 | task 4720 | stop processing: n_tokens = 1210, truncated = 0 4.51.277.392 I slot print_timing: id 1 | task 4450 | n_gen = 436, tg = 22.23 t/s, tg_3s = 22.06 t/s 4.51.351.284 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.802 4.51.351.303 I slot launch_slot_: id 0 | task 4895 | processing task, is_child = 0 4.53.388.308 I slot print_timing: id 2 | task 4778 | n_gen = 156, tg = 22.29 t/s, tg_3s = 18.63 t/s 4.54.316.156 I slot print_timing: id 1 | task 4450 | n_gen = 502, tg = 22.16 t/s, tg_3s = 21.72 t/s 4.54.356.271 I slot print_timing: id 2 | task 4778 | prompt eval time = 423.75 ms / 61 tokens ( 6.95 ms per token, 143.95 tokens per second) 4.54.356.275 I slot print_timing: id 2 | task 4778 | eval time = 7920.80 ms / 180 tokens ( 44.25 ms per token, 22.60 tokens per second) 4.54.356.276 I slot print_timing: id 2 | task 4778 | total time = 8344.55 ms / 241 tokens 4.54.356.277 I slot print_timing: id 2 | task 4778 | graphs reused = 4412 4.54.356.278 I slot print_timing: id 2 | task 4778 | graph reallocs = 0 / 0 (same size) / (changed size) 4.54.356.348 I slot release: id 2 | task 4778 | stop processing: n_tokens = 1211, truncated = 0 4.54.414.447 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.802 4.54.414.477 I slot launch_slot_: id 2 | task 4963 | processing task, is_child = 0 4.56.173.936 I slot print_timing: id 3 | task 4892 | n_gen = 100, tg = 20.53 t/s, tg_3s = 20.74 t/s 4.56.253.287 I slot print_timing: id 0 | task 4895 | n_gen = 100, tg = 22.17 t/s, tg_3s = 22.39 t/s 4.57.333.311 I slot print_timing: id 1 | task 4450 | n_gen = 565, tg = 22.01 t/s, tg_3s = 20.88 t/s 4.58.933.984 I slot print_timing: id 2 | task 4963 | n_gen = 100, tg = 24.93 t/s, tg_3s = 25.19 t/s 4.59.173.977 I slot print_timing: id 1 | task 4450 | prompt eval time = 634.70 ms / 75 tokens ( 8.46 ms per token, 118.17 tokens per second) 4.59.173.981 I slot print_timing: id 1 | task 4450 | eval time = 27462.08 ms / 611 tokens ( 45.02 ms per token, 22.21 tokens per second) 4.59.173.984 I slot print_timing: id 1 | task 4450 | total time = 28096.78 ms / 686 tokens 4.59.173.984 I slot print_timing: id 1 | task 4450 | graphs reused = 4516 4.59.173.985 I slot print_timing: id 1 | task 4450 | graph reallocs = 0 / 0 (same size) / (changed size) 4.59.174.062 I slot release: id 1 | task 4450 | stop processing: n_tokens = 1656, truncated = 0 4.59.174.407 I slot print_timing: id 3 | task 4892 | n_gen = 175, tg = 22.24 t/s, tg_3s = 25.00 t/s 4.59.231.468 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.586 4.59.231.495 I slot launch_slot_: id 1 | task 5072 | processing task, is_child = 0 4.59.621.165 I slot print_timing: id 0 | task 4895 | n_gen = 175, tg = 22.21 t/s, tg_3s = 22.27 t/s 5.01.965.027 I slot print_timing: id 2 | task 4963 | n_gen = 165, tg = 23.42 t/s, tg_3s = 21.44 t/s 5.02.204.997 I slot print_timing: id 3 | task 4892 | n_gen = 240, tg = 22.02 t/s, tg_3s = 21.45 t/s 5.02.643.848 I slot print_timing: id 0 | task 4895 | n_gen = 249, tg = 22.84 t/s, tg_3s = 24.48 t/s 5.03.682.392 I slot print_timing: id 1 | task 5072 | n_gen = 100, tg = 24.97 t/s, tg_3s = 25.22 t/s 5.04.081.667 I slot print_timing: id 0 | task 4895 | prompt eval time = 436.23 ms / 78 tokens ( 5.59 ms per token, 178.80 tokens per second) 5.04.081.675 I slot print_timing: id 0 | task 4895 | eval time = 12294.12 ms / 285 tokens ( 43.29 ms per token, 23.10 tokens per second) 5.04.081.676 I slot print_timing: id 0 | task 4895 | total time = 12730.35 ms / 363 tokens 5.04.081.676 I slot print_timing: id 0 | task 4895 | graphs reused = 4623 5.04.081.677 I slot print_timing: id 0 | task 4895 | graph reallocs = 0 / 0 (same size) / (changed size) 5.04.081.750 I slot release: id 0 | task 4895 | stop processing: n_tokens = 1333, truncated = 0 5.04.123.373 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.728 5.04.123.399 I slot launch_slot_: id 0 | task 5185 | processing task, is_child = 0 5.04.986.154 I slot print_timing: id 2 | task 4963 | n_gen = 231, tg = 22.95 t/s, tg_3s = 21.85 t/s 5.05.225.316 I slot print_timing: id 3 | task 4892 | n_gen = 306, tg = 21.98 t/s, tg_3s = 21.85 t/s 5.06.702.895 I slot print_timing: id 1 | task 5072 | n_gen = 166, tg = 23.62 t/s, tg_3s = 21.85 t/s 5.07.704.017 I slot print_timing: id 1 | task 5072 | prompt eval time = 486.25 ms / 88 tokens ( 5.53 ms per token, 180.98 tokens per second) 5.07.704.021 I slot print_timing: id 1 | task 5072 | eval time = 7986.27 ms / 191 tokens ( 42.03 ms per token, 23.79 tokens per second) 5.07.704.023 I slot print_timing: id 1 | task 5072 | total time = 8472.51 ms / 279 tokens 5.07.704.023 I slot print_timing: id 1 | task 5072 | graphs reused = 4701 5.07.704.024 I slot print_timing: id 1 | task 5072 | graph reallocs = 0 / 0 (same size) / (changed size) 5.07.704.097 I slot release: id 1 | task 5072 | stop processing: n_tokens = 1249, truncated = 0 5.07.761.176 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.952 (> 0.100 thold), f_keep = 0.777 5.07.761.200 I slot launch_slot_: id 1 | task 5267 | processing task, is_child = 0 5.08.058.039 I slot print_timing: id 2 | task 4963 | n_gen = 301, tg = 22.91 t/s, tg_3s = 22.79 t/s 5.08.238.034 I slot print_timing: id 3 | task 4892 | n_gen = 373, tg = 22.03 t/s, tg_3s = 22.24 t/s 5.08.885.229 I slot print_timing: id 0 | task 5185 | n_gen = 100, tg = 22.98 t/s, tg_3s = 23.21 t/s 5.11.090.396 I slot print_timing: id 2 | task 4963 | n_gen = 375, tg = 23.19 t/s, tg_3s = 24.40 t/s 5.11.250.787 I slot print_timing: id 3 | task 4892 | n_gen = 448, tg = 22.46 t/s, tg_3s = 24.89 t/s 5.11.897.826 I slot print_timing: id 0 | task 5185 | n_gen = 175, tg = 23.77 t/s, tg_3s = 24.90 t/s 5.12.138.891 I slot print_timing: id 1 | task 5267 | n_gen = 100, tg = 24.85 t/s, tg_3s = 25.10 t/s 5.12.259.145 I slot print_timing: id 1 | task 5267 | prompt eval time = 393.44 ms / 49 tokens ( 8.03 ms per token, 124.54 tokens per second) 5.12.259.153 I slot print_timing: id 1 | task 5267 | eval time = 4104.50 ms / 103 tokens ( 40.24 ms per token, 24.85 tokens per second) 5.12.259.154 I slot print_timing: id 1 | task 5267 | total time = 4497.94 ms / 152 tokens 5.12.259.155 I slot print_timing: id 1 | task 5267 | graphs reused = 4800 5.12.259.155 I slot print_timing: id 1 | task 5267 | graph reallocs = 0 / 0 (same size) / (changed size) 5.12.259.227 I slot release: id 1 | task 5267 | stop processing: n_tokens = 1122, truncated = 0 5.12.316.759 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.865 5.12.316.788 I slot launch_slot_: id 1 | task 5373 | processing task, is_child = 0 5.14.106.180 I slot print_timing: id 2 | task 4963 | n_gen = 440, tg = 22.93 t/s, tg_3s = 21.55 t/s 5.14.267.001 I slot print_timing: id 3 | task 4892 | n_gen = 513, tg = 22.34 t/s, tg_3s = 21.55 t/s 5.14.909.609 I slot print_timing: id 0 | task 5185 | n_gen = 240, tg = 23.13 t/s, tg_3s = 21.58 t/s 5.16.716.853 I slot print_timing: id 1 | task 5373 | prompt eval time = 460.30 ms / 73 tokens ( 6.31 ms per token, 158.59 tokens per second) 5.16.716.858 I slot print_timing: id 1 | task 5373 | eval time = 3939.75 ms / 99 tokens ( 40.20 ms per token, 24.87 tokens per second) 5.16.716.860 I slot print_timing: id 1 | task 5373 | total time = 4400.06 ms / 172 tokens 5.16.716.861 I slot print_timing: id 1 | task 5373 | graphs reused = 4897 5.16.716.862 I slot print_timing: id 1 | task 5373 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.716.932 I slot release: id 1 | task 5373 | stop processing: n_tokens = 1142, truncated = 0 5.16.774.596 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.850 5.16.774.621 I slot launch_slot_: id 1 | task 5475 | processing task, is_child = 0 5.17.169.701 I slot print_timing: id 2 | task 4963 | n_gen = 507, tg = 22.79 t/s, tg_3s = 21.87 t/s 5.17.309.930 I slot print_timing: id 3 | task 4892 | n_gen = 578, tg = 22.23 t/s, tg_3s = 21.36 t/s 5.17.919.974 I slot print_timing: id 0 | task 5185 | n_gen = 304, tg = 22.71 t/s, tg_3s = 21.26 t/s 5.20.174.145 I slot print_timing: id 2 | task 4963 | n_gen = 580, tg = 22.97 t/s, tg_3s = 24.30 t/s 5.20.334.893 I slot print_timing: id 3 | task 4892 | prompt eval time = 489.88 ms / 109 tokens ( 4.49 ms per token, 222.51 tokens per second) 5.20.334.899 I slot print_timing: id 3 | task 4892 | eval time = 28983.61 ms / 653 tokens ( 44.45 ms per token, 22.50 tokens per second) 5.20.334.900 I slot print_timing: id 3 | task 4892 | total time = 29473.48 ms / 762 tokens 5.20.334.901 I slot print_timing: id 3 | task 4892 | graphs reused = 4972 5.20.334.902 I slot print_timing: id 3 | task 4892 | graph reallocs = 0 / 0 (same size) / (changed size) 5.20.334.976 I slot release: id 3 | task 4892 | stop processing: n_tokens = 1732, truncated = 0 5.20.376.036 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.561 5.20.376.072 I slot launch_slot_: id 3 | task 5555 | processing task, is_child = 0 5.20.933.577 I slot print_timing: id 0 | task 5185 | n_gen = 371, tg = 22.62 t/s, tg_3s = 22.23 t/s 5.21.580.197 I slot print_timing: id 1 | task 5475 | n_gen = 100, tg = 22.95 t/s, tg_3s = 23.18 t/s 5.23.183.476 I slot print_timing: id 2 | task 4963 | n_gen = 647, tg = 22.89 t/s, tg_3s = 22.26 t/s 5.23.945.479 I slot print_timing: id 0 | task 5185 | n_gen = 446, tg = 22.98 t/s, tg_3s = 24.90 t/s 5.24.586.884 I slot print_timing: id 1 | task 5475 | n_gen = 175, tg = 23.77 t/s, tg_3s = 24.94 t/s 5.24.747.619 I slot print_timing: id 3 | task 5555 | n_gen = 100, tg = 24.90 t/s, tg_3s = 25.15 t/s 5.26.198.920 I slot print_timing: id 2 | task 4963 | n_gen = 722, tg = 23.08 t/s, tg_3s = 24.87 t/s 5.26.962.062 I slot print_timing: id 0 | task 5185 | n_gen = 521, tg = 23.23 t/s, tg_3s = 24.86 t/s 5.27.444.401 I slot print_timing: id 1 | task 5475 | prompt eval time = 492.16 ms / 89 tokens ( 5.53 ms per token, 180.84 tokens per second) 5.27.444.408 I slot print_timing: id 1 | task 5475 | eval time = 10177.60 ms / 246 tokens ( 41.54 ms per token, 24.07 tokens per second) 5.27.444.409 I slot print_timing: id 1 | task 5475 | total time = 10669.76 ms / 335 tokens 5.27.444.410 I slot print_timing: id 1 | task 5475 | graphs reused = 5136 5.27.444.411 I slot print_timing: id 1 | task 5475 | graph reallocs = 0 / 0 (same size) / (changed size) 5.27.444.483 I slot release: id 1 | task 5475 | stop processing: n_tokens = 1305, truncated = 0 5.27.501.900 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.744 5.27.501.927 I slot launch_slot_: id 1 | task 5725 | processing task, is_child = 0 5.27.899.904 I slot print_timing: id 3 | task 5555 | n_gen = 169, tg = 23.57 t/s, tg_3s = 21.89 t/s 5.29.213.683 I slot print_timing: id 2 | task 4963 | n_gen = 786, tg = 22.92 t/s, tg_3s = 21.23 t/s 5.29.978.221 I slot print_timing: id 0 | task 5185 | n_gen = 585, tg = 22.99 t/s, tg_3s = 21.22 t/s 5.30.300.549 I slot print_timing: id 3 | task 5555 | prompt eval time = 395.69 ms / 69 tokens ( 5.73 ms per token, 174.38 tokens per second) 5.30.300.553 I slot print_timing: id 3 | task 5555 | eval time = 9528.78 ms / 227 tokens ( 42.16 ms per token, 23.72 tokens per second) 5.30.300.554 I slot print_timing: id 3 | task 5555 | total time = 9924.47 ms / 296 tokens 5.30.300.555 I slot print_timing: id 3 | task 5555 | graphs reused = 5192 5.30.300.556 I slot print_timing: id 3 | task 5555 | graph reallocs = 0 / 0 (same size) / (changed size) 5.30.300.629 I slot release: id 3 | task 5555 | stop processing: n_tokens = 1266, truncated = 0 5.30.341.919 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.767 5.30.341.958 I slot launch_slot_: id 3 | task 5786 | processing task, is_child = 0 5.32.242.960 I slot print_timing: id 2 | task 4963 | n_gen = 852, tg = 22.83 t/s, tg_3s = 21.79 t/s 5.32.363.664 I slot print_timing: id 1 | task 5725 | n_gen = 100, tg = 22.67 t/s, tg_3s = 22.90 t/s 5.33.007.598 I slot print_timing: id 0 | task 5185 | n_gen = 651, tg = 22.86 t/s, tg_3s = 21.79 t/s 5.33.288.440 I slot print_timing: id 2 | task 4963 | prompt eval time = 549.08 ms / 128 tokens ( 4.29 ms per token, 233.12 tokens per second) 5.33.288.444 I slot print_timing: id 2 | task 4963 | eval time = 38324.87 ms / 878 tokens ( 43.70 ms per token, 22.88 tokens per second) 5.33.288.445 I slot print_timing: id 2 | task 4963 | total time = 38873.96 ms / 1006 tokens 5.33.288.445 I slot print_timing: id 2 | task 4963 | graphs reused = 5253 5.33.288.446 I slot print_timing: id 2 | task 4963 | graph reallocs = 0 / 0 (same size) / (changed size) 5.33.288.503 I slot release: id 2 | task 4963 | stop processing: n_tokens = 1976, truncated = 0 5.33.346.737 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.491 5.33.371.135 I slot launch_slot_: id 2 | task 5852 | processing task, is_child = 0 5.35.210.363 I slot print_timing: id 3 | task 5786 | n_gen = 100, tg = 22.43 t/s, tg_3s = 22.66 t/s 5.35.369.209 I slot print_timing: id 1 | task 5725 | n_gen = 164, tg = 22.11 t/s, tg_3s = 21.29 t/s 5.36.009.509 I slot print_timing: id 0 | task 5185 | n_gen = 715, tg = 22.72 t/s, tg_3s = 21.32 t/s 5.37.820.053 I slot print_timing: id 2 | task 5852 | n_gen = 100, tg = 24.88 t/s, tg_3s = 25.13 t/s 5.38.221.052 I slot print_timing: id 3 | task 5786 | n_gen = 175, tg = 23.44 t/s, tg_3s = 24.91 t/s 5.38.381.327 I slot print_timing: id 1 | task 5725 | n_gen = 239, tg = 22.92 t/s, tg_3s = 24.90 t/s 5.38.943.400 I slot print_timing: id 1 | task 5725 | prompt eval time = 494.88 ms / 90 tokens ( 5.50 ms per token, 181.86 tokens per second) 5.38.943.408 I slot print_timing: id 1 | task 5725 | eval time = 10946.58 ms / 253 tokens ( 43.44 ms per token, 23.02 tokens per second) 5.38.943.409 I slot print_timing: id 1 | task 5725 | total time = 11441.46 ms / 343 tokens 5.38.943.410 I slot print_timing: id 1 | task 5725 | graphs reused = 5378 5.38.943.411 I slot print_timing: id 1 | task 5725 | graph reallocs = 0 / 0 (same size) / (changed size) 5.38.943.486 I slot release: id 1 | task 5725 | stop processing: n_tokens = 1313, truncated = 0 5.38.999.788 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.740 5.38.999.813 I slot launch_slot_: id 1 | task 5983 | processing task, is_child = 0 5.39.334.273 I slot print_timing: id 0 | task 5185 | n_gen = 790, tg = 22.70 t/s, tg_3s = 22.56 t/s 5.40.849.595 I slot print_timing: id 2 | task 5852 | n_gen = 166, tg = 23.54 t/s, tg_3s = 21.79 t/s 5.41.251.567 I slot print_timing: id 3 | task 5786 | n_gen = 241, tg = 22.96 t/s, tg_3s = 21.78 t/s 5.42.336.150 I slot print_timing: id 0 | task 5185 | n_gen = 863, tg = 22.83 t/s, tg_3s = 24.32 t/s 5.43.300.967 I slot print_timing: id 2 | task 5852 | prompt eval time = 470.05 ms / 79 tokens ( 5.95 ms per token, 168.07 tokens per second) 5.43.300.974 I slot print_timing: id 2 | task 5852 | eval time = 9459.76 ms / 227 tokens ( 41.86 ms per token, 23.89 tokens per second) 5.43.300.975 I slot print_timing: id 2 | task 5852 | total time = 9929.82 ms / 306 tokens 5.43.300.976 I slot print_timing: id 2 | task 5852 | graphs reused = 5473 5.43.300.977 I slot print_timing: id 2 | task 5852 | graph reallocs = 0 / 0 (same size) / (changed size) 5.43.301.050 I slot release: id 2 | task 5852 | stop processing: n_tokens = 1275, truncated = 0 5.43.359.029 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.762 5.43.359.056 I slot launch_slot_: id 2 | task 6083 | processing task, is_child = 0 5.43.939.819 I slot print_timing: id 1 | task 5983 | n_gen = 100, tg = 21.96 t/s, tg_3s = 22.18 t/s 5.44.272.231 I slot print_timing: id 3 | task 5786 | n_gen = 303, tg = 22.41 t/s, tg_3s = 20.53 t/s 5.45.356.492 I slot print_timing: id 0 | task 5185 | n_gen = 925, tg = 22.66 t/s, tg_3s = 20.53 t/s 5.46.000.732 I slot print_timing: id 1 | task 5983 | prompt eval time = 431.64 ms / 66 tokens ( 6.54 ms per token, 152.90 tokens per second) 5.46.000.740 I slot print_timing: id 1 | task 5983 | eval time = 6569.26 ms / 151 tokens ( 43.80 ms per token, 22.83 tokens per second) 5.46.000.741 I slot print_timing: id 1 | task 5983 | total time = 7000.91 ms / 217 tokens 5.46.000.742 I slot print_timing: id 1 | task 5983 | graphs reused = 5523 5.46.000.743 I slot print_timing: id 1 | task 5983 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.000.812 I slot release: id 1 | task 5983 | stop processing: n_tokens = 1187, truncated = 0 5.46.058.446 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.818 5.46.058.469 I slot launch_slot_: id 1 | task 6138 | processing task, is_child = 0 5.46.795.037 I slot print_timing: id 0 | task 5185 | prompt eval time = 454.12 ms / 92 tokens ( 4.94 ms per token, 202.59 tokens per second) 5.46.795.042 I slot print_timing: id 0 | task 5185 | eval time = 42217.51 ms / 952 tokens ( 44.39 ms per token, 22.53 tokens per second) 5.46.795.043 I slot print_timing: id 0 | task 5185 | total time = 42671.63 ms / 1044 tokens 5.46.795.044 I slot print_timing: id 0 | task 5185 | graphs reused = 5530 5.46.795.044 I slot print_timing: id 0 | task 5185 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.795.097 I slot release: id 0 | task 5185 | stop processing: n_tokens = 2014, truncated = 0 5.46.833.576 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.951 (> 0.100 thold), f_keep = 0.482 5.46.860.945 I slot launch_slot_: id 0 | task 6150 | processing task, is_child = 0 5.47.305.170 I slot print_timing: id 3 | task 5786 | n_gen = 362, tg = 21.87 t/s, tg_3s = 19.45 t/s 5.48.593.432 I slot print_timing: id 2 | task 6083 | n_gen = 100, tg = 21.27 t/s, tg_3s = 21.49 t/s 5.49.591.778 I slot print_timing: id 2 | task 6083 | prompt eval time = 580.89 ms / 137 tokens ( 4.24 ms per token, 235.84 tokens per second) 5.49.591.782 I slot print_timing: id 2 | task 6083 | eval time = 5651.82 ms / 125 tokens ( 45.58 ms per token, 21.94 tokens per second) 5.49.591.783 I slot print_timing: id 2 | task 6083 | total time = 6232.71 ms / 262 tokens 5.49.591.784 I slot print_timing: id 2 | task 6083 | graphs reused = 5589 5.49.591.785 I slot print_timing: id 2 | task 6083 | graph reallocs = 0 / 0 (same size) / (changed size) 5.49.591.866 I slot release: id 2 | task 6083 | stop processing: n_tokens = 1232, truncated = 0 5.49.649.717 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.788 5.49.649.743 I slot launch_slot_: id 2 | task 6213 | processing task, is_child = 0 5.50.330.622 I slot print_timing: id 3 | task 5786 | n_gen = 427, tg = 21.81 t/s, tg_3s = 21.48 t/s 5.51.170.186 I slot print_timing: id 1 | task 6138 | n_gen = 100, tg = 21.08 t/s, tg_3s = 21.29 t/s 5.51.250.799 I slot print_timing: id 3 | task 5786 | prompt eval time = 454.60 ms / 88 tokens ( 5.17 ms per token, 193.58 tokens per second) 5.51.250.803 I slot print_timing: id 3 | task 5786 | eval time = 20454.23 ms / 450 tokens ( 45.56 ms per token, 21.95 tokens per second) 5.51.250.804 I slot print_timing: id 3 | task 5786 | total time = 20908.83 ms / 538 tokens 5.51.250.805 I slot print_timing: id 3 | task 5786 | graphs reused = 5615 5.51.250.806 I slot print_timing: id 3 | task 5786 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.250.882 I slot release: id 3 | task 5786 | stop processing: n_tokens = 1508, truncated = 0 5.51.292.256 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.644 5.51.292.282 I slot launch_slot_: id 3 | task 6245 | processing task, is_child = 0 5.51.920.751 I slot print_timing: id 0 | task 6150 | n_gen = 100, tg = 21.07 t/s, tg_3s = 21.29 t/s 5.54.191.412 I slot print_timing: id 1 | task 6138 | n_gen = 168, tg = 21.64 t/s, tg_3s = 22.51 t/s 5.54.390.268 I slot print_timing: id 2 | task 6213 | n_gen = 100, tg = 23.19 t/s, tg_3s = 23.42 t/s 5.54.946.555 I slot print_timing: id 0 | task 6150 | n_gen = 176, tg = 22.66 t/s, tg_3s = 25.12 t/s 5.55.627.052 I slot print_timing: id 1 | task 6138 | prompt eval time = 415.27 ms / 58 tokens ( 7.16 ms per token, 139.67 tokens per second) 5.55.627.061 I slot print_timing: id 1 | task 6138 | eval time = 9153.31 ms / 204 tokens ( 45.09 ms per token, 22.18 tokens per second) 5.55.627.062 I slot print_timing: id 1 | task 6138 | total time = 9568.57 ms / 262 tokens 5.55.627.063 I slot print_timing: id 1 | task 6138 | graphs reused = 5712 5.55.627.064 I slot print_timing: id 1 | task 6138 | graph reallocs = 0 / 0 (same size) / (changed size) 5.55.627.139 I slot release: id 1 | task 6138 | stop processing: n_tokens = 1232, truncated = 0 5.55.627.494 I slot print_timing: id 3 | task 6245 | n_gen = 100, tg = 25.10 t/s, tg_3s = 25.35 t/s 5.55.684.127 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.788 5.55.684.152 I slot launch_slot_: id 1 | task 6348 | processing task, is_child = 0 5.57.423.894 I slot print_timing: id 2 | task 6213 | n_gen = 166, tg = 22.59 t/s, tg_3s = 21.76 t/s 5.57.742.005 I slot print_timing: id 0 | task 6150 | prompt eval time = 361.87 ms / 51 tokens ( 7.10 ms per token, 140.93 tokens per second) 5.57.742.011 I slot print_timing: id 0 | task 6150 | eval time = 10519.17 ms / 236 tokens ( 44.76 ms per token, 22.34 tokens per second) 5.57.742.012 I slot print_timing: id 0 | task 6150 | total time = 10881.04 ms / 287 tokens 5.57.742.013 I slot print_timing: id 0 | task 6150 | graphs reused = 5750 5.57.742.013 I slot print_timing: id 0 | task 6150 | graph reallocs = 0 / 0 (same size) / (changed size) 5.57.742.083 I slot release: id 0 | task 6150 | stop processing: n_tokens = 1256, truncated = 0 5.57.783.180 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.773 5.57.783.208 I slot launch_slot_: id 0 | task 6392 | processing task, is_child = 0 5.58.645.114 I slot print_timing: id 3 | task 6245 | n_gen = 158, tg = 22.55 t/s, tg_3s = 19.22 t/s 5.58.684.670 I slot print_timing: id 3 | task 6245 | prompt eval time = 390.58 ms / 63 tokens ( 6.20 ms per token, 161.30 tokens per second) 5.58.684.676 I slot print_timing: id 3 | task 6245 | eval time = 7001.80 ms / 159 tokens ( 44.32 ms per token, 22.57 tokens per second) 5.58.684.676 I slot print_timing: id 3 | task 6245 | total time = 7392.38 ms / 222 tokens 5.58.684.677 I slot print_timing: id 3 | task 6245 | graphs reused = 5763 5.58.684.677 I slot print_timing: id 3 | task 6245 | graph reallocs = 0 / 0 (same size) / (changed size) 5.58.684.722 I slot release: id 3 | task 6245 | stop processing: n_tokens = 1192, truncated = 0 5.58.722.637 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.815 5.58.722.661 I slot launch_slot_: id 3 | task 6409 | processing task, is_child = 0 6.00.440.916 I slot print_timing: id 2 | task 6213 | n_gen = 225, tg = 21.71 t/s, tg_3s = 19.56 t/s 6.00.765.277 I slot print_timing: id 1 | task 6348 | n_gen = 100, tg = 21.40 t/s, tg_3s = 21.61 t/s 6.02.476.495 I slot print_timing: id 0 | task 6392 | n_gen = 100, tg = 22.98 t/s, tg_3s = 23.21 t/s 6.03.113.435 I slot print_timing: id 3 | task 6409 | n_gen = 100, tg = 25.02 t/s, tg_3s = 25.28 t/s 6.03.471.625 I slot print_timing: id 2 | task 6213 | n_gen = 301, tg = 22.47 t/s, tg_3s = 25.08 t/s 6.03.791.015 I slot print_timing: id 1 | task 6348 | n_gen = 176, tg = 22.87 t/s, tg_3s = 25.12 t/s 6.05.506.427 I slot print_timing: id 0 | task 6392 | n_gen = 176, tg = 23.85 t/s, tg_3s = 25.08 t/s 6.06.144.870 I slot print_timing: id 3 | task 6409 | n_gen = 176, tg = 25.04 t/s, tg_3s = 25.07 t/s 6.06.503.689 I slot print_timing: id 2 | task 6213 | n_gen = 377, tg = 22.95 t/s, tg_3s = 25.07 t/s 6.06.822.932 I slot print_timing: id 1 | task 6348 | n_gen = 252, tg = 23.49 t/s, tg_3s = 25.07 t/s 6.08.540.514 I slot print_timing: id 0 | task 6392 | n_gen = 252, tg = 24.20 t/s, tg_3s = 25.05 t/s 6.09.027.493 I slot print_timing: id 3 | task 6409 | prompt eval time = 434.53 ms / 79 tokens ( 5.50 ms per token, 181.81 tokens per second) 6.09.027.498 I slot print_timing: id 3 | task 6409 | eval time = 9870.29 ms / 248 tokens ( 39.96 ms per token, 25.02 tokens per second) 6.09.027.499 I slot print_timing: id 3 | task 6409 | total time = 10304.82 ms / 327 tokens 6.09.027.499 I slot print_timing: id 3 | task 6409 | graphs reused = 6007 6.09.027.500 I slot print_timing: id 3 | task 6409 | graph reallocs = 0 / 0 (same size) / (changed size) 6.09.027.585 I slot release: id 3 | task 6409 | stop processing: n_tokens = 1297, truncated = 0 6.09.068.813 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.749 6.09.068.839 I slot launch_slot_: id 3 | task 6660 | processing task, is_child = 0 6.09.518.007 I slot print_timing: id 2 | task 6213 | n_gen = 443, tg = 22.79 t/s, tg_3s = 21.90 t/s 6.09.839.284 I slot print_timing: id 1 | task 6348 | n_gen = 318, tg = 23.14 t/s, tg_3s = 21.88 t/s 6.11.569.901 I slot print_timing: id 0 | task 6392 | n_gen = 318, tg = 23.65 t/s, tg_3s = 21.79 t/s 6.11.730.688 I slot print_timing: id 2 | task 6213 | prompt eval time = 471.14 ms / 82 tokens ( 5.75 ms per token, 174.05 tokens per second) 6.11.730.693 I slot print_timing: id 2 | task 6213 | eval time = 21609.80 ms / 498 tokens ( 43.48 ms per token, 23.00 tokens per second) 6.11.730.694 I slot print_timing: id 2 | task 6213 | total time = 22080.94 ms / 580 tokens 6.11.730.695 I slot print_timing: id 2 | task 6213 | graphs reused = 6060 6.11.730.696 I slot print_timing: id 2 | task 6213 | graph reallocs = 0 / 0 (same size) / (changed size) 6.11.730.772 I slot release: id 2 | task 6213 | stop processing: n_tokens = 1550, truncated = 0 6.11.788.970 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.626 6.11.788.997 I slot launch_slot_: id 2 | task 6719 | processing task, is_child = 0 6.12.860.809 I slot print_timing: id 1 | task 6348 | n_gen = 382, tg = 22.78 t/s, tg_3s = 21.18 t/s 6.12.900.735 I slot print_timing: id 1 | task 6348 | prompt eval time = 454.39 ms / 72 tokens ( 6.31 ms per token, 158.45 tokens per second) 6.12.900.743 I slot print_timing: id 1 | task 6348 | eval time = 16762.18 ms / 383 tokens ( 43.88 ms per token, 22.79 tokens per second) 6.12.900.748 I slot print_timing: id 1 | task 6348 | total time = 17216.58 ms / 455 tokens 6.12.900.749 I slot print_timing: id 1 | task 6348 | graphs reused = 6074 6.12.900.750 I slot print_timing: id 1 | task 6348 | graph reallocs = 0 / 0 (same size) / (changed size) 6.12.900.821 I slot release: id 1 | task 6348 | stop processing: n_tokens = 1425, truncated = 0 6.12.957.978 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.681 6.12.958.009 I slot launch_slot_: id 1 | task 6738 | processing task, is_child = 0 6.13.964.660 I slot print_timing: id 0 | task 6392 | prompt eval time = 384.68 ms / 65 tokens ( 5.92 ms per token, 168.97 tokens per second) 6.13.964.668 I slot print_timing: id 0 | task 6392 | eval time = 15796.76 ms / 356 tokens ( 44.50 ms per token, 22.47 tokens per second) 6.13.964.669 I slot print_timing: id 0 | task 6392 | total time = 16181.44 ms / 421 tokens 6.13.964.669 I slot print_timing: id 0 | task 6392 | graphs reused = 6086 6.13.964.670 I slot print_timing: id 0 | task 6392 | graph reallocs = 0 / 0 (same size) / (changed size) 6.13.964.741 I slot release: id 0 | task 6392 | stop processing: n_tokens = 1391, truncated = 0 6.14.006.021 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.698 6.14.006.052 I slot launch_slot_: id 0 | task 6755 | processing task, is_child = 0 6.14.718.264 I slot print_timing: id 3 | task 6660 | n_gen = 100, tg = 19.04 t/s, tg_3s = 19.23 t/s 6.17.027.212 I slot print_timing: id 2 | task 6719 | n_gen = 100, tg = 20.92 t/s, tg_3s = 21.13 t/s 6.17.750.440 I slot print_timing: id 1 | task 6738 | n_gen = 100, tg = 22.94 t/s, tg_3s = 23.17 t/s 6.17.750.782 I slot print_timing: id 3 | task 6660 | n_gen = 176, tg = 21.26 t/s, tg_3s = 25.06 t/s 6.18.386.858 I slot print_timing: id 0 | task 6755 | n_gen = 100, tg = 25.08 t/s, tg_3s = 25.34 t/s 6.19.421.471 I slot print_timing: id 3 | task 6660 | prompt eval time = 449.30 ms / 84 tokens ( 5.35 ms per token, 186.96 tokens per second) 6.19.421.476 I slot print_timing: id 3 | task 6660 | eval time = 9903.32 ms / 218 tokens ( 45.64 ms per token, 21.91 tokens per second) 6.19.421.477 I slot print_timing: id 3 | task 6660 | total time = 10352.62 ms / 302 tokens 6.19.421.478 I slot print_timing: id 3 | task 6660 | graphs reused = 6210 6.19.421.479 I slot print_timing: id 3 | task 6660 | graph reallocs = 0 / 0 (same size) / (changed size) 6.19.421.559 I slot release: id 3 | task 6660 | stop processing: n_tokens = 1272, truncated = 0 6.19.462.542 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.763 6.19.462.570 I slot launch_slot_: id 3 | task 6884 | processing task, is_child = 0 6.19.975.069 I slot print_timing: id 0 | task 6755 | prompt eval time = 433.96 ms / 78 tokens ( 5.56 ms per token, 179.74 tokens per second) 6.19.975.075 I slot print_timing: id 0 | task 6755 | eval time = 5535.05 ms / 132 tokens ( 42.25 ms per token, 23.67 tokens per second) 6.19.975.075 I slot print_timing: id 0 | task 6755 | total time = 5969.01 ms / 210 tokens 6.19.975.076 I slot print_timing: id 0 | task 6755 | graphs reused = 6212 6.19.975.076 I slot print_timing: id 0 | task 6755 | graph reallocs = 0 / 0 (same size) / (changed size) 6.19.975.120 I slot release: id 0 | task 6755 | stop processing: n_tokens = 1180, truncated = 0 6.20.012.755 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.823 6.20.012.780 I slot launch_slot_: id 0 | task 6891 | processing task, is_child = 0 6.20.319.416 I slot print_timing: id 2 | task 6719 | n_gen = 168, tg = 20.81 t/s, tg_3s = 20.65 t/s 6.20.755.856 I slot print_timing: id 1 | task 6738 | n_gen = 160, tg = 21.72 t/s, tg_3s = 19.96 t/s 6.23.358.613 I slot print_timing: id 2 | task 6719 | n_gen = 243, tg = 21.87 t/s, tg_3s = 24.68 t/s 6.23.757.118 I slot print_timing: id 1 | task 6738 | n_gen = 235, tg = 22.67 t/s, tg_3s = 24.99 t/s 6.24.116.462 I slot print_timing: id 3 | task 6884 | n_gen = 100, tg = 23.23 t/s, tg_3s = 23.46 t/s 6.24.355.438 I slot print_timing: id 0 | task 6891 | n_gen = 100, tg = 25.01 t/s, tg_3s = 25.27 t/s 6.24.874.311 I slot print_timing: id 2 | task 6719 | prompt eval time = 505.49 ms / 101 tokens ( 5.00 ms per token, 199.80 tokens per second) 6.24.874.315 I slot print_timing: id 2 | task 6719 | eval time = 12579.81 ms / 281 tokens ( 44.93 ms per token, 22.26 tokens per second) 6.24.874.316 I slot print_timing: id 2 | task 6719 | total time = 13085.30 ms / 382 tokens 6.24.874.317 I slot print_timing: id 2 | task 6719 | graphs reused = 6323 6.24.874.318 I slot print_timing: id 2 | task 6719 | graph reallocs = 0 / 0 (same size) / (changed size) 6.24.874.394 I slot release: id 2 | task 6719 | stop processing: n_tokens = 1352, truncated = 0 6.24.931.986 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.718 6.24.932.018 I slot launch_slot_: id 2 | task 7007 | processing task, is_child = 0 6.26.784.614 I slot print_timing: id 1 | task 6738 | n_gen = 300, tg = 22.40 t/s, tg_3s = 21.47 t/s 6.27.143.357 I slot print_timing: id 3 | task 6884 | n_gen = 165, tg = 22.50 t/s, tg_3s = 21.47 t/s 6.27.382.209 I slot print_timing: id 0 | task 6891 | n_gen = 165, tg = 23.48 t/s, tg_3s = 21.48 t/s 6.29.376.201 I slot print_timing: id 2 | task 7007 | n_gen = 100, tg = 25.02 t/s, tg_3s = 25.27 t/s 6.29.815.522 I slot print_timing: id 1 | task 6738 | n_gen = 376, tg = 22.89 t/s, tg_3s = 25.07 t/s 6.30.175.511 I slot print_timing: id 3 | task 6884 | n_gen = 241, tg = 23.25 t/s, tg_3s = 25.06 t/s 6.30.414.475 I slot print_timing: id 0 | task 6891 | n_gen = 241, tg = 23.96 t/s, tg_3s = 25.06 t/s 6.32.385.373 I slot print_timing: id 2 | task 7007 | n_gen = 175, tg = 24.98 t/s, tg_3s = 24.92 t/s 6.32.826.906 I slot print_timing: id 1 | task 6738 | n_gen = 451, tg = 23.21 t/s, tg_3s = 24.91 t/s 6.33.188.019 I slot print_timing: id 3 | task 6884 | n_gen = 316, tg = 23.62 t/s, tg_3s = 24.90 t/s 6.33.428.215 I slot print_timing: id 0 | task 6891 | n_gen = 316, tg = 24.17 t/s, tg_3s = 24.89 t/s 6.34.961.951 I slot print_timing: id 3 | task 6884 | prompt eval time = 391.42 ms / 62 tokens ( 6.31 ms per token, 158.40 tokens per second) 6.34.961.956 I slot print_timing: id 3 | task 6884 | eval time = 15107.95 ms / 360 tokens ( 42.08 ms per token, 23.76 tokens per second) 6.34.961.957 I slot print_timing: id 3 | task 6884 | total time = 15499.37 ms / 422 tokens 6.34.961.958 I slot print_timing: id 3 | task 6884 | graphs reused = 6558 6.34.961.959 I slot print_timing: id 3 | task 6884 | graph reallocs = 0 / 0 (same size) / (changed size) 6.34.962.046 I slot release: id 3 | task 6884 | stop processing: n_tokens = 1392, truncated = 0 6.35.003.732 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.698 6.35.003.758 I slot launch_slot_: id 3 | task 7249 | processing task, is_child = 0 6.35.469.078 I slot print_timing: id 2 | task 7007 | n_gen = 241, tg = 23.88 t/s, tg_3s = 21.40 t/s 6.35.830.220 I slot print_timing: id 1 | task 6738 | n_gen = 514, tg = 22.91 t/s, tg_3s = 20.98 t/s 6.35.918.759 I slot print_timing: id 1 | task 6738 | prompt eval time = 477.25 ms / 79 tokens ( 6.04 ms per token, 165.53 tokens per second) 6.35.918.764 I slot print_timing: id 1 | task 6738 | eval time = 22483.49 ms / 516 tokens ( 43.66 ms per token, 22.91 tokens per second) 6.35.918.765 I slot print_timing: id 1 | task 6738 | total time = 22960.74 ms / 595 tokens 6.35.918.766 I slot print_timing: id 1 | task 6738 | graphs reused = 6566 6.35.918.767 I slot print_timing: id 1 | task 6738 | graph reallocs = 0 / 0 (same size) / (changed size) 6.35.918.850 I slot release: id 1 | task 6738 | stop processing: n_tokens = 1565, truncated = 0 6.35.977.418 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.620 6.35.977.449 I slot launch_slot_: id 1 | task 7262 | processing task, is_child = 0 6.36.465.237 I slot print_timing: id 0 | task 6891 | n_gen = 369, tg = 22.90 t/s, tg_3s = 17.45 t/s 6.38.505.569 I slot print_timing: id 2 | task 7007 | n_gen = 305, tg = 23.23 t/s, tg_3s = 21.08 t/s 6.39.503.628 I slot print_timing: id 0 | task 6891 | n_gen = 445, tg = 23.24 t/s, tg_3s = 25.01 t/s 6.39.950.204 I slot print_timing: id 3 | task 7249 | n_gen = 100, tg = 22.49 t/s, tg_3s = 22.72 t/s 6.40.429.951 I slot print_timing: id 1 | task 7262 | n_gen = 100, tg = 24.97 t/s, tg_3s = 25.22 t/s 6.41.069.979 I slot print_timing: id 2 | task 7007 | prompt eval time = 486.92 ms / 91 tokens ( 5.35 ms per token, 186.89 tokens per second) 6.41.069.983 I slot print_timing: id 2 | task 7007 | eval time = 15651.03 ms / 369 tokens ( 42.53 ms per token, 23.51 tokens per second) 6.41.069.984 I slot print_timing: id 2 | task 7007 | total time = 16137.95 ms / 460 tokens 6.41.069.984 I slot print_timing: id 2 | task 7007 | graphs reused = 6679 6.41.069.985 I slot print_timing: id 2 | task 7007 | graph reallocs = 0 / 0 (same size) / (changed size) 6.41.070.056 I slot release: id 2 | task 7007 | stop processing: n_tokens = 1430, truncated = 0 6.41.127.470 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.679 6.41.127.496 I slot launch_slot_: id 2 | task 7381 | processing task, is_child = 0 6.42.505.744 I slot print_timing: id 0 | task 6891 | n_gen = 510, tg = 23.02 t/s, tg_3s = 21.65 t/s 6.42.986.229 I slot print_timing: id 3 | task 7249 | n_gen = 166, tg = 22.18 t/s, tg_3s = 21.74 t/s 6.43.465.104 I slot print_timing: id 1 | task 7262 | n_gen = 166, tg = 23.57 t/s, tg_3s = 21.75 t/s 6.45.509.845 I slot print_timing: id 0 | task 6891 | n_gen = 585, tg = 23.26 t/s, tg_3s = 24.97 t/s 6.45.550.337 I slot print_timing: id 2 | task 7381 | n_gen = 100, tg = 24.86 t/s, tg_3s = 25.11 t/s 6.45.991.730 I slot print_timing: id 3 | task 7249 | n_gen = 241, tg = 22.98 t/s, tg_3s = 24.95 t/s 6.46.472.773 I slot print_timing: id 1 | task 7262 | n_gen = 241, tg = 23.98 t/s, tg_3s = 24.94 t/s 6.48.524.878 I slot print_timing: id 0 | task 6891 | n_gen = 660, tg = 23.43 t/s, tg_3s = 24.88 t/s 6.48.565.555 I slot print_timing: id 2 | task 7381 | n_gen = 175, tg = 24.87 t/s, tg_3s = 24.87 t/s 6.49.008.687 I slot print_timing: id 3 | task 7249 | n_gen = 316, tg = 23.40 t/s, tg_3s = 24.86 t/s 6.49.491.548 I slot print_timing: id 1 | task 7262 | n_gen = 316, tg = 24.18 t/s, tg_3s = 24.84 t/s 6.49.612.669 I slot print_timing: id 2 | task 7381 | prompt eval time = 440.56 ms / 69 tokens ( 6.38 ms per token, 156.62 tokens per second) 6.49.612.675 I slot print_timing: id 2 | task 7381 | eval time = 8044.61 ms / 201 tokens ( 40.22 ms per token, 24.86 tokens per second) 6.49.612.676 I slot print_timing: id 2 | task 7381 | total time = 8485.16 ms / 270 tokens 6.49.612.676 I slot print_timing: id 2 | task 7381 | graphs reused = 6877 6.49.612.677 I slot print_timing: id 2 | task 7381 | graph reallocs = 0 / 0 (same size) / (changed size) 6.49.612.752 I slot release: id 2 | task 7381 | stop processing: n_tokens = 1240, truncated = 0 6.49.670.971 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.783 6.49.671.004 I slot launch_slot_: id 2 | task 7585 | processing task, is_child = 0 6.50.938.200 I slot print_timing: id 1 | task 7262 | prompt eval time = 487.92 ms / 85 tokens ( 5.74 ms per token, 174.21 tokens per second) 6.50.938.207 I slot print_timing: id 1 | task 7262 | eval time = 14472.82 ms / 342 tokens ( 42.44 ms per token, 23.56 tokens per second) 6.50.938.208 I slot print_timing: id 1 | task 7262 | total time = 14960.74 ms / 427 tokens 6.50.938.209 I slot print_timing: id 1 | task 7262 | graphs reused = 6896 6.50.938.209 I slot print_timing: id 1 | task 7262 | graph reallocs = 0 / 0 (same size) / (changed size) 6.50.938.290 I slot release: id 1 | task 7262 | stop processing: n_tokens = 1397, truncated = 0 6.50.995.853 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.695 6.50.995.877 I slot launch_slot_: id 1 | task 7609 | processing task, is_child = 0 6.51.539.170 I slot print_timing: id 0 | task 6891 | n_gen = 714, tg = 22.90 t/s, tg_3s = 17.91 t/s 6.52.026.276 I slot print_timing: id 3 | task 7249 | n_gen = 370, tg = 22.39 t/s, tg_3s = 17.90 t/s 6.54.565.039 I slot print_timing: id 0 | task 6891 | n_gen = 789, tg = 23.06 t/s, tg_3s = 24.79 t/s 6.54.565.379 I slot print_timing: id 2 | task 7585 | n_gen = 100, tg = 22.29 t/s, tg_3s = 22.52 t/s 6.55.048.301 I slot print_timing: id 3 | task 7249 | n_gen = 445, tg = 22.77 t/s, tg_3s = 24.82 t/s 6.55.490.690 I slot print_timing: id 1 | task 7609 | n_gen = 100, tg = 24.78 t/s, tg_3s = 25.03 t/s 6.57.587.184 I slot print_timing: id 0 | task 6891 | n_gen = 864, tg = 23.21 t/s, tg_3s = 24.82 t/s 6.57.587.529 I slot print_timing: id 2 | task 7585 | n_gen = 175, tg = 23.31 t/s, tg_3s = 24.82 t/s 6.58.070.959 I slot print_timing: id 3 | task 7249 | n_gen = 520, tg = 23.04 t/s, tg_3s = 24.81 t/s 6.58.513.941 I slot print_timing: id 1 | task 7609 | n_gen = 175, tg = 24.79 t/s, tg_3s = 24.81 t/s 7.00.613.041 I slot print_timing: id 0 | task 6891 | n_gen = 939, tg = 23.32 t/s, tg_3s = 24.79 t/s 7.00.613.381 I slot print_timing: id 2 | task 7585 | n_gen = 250, tg = 23.74 t/s, tg_3s = 24.79 t/s 7.01.097.140 I slot print_timing: id 3 | task 7249 | n_gen = 595, tg = 23.25 t/s, tg_3s = 24.78 t/s 7.01.540.861 I slot print_timing: id 1 | task 7609 | n_gen = 250, tg = 24.79 t/s, tg_3s = 24.78 t/s 7.03.640.568 I slot print_timing: id 0 | task 6891 | n_gen = 1014, tg = 23.43 t/s, tg_3s = 24.77 t/s 7.03.640.908 I slot print_timing: id 2 | task 7585 | n_gen = 325, tg = 23.97 t/s, tg_3s = 24.77 t/s 7.04.054.368 I slot print_timing: id 0 | task 6891 | prompt eval time = 384.63 ms / 62 tokens ( 6.20 ms per token, 161.19 tokens per second) 7.04.054.373 I slot print_timing: id 0 | task 6891 | eval time = 43656.94 ms / 1024 tokens ( 42.68 ms per token, 23.43 tokens per second) 7.04.054.374 I slot print_timing: id 0 | task 6891 | total time = 44041.58 ms / 1086 tokens 7.04.054.375 I slot print_timing: id 0 | task 6891 | graphs reused = 7204 7.04.054.376 I slot print_timing: id 0 | task 6891 | graph reallocs = 0 / 0 (same size) / (changed size) 7.04.054.442 I slot release: id 0 | task 6891 | stop processing: n_tokens = 2056, truncated = 0 7.04.096.138 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.472 7.04.126.524 I slot launch_slot_: id 0 | task 7924 | processing task, is_child = 0 7.04.477.622 I slot print_timing: id 3 | task 7249 | n_gen = 670, tg = 23.13 t/s, tg_3s = 22.19 t/s 7.04.555.886 I slot print_timing: id 1 | task 7609 | n_gen = 315, tg = 24.04 t/s, tg_3s = 21.56 t/s 7.06.663.953 I slot print_timing: id 2 | task 7585 | n_gen = 390, tg = 23.52 t/s, tg_3s = 21.50 t/s 7.07.508.219 I slot print_timing: id 3 | task 7249 | n_gen = 744, tg = 23.25 t/s, tg_3s = 24.42 t/s 7.07.588.534 I slot print_timing: id 1 | task 7609 | n_gen = 390, tg = 24.17 t/s, tg_3s = 24.73 t/s 7.08.553.136 I slot print_timing: id 0 | task 7924 | n_gen = 100, tg = 24.77 t/s, tg_3s = 25.02 t/s 7.09.679.827 I slot print_timing: id 2 | task 7585 | n_gen = 465, tg = 23.73 t/s, tg_3s = 24.87 t/s 7.10.525.089 I slot print_timing: id 3 | task 7249 | n_gen = 819, tg = 23.39 t/s, tg_3s = 24.86 t/s 7.10.605.714 I slot print_timing: id 1 | task 7609 | n_gen = 465, tg = 24.28 t/s, tg_3s = 24.86 t/s 7.10.848.086 I slot print_timing: id 2 | task 7585 | prompt eval time = 453.25 ms / 73 tokens ( 6.21 ms per token, 161.06 tokens per second) 7.10.848.090 I slot print_timing: id 2 | task 7585 | eval time = 20723.83 ms / 494 tokens ( 42.04 ms per token, 23.79 tokens per second) 7.10.848.091 I slot print_timing: id 2 | task 7585 | total time = 21177.07 ms / 567 tokens 7.10.848.092 I slot print_timing: id 2 | task 7585 | graphs reused = 7359 7.10.848.093 I slot print_timing: id 2 | task 7585 | graph reallocs = 0 / 0 (same size) / (changed size) 7.10.848.168 I slot release: id 2 | task 7585 | stop processing: n_tokens = 1537, truncated = 0 7.10.906.359 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.632 7.10.906.388 I slot launch_slot_: id 2 | task 8084 | processing task, is_child = 0 7.11.590.480 I slot print_timing: id 0 | task 7924 | n_gen = 165, tg = 23.31 t/s, tg_3s = 21.40 t/s 7.13.162.212 I slot print_timing: id 0 | task 7924 | prompt eval time = 429.27 ms / 76 tokens ( 5.65 ms per token, 177.04 tokens per second) 7.13.162.220 I slot print_timing: id 0 | task 7924 | eval time = 8606.40 ms / 204 tokens ( 42.40 ms per token, 23.59 tokens per second) 7.13.162.221 I slot print_timing: id 0 | task 7924 | total time = 9035.68 ms / 280 tokens 7.13.162.222 I slot print_timing: id 0 | task 7924 | graphs reused = 7402 7.13.162.223 I slot print_timing: id 0 | task 7924 | graph reallocs = 0 / 0 (same size) / (changed size) 7.13.162.293 I slot release: id 0 | task 7924 | stop processing: n_tokens = 1249, truncated = 0 7.13.204.259 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.777 7.13.204.283 I slot launch_slot_: id 0 | task 8132 | processing task, is_child = 0 7.13.564.173 I slot print_timing: id 3 | task 7249 | n_gen = 876, tg = 23.02 t/s, tg_3s = 18.76 t/s 7.13.642.423 I slot print_timing: id 1 | task 7609 | n_gen = 521, tg = 23.48 t/s, tg_3s = 18.44 t/s 7.14.287.652 I slot print_timing: id 1 | task 7609 | prompt eval time = 500.26 ms / 100 tokens ( 5.00 ms per token, 199.90 tokens per second) 7.14.287.660 I slot print_timing: id 1 | task 7609 | eval time = 22791.50 ms / 537 tokens ( 42.52 ms per token, 23.52 tokens per second) 7.14.287.661 I slot print_timing: id 1 | task 7609 | total time = 23291.76 ms / 637 tokens 7.14.287.662 I slot print_timing: id 1 | task 7609 | graphs reused = 7418 7.14.287.662 I slot print_timing: id 1 | task 7609 | graph reallocs = 0 / 0 (same size) / (changed size) 7.14.287.735 I slot release: id 1 | task 7609 | stop processing: n_tokens = 1607, truncated = 0 7.14.345.315 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.604 7.14.345.341 I slot launch_slot_: id 1 | task 8152 | processing task, is_child = 0 7.16.162.281 I slot print_timing: id 2 | task 8084 | n_gen = 100, tg = 20.72 t/s, tg_3s = 20.93 t/s 7.16.564.740 I slot print_timing: id 3 | task 7249 | n_gen = 939, tg = 22.87 t/s, tg_3s = 21.00 t/s 7.18.068.937 I slot print_timing: id 0 | task 8132 | n_gen = 100, tg = 22.36 t/s, tg_3s = 22.59 t/s 7.18.839.586 I slot print_timing: id 1 | task 8152 | n_gen = 100, tg = 24.72 t/s, tg_3s = 24.97 t/s 7.19.163.917 I slot print_timing: id 2 | task 8084 | n_gen = 174, tg = 22.24 t/s, tg_3s = 24.65 t/s 7.19.569.738 I slot print_timing: id 3 | task 7249 | n_gen = 1013, tg = 22.99 t/s, tg_3s = 24.63 t/s 7.20.015.460 I slot print_timing: id 3 | task 7249 | prompt eval time = 544.35 ms / 134 tokens ( 4.06 ms per token, 246.16 tokens per second) 7.20.015.465 I slot print_timing: id 3 | task 7249 | eval time = 44467.34 ms / 1024 tokens ( 43.47 ms per token, 23.01 tokens per second) 7.20.015.466 I slot print_timing: id 3 | task 7249 | total time = 45011.69 ms / 1158 tokens 7.20.015.467 I slot print_timing: id 3 | task 7249 | graphs reused = 7544 7.20.015.468 I slot print_timing: id 3 | task 7249 | graph reallocs = 0 / 0 (same size) / (changed size) 7.20.015.561 I slot release: id 3 | task 7249 | stop processing: n_tokens = 2128, truncated = 0 7.20.056.343 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.456 7.20.089.669 I slot launch_slot_: id 3 | task 8284 | processing task, is_child = 0 7.21.080.052 I slot print_timing: id 0 | task 8132 | n_gen = 165, tg = 22.05 t/s, tg_3s = 21.59 t/s 7.21.843.311 I slot print_timing: id 1 | task 8152 | n_gen = 165, tg = 23.40 t/s, tg_3s = 21.64 t/s 7.22.201.423 I slot print_timing: id 2 | task 8084 | n_gen = 240, tg = 22.10 t/s, tg_3s = 21.73 t/s 7.24.118.110 I slot print_timing: id 0 | task 8132 | n_gen = 241, tg = 22.91 t/s, tg_3s = 25.02 t/s 7.24.478.168 I slot print_timing: id 3 | task 8284 | n_gen = 100, tg = 24.99 t/s, tg_3s = 25.24 t/s 7.24.878.306 I slot print_timing: id 1 | task 8152 | n_gen = 241, tg = 23.89 t/s, tg_3s = 25.04 t/s 7.25.238.074 I slot print_timing: id 2 | task 8084 | n_gen = 316, tg = 22.74 t/s, tg_3s = 25.03 t/s 7.27.157.515 I slot print_timing: id 0 | task 8132 | n_gen = 317, tg = 23.38 t/s, tg_3s = 25.00 t/s 7.27.517.530 I slot print_timing: id 3 | task 8284 | n_gen = 176, tg = 25.00 t/s, tg_3s = 25.01 t/s 7.27.917.883 I slot print_timing: id 1 | task 8152 | n_gen = 317, tg = 24.15 t/s, tg_3s = 25.00 t/s 7.28.238.507 I slot print_timing: id 2 | task 8084 | n_gen = 391, tg = 23.14 t/s, tg_3s = 25.00 t/s 7.30.004.584 I slot print_timing: id 1 | task 8152 | prompt eval time = 488.67 ms / 85 tokens ( 5.75 ms per token, 173.94 tokens per second) 7.30.004.591 I slot print_timing: id 1 | task 8152 | eval time = 15170.56 ms / 369 tokens ( 41.22 ms per token, 24.26 tokens per second) 7.30.004.593 I slot print_timing: id 1 | task 8152 | total time = 15659.23 ms / 454 tokens 7.30.004.593 I slot print_timing: id 1 | task 8152 | graphs reused = 7778 7.30.004.594 I slot print_timing: id 1 | task 8152 | graph reallocs = 0 / 0 (same size) / (changed size) 7.30.004.667 I slot release: id 1 | task 8152 | stop processing: n_tokens = 1424, truncated = 0 7.30.061.879 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.682 7.30.061.918 I slot launch_slot_: id 1 | task 8525 | processing task, is_child = 0 7.30.452.847 I slot print_timing: id 0 | task 8132 | n_gen = 390, tg = 23.14 t/s, tg_3s = 22.15 t/s 7.30.559.429 I slot print_timing: id 3 | task 8284 | n_gen = 241, tg = 23.90 t/s, tg_3s = 21.37 t/s 7.31.249.485 I slot print_timing: id 2 | task 8084 | n_gen = 455, tg = 22.85 t/s, tg_3s = 21.26 t/s 7.32.417.542 I slot print_timing: id 2 | task 8084 | prompt eval time = 478.57 ms / 85 tokens ( 5.63 ms per token, 177.61 tokens per second) 7.32.417.549 I slot print_timing: id 2 | task 8084 | eval time = 21032.58 ms / 484 tokens ( 43.55 ms per token, 22.96 tokens per second) 7.32.417.550 I slot print_timing: id 2 | task 8084 | total time = 21511.15 ms / 569 tokens 7.32.417.550 I slot print_timing: id 2 | task 8084 | graphs reused = 7822 7.32.417.551 I slot print_timing: id 2 | task 8084 | graph reallocs = 0 / 0 (same size) / (changed size) 7.32.417.622 I slot release: id 2 | task 8084 | stop processing: n_tokens = 1539, truncated = 0 7.32.474.704 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.631 7.32.474.735 I slot launch_slot_: id 2 | task 8575 | processing task, is_child = 0 7.33.459.825 I slot print_timing: id 0 | task 8132 | n_gen = 453, tg = 22.81 t/s, tg_3s = 20.95 t/s 7.33.580.212 I slot print_timing: id 3 | task 8284 | n_gen = 306, tg = 23.35 t/s, tg_3s = 21.52 t/s 7.34.704.878 I slot print_timing: id 0 | task 8132 | prompt eval time = 438.06 ms / 87 tokens ( 5.04 ms per token, 198.60 tokens per second) 7.34.704.885 I slot print_timing: id 0 | task 8132 | eval time = 21062.53 ms / 484 tokens ( 43.61 ms per token, 22.93 tokens per second) 7.34.704.886 I slot print_timing: id 0 | task 8132 | total time = 21500.58 ms / 571 tokens 7.34.704.887 I slot print_timing: id 0 | task 8132 | graphs reused = 7864 7.34.704.888 I slot print_timing: id 0 | task 8132 | graph reallocs = 0 / 0 (same size) / (changed size) 7.34.704.961 I slot release: id 0 | task 8132 | stop processing: n_tokens = 1541, truncated = 0 7.34.746.284 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.630 7.34.746.309 I slot launch_slot_: id 0 | task 8623 | processing task, is_child = 0 7.35.266.030 I slot print_timing: id 1 | task 8525 | n_gen = 100, tg = 21.03 t/s, tg_3s = 21.25 t/s 7.36.589.302 I slot print_timing: id 3 | task 8284 | n_gen = 373, tg = 23.14 t/s, tg_3s = 22.27 t/s 7.37.228.795 I slot print_timing: id 2 | task 8575 | n_gen = 100, tg = 23.07 t/s, tg_3s = 23.31 t/s 7.38.266.614 I slot print_timing: id 1 | task 8525 | n_gen = 175, tg = 22.58 t/s, tg_3s = 25.00 t/s 7.39.106.146 I slot print_timing: id 0 | task 8623 | n_gen = 100, tg = 24.99 t/s, tg_3s = 25.24 t/s 7.39.592.602 I slot print_timing: id 3 | task 8284 | n_gen = 448, tg = 23.43 t/s, tg_3s = 24.97 t/s 7.40.231.455 I slot print_timing: id 2 | task 8575 | n_gen = 175, tg = 23.86 t/s, tg_3s = 24.98 t/s 7.40.511.197 I slot print_timing: id 1 | task 8525 | prompt eval time = 497.19 ms / 84 tokens ( 5.92 ms per token, 168.95 tokens per second) 7.40.511.202 I slot print_timing: id 1 | task 8525 | eval time = 9952.08 ms / 231 tokens ( 43.27 ms per token, 23.11 tokens per second) 7.40.511.203 I slot print_timing: id 1 | task 8525 | total time = 10449.27 ms / 315 tokens 7.40.511.203 I slot print_timing: id 1 | task 8525 | graphs reused = 7997 7.40.511.204 I slot print_timing: id 1 | task 8525 | graph reallocs = 0 / 0 (same size) / (changed size) 7.40.511.277 I slot release: id 1 | task 8525 | stop processing: n_tokens = 1285, truncated = 0 7.40.568.634 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.756 7.40.568.673 I slot launch_slot_: id 1 | task 8761 | processing task, is_child = 0 7.41.683.748 I slot print_timing: id 0 | task 8623 | prompt eval time = 397.89 ms / 66 tokens ( 6.03 ms per token, 165.88 tokens per second) 7.41.683.755 I slot print_timing: id 0 | task 8623 | eval time = 6539.54 ms / 155 tokens ( 42.46 ms per token, 23.55 tokens per second) 7.41.683.756 I slot print_timing: id 0 | task 8623 | total time = 6937.43 ms / 221 tokens 7.41.683.757 I slot print_timing: id 0 | task 8623 | graphs reused = 8013 7.41.683.757 I slot print_timing: id 0 | task 8623 | graph reallocs = 0 / 0 (same size) / (changed size) 7.41.683.830 I slot release: id 0 | task 8623 | stop processing: n_tokens = 1191, truncated = 0 7.41.725.016 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.815 7.41.725.042 I slot launch_slot_: id 0 | task 8782 | processing task, is_child = 0 7.42.598.884 I slot print_timing: id 3 | task 8284 | n_gen = 503, tg = 22.73 t/s, tg_3s = 18.30 t/s 7.42.679.174 I slot print_timing: id 2 | task 8575 | prompt eval time = 463.42 ms / 74 tokens ( 6.26 ms per token, 159.68 tokens per second) 7.42.679.184 I slot print_timing: id 2 | task 8575 | eval time = 9741.00 ms / 216 tokens ( 45.31 ms per token, 22.07 tokens per second) 7.42.679.185 I slot print_timing: id 2 | task 8575 | total time = 10204.42 ms / 290 tokens 7.42.679.186 I slot print_timing: id 2 | task 8575 | graphs reused = 8023 7.42.679.187 I slot print_timing: id 2 | task 8575 | graph reallocs = 0 / 0 (same size) / (changed size) 7.42.679.278 I slot release: id 2 | task 8575 | stop processing: n_tokens = 1260, truncated = 0 7.42.742.191 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.771 7.42.742.221 I slot launch_slot_: id 2 | task 8797 | processing task, is_child = 0 7.45.627.204 I slot print_timing: id 3 | task 8284 | n_gen = 568, tg = 22.58 t/s, tg_3s = 21.46 t/s 7.45.827.101 I slot print_timing: id 1 | task 8761 | n_gen = 100, tg = 20.52 t/s, tg_3s = 20.72 t/s 7.46.627.249 I slot print_timing: id 0 | task 8782 | n_gen = 100, tg = 22.54 t/s, tg_3s = 22.77 t/s 7.47.187.552 I slot print_timing: id 2 | task 8797 | n_gen = 100, tg = 24.92 t/s, tg_3s = 25.17 t/s 7.47.988.813 I slot print_timing: id 1 | task 8761 | prompt eval time = 433.11 ms / 65 tokens ( 6.66 ms per token, 150.08 tokens per second) 7.47.988.817 I slot print_timing: id 1 | task 8761 | eval time = 6987.02 ms / 154 tokens ( 45.67 ms per token, 21.90 tokens per second) 7.47.988.818 I slot print_timing: id 1 | task 8761 | total time = 7420.13 ms / 219 tokens 7.47.988.819 I slot print_timing: id 1 | task 8761 | graphs reused = 8141 7.47.988.820 I slot print_timing: id 1 | task 8761 | graph reallocs = 0 / 0 (same size) / (changed size) 7.47.988.891 I slot release: id 1 | task 8761 | stop processing: n_tokens = 1189, truncated = 0 7.48.046.602 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.817 7.48.046.625 I slot launch_slot_: id 1 | task 8920 | processing task, is_child = 0 7.48.655.058 I slot print_timing: id 3 | task 8284 | n_gen = 633, tg = 22.46 t/s, tg_3s = 21.47 t/s 7.49.627.862 I slot print_timing: id 0 | task 8782 | n_gen = 164, tg = 22.05 t/s, tg_3s = 21.33 t/s 7.50.190.799 I slot print_timing: id 2 | task 8797 | n_gen = 164, tg = 23.37 t/s, tg_3s = 21.31 t/s 7.51.676.649 I slot print_timing: id 3 | task 8284 | n_gen = 708, tg = 22.69 t/s, tg_3s = 24.82 t/s 7.52.521.400 I slot print_timing: id 1 | task 8920 | n_gen = 100, tg = 24.81 t/s, tg_3s = 25.06 t/s 7.52.642.151 I slot print_timing: id 0 | task 8782 | n_gen = 239, tg = 22.87 t/s, tg_3s = 24.88 t/s 7.53.204.987 I slot print_timing: id 2 | task 8797 | n_gen = 239, tg = 23.82 t/s, tg_3s = 24.88 t/s 7.54.699.144 I slot print_timing: id 3 | task 8284 | n_gen = 783, tg = 22.88 t/s, tg_3s = 24.81 t/s 7.54.779.416 I slot print_timing: id 2 | task 8797 | prompt eval time = 472.76 ms / 83 tokens ( 5.70 ms per token, 175.57 tokens per second) 7.54.779.423 I slot print_timing: id 2 | task 8797 | eval time = 11564.43 ms / 278 tokens ( 41.75 ms per token, 23.95 tokens per second) 7.54.779.424 I slot print_timing: id 2 | task 8797 | total time = 12037.19 ms / 361 tokens 7.54.779.425 I slot print_timing: id 2 | task 8797 | graphs reused = 8294 7.54.779.426 I slot print_timing: id 2 | task 8797 | graph reallocs = 0 / 0 (same size) / (changed size) 7.54.779.495 I slot release: id 2 | task 8797 | stop processing: n_tokens = 1331, truncated = 0 7.54.837.493 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.730 7.54.837.528 I slot launch_slot_: id 2 | task 9079 | processing task, is_child = 0 7.55.548.276 I slot print_timing: id 1 | task 8920 | n_gen = 165, tg = 23.37 t/s, tg_3s = 21.47 t/s 7.55.669.012 I slot print_timing: id 0 | task 8782 | n_gen = 304, tg = 22.55 t/s, tg_3s = 21.47 t/s 7.57.720.037 I slot print_timing: id 3 | task 8284 | n_gen = 848, tg = 22.77 t/s, tg_3s = 21.52 t/s 7.58.523.559 I slot print_timing: id 1 | task 8920 | prompt eval time = 484.30 ms / 82 tokens ( 5.91 ms per token, 169.32 tokens per second) 7.58.523.566 I slot print_timing: id 1 | task 8920 | eval time = 9992.62 ms / 239 tokens ( 41.99 ms per token, 23.82 tokens per second) 7.58.523.567 I slot print_timing: id 1 | task 8920 | total time = 10476.92 ms / 321 tokens 7.58.523.568 I slot print_timing: id 1 | task 8920 | graphs reused = 8373 7.58.523.569 I slot print_timing: id 1 | task 8920 | graph reallocs = 0 / 0 (same size) / (changed size) 7.58.523.652 I slot release: id 1 | task 8920 | stop processing: n_tokens = 1291, truncated = 0 7.58.581.024 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.752 7.58.581.049 I slot launch_slot_: id 1 | task 9163 | processing task, is_child = 0 7.58.964.838 I slot print_timing: id 0 | task 8782 | n_gen = 377, tg = 22.47 t/s, tg_3s = 22.15 t/s 7.59.712.087 I slot print_timing: id 2 | task 9079 | n_gen = 100, tg = 22.42 t/s, tg_3s = 22.64 t/s 8.00.756.802 I slot print_timing: id 3 | task 8284 | n_gen = 913, tg = 22.66 t/s, tg_3s = 21.40 t/s 8.01.279.010 I slot print_timing: id 3 | task 8284 | prompt eval time = 426.66 ms / 70 tokens ( 6.10 ms per token, 164.07 tokens per second) 8.01.279.017 I slot print_timing: id 3 | task 8284 | eval time = 40762.67 ms / 926 tokens ( 44.07 ms per token, 22.69 tokens per second) 8.01.279.018 I slot print_timing: id 3 | task 8284 | total time = 41189.33 ms / 996 tokens 8.01.279.019 I slot print_timing: id 3 | task 8284 | graphs reused = 8427 8.01.279.019 I slot print_timing: id 3 | task 8284 | graph reallocs = 0 / 0 (same size) / (changed size) 8.01.279.093 I slot release: id 3 | task 8284 | stop processing: n_tokens = 1965, truncated = 0 8.01.320.367 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.494 8.01.354.917 I slot launch_slot_: id 3 | task 9222 | processing task, is_child = 0 8.01.979.095 I slot print_timing: id 0 | task 8782 | n_gen = 442, tg = 22.34 t/s, tg_3s = 21.56 t/s 8.02.745.031 I slot print_timing: id 2 | task 9079 | n_gen = 167, tg = 22.28 t/s, tg_3s = 22.09 t/s 8.03.383.290 I slot print_timing: id 1 | task 9163 | n_gen = 100, tg = 22.91 t/s, tg_3s = 23.14 t/s 8.04.665.101 I slot print_timing: id 2 | task 9079 | prompt eval time = 458.36 ms / 72 tokens ( 6.37 ms per token, 157.08 tokens per second) 8.04.665.109 I slot print_timing: id 2 | task 9079 | eval time = 9369.20 ms / 215 tokens ( 43.78 ms per token, 22.84 tokens per second) 8.04.665.110 I slot print_timing: id 2 | task 9079 | total time = 9827.56 ms / 287 tokens 8.04.665.110 I slot print_timing: id 2 | task 9079 | graphs reused = 8499 8.04.665.111 I slot print_timing: id 2 | task 9079 | graph reallocs = 0 / 0 (same size) / (changed size) 8.04.665.183 I slot release: id 2 | task 9079 | stop processing: n_tokens = 1257, truncated = 0 8.04.723.415 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.772 8.04.723.440 I slot launch_slot_: id 2 | task 9299 | processing task, is_child = 0 8.05.129.361 I slot print_timing: id 0 | task 8782 | prompt eval time = 509.51 ms / 130 tokens ( 3.92 ms per token, 255.15 tokens per second) 8.05.129.366 I slot print_timing: id 0 | task 8782 | eval time = 22894.80 ms / 511 tokens ( 44.89 ms per token, 22.28 tokens per second) 8.05.129.367 I slot print_timing: id 0 | task 8782 | total time = 23404.31 ms / 641 tokens 8.05.129.367 I slot print_timing: id 0 | task 8782 | graphs reused = 8499 8.05.129.368 I slot print_timing: id 0 | task 8782 | graph reallocs = 0 / 0 (same size) / (changed size) 8.05.129.421 I slot release: id 0 | task 8782 | stop processing: n_tokens = 1611, truncated = 0 8.05.218.424 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.603 8.05.218.446 I slot launch_slot_: id 0 | task 9302 | processing task, is_child = 0 8.06.402.189 I slot print_timing: id 1 | task 9163 | n_gen = 157, tg = 21.25 t/s, tg_3s = 18.88 t/s 8.06.442.195 I slot print_timing: id 3 | task 9222 | n_gen = 100, tg = 21.05 t/s, tg_3s = 21.26 t/s 8.07.759.511 I slot print_timing: id 1 | task 9163 | prompt eval time = 480.92 ms / 83 tokens ( 5.79 ms per token, 172.59 tokens per second) 8.07.759.516 I slot print_timing: id 1 | task 9163 | eval time = 8697.53 ms / 191 tokens ( 45.78 ms per token, 21.85 tokens per second) 8.07.759.517 I slot print_timing: id 1 | task 9163 | total time = 9178.45 ms / 274 tokens 8.07.759.518 I slot print_timing: id 1 | task 9163 | graphs reused = 8551 8.07.759.519 I slot print_timing: id 1 | task 9163 | graph reallocs = 0 / 0 (same size) / (changed size) 8.07.759.594 I slot release: id 1 | task 9163 | stop processing: n_tokens = 1244, truncated = 0 8.07.816.573 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.781 8.07.816.598 I slot launch_slot_: id 1 | task 9360 | processing task, is_child = 0 8.09.444.486 I slot print_timing: id 3 | task 9222 | n_gen = 163, tg = 21.02 t/s, tg_3s = 20.98 t/s 8.09.961.344 I slot print_timing: id 2 | task 9299 | n_gen = 100, tg = 20.87 t/s, tg_3s = 21.08 t/s 8.10.040.394 I slot print_timing: id 0 | task 9302 | n_gen = 100, tg = 22.28 t/s, tg_3s = 22.50 t/s 8.10.398.578 I slot print_timing: id 3 | task 9222 | prompt eval time = 383.87 ms / 57 tokens ( 6.73 ms per token, 148.49 tokens per second) 8.10.398.585 I slot print_timing: id 3 | task 9222 | eval time = 8659.78 ms / 187 tokens ( 46.56 ms per token, 21.48 tokens per second) 8.10.398.586 I slot print_timing: id 3 | task 9222 | total time = 9043.64 ms / 244 tokens 8.10.398.587 I slot print_timing: id 3 | task 9222 | graphs reused = 8601 8.10.398.588 I slot print_timing: id 3 | task 9222 | graph reallocs = 0 / 0 (same size) / (changed size) 8.10.398.664 I slot release: id 3 | task 9222 | stop processing: n_tokens = 1212, truncated = 0 8.10.439.600 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.801 8.10.439.624 I slot launch_slot_: id 3 | task 9415 | processing task, is_child = 0 8.12.684.297 I slot print_timing: id 1 | task 9360 | n_gen = 100, tg = 22.91 t/s, tg_3s = 23.14 t/s 8.12.968.953 I slot print_timing: id 2 | task 9299 | n_gen = 166, tg = 21.29 t/s, tg_3s = 21.94 t/s 8.13.048.126 I slot print_timing: id 0 | task 9302 | n_gen = 166, tg = 22.14 t/s, tg_3s = 21.94 t/s 8.14.840.634 I slot print_timing: id 3 | task 9415 | n_gen = 100, tg = 25.03 t/s, tg_3s = 25.29 t/s 8.15.721.582 I slot print_timing: id 1 | task 9360 | n_gen = 176, tg = 23.78 t/s, tg_3s = 25.02 t/s 8.16.001.587 I slot print_timing: id 2 | task 9299 | n_gen = 242, tg = 22.35 t/s, tg_3s = 25.06 t/s 8.16.080.701 I slot print_timing: id 0 | task 9302 | n_gen = 242, tg = 22.99 t/s, tg_3s = 25.06 t/s 8.17.318.278 I slot print_timing: id 1 | task 9360 | prompt eval time = 545.55 ms / 117 tokens ( 4.66 ms per token, 214.46 tokens per second) 8.17.318.287 I slot print_timing: id 1 | task 9360 | eval time = 8956.12 ms / 216 tokens ( 41.66 ms per token, 24.01 tokens per second) 8.17.318.288 I slot print_timing: id 1 | task 9360 | total time = 9501.67 ms / 333 tokens 8.17.318.289 I slot print_timing: id 1 | task 9360 | graphs reused = 8759 8.17.318.289 I slot print_timing: id 1 | task 9360 | graph reallocs = 0 / 0 (same size) / (changed size) 8.17.318.368 I slot release: id 1 | task 9360 | stop processing: n_tokens = 1303, truncated = 0 8.17.375.613 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.745 8.17.375.641 I slot launch_slot_: id 1 | task 9580 | processing task, is_child = 0 8.17.844.595 I slot print_timing: id 3 | task 9415 | n_gen = 165, tg = 23.57 t/s, tg_3s = 21.64 t/s 8.19.009.844 I slot print_timing: id 2 | task 9299 | n_gen = 307, tg = 22.19 t/s, tg_3s = 21.61 t/s 8.19.089.223 I slot print_timing: id 0 | task 9302 | n_gen = 307, tg = 22.68 t/s, tg_3s = 21.61 t/s 8.20.206.293 I slot print_timing: id 0 | task 9302 | prompt eval time = 378.43 ms / 57 tokens ( 6.64 ms per token, 150.62 tokens per second) 8.20.206.300 I slot print_timing: id 0 | task 9302 | eval time = 14609.41 ms / 335 tokens ( 43.74 ms per token, 22.86 tokens per second) 8.20.206.302 I slot print_timing: id 0 | task 9302 | total time = 14987.84 ms / 392 tokens 8.20.206.302 I slot print_timing: id 0 | task 9302 | graphs reused = 8817 8.20.206.303 I slot print_timing: id 0 | task 9302 | graph reallocs = 0 / 0 (same size) / (changed size) 8.20.206.372 I slot release: id 0 | task 9302 | stop processing: n_tokens = 1362, truncated = 0 8.20.247.816 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.713 8.20.247.844 I slot launch_slot_: id 0 | task 9643 | processing task, is_child = 0 8.20.849.409 I slot print_timing: id 3 | task 9415 | n_gen = 230, tg = 22.98 t/s, tg_3s = 21.63 t/s 8.21.332.805 I slot print_timing: id 3 | task 9415 | prompt eval time = 446.29 ms / 86 tokens ( 5.19 ms per token, 192.70 tokens per second) 8.21.332.817 I slot print_timing: id 3 | task 9415 | eval time = 10446.88 ms / 242 tokens ( 43.35 ms per token, 23.07 tokens per second) 8.21.332.818 I slot print_timing: id 3 | task 9415 | total time = 10893.17 ms / 328 tokens 8.21.332.821 I slot print_timing: id 3 | task 9415 | graphs reused = 8832 8.21.332.822 I slot print_timing: id 3 | task 9415 | graph reallocs = 0 / 0 (same size) / (changed size) 8.21.332.897 I slot release: id 3 | task 9415 | stop processing: n_tokens = 1298, truncated = 0 8.21.373.848 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.748 8.21.373.874 I slot launch_slot_: id 3 | task 9662 | processing task, is_child = 0 8.22.036.841 I slot print_timing: id 2 | task 9299 | n_gen = 365, tg = 21.64 t/s, tg_3s = 19.16 t/s 8.22.517.555 I slot print_timing: id 1 | task 9580 | n_gen = 100, tg = 21.18 t/s, tg_3s = 21.40 t/s 8.23.989.604 I slot print_timing: id 2 | task 9299 | prompt eval time = 494.89 ms / 96 tokens ( 5.16 ms per token, 193.98 tokens per second) 8.23.989.611 I slot print_timing: id 2 | task 9299 | eval time = 18771.26 ms / 414 tokens ( 45.45 ms per token, 22.00 tokens per second) 8.23.989.612 I slot print_timing: id 2 | task 9299 | total time = 19266.15 ms / 510 tokens 8.23.989.613 I slot print_timing: id 2 | task 9299 | graphs reused = 8887 8.23.989.614 I slot print_timing: id 2 | task 9299 | graph reallocs = 0 / 0 (same size) / (changed size) 8.23.989.687 I slot release: id 2 | task 9299 | stop processing: n_tokens = 1480, truncated = 0 8.24.047.171 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.656 8.24.047.196 I slot launch_slot_: id 2 | task 9722 | processing task, is_child = 0 8.25.400.352 I slot print_timing: id 0 | task 9643 | n_gen = 100, tg = 21.18 t/s, tg_3s = 21.40 t/s 8.25.519.515 I slot print_timing: id 1 | task 9580 | n_gen = 165, tg = 21.37 t/s, tg_3s = 21.65 t/s 8.26.122.090 I slot print_timing: id 3 | task 9662 | n_gen = 100, tg = 22.68 t/s, tg_3s = 22.91 t/s 8.28.029.294 I slot print_timing: id 3 | task 9662 | prompt eval time = 383.92 ms / 59 tokens ( 6.51 ms per token, 153.68 tokens per second) 8.28.029.302 I slot print_timing: id 3 | task 9662 | eval time = 6271.49 ms / 148 tokens ( 42.66 ms per token, 23.44 tokens per second) 8.28.029.303 I slot print_timing: id 3 | task 9662 | total time = 6655.41 ms / 207 tokens 8.28.029.304 I slot print_timing: id 3 | task 9662 | graphs reused = 8973 8.28.029.310 I slot print_timing: id 3 | task 9662 | graph reallocs = 0 / 0 (same size) / (changed size) 8.28.029.381 I slot release: id 3 | task 9662 | stop processing: n_tokens = 1177, truncated = 0 8.28.070.219 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.825 8.28.070.242 I slot launch_slot_: id 3 | task 9814 | processing task, is_child = 0 8.28.455.318 I slot print_timing: id 0 | task 9643 | n_gen = 168, tg = 21.61 t/s, tg_3s = 22.26 t/s 8.28.533.235 I slot print_timing: id 1 | task 9580 | n_gen = 231, tg = 21.52 t/s, tg_3s = 21.90 t/s 8.28.856.111 I slot print_timing: id 2 | task 9722 | n_gen = 100, tg = 22.85 t/s, tg_3s = 23.08 t/s 8.29.420.989 I slot print_timing: id 0 | task 9643 | prompt eval time = 479.33 ms / 101 tokens ( 4.75 ms per token, 210.71 tokens per second) 8.29.420.996 I slot print_timing: id 0 | task 9643 | eval time = 8693.79 ms / 191 tokens ( 45.76 ms per token, 21.85 tokens per second) 8.29.420.997 I slot print_timing: id 0 | task 9643 | total time = 9173.12 ms / 292 tokens 8.29.420.997 I slot print_timing: id 0 | task 9643 | graphs reused = 8993 8.29.420.998 I slot print_timing: id 0 | task 9643 | graph reallocs = 0 / 0 (same size) / (changed size) 8.29.421.069 I slot release: id 0 | task 9643 | stop processing: n_tokens = 1262, truncated = 0 8.29.462.140 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.769 8.29.462.162 I slot launch_slot_: id 0 | task 9840 | processing task, is_child = 0 8.31.559.432 I slot print_timing: id 1 | task 9580 | n_gen = 299, tg = 21.73 t/s, tg_3s = 22.47 t/s 8.31.877.962 I slot print_timing: id 2 | task 9722 | n_gen = 168, tg = 22.71 t/s, tg_3s = 22.50 t/s 8.32.794.856 I slot print_timing: id 3 | task 9814 | n_gen = 100, tg = 23.23 t/s, tg_3s = 23.47 t/s 8.33.792.423 I slot print_timing: id 0 | task 9840 | n_gen = 100, tg = 25.06 t/s, tg_3s = 25.31 t/s 8.33.912.272 I slot print_timing: id 1 | task 9580 | prompt eval time = 468.79 ms / 78 tokens ( 6.01 ms per token, 166.39 tokens per second) 8.33.912.277 I slot print_timing: id 1 | task 9580 | eval time = 16067.84 ms / 358 tokens ( 45.01 ms per token, 22.22 tokens per second) 8.33.912.278 I slot print_timing: id 1 | task 9580 | total time = 16536.62 ms / 436 tokens 8.33.912.279 I slot print_timing: id 1 | task 9580 | graphs reused = 9095 8.33.912.280 I slot print_timing: id 1 | task 9580 | graph reallocs = 0 / 0 (same size) / (changed size) 8.33.912.353 I slot release: id 1 | task 9580 | stop processing: n_tokens = 1406, truncated = 0 8.33.969.321 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.691 8.33.969.348 I slot launch_slot_: id 1 | task 9946 | processing task, is_child = 0 8.34.895.183 I slot print_timing: id 2 | task 9722 | prompt eval time = 477.05 ms / 85 tokens ( 5.61 ms per token, 178.18 tokens per second) 8.34.895.191 I slot print_timing: id 2 | task 9722 | eval time = 10370.93 ms / 234 tokens ( 44.51 ms per token, 22.47 tokens per second) 8.34.895.191 I slot print_timing: id 2 | task 9722 | total time = 10847.98 ms / 319 tokens 8.34.895.192 I slot print_timing: id 2 | task 9722 | graphs reused = 9105 8.34.895.193 I slot print_timing: id 2 | task 9722 | graph reallocs = 0 / 0 (same size) / (changed size) 8.34.895.264 I slot release: id 2 | task 9722 | stop processing: n_tokens = 1289, truncated = 0 8.34.952.730 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.753 8.34.952.759 I slot launch_slot_: id 2 | task 9962 | processing task, is_child = 0 8.35.836.216 I slot print_timing: id 3 | task 9814 | n_gen = 156, tg = 21.22 t/s, tg_3s = 18.41 t/s 8.36.829.151 I slot print_timing: id 0 | task 9840 | n_gen = 156, tg = 22.18 t/s, tg_3s = 18.44 t/s 8.38.784.155 I slot print_timing: id 1 | task 9946 | n_gen = 100, tg = 22.62 t/s, tg_3s = 22.85 t/s 8.38.864.413 I slot print_timing: id 3 | task 9814 | n_gen = 232, tg = 22.36 t/s, tg_3s = 25.10 t/s 8.39.380.937 I slot print_timing: id 2 | task 9962 | n_gen = 100, tg = 25.05 t/s, tg_3s = 25.31 t/s 8.39.860.539 I slot print_timing: id 0 | task 9840 | n_gen = 232, tg = 23.06 t/s, tg_3s = 25.07 t/s 8.40.780.102 I slot print_timing: id 1 | task 9946 | prompt eval time = 438.26 ms / 65 tokens ( 6.74 ms per token, 148.31 tokens per second) 8.40.780.110 I slot print_timing: id 1 | task 9946 | eval time = 6372.48 ms / 150 tokens ( 42.77 ms per token, 23.38 tokens per second) 8.40.780.111 I slot print_timing: id 1 | task 9946 | total time = 6810.74 ms / 215 tokens 8.40.780.111 I slot print_timing: id 1 | task 9946 | graphs reused = 9236 8.40.780.112 I slot print_timing: id 1 | task 9946 | graph reallocs = 0 / 0 (same size) / (changed size) 8.40.780.181 I slot release: id 1 | task 9946 | stop processing: n_tokens = 1185, truncated = 0 8.40.837.667 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.819 8.40.837.699 I slot launch_slot_: id 1 | task 10100 | processing task, is_child = 0 8.41.892.611 I slot print_timing: id 3 | task 9814 | n_gen = 297, tg = 22.16 t/s, tg_3s = 21.46 t/s 8.42.412.853 I slot print_timing: id 2 | task 9962 | n_gen = 165, tg = 23.48 t/s, tg_3s = 21.44 t/s 8.42.893.047 I slot print_timing: id 0 | task 9840 | n_gen = 297, tg = 22.68 t/s, tg_3s = 21.43 t/s 8.44.133.464 I slot print_timing: id 0 | task 9840 | prompt eval time = 379.82 ms / 62 tokens ( 6.13 ms per token, 163.24 tokens per second) 8.44.133.471 I slot print_timing: id 0 | task 9840 | eval time = 14291.48 ms / 328 tokens ( 43.70 ms per token, 22.88 tokens per second) 8.44.133.472 I slot print_timing: id 0 | task 9840 | total time = 14671.29 ms / 390 tokens 8.44.133.473 I slot print_timing: id 0 | task 9840 | graphs reused = 9305 8.44.133.474 I slot print_timing: id 0 | task 9840 | graph reallocs = 0 / 0 (same size) / (changed size) 8.44.133.545 I slot release: id 0 | task 9840 | stop processing: n_tokens = 1360, truncated = 0 8.44.175.051 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.714 8.44.175.089 I slot launch_slot_: id 0 | task 10174 | processing task, is_child = 0 8.44.929.668 I slot print_timing: id 3 | task 9814 | n_gen = 365, tg = 22.20 t/s, tg_3s = 22.39 t/s 8.45.451.461 I slot print_timing: id 2 | task 9962 | n_gen = 233, tg = 23.15 t/s, tg_3s = 22.38 t/s 8.45.611.212 I slot print_timing: id 1 | task 10100 | n_gen = 100, tg = 23.11 t/s, tg_3s = 23.34 t/s 8.47.934.225 I slot print_timing: id 3 | task 9814 | n_gen = 440, tg = 22.63 t/s, tg_3s = 24.96 t/s 8.48.454.674 I slot print_timing: id 2 | task 9962 | n_gen = 308, tg = 23.57 t/s, tg_3s = 24.97 t/s 8.48.534.289 I slot print_timing: id 0 | task 10174 | n_gen = 100, tg = 24.96 t/s, tg_3s = 25.21 t/s 8.48.614.700 I slot print_timing: id 1 | task 10100 | n_gen = 175, tg = 23.88 t/s, tg_3s = 24.97 t/s 8.49.860.969 I slot print_timing: id 2 | task 9962 | prompt eval time = 476.84 ms / 86 tokens ( 5.54 ms per token, 180.35 tokens per second) 8.49.860.977 I slot print_timing: id 2 | task 9962 | eval time = 14431.36 ms / 343 tokens ( 42.20 ms per token, 23.70 tokens per second) 8.49.860.977 I slot print_timing: id 2 | task 9962 | total time = 14908.20 ms / 429 tokens 8.49.860.978 I slot print_timing: id 2 | task 9962 | graphs reused = 9435 8.49.860.979 I slot print_timing: id 2 | task 9962 | graph reallocs = 0 / 0 (same size) / (changed size) 8.49.861.043 I slot release: id 2 | task 9962 | stop processing: n_tokens = 1399, truncated = 0 8.49.916.930 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.694 8.49.916.952 I slot launch_slot_: id 2 | task 10310 | processing task, is_child = 0 8.50.966.013 I slot print_timing: id 3 | task 9814 | n_gen = 505, tg = 22.47 t/s, tg_3s = 21.44 t/s 8.51.564.725 I slot print_timing: id 0 | task 10174 | n_gen = 165, tg = 23.44 t/s, tg_3s = 21.45 t/s 8.51.645.005 I slot print_timing: id 1 | task 10100 | n_gen = 240, tg = 23.16 t/s, tg_3s = 21.45 t/s 8.52.804.749 I slot print_timing: id 0 | task 10174 | prompt eval time = 392.90 ms / 67 tokens ( 5.86 ms per token, 170.53 tokens per second) 8.52.804.756 I slot print_timing: id 0 | task 10174 | eval time = 8236.75 ms / 196 tokens ( 42.24 ms per token, 23.67 tokens per second) 8.52.804.757 I slot print_timing: id 0 | task 10174 | total time = 8629.65 ms / 263 tokens 8.52.804.758 I slot print_timing: id 0 | task 10174 | graphs reused = 9494 8.52.804.759 I slot print_timing: id 0 | task 10174 | graph reallocs = 0 / 0 (same size) / (changed size) 8.52.804.832 I slot release: id 0 | task 10174 | stop processing: n_tokens = 1233, truncated = 0 8.52.846.223 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.788 8.52.846.247 I slot launch_slot_: id 0 | task 10374 | processing task, is_child = 0 8.53.977.600 I slot print_timing: id 3 | task 9814 | n_gen = 570, tg = 22.36 t/s, tg_3s = 21.58 t/s 8.54.660.343 I slot print_timing: id 1 | task 10100 | n_gen = 305, tg = 22.80 t/s, tg_3s = 21.56 t/s 8.54.780.695 I slot print_timing: id 2 | task 10310 | n_gen = 100, tg = 22.59 t/s, tg_3s = 22.82 t/s 8.56.988.158 I slot print_timing: id 3 | task 9814 | n_gen = 645, tg = 22.63 t/s, tg_3s = 24.91 t/s 8.57.308.177 I slot print_timing: id 0 | task 10374 | n_gen = 100, tg = 24.88 t/s, tg_3s = 25.14 t/s 8.57.469.199 I slot print_timing: id 1 | task 10100 | prompt eval time = 489.21 ms / 89 tokens ( 5.50 ms per token, 181.93 tokens per second) 8.57.469.206 I slot print_timing: id 1 | task 10100 | eval time = 16142.28 ms / 375 tokens ( 43.16 ms per token, 23.17 tokens per second) 8.57.469.207 I slot print_timing: id 1 | task 10100 | total time = 16631.49 ms / 464 tokens 8.57.469.208 I slot print_timing: id 1 | task 10100 | graphs reused = 9597 8.57.469.209 I slot print_timing: id 1 | task 10100 | graph reallocs = 0 / 0 (same size) / (changed size) 8.57.469.287 I slot release: id 1 | task 10100 | stop processing: n_tokens = 1434, truncated = 0 8.57.526.491 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.677 8.57.526.523 I slot launch_slot_: id 1 | task 10481 | processing task, is_child = 0 8.57.901.588 I slot print_timing: id 2 | task 10310 | n_gen = 169, tg = 22.39 t/s, tg_3s = 22.11 t/s 9.00.005.467 I slot print_timing: id 3 | task 9814 | n_gen = 710, tg = 22.53 t/s, tg_3s = 21.54 t/s 9.00.325.691 I slot print_timing: id 0 | task 10374 | n_gen = 165, tg = 23.44 t/s, tg_3s = 21.54 t/s 9.00.933.678 I slot print_timing: id 2 | task 10310 | n_gen = 243, tg = 22.97 t/s, tg_3s = 24.41 t/s 9.01.979.200 I slot print_timing: id 1 | task 10481 | n_gen = 100, tg = 24.87 t/s, tg_3s = 25.12 t/s 9.03.025.876 I slot print_timing: id 3 | task 9814 | n_gen = 785, tg = 22.73 t/s, tg_3s = 24.83 t/s 9.03.347.068 I slot print_timing: id 0 | task 10374 | n_gen = 240, tg = 23.86 t/s, tg_3s = 24.82 t/s 9.03.950.705 I slot print_timing: id 2 | task 10310 | n_gen = 318, tg = 23.39 t/s, tg_3s = 24.86 t/s 9.04.998.625 I slot print_timing: id 1 | task 10481 | n_gen = 175, tg = 24.86 t/s, tg_3s = 24.84 t/s 9.06.046.347 I slot print_timing: id 3 | task 9814 | n_gen = 860, tg = 22.90 t/s, tg_3s = 24.83 t/s 9.06.367.872 I slot print_timing: id 0 | task 10374 | n_gen = 315, tg = 24.08 t/s, tg_3s = 24.83 t/s 9.06.972.522 I slot print_timing: id 2 | task 10310 | n_gen = 393, tg = 23.65 t/s, tg_3s = 24.82 t/s 9.08.020.457 I slot print_timing: id 1 | task 10481 | n_gen = 250, tg = 24.84 t/s, tg_3s = 24.82 t/s 9.08.342.487 I slot print_timing: id 1 | task 10481 | prompt eval time = 471.78 ms / 93 tokens ( 5.07 ms per token, 197.12 tokens per second) 9.08.342.495 I slot print_timing: id 1 | task 10481 | eval time = 10344.17 ms / 258 tokens ( 40.25 ms per token, 24.84 tokens per second) 9.08.342.497 I slot print_timing: id 1 | task 10481 | total time = 10815.95 ms / 351 tokens 9.08.342.498 I slot print_timing: id 1 | task 10481 | graphs reused = 9852 9.08.342.499 I slot print_timing: id 1 | task 10481 | graph reallocs = 0 / 0 (same size) / (changed size) 9.08.342.582 I slot release: id 1 | task 10481 | stop processing: n_tokens = 1321, truncated = 0 9.08.400.236 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.735 9.08.400.260 I slot launch_slot_: id 1 | task 10742 | processing task, is_child = 0 9.09.046.744 I slot print_timing: id 3 | task 9814 | n_gen = 924, tg = 22.78 t/s, tg_3s = 21.33 t/s 9.09.368.303 I slot print_timing: id 0 | task 10374 | n_gen = 379, tg = 23.57 t/s, tg_3s = 21.33 t/s 9.10.012.530 I slot print_timing: id 2 | task 10310 | n_gen = 458, tg = 23.30 t/s, tg_3s = 21.38 t/s 9.12.077.279 I slot print_timing: id 3 | task 9814 | n_gen = 999, tg = 22.92 t/s, tg_3s = 24.75 t/s 9.12.401.258 I slot print_timing: id 0 | task 10374 | n_gen = 454, tg = 23.75 t/s, tg_3s = 24.73 t/s 9.12.889.349 I slot print_timing: id 1 | task 10742 | n_gen = 100, tg = 24.69 t/s, tg_3s = 24.93 t/s 9.13.052.266 I slot print_timing: id 2 | task 10310 | n_gen = 533, tg = 23.48 t/s, tg_3s = 24.67 t/s 9.13.092.972 I slot print_timing: id 3 | task 9814 | prompt eval time = 463.22 ms / 101 tokens ( 4.59 ms per token, 218.04 tokens per second) 9.13.092.978 I slot print_timing: id 3 | task 9814 | eval time = 44559.50 ms / 1024 tokens ( 43.56 ms per token, 22.96 tokens per second) 9.13.092.979 I slot print_timing: id 3 | task 9814 | total time = 45022.72 ms / 1125 tokens 9.13.092.979 I slot print_timing: id 3 | task 9814 | graphs reused = 9954 9.13.092.980 I slot print_timing: id 3 | task 9814 | graph reallocs = 0 / 0 (same size) / (changed size) 9.13.093.049 I slot release: id 3 | task 9814 | stop processing: n_tokens = 2095, truncated = 0 9.13.133.882 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.463 9.13.170.565 I slot launch_slot_: id 3 | task 10850 | processing task, is_child = 0 9.15.405.373 I slot print_timing: id 0 | task 10374 | n_gen = 519, tg = 23.46 t/s, tg_3s = 21.64 t/s 9.15.926.949 I slot print_timing: id 1 | task 10742 | n_gen = 166, tg = 23.41 t/s, tg_3s = 21.73 t/s 9.16.087.905 I slot print_timing: id 2 | task 10310 | n_gen = 599, tg = 23.28 t/s, tg_3s = 21.74 t/s 9.17.573.286 I slot print_timing: id 3 | task 10850 | n_gen = 100, tg = 24.89 t/s, tg_3s = 25.14 t/s 9.18.415.299 I slot print_timing: id 0 | task 10374 | n_gen = 594, tg = 23.64 t/s, tg_3s = 24.92 t/s 9.18.938.250 I slot print_timing: id 1 | task 10742 | n_gen = 241, tg = 23.86 t/s, tg_3s = 24.91 t/s 9.19.099.120 I slot print_timing: id 2 | task 10310 | n_gen = 674, tg = 23.45 t/s, tg_3s = 24.91 t/s 9.20.587.366 I slot print_timing: id 3 | task 10850 | n_gen = 175, tg = 24.89 t/s, tg_3s = 24.88 t/s 9.21.431.503 I slot print_timing: id 0 | task 10374 | n_gen = 669, tg = 23.77 t/s, tg_3s = 24.87 t/s 9.21.552.316 I slot print_timing: id 1 | task 10742 | prompt eval time = 478.61 ms / 85 tokens ( 5.63 ms per token, 177.60 tokens per second) 9.21.552.322 I slot print_timing: id 1 | task 10742 | eval time = 12673.43 ms / 306 tokens ( 41.55 ms per token, 24.07 tokens per second) 9.21.552.323 I slot print_timing: id 1 | task 10742 | total time = 13152.04 ms / 391 tokens 9.21.552.324 I slot print_timing: id 1 | task 10742 | graphs reused = 10151 9.21.552.325 I slot print_timing: id 1 | task 10742 | graph reallocs = 0 / 0 (same size) / (changed size) 9.21.552.399 I slot release: id 1 | task 10742 | stop processing: n_tokens = 1361, truncated = 0 9.21.610.012 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.713 9.21.610.040 I slot launch_slot_: id 1 | task 11052 | processing task, is_child = 0 9.22.127.132 I slot print_timing: id 2 | task 10310 | n_gen = 740, tg = 23.29 t/s, tg_3s = 21.80 t/s 9.23.617.670 I slot print_timing: id 3 | task 10850 | n_gen = 241, tg = 23.95 t/s, tg_3s = 21.78 t/s 9.24.462.610 I slot print_timing: id 0 | task 10374 | n_gen = 735, tg = 23.58 t/s, tg_3s = 21.77 t/s 9.25.146.618 I slot print_timing: id 2 | task 10310 | n_gen = 815, tg = 23.43 t/s, tg_3s = 24.84 t/s 9.26.032.758 I slot print_timing: id 1 | task 11052 | n_gen = 100, tg = 24.80 t/s, tg_3s = 25.05 t/s 9.26.638.129 I slot print_timing: id 3 | task 10850 | n_gen = 316, tg = 24.15 t/s, tg_3s = 24.83 t/s 9.27.484.613 I slot print_timing: id 0 | task 10374 | n_gen = 810, tg = 23.69 t/s, tg_3s = 24.82 t/s 9.28.170.418 I slot print_timing: id 2 | task 10310 | n_gen = 890, tg = 23.54 t/s, tg_3s = 24.80 t/s 9.29.056.539 I slot print_timing: id 1 | task 11052 | n_gen = 175, tg = 24.80 t/s, tg_3s = 24.80 t/s 9.29.662.914 I slot print_timing: id 3 | task 10850 | n_gen = 391, tg = 24.27 t/s, tg_3s = 24.80 t/s 9.30.509.759 I slot print_timing: id 0 | task 10374 | n_gen = 885, tg = 23.78 t/s, tg_3s = 24.79 t/s 9.31.197.273 I slot print_timing: id 2 | task 10310 | n_gen = 965, tg = 23.63 t/s, tg_3s = 24.78 t/s 9.32.086.194 I slot print_timing: id 1 | task 11052 | n_gen = 250, tg = 24.79 t/s, tg_3s = 24.76 t/s 9.32.662.593 I slot print_timing: id 1 | task 11052 | prompt eval time = 431.12 ms / 63 tokens ( 6.84 ms per token, 146.13 tokens per second) 9.32.662.603 I slot print_timing: id 1 | task 11052 | eval time = 10621.42 ms / 264 tokens ( 40.39 ms per token, 24.76 tokens per second) 9.32.662.604 I slot print_timing: id 1 | task 11052 | total time = 11052.55 ms / 327 tokens 9.32.662.605 I slot print_timing: id 1 | task 11052 | graphs reused = 10412 9.32.662.606 I slot print_timing: id 1 | task 11052 | graph reallocs = 0 / 0 (same size) / (changed size) 9.32.662.680 I slot release: id 1 | task 11052 | stop processing: n_tokens = 1297, truncated = 0 9.32.663.028 I slot print_timing: id 3 | task 10850 | n_gen = 465, tg = 24.34 t/s, tg_3s = 24.67 t/s 9.32.720.708 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.749 9.32.720.737 I slot launch_slot_: id 1 | task 11319 | processing task, is_child = 0 9.33.348.095 I slot print_timing: id 3 | task 10850 | prompt eval time = 425.29 ms / 71 tokens ( 5.99 ms per token, 166.95 tokens per second) 9.33.348.105 I slot print_timing: id 3 | task 10850 | eval time = 19752.22 ms / 470 tokens ( 42.12 ms per token, 23.74 tokens per second) 9.33.348.107 I slot print_timing: id 3 | task 10850 | total time = 20177.50 ms / 541 tokens 9.33.348.108 I slot print_timing: id 3 | task 10850 | graphs reused = 10413 9.33.348.110 I slot print_timing: id 3 | task 10850 | graph reallocs = 0 / 0 (same size) / (changed size) 9.33.348.245 I slot release: id 3 | task 10850 | stop processing: n_tokens = 1510, truncated = 0 9.33.393.107 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.643 9.33.393.134 I slot launch_slot_: id 3 | task 11325 | processing task, is_child = 0 9.33.692.994 I slot print_timing: id 0 | task 10374 | n_gen = 945, tg = 23.39 t/s, tg_3s = 18.85 t/s 9.34.225.823 I slot print_timing: id 2 | task 10310 | n_gen = 1020, tg = 23.25 t/s, tg_3s = 18.16 t/s 9.34.388.805 I slot print_timing: id 2 | task 10310 | prompt eval time = 481.07 ms / 87 tokens ( 5.53 ms per token, 180.85 tokens per second) 9.34.388.811 I slot print_timing: id 2 | task 10310 | eval time = 43990.78 ms / 1024 tokens ( 43.00 ms per token, 23.25 tokens per second) 9.34.388.812 I slot print_timing: id 2 | task 10310 | total time = 44471.84 ms / 1111 tokens 9.34.388.812 I slot print_timing: id 2 | task 10310 | graphs reused = 10427 9.34.388.813 I slot print_timing: id 2 | task 10310 | graph reallocs = 0 / 0 (same size) / (changed size) 9.34.388.889 I slot release: id 2 | task 10310 | stop processing: n_tokens = 2081, truncated = 0 9.34.447.115 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.467 9.34.486.927 I slot launch_slot_: id 2 | task 11344 | processing task, is_child = 0 9.36.712.114 I slot print_timing: id 0 | task 10374 | n_gen = 1008, tg = 23.21 t/s, tg_3s = 20.87 t/s 9.37.360.880 I slot print_timing: id 0 | task 10374 | prompt eval time = 483.61 ms / 101 tokens ( 4.79 ms per token, 208.85 tokens per second) 9.37.360.888 I slot print_timing: id 0 | task 10374 | eval time = 44031.02 ms / 1024 tokens ( 43.04 ms per token, 23.23 tokens per second) 9.37.360.890 I slot print_timing: id 0 | task 10374 | total time = 44514.62 ms / 1125 tokens 9.37.360.891 I slot print_timing: id 0 | task 10374 | graphs reused = 10485 9.37.360.892 I slot print_timing: id 0 | task 10374 | graph reallocs = 0 / 0 (same size) / (changed size) 9.37.360.963 I slot release: id 0 | task 10374 | stop processing: n_tokens = 2095, truncated = 0 9.37.402.043 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.463 9.37.441.062 I slot launch_slot_: id 0 | task 11408 | processing task, is_child = 0 9.38.423.927 I slot print_timing: id 1 | task 11319 | n_gen = 100, tg = 19.18 t/s, tg_3s = 19.38 t/s 9.38.623.616 I slot print_timing: id 3 | task 11325 | n_gen = 100, tg = 20.41 t/s, tg_3s = 20.61 t/s 9.39.258.771 I slot print_timing: id 3 | task 11325 | prompt eval time = 379.24 ms / 56 tokens ( 6.77 ms per token, 147.66 tokens per second) 9.39.258.779 I slot print_timing: id 3 | task 11325 | eval time = 5486.38 ms / 116 tokens ( 47.71 ms per token, 20.96 tokens per second) 9.39.258.780 I slot print_timing: id 3 | task 11325 | total time = 5865.62 ms / 172 tokens 9.39.258.780 I slot print_timing: id 3 | task 11325 | graphs reused = 10518 9.39.258.781 I slot print_timing: id 3 | task 11325 | graph reallocs = 0 / 0 (same size) / (changed size) 9.39.258.853 I slot release: id 3 | task 11325 | stop processing: n_tokens = 1142, truncated = 0 9.39.299.922 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.850 9.39.299.947 I slot launch_slot_: id 3 | task 11446 | processing task, is_child = 0 9.39.661.512 I slot print_timing: id 2 | task 11344 | n_gen = 100, tg = 20.92 t/s, tg_3s = 21.13 t/s 9.41.459.669 I slot print_timing: id 1 | task 11319 | n_gen = 167, tg = 20.25 t/s, tg_3s = 22.07 t/s 9.42.252.483 I slot print_timing: id 0 | task 11408 | n_gen = 100, tg = 22.95 t/s, tg_3s = 23.18 t/s 9.42.451.198 I slot print_timing: id 2 | task 11344 | prompt eval time = 442.37 ms / 68 tokens ( 6.51 ms per token, 153.72 tokens per second) 9.42.451.205 I slot print_timing: id 2 | task 11344 | eval time = 7521.89 ms / 169 tokens ( 44.77 ms per token, 22.33 tokens per second) 9.42.451.206 I slot print_timing: id 2 | task 11344 | total time = 7964.26 ms / 237 tokens 9.42.451.207 I slot print_timing: id 2 | task 11344 | graphs reused = 10584 9.42.451.208 I slot print_timing: id 2 | task 11344 | graph reallocs = 0 / 0 (same size) / (changed size) 9.42.451.283 I slot release: id 2 | task 11344 | stop processing: n_tokens = 1206, truncated = 0 9.42.509.179 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.805 9.42.509.213 I slot launch_slot_: id 2 | task 11518 | processing task, is_child = 0 9.44.111.336 I slot print_timing: id 3 | task 11446 | n_gen = 100, tg = 22.65 t/s, tg_3s = 22.88 t/s 9.44.309.016 I slot print_timing: id 0 | task 11408 | prompt eval time = 497.04 ms / 80 tokens ( 6.21 ms per token, 160.95 tokens per second) 9.44.309.023 I slot print_timing: id 0 | task 11408 | eval time = 6370.90 ms / 141 tokens ( 45.51 ms per token, 21.97 tokens per second) 9.44.309.024 I slot print_timing: id 0 | task 11408 | total time = 6867.93 ms / 221 tokens 9.44.309.024 I slot print_timing: id 0 | task 11408 | graphs reused = 10616 9.44.309.025 I slot print_timing: id 0 | task 11408 | graph reallocs = 0 / 0 (same size) / (changed size) 9.44.309.098 I slot release: id 0 | task 11408 | stop processing: n_tokens = 1172, truncated = 0 9.44.350.124 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.828 9.44.350.155 I slot launch_slot_: id 0 | task 11555 | processing task, is_child = 0 9.44.650.249 I slot print_timing: id 1 | task 11319 | n_gen = 230, tg = 20.11 t/s, tg_3s = 19.75 t/s 9.47.121.479 I slot print_timing: id 3 | task 11446 | n_gen = 168, tg = 22.62 t/s, tg_3s = 22.59 t/s 9.47.241.340 I slot print_timing: id 2 | task 11518 | n_gen = 100, tg = 23.32 t/s, tg_3s = 23.56 t/s 9.47.679.355 I slot print_timing: id 1 | task 11319 | n_gen = 305, tg = 21.09 t/s, tg_3s = 24.76 t/s 9.48.676.280 I slot print_timing: id 0 | task 11555 | n_gen = 100, tg = 25.07 t/s, tg_3s = 25.33 t/s 9.49.155.087 I slot print_timing: id 3 | task 11446 | prompt eval time = 440.03 ms / 83 tokens ( 5.30 ms per token, 188.62 tokens per second) 9.49.155.094 I slot print_timing: id 3 | task 11446 | eval time = 9415.10 ms / 219 tokens ( 43.19 ms per token, 23.15 tokens per second) 9.49.155.095 I slot print_timing: id 3 | task 11446 | total time = 9855.13 ms / 302 tokens 9.49.155.096 I slot print_timing: id 3 | task 11446 | graphs reused = 10727 9.49.155.097 I slot print_timing: id 3 | task 11446 | graph reallocs = 0 / 0 (same size) / (changed size) 9.49.155.170 I slot release: id 3 | task 11446 | stop processing: n_tokens = 1272, truncated = 0 9.49.195.903 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.875 (> 0.100 thold), f_keep = 0.763 9.49.195.927 I slot launch_slot_: id 3 | task 11670 | processing task, is_child = 0 9.50.247.079 I slot print_timing: id 2 | task 11518 | n_gen = 164, tg = 22.48 t/s, tg_3s = 21.29 t/s 9.50.686.376 I slot print_timing: id 1 | task 11319 | n_gen = 369, tg = 21.12 t/s, tg_3s = 21.28 t/s 9.51.682.641 I slot print_timing: id 0 | task 11555 | n_gen = 164, tg = 23.44 t/s, tg_3s = 21.29 t/s 9.53.261.499 I slot print_timing: id 2 | task 11518 | n_gen = 240, tg = 23.28 t/s, tg_3s = 25.21 t/s 9.53.662.843 I slot print_timing: id 3 | task 11670 | n_gen = 100, tg = 25.14 t/s, tg_3s = 25.40 t/s 9.53.702.590 I slot print_timing: id 1 | task 11319 | n_gen = 445, tg = 21.72 t/s, tg_3s = 25.20 t/s 9.54.014.482 I slot print_timing: id 1 | task 11319 | prompt eval time = 542.47 ms / 118 tokens ( 4.60 ms per token, 217.52 tokens per second) 9.54.014.487 I slot print_timing: id 1 | task 11319 | eval time = 20751.27 ms / 453 tokens ( 45.91 ms per token, 21.78 tokens per second) 9.54.014.488 I slot print_timing: id 1 | task 11319 | total time = 21293.74 ms / 571 tokens 9.54.014.488 I slot print_timing: id 1 | task 11319 | graphs reused = 10832 9.54.014.489 I slot print_timing: id 1 | task 11319 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.014.538 I slot release: id 1 | task 11319 | stop processing: n_tokens = 1541, truncated = 0 9.54.067.674 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.630 9.54.067.698 I slot launch_slot_: id 1 | task 11782 | processing task, is_child = 0 9.54.692.903 I slot print_timing: id 0 | task 11555 | n_gen = 230, tg = 22.98 t/s, tg_3s = 21.92 t/s 9.55.599.385 I slot print_timing: id 0 | task 11555 | prompt eval time = 377.88 ms / 59 tokens ( 6.40 ms per token, 156.13 tokens per second) 9.55.599.393 I slot print_timing: id 0 | task 11555 | eval time = 10871.34 ms / 253 tokens ( 43.14 ms per token, 23.18 tokens per second) 9.55.599.393 I slot print_timing: id 0 | task 11555 | total time = 11249.22 ms / 312 tokens 9.55.599.394 I slot print_timing: id 0 | task 11555 | graphs reused = 10858 9.55.599.395 I slot print_timing: id 0 | task 11555 | graph reallocs = 0 / 0 (same size) / (changed size) 9.55.599.459 I slot release: id 0 | task 11555 | stop processing: n_tokens = 1282, truncated = 0 9.55.640.385 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.757 9.55.640.409 I slot launch_slot_: id 0 | task 11813 | processing task, is_child = 0 9.56.290.124 I slot print_timing: id 2 | task 11518 | n_gen = 296, tg = 22.19 t/s, tg_3s = 18.49 t/s 9.56.697.618 I slot print_timing: id 3 | task 11670 | n_gen = 156, tg = 22.23 t/s, tg_3s = 18.45 t/s 9.58.889.073 I slot print_timing: id 1 | task 11782 | n_gen = 100, tg = 22.71 t/s, tg_3s = 22.94 t/s 9.59.327.370 I slot print_timing: id 2 | task 11518 | n_gen = 372, tg = 22.72 t/s, tg_3s = 25.02 t/s 9.59.726.667 I slot print_timing: id 3 | task 11670 | n_gen = 232, tg = 23.10 t/s, tg_3s = 25.09 t/s 10.00.085.929 I slot print_timing: id 0 | task 11813 | n_gen = 100, tg = 25.02 t/s, tg_3s = 25.27 t/s 10.01.928.326 I slot print_timing: id 1 | task 11782 | n_gen = 176, tg = 23.66 t/s, tg_3s = 25.01 t/s 10.02.328.345 I slot print_timing: id 2 | task 11518 | n_gen = 447, tg = 23.07 t/s, tg_3s = 24.99 t/s 10.02.730.185 I slot print_timing: id 3 | task 11670 | n_gen = 307, tg = 23.53 t/s, tg_3s = 24.97 t/s 10.03.091.752 I slot print_timing: id 0 | task 11813 | n_gen = 175, tg = 24.99 t/s, tg_3s = 24.95 t/s 10.04.946.491 I slot print_timing: id 1 | task 11782 | n_gen = 251, tg = 24.00 t/s, tg_3s = 24.85 t/s 10.05.349.737 I slot print_timing: id 2 | task 11518 | n_gen = 522, tg = 23.31 t/s, tg_3s = 24.82 t/s 10.05.752.058 I slot print_timing: id 3 | task 11670 | n_gen = 382, tg = 23.77 t/s, tg_3s = 24.82 t/s 10.06.114.819 I slot print_timing: id 0 | task 11813 | n_gen = 250, tg = 24.94 t/s, tg_3s = 24.81 t/s 10.07.322.250 I slot print_timing: id 2 | task 11518 | prompt eval time = 487.62 ms / 88 tokens ( 5.54 ms per token, 180.47 tokens per second) 10.07.322.257 I slot print_timing: id 2 | task 11518 | eval time = 24325.41 ms / 571 tokens ( 42.68 ms per token, 23.43 tokens per second) 10.07.322.258 I slot print_timing: id 2 | task 11518 | total time = 24813.03 ms / 659 tokens 10.07.322.259 I slot print_timing: id 2 | task 11518 | graphs reused = 11135 10.07.322.260 I slot print_timing: id 2 | task 11518 | graph reallocs = 0 / 0 (same size) / (changed size) 10.07.322.333 I slot release: id 2 | task 11518 | stop processing: n_tokens = 1629, truncated = 0 10.07.379.693 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.596 10.07.379.721 I slot launch_slot_: id 2 | task 12096 | processing task, is_child = 0 10.07.977.733 I slot print_timing: id 1 | task 11782 | n_gen = 316, tg = 23.43 t/s, tg_3s = 21.44 t/s 10.08.789.080 I slot print_timing: id 3 | task 11670 | n_gen = 447, tg = 23.40 t/s, tg_3s = 21.40 t/s 10.09.150.267 I slot print_timing: id 0 | task 11813 | n_gen = 315, tg = 24.11 t/s, tg_3s = 21.41 t/s 10.10.998.182 I slot print_timing: id 1 | task 11782 | n_gen = 391, tg = 23.68 t/s, tg_3s = 24.83 t/s 10.11.801.579 I slot print_timing: id 3 | task 11670 | n_gen = 522, tg = 23.60 t/s, tg_3s = 24.90 t/s 10.11.841.687 I slot print_timing: id 2 | task 12096 | n_gen = 100, tg = 24.83 t/s, tg_3s = 25.08 t/s 10.12.162.469 I slot print_timing: id 0 | task 11813 | n_gen = 390, tg = 24.26 t/s, tg_3s = 24.90 t/s 10.13.570.080 I slot print_timing: id 2 | task 12096 | prompt eval time = 474.80 ms / 78 tokens ( 6.09 ms per token, 164.28 tokens per second) 10.13.570.087 I slot print_timing: id 2 | task 12096 | eval time = 5715.55 ms / 143 tokens ( 40.25 ms per token, 24.84 tokens per second) 10.13.570.088 I slot print_timing: id 2 | task 12096 | total time = 6190.35 ms / 221 tokens 10.13.570.089 I slot print_timing: id 2 | task 12096 | graphs reused = 11275 10.13.570.090 I slot print_timing: id 2 | task 12096 | graph reallocs = 0 / 0 (same size) / (changed size) 10.13.570.168 I slot release: id 2 | task 12096 | stop processing: n_tokens = 1191, truncated = 0 10.13.628.233 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.815 10.13.628.260 I slot launch_slot_: id 2 | task 12242 | processing task, is_child = 0 10.14.069.562 I slot print_timing: id 1 | task 11782 | n_gen = 457, tg = 23.34 t/s, tg_3s = 21.49 t/s 10.14.817.512 I slot print_timing: id 3 | task 11670 | n_gen = 585, tg = 23.27 t/s, tg_3s = 20.89 t/s 10.14.937.773 I slot print_timing: id 0 | task 11813 | prompt eval time = 488.56 ms / 112 tokens ( 4.36 ms per token, 229.25 tokens per second) 10.14.937.781 I slot print_timing: id 0 | task 11813 | eval time = 18808.80 ms / 447 tokens ( 42.17 ms per token, 23.71 tokens per second) 10.14.937.782 I slot print_timing: id 0 | task 11813 | total time = 19297.36 ms / 559 tokens 10.14.937.783 I slot print_timing: id 0 | task 11813 | graphs reused = 11293 10.14.937.784 I slot print_timing: id 0 | task 11813 | graph reallocs = 0 / 0 (same size) / (changed size) 10.14.937.860 I slot release: id 0 | task 11813 | stop processing: n_tokens = 1529, truncated = 0 10.14.979.706 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.635 10.14.979.735 I slot launch_slot_: id 0 | task 12265 | processing task, is_child = 0 10.17.099.667 I slot print_timing: id 1 | task 11782 | n_gen = 522, tg = 23.08 t/s, tg_3s = 21.45 t/s 10.17.422.025 I slot print_timing: id 3 | task 11670 | prompt eval time = 529.28 ms / 139 tokens ( 3.81 ms per token, 262.62 tokens per second) 10.17.422.029 I slot print_timing: id 3 | task 11670 | eval time = 27696.80 ms / 641 tokens ( 43.28 ms per token, 23.11 tokens per second) 10.17.422.030 I slot print_timing: id 3 | task 11670 | total time = 28226.09 ms / 780 tokens 10.17.422.031 I slot print_timing: id 3 | task 11670 | graphs reused = 11343 10.17.422.032 I slot print_timing: id 3 | task 11670 | graph reallocs = 0 / 0 (same size) / (changed size) 10.17.422.120 I slot release: id 3 | task 11670 | stop processing: n_tokens = 1750, truncated = 0 10.17.463.238 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.555 10.17.463.269 I slot launch_slot_: id 3 | task 12319 | processing task, is_child = 0 10.18.903.817 I slot print_timing: id 2 | task 12242 | n_gen = 100, tg = 20.89 t/s, tg_3s = 21.10 t/s 10.19.783.170 I slot print_timing: id 0 | task 12265 | n_gen = 100, tg = 22.60 t/s, tg_3s = 22.82 t/s 10.20.103.161 I slot print_timing: id 1 | task 11782 | n_gen = 587, tg = 22.92 t/s, tg_3s = 21.64 t/s 10.21.903.057 I slot print_timing: id 3 | task 12319 | n_gen = 100, tg = 24.97 t/s, tg_3s = 25.23 t/s 10.21.942.965 I slot print_timing: id 2 | task 12242 | n_gen = 176, tg = 22.50 t/s, tg_3s = 25.01 t/s 10.22.822.798 I slot print_timing: id 0 | task 12265 | n_gen = 176, tg = 23.58 t/s, tg_3s = 25.00 t/s 10.23.103.403 I slot print_timing: id 1 | task 11782 | n_gen = 662, tg = 23.13 t/s, tg_3s = 25.00 t/s 10.24.910.907 I slot print_timing: id 3 | task 12319 | n_gen = 175, tg = 24.96 t/s, tg_3s = 24.93 t/s 10.24.950.860 I slot print_timing: id 2 | task 12242 | n_gen = 251, tg = 23.18 t/s, tg_3s = 24.93 t/s 10.25.835.055 I slot print_timing: id 0 | task 12265 | n_gen = 251, tg = 23.96 t/s, tg_3s = 24.90 t/s 10.26.117.712 I slot print_timing: id 1 | task 11782 | n_gen = 737, tg = 23.30 t/s, tg_3s = 24.88 t/s 10.27.933.366 I slot print_timing: id 3 | task 12319 | n_gen = 250, tg = 24.91 t/s, tg_3s = 24.81 t/s 10.27.973.437 I slot print_timing: id 2 | task 12242 | prompt eval time = 535.76 ms / 109 tokens ( 4.92 ms per token, 203.45 tokens per second) 10.27.973.441 I slot print_timing: id 2 | task 12242 | eval time = 13809.41 ms / 326 tokens ( 42.49 ms per token, 23.53 tokens per second) 10.27.973.442 I slot print_timing: id 2 | task 12242 | total time = 14345.17 ms / 435 tokens 10.27.973.443 I slot print_timing: id 2 | task 12242 | graphs reused = 11591 10.27.973.443 I slot print_timing: id 2 | task 12242 | graph reallocs = 0 / 0 (same size) / (changed size) 10.27.973.526 I slot release: id 2 | task 12242 | stop processing: n_tokens = 1405, truncated = 0 10.28.031.850 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.691 10.28.031.879 I slot launch_slot_: id 2 | task 12573 | processing task, is_child = 0 10.28.845.854 I slot print_timing: id 0 | task 12265 | n_gen = 315, tg = 23.36 t/s, tg_3s = 21.26 t/s 10.29.127.259 I slot print_timing: id 1 | task 11782 | n_gen = 801, tg = 23.12 t/s, tg_3s = 21.27 t/s 10.30.934.789 I slot print_timing: id 3 | task 12319 | n_gen = 314, tg = 24.08 t/s, tg_3s = 21.32 t/s 10.31.821.740 I slot print_timing: id 3 | task 12319 | prompt eval time = 475.56 ms / 101 tokens ( 4.71 ms per token, 212.38 tokens per second) 10.31.821.747 I slot print_timing: id 3 | task 12319 | eval time = 13882.90 ms / 336 tokens ( 41.44 ms per token, 24.13 tokens per second) 10.31.821.748 I slot print_timing: id 3 | task 12319 | total time = 14358.46 ms / 437 tokens 10.31.821.749 I slot print_timing: id 3 | task 12319 | graphs reused = 11672 10.31.821.750 I slot print_timing: id 3 | task 12319 | graph reallocs = 0 / 0 (same size) / (changed size) 10.31.821.839 I slot release: id 3 | task 12319 | stop processing: n_tokens = 1406, truncated = 0 10.31.862.771 I slot print_timing: id 0 | task 12265 | n_gen = 390, tg = 23.63 t/s, tg_3s = 24.86 t/s 10.31.863.071 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.691 10.31.863.098 I slot launch_slot_: id 3 | task 12659 | processing task, is_child = 0 10.32.191.549 I slot print_timing: id 1 | task 11782 | n_gen = 870, tg = 23.07 t/s, tg_3s = 22.52 t/s 10.32.841.943 I slot print_timing: id 2 | task 12573 | n_gen = 100, tg = 22.88 t/s, tg_3s = 23.11 t/s 10.34.889.057 I slot print_timing: id 0 | task 12265 | n_gen = 457, tg = 23.40 t/s, tg_3s = 22.14 t/s 10.35.210.732 I slot print_timing: id 1 | task 11782 | n_gen = 944, tg = 23.18 t/s, tg_3s = 24.51 t/s 10.35.851.615 I slot print_timing: id 2 | task 12573 | n_gen = 175, tg = 23.72 t/s, tg_3s = 24.92 t/s 10.36.253.812 I slot print_timing: id 3 | task 12659 | n_gen = 100, tg = 24.85 t/s, tg_3s = 25.10 t/s 10.36.412.459 I slot print_timing: id 0 | task 12265 | prompt eval time = 422.11 ms / 78 tokens ( 5.41 ms per token, 184.79 tokens per second) 10.36.412.463 I slot print_timing: id 0 | task 12265 | eval time = 21010.61 ms / 495 tokens ( 42.53 ms per token, 23.51 tokens per second) 10.36.412.464 I slot print_timing: id 0 | task 12265 | total time = 21432.71 ms / 573 tokens 10.36.412.465 I slot print_timing: id 0 | task 12265 | graphs reused = 11774 10.36.412.466 I slot print_timing: id 0 | task 12265 | graph reallocs = 0 / 0 (same size) / (changed size) 10.36.412.536 I slot release: id 0 | task 12265 | stop processing: n_tokens = 1543, truncated = 0 10.36.453.471 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.629 10.36.453.495 I slot launch_slot_: id 0 | task 12766 | processing task, is_child = 0 10.38.246.681 I slot print_timing: id 1 | task 11782 | n_gen = 1011, tg = 23.10 t/s, tg_3s = 22.07 t/s 10.38.772.792 I slot print_timing: id 1 | task 11782 | prompt eval time = 462.86 ms / 73 tokens ( 6.34 ms per token, 157.71 tokens per second) 10.38.772.799 I slot print_timing: id 1 | task 11782 | eval time = 44242.22 ms / 1024 tokens ( 43.25 ms per token, 23.12 tokens per second) 10.38.772.800 I slot print_timing: id 1 | task 11782 | total time = 44705.08 ms / 1097 tokens 10.38.772.801 I slot print_timing: id 1 | task 11782 | graphs reused = 11820 10.38.772.802 I slot print_timing: id 1 | task 11782 | graph reallocs = 0 / 0 (same size) / (changed size) 10.38.772.871 I slot release: id 1 | task 11782 | stop processing: n_tokens = 2067, truncated = 0 10.38.830.324 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.470 10.38.854.909 I slot launch_slot_: id 1 | task 12817 | processing task, is_child = 0 10.39.193.224 I slot print_timing: id 2 | task 12573 | n_gen = 241, tg = 22.48 t/s, tg_3s = 19.75 t/s 10.39.292.383 I slot print_timing: id 3 | task 12659 | n_gen = 157, tg = 22.22 t/s, tg_3s = 18.76 t/s 10.40.056.993 I slot print_timing: id 3 | task 12659 | prompt eval time = 407.12 ms / 67 tokens ( 6.08 ms per token, 164.57 tokens per second) 10.40.057.001 I slot print_timing: id 3 | task 12659 | eval time = 7786.77 ms / 176 tokens ( 44.50 ms per token, 22.47 tokens per second) 10.40.057.002 I slot print_timing: id 3 | task 12659 | total time = 8193.89 ms / 243 tokens 10.40.057.003 I slot print_timing: id 3 | task 12659 | graphs reused = 11838 10.40.057.004 I slot print_timing: id 3 | task 12659 | graph reallocs = 0 / 0 (same size) / (changed size) 10.40.057.080 I slot release: id 3 | task 12659 | stop processing: n_tokens = 1213, truncated = 0 10.40.098.216 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.800 10.40.098.243 I slot launch_slot_: id 3 | task 12840 | processing task, is_child = 0 10.41.612.255 I slot print_timing: id 0 | task 12766 | n_gen = 100, tg = 20.89 t/s, tg_3s = 21.10 t/s 10.42.050.557 I slot print_timing: id 2 | task 12573 | prompt eval time = 483.39 ms / 86 tokens ( 5.62 ms per token, 177.91 tokens per second) 10.42.050.565 I slot print_timing: id 2 | task 12573 | eval time = 13535.28 ms / 302 tokens ( 44.97 ms per token, 22.24 tokens per second) 10.42.050.566 I slot print_timing: id 2 | task 12573 | total time = 14018.67 ms / 388 tokens 10.42.050.567 I slot print_timing: id 2 | task 12573 | graphs reused = 11875 10.42.050.568 I slot print_timing: id 2 | task 12573 | graph reallocs = 0 / 0 (same size) / (changed size) 10.42.050.649 I slot release: id 2 | task 12573 | stop processing: n_tokens = 1358, truncated = 0 10.42.108.160 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.715 10.42.108.186 I slot launch_slot_: id 2 | task 12882 | processing task, is_child = 0 10.44.116.500 I slot print_timing: id 1 | task 12817 | n_gen = 100, tg = 20.52 t/s, tg_3s = 20.73 t/s 10.44.637.791 I slot print_timing: id 0 | task 12766 | n_gen = 163, tg = 20.87 t/s, tg_3s = 20.82 t/s 10.44.996.256 I slot print_timing: id 3 | task 12840 | n_gen = 100, tg = 22.17 t/s, tg_3s = 22.39 t/s 10.45.751.366 I slot print_timing: id 1 | task 12817 | prompt eval time = 437.30 ms / 69 tokens ( 6.34 ms per token, 157.79 tokens per second) 10.45.751.375 I slot print_timing: id 1 | task 12817 | eval time = 6459.15 ms / 141 tokens ( 46.14 ms per token, 21.67 tokens per second) 10.45.751.376 I slot print_timing: id 1 | task 12817 | total time = 6896.44 ms / 210 tokens 10.45.751.377 I slot print_timing: id 1 | task 12817 | graphs reused = 11950 10.45.751.377 I slot print_timing: id 1 | task 12817 | graph reallocs = 0 / 0 (same size) / (changed size) 10.45.751.446 I slot release: id 1 | task 12817 | stop processing: n_tokens = 1179, truncated = 0 10.45.808.736 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.824 10.45.808.765 I slot launch_slot_: id 1 | task 12963 | processing task, is_child = 0 10.47.049.157 I slot print_timing: id 2 | task 12882 | n_gen = 100, tg = 22.66 t/s, tg_3s = 22.89 t/s 10.47.647.527 I slot print_timing: id 0 | task 12766 | n_gen = 228, tg = 21.07 t/s, tg_3s = 21.60 t/s 10.48.013.549 I slot print_timing: id 3 | task 12840 | n_gen = 165, tg = 21.92 t/s, tg_3s = 21.54 t/s 10.49.570.332 I slot print_timing: id 3 | task 12840 | prompt eval time = 432.60 ms / 76 tokens ( 5.69 ms per token, 175.68 tokens per second) 10.49.570.339 I slot print_timing: id 3 | task 12840 | eval time = 9039.48 ms / 204 tokens ( 44.53 ms per token, 22.46 tokens per second) 10.49.570.340 I slot print_timing: id 3 | task 12840 | total time = 9472.08 ms / 280 tokens 10.49.570.341 I slot print_timing: id 3 | task 12840 | graphs reused = 12030 10.49.570.342 I slot print_timing: id 3 | task 12840 | graph reallocs = 0 / 0 (same size) / (changed size) 10.49.570.417 I slot release: id 3 | task 12840 | stop processing: n_tokens = 1250, truncated = 0 10.49.611.329 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.777 10.49.611.351 I slot launch_slot_: id 3 | task 13049 | processing task, is_child = 0 10.50.066.323 I slot print_timing: id 2 | task 12882 | n_gen = 166, tg = 22.34 t/s, tg_3s = 21.87 t/s 10.50.631.858 I slot print_timing: id 1 | task 12963 | n_gen = 100, tg = 22.76 t/s, tg_3s = 22.99 t/s 10.50.671.629 I slot print_timing: id 0 | task 12766 | n_gen = 294, tg = 21.24 t/s, tg_3s = 21.82 t/s 10.53.066.900 I slot print_timing: id 2 | task 12882 | n_gen = 241, tg = 23.11 t/s, tg_3s = 25.00 t/s 10.53.666.243 I slot print_timing: id 1 | task 12963 | n_gen = 176, tg = 23.70 t/s, tg_3s = 25.05 t/s 10.53.706.026 I slot print_timing: id 0 | task 12766 | n_gen = 370, tg = 21.92 t/s, tg_3s = 25.05 t/s 10.54.026.642 I slot print_timing: id 3 | task 13049 | n_gen = 100, tg = 25.00 t/s, tg_3s = 25.25 t/s 10.55.630.847 I slot print_timing: id 1 | task 12963 | prompt eval time = 473.09 ms / 79 tokens ( 5.99 ms per token, 166.99 tokens per second) 10.55.630.854 I slot print_timing: id 1 | task 12963 | eval time = 9348.98 ms / 225 tokens ( 41.74 ms per token, 23.96 tokens per second) 10.55.630.856 I slot print_timing: id 1 | task 12963 | total time = 9822.07 ms / 304 tokens 10.55.630.856 I slot print_timing: id 1 | task 12963 | graphs reused = 12167 10.55.630.857 I slot print_timing: id 1 | task 12963 | graph reallocs = 0 / 0 (same size) / (changed size) 10.55.630.924 I slot release: id 1 | task 12963 | stop processing: n_tokens = 1274, truncated = 0 10.55.687.624 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.762 10.55.687.650 I slot launch_slot_: id 1 | task 13192 | processing task, is_child = 0 10.56.130.808 I slot print_timing: id 2 | task 12882 | n_gen = 308, tg = 22.82 t/s, tg_3s = 21.87 t/s 10.56.729.904 I slot print_timing: id 0 | task 12766 | n_gen = 436, tg = 21.91 t/s, tg_3s = 21.83 t/s 10.57.050.206 I slot print_timing: id 3 | task 13049 | n_gen = 166, tg = 23.63 t/s, tg_3s = 21.83 t/s 10.57.330.265 I slot print_timing: id 3 | task 13049 | prompt eval time = 455.10 ms / 92 tokens ( 4.95 ms per token, 202.16 tokens per second) 10.57.330.272 I slot print_timing: id 3 | task 13049 | eval time = 7263.81 ms / 173 tokens ( 42.23 ms per token, 23.68 tokens per second) 10.57.330.273 I slot print_timing: id 3 | task 13049 | total time = 7718.90 ms / 265 tokens 10.57.330.274 I slot print_timing: id 3 | task 13049 | graphs reused = 12196 10.57.330.275 I slot print_timing: id 3 | task 13049 | graph reallocs = 0 / 0 (same size) / (changed size) 10.57.330.349 I slot release: id 3 | task 13049 | stop processing: n_tokens = 1235, truncated = 0 10.57.371.438 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.786 10.57.371.472 I slot launch_slot_: id 3 | task 13226 | processing task, is_child = 0 10.59.148.628 I slot print_timing: id 2 | task 12882 | n_gen = 373, tg = 22.59 t/s, tg_3s = 21.54 t/s 10.59.755.191 I slot print_timing: id 0 | task 12766 | n_gen = 501, tg = 21.85 t/s, tg_3s = 21.49 t/s 11.00.514.849 I slot print_timing: id 1 | task 13192 | n_gen = 100, tg = 22.58 t/s, tg_3s = 22.81 t/s 11.01.839.221 I slot print_timing: id 1 | task 13192 | prompt eval time = 443.05 ms / 63 tokens ( 7.03 ms per token, 142.20 tokens per second) 11.01.839.226 I slot print_timing: id 1 | task 13192 | eval time = 5708.51 ms / 133 tokens ( 43.25 ms per token, 23.12 tokens per second) 11.01.839.228 I slot print_timing: id 1 | task 13192 | total time = 6151.56 ms / 196 tokens 11.01.839.228 I slot print_timing: id 1 | task 13192 | graphs reused = 12293 11.01.839.229 I slot print_timing: id 1 | task 13192 | graph reallocs = 0 / 0 (same size) / (changed size) 11.01.839.301 I slot release: id 1 | task 13192 | stop processing: n_tokens = 1166, truncated = 0 11.01.839.649 I slot print_timing: id 3 | task 13226 | n_gen = 100, tg = 24.94 t/s, tg_3s = 25.19 t/s 11.01.896.944 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.834 11.01.896.973 I slot launch_slot_: id 1 | task 13329 | processing task, is_child = 0 11.02.222.597 I slot print_timing: id 2 | task 12882 | n_gen = 442, tg = 22.57 t/s, tg_3s = 22.45 t/s 11.02.770.555 I slot print_timing: id 0 | task 12766 | n_gen = 567, tg = 21.86 t/s, tg_3s = 21.89 t/s 11.04.860.093 I slot print_timing: id 3 | task 13226 | n_gen = 166, tg = 23.60 t/s, tg_3s = 21.85 t/s 11.05.262.404 I slot print_timing: id 2 | task 12882 | n_gen = 516, tg = 22.81 t/s, tg_3s = 24.34 t/s 11.05.785.875 I slot print_timing: id 0 | task 12766 | n_gen = 642, tg = 22.17 t/s, tg_3s = 24.87 t/s 11.06.309.472 I slot print_timing: id 1 | task 13329 | n_gen = 100, tg = 24.81 t/s, tg_3s = 25.06 t/s 11.07.877.064 I slot print_timing: id 3 | task 13226 | n_gen = 241, tg = 23.98 t/s, tg_3s = 24.86 t/s 11.07.917.186 I slot print_timing: id 3 | task 13226 | prompt eval time = 498.30 ms / 109 tokens ( 4.57 ms per token, 218.74 tokens per second) 11.07.917.194 I slot print_timing: id 3 | task 13226 | eval time = 10047.41 ms / 242 tokens ( 41.69 ms per token, 23.99 tokens per second) 11.07.917.195 I slot print_timing: id 3 | task 13226 | total time = 10545.71 ms / 351 tokens 11.07.917.196 I slot print_timing: id 3 | task 13226 | graphs reused = 12431 11.07.917.197 I slot print_timing: id 3 | task 13226 | graph reallocs = 0 / 0 (same size) / (changed size) 11.07.917.271 I slot release: id 3 | task 13226 | stop processing: n_tokens = 1321, truncated = 0 11.08.274.871 I slot print_timing: id 2 | task 12882 | n_gen = 592, tg = 23.09 t/s, tg_3s = 25.23 t/s 11.08.800.681 I slot print_timing: id 0 | task 12766 | n_gen = 720, tg = 22.52 t/s, tg_3s = 25.87 t/s 11.09.117.009 I slot print_timing: id 1 | task 13329 | prompt eval time = 422.36 ms / 64 tokens ( 6.60 ms per token, 151.53 tokens per second) 11.09.117.016 I slot print_timing: id 1 | task 13329 | eval time = 6797.66 ms / 174 tokens ( 39.29 ms per token, 25.45 tokens per second) 11.09.117.017 I slot print_timing: id 1 | task 13329 | total time = 7220.03 ms / 238 tokens 11.09.117.018 I slot print_timing: id 1 | task 13329 | graphs reused = 12464 11.09.117.018 I slot print_timing: id 1 | task 13329 | graph reallocs = 0 / 0 (same size) / (changed size) 11.09.117.087 I slot release: id 1 | task 13329 | stop processing: n_tokens = 1209, truncated = 0 11.11.288.273 I slot print_timing: id 2 | task 12882 | n_gen = 661, tg = 23.07 t/s, tg_3s = 22.90 t/s 11.11.818.270 I slot print_timing: id 0 | task 12766 | n_gen = 785, tg = 22.44 t/s, tg_3s = 21.54 t/s 11.14.328.252 I slot print_timing: id 2 | task 12882 | n_gen = 724, tg = 22.84 t/s, tg_3s = 20.72 t/s 11.14.859.239 I slot print_timing: id 0 | task 12766 | n_gen = 848, tg = 22.30 t/s, tg_3s = 20.72 t/s 11.17.365.912 I slot print_timing: id 2 | task 12882 | n_gen = 787, tg = 22.66 t/s, tg_3s = 20.74 t/s 11.17.896.228 I slot print_timing: id 0 | task 12766 | n_gen = 911, tg = 22.18 t/s, tg_3s = 20.74 t/s 11.20.402.999 I slot print_timing: id 2 | task 12882 | n_gen = 850, tg = 22.51 t/s, tg_3s = 20.74 t/s 11.20.933.736 I slot print_timing: id 0 | task 12766 | n_gen = 974, tg = 22.08 t/s, tg_3s = 20.74 t/s 11.22.917.837 I slot print_timing: id 2 | task 12882 | prompt eval time = 571.51 ms / 134 tokens ( 4.26 ms per token, 234.47 tokens per second) 11.22.917.844 I slot print_timing: id 2 | task 12882 | eval time = 40238.13 ms / 902 tokens ( 44.66 ms per token, 22.39 tokens per second) 11.22.917.845 I slot print_timing: id 2 | task 12882 | total time = 40809.64 ms / 1036 tokens 11.22.917.845 I slot print_timing: id 2 | task 12882 | graphs reused = 12464 11.22.917.846 I slot print_timing: id 2 | task 12882 | graph reallocs = 0 / 0 (same size) / (changed size) 11.22.917.901 I slot release: id 2 | task 12882 | stop processing: n_tokens = 2006, truncated = 0 11.23.114.806 I slot print_timing: id 0 | task 12766 | prompt eval time = 420.51 ms / 80 tokens ( 5.26 ms per token, 190.25 tokens per second) 11.23.114.812 I slot print_timing: id 0 | task 12766 | eval time = 46240.79 ms / 1024 tokens ( 45.20 ms per token, 22.12 tokens per second) 11.23.114.813 I slot print_timing: id 0 | task 12766 | total time = 46661.30 ms / 1104 tokens 11.23.114.813 I slot print_timing: id 0 | task 12766 | graphs reused = 12472 11.23.114.814 I slot print_timing: id 0 | task 12766 | graph reallocs = 0 / 0 (same size) / (changed size) 11.23.114.859 I slot release: id 0 | task 12766 | stop processing: n_tokens = 2074, truncated = 0 11.23.135.227 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1321, t_last = 349676664266 11.23.149.480 I slot launch_slot_: id 3 | task 13800 | processing task, is_child = 0 11.24.230.427 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1209, t_last = 349677864082 11.24.230.714 I slot launch_slot_: id 1 | task 13801 | processing task, is_child = 0 11.24.230.967 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2006, t_last = 349691664896 11.24.231.141 I slot launch_slot_: id 2 | task 13802 | processing task, is_child = 0 11.24.231.253 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2074, t_last = 349691861854 11.24.231.406 I slot launch_slot_: id 0 | task 13803 | processing task, is_child = 0 11.27.899.248 I slot print_timing: id 0 | task 13803 | prompt processing, n_tokens = 336, progress = 0.39, t = 3.67 s / 91.61 tokens per second 11.28.606.350 I slot print_timing: id 1 | task 13801 | prompt processing, n_tokens = 546, progress = 0.80, t = 3.67 s / 148.87 tokens per second 11.28.613.928 I slot print_timing: id 2 | task 13802 | prompt processing, n_tokens = 351, progress = 0.40, t = 3.67 s / 95.71 tokens per second 11.28.618.805 I slot print_timing: id 3 | task 13800 | prompt processing, n_tokens = 578, progress = 0.84, t = 3.67 s / 157.62 tokens per second 11.30.299.956 I slot print_timing: id 0 | task 13803 | prompt processing, n_tokens = 745, progress = 0.87, t = 6.07 s / 122.76 tokens per second 11.30.890.759 I slot print_timing: id 1 | task 13801 | prompt processing, n_tokens = 679, progress = 0.99, t = 6.07 s / 111.89 tokens per second 11.30.896.776 I slot print_timing: id 2 | task 13802 | prompt processing, n_tokens = 768, progress = 0.89, t = 6.07 s / 126.56 tokens per second 11.30.897.945 I slot print_timing: id 3 | task 13800 | prompt processing, n_tokens = 687, progress = 0.99, t = 6.07 s / 113.22 tokens per second 11.31.686.934 I slot print_timing: id 0 | task 13803 | prompt processing, n_tokens = 848, progress = 1.00, t = 7.46 s / 113.75 tokens per second 11.31.694.090 I slot print_timing: id 2 | task 13802 | prompt processing, n_tokens = 863, progress = 1.00, t = 7.45 s / 115.77 tokens per second 11.31.822.526 I slot print_timing: id 1 | task 13801 | prompt eval time = 7454.99 ms / 683 tokens ( 10.92 ms per token, 91.62 tokens per second) 11.31.822.532 I slot print_timing: id 1 | task 13801 | eval time = 135.81 ms / 2 tokens ( 135.81 ms per token, 7.36 tokens per second) 11.31.822.532 I slot print_timing: id 1 | task 13801 | total time = 7590.80 ms / 685 tokens 11.31.822.533 I slot print_timing: id 1 | task 13801 | graphs reused = 12472 11.31.822.534 I slot print_timing: id 1 | task 13801 | graph reallocs = 0 / 0 (same size) / (changed size) 11.31.822.609 I slot release: id 1 | task 13801 | stop processing: n_tokens = 684, truncated = 0 11.31.823.164 I slot print_timing: id 3 | task 13800 | prompt eval time = 7454.80 ms / 691 tokens ( 10.79 ms per token, 92.69 tokens per second) 11.31.823.168 I slot print_timing: id 3 | task 13800 | eval time = 136.24 ms / 2 tokens ( 136.24 ms per token, 7.34 tokens per second) 11.31.823.170 I slot print_timing: id 3 | task 13800 | total time = 7591.05 ms / 693 tokens 11.31.823.170 I slot print_timing: id 3 | task 13800 | graphs reused = 12472 11.31.823.171 I slot print_timing: id 3 | task 13800 | graph reallocs = 0 / 0 (same size) / (changed size) 11.31.823.221 I slot release: id 3 | task 13800 | stop processing: n_tokens = 692, truncated = 0 11.31.871.535 I slot print_timing: id 0 | task 13803 | prompt eval time = 7590.93 ms / 852 tokens ( 8.91 ms per token, 112.24 tokens per second) 11.31.871.540 I slot print_timing: id 0 | task 13803 | eval time = 49.19 ms / 2 tokens ( 49.19 ms per token, 20.33 tokens per second) 11.31.871.541 I slot print_timing: id 0 | task 13803 | total time = 7640.11 ms / 854 tokens 11.31.871.541 I slot print_timing: id 0 | task 13803 | graphs reused = 12472 11.31.871.542 I slot print_timing: id 0 | task 13803 | graph reallocs = 0 / 0 (same size) / (changed size) 11.31.871.600 I slot release: id 0 | task 13803 | stop processing: n_tokens = 853, truncated = 0 11.31.871.826 I slot print_timing: id 2 | task 13802 | prompt eval time = 7591.12 ms / 867 tokens ( 8.76 ms per token, 114.21 tokens per second) 11.31.871.830 I slot print_timing: id 2 | task 13802 | eval time = 48.83 ms / 2 tokens ( 48.83 ms per token, 20.48 tokens per second) 11.31.871.831 I slot print_timing: id 2 | task 13802 | total time = 7639.94 ms / 869 tokens 11.31.871.831 I slot print_timing: id 2 | task 13802 | graphs reused = 12472 11.31.871.832 I slot print_timing: id 2 | task 13802 | graph reallocs = 0 / 0 (same size) / (changed size) 11.31.871.882 I slot release: id 2 | task 13802 | stop processing: n_tokens = 868, truncated = 0 11.31.871.898 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 684, t_last = 349700569605 11.31.892.671 I slot launch_slot_: id 1 | task 13811 | processing task, is_child = 0 11.31.928.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.844 MiB) 11.31.928.338 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.695 MiB) 11.31.928.344 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.798 MiB) 11.31.928.352 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.275 MiB) 11.31.928.359 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 30.839 MiB) 11.32.006.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.024 MiB) 11.32.006.590 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.470 MiB) 11.32.006.597 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.711 MiB) 11.32.006.602 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.829 MiB) 11.32.006.605 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.977 MiB) 11.32.006.609 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 28.213 MiB) 11.32.006.616 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.695 MiB) 11.32.047.750 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 692, t_last = 349700570216 11.32.047.922 I slot launch_slot_: id 3 | task 13812 | processing task, is_child = 0 11.32.048.065 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 853, t_last = 349700618595 11.32.048.170 I slot launch_slot_: id 0 | task 13813 | processing task, is_child = 0 11.32.048.235 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 868, t_last = 349700618877 11.32.048.336 I slot launch_slot_: id 2 | task 13814 | processing task, is_child = 0 11.36.180.650 I slot print_timing: id 0 | task 13813 | prompt processing, n_tokens = 589, progress = 0.86, t = 4.13 s / 142.54 tokens per second 11.36.220.318 I slot print_timing: id 1 | task 13811 | prompt processing, n_tokens = 589, progress = 0.87, t = 4.13 s / 142.54 tokens per second 11.36.221.623 I slot print_timing: id 2 | task 13814 | prompt processing, n_tokens = 589, progress = 0.81, t = 4.13 s / 142.54 tokens per second 11.36.222.920 I slot print_timing: id 3 | task 13812 | prompt processing, n_tokens = 589, progress = 0.81, t = 4.13 s / 142.55 tokens per second 11.37.281.441 I slot print_timing: id 0 | task 13813 | prompt processing, n_tokens = 682, progress = 0.99, t = 5.23 s / 130.32 tokens per second 11.37.321.193 I slot print_timing: id 1 | task 13811 | prompt processing, n_tokens = 676, progress = 0.99, t = 5.23 s / 129.18 tokens per second 11.37.323.412 I slot print_timing: id 2 | task 13814 | prompt processing, n_tokens = 726, progress = 0.99, t = 5.23 s / 138.74 tokens per second 11.37.325.933 I slot print_timing: id 3 | task 13812 | prompt processing, n_tokens = 721, progress = 0.99, t = 5.23 s / 137.79 tokens per second 11.37.473.196 I slot print_timing: id 0 | task 13813 | prompt eval time = 5382.95 ms / 686 tokens ( 7.85 ms per token, 127.44 tokens per second) 11.37.473.202 I slot print_timing: id 0 | task 13813 | eval time = 41.89 ms / 2 tokens ( 41.89 ms per token, 23.87 tokens per second) 11.37.473.202 I slot print_timing: id 0 | task 13813 | total time = 5424.85 ms / 688 tokens 11.37.473.203 I slot print_timing: id 0 | task 13813 | graphs reused = 12473 11.37.473.203 I slot print_timing: id 0 | task 13813 | graph reallocs = 0 / 0 (same size) / (changed size) 11.37.473.242 I slot release: id 0 | task 13813 | stop processing: n_tokens = 687, truncated = 0 11.37.473.333 I slot print_timing: id 1 | task 13811 | prompt eval time = 5382.96 ms / 680 tokens ( 7.92 ms per token, 126.32 tokens per second) 11.37.473.335 I slot print_timing: id 1 | task 13811 | eval time = 41.91 ms / 2 tokens ( 41.91 ms per token, 23.86 tokens per second) 11.37.473.336 I slot print_timing: id 1 | task 13811 | total time = 5424.87 ms / 682 tokens 11.37.473.336 I slot print_timing: id 1 | task 13811 | graphs reused = 12473 11.37.473.336 I slot print_timing: id 1 | task 13811 | graph reallocs = 0 / 0 (same size) / (changed size) 11.37.473.356 I slot release: id 1 | task 13811 | stop processing: n_tokens = 681, truncated = 0 11.37.473.465 I slot print_timing: id 2 | task 13814 | prompt eval time = 5383.23 ms / 730 tokens ( 7.37 ms per token, 135.61 tokens per second) 11.37.473.467 I slot print_timing: id 2 | task 13814 | eval time = 41.69 ms / 2 tokens ( 41.69 ms per token, 23.98 tokens per second) 11.37.473.467 I slot print_timing: id 2 | task 13814 | total time = 5424.92 ms / 732 tokens 11.37.473.468 I slot print_timing: id 2 | task 13814 | graphs reused = 12473 11.37.473.468 I slot print_timing: id 2 | task 13814 | graph reallocs = 0 / 0 (same size) / (changed size) 11.37.473.494 I slot release: id 2 | task 13814 | stop processing: n_tokens = 731, truncated = 0 11.37.473.583 I slot print_timing: id 3 | task 13812 | prompt eval time = 5383.27 ms / 725 tokens ( 7.43 ms per token, 134.68 tokens per second) 11.37.473.587 I slot print_timing: id 3 | task 13812 | eval time = 41.67 ms / 2 tokens ( 41.67 ms per token, 24.00 tokens per second) 11.37.473.587 I slot print_timing: id 3 | task 13812 | total time = 5424.94 ms / 727 tokens 11.37.473.587 I slot print_timing: id 3 | task 13812 | graphs reused = 12473 11.37.473.588 I slot print_timing: id 3 | task 13812 | graph reallocs = 0 / 0 (same size) / (changed size) 11.37.473.604 I slot release: id 3 | task 13812 | stop processing: n_tokens = 726, truncated = 0 11.37.484.071 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.875 (> 0.100 thold), f_keep = 0.894 11.37.484.132 I slot launch_slot_: id 0 | task 13821 | processing task, is_child = 0 11.37.484.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.352 MiB) 11.37.484.216 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.157 MiB) 11.37.484.221 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.900 MiB) 11.37.484.226 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.547 MiB) 11.37.484.230 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.813 MiB) 11.37.484.235 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 16.890 MiB) 11.37.484.239 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.977 MiB) 11.37.515.211 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.367 MiB) 11.37.515.225 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.977 MiB) 11.37.515.233 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 15.413 MiB) 11.37.515.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.516 MiB) 11.37.515.242 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.993 MiB) 11.37.515.246 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.336 MiB) 11.37.515.251 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.752 MiB) 11.37.562.275 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.900 MiB) 11.37.562.297 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 28.377 MiB) 11.37.562.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.531 MiB) 11.37.562.310 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.649 MiB) 11.37.562.318 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.798 MiB) 11.37.562.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.752 MiB) 11.37.608.396 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 681, t_last = 349706220351 11.37.608.670 I slot launch_slot_: id 1 | task 13822 | processing task, is_child = 0 11.37.608.789 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 349706220489 11.37.608.892 I slot launch_slot_: id 2 | task 13823 | processing task, is_child = 0 11.37.608.951 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 349706220599 11.37.609.050 I slot launch_slot_: id 3 | task 13824 | processing task, is_child = 0 11.41.459.878 I slot print_timing: id 0 | task 13821 | prompt eval time = 2098.00 ms / 88 tokens ( 23.84 ms per token, 41.94 tokens per second) 11.41.459.881 I slot print_timing: id 0 | task 13821 | eval time = 1752.81 ms / 2 tokens ( 1752.81 ms per token, 0.57 tokens per second) 11.41.459.881 I slot print_timing: id 0 | task 13821 | total time = 3850.82 ms / 90 tokens 11.41.459.882 I slot print_timing: id 0 | task 13821 | graphs reused = 12473 11.41.459.882 I slot print_timing: id 0 | task 13821 | graph reallocs = 0 / 0 (same size) / (changed size) 11.41.460.008 I slot release: id 0 | task 13821 | stop processing: n_tokens = 703, truncated = 0 11.41.460.022 I slot print_timing: id 1 | task 13822 | prompt processing, n_tokens = 648, progress = 0.85, t = 3.85 s / 168.36 tokens per second 11.41.461.827 I slot print_timing: id 2 | task 13823 | prompt processing, n_tokens = 648, progress = 0.84, t = 3.85 s / 168.36 tokens per second 11.41.464.030 I slot print_timing: id 3 | task 13824 | prompt processing, n_tokens = 344, progress = 0.40, t = 3.85 s / 89.40 tokens per second 11.42.262.202 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 703, t_last = 349710207004 11.42.262.282 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.423 MiB) 11.42.262.296 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.111 MiB) 11.42.262.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.352 MiB) 11.42.262.307 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.752 MiB) 11.42.262.313 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.423 MiB) 11.42.262.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.531 MiB) 11.42.263.723 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.367 MiB) 11.42.264.655 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.813 MiB) 11.42.848.189 I slot launch_slot_: id 0 | task 13829 | processing task, is_child = 0 11.42.848.322 I slot print_timing: id 1 | task 13822 | prompt processing, n_tokens = 757, progress = 0.99, t = 4.65 s / 162.74 tokens per second 11.42.850.873 I slot print_timing: id 2 | task 13823 | prompt processing, n_tokens = 767, progress = 0.99, t = 4.65 s / 164.90 tokens per second 11.42.852.386 I slot print_timing: id 3 | task 13824 | prompt processing, n_tokens = 740, progress = 0.86, t = 4.65 s / 159.12 tokens per second 11.43.764.227 I slot print_timing: id 3 | task 13824 | prompt processing, n_tokens = 856, progress = 1.00, t = 6.15 s / 139.15 tokens per second 11.44.331.530 I slot print_timing: id 1 | task 13822 | prompt eval time = 6152.88 ms / 761 tokens ( 8.09 ms per token, 123.68 tokens per second) 11.44.331.535 I slot print_timing: id 1 | task 13822 | eval time = 567.90 ms / 2 tokens ( 567.90 ms per token, 1.76 tokens per second) 11.44.331.536 I slot print_timing: id 1 | task 13822 | total time = 6720.78 ms / 763 tokens 11.44.331.536 I slot print_timing: id 1 | task 13822 | graphs reused = 12473 11.44.331.537 I slot print_timing: id 1 | task 13822 | graph reallocs = 0 / 0 (same size) / (changed size) 11.44.331.653 I slot release: id 1 | task 13822 | stop processing: n_tokens = 762, truncated = 0 11.44.331.809 I slot print_timing: id 2 | task 13823 | prompt eval time = 6152.94 ms / 771 tokens ( 7.98 ms per token, 125.31 tokens per second) 11.44.331.815 I slot print_timing: id 2 | task 13823 | eval time = 568.03 ms / 2 tokens ( 568.03 ms per token, 1.76 tokens per second) 11.44.331.815 I slot print_timing: id 2 | task 13823 | total time = 6720.97 ms / 773 tokens 11.44.331.815 I slot print_timing: id 2 | task 13823 | graphs reused = 12473 11.44.331.816 I slot print_timing: id 2 | task 13823 | graph reallocs = 0 / 0 (same size) / (changed size) 11.44.331.854 I slot release: id 2 | task 13823 | stop processing: n_tokens = 772, truncated = 0 11.44.375.612 I slot print_timing: id 3 | task 13824 | prompt eval time = 6720.25 ms / 860 tokens ( 7.81 ms per token, 127.97 tokens per second) 11.44.375.616 I slot print_timing: id 3 | task 13824 | eval time = 43.60 ms / 2 tokens ( 43.60 ms per token, 22.93 tokens per second) 11.44.375.617 I slot print_timing: id 3 | task 13824 | total time = 6763.85 ms / 862 tokens 11.44.375.617 I slot print_timing: id 3 | task 13824 | graphs reused = 12473 11.44.375.618 I slot print_timing: id 3 | task 13824 | graph reallocs = 0 / 0 (same size) / (changed size) 11.44.375.699 I slot release: id 3 | task 13824 | stop processing: n_tokens = 861, truncated = 0 11.44.375.706 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 762, t_last = 349713078649 11.44.375.790 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.172 MiB) 11.44.375.803 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.516 MiB) 11.44.375.809 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.367 MiB) 11.44.376.961 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.649 MiB) 11.44.377.377 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.649 MiB) 11.44.377.552 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.367 MiB) 11.44.378.448 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.408 MiB) 11.44.393.972 I slot launch_slot_: id 1 | task 13833 | processing task, is_child = 0 11.44.394.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.875 MiB) 11.44.396.075 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.900 MiB) 11.44.398.769 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.941 MiB) 11.44.399.890 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.665 MiB) 11.44.401.029 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.649 MiB) 11.44.402.425 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.111 MiB) 11.44.424.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.777 MiB) 11.44.424.974 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.111 MiB) 11.44.428.289 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.485 MiB) 11.44.430.039 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 28.705 MiB) 11.44.431.022 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.875 MiB) 11.44.431.844 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.665 MiB) 11.44.432.850 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.736 MiB) 11.44.452.856 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 349713078849 11.44.453.052 I slot launch_slot_: id 2 | task 13834 | processing task, is_child = 0 11.44.453.117 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 861, t_last = 349713122696 11.44.453.235 I slot launch_slot_: id 3 | task 13835 | processing task, is_child = 0 11.47.185.082 I slot print_timing: id 0 | task 13829 | prompt processing, n_tokens = 880, progress = 1.00, t = 4.34 s / 202.91 tokens per second 11.48.706.461 I slot print_timing: id 1 | task 13833 | prompt processing, n_tokens = 403, progress = 0.44, t = 4.25 s / 94.86 tokens per second 11.48.710.483 I slot print_timing: id 2 | task 13834 | prompt processing, n_tokens = 295, progress = 0.36, t = 4.25 s / 69.47 tokens per second 11.48.713.071 I slot print_timing: id 3 | task 13835 | prompt processing, n_tokens = 655, progress = 0.41, t = 4.25 s / 154.27 tokens per second 11.51.251.335 I slot print_timing: id 0 | task 13829 | prompt eval time = 5858.24 ms / 884 tokens ( 6.63 ms per token, 150.90 tokens per second) 11.51.251.338 I slot print_timing: id 0 | task 13829 | eval time = 2544.88 ms / 2 tokens ( 2544.88 ms per token, 0.39 tokens per second) 11.51.251.338 I slot print_timing: id 0 | task 13829 | total time = 8403.12 ms / 886 tokens 11.51.251.339 I slot print_timing: id 0 | task 13829 | graphs reused = 12474 11.51.251.339 I slot print_timing: id 0 | task 13829 | graph reallocs = 0 / 0 (same size) / (changed size) 11.51.251.404 I slot release: id 0 | task 13829 | stop processing: n_tokens = 885, truncated = 0 11.51.251.417 I slot print_timing: id 1 | task 13833 | prompt processing, n_tokens = 781, progress = 0.85, t = 6.79 s / 114.97 tokens per second 11.51.256.936 I slot print_timing: id 2 | task 13834 | prompt processing, n_tokens = 655, progress = 0.81, t = 6.79 s / 96.44 tokens per second 11.51.260.964 I slot print_timing: id 3 | task 13835 | prompt processing, n_tokens = 1097, progress = 0.68, t = 6.79 s / 161.55 tokens per second 11.52.290.463 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 885, t_last = 349719998399 11.52.290.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.172 MiB) 11.52.290.568 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.172 MiB) 11.52.290.574 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.603 MiB) 11.52.290.582 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.024 MiB) 11.52.290.588 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 27.228 MiB) 11.52.290.597 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.244 MiB) 11.52.291.581 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 27.885 MiB) 11.53.014.148 I slot launch_slot_: id 0 | task 13841 | processing task, is_child = 0 11.53.014.729 I slot print_timing: id 1 | task 13833 | prompt processing, n_tokens = 915, progress = 1.00, t = 7.83 s / 116.82 tokens per second 11.53.016.161 I slot print_timing: id 2 | task 13834 | prompt processing, n_tokens = 807, progress = 1.00, t = 7.83 s / 103.06 tokens per second 11.53.017.536 I slot print_timing: id 3 | task 13835 | prompt processing, n_tokens = 1609, progress = 1.00, t = 7.83 s / 205.49 tokens per second 11.53.936.780 I slot print_timing: id 1 | task 13833 | prompt eval time = 9028.48 ms / 919 tokens ( 9.82 ms per token, 101.79 tokens per second) 11.53.936.782 I slot print_timing: id 1 | task 13833 | eval time = 450.37 ms / 2 tokens ( 450.37 ms per token, 2.22 tokens per second) 11.53.936.783 I slot print_timing: id 1 | task 13833 | total time = 9478.85 ms / 921 tokens 11.53.936.783 I slot print_timing: id 1 | task 13833 | graphs reused = 12474 11.53.936.783 I slot print_timing: id 1 | task 13833 | graph reallocs = 0 / 0 (same size) / (changed size) 11.53.936.830 I slot release: id 1 | task 13833 | stop processing: n_tokens = 920, truncated = 0 11.53.936.926 I slot print_timing: id 2 | task 13834 | prompt eval time = 9026.90 ms / 811 tokens ( 11.13 ms per token, 89.84 tokens per second) 11.53.936.931 I slot print_timing: id 2 | task 13834 | eval time = 450.34 ms / 2 tokens ( 450.34 ms per token, 2.22 tokens per second) 11.53.936.932 I slot print_timing: id 2 | task 13834 | total time = 9477.23 ms / 813 tokens 11.53.936.932 I slot print_timing: id 2 | task 13834 | graphs reused = 12474 11.53.936.932 I slot print_timing: id 2 | task 13834 | graph reallocs = 0 / 0 (same size) / (changed size) 11.53.937.046 I slot release: id 2 | task 13834 | stop processing: n_tokens = 812, truncated = 0 11.53.937.150 I slot print_timing: id 3 | task 13835 | prompt eval time = 9026.24 ms / 1613 tokens ( 5.60 ms per token, 178.70 tokens per second) 11.53.937.151 I slot print_timing: id 3 | task 13835 | eval time = 450.33 ms / 2 tokens ( 450.33 ms per token, 2.22 tokens per second) 11.53.937.152 I slot print_timing: id 3 | task 13835 | total time = 9476.57 ms / 1615 tokens 11.53.937.152 I slot print_timing: id 3 | task 13835 | graphs reused = 12474 11.53.937.152 I slot print_timing: id 3 | task 13835 | graph reallocs = 0 / 0 (same size) / (changed size) 11.53.937.320 I slot release: id 3 | task 13835 | stop processing: n_tokens = 1614, truncated = 0 11.54.250.179 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 920, t_last = 349722683826 11.54.250.262 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.547 MiB) 11.54.251.210 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.695 MiB) 11.54.251.665 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.875 MiB) 11.54.252.387 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.516 MiB) 11.54.252.833 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.352 MiB) 11.54.252.843 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.008 MiB) 11.54.254.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.649 MiB) 11.54.254.195 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.531 MiB) 11.54.254.513 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.680 MiB) 11.54.914.957 I slot launch_slot_: id 1 | task 13846 | processing task, is_child = 0 11.54.915.034 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.618 MiB) 11.54.915.048 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.157 MiB) 11.54.916.043 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.782 MiB) 11.54.916.052 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.095 MiB) 11.54.916.060 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 16.234 MiB) 11.54.916.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.993 MiB) 11.54.916.359 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.470 MiB) 11.54.984.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.680 MiB) 11.54.985.270 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.695 MiB) 11.54.985.806 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.618 MiB) 11.54.985.823 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.439 MiB) 11.54.985.854 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.516 MiB) 11.54.985.905 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.383 MiB) 11.54.986.939 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.423 MiB) 11.54.987.874 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 16.070 MiB) 11.54.989.537 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.336 MiB) 11.55.031.203 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 812, t_last = 349722684042 11.55.031.388 I slot launch_slot_: id 2 | task 13847 | processing task, is_child = 0 11.55.031.489 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1614, t_last = 349722684317 11.55.031.636 I slot launch_slot_: id 3 | task 13848 | processing task, is_child = 0 11.56.059.666 I slot print_timing: id 0 | task 13841 | prompt processing, n_tokens = 823, progress = 1.00, t = 3.05 s / 270.24 tokens per second 11.58.711.132 I slot print_timing: id 0 | task 13841 | prompt eval time = 3907.32 ms / 827 tokens ( 4.72 ms per token, 211.65 tokens per second) 11.58.711.135 I slot print_timing: id 0 | task 13841 | eval time = 1789.65 ms / 2 tokens ( 1789.65 ms per token, 0.56 tokens per second) 11.58.711.135 I slot print_timing: id 0 | task 13841 | total time = 5696.97 ms / 829 tokens 11.58.711.136 I slot print_timing: id 0 | task 13841 | graphs reused = 12474 11.58.711.136 I slot print_timing: id 0 | task 13841 | graph reallocs = 0 / 0 (same size) / (changed size) 11.58.711.219 I slot release: id 0 | task 13841 | stop processing: n_tokens = 828, truncated = 0 11.58.711.234 I slot print_timing: id 1 | task 13846 | prompt processing, n_tokens = 527, progress = 0.84, t = 3.67 s / 143.47 tokens per second 11.58.713.917 I slot print_timing: id 2 | task 13847 | prompt processing, n_tokens = 527, progress = 0.81, t = 3.67 s / 143.54 tokens per second 11.58.716.540 I slot print_timing: id 3 | task 13848 | prompt processing, n_tokens = 264, progress = 0.34, t = 3.67 s / 71.95 tokens per second 11.59.558.853 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 349727458216 11.59.558.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.618 MiB) 11.59.558.960 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.900 MiB) 11.59.558.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.383 MiB) 11.59.558.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.172 MiB) 11.59.558.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.665 MiB) 11.59.558.986 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.275 MiB) 11.59.558.989 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.054 MiB) 12.00.172.301 I slot launch_slot_: id 0 | task 13853 | processing task, is_child = 0 12.00.172.442 I slot print_timing: id 1 | task 13846 | prompt processing, n_tokens = 623, progress = 0.99, t = 4.52 s / 137.80 tokens per second 12.00.174.972 I slot print_timing: id 2 | task 13847 | prompt processing, n_tokens = 650, progress = 0.99, t = 4.52 s / 143.83 tokens per second 12.00.176.570 I slot print_timing: id 3 | task 13848 | prompt processing, n_tokens = 680, progress = 0.87, t = 4.52 s / 150.55 tokens per second 12.00.964.360 I slot print_timing: id 3 | task 13848 | prompt processing, n_tokens = 776, progress = 0.99, t = 5.92 s / 131.05 tokens per second 12.01.114.231 I slot print_timing: id 1 | task 13846 | prompt eval time = 5925.89 ms / 627 tokens ( 9.45 ms per token, 105.81 tokens per second) 12.01.114.236 I slot print_timing: id 1 | task 13846 | eval time = 150.52 ms / 2 tokens ( 150.52 ms per token, 6.64 tokens per second) 12.01.114.237 I slot print_timing: id 1 | task 13846 | total time = 6076.41 ms / 629 tokens 12.01.114.237 I slot print_timing: id 1 | task 13846 | graphs reused = 12474 12.01.114.238 I slot print_timing: id 1 | task 13846 | graph reallocs = 0 / 0 (same size) / (changed size) 12.01.114.295 I slot release: id 1 | task 13846 | stop processing: n_tokens = 628, truncated = 0 12.01.114.431 I slot print_timing: id 2 | task 13847 | prompt eval time = 5924.41 ms / 654 tokens ( 9.06 ms per token, 110.39 tokens per second) 12.01.114.434 I slot print_timing: id 2 | task 13847 | eval time = 150.49 ms / 2 tokens ( 150.49 ms per token, 6.64 tokens per second) 12.01.114.434 I slot print_timing: id 2 | task 13847 | total time = 6074.90 ms / 656 tokens 12.01.114.435 I slot print_timing: id 2 | task 13847 | graphs reused = 12474 12.01.114.435 I slot print_timing: id 2 | task 13847 | graph reallocs = 0 / 0 (same size) / (changed size) 12.01.114.459 I slot release: id 2 | task 13847 | stop processing: n_tokens = 655, truncated = 0 12.01.863.537 I slot print_timing: id 3 | task 13848 | prompt eval time = 6072.76 ms / 780 tokens ( 7.79 ms per token, 128.44 tokens per second) 12.01.863.540 I slot print_timing: id 3 | task 13848 | eval time = 748.83 ms / 2 tokens ( 748.83 ms per token, 1.34 tokens per second) 12.01.863.541 I slot print_timing: id 3 | task 13848 | total time = 6821.59 ms / 782 tokens 12.01.863.541 I slot print_timing: id 3 | task 13848 | graphs reused = 12474 12.01.863.541 I slot print_timing: id 3 | task 13848 | graph reallocs = 0 / 0 (same size) / (changed size) 12.01.863.611 I slot release: id 3 | task 13848 | stop processing: n_tokens = 781, truncated = 0 12.01.863.618 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.879 12.01.863.693 I slot launch_slot_: id 1 | task 13857 | processing task, is_child = 0 12.01.863.771 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.531 MiB) 12.01.863.783 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.275 MiB) 12.01.865.200 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.126 MiB) 12.01.866.196 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.634 MiB) 12.01.866.213 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.275 MiB) 12.01.866.682 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.290 MiB) 12.01.867.063 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.454 MiB) 12.01.898.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 15.085 MiB) 12.01.898.895 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.219 MiB) 12.01.898.904 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.034 MiB) 12.01.898.982 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.188 MiB) 12.01.898.990 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 16.562 MiB) 12.01.899.391 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.111 MiB) 12.01.899.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.531 MiB) 12.01.916.927 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.843 12.01.917.032 I slot launch_slot_: id 2 | task 13858 | processing task, is_child = 0 12.01.917.097 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 781, t_last = 349730610606 12.01.917.200 I slot launch_slot_: id 3 | task 13859 | processing task, is_child = 0 12.03.483.849 I slot print_timing: id 0 | task 13853 | prompt eval time = 3250.99 ms / 631 tokens ( 5.15 ms per token, 194.10 tokens per second) 12.03.483.852 I slot print_timing: id 0 | task 13853 | eval time = 60.54 ms / 2 tokens ( 60.54 ms per token, 16.52 tokens per second) 12.03.483.852 I slot print_timing: id 0 | task 13853 | total time = 3311.53 ms / 633 tokens 12.03.483.852 I slot print_timing: id 0 | task 13853 | graphs reused = 12474 12.03.483.853 I slot print_timing: id 0 | task 13853 | graph reallocs = 0 / 0 (same size) / (changed size) 12.03.483.900 I slot release: id 0 | task 13853 | stop processing: n_tokens = 632, truncated = 0 12.03.483.991 I slot print_timing: id 1 | task 13857 | prompt eval time = 1499.51 ms / 82 tokens ( 18.29 ms per token, 54.68 tokens per second) 12.03.483.992 I slot print_timing: id 1 | task 13857 | eval time = 60.57 ms / 2 tokens ( 60.57 ms per token, 16.51 tokens per second) 12.03.483.993 I slot print_timing: id 1 | task 13857 | total time = 1560.08 ms / 84 tokens 12.03.483.993 I slot print_timing: id 1 | task 13857 | graphs reused = 12474 12.03.483.994 I slot print_timing: id 1 | task 13857 | graph reallocs = 0 / 0 (same size) / (changed size) 12.03.484.013 I slot release: id 1 | task 13857 | stop processing: n_tokens = 635, truncated = 0 12.03.484.112 I slot print_timing: id 2 | task 13858 | prompt eval time = 1498.53 ms / 84 tokens ( 17.84 ms per token, 56.05 tokens per second) 12.03.484.114 I slot print_timing: id 2 | task 13858 | eval time = 60.53 ms / 2 tokens ( 60.53 ms per token, 16.52 tokens per second) 12.03.484.114 I slot print_timing: id 2 | task 13858 | total time = 1559.06 ms / 86 tokens 12.03.484.114 I slot print_timing: id 2 | task 13858 | graphs reused = 12474 12.03.484.115 I slot print_timing: id 2 | task 13858 | graph reallocs = 0 / 0 (same size) / (changed size) 12.03.484.134 I slot release: id 2 | task 13858 | stop processing: n_tokens = 637, truncated = 0 12.03.494.692 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 349732230895 12.03.494.759 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.367 MiB) 12.03.495.064 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.695 MiB) 12.03.495.357 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.829 MiB) 12.03.495.639 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.500 MiB) 12.03.496.300 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.367 MiB) 12.03.496.744 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.485 MiB) 12.03.497.484 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.603 MiB) 12.04.247.901 I slot launch_slot_: id 0 | task 13864 | processing task, is_child = 0 12.04.247.974 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.080 MiB) 12.04.247.983 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.500 MiB) 12.04.248.429 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 15.578 MiB) 12.04.249.043 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 28.541 MiB) 12.04.249.437 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.454 MiB) 12.04.250.160 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.695 MiB) 12.04.251.991 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.829 MiB) 12.04.252.738 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.883 MiB) 12.04.453.109 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 349732231008 12.04.453.277 I slot launch_slot_: id 1 | task 13865 | processing task, is_child = 0 12.04.453.333 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 349732231129 12.04.453.446 I slot launch_slot_: id 2 | task 13866 | processing task, is_child = 0 12.05.402.403 I slot print_timing: id 3 | task 13859 | prompt processing, n_tokens = 756, progress = 0.99, t = 3.20 s / 236.28 tokens per second 12.06.992.304 I slot print_timing: id 3 | task 13859 | prompt eval time = 4432.44 ms / 760 tokens ( 5.83 ms per token, 171.46 tokens per second) 12.06.992.307 I slot print_timing: id 3 | task 13859 | eval time = 633.64 ms / 2 tokens ( 633.64 ms per token, 1.58 tokens per second) 12.06.992.307 I slot print_timing: id 3 | task 13859 | total time = 5066.08 ms / 762 tokens 12.06.992.308 I slot print_timing: id 3 | task 13859 | graphs reused = 12474 12.06.992.308 I slot print_timing: id 3 | task 13859 | graph reallocs = 0 / 0 (same size) / (changed size) 12.06.992.354 I slot release: id 3 | task 13859 | stop processing: n_tokens = 761, truncated = 0 12.09.180.869 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 761, t_last = 349735739349 12.09.180.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 241.068 MiB) 12.09.306.112 I slot launch_slot_: id 3 | task 13871 | processing task, is_child = 0 12.09.306.133 I slot print_timing: id 0 | task 13864 | prompt processing, n_tokens = 741, progress = 0.87, t = 4.73 s / 156.75 tokens per second 12.09.314.626 I slot print_timing: id 1 | task 13865 | prompt processing, n_tokens = 741, progress = 0.85, t = 4.73 s / 156.75 tokens per second 12.09.322.072 I slot print_timing: id 2 | task 13866 | prompt processing, n_tokens = 741, progress = 0.83, t = 4.73 s / 156.77 tokens per second 12.10.430.739 I slot print_timing: id 0 | task 13864 | prompt processing, n_tokens = 848, progress = 1.00, t = 5.98 s / 141.87 tokens per second 12.10.559.988 I slot print_timing: id 1 | task 13865 | prompt processing, n_tokens = 867, progress = 1.00, t = 5.98 s / 145.05 tokens per second 12.10.562.743 I slot print_timing: id 2 | task 13866 | prompt processing, n_tokens = 889, progress = 1.00, t = 5.98 s / 148.75 tokens per second 12.11.418.381 I slot print_timing: id 0 | task 13864 | prompt eval time = 6672.59 ms / 852 tokens ( 7.83 ms per token, 127.69 tokens per second) 12.11.418.387 I slot print_timing: id 0 | task 13864 | eval time = 292.33 ms / 2 tokens ( 292.33 ms per token, 3.42 tokens per second) 12.11.418.388 I slot print_timing: id 0 | task 13864 | total time = 6964.92 ms / 854 tokens 12.11.418.388 I slot print_timing: id 0 | task 13864 | graphs reused = 12475 12.11.418.388 I slot print_timing: id 0 | task 13864 | graph reallocs = 0 / 0 (same size) / (changed size) 12.11.418.440 I slot release: id 0 | task 13864 | stop processing: n_tokens = 853, truncated = 0 12.11.418.590 I slot print_timing: id 1 | task 13865 | prompt eval time = 6672.74 ms / 871 tokens ( 7.66 ms per token, 130.53 tokens per second) 12.11.418.592 I slot print_timing: id 1 | task 13865 | eval time = 292.30 ms / 2 tokens ( 292.30 ms per token, 3.42 tokens per second) 12.11.418.592 I slot print_timing: id 1 | task 13865 | total time = 6965.04 ms / 873 tokens 12.11.418.593 I slot print_timing: id 1 | task 13865 | graphs reused = 12475 12.11.418.593 I slot print_timing: id 1 | task 13865 | graph reallocs = 0 / 0 (same size) / (changed size) 12.11.418.616 I slot release: id 1 | task 13865 | stop processing: n_tokens = 872, truncated = 0 12.11.418.710 I slot print_timing: id 2 | task 13866 | prompt eval time = 6672.22 ms / 893 tokens ( 7.47 ms per token, 133.84 tokens per second) 12.11.418.712 I slot print_timing: id 2 | task 13866 | eval time = 292.17 ms / 2 tokens ( 292.17 ms per token, 3.42 tokens per second) 12.11.418.712 I slot print_timing: id 2 | task 13866 | total time = 6964.39 ms / 895 tokens 12.11.418.712 I slot print_timing: id 2 | task 13866 | graphs reused = 12475 12.11.418.713 I slot print_timing: id 2 | task 13866 | graph reallocs = 0 / 0 (same size) / (changed size) 12.11.418.743 I slot release: id 2 | task 13866 | stop processing: n_tokens = 894, truncated = 0 12.11.428.963 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 853, t_last = 349740165435 12.12.156.987 I slot launch_slot_: id 0 | task 13876 | processing task, is_child = 0 12.12.157.074 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.035 MiB) 12.12.186.626 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 288.089 MiB) 12.12.215.996 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.878 12.12.216.088 I slot launch_slot_: id 1 | task 13877 | processing task, is_child = 0 12.12.216.161 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 894, t_last = 349740165738 12.12.216.267 I slot launch_slot_: id 2 | task 13878 | processing task, is_child = 0 12.13.426.500 I slot print_timing: id 3 | task 13871 | prompt processing, n_tokens = 857, progress = 1.00, t = 3.98 s / 215.50 tokens per second 12.15.370.858 I slot print_timing: id 1 | task 13877 | prompt eval time = 1996.77 ms / 93 tokens ( 21.47 ms per token, 46.58 tokens per second) 12.15.370.863 I slot print_timing: id 1 | task 13877 | eval time = 1157.69 ms / 2 tokens ( 1157.69 ms per token, 0.86 tokens per second) 12.15.370.864 I slot print_timing: id 1 | task 13877 | total time = 3154.46 ms / 95 tokens 12.15.370.864 I slot print_timing: id 1 | task 13877 | graphs reused = 12475 12.15.370.874 I slot print_timing: id 1 | task 13877 | graph reallocs = 0 / 0 (same size) / (changed size) 12.15.370.921 I slot release: id 1 | task 13877 | stop processing: n_tokens = 860, truncated = 0 12.15.371.073 I slot print_timing: id 3 | task 13871 | prompt eval time = 4887.57 ms / 861 tokens ( 5.68 ms per token, 176.16 tokens per second) 12.15.371.078 I slot print_timing: id 3 | task 13871 | eval time = 1157.80 ms / 2 tokens ( 1157.80 ms per token, 0.86 tokens per second) 12.15.371.078 I slot print_timing: id 3 | task 13871 | total time = 6045.37 ms / 863 tokens 12.15.371.079 I slot print_timing: id 3 | task 13871 | graphs reused = 12475 12.15.371.079 I slot print_timing: id 3 | task 13871 | graph reallocs = 0 / 0 (same size) / (changed size) 12.15.371.104 I slot release: id 3 | task 13871 | stop processing: n_tokens = 862, truncated = 0 12.15.371.112 I slot print_timing: id 0 | task 13876 | prompt processing, n_tokens = 617, progress = 0.83, t = 3.15 s / 195.60 tokens per second 12.15.373.146 I slot print_timing: id 2 | task 13878 | prompt processing, n_tokens = 390, progress = 0.43, t = 3.15 s / 123.69 tokens per second 12.15.778.561 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 349744117916 12.16.386.393 I slot launch_slot_: id 1 | task 13883 | processing task, is_child = 0 12.16.386.502 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.911 MiB) 12.16.415.361 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 862, t_last = 349744118099 12.16.415.506 I slot launch_slot_: id 3 | task 13884 | processing task, is_child = 0 12.16.415.518 I slot print_timing: id 0 | task 13876 | prompt processing, n_tokens = 740, progress = 0.99, t = 3.56 s / 207.73 tokens per second 12.16.421.867 I slot print_timing: id 2 | task 13878 | prompt processing, n_tokens = 686, progress = 0.76, t = 3.56 s / 192.64 tokens per second 12.17.486.316 I slot print_timing: id 2 | task 13878 | prompt processing, n_tokens = 902, progress = 1.00, t = 5.27 s / 171.21 tokens per second 12.18.445.403 I slot print_timing: id 0 | task 13876 | prompt eval time = 5269.76 ms / 744 tokens ( 7.08 ms per token, 141.18 tokens per second) 12.18.445.409 I slot print_timing: id 0 | task 13876 | eval time = 959.37 ms / 2 tokens ( 959.37 ms per token, 1.04 tokens per second) 12.18.445.409 I slot print_timing: id 0 | task 13876 | total time = 6229.12 ms / 746 tokens 12.18.445.410 I slot print_timing: id 0 | task 13876 | graphs reused = 12475 12.18.445.410 I slot print_timing: id 0 | task 13876 | graph reallocs = 0 / 0 (same size) / (changed size) 12.18.445.490 I slot release: id 0 | task 13876 | stop processing: n_tokens = 745, truncated = 0 12.18.970.357 I slot print_timing: id 2 | task 13878 | prompt eval time = 6228.05 ms / 906 tokens ( 6.87 ms per token, 145.47 tokens per second) 12.18.970.359 I slot print_timing: id 2 | task 13878 | eval time = 524.75 ms / 2 tokens ( 524.75 ms per token, 1.91 tokens per second) 12.18.970.360 I slot print_timing: id 2 | task 13878 | total time = 6752.80 ms / 908 tokens 12.18.970.360 I slot print_timing: id 2 | task 13878 | graphs reused = 12475 12.18.970.361 I slot print_timing: id 2 | task 13878 | graph reallocs = 0 / 0 (same size) / (changed size) 12.18.970.473 I slot release: id 2 | task 13878 | stop processing: n_tokens = 907, truncated = 0 12.18.970.483 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.784 12.18.970.572 I slot launch_slot_: id 2 | task 13888 | processing task, is_child = 0 12.18.986.707 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 745, t_last = 349747192486 12.18.986.867 I slot launch_slot_: id 0 | task 13889 | processing task, is_child = 0 12.20.928.417 I slot print_timing: id 1 | task 13883 | prompt processing, n_tokens = 686, progress = 0.86, t = 4.00 s / 171.61 tokens per second 12.20.931.420 I slot print_timing: id 3 | task 13884 | prompt processing, n_tokens = 686, progress = 0.77, t = 4.00 s / 171.66 tokens per second 12.22.320.669 I slot print_timing: id 0 | task 13889 | prompt processing, n_tokens = 259, progress = 0.30, t = 3.33 s / 77.69 tokens per second 12.22.320.680 I slot print_timing: id 1 | task 13883 | prompt processing, n_tokens = 793, progress = 0.99, t = 5.90 s / 134.44 tokens per second 12.22.330.677 I slot print_timing: id 3 | task 13884 | prompt processing, n_tokens = 890, progress = 1.00, t = 5.90 s / 150.91 tokens per second 12.22.776.002 I slot print_timing: id 2 | task 13888 | prompt eval time = 3332.85 ms / 88 tokens ( 37.87 ms per token, 26.40 tokens per second) 12.22.776.005 I slot print_timing: id 2 | task 13888 | eval time = 455.34 ms / 2 tokens ( 455.34 ms per token, 2.20 tokens per second) 12.22.776.005 I slot print_timing: id 2 | task 13888 | total time = 3788.19 ms / 90 tokens 12.22.776.006 I slot print_timing: id 2 | task 13888 | graphs reused = 12475 12.22.776.006 I slot print_timing: id 2 | task 13888 | graph reallocs = 0 / 0 (same size) / (changed size) 12.22.776.082 I slot release: id 2 | task 13888 | stop processing: n_tokens = 800, truncated = 0 12.22.776.362 I slot print_timing: id 0 | task 13889 | prompt processing, n_tokens = 347, progress = 0.40, t = 3.79 s / 91.59 tokens per second 12.23.480.653 I slot print_timing: id 1 | task 13883 | prompt eval time = 6354.12 ms / 797 tokens ( 7.97 ms per token, 125.43 tokens per second) 12.23.480.658 I slot print_timing: id 1 | task 13883 | eval time = 704.77 ms / 2 tokens ( 704.77 ms per token, 1.42 tokens per second) 12.23.480.658 I slot print_timing: id 1 | task 13883 | total time = 7058.90 ms / 799 tokens 12.23.480.659 I slot print_timing: id 1 | task 13883 | graphs reused = 12475 12.23.480.659 I slot print_timing: id 1 | task 13883 | graph reallocs = 0 / 0 (same size) / (changed size) 12.23.480.706 I slot release: id 1 | task 13883 | stop processing: n_tokens = 798, truncated = 0 12.23.480.867 I slot print_timing: id 3 | task 13884 | prompt eval time = 6353.33 ms / 894 tokens ( 7.11 ms per token, 140.71 tokens per second) 12.23.480.871 I slot print_timing: id 3 | task 13884 | eval time = 704.51 ms / 2 tokens ( 704.51 ms per token, 1.42 tokens per second) 12.23.480.871 I slot print_timing: id 3 | task 13884 | total time = 7057.84 ms / 896 tokens 12.23.480.871 I slot print_timing: id 3 | task 13884 | graphs reused = 12475 12.23.480.872 I slot print_timing: id 3 | task 13884 | graph reallocs = 0 / 0 (same size) / (changed size) 12.23.480.945 I slot release: id 3 | task 13884 | stop processing: n_tokens = 895, truncated = 0 12.23.480.951 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.891 12.23.481.017 I slot launch_slot_: id 1 | task 13894 | processing task, is_child = 0 12.23.481.101 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.648 MiB) 12.23.519.352 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.886 MiB) 12.23.551.082 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 349751523077 12.23.551.248 I slot launch_slot_: id 2 | task 13895 | processing task, is_child = 0 12.23.551.313 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 349752227940 12.23.551.427 I slot launch_slot_: id 3 | task 13896 | processing task, is_child = 0 12.23.551.434 I slot print_timing: id 0 | task 13889 | prompt processing, n_tokens = 686, progress = 0.79, t = 4.49 s / 152.66 tokens per second 12.24.511.960 I slot print_timing: id 0 | task 13889 | prompt processing, n_tokens = 859, progress = 1.00, t = 5.53 s / 155.47 tokens per second 12.25.864.489 I slot print_timing: id 0 | task 13889 | prompt eval time = 6255.82 ms / 863 tokens ( 7.25 ms per token, 137.95 tokens per second) 12.25.864.493 I slot print_timing: id 0 | task 13889 | eval time = 621.78 ms / 2 tokens ( 621.78 ms per token, 1.61 tokens per second) 12.25.864.494 I slot print_timing: id 0 | task 13889 | total time = 6877.60 ms / 865 tokens 12.25.864.494 I slot print_timing: id 0 | task 13889 | graphs reused = 12475 12.25.864.494 I slot print_timing: id 0 | task 13889 | graph reallocs = 0 / 0 (same size) / (changed size) 12.25.864.561 I slot release: id 0 | task 13889 | stop processing: n_tokens = 864, truncated = 0 12.25.864.707 I slot print_timing: id 1 | task 13894 | prompt eval time = 1684.48 ms / 74 tokens ( 22.76 ms per token, 43.93 tokens per second) 12.25.864.709 I slot print_timing: id 1 | task 13894 | eval time = 621.86 ms / 2 tokens ( 621.86 ms per token, 1.61 tokens per second) 12.25.864.710 I slot print_timing: id 1 | task 13894 | total time = 2306.35 ms / 76 tokens 12.25.864.710 I slot print_timing: id 1 | task 13894 | graphs reused = 12475 12.25.864.711 I slot print_timing: id 1 | task 13894 | graph reallocs = 0 / 0 (same size) / (changed size) 12.25.864.736 I slot release: id 1 | task 13894 | stop processing: n_tokens = 786, truncated = 0 12.27.190.898 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 864, t_last = 349754611557 12.27.416.637 I slot launch_slot_: id 0 | task 13901 | processing task, is_child = 0 12.27.416.722 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.011 MiB) 12.27.455.356 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 786, t_last = 349754611731 12.27.455.523 I slot launch_slot_: id 1 | task 13902 | processing task, is_child = 0 12.27.455.805 I slot print_timing: id 2 | task 13895 | prompt processing, n_tokens = 678, progress = 0.85, t = 3.63 s / 186.77 tokens per second 12.27.456.969 I slot print_timing: id 3 | task 13896 | prompt processing, n_tokens = 678, progress = 0.81, t = 3.63 s / 186.78 tokens per second 12.28.943.531 I slot print_timing: id 2 | task 13895 | prompt processing, n_tokens = 794, progress = 0.99, t = 5.14 s / 154.47 tokens per second 12.28.945.656 I slot print_timing: id 3 | task 13896 | prompt processing, n_tokens = 837, progress = 1.00, t = 5.14 s / 162.84 tokens per second 12.30.955.631 I slot print_timing: id 2 | task 13895 | prompt eval time = 6386.32 ms / 798 tokens ( 8.00 ms per token, 124.95 tokens per second) 12.30.955.634 I slot print_timing: id 2 | task 13895 | eval time = 1008.49 ms / 2 tokens ( 1008.49 ms per token, 0.99 tokens per second) 12.30.955.634 I slot print_timing: id 2 | task 13895 | total time = 7394.81 ms / 800 tokens 12.30.955.635 I slot print_timing: id 2 | task 13895 | graphs reused = 12475 12.30.955.635 I slot print_timing: id 2 | task 13895 | graph reallocs = 0 / 0 (same size) / (changed size) 12.30.955.724 I slot release: id 2 | task 13895 | stop processing: n_tokens = 799, truncated = 0 12.30.955.881 I slot print_timing: id 3 | task 13896 | prompt eval time = 6386.32 ms / 841 tokens ( 7.59 ms per token, 131.69 tokens per second) 12.30.955.885 I slot print_timing: id 3 | task 13896 | eval time = 1008.64 ms / 2 tokens ( 1008.64 ms per token, 0.99 tokens per second) 12.30.955.886 I slot print_timing: id 3 | task 13896 | total time = 7394.97 ms / 843 tokens 12.30.955.886 I slot print_timing: id 3 | task 13896 | graphs reused = 12475 12.30.955.887 I slot print_timing: id 3 | task 13896 | graph reallocs = 0 / 0 (same size) / (changed size) 12.30.955.911 I slot release: id 3 | task 13896 | stop processing: n_tokens = 842, truncated = 0 12.30.955.919 I slot print_timing: id 0 | task 13901 | prompt processing, n_tokens = 313, progress = 0.38, t = 3.50 s / 89.43 tokens per second 12.30.958.689 I slot print_timing: id 1 | task 13902 | prompt processing, n_tokens = 686, progress = 0.57, t = 3.50 s / 196.01 tokens per second 12.32.310.037 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 349759702719 12.32.449.144 I slot launch_slot_: id 2 | task 13907 | processing task, is_child = 0 12.32.449.234 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.553 MiB) 12.32.483.712 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 842, t_last = 349759702906 12.32.483.859 I slot launch_slot_: id 3 | task 13908 | processing task, is_child = 0 12.32.483.868 I slot print_timing: id 0 | task 13901 | prompt processing, n_tokens = 678, progress = 0.82, t = 4.85 s / 139.66 tokens per second 12.32.490.399 I slot print_timing: id 1 | task 13902 | prompt processing, n_tokens = 1028, progress = 0.86, t = 4.85 s / 211.77 tokens per second 12.33.867.859 I slot print_timing: id 0 | task 13901 | prompt processing, n_tokens = 825, progress = 1.00, t = 6.41 s / 128.66 tokens per second 12.33.940.886 I slot print_timing: id 1 | task 13902 | prompt processing, n_tokens = 1198, progress = 1.00, t = 6.41 s / 186.83 tokens per second 12.35.917.361 I slot print_timing: id 0 | task 13901 | prompt eval time = 7367.52 ms / 829 tokens ( 8.89 ms per token, 112.52 tokens per second) 12.35.917.366 I slot print_timing: id 0 | task 13901 | eval time = 1094.30 ms / 2 tokens ( 1094.30 ms per token, 0.91 tokens per second) 12.35.917.367 I slot print_timing: id 0 | task 13901 | total time = 8461.82 ms / 831 tokens 12.35.917.367 I slot print_timing: id 0 | task 13901 | graphs reused = 12475 12.35.917.368 I slot print_timing: id 0 | task 13901 | graph reallocs = 0 / 0 (same size) / (changed size) 12.35.917.438 I slot release: id 0 | task 13901 | stop processing: n_tokens = 830, truncated = 0 12.35.917.548 I slot print_timing: id 1 | task 13902 | prompt eval time = 7367.52 ms / 1202 tokens ( 6.13 ms per token, 163.15 tokens per second) 12.35.917.551 I slot print_timing: id 1 | task 13902 | eval time = 1094.35 ms / 2 tokens ( 1094.35 ms per token, 0.91 tokens per second) 12.35.917.551 I slot print_timing: id 1 | task 13902 | total time = 8461.86 ms / 1204 tokens 12.35.917.552 I slot print_timing: id 1 | task 13902 | graphs reused = 12475 12.35.917.552 I slot print_timing: id 1 | task 13902 | graph reallocs = 0 / 0 (same size) / (changed size) 12.35.917.607 I slot release: id 1 | task 13902 | stop processing: n_tokens = 1203, truncated = 0 12.35.917.616 I slot print_timing: id 2 | task 13907 | prompt processing, n_tokens = 692, progress = 0.57, t = 3.42 s / 202.33 tokens per second 12.35.919.742 I slot print_timing: id 3 | task 13908 | prompt processing, n_tokens = 609, progress = 0.54, t = 3.42 s / 178.06 tokens per second 12.37.206.505 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 830, t_last = 349764664433 12.37.527.504 I slot launch_slot_: id 0 | task 13913 | processing task, is_child = 0 12.37.527.612 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 346.047 MiB) 12.37.569.655 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.875 12.37.569.751 I slot launch_slot_: id 1 | task 13914 | processing task, is_child = 0 12.37.571.080 I slot print_timing: id 2 | task 13907 | prompt processing, n_tokens = 1028, progress = 0.85, t = 4.71 s / 218.28 tokens per second 12.37.572.236 I slot print_timing: id 3 | task 13908 | prompt processing, n_tokens = 1028, progress = 0.91, t = 4.71 s / 218.29 tokens per second 12.38.960.793 I slot print_timing: id 2 | task 13907 | prompt processing, n_tokens = 1204, progress = 1.00, t = 6.14 s / 196.04 tokens per second 12.38.966.924 I slot print_timing: id 3 | task 13908 | prompt processing, n_tokens = 1121, progress = 1.00, t = 6.14 s / 182.53 tokens per second 12.40.147.407 I slot print_timing: id 1 | task 13914 | prompt eval time = 1784.55 ms / 109 tokens ( 16.37 ms per token, 61.08 tokens per second) 12.40.147.409 I slot print_timing: id 1 | task 13914 | eval time = 792.94 ms / 2 tokens ( 792.94 ms per token, 1.26 tokens per second) 12.40.147.409 I slot print_timing: id 1 | task 13914 | total time = 2577.50 ms / 111 tokens 12.40.147.410 I slot print_timing: id 1 | task 13914 | graphs reused = 12475 12.40.147.410 I slot print_timing: id 1 | task 13914 | graph reallocs = 0 / 0 (same size) / (changed size) 12.40.147.478 I slot release: id 1 | task 13914 | stop processing: n_tokens = 1163, truncated = 0 12.40.147.642 I slot print_timing: id 2 | task 13907 | prompt eval time = 6857.59 ms / 1208 tokens ( 5.68 ms per token, 176.16 tokens per second) 12.40.147.651 I slot print_timing: id 2 | task 13907 | eval time = 793.03 ms / 2 tokens ( 793.03 ms per token, 1.26 tokens per second) 12.40.147.651 I slot print_timing: id 2 | task 13907 | total time = 7650.62 ms / 1210 tokens 12.40.147.655 I slot print_timing: id 2 | task 13907 | graphs reused = 12475 12.40.147.656 I slot print_timing: id 2 | task 13907 | graph reallocs = 0 / 0 (same size) / (changed size) 12.40.147.692 I slot release: id 2 | task 13907 | stop processing: n_tokens = 1209, truncated = 0 12.40.147.855 I slot print_timing: id 3 | task 13908 | prompt eval time = 6857.62 ms / 1125 tokens ( 6.10 ms per token, 164.05 tokens per second) 12.40.147.860 I slot print_timing: id 3 | task 13908 | eval time = 793.11 ms / 2 tokens ( 793.11 ms per token, 1.26 tokens per second) 12.40.147.861 I slot print_timing: id 3 | task 13908 | total time = 7650.72 ms / 1127 tokens 12.40.147.861 I slot print_timing: id 3 | task 13908 | graphs reused = 12475 12.40.147.862 I slot print_timing: id 3 | task 13908 | graph reallocs = 0 / 0 (same size) / (changed size) 12.40.147.890 I slot release: id 3 | task 13908 | stop processing: n_tokens = 1126, truncated = 0 12.40.158.537 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1163, t_last = 349768894473 12.40.495.561 I slot launch_slot_: id 1 | task 13919 | processing task, is_child = 0 12.40.495.659 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 345.527 MiB) 12.40.701.164 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.102 MiB) 12.40.827.042 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1209, t_last = 349768894687 12.40.827.224 I slot launch_slot_: id 2 | task 13920 | processing task, is_child = 0 12.40.827.298 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1126, t_last = 349768894885 12.40.827.408 I slot launch_slot_: id 3 | task 13921 | processing task, is_child = 0 12.42.552.886 I slot print_timing: id 0 | task 13913 | prompt eval time = 4150.34 ms / 690 tokens ( 6.01 ms per token, 166.25 tokens per second) 12.42.552.888 I slot print_timing: id 0 | task 13913 | eval time = 832.76 ms / 2 tokens ( 832.76 ms per token, 1.20 tokens per second) 12.42.552.889 I slot print_timing: id 0 | task 13913 | total time = 4983.11 ms / 692 tokens 12.42.552.889 I slot print_timing: id 0 | task 13913 | graphs reused = 12475 12.42.552.890 I slot print_timing: id 0 | task 13913 | graph reallocs = 0 / 0 (same size) / (changed size) 12.42.552.966 I slot release: id 0 | task 13913 | stop processing: n_tokens = 691, truncated = 0 12.43.539.893 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 691, t_last = 349771299961 12.44.245.816 I slot launch_slot_: id 0 | task 13925 | processing task, is_child = 0 12.45.896.908 I slot print_timing: id 1 | task 13919 | prompt processing, n_tokens = 704, progress = 0.99, t = 4.47 s / 157.45 tokens per second 12.45.898.645 I slot print_timing: id 2 | task 13920 | prompt processing, n_tokens = 661, progress = 0.83, t = 4.47 s / 147.84 tokens per second 12.45.901.515 I slot print_timing: id 3 | task 13921 | prompt processing, n_tokens = 765, progress = 0.99, t = 4.47 s / 171.10 tokens per second 12.46.660.037 I slot print_timing: id 2 | task 13920 | prompt processing, n_tokens = 797, progress = 1.00, t = 5.81 s / 137.25 tokens per second 12.47.457.545 I slot print_timing: id 1 | task 13919 | prompt eval time = 5807.23 ms / 708 tokens ( 8.20 ms per token, 121.92 tokens per second) 12.47.457.550 I slot print_timing: id 1 | task 13919 | eval time = 805.03 ms / 2 tokens ( 805.03 ms per token, 1.24 tokens per second) 12.47.457.551 I slot print_timing: id 1 | task 13919 | total time = 6612.26 ms / 710 tokens 12.47.457.551 I slot print_timing: id 1 | task 13919 | graphs reused = 12475 12.47.457.552 I slot print_timing: id 1 | task 13919 | graph reallocs = 0 / 0 (same size) / (changed size) 12.47.457.600 I slot release: id 1 | task 13919 | stop processing: n_tokens = 709, truncated = 0 12.47.457.833 I slot print_timing: id 3 | task 13921 | prompt eval time = 5807.06 ms / 769 tokens ( 7.55 ms per token, 132.42 tokens per second) 12.47.457.835 I slot print_timing: id 3 | task 13921 | eval time = 805.18 ms / 2 tokens ( 805.18 ms per token, 1.24 tokens per second) 12.47.457.836 I slot print_timing: id 3 | task 13921 | total time = 6612.24 ms / 771 tokens 12.47.457.836 I slot print_timing: id 3 | task 13921 | graphs reused = 12475 12.47.457.837 I slot print_timing: id 3 | task 13921 | graph reallocs = 0 / 0 (same size) / (changed size) 12.47.457.930 I slot release: id 3 | task 13921 | stop processing: n_tokens = 770, truncated = 0 12.47.457.947 I slot print_timing: id 0 | task 13925 | prompt processing, n_tokens = 577, progress = 0.82, t = 3.21 s / 179.66 tokens per second 12.47.882.210 I slot print_timing: id 2 | task 13920 | prompt eval time = 6612.27 ms / 801 tokens ( 8.26 ms per token, 121.14 tokens per second) 12.47.882.214 I slot print_timing: id 2 | task 13920 | eval time = 424.50 ms / 2 tokens ( 424.50 ms per token, 2.36 tokens per second) 12.47.882.214 I slot print_timing: id 2 | task 13920 | total time = 7036.77 ms / 803 tokens 12.47.882.214 I slot print_timing: id 2 | task 13920 | graphs reused = 12475 12.47.882.219 I slot print_timing: id 2 | task 13920 | graph reallocs = 0 / 0 (same size) / (changed size) 12.47.882.272 I slot release: id 2 | task 13920 | stop processing: n_tokens = 802, truncated = 0 12.47.882.280 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 709, t_last = 349776204595 12.47.882.362 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.274 MiB) 12.47.939.772 I slot launch_slot_: id 1 | task 13930 | processing task, is_child = 0 12.48.006.945 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.874 MiB) 12.48.201.292 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 770, t_last = 349776204926 12.48.201.538 I slot launch_slot_: id 3 | task 13931 | processing task, is_child = 0 12.48.201.608 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 802, t_last = 349776629267 12.48.201.714 I slot launch_slot_: id 2 | task 13932 | processing task, is_child = 0 12.48.201.724 I slot print_timing: id 0 | task 13925 | prompt processing, n_tokens = 698, progress = 0.99, t = 3.64 s / 191.96 tokens per second 12.49.583.638 I slot print_timing: id 0 | task 13925 | prompt eval time = 4740.89 ms / 702 tokens ( 6.75 ms per token, 148.07 tokens per second) 12.49.583.644 I slot print_timing: id 0 | task 13925 | eval time = 596.91 ms / 2 tokens ( 596.91 ms per token, 1.68 tokens per second) 12.49.583.644 I slot print_timing: id 0 | task 13925 | total time = 5337.80 ms / 704 tokens 12.49.583.645 I slot print_timing: id 0 | task 13925 | graphs reused = 12475 12.49.583.645 I slot print_timing: id 0 | task 13925 | graph reallocs = 0 / 0 (same size) / (changed size) 12.49.583.784 I slot release: id 0 | task 13925 | stop processing: n_tokens = 703, truncated = 0 12.51.632.425 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.848 (> 0.100 thold), f_keep = 0.856 12.51.632.564 I slot launch_slot_: id 0 | task 13936 | processing task, is_child = 0 12.51.672.044 I slot print_timing: id 1 | task 13930 | prompt processing, n_tokens = 577, progress = 0.84, t = 3.42 s / 168.54 tokens per second 12.51.673.387 I slot print_timing: id 2 | task 13932 | prompt processing, n_tokens = 577, progress = 0.85, t = 3.42 s / 168.54 tokens per second 12.51.674.716 I slot print_timing: id 3 | task 13931 | prompt processing, n_tokens = 577, progress = 0.77, t = 3.42 s / 168.55 tokens per second 12.52.791.753 I slot print_timing: id 1 | task 13930 | prompt processing, n_tokens = 683, progress = 0.99, t = 4.29 s / 159.09 tokens per second 12.52.869.737 I slot print_timing: id 2 | task 13932 | prompt processing, n_tokens = 678, progress = 0.99, t = 4.29 s / 157.93 tokens per second 12.52.871.134 I slot print_timing: id 3 | task 13931 | prompt processing, n_tokens = 746, progress = 0.99, t = 4.29 s / 173.77 tokens per second 12.53.049.140 I slot print_timing: id 0 | task 13936 | prompt eval time = 1374.20 ms / 108 tokens ( 12.72 ms per token, 78.59 tokens per second) 12.53.049.142 I slot print_timing: id 0 | task 13936 | eval time = 42.35 ms / 2 tokens ( 42.35 ms per token, 23.61 tokens per second) 12.53.049.143 I slot print_timing: id 0 | task 13936 | total time = 1416.55 ms / 110 tokens 12.53.049.143 I slot print_timing: id 0 | task 13936 | graphs reused = 12475 12.53.049.144 I slot print_timing: id 0 | task 13936 | graph reallocs = 0 / 0 (same size) / (changed size) 12.53.049.197 I slot release: id 0 | task 13936 | stop processing: n_tokens = 711, truncated = 0 12.53.049.284 I slot print_timing: id 1 | task 13930 | prompt eval time = 4798.11 ms / 687 tokens ( 6.98 ms per token, 143.18 tokens per second) 12.53.049.290 I slot print_timing: id 1 | task 13930 | eval time = 42.29 ms / 2 tokens ( 42.29 ms per token, 23.64 tokens per second) 12.53.049.290 I slot print_timing: id 1 | task 13930 | total time = 4840.40 ms / 689 tokens 12.53.049.291 I slot print_timing: id 1 | task 13930 | graphs reused = 12475 12.53.049.291 I slot print_timing: id 1 | task 13930 | graph reallocs = 0 / 0 (same size) / (changed size) 12.53.049.326 I slot release: id 1 | task 13930 | stop processing: n_tokens = 688, truncated = 0 12.53.049.407 I slot print_timing: id 2 | task 13932 | prompt eval time = 4798.22 ms / 682 tokens ( 7.04 ms per token, 142.14 tokens per second) 12.53.049.409 I slot print_timing: id 2 | task 13932 | eval time = 42.21 ms / 2 tokens ( 42.21 ms per token, 23.69 tokens per second) 12.53.049.409 I slot print_timing: id 2 | task 13932 | total time = 4840.43 ms / 684 tokens 12.53.049.410 I slot print_timing: id 2 | task 13932 | graphs reused = 12475 12.53.049.410 I slot print_timing: id 2 | task 13932 | graph reallocs = 0 / 0 (same size) / (changed size) 12.53.049.431 I slot release: id 2 | task 13932 | stop processing: n_tokens = 683, truncated = 0 12.53.049.517 I slot print_timing: id 3 | task 13931 | prompt eval time = 4798.34 ms / 750 tokens ( 6.40 ms per token, 156.30 tokens per second) 12.53.049.520 I slot print_timing: id 3 | task 13931 | eval time = 42.10 ms / 2 tokens ( 42.10 ms per token, 23.75 tokens per second) 12.53.049.520 I slot print_timing: id 3 | task 13931 | total time = 4840.44 ms / 752 tokens 12.53.049.520 I slot print_timing: id 3 | task 13931 | graphs reused = 12475 12.53.049.521 I slot print_timing: id 3 | task 13931 | graph reallocs = 0 / 0 (same size) / (changed size) 12.53.049.543 I slot release: id 3 | task 13931 | stop processing: n_tokens = 751, truncated = 0 12.53.058.927 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 349781796192 12.53.074.898 I slot launch_slot_: id 0 | task 13940 | processing task, is_child = 0 12.53.074.963 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.528 MiB) 12.53.122.002 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 286.940 MiB) 12.53.149.780 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 688, t_last = 349781796321 12.53.149.939 I slot launch_slot_: id 1 | task 13941 | processing task, is_child = 0 12.53.150.070 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 349781796426 12.53.150.168 I slot launch_slot_: id 2 | task 13942 | processing task, is_child = 0 12.53.150.228 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 349781796538 12.53.150.329 I slot launch_slot_: id 3 | task 13943 | processing task, is_child = 0 12.58.277.903 I slot print_timing: id 0 | task 13940 | prompt processing, n_tokens = 719, progress = 0.88, t = 5.13 s / 140.22 tokens per second 12.58.358.939 I slot print_timing: id 1 | task 13941 | prompt processing, n_tokens = 719, progress = 0.86, t = 5.13 s / 140.23 tokens per second 12.58.362.749 I slot print_timing: id 2 | task 13942 | prompt processing, n_tokens = 719, progress = 0.88, t = 5.13 s / 140.23 tokens per second 12.58.366.430 I slot print_timing: id 3 | task 13943 | prompt processing, n_tokens = 719, progress = 0.87, t = 5.13 s / 140.23 tokens per second 12.59.272.494 I slot print_timing: id 0 | task 13940 | prompt processing, n_tokens = 810, progress = 1.00, t = 6.12 s / 132.31 tokens per second 12.59.353.853 I slot print_timing: id 1 | task 13941 | prompt processing, n_tokens = 832, progress = 1.00, t = 6.12 s / 135.90 tokens per second 12.59.357.753 I slot print_timing: id 2 | task 13942 | prompt processing, n_tokens = 814, progress = 1.00, t = 6.12 s / 132.96 tokens per second 12.59.361.581 I slot print_timing: id 3 | task 13943 | prompt processing, n_tokens = 827, progress = 1.00, t = 6.12 s / 135.09 tokens per second 12.59.512.134 I slot print_timing: id 0 | task 13940 | prompt eval time = 6319.35 ms / 814 tokens ( 7.76 ms per token, 128.81 tokens per second) 12.59.512.139 I slot print_timing: id 0 | task 13940 | eval time = 42.45 ms / 2 tokens ( 42.45 ms per token, 23.56 tokens per second) 12.59.512.140 I slot print_timing: id 0 | task 13940 | total time = 6361.79 ms / 816 tokens 12.59.512.140 I slot print_timing: id 0 | task 13940 | graphs reused = 12476 12.59.512.141 I slot print_timing: id 0 | task 13940 | graph reallocs = 0 / 0 (same size) / (changed size) 12.59.512.207 I slot release: id 0 | task 13940 | stop processing: n_tokens = 815, truncated = 0 12.59.512.299 I slot print_timing: id 1 | task 13941 | prompt eval time = 6319.43 ms / 836 tokens ( 7.56 ms per token, 132.29 tokens per second) 12.59.512.302 I slot print_timing: id 1 | task 13941 | eval time = 42.42 ms / 2 tokens ( 42.42 ms per token, 23.57 tokens per second) 12.59.512.302 I slot print_timing: id 1 | task 13941 | total time = 6361.85 ms / 838 tokens 12.59.512.303 I slot print_timing: id 1 | task 13941 | graphs reused = 12476 12.59.512.303 I slot print_timing: id 1 | task 13941 | graph reallocs = 0 / 0 (same size) / (changed size) 12.59.512.328 I slot release: id 1 | task 13941 | stop processing: n_tokens = 837, truncated = 0 12.59.512.436 I slot print_timing: id 2 | task 13942 | prompt eval time = 6319.57 ms / 818 tokens ( 7.73 ms per token, 129.44 tokens per second) 12.59.512.439 I slot print_timing: id 2 | task 13942 | eval time = 42.31 ms / 2 tokens ( 42.31 ms per token, 23.63 tokens per second) 12.59.512.440 I slot print_timing: id 2 | task 13942 | total time = 6361.89 ms / 820 tokens 12.59.512.442 I slot print_timing: id 2 | task 13942 | graphs reused = 12476 12.59.512.442 I slot print_timing: id 2 | task 13942 | graph reallocs = 0 / 0 (same size) / (changed size) 12.59.512.467 I slot release: id 2 | task 13942 | stop processing: n_tokens = 819, truncated = 0 12.59.512.561 I slot print_timing: id 3 | task 13943 | prompt eval time = 6319.76 ms / 831 tokens ( 7.61 ms per token, 131.49 tokens per second) 12.59.512.563 I slot print_timing: id 3 | task 13943 | eval time = 42.17 ms / 2 tokens ( 42.17 ms per token, 23.72 tokens per second) 12.59.512.563 I slot print_timing: id 3 | task 13943 | total time = 6361.93 ms / 833 tokens 12.59.512.563 I slot print_timing: id 3 | task 13943 | graphs reused = 12476 12.59.512.564 I slot print_timing: id 3 | task 13943 | graph reallocs = 0 / 0 (same size) / (changed size) 12.59.512.586 I slot release: id 3 | task 13943 | stop processing: n_tokens = 832, truncated = 0 12.59.521.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 815, t_last = 349788259202 12.59.536.500 I slot launch_slot_: id 0 | task 13952 | processing task, is_child = 0 12.59.536.568 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 343.476 MiB) 12.59.591.029 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 143.082 MiB) 12.59.637.177 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 837, t_last = 349788259323 12.59.637.404 I slot launch_slot_: id 1 | task 13951 | processing task, is_child = 0 12.59.637.561 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.894 (> 0.100 thold), f_keep = 0.908 12.59.637.603 I slot launch_slot_: id 2 | task 13953 | processing task, is_child = 0 12.59.637.666 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 832, t_last = 349788259581 12.59.637.776 I slot launch_slot_: id 3 | task 13954 | processing task, is_child = 0 13.03.379.775 I slot print_timing: id 2 | task 13953 | prompt eval time = 2023.28 ms / 88 tokens ( 22.99 ms per token, 43.49 tokens per second) 13.03.379.778 I slot print_timing: id 2 | task 13953 | eval time = 1718.42 ms / 2 tokens ( 1718.42 ms per token, 0.58 tokens per second) 13.03.379.779 I slot print_timing: id 2 | task 13953 | total time = 3741.70 ms / 90 tokens 13.03.379.779 I slot print_timing: id 2 | task 13953 | graphs reused = 12476 13.03.379.779 I slot print_timing: id 2 | task 13953 | graph reallocs = 0 / 0 (same size) / (changed size) 13.03.379.831 I slot release: id 2 | task 13953 | stop processing: n_tokens = 833, truncated = 0 13.03.379.843 I slot print_timing: id 0 | task 13952 | prompt processing, n_tokens = 599, progress = 0.85, t = 3.74 s / 160.09 tokens per second 13.03.384.942 I slot print_timing: id 1 | task 13951 | prompt processing, n_tokens = 599, progress = 0.85, t = 3.74 s / 160.09 tokens per second 13.03.388.029 I slot print_timing: id 3 | task 13954 | prompt processing, n_tokens = 355, progress = 0.41, t = 3.74 s / 94.92 tokens per second 13.03.924.254 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 833, t_last = 349792126826 13.03.924.375 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.106 MiB) 13.04.624.120 I slot launch_slot_: id 2 | task 13959 | processing task, is_child = 0 13.04.624.149 I slot print_timing: id 0 | task 13952 | prompt processing, n_tokens = 700, progress = 0.99, t = 4.29 s / 163.30 tokens per second 13.04.627.015 I slot print_timing: id 1 | task 13951 | prompt processing, n_tokens = 702, progress = 0.99, t = 4.29 s / 163.78 tokens per second 13.04.629.795 I slot print_timing: id 3 | task 13954 | prompt processing, n_tokens = 733, progress = 0.84, t = 4.28 s / 171.07 tokens per second 13.05.357.135 I slot print_timing: id 3 | task 13954 | prompt processing, n_tokens = 867, progress = 1.00, t = 5.71 s / 151.72 tokens per second 13.05.896.143 I slot print_timing: id 0 | task 13952 | prompt eval time = 5716.35 ms / 704 tokens ( 8.12 ms per token, 123.16 tokens per second) 13.05.896.146 I slot print_timing: id 0 | task 13952 | eval time = 542.00 ms / 2 tokens ( 542.00 ms per token, 1.85 tokens per second) 13.05.896.147 I slot print_timing: id 0 | task 13952 | total time = 6258.36 ms / 706 tokens 13.05.896.147 I slot print_timing: id 0 | task 13952 | graphs reused = 12476 13.05.896.148 I slot print_timing: id 0 | task 13952 | graph reallocs = 0 / 0 (same size) / (changed size) 13.05.896.228 I slot release: id 0 | task 13952 | stop processing: n_tokens = 705, truncated = 0 13.05.896.386 I slot print_timing: id 1 | task 13951 | prompt eval time = 5716.35 ms / 706 tokens ( 8.10 ms per token, 123.51 tokens per second) 13.05.896.389 I slot print_timing: id 1 | task 13951 | eval time = 542.11 ms / 2 tokens ( 542.11 ms per token, 1.84 tokens per second) 13.05.896.390 I slot print_timing: id 1 | task 13951 | total time = 6258.46 ms / 708 tokens 13.05.896.390 I slot print_timing: id 1 | task 13951 | graphs reused = 12476 13.05.896.390 I slot print_timing: id 1 | task 13951 | graph reallocs = 0 / 0 (same size) / (changed size) 13.05.896.420 I slot release: id 1 | task 13951 | stop processing: n_tokens = 707, truncated = 0 13.06.074.597 I slot print_timing: id 3 | task 13954 | prompt eval time = 6257.25 ms / 871 tokens ( 7.18 ms per token, 139.20 tokens per second) 13.06.074.599 I slot print_timing: id 3 | task 13954 | eval time = 177.89 ms / 2 tokens ( 177.89 ms per token, 5.62 tokens per second) 13.06.074.600 I slot print_timing: id 3 | task 13954 | total time = 6435.13 ms / 873 tokens 13.06.074.600 I slot print_timing: id 3 | task 13954 | graphs reused = 12476 13.06.074.600 I slot print_timing: id 3 | task 13954 | graph reallocs = 0 / 0 (same size) / (changed size) 13.06.074.684 I slot release: id 3 | task 13954 | stop processing: n_tokens = 872, truncated = 0 13.06.074.690 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.869 13.06.074.744 I slot launch_slot_: id 3 | task 13963 | processing task, is_child = 0 13.06.074.818 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.157 MiB) 13.06.100.684 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 143.574 MiB) 13.06.139.125 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 705, t_last = 349794643224 13.06.139.320 I slot launch_slot_: id 0 | task 13964 | processing task, is_child = 0 13.06.139.388 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 349794643415 13.06.139.495 I slot launch_slot_: id 1 | task 13965 | processing task, is_child = 0 13.08.678.917 I slot print_timing: id 2 | task 13959 | prompt processing, n_tokens = 844, progress = 1.00, t = 4.05 s / 208.44 tokens per second 13.08.982.458 I slot print_timing: id 3 | task 13963 | prompt eval time = 2521.68 ms / 98 tokens ( 25.73 ms per token, 38.86 tokens per second) 13.08.982.463 I slot print_timing: id 3 | task 13963 | eval time = 303.56 ms / 2 tokens ( 303.56 ms per token, 3.29 tokens per second) 13.08.982.464 I slot print_timing: id 3 | task 13963 | total time = 2825.24 ms / 100 tokens 13.08.982.464 I slot print_timing: id 3 | task 13963 | graphs reused = 12476 13.08.982.464 I slot print_timing: id 3 | task 13963 | graph reallocs = 0 / 0 (same size) / (changed size) 13.08.982.566 I slot release: id 3 | task 13963 | stop processing: n_tokens = 857, truncated = 0 13.10.545.306 I slot print_timing: id 2 | task 13959 | prompt eval time = 4352.71 ms / 848 tokens ( 5.13 ms per token, 194.82 tokens per second) 13.10.545.308 I slot print_timing: id 2 | task 13959 | eval time = 1562.93 ms / 2 tokens ( 1562.93 ms per token, 0.64 tokens per second) 13.10.545.309 I slot print_timing: id 2 | task 13959 | total time = 5915.64 ms / 850 tokens 13.10.545.309 I slot print_timing: id 2 | task 13959 | graphs reused = 12476 13.10.545.310 I slot print_timing: id 2 | task 13959 | graph reallocs = 0 / 0 (same size) / (changed size) 13.10.545.363 I slot release: id 2 | task 13959 | stop processing: n_tokens = 849, truncated = 0 13.10.545.372 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 857, t_last = 349797729562 13.10.545.459 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 141.701 MiB) 13.10.574.432 I slot launch_slot_: id 3 | task 13970 | processing task, is_child = 0 13.10.574.503 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.487 MiB) 13.10.574.523 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.009 MiB) 13.10.622.704 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 849, t_last = 349799292359 13.10.622.871 I slot launch_slot_: id 2 | task 13971 | processing task, is_child = 0 13.10.622.879 I slot print_timing: id 0 | task 13964 | prompt processing, n_tokens = 685, progress = 0.83, t = 4.41 s / 155.48 tokens per second 13.10.637.367 I slot print_timing: id 1 | task 13965 | prompt processing, n_tokens = 685, progress = 0.87, t = 4.41 s / 155.49 tokens per second 13.11.554.814 I slot print_timing: id 0 | task 13964 | prompt processing, n_tokens = 818, progress = 1.00, t = 5.42 s / 151.05 tokens per second 13.11.740.832 I slot print_timing: id 1 | task 13965 | prompt processing, n_tokens = 786, progress = 0.99, t = 5.42 s / 145.15 tokens per second 13.12.576.976 I slot print_timing: id 0 | task 13964 | prompt eval time = 6266.58 ms / 822 tokens ( 7.62 ms per token, 131.17 tokens per second) 13.12.576.979 I slot print_timing: id 0 | task 13964 | eval time = 170.89 ms / 2 tokens ( 170.89 ms per token, 5.85 tokens per second) 13.12.576.979 I slot print_timing: id 0 | task 13964 | total time = 6437.47 ms / 824 tokens 13.12.576.980 I slot print_timing: id 0 | task 13964 | graphs reused = 12476 13.12.576.980 I slot print_timing: id 0 | task 13964 | graph reallocs = 0 / 0 (same size) / (changed size) 13.12.577.186 I slot release: id 0 | task 13964 | stop processing: n_tokens = 823, truncated = 0 13.12.577.279 I slot print_timing: id 1 | task 13965 | prompt eval time = 6266.59 ms / 790 tokens ( 7.93 ms per token, 126.07 tokens per second) 13.12.577.285 I slot print_timing: id 1 | task 13965 | eval time = 171.06 ms / 2 tokens ( 171.06 ms per token, 5.85 tokens per second) 13.12.577.286 I slot print_timing: id 1 | task 13965 | total time = 6437.65 ms / 792 tokens 13.12.577.286 I slot print_timing: id 1 | task 13965 | graphs reused = 12476 13.12.577.287 I slot print_timing: id 1 | task 13965 | graph reallocs = 0 / 0 (same size) / (changed size) 13.12.577.319 I slot release: id 1 | task 13965 | stop processing: n_tokens = 791, truncated = 0 13.13.994.550 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.863 13.13.994.655 I slot launch_slot_: id 0 | task 13976 | processing task, is_child = 0 13.13.994.738 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 177.788 MiB) 13.14.042.552 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 791, t_last = 349801324315 13.14.042.728 I slot launch_slot_: id 1 | task 13977 | processing task, is_child = 0 13.14.043.999 I slot print_timing: id 2 | task 13971 | prompt processing, n_tokens = 685, progress = 0.86, t = 3.35 s / 204.47 tokens per second 13.14.045.172 I slot print_timing: id 3 | task 13970 | prompt processing, n_tokens = 685, progress = 0.86, t = 3.35 s / 204.47 tokens per second 13.15.328.881 I slot print_timing: id 2 | task 13971 | prompt processing, n_tokens = 791, progress = 0.99, t = 4.65 s / 170.17 tokens per second 13.15.331.601 I slot print_timing: id 3 | task 13970 | prompt processing, n_tokens = 795, progress = 0.99, t = 4.65 s / 171.04 tokens per second 13.16.475.077 I slot print_timing: id 0 | task 13976 | prompt eval time = 1847.89 ms / 73 tokens ( 25.31 ms per token, 39.50 tokens per second) 13.16.475.082 I slot print_timing: id 0 | task 13976 | eval time = 584.44 ms / 2 tokens ( 584.44 ms per token, 1.71 tokens per second) 13.16.475.082 I slot print_timing: id 0 | task 13976 | total time = 2432.34 ms / 75 tokens 13.16.475.083 I slot print_timing: id 0 | task 13976 | graphs reused = 12476 13.16.475.083 I slot print_timing: id 0 | task 13976 | graph reallocs = 0 / 0 (same size) / (changed size) 13.16.475.161 I slot release: id 0 | task 13976 | stop processing: n_tokens = 784, truncated = 0 13.16.475.253 I slot print_timing: id 2 | task 13971 | prompt eval time = 5246.42 ms / 795 tokens ( 6.60 ms per token, 151.53 tokens per second) 13.16.475.255 I slot print_timing: id 2 | task 13971 | eval time = 584.48 ms / 2 tokens ( 584.48 ms per token, 1.71 tokens per second) 13.16.475.256 I slot print_timing: id 2 | task 13971 | total time = 5830.90 ms / 797 tokens 13.16.475.256 I slot print_timing: id 2 | task 13971 | graphs reused = 12476 13.16.475.257 I slot print_timing: id 2 | task 13971 | graph reallocs = 0 / 0 (same size) / (changed size) 13.16.475.305 I slot release: id 2 | task 13971 | stop processing: n_tokens = 796, truncated = 0 13.16.475.418 I slot print_timing: id 3 | task 13970 | prompt eval time = 5246.71 ms / 799 tokens ( 6.57 ms per token, 152.29 tokens per second) 13.16.475.420 I slot print_timing: id 3 | task 13970 | eval time = 584.24 ms / 2 tokens ( 584.24 ms per token, 1.71 tokens per second) 13.16.475.420 I slot print_timing: id 3 | task 13970 | total time = 5830.95 ms / 801 tokens 13.16.475.421 I slot print_timing: id 3 | task 13970 | graphs reused = 12476 13.16.475.421 I slot print_timing: id 3 | task 13970 | graph reallocs = 0 / 0 (same size) / (changed size) 13.16.475.448 I slot release: id 3 | task 13970 | stop processing: n_tokens = 800, truncated = 0 13.17.191.812 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 784, t_last = 349805222156 13.17.191.903 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 151.984 MiB) 13.17.638.694 I slot launch_slot_: id 0 | task 13983 | processing task, is_child = 0 13.17.638.768 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 152.942 MiB) 13.17.695.366 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.487 MiB) 13.17.726.439 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 796, t_last = 349805222300 13.17.726.628 I slot launch_slot_: id 2 | task 13984 | processing task, is_child = 0 13.17.726.693 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 349805222443 13.17.726.803 I slot launch_slot_: id 3 | task 13985 | processing task, is_child = 0 13.17.726.943 I slot print_timing: id 1 | task 13977 | prompt processing, n_tokens = 1088, progress = 1.00, t = 3.15 s / 345.62 tokens per second 13.21.281.311 I slot print_timing: id 1 | task 13977 | prompt eval time = 5360.68 ms / 1092 tokens ( 4.91 ms per token, 203.71 tokens per second) 13.21.281.314 I slot print_timing: id 1 | task 13977 | eval time = 1876.75 ms / 2 tokens ( 1876.75 ms per token, 0.53 tokens per second) 13.21.281.314 I slot print_timing: id 1 | task 13977 | total time = 7237.42 ms / 1094 tokens 13.21.281.314 I slot print_timing: id 1 | task 13977 | graphs reused = 12476 13.21.281.315 I slot print_timing: id 1 | task 13977 | graph reallocs = 0 / 0 (same size) / (changed size) 13.21.281.418 I slot release: id 1 | task 13977 | stop processing: n_tokens = 1093, truncated = 0 13.21.281.434 I slot print_timing: id 0 | task 13983 | prompt processing, n_tokens = 358, progress = 0.31, t = 3.55 s / 100.72 tokens per second 13.21.281.446 I slot print_timing: id 2 | task 13984 | prompt processing, n_tokens = 358, progress = 0.33, t = 3.55 s / 100.76 tokens per second 13.21.281.455 I slot print_timing: id 3 | task 13985 | prompt processing, n_tokens = 895, progress = 0.37, t = 3.55 s / 251.91 tokens per second 13.23.586.917 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1093, t_last = 349810028414 13.23.587.019 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.878 MiB) 13.24.206.528 I slot launch_slot_: id 1 | task 13989 | processing task, is_child = 0 13.24.206.551 I slot print_timing: id 0 | task 13983 | prompt processing, n_tokens = 640, progress = 0.55, t = 5.86 s / 109.21 tokens per second 13.24.207.979 I slot print_timing: id 2 | task 13984 | prompt processing, n_tokens = 584, progress = 0.53, t = 5.86 s / 99.68 tokens per second 13.24.209.175 I slot print_timing: id 3 | task 13985 | prompt processing, n_tokens = 1903, progress = 0.79, t = 5.86 s / 324.82 tokens per second 13.26.753.930 I slot print_timing: id 0 | task 13983 | prompt processing, n_tokens = 940, progress = 0.81, t = 9.03 s / 104.13 tokens per second 13.26.877.308 I slot print_timing: id 2 | task 13984 | prompt processing, n_tokens = 940, progress = 0.85, t = 9.03 s / 104.15 tokens per second 13.26.878.818 I slot print_timing: id 3 | task 13985 | prompt processing, n_tokens = 2137, progress = 0.88, t = 9.03 s / 236.77 tokens per second 13.29.233.224 I slot print_timing: id 0 | task 13983 | prompt processing, n_tokens = 1152, progress = 1.00, t = 11.51 s / 100.12 tokens per second 13.29.660.777 I slot print_timing: id 1 | task 13989 | prompt processing, n_tokens = 895, progress = 0.38, t = 5.03 s / 178.10 tokens per second 13.29.660.817 I slot print_timing: id 2 | task 13984 | prompt processing, n_tokens = 1096, progress = 1.00, t = 11.50 s / 95.26 tokens per second 13.29.664.281 I slot print_timing: id 3 | task 13985 | prompt processing, n_tokens = 2415, progress = 1.00, t = 11.50 s / 209.91 tokens per second 13.31.445.657 I slot print_timing: id 1 | task 13989 | prompt processing, n_tokens = 1817, progress = 0.78, t = 7.24 s / 251.07 tokens per second 13.32.195.882 I slot print_timing: id 0 | task 13983 | prompt eval time = 13718.28 ms / 1156 tokens ( 11.87 ms per token, 84.27 tokens per second) 13.32.195.888 I slot print_timing: id 0 | task 13983 | eval time = 750.78 ms / 2 tokens ( 750.78 ms per token, 1.33 tokens per second) 13.32.195.888 I slot print_timing: id 0 | task 13983 | total time = 14469.06 ms / 1158 tokens 13.32.195.889 I slot print_timing: id 0 | task 13983 | graphs reused = 12476 13.32.195.889 I slot print_timing: id 0 | task 13983 | graph reallocs = 0 / 0 (same size) / (changed size) 13.32.195.984 I slot release: id 0 | task 13983 | stop processing: n_tokens = 1157, truncated = 0 13.32.196.139 I slot print_timing: id 2 | task 13984 | prompt eval time = 13717.00 ms / 1100 tokens ( 12.47 ms per token, 80.19 tokens per second) 13.32.196.141 I slot print_timing: id 2 | task 13984 | eval time = 750.90 ms / 2 tokens ( 750.90 ms per token, 1.33 tokens per second) 13.32.196.142 I slot print_timing: id 2 | task 13984 | total time = 14467.90 ms / 1102 tokens 13.32.196.142 I slot print_timing: id 2 | task 13984 | graphs reused = 12476 13.32.196.143 I slot print_timing: id 2 | task 13984 | graph reallocs = 0 / 0 (same size) / (changed size) 13.32.196.177 I slot release: id 2 | task 13984 | stop processing: n_tokens = 1101, truncated = 0 13.32.196.383 I slot print_timing: id 3 | task 13985 | prompt eval time = 13717.29 ms / 2419 tokens ( 5.67 ms per token, 176.35 tokens per second) 13.32.196.386 I slot print_timing: id 3 | task 13985 | eval time = 750.74 ms / 2 tokens ( 750.74 ms per token, 1.33 tokens per second) 13.32.196.387 I slot print_timing: id 3 | task 13985 | total time = 14468.02 ms / 2421 tokens 13.32.196.387 I slot print_timing: id 3 | task 13985 | graphs reused = 12476 13.32.196.387 I slot print_timing: id 3 | task 13985 | graph reallocs = 0 / 0 (same size) / (changed size) 13.32.197.058 I slot release: id 3 | task 13985 | stop processing: n_tokens = 2420, truncated = 0 13.32.197.076 I slot print_timing: id 1 | task 13989 | prompt processing, n_tokens = 2137, progress = 0.92, t = 7.99 s / 267.53 tokens per second 13.32.212.526 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1157, t_last = 349820942981 13.32.212.617 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 169.229 MiB) 13.32.729.046 I slot launch_slot_: id 0 | task 13995 | processing task, is_child = 0 13.32.729.137 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 154.993 MiB) 13.32.769.111 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 191.837 MiB) 13.32.848.821 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.897 13.32.848.911 I slot launch_slot_: id 3 | task 13996 | processing task, is_child = 0 13.32.849.003 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1101, t_last = 349820943172 13.32.853.029 I slot launch_slot_: id 2 | task 13997 | processing task, is_child = 0 13.32.853.217 I slot print_timing: id 1 | task 13989 | prompt processing, n_tokens = 2329, progress = 1.00, t = 8.00 s / 290.95 tokens per second 13.35.655.473 I slot print_timing: id 1 | task 13989 | prompt eval time = 9913.63 ms / 2333 tokens ( 4.25 ms per token, 235.33 tokens per second) 13.35.655.476 I slot print_timing: id 1 | task 13989 | eval time = 1534.02 ms / 2 tokens ( 1534.02 ms per token, 0.65 tokens per second) 13.35.655.476 I slot print_timing: id 1 | task 13989 | total time = 11447.65 ms / 2335 tokens 13.35.655.477 I slot print_timing: id 1 | task 13989 | graphs reused = 12476 13.35.655.477 I slot print_timing: id 1 | task 13989 | graph reallocs = 0 / 0 (same size) / (changed size) 13.35.655.879 I slot release: id 1 | task 13989 | stop processing: n_tokens = 2334, truncated = 0 13.36.989.469 I slot print_timing: id 3 | task 13996 | prompt eval time = 2768.03 ms / 304 tokens ( 9.11 ms per token, 109.83 tokens per second) 13.36.989.472 I slot print_timing: id 3 | task 13996 | eval time = 1333.30 ms / 2 tokens ( 1333.30 ms per token, 0.75 tokens per second) 13.36.989.473 I slot print_timing: id 3 | task 13996 | total time = 4101.33 ms / 306 tokens 13.36.989.473 I slot print_timing: id 3 | task 13996 | graphs reused = 12476 13.36.989.473 I slot print_timing: id 3 | task 13996 | graph reallocs = 0 / 0 (same size) / (changed size) 13.36.989.613 I slot release: id 3 | task 13996 | stop processing: n_tokens = 2475, truncated = 0 13.36.989.622 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2334, t_last = 349824402875 13.37.017.149 I slot launch_slot_: id 1 | task 14001 | processing task, is_child = 0 13.37.017.296 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 156.525 MiB) 13.37.017.320 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 139.622 MiB) 13.37.058.435 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2475, t_last = 349825736609 13.37.058.642 I slot launch_slot_: id 3 | task 14002 | processing task, is_child = 0 13.37.058.655 I slot print_timing: id 0 | task 13995 | prompt processing, n_tokens = 1106, progress = 0.68, t = 4.14 s / 267.40 tokens per second 13.38.408.224 I slot print_timing: id 2 | task 13997 | prompt eval time = 4134.67 ms / 435 tokens ( 9.50 ms per token, 105.21 tokens per second) 13.38.408.226 I slot print_timing: id 2 | task 13997 | eval time = 1418.89 ms / 2 tokens ( 1418.89 ms per token, 0.70 tokens per second) 13.38.408.227 I slot print_timing: id 2 | task 13997 | total time = 5553.56 ms / 437 tokens 13.38.408.227 I slot print_timing: id 2 | task 13997 | graphs reused = 12476 13.38.408.228 I slot print_timing: id 2 | task 13997 | graph reallocs = 0 / 0 (same size) / (changed size) 13.38.408.364 I slot release: id 2 | task 13997 | stop processing: n_tokens = 2572, truncated = 0 13.38.408.379 I slot print_timing: id 0 | task 13995 | prompt processing, n_tokens = 1317, progress = 0.81, t = 5.56 s / 237.08 tokens per second 13.39.655.038 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2572, t_last = 349827155360 13.39.655.186 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 152.914 MiB) 13.39.655.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 137.421 MiB) 13.40.260.155 I slot launch_slot_: id 2 | task 14005 | processing task, is_child = 0 13.40.260.170 I slot print_timing: id 0 | task 13995 | prompt processing, n_tokens = 1618, progress = 1.00, t = 6.80 s / 237.87 tokens per second 13.43.588.330 I slot print_timing: id 1 | task 14001 | prompt processing, n_tokens = 1170, progress = 0.69, t = 6.52 s / 179.37 tokens per second 13.43.590.066 I slot print_timing: id 2 | task 14005 | prompt processing, n_tokens = 184, progress = 0.11, t = 3.32 s / 55.40 tokens per second 13.43.593.036 I slot print_timing: id 3 | task 14002 | prompt processing, n_tokens = 1317, progress = 0.70, t = 6.52 s / 201.91 tokens per second 13.44.978.393 I slot print_timing: id 0 | task 13995 | prompt eval time = 10735.27 ms / 1622 tokens ( 6.62 ms per token, 151.09 tokens per second) 13.44.978.396 I slot print_timing: id 0 | task 13995 | eval time = 1390.07 ms / 2 tokens ( 1390.07 ms per token, 0.72 tokens per second) 13.44.978.396 I slot print_timing: id 0 | task 13995 | total time = 12125.35 ms / 1624 tokens 13.44.978.397 I slot print_timing: id 0 | task 13995 | graphs reused = 12476 13.44.978.397 I slot print_timing: id 0 | task 13995 | graph reallocs = 0 / 0 (same size) / (changed size) 13.44.978.633 I slot release: id 0 | task 13995 | stop processing: n_tokens = 1623, truncated = 0 13.44.978.647 I slot print_timing: id 1 | task 14001 | prompt processing, n_tokens = 1317, progress = 0.78, t = 7.91 s / 166.44 tokens per second 13.44.980.799 I slot print_timing: id 2 | task 14005 | prompt processing, n_tokens = 473, progress = 0.28, t = 4.71 s / 100.40 tokens per second 13.44.980.822 I slot print_timing: id 3 | task 14002 | prompt processing, n_tokens = 1354, progress = 0.72, t = 7.91 s / 171.12 tokens per second 13.47.781.926 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.761 (> 0.100 thold), f_keep = 0.832 13.47.782.046 I slot launch_slot_: id 0 | task 14009 | processing task, is_child = 0 13.48.284.079 I slot print_timing: id 1 | task 14001 | prompt processing, n_tokens = 1682, progress = 1.00, t = 10.72 s / 156.95 tokens per second 13.48.286.790 I slot print_timing: id 2 | task 14005 | prompt processing, n_tokens = 1176, progress = 0.70, t = 7.51 s / 156.49 tokens per second 13.48.288.789 I slot print_timing: id 3 | task 14002 | prompt processing, n_tokens = 1866, progress = 1.00, t = 10.72 s / 174.13 tokens per second 13.49.639.448 I slot print_timing: id 2 | task 14005 | prompt processing, n_tokens = 1317, progress = 0.78, t = 9.37 s / 140.61 tokens per second 13.50.471.483 I slot print_timing: id 1 | task 14001 | prompt eval time = 12568.31 ms / 1686 tokens ( 7.45 ms per token, 134.15 tokens per second) 13.50.471.486 I slot print_timing: id 1 | task 14001 | eval time = 837.91 ms / 2 tokens ( 837.91 ms per token, 1.19 tokens per second) 13.50.471.487 I slot print_timing: id 1 | task 14001 | total time = 13406.22 ms / 1688 tokens 13.50.471.487 I slot print_timing: id 1 | task 14001 | graphs reused = 12476 13.50.471.487 I slot print_timing: id 1 | task 14001 | graph reallocs = 0 / 0 (same size) / (changed size) 13.50.471.612 I slot release: id 1 | task 14001 | stop processing: n_tokens = 1687, truncated = 0 13.50.471.759 I slot print_timing: id 3 | task 14002 | prompt eval time = 12568.14 ms / 1870 tokens ( 6.72 ms per token, 148.79 tokens per second) 13.50.471.762 I slot print_timing: id 3 | task 14002 | eval time = 838.05 ms / 2 tokens ( 838.05 ms per token, 1.19 tokens per second) 13.50.471.763 I slot print_timing: id 3 | task 14002 | total time = 13406.20 ms / 1872 tokens 13.50.471.763 I slot print_timing: id 3 | task 14002 | graphs reused = 12476 13.50.471.764 I slot print_timing: id 3 | task 14002 | graph reallocs = 0 / 0 (same size) / (changed size) 13.50.471.845 I slot release: id 3 | task 14002 | stop processing: n_tokens = 1871, truncated = 0 13.50.471.859 I slot print_timing: id 2 | task 14005 | prompt processing, n_tokens = 1688, progress = 1.00, t = 10.20 s / 165.42 tokens per second 13.50.539.475 I slot print_timing: id 0 | task 14009 | prompt eval time = 2689.31 ms / 425 tokens ( 6.33 ms per token, 158.03 tokens per second) 13.50.539.480 I slot print_timing: id 0 | task 14009 | eval time = 68.11 ms / 2 tokens ( 68.11 ms per token, 14.68 tokens per second) 13.50.539.481 I slot print_timing: id 0 | task 14009 | total time = 2757.41 ms / 427 tokens 13.50.539.482 I slot print_timing: id 0 | task 14009 | graphs reused = 12476 13.50.539.482 I slot print_timing: id 0 | task 14009 | graph reallocs = 0 / 0 (same size) / (changed size) 13.50.539.603 I slot release: id 0 | task 14009 | stop processing: n_tokens = 1776, truncated = 0 13.50.539.819 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1687, t_last = 349839218608 13.50.539.936 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 172.304 MiB) 13.50.629.267 I slot launch_slot_: id 1 | task 14013 | processing task, is_child = 0 13.50.629.378 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 174.205 MiB) 13.50.629.403 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 150.932 MiB) 13.50.739.778 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.738 MiB) 13.50.768.986 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.832 (> 0.100 thold), f_keep = 0.760 13.50.769.074 I slot launch_slot_: id 0 | task 14014 | processing task, is_child = 0 13.50.769.183 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1871, t_last = 349839218841 13.50.769.328 I slot launch_slot_: id 3 | task 14015 | processing task, is_child = 0 13.52.197.619 I slot print_timing: id 2 | task 14005 | prompt eval time = 10272.72 ms / 1692 tokens ( 6.07 ms per token, 164.71 tokens per second) 13.52.197.627 I slot print_timing: id 2 | task 14005 | eval time = 1657.80 ms / 2 tokens ( 1657.80 ms per token, 0.60 tokens per second) 13.52.197.628 I slot print_timing: id 2 | task 14005 | total time = 11930.52 ms / 1694 tokens 13.52.197.628 I slot print_timing: id 2 | task 14005 | graphs reused = 12476 13.52.197.629 I slot print_timing: id 2 | task 14005 | graph reallocs = 0 / 0 (same size) / (changed size) 13.52.197.745 I slot release: id 2 | task 14005 | stop processing: n_tokens = 1693, truncated = 0 13.52.492.179 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1693, t_last = 349840944741 13.52.492.292 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.557 MiB) 13.52.596.485 I slot launch_slot_: id 2 | task 14018 | processing task, is_child = 0 13.54.440.814 I slot print_timing: id 0 | task 14014 | prompt eval time = 1722.84 ms / 273 tokens ( 6.31 ms per token, 158.46 tokens per second) 13.54.440.816 I slot print_timing: id 0 | task 14014 | eval time = 1948.64 ms / 2 tokens ( 1948.64 ms per token, 0.51 tokens per second) 13.54.440.817 I slot print_timing: id 0 | task 14014 | total time = 3671.47 ms / 275 tokens 13.54.440.817 I slot print_timing: id 0 | task 14014 | graphs reused = 12476 13.54.440.818 I slot print_timing: id 0 | task 14014 | graph reallocs = 0 / 0 (same size) / (changed size) 13.54.440.949 I slot release: id 0 | task 14014 | stop processing: n_tokens = 1624, truncated = 0 13.54.440.966 I slot print_timing: id 1 | task 14013 | prompt processing, n_tokens = 538, progress = 0.84, t = 3.67 s / 146.59 tokens per second 13.54.444.448 I slot print_timing: id 3 | task 14015 | prompt processing, n_tokens = 538, progress = 0.81, t = 3.67 s / 146.60 tokens per second 13.55.100.564 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1624, t_last = 349843187946 13.55.100.719 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.663 MiB) 13.55.100.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.304 MiB) 13.55.419.591 I slot launch_slot_: id 0 | task 14021 | processing task, is_child = 0 13.55.420.075 I slot print_timing: id 1 | task 14013 | prompt processing, n_tokens = 634, progress = 0.99, t = 4.33 s / 146.43 tokens per second 13.55.423.635 I slot print_timing: id 3 | task 14015 | prompt processing, n_tokens = 658, progress = 0.99, t = 4.33 s / 151.98 tokens per second 13.56.579.046 I slot print_timing: id 2 | task 14018 | prompt processing, n_tokens = 538, progress = 0.80, t = 3.98 s / 135.33 tokens per second 13.57.099.799 I slot print_timing: id 1 | task 14013 | prompt eval time = 5805.37 ms / 638 tokens ( 9.10 ms per token, 109.90 tokens per second) 13.57.099.802 I slot print_timing: id 1 | task 14013 | eval time = 523.74 ms / 2 tokens ( 523.74 ms per token, 1.91 tokens per second) 13.57.099.803 I slot print_timing: id 1 | task 14013 | total time = 6329.10 ms / 640 tokens 13.57.099.803 I slot print_timing: id 1 | task 14013 | graphs reused = 12476 13.57.099.808 I slot print_timing: id 1 | task 14013 | graph reallocs = 0 / 0 (same size) / (changed size) 13.57.099.868 I slot release: id 1 | task 14013 | stop processing: n_tokens = 639, truncated = 0 13.57.099.969 I slot print_timing: id 3 | task 14015 | prompt eval time = 5805.35 ms / 662 tokens ( 8.77 ms per token, 114.03 tokens per second) 13.57.099.971 I slot print_timing: id 3 | task 14015 | eval time = 523.73 ms / 2 tokens ( 523.73 ms per token, 1.91 tokens per second) 13.57.099.972 I slot print_timing: id 3 | task 14015 | total time = 6329.08 ms / 664 tokens 13.57.099.972 I slot print_timing: id 3 | task 14015 | graphs reused = 12476 13.57.099.972 I slot print_timing: id 3 | task 14015 | graph reallocs = 0 / 0 (same size) / (changed size) 13.57.099.993 I slot release: id 3 | task 14015 | stop processing: n_tokens = 663, truncated = 0 13.57.104.407 I slot print_timing: id 2 | task 14018 | prompt processing, n_tokens = 669, progress = 0.99, t = 4.50 s / 148.69 tokens per second 13.57.879.235 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 639, t_last = 349845846865 13.57.895.397 I slot launch_slot_: id 1 | task 14025 | processing task, is_child = 0 13.57.895.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 160.600 MiB) 13.57.920.846 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.862 (> 0.100 thold), f_keep = 0.849 13.57.920.927 I slot launch_slot_: id 3 | task 14026 | processing task, is_child = 0 13.58.804.518 I slot print_timing: id 2 | task 14018 | prompt eval time = 5278.87 ms / 673 tokens ( 7.84 ms per token, 127.49 tokens per second) 13.58.804.521 I slot print_timing: id 2 | task 14018 | eval time = 925.28 ms / 2 tokens ( 925.28 ms per token, 1.08 tokens per second) 13.58.804.522 I slot print_timing: id 2 | task 14018 | total time = 6204.15 ms / 675 tokens 13.58.804.522 I slot print_timing: id 2 | task 14018 | graphs reused = 12476 13.58.804.523 I slot print_timing: id 2 | task 14018 | graph reallocs = 0 / 0 (same size) / (changed size) 13.58.804.556 I slot release: id 2 | task 14018 | stop processing: n_tokens = 674, truncated = 0 13.58.804.567 I slot print_timing: id 0 | task 14021 | prompt processing, n_tokens = 635, progress = 0.99, t = 3.38 s / 187.61 tokens per second 13.59.229.419 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 674, t_last = 349847551551 13.59.229.492 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 152.818 MiB) 13.59.252.046 I slot launch_slot_: id 2 | task 14029 | processing task, is_child = 0 14.00.406.782 I slot print_timing: id 0 | task 14021 | prompt eval time = 3809.50 ms / 639 tokens ( 5.96 ms per token, 167.74 tokens per second) 14.00.406.788 I slot print_timing: id 0 | task 14021 | eval time = 1177.66 ms / 2 tokens ( 1177.66 ms per token, 0.85 tokens per second) 14.00.406.789 I slot print_timing: id 0 | task 14021 | total time = 4987.16 ms / 641 tokens 14.00.406.789 I slot print_timing: id 0 | task 14021 | graphs reused = 12476 14.00.406.790 I slot print_timing: id 0 | task 14021 | graph reallocs = 0 / 0 (same size) / (changed size) 14.00.406.823 I slot release: id 0 | task 14021 | stop processing: n_tokens = 640, truncated = 0 14.00.407.055 I slot print_timing: id 3 | task 14026 | prompt eval time = 1307.27 ms / 90 tokens ( 14.53 ms per token, 68.85 tokens per second) 14.00.407.060 I slot print_timing: id 3 | task 14026 | eval time = 1177.64 ms / 2 tokens ( 1177.64 ms per token, 0.85 tokens per second) 14.00.407.061 I slot print_timing: id 3 | task 14026 | total time = 2484.91 ms / 92 tokens 14.00.407.061 I slot print_timing: id 3 | task 14026 | graphs reused = 12476 14.00.407.061 I slot print_timing: id 3 | task 14026 | graph reallocs = 0 / 0 (same size) / (changed size) 14.00.407.101 I slot release: id 3 | task 14026 | stop processing: n_tokens = 654, truncated = 0 14.01.052.494 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 640, t_last = 349849153818 14.01.052.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.415 MiB) 14.01.178.147 I slot launch_slot_: id 0 | task 14032 | processing task, is_child = 0 14.01.178.230 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.118 MiB) 14.01.214.881 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 654, t_last = 349849154096 14.01.215.032 I slot launch_slot_: id 3 | task 14033 | processing task, is_child = 0 14.01.215.140 I slot print_timing: id 1 | task 14025 | prompt processing, n_tokens = 699, progress = 0.99, t = 3.13 s / 223.29 tokens per second 14.02.364.503 I slot print_timing: id 2 | task 14029 | prompt processing, n_tokens = 441, progress = 0.46, t = 3.11 s / 141.84 tokens per second 14.03.689.360 I slot print_timing: id 1 | task 14025 | prompt eval time = 4441.81 ms / 703 tokens ( 6.32 ms per token, 158.27 tokens per second) 14.03.689.366 I slot print_timing: id 1 | task 14025 | eval time = 1325.49 ms / 2 tokens ( 1325.49 ms per token, 0.75 tokens per second) 14.03.689.366 I slot print_timing: id 1 | task 14025 | total time = 5767.30 ms / 705 tokens 14.03.689.367 I slot print_timing: id 1 | task 14025 | graphs reused = 12476 14.03.689.367 I slot print_timing: id 1 | task 14025 | graph reallocs = 0 / 0 (same size) / (changed size) 14.03.689.485 I slot release: id 1 | task 14025 | stop processing: n_tokens = 704, truncated = 0 14.03.691.331 I slot print_timing: id 2 | task 14029 | prompt processing, n_tokens = 818, progress = 0.85, t = 4.43 s / 184.46 tokens per second 14.05.004.783 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 704, t_last = 349852436481 14.05.004.861 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.150 MiB) 14.05.583.785 I slot launch_slot_: id 1 | task 14037 | processing task, is_child = 0 14.05.583.805 I slot print_timing: id 0 | task 14032 | prompt processing, n_tokens = 593, progress = 0.85, t = 3.79 s / 156.48 tokens per second 14.05.591.050 I slot print_timing: id 2 | task 14029 | prompt processing, n_tokens = 953, progress = 1.00, t = 5.75 s / 165.73 tokens per second 14.05.592.349 I slot print_timing: id 3 | task 14033 | prompt processing, n_tokens = 593, progress = 0.84, t = 3.79 s / 156.53 tokens per second 14.06.687.796 I slot print_timing: id 0 | task 14032 | prompt processing, n_tokens = 697, progress = 0.99, t = 5.47 s / 127.36 tokens per second 14.06.693.729 I slot print_timing: id 3 | task 14033 | prompt processing, n_tokens = 701, progress = 0.99, t = 5.47 s / 128.12 tokens per second 14.07.182.293 I slot print_timing: id 2 | task 14029 | prompt eval time = 7433.15 ms / 957 tokens ( 7.77 ms per token, 128.75 tokens per second) 14.07.182.299 I slot print_timing: id 2 | task 14029 | eval time = 494.51 ms / 2 tokens ( 494.51 ms per token, 2.02 tokens per second) 14.07.182.299 I slot print_timing: id 2 | task 14029 | total time = 7927.66 ms / 959 tokens 14.07.182.299 I slot print_timing: id 2 | task 14029 | graphs reused = 12476 14.07.182.300 I slot print_timing: id 2 | task 14029 | graph reallocs = 0 / 0 (same size) / (changed size) 14.07.183.443 I slot release: id 2 | task 14029 | stop processing: n_tokens = 958, truncated = 0 14.07.961.525 I slot print_timing: id 0 | task 14032 | prompt eval time = 5967.13 ms / 701 tokens ( 8.51 ms per token, 117.48 tokens per second) 14.07.961.530 I slot print_timing: id 0 | task 14032 | eval time = 779.35 ms / 2 tokens ( 779.35 ms per token, 1.28 tokens per second) 14.07.961.531 I slot print_timing: id 0 | task 14032 | total time = 6746.48 ms / 703 tokens 14.07.961.531 I slot print_timing: id 0 | task 14032 | graphs reused = 12476 14.07.961.532 I slot print_timing: id 0 | task 14032 | graph reallocs = 0 / 0 (same size) / (changed size) 14.07.962.912 I slot release: id 0 | task 14032 | stop processing: n_tokens = 702, truncated = 0 14.07.963.168 I slot print_timing: id 3 | task 14033 | prompt eval time = 5967.41 ms / 705 tokens ( 8.46 ms per token, 118.14 tokens per second) 14.07.963.173 I slot print_timing: id 3 | task 14033 | eval time = 779.42 ms / 2 tokens ( 779.42 ms per token, 1.28 tokens per second) 14.07.963.173 I slot print_timing: id 3 | task 14033 | total time = 6746.83 ms / 707 tokens 14.07.963.173 I slot print_timing: id 3 | task 14033 | graphs reused = 12476 14.07.963.174 I slot print_timing: id 3 | task 14033 | graph reallocs = 0 / 0 (same size) / (changed size) 14.07.963.231 I slot release: id 3 | task 14033 | stop processing: n_tokens = 706, truncated = 0 14.07.963.243 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 958, t_last = 349855930440 14.07.963.389 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 187.579 MiB) 14.08.015.381 I slot launch_slot_: id 2 | task 14041 | processing task, is_child = 0 14.08.034.812 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 153.202 MiB) 14.08.052.130 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 702, t_last = 349856709909 14.08.052.279 I slot launch_slot_: id 0 | task 14042 | processing task, is_child = 0 14.08.052.338 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 706, t_last = 349856710228 14.08.052.432 I slot launch_slot_: id 3 | task 14043 | processing task, is_child = 0 14.09.039.967 I slot print_timing: id 1 | task 14037 | prompt processing, n_tokens = 747, progress = 0.99, t = 3.28 s / 227.48 tokens per second 14.11.190.345 I slot print_timing: id 1 | task 14037 | prompt eval time = 4674.92 ms / 751 tokens ( 6.22 ms per token, 160.64 tokens per second) 14.11.190.354 I slot print_timing: id 1 | task 14037 | eval time = 924.47 ms / 2 tokens ( 924.47 ms per token, 1.08 tokens per second) 14.11.190.354 I slot print_timing: id 1 | task 14037 | total time = 5599.38 ms / 753 tokens 14.11.190.355 I slot print_timing: id 1 | task 14037 | graphs reused = 12476 14.11.190.355 I slot print_timing: id 1 | task 14037 | graph reallocs = 0 / 0 (same size) / (changed size) 14.11.192.200 I slot release: id 1 | task 14037 | stop processing: n_tokens = 752, truncated = 0 14.11.192.227 I slot print_timing: id 0 | task 14042 | prompt processing, n_tokens = 287, progress = 0.36, t = 3.14 s / 91.47 tokens per second 14.11.194.123 I slot print_timing: id 2 | task 14041 | prompt processing, n_tokens = 640, progress = 0.86, t = 3.14 s / 204.05 tokens per second 14.11.196.850 I slot print_timing: id 3 | task 14043 | prompt processing, n_tokens = 293, progress = 0.36, t = 3.14 s / 93.42 tokens per second 14.12.381.512 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.884 14.12.381.590 I slot launch_slot_: id 1 | task 14048 | processing task, is_child = 0 14.12.381.598 I slot print_timing: id 0 | task 14042 | prompt processing, n_tokens = 640, progress = 0.80, t = 4.33 s / 147.84 tokens per second 14.12.927.545 I slot print_timing: id 2 | task 14041 | prompt processing, n_tokens = 741, progress = 0.99, t = 4.33 s / 171.22 tokens per second 14.12.929.152 I slot print_timing: id 3 | task 14043 | prompt processing, n_tokens = 640, progress = 0.79, t = 4.33 s / 147.88 tokens per second 14.14.261.404 I slot print_timing: id 0 | task 14042 | prompt processing, n_tokens = 799, progress = 1.00, t = 6.21 s / 128.69 tokens per second 14.14.267.493 I slot print_timing: id 3 | task 14043 | prompt processing, n_tokens = 805, progress = 1.00, t = 6.21 s / 129.68 tokens per second 14.14.393.147 I slot print_timing: id 2 | task 14041 | prompt eval time = 6207.70 ms / 745 tokens ( 8.33 ms per token, 120.01 tokens per second) 14.14.393.152 I slot print_timing: id 2 | task 14041 | eval time = 131.75 ms / 2 tokens ( 131.75 ms per token, 7.59 tokens per second) 14.14.393.153 I slot print_timing: id 2 | task 14041 | total time = 6339.45 ms / 747 tokens 14.14.393.153 I slot print_timing: id 2 | task 14041 | graphs reused = 12476 14.14.393.153 I slot print_timing: id 2 | task 14041 | graph reallocs = 0 / 0 (same size) / (changed size) 14.14.393.204 I slot release: id 2 | task 14041 | stop processing: n_tokens = 746, truncated = 0 14.14.446.621 I slot print_timing: id 0 | task 14042 | prompt eval time = 6340.49 ms / 803 tokens ( 7.90 ms per token, 126.65 tokens per second) 14.14.446.626 I slot print_timing: id 0 | task 14042 | eval time = 53.69 ms / 2 tokens ( 53.69 ms per token, 18.62 tokens per second) 14.14.446.627 I slot print_timing: id 0 | task 14042 | total time = 6394.18 ms / 805 tokens 14.14.446.627 I slot print_timing: id 0 | task 14042 | graphs reused = 12476 14.14.446.628 I slot print_timing: id 0 | task 14042 | graph reallocs = 0 / 0 (same size) / (changed size) 14.14.446.672 I slot release: id 0 | task 14042 | stop processing: n_tokens = 804, truncated = 0 14.14.446.761 I slot print_timing: id 1 | task 14048 | prompt eval time = 1467.90 ms / 102 tokens ( 14.39 ms per token, 69.49 tokens per second) 14.14.446.766 I slot print_timing: id 1 | task 14048 | eval time = 53.70 ms / 2 tokens ( 53.70 ms per token, 18.62 tokens per second) 14.14.446.766 I slot print_timing: id 1 | task 14048 | total time = 1521.60 ms / 104 tokens 14.14.446.766 I slot print_timing: id 1 | task 14048 | graphs reused = 12476 14.14.446.767 I slot print_timing: id 1 | task 14048 | graph reallocs = 0 / 0 (same size) / (changed size) 14.14.446.806 I slot release: id 1 | task 14048 | stop processing: n_tokens = 768, truncated = 0 14.14.446.908 I slot print_timing: id 3 | task 14043 | prompt eval time = 6339.52 ms / 809 tokens ( 7.84 ms per token, 127.61 tokens per second) 14.14.446.910 I slot print_timing: id 3 | task 14043 | eval time = 53.57 ms / 2 tokens ( 53.57 ms per token, 18.67 tokens per second) 14.14.446.911 I slot print_timing: id 3 | task 14043 | total time = 6393.09 ms / 811 tokens 14.14.446.911 I slot print_timing: id 3 | task 14043 | graphs reused = 12476 14.14.446.911 I slot print_timing: id 3 | task 14043 | graph reallocs = 0 / 0 (same size) / (changed size) 14.14.446.933 I slot release: id 3 | task 14043 | stop processing: n_tokens = 810, truncated = 0 14.14.446.937 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 349863140199 14.14.447.008 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 157.318 MiB) 14.14.474.358 I slot launch_slot_: id 2 | task 14052 | processing task, is_child = 0 14.14.474.435 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 156.169 MiB) 14.14.490.367 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 184.081 MiB) 14.14.518.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.062 MiB) 14.14.539.168 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 804, t_last = 349863193667 14.14.539.323 I slot launch_slot_: id 0 | task 14053 | processing task, is_child = 0 14.14.539.457 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 768, t_last = 349863193801 14.14.539.563 I slot launch_slot_: id 1 | task 14054 | processing task, is_child = 0 14.14.539.625 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 810, t_last = 349863193928 14.14.539.728 I slot launch_slot_: id 3 | task 14055 | processing task, is_child = 0 14.18.887.698 I slot print_timing: id 0 | task 14053 | prompt processing, n_tokens = 545, progress = 0.82, t = 4.35 s / 125.35 tokens per second 14.19.003.251 I slot print_timing: id 1 | task 14054 | prompt processing, n_tokens = 612, progress = 0.86, t = 4.35 s / 140.76 tokens per second 14.19.004.658 I slot print_timing: id 2 | task 14052 | prompt processing, n_tokens = 507, progress = 0.84, t = 4.35 s / 116.61 tokens per second 14.19.017.055 I slot print_timing: id 3 | task 14055 | prompt processing, n_tokens = 224, progress = 0.30, t = 4.35 s / 51.52 tokens per second 14.19.970.449 I slot print_timing: id 0 | task 14053 | prompt processing, n_tokens = 662, progress = 0.99, t = 5.43 s / 121.90 tokens per second 14.20.584.165 I slot print_timing: id 1 | task 14054 | prompt processing, n_tokens = 711, progress = 0.99, t = 5.43 s / 130.93 tokens per second 14.20.586.561 I slot print_timing: id 2 | task 14052 | prompt processing, n_tokens = 596, progress = 0.99, t = 5.43 s / 109.75 tokens per second 14.20.589.087 I slot print_timing: id 3 | task 14055 | prompt processing, n_tokens = 612, progress = 0.83, t = 5.43 s / 112.70 tokens per second 14.21.090.636 I slot print_timing: id 3 | task 14055 | prompt processing, n_tokens = 736, progress = 0.99, t = 6.55 s / 112.36 tokens per second 14.21.168.042 I slot print_timing: id 0 | task 14053 | prompt eval time = 6550.59 ms / 666 tokens ( 9.84 ms per token, 101.67 tokens per second) 14.21.168.047 I slot print_timing: id 0 | task 14053 | eval time = 77.72 ms / 2 tokens ( 77.72 ms per token, 12.87 tokens per second) 14.21.168.048 I slot print_timing: id 0 | task 14053 | total time = 6628.31 ms / 668 tokens 14.21.168.048 I slot print_timing: id 0 | task 14053 | graphs reused = 12476 14.21.168.048 I slot print_timing: id 0 | task 14053 | graph reallocs = 0 / 0 (same size) / (changed size) 14.21.169.614 I slot release: id 0 | task 14053 | stop processing: n_tokens = 667, truncated = 0 14.21.169.706 I slot print_timing: id 1 | task 14054 | prompt eval time = 6550.62 ms / 715 tokens ( 9.16 ms per token, 109.15 tokens per second) 14.21.169.709 I slot print_timing: id 1 | task 14054 | eval time = 79.23 ms / 2 tokens ( 79.23 ms per token, 12.62 tokens per second) 14.21.169.709 I slot print_timing: id 1 | task 14054 | total time = 6629.85 ms / 717 tokens 14.21.169.710 I slot print_timing: id 1 | task 14054 | graphs reused = 12476 14.21.169.710 I slot print_timing: id 1 | task 14054 | graph reallocs = 0 / 0 (same size) / (changed size) 14.21.169.759 I slot release: id 1 | task 14054 | stop processing: n_tokens = 716, truncated = 0 14.21.169.843 I slot print_timing: id 2 | task 14052 | prompt eval time = 6550.68 ms / 600 tokens ( 10.92 ms per token, 91.59 tokens per second) 14.21.169.844 I slot print_timing: id 2 | task 14052 | eval time = 79.21 ms / 2 tokens ( 79.21 ms per token, 12.62 tokens per second) 14.21.169.845 I slot print_timing: id 2 | task 14052 | total time = 6629.89 ms / 602 tokens 14.21.169.845 I slot print_timing: id 2 | task 14052 | graphs reused = 12476 14.21.169.846 I slot print_timing: id 2 | task 14052 | graph reallocs = 0 / 0 (same size) / (changed size) 14.21.169.894 I slot release: id 2 | task 14052 | stop processing: n_tokens = 601, truncated = 0 14.21.193.844 I slot print_timing: id 3 | task 14055 | prompt eval time = 6630.00 ms / 740 tokens ( 8.96 ms per token, 111.61 tokens per second) 14.21.193.846 I slot print_timing: id 3 | task 14055 | eval time = 23.81 ms / 2 tokens ( 23.81 ms per token, 42.00 tokens per second) 14.21.193.846 I slot print_timing: id 3 | task 14055 | total time = 6653.81 ms / 742 tokens 14.21.193.846 I slot print_timing: id 3 | task 14055 | graphs reused = 12476 14.21.193.847 I slot print_timing: id 3 | task 14055 | graph reallocs = 0 / 0 (same size) / (changed size) 14.21.193.877 I slot release: id 3 | task 14055 | stop processing: n_tokens = 741, truncated = 0 14.21.193.881 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 667, t_last = 349869916610 14.21.193.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 184.245 MiB) 14.21.217.223 I slot launch_slot_: id 0 | task 14063 | processing task, is_child = 0 14.21.217.294 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 181.974 MiB) 14.21.274.982 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.299 MiB) 14.21.287.584 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 716, t_last = 349869916754 14.21.287.749 I slot launch_slot_: id 1 | task 14064 | processing task, is_child = 0 14.21.287.860 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 601, t_last = 349869916889 14.21.289.295 I slot launch_slot_: id 2 | task 14065 | processing task, is_child = 0 14.21.289.361 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 349869940872 14.21.289.458 I slot launch_slot_: id 3 | task 14066 | processing task, is_child = 0 14.25.089.909 I slot print_timing: id 0 | task 14063 | prompt processing, n_tokens = 522, progress = 0.81, t = 3.80 s / 137.36 tokens per second 14.25.091.296 I slot print_timing: id 1 | task 14064 | prompt processing, n_tokens = 522, progress = 0.84, t = 3.80 s / 137.36 tokens per second 14.25.093.193 I slot print_timing: id 3 | task 14066 | prompt processing, n_tokens = 522, progress = 0.84, t = 3.77 s / 138.56 tokens per second 14.26.074.464 I slot print_timing: id 2 | task 14065 | prompt eval time = 3800.26 ms / 102 tokens ( 37.26 ms per token, 26.84 tokens per second) 14.26.074.468 I slot print_timing: id 2 | task 14065 | eval time = 984.56 ms / 2 tokens ( 984.56 ms per token, 1.02 tokens per second) 14.26.074.468 I slot print_timing: id 2 | task 14065 | total time = 4784.83 ms / 104 tokens 14.26.074.469 I slot print_timing: id 2 | task 14065 | graphs reused = 12476 14.26.074.469 I slot print_timing: id 2 | task 14065 | graph reallocs = 0 / 0 (same size) / (changed size) 14.26.074.508 I slot release: id 2 | task 14065 | stop processing: n_tokens = 647, truncated = 0 14.26.074.519 I slot print_timing: id 0 | task 14063 | prompt processing, n_tokens = 642, progress = 0.99, t = 4.78 s / 134.17 tokens per second 14.26.076.442 I slot print_timing: id 1 | task 14064 | prompt processing, n_tokens = 617, progress = 0.99, t = 4.78 s / 128.95 tokens per second 14.26.078.529 I slot print_timing: id 3 | task 14066 | prompt processing, n_tokens = 618, progress = 0.99, t = 4.75 s / 130.05 tokens per second 14.26.178.112 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 647, t_last = 349874821503 14.26.178.185 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.022 MiB) 14.26.195.711 I slot launch_slot_: id 2 | task 14072 | processing task, is_child = 0 14.26.568.036 I slot print_timing: id 0 | task 14063 | prompt eval time = 4888.40 ms / 646 tokens ( 7.57 ms per token, 132.15 tokens per second) 14.26.568.042 I slot print_timing: id 0 | task 14063 | eval time = 390.17 ms / 2 tokens ( 390.17 ms per token, 2.56 tokens per second) 14.26.568.042 I slot print_timing: id 0 | task 14063 | total time = 5278.57 ms / 648 tokens 14.26.568.043 I slot print_timing: id 0 | task 14063 | graphs reused = 12476 14.26.568.043 I slot print_timing: id 0 | task 14063 | graph reallocs = 0 / 0 (same size) / (changed size) 14.26.568.098 I slot release: id 0 | task 14063 | stop processing: n_tokens = 647, truncated = 0 14.26.568.253 I slot print_timing: id 1 | task 14064 | prompt eval time = 4888.44 ms / 621 tokens ( 7.87 ms per token, 127.03 tokens per second) 14.26.568.255 I slot print_timing: id 1 | task 14064 | eval time = 390.27 ms / 2 tokens ( 390.27 ms per token, 2.56 tokens per second) 14.26.568.256 I slot print_timing: id 1 | task 14064 | total time = 5278.70 ms / 623 tokens 14.26.568.256 I slot print_timing: id 1 | task 14064 | graphs reused = 12476 14.26.568.256 I slot print_timing: id 1 | task 14064 | graph reallocs = 0 / 0 (same size) / (changed size) 14.26.568.286 I slot release: id 1 | task 14064 | stop processing: n_tokens = 622, truncated = 0 14.26.568.417 I slot print_timing: id 3 | task 14066 | prompt eval time = 4855.77 ms / 622 tokens ( 7.81 ms per token, 128.09 tokens per second) 14.26.568.420 I slot print_timing: id 3 | task 14066 | eval time = 390.31 ms / 2 tokens ( 390.31 ms per token, 2.56 tokens per second) 14.26.568.420 I slot print_timing: id 3 | task 14066 | total time = 5246.08 ms / 624 tokens 14.26.568.420 I slot print_timing: id 3 | task 14066 | graphs reused = 12476 14.26.568.421 I slot print_timing: id 3 | task 14066 | graph reallocs = 0 / 0 (same size) / (changed size) 14.26.568.442 I slot release: id 3 | task 14066 | stop processing: n_tokens = 623, truncated = 0 14.26.644.779 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.889 (> 0.100 thold), f_keep = 0.845 14.26.644.844 I slot launch_slot_: id 0 | task 14076 | processing task, is_child = 0 14.27.383.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 155.882 MiB) 14.27.401.235 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 14.27.401.333 I slot launch_slot_: id 1 | task 14077 | processing task, is_child = 0 14.27.401.392 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.878 14.27.401.435 I slot launch_slot_: id 3 | task 14078 | processing task, is_child = 0 14.28.380.850 I slot print_timing: id 0 | task 14076 | prompt eval time = 937.33 ms / 68 tokens ( 13.78 ms per token, 72.55 tokens per second) 14.28.380.853 I slot print_timing: id 0 | task 14076 | eval time = 42.08 ms / 2 tokens ( 42.08 ms per token, 23.76 tokens per second) 14.28.380.853 I slot print_timing: id 0 | task 14076 | total time = 979.40 ms / 70 tokens 14.28.380.854 I slot print_timing: id 0 | task 14076 | graphs reused = 12476 14.28.380.854 I slot print_timing: id 0 | task 14076 | graph reallocs = 0 / 0 (same size) / (changed size) 14.28.380.891 I slot release: id 0 | task 14076 | stop processing: n_tokens = 616, truncated = 0 14.28.380.984 I slot print_timing: id 1 | task 14077 | prompt eval time = 936.33 ms / 70 tokens ( 13.38 ms per token, 74.76 tokens per second) 14.28.380.986 I slot print_timing: id 1 | task 14077 | eval time = 42.04 ms / 2 tokens ( 42.04 ms per token, 23.79 tokens per second) 14.28.380.986 I slot print_timing: id 1 | task 14077 | total time = 978.37 ms / 72 tokens 14.28.380.987 I slot print_timing: id 1 | task 14077 | graphs reused = 12476 14.28.380.987 I slot print_timing: id 1 | task 14077 | graph reallocs = 0 / 0 (same size) / (changed size) 14.28.381.012 I slot release: id 1 | task 14077 | stop processing: n_tokens = 618, truncated = 0 14.28.381.099 I slot print_timing: id 2 | task 14072 | prompt eval time = 2143.43 ms / 617 tokens ( 3.47 ms per token, 287.86 tokens per second) 14.28.381.100 I slot print_timing: id 2 | task 14072 | eval time = 41.95 ms / 2 tokens ( 41.95 ms per token, 23.84 tokens per second) 14.28.381.101 I slot print_timing: id 2 | task 14072 | total time = 2185.38 ms / 619 tokens 14.28.381.101 I slot print_timing: id 2 | task 14072 | graphs reused = 12476 14.28.381.101 I slot print_timing: id 2 | task 14072 | graph reallocs = 0 / 0 (same size) / (changed size) 14.28.381.137 I slot release: id 2 | task 14072 | stop processing: n_tokens = 618, truncated = 0 14.28.381.229 I slot print_timing: id 3 | task 14078 | prompt eval time = 928.67 ms / 77 tokens ( 12.06 ms per token, 82.91 tokens per second) 14.28.381.232 I slot print_timing: id 3 | task 14078 | eval time = 41.86 ms / 2 tokens ( 41.86 ms per token, 23.89 tokens per second) 14.28.381.233 I slot print_timing: id 3 | task 14078 | total time = 970.54 ms / 79 tokens 14.28.381.233 I slot print_timing: id 3 | task 14078 | graphs reused = 12476 14.28.381.233 I slot print_timing: id 3 | task 14078 | graph reallocs = 0 / 0 (same size) / (changed size) 14.28.381.251 I slot release: id 3 | task 14078 | stop processing: n_tokens = 625, truncated = 0 14.28.391.916 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.888 14.28.392.038 I slot launch_slot_: id 0 | task 14082 | processing task, is_child = 0 14.28.392.117 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 152.819 MiB) 14.28.412.373 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 182.246 MiB) 14.28.436.780 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 145.516 MiB) 14.28.465.722 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.890 14.28.465.803 I slot launch_slot_: id 1 | task 14083 | processing task, is_child = 0 14.28.465.922 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.875 (> 0.100 thold), f_keep = 0.885 14.28.465.971 I slot launch_slot_: id 2 | task 14084 | processing task, is_child = 0 14.28.466.027 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.834 (> 0.100 thold), f_keep = 0.875 14.28.466.065 I slot launch_slot_: id 3 | task 14085 | processing task, is_child = 0 14.29.537.631 I slot print_timing: id 0 | task 14082 | prompt eval time = 1029.52 ms / 71 tokens ( 14.50 ms per token, 68.96 tokens per second) 14.29.537.633 I slot print_timing: id 0 | task 14082 | eval time = 42.04 ms / 2 tokens ( 42.04 ms per token, 23.79 tokens per second) 14.29.537.634 I slot print_timing: id 0 | task 14082 | total time = 1071.55 ms / 73 tokens 14.29.537.634 I slot print_timing: id 0 | task 14082 | graphs reused = 12476 14.29.537.634 I slot print_timing: id 0 | task 14082 | graph reallocs = 0 / 0 (same size) / (changed size) 14.29.537.680 I slot release: id 0 | task 14082 | stop processing: n_tokens = 619, truncated = 0 14.29.537.776 I slot print_timing: id 1 | task 14083 | prompt eval time = 1028.52 ms / 76 tokens ( 13.53 ms per token, 73.89 tokens per second) 14.29.537.779 I slot print_timing: id 1 | task 14083 | eval time = 41.99 ms / 2 tokens ( 41.99 ms per token, 23.82 tokens per second) 14.29.537.779 I slot print_timing: id 1 | task 14083 | total time = 1070.51 ms / 78 tokens 14.29.537.780 I slot print_timing: id 1 | task 14083 | graphs reused = 12476 14.29.537.780 I slot print_timing: id 1 | task 14083 | graph reallocs = 0 / 0 (same size) / (changed size) 14.29.537.807 I slot release: id 1 | task 14083 | stop processing: n_tokens = 627, truncated = 0 14.29.537.903 I slot print_timing: id 2 | task 14084 | prompt eval time = 1027.59 ms / 78 tokens ( 13.17 ms per token, 75.91 tokens per second) 14.29.537.905 I slot print_timing: id 2 | task 14084 | eval time = 41.91 ms / 2 tokens ( 41.91 ms per token, 23.86 tokens per second) 14.29.537.905 I slot print_timing: id 2 | task 14084 | total time = 1069.50 ms / 80 tokens 14.29.537.906 I slot print_timing: id 2 | task 14084 | graphs reused = 12476 14.29.537.906 I slot print_timing: id 2 | task 14084 | graph reallocs = 0 / 0 (same size) / (changed size) 14.29.537.926 I slot release: id 2 | task 14084 | stop processing: n_tokens = 626, truncated = 0 14.29.538.027 I slot print_timing: id 3 | task 14085 | prompt eval time = 1026.56 ms / 109 tokens ( 9.42 ms per token, 106.18 tokens per second) 14.29.538.030 I slot print_timing: id 3 | task 14085 | eval time = 41.91 ms / 2 tokens ( 41.91 ms per token, 23.86 tokens per second) 14.29.538.031 I slot print_timing: id 3 | task 14085 | total time = 1068.46 ms / 111 tokens 14.29.538.031 I slot print_timing: id 3 | task 14085 | graphs reused = 12476 14.29.538.032 I slot print_timing: id 3 | task 14085 | graph reallocs = 0 / 0 (same size) / (changed size) 14.29.538.047 I slot release: id 3 | task 14085 | stop processing: n_tokens = 657, truncated = 0 14.29.548.494 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 349878284675 14.29.548.566 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 145.037 MiB) 14.29.548.593 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 151.547 MiB) 14.29.581.658 I slot launch_slot_: id 0 | task 14089 | processing task, is_child = 0 14.29.581.728 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.246 MiB) 14.29.619.949 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.352 MiB) 14.29.654.477 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.629 MiB) 14.29.702.263 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 349878284802 14.29.702.413 I slot launch_slot_: id 1 | task 14090 | processing task, is_child = 0 14.29.702.535 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 626, t_last = 349878284921 14.29.702.635 I slot launch_slot_: id 2 | task 14091 | processing task, is_child = 0 14.29.702.691 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 657, t_last = 349878285042 14.29.702.783 I slot launch_slot_: id 3 | task 14092 | processing task, is_child = 0 14.32.722.813 I slot print_timing: id 0 | task 14089 | prompt processing, n_tokens = 269, progress = 0.34, t = 3.02 s / 89.07 tokens per second 14.32.791.181 I slot print_timing: id 1 | task 14090 | prompt processing, n_tokens = 280, progress = 0.35, t = 3.02 s / 92.72 tokens per second 14.32.793.484 I slot print_timing: id 2 | task 14091 | prompt processing, n_tokens = 472, progress = 0.48, t = 3.02 s / 156.30 tokens per second 14.32.824.420 I slot print_timing: id 3 | task 14092 | prompt processing, n_tokens = 482, progress = 0.48, t = 3.02 s / 159.61 tokens per second 14.35.657.922 I slot print_timing: id 0 | task 14089 | prompt processing, n_tokens = 677, progress = 0.86, t = 5.96 s / 113.68 tokens per second 14.35.729.548 I slot print_timing: id 1 | task 14090 | prompt processing, n_tokens = 677, progress = 0.85, t = 5.96 s / 113.69 tokens per second 14.35.736.408 I slot print_timing: id 2 | task 14091 | prompt processing, n_tokens = 824, progress = 0.83, t = 5.95 s / 138.37 tokens per second 14.35.743.385 I slot print_timing: id 3 | task 14092 | prompt processing, n_tokens = 824, progress = 0.83, t = 5.95 s / 138.37 tokens per second 14.37.019.936 I slot print_timing: id 0 | task 14089 | prompt processing, n_tokens = 781, progress = 0.99, t = 7.32 s / 106.74 tokens per second 14.37.088.487 I slot print_timing: id 1 | task 14090 | prompt processing, n_tokens = 792, progress = 0.99, t = 7.32 s / 108.24 tokens per second 14.37.091.035 I slot print_timing: id 2 | task 14091 | prompt processing, n_tokens = 984, progress = 1.00, t = 7.32 s / 134.48 tokens per second 14.37.093.234 I slot print_timing: id 3 | task 14092 | prompt processing, n_tokens = 994, progress = 1.00, t = 7.32 s / 135.85 tokens per second 14.37.241.355 I slot print_timing: id 0 | task 14089 | prompt eval time = 7496.42 ms / 785 tokens ( 9.55 ms per token, 104.72 tokens per second) 14.37.241.360 I slot print_timing: id 0 | task 14089 | eval time = 42.14 ms / 2 tokens ( 42.14 ms per token, 23.73 tokens per second) 14.37.241.362 I slot print_timing: id 0 | task 14089 | total time = 7538.56 ms / 787 tokens 14.37.241.362 I slot print_timing: id 0 | task 14089 | graphs reused = 12477 14.37.241.362 I slot print_timing: id 0 | task 14089 | graph reallocs = 0 / 0 (same size) / (changed size) 14.37.241.516 I slot release: id 0 | task 14089 | stop processing: n_tokens = 786, truncated = 0 14.37.241.610 I slot print_timing: id 1 | task 14090 | prompt eval time = 7496.46 ms / 796 tokens ( 9.42 ms per token, 106.18 tokens per second) 14.37.241.617 I slot print_timing: id 1 | task 14090 | eval time = 42.27 ms / 2 tokens ( 42.27 ms per token, 23.66 tokens per second) 14.37.241.618 I slot print_timing: id 1 | task 14090 | total time = 7538.73 ms / 798 tokens 14.37.241.618 I slot print_timing: id 1 | task 14090 | graphs reused = 12477 14.37.241.619 I slot print_timing: id 1 | task 14090 | graph reallocs = 0 / 0 (same size) / (changed size) 14.37.241.649 I slot release: id 1 | task 14090 | stop processing: n_tokens = 797, truncated = 0 14.37.241.731 I slot print_timing: id 2 | task 14091 | prompt eval time = 7496.65 ms / 988 tokens ( 7.59 ms per token, 131.79 tokens per second) 14.37.241.733 I slot print_timing: id 2 | task 14091 | eval time = 42.13 ms / 2 tokens ( 42.13 ms per token, 23.74 tokens per second) 14.37.241.734 I slot print_timing: id 2 | task 14091 | total time = 7538.78 ms / 990 tokens 14.37.241.734 I slot print_timing: id 2 | task 14091 | graphs reused = 12477 14.37.241.734 I slot print_timing: id 2 | task 14091 | graph reallocs = 0 / 0 (same size) / (changed size) 14.37.242.596 I slot release: id 2 | task 14091 | stop processing: n_tokens = 989, truncated = 0 14.37.242.700 I slot print_timing: id 3 | task 14092 | prompt eval time = 7496.70 ms / 998 tokens ( 7.51 ms per token, 133.13 tokens per second) 14.37.242.702 I slot print_timing: id 3 | task 14092 | eval time = 42.97 ms / 2 tokens ( 42.97 ms per token, 23.27 tokens per second) 14.37.242.702 I slot print_timing: id 3 | task 14092 | total time = 7539.67 ms / 1000 tokens 14.37.242.702 I slot print_timing: id 3 | task 14092 | graphs reused = 12477 14.37.242.703 I slot print_timing: id 3 | task 14092 | graph reallocs = 0 / 0 (same size) / (changed size) 14.37.242.722 I slot release: id 3 | task 14092 | stop processing: n_tokens = 999, truncated = 0 14.37.255.808 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.892 14.37.255.932 I slot launch_slot_: id 3 | task 14100 | processing task, is_child = 0 14.37.256.017 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 160.873 MiB) 14.37.285.231 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.087 MiB) 14.37.312.437 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 147.212 MiB) 14.37.367.540 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.900 14.37.367.646 I slot launch_slot_: id 2 | task 14101 | processing task, is_child = 0 14.37.367.789 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 786, t_last = 349885988513 14.37.369.538 I slot launch_slot_: id 0 | task 14102 | processing task, is_child = 0 14.37.369.610 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 349885988644 14.37.369.708 I slot launch_slot_: id 1 | task 14103 | processing task, is_child = 0 14.39.717.873 I slot print_timing: id 2 | task 14101 | prompt eval time = 1808.30 ms / 95 tokens ( 19.03 ms per token, 52.54 tokens per second) 14.39.717.879 I slot print_timing: id 2 | task 14101 | eval time = 511.03 ms / 2 tokens ( 511.03 ms per token, 1.96 tokens per second) 14.39.717.879 I slot print_timing: id 2 | task 14101 | total time = 2319.33 ms / 97 tokens 14.39.717.880 I slot print_timing: id 2 | task 14101 | graphs reused = 12477 14.39.717.880 I slot print_timing: id 2 | task 14101 | graph reallocs = 0 / 0 (same size) / (changed size) 14.39.717.933 I slot release: id 2 | task 14101 | stop processing: n_tokens = 986, truncated = 0 14.39.718.070 I slot print_timing: id 3 | task 14100 | prompt eval time = 1807.27 ms / 86 tokens ( 21.01 ms per token, 47.59 tokens per second) 14.39.718.074 I slot print_timing: id 3 | task 14100 | eval time = 511.10 ms / 2 tokens ( 511.10 ms per token, 1.96 tokens per second) 14.39.718.075 I slot print_timing: id 3 | task 14100 | total time = 2318.37 ms / 88 tokens 14.39.718.075 I slot print_timing: id 3 | task 14100 | graphs reused = 12477 14.39.718.075 I slot print_timing: id 3 | task 14100 | graph reallocs = 0 / 0 (same size) / (changed size) 14.39.718.117 I slot release: id 3 | task 14100 | stop processing: n_tokens = 978, truncated = 0 14.40.469.237 I slot print_timing: id 0 | task 14102 | prompt eval time = 2348.04 ms / 163 tokens ( 14.41 ms per token, 69.42 tokens per second) 14.40.469.239 I slot print_timing: id 0 | task 14102 | eval time = 751.48 ms / 2 tokens ( 751.48 ms per token, 1.33 tokens per second) 14.40.469.239 I slot print_timing: id 0 | task 14102 | total time = 3099.52 ms / 165 tokens 14.40.469.240 I slot print_timing: id 0 | task 14102 | graphs reused = 12477 14.40.469.240 I slot print_timing: id 0 | task 14102 | graph reallocs = 0 / 0 (same size) / (changed size) 14.40.469.302 I slot release: id 0 | task 14102 | stop processing: n_tokens = 987, truncated = 0 14.40.469.311 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.903 14.40.469.411 I slot launch_slot_: id 0 | task 14108 | processing task, is_child = 0 14.40.508.024 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 147.403 MiB) 14.40.508.049 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.427 MiB) 14.40.603.994 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.904 14.40.604.138 I slot launch_slot_: id 2 | task 14109 | processing task, is_child = 0 14.40.604.223 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.911 14.40.604.274 I slot launch_slot_: id 3 | task 14110 | processing task, is_child = 0 14.40.609.877 I slot print_timing: id 1 | task 14103 | prompt processing, n_tokens = 824, progress = 0.83, t = 3.07 s / 268.34 tokens per second 14.41.843.598 I slot print_timing: id 1 | task 14103 | prompt processing, n_tokens = 987, progress = 1.00, t = 4.35 s / 226.74 tokens per second 14.42.013.730 I slot print_timing: id 0 | task 14108 | prompt eval time = 1367.00 ms / 98 tokens ( 13.95 ms per token, 71.69 tokens per second) 14.42.013.732 I slot print_timing: id 0 | task 14108 | eval time = 42.44 ms / 2 tokens ( 42.44 ms per token, 23.56 tokens per second) 14.42.013.732 I slot print_timing: id 0 | task 14108 | total time = 1409.44 ms / 100 tokens 14.42.013.733 I slot print_timing: id 0 | task 14108 | graphs reused = 12477 14.42.013.733 I slot print_timing: id 0 | task 14108 | graph reallocs = 0 / 0 (same size) / (changed size) 14.42.013.794 I slot release: id 0 | task 14108 | stop processing: n_tokens = 990, truncated = 0 14.42.013.884 I slot print_timing: id 1 | task 14103 | prompt eval time = 4573.06 ms / 991 tokens ( 4.61 ms per token, 216.70 tokens per second) 14.42.013.887 I slot print_timing: id 1 | task 14103 | eval time = 42.40 ms / 2 tokens ( 42.40 ms per token, 23.58 tokens per second) 14.42.013.888 I slot print_timing: id 1 | task 14103 | total time = 4615.47 ms / 993 tokens 14.42.013.888 I slot print_timing: id 1 | task 14103 | graphs reused = 12477 14.42.013.889 I slot print_timing: id 1 | task 14103 | graph reallocs = 0 / 0 (same size) / (changed size) 14.42.013.925 I slot release: id 1 | task 14103 | stop processing: n_tokens = 992, truncated = 0 14.42.014.015 I slot print_timing: id 2 | task 14109 | prompt eval time = 1325.05 ms / 88 tokens ( 15.06 ms per token, 66.41 tokens per second) 14.42.014.018 I slot print_timing: id 2 | task 14109 | eval time = 42.42 ms / 2 tokens ( 42.42 ms per token, 23.57 tokens per second) 14.42.014.018 I slot print_timing: id 2 | task 14109 | total time = 1367.47 ms / 90 tokens 14.42.014.019 I slot print_timing: id 2 | task 14109 | graphs reused = 12477 14.42.014.019 I slot print_timing: id 2 | task 14109 | graph reallocs = 0 / 0 (same size) / (changed size) 14.42.014.058 I slot release: id 2 | task 14109 | stop processing: n_tokens = 980, truncated = 0 14.42.014.158 I slot print_timing: id 3 | task 14110 | prompt eval time = 1323.98 ms / 103 tokens ( 12.85 ms per token, 77.80 tokens per second) 14.42.014.161 I slot print_timing: id 3 | task 14110 | eval time = 42.44 ms / 2 tokens ( 42.44 ms per token, 23.56 tokens per second) 14.42.014.161 I slot print_timing: id 3 | task 14110 | total time = 1366.42 ms / 105 tokens 14.42.014.161 I slot print_timing: id 3 | task 14110 | graphs reused = 12477 14.42.014.162 I slot print_timing: id 3 | task 14110 | graph reallocs = 0 / 0 (same size) / (changed size) 14.42.015.199 I slot release: id 3 | task 14110 | stop processing: n_tokens = 995, truncated = 0 14.42.025.202 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.900 14.42.025.315 I slot launch_slot_: id 0 | task 14114 | processing task, is_child = 0 14.42.102.228 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.561 MiB) 14.42.102.255 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 153.803 MiB) 14.42.179.906 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 190.875 MiB) 14.42.364.329 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.898 14.42.364.452 I slot launch_slot_: id 1 | task 14115 | processing task, is_child = 0 14.42.364.612 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.909 14.42.364.669 I slot launch_slot_: id 2 | task 14116 | processing task, is_child = 0 14.42.364.735 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.895 14.42.364.778 I slot launch_slot_: id 3 | task 14117 | processing task, is_child = 0 14.43.354.550 I slot print_timing: id 0 | task 14114 | prompt eval time = 946.83 ms / 92 tokens ( 10.29 ms per token, 97.17 tokens per second) 14.43.354.553 I slot print_timing: id 0 | task 14114 | eval time = 42.92 ms / 2 tokens ( 42.92 ms per token, 23.30 tokens per second) 14.43.354.554 I slot print_timing: id 0 | task 14114 | total time = 989.76 ms / 94 tokens 14.43.354.554 I slot print_timing: id 0 | task 14114 | graphs reused = 12477 14.43.354.555 I slot print_timing: id 0 | task 14114 | graph reallocs = 0 / 0 (same size) / (changed size) 14.43.354.610 I slot release: id 0 | task 14114 | stop processing: n_tokens = 984, truncated = 0 14.43.354.699 I slot print_timing: id 1 | task 14115 | prompt eval time = 944.28 ms / 91 tokens ( 10.38 ms per token, 96.37 tokens per second) 14.43.354.701 I slot print_timing: id 1 | task 14115 | eval time = 42.93 ms / 2 tokens ( 42.93 ms per token, 23.29 tokens per second) 14.43.354.701 I slot print_timing: id 1 | task 14115 | total time = 987.21 ms / 93 tokens 14.43.354.702 I slot print_timing: id 1 | task 14115 | graphs reused = 12477 14.43.354.702 I slot print_timing: id 1 | task 14115 | graph reallocs = 0 / 0 (same size) / (changed size) 14.43.354.730 I slot release: id 1 | task 14115 | stop processing: n_tokens = 983, truncated = 0 14.43.354.817 I slot print_timing: id 2 | task 14116 | prompt eval time = 943.53 ms / 96 tokens ( 9.83 ms per token, 101.75 tokens per second) 14.43.354.819 I slot print_timing: id 2 | task 14116 | eval time = 42.61 ms / 2 tokens ( 42.61 ms per token, 23.47 tokens per second) 14.43.354.820 I slot print_timing: id 2 | task 14116 | total time = 986.14 ms / 98 tokens 14.43.354.820 I slot print_timing: id 2 | task 14116 | graphs reused = 12477 14.43.354.820 I slot print_timing: id 2 | task 14116 | graph reallocs = 0 / 0 (same size) / (changed size) 14.43.354.862 I slot release: id 2 | task 14116 | stop processing: n_tokens = 988, truncated = 0 14.43.354.953 I slot print_timing: id 3 | task 14117 | prompt eval time = 942.50 ms / 99 tokens ( 9.52 ms per token, 105.04 tokens per second) 14.43.354.957 I slot print_timing: id 3 | task 14117 | eval time = 42.60 ms / 2 tokens ( 42.60 ms per token, 23.47 tokens per second) 14.43.354.957 I slot print_timing: id 3 | task 14117 | total time = 985.10 ms / 101 tokens 14.43.354.959 I slot print_timing: id 3 | task 14117 | graphs reused = 12477 14.43.354.959 I slot print_timing: id 3 | task 14117 | graph reallocs = 0 / 0 (same size) / (changed size) 14.43.355.006 I slot release: id 3 | task 14117 | stop processing: n_tokens = 991, truncated = 0 14.43.366.263 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.905 14.43.366.375 I slot launch_slot_: id 0 | task 14121 | processing task, is_child = 0 14.43.366.455 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 154.282 MiB) 14.43.427.104 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 154.665 MiB) 14.43.427.128 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 181.687 MiB) 14.43.472.962 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 183.438 MiB) 14.43.509.302 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.906 14.43.509.392 I slot launch_slot_: id 1 | task 14122 | processing task, is_child = 0 14.43.509.540 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 349892101857 14.43.509.654 I slot launch_slot_: id 2 | task 14123 | processing task, is_child = 0 14.43.509.727 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 349892102001 14.43.509.839 I slot launch_slot_: id 3 | task 14124 | processing task, is_child = 0 14.45.692.364 I slot print_timing: id 0 | task 14121 | prompt eval time = 1850.77 ms / 94 tokens ( 19.69 ms per token, 50.79 tokens per second) 14.45.692.367 I slot print_timing: id 0 | task 14121 | eval time = 331.74 ms / 2 tokens ( 331.74 ms per token, 3.01 tokens per second) 14.45.692.367 I slot print_timing: id 0 | task 14121 | total time = 2182.51 ms / 96 tokens 14.45.692.368 I slot print_timing: id 0 | task 14121 | graphs reused = 12477 14.45.692.368 I slot print_timing: id 0 | task 14121 | graph reallocs = 0 / 0 (same size) / (changed size) 14.45.692.412 I slot release: id 0 | task 14121 | stop processing: n_tokens = 986, truncated = 0 14.45.692.553 I slot print_timing: id 1 | task 14122 | prompt eval time = 1849.19 ms / 95 tokens ( 19.47 ms per token, 51.37 tokens per second) 14.45.692.555 I slot print_timing: id 1 | task 14122 | eval time = 331.79 ms / 2 tokens ( 331.79 ms per token, 3.01 tokens per second) 14.45.692.555 I slot print_timing: id 1 | task 14122 | total time = 2180.98 ms / 97 tokens 14.45.692.555 I slot print_timing: id 1 | task 14122 | graphs reused = 12477 14.45.692.556 I slot print_timing: id 1 | task 14122 | graph reallocs = 0 / 0 (same size) / (changed size) 14.45.692.587 I slot release: id 1 | task 14122 | stop processing: n_tokens = 987, truncated = 0 14.47.058.178 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 349894439407 14.47.058.287 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 181.906 MiB) 14.47.135.086 I slot launch_slot_: id 0 | task 14129 | processing task, is_child = 0 14.47.135.225 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.651 MiB) 14.47.173.162 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 987, t_last = 349894439582 14.47.173.372 I slot launch_slot_: id 1 | task 14130 | processing task, is_child = 0 14.47.173.709 I slot print_timing: id 2 | task 14123 | prompt processing, n_tokens = 764, progress = 0.86, t = 3.55 s / 215.49 tokens per second 14.47.175.281 I slot print_timing: id 3 | task 14124 | prompt processing, n_tokens = 764, progress = 0.84, t = 3.55 s / 215.50 tokens per second 14.48.421.425 I slot print_timing: id 2 | task 14123 | prompt processing, n_tokens = 889, progress = 1.00, t = 4.83 s / 183.92 tokens per second 14.48.422.940 I slot print_timing: id 3 | task 14124 | prompt processing, n_tokens = 901, progress = 1.00, t = 4.83 s / 186.41 tokens per second 14.49.674.374 I slot print_timing: id 2 | task 14123 | prompt eval time = 5575.78 ms / 893 tokens ( 6.24 ms per token, 160.16 tokens per second) 14.49.674.377 I slot print_timing: id 2 | task 14123 | eval time = 585.81 ms / 2 tokens ( 585.81 ms per token, 1.71 tokens per second) 14.49.674.377 I slot print_timing: id 2 | task 14123 | total time = 6161.59 ms / 895 tokens 14.49.674.378 I slot print_timing: id 2 | task 14123 | graphs reused = 12477 14.49.674.378 I slot print_timing: id 2 | task 14123 | graph reallocs = 0 / 0 (same size) / (changed size) 14.49.674.553 I slot release: id 2 | task 14123 | stop processing: n_tokens = 894, truncated = 0 14.49.674.658 I slot print_timing: id 3 | task 14124 | prompt eval time = 5575.80 ms / 905 tokens ( 6.16 ms per token, 162.31 tokens per second) 14.49.674.660 I slot print_timing: id 3 | task 14124 | eval time = 585.93 ms / 2 tokens ( 585.93 ms per token, 1.71 tokens per second) 14.49.674.660 I slot print_timing: id 3 | task 14124 | total time = 6161.73 ms / 907 tokens 14.49.674.661 I slot print_timing: id 3 | task 14124 | graphs reused = 12477 14.49.674.661 I slot print_timing: id 3 | task 14124 | graph reallocs = 0 / 0 (same size) / (changed size) 14.49.674.701 I slot release: id 3 | task 14124 | stop processing: n_tokens = 906, truncated = 0 14.50.897.688 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.883 14.50.897.803 I slot launch_slot_: id 2 | task 14135 | processing task, is_child = 0 14.50.897.903 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.583 MiB) 14.51.046.970 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.864 (> 0.100 thold), f_keep = 0.871 14.51.047.111 I slot launch_slot_: id 3 | task 14136 | processing task, is_child = 0 14.51.047.124 I slot print_timing: id 0 | task 14129 | prompt processing, n_tokens = 764, progress = 0.81, t = 3.72 s / 205.14 tokens per second 14.51.076.596 I slot print_timing: id 1 | task 14130 | prompt processing, n_tokens = 764, progress = 0.79, t = 3.72 s / 205.15 tokens per second 14.52.433.325 I slot print_timing: id 0 | task 14129 | prompt processing, n_tokens = 937, progress = 1.00, t = 5.26 s / 178.14 tokens per second 14.52.529.757 I slot print_timing: id 1 | task 14130 | prompt processing, n_tokens = 964, progress = 1.00, t = 5.26 s / 183.28 tokens per second 14.52.690.629 I slot print_timing: id 0 | task 14129 | prompt eval time = 5474.99 ms / 941 tokens ( 5.82 ms per token, 171.87 tokens per second) 14.52.690.631 I slot print_timing: id 0 | task 14129 | eval time = 42.25 ms / 2 tokens ( 42.25 ms per token, 23.67 tokens per second) 14.52.690.632 I slot print_timing: id 0 | task 14129 | total time = 5517.24 ms / 943 tokens 14.52.690.632 I slot print_timing: id 0 | task 14129 | graphs reused = 12477 14.52.690.633 I slot print_timing: id 0 | task 14129 | graph reallocs = 0 / 0 (same size) / (changed size) 14.52.690.729 I slot release: id 0 | task 14129 | stop processing: n_tokens = 942, truncated = 0 14.52.690.827 I slot print_timing: id 1 | task 14130 | prompt eval time = 5474.92 ms / 968 tokens ( 5.66 ms per token, 176.81 tokens per second) 14.52.690.830 I slot print_timing: id 1 | task 14130 | eval time = 42.35 ms / 2 tokens ( 42.35 ms per token, 23.61 tokens per second) 14.52.690.830 I slot print_timing: id 1 | task 14130 | total time = 5517.27 ms / 970 tokens 14.52.690.831 I slot print_timing: id 1 | task 14130 | graphs reused = 12477 14.52.690.831 I slot print_timing: id 1 | task 14130 | graph reallocs = 0 / 0 (same size) / (changed size) 14.52.691.870 I slot release: id 1 | task 14130 | stop processing: n_tokens = 969, truncated = 0 14.52.691.978 I slot print_timing: id 2 | task 14135 | prompt eval time = 1564.20 ms / 108 tokens ( 14.48 ms per token, 69.04 tokens per second) 14.52.691.981 I slot print_timing: id 2 | task 14135 | eval time = 43.33 ms / 2 tokens ( 43.33 ms per token, 23.08 tokens per second) 14.52.691.982 I slot print_timing: id 2 | task 14135 | total time = 1607.52 ms / 110 tokens 14.52.691.982 I slot print_timing: id 2 | task 14135 | graphs reused = 12477 14.52.691.982 I slot print_timing: id 2 | task 14135 | graph reallocs = 0 / 0 (same size) / (changed size) 14.52.692.055 I slot release: id 2 | task 14135 | stop processing: n_tokens = 898, truncated = 0 14.52.692.161 I slot print_timing: id 3 | task 14136 | prompt eval time = 1562.83 ms / 124 tokens ( 12.60 ms per token, 79.34 tokens per second) 14.52.692.164 I slot print_timing: id 3 | task 14136 | eval time = 43.41 ms / 2 tokens ( 43.41 ms per token, 23.04 tokens per second) 14.52.692.164 I slot print_timing: id 3 | task 14136 | total time = 1606.23 ms / 126 tokens 14.52.692.165 I slot print_timing: id 3 | task 14136 | graphs reused = 12477 14.52.692.165 I slot print_timing: id 3 | task 14136 | graph reallocs = 0 / 0 (same size) / (changed size) 14.52.692.198 I slot release: id 3 | task 14136 | stop processing: n_tokens = 914, truncated = 0 14.52.701.350 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 942, t_last = 349901437725 14.52.701.425 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.168 MiB) 14.52.730.164 I slot launch_slot_: id 0 | task 14140 | processing task, is_child = 0 14.52.770.831 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 199.030 MiB) 14.52.803.705 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.540 MiB) 14.52.842.803 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 969, t_last = 349901438866 14.52.842.999 I slot launch_slot_: id 1 | task 14141 | processing task, is_child = 0 14.52.843.132 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 898, t_last = 349901439051 14.52.843.236 I slot launch_slot_: id 2 | task 14142 | processing task, is_child = 0 14.52.843.302 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 914, t_last = 349901439193 14.52.843.403 I slot launch_slot_: id 3 | task 14143 | processing task, is_child = 0 14.56.948.804 I slot print_timing: id 0 | task 14140 | prompt processing, n_tokens = 536, progress = 0.85, t = 4.11 s / 130.56 tokens per second 14.57.016.280 I slot print_timing: id 1 | task 14141 | prompt processing, n_tokens = 536, progress = 0.83, t = 4.11 s / 130.57 tokens per second 14.57.018.619 I slot print_timing: id 2 | task 14142 | prompt processing, n_tokens = 536, progress = 0.82, t = 4.11 s / 130.57 tokens per second 14.57.021.064 I slot print_timing: id 3 | task 14143 | prompt processing, n_tokens = 536, progress = 0.77, t = 4.10 s / 130.57 tokens per second 14.58.096.595 I slot print_timing: id 0 | task 14140 | prompt processing, n_tokens = 623, progress = 0.99, t = 5.25 s / 118.60 tokens per second 14.58.332.812 I slot print_timing: id 1 | task 14141 | prompt processing, n_tokens = 639, progress = 0.99, t = 5.25 s / 121.64 tokens per second 14.58.335.170 I slot print_timing: id 2 | task 14142 | prompt processing, n_tokens = 648, progress = 0.99, t = 5.25 s / 123.36 tokens per second 14.58.336.421 I slot print_timing: id 3 | task 14143 | prompt processing, n_tokens = 692, progress = 0.99, t = 5.25 s / 131.74 tokens per second 14.58.483.355 I slot print_timing: id 0 | task 14140 | prompt eval time = 5598.14 ms / 627 tokens ( 8.93 ms per token, 112.00 tokens per second) 14.58.483.358 I slot print_timing: id 0 | task 14140 | eval time = 41.79 ms / 2 tokens ( 41.79 ms per token, 23.93 tokens per second) 14.58.483.358 I slot print_timing: id 0 | task 14140 | total time = 5639.94 ms / 629 tokens 14.58.483.359 I slot print_timing: id 0 | task 14140 | graphs reused = 12478 14.58.483.359 I slot print_timing: id 0 | task 14140 | graph reallocs = 0 / 0 (same size) / (changed size) 14.58.483.476 I slot release: id 0 | task 14140 | stop processing: n_tokens = 628, truncated = 0 14.58.483.575 I slot print_timing: id 1 | task 14141 | prompt eval time = 5598.09 ms / 643 tokens ( 8.71 ms per token, 114.86 tokens per second) 14.58.483.579 I slot print_timing: id 1 | task 14141 | eval time = 41.92 ms / 2 tokens ( 41.92 ms per token, 23.85 tokens per second) 14.58.483.580 I slot print_timing: id 1 | task 14141 | total time = 5640.01 ms / 645 tokens 14.58.483.580 I slot print_timing: id 1 | task 14141 | graphs reused = 12478 14.58.483.581 I slot print_timing: id 1 | task 14141 | graph reallocs = 0 / 0 (same size) / (changed size) 14.58.483.603 I slot release: id 1 | task 14141 | stop processing: n_tokens = 644, truncated = 0 14.58.483.705 I slot print_timing: id 2 | task 14142 | prompt eval time = 5598.16 ms / 652 tokens ( 8.59 ms per token, 116.47 tokens per second) 14.58.483.707 I slot print_timing: id 2 | task 14142 | eval time = 41.85 ms / 2 tokens ( 41.85 ms per token, 23.89 tokens per second) 14.58.483.708 I slot print_timing: id 2 | task 14142 | total time = 5640.01 ms / 654 tokens 14.58.483.708 I slot print_timing: id 2 | task 14142 | graphs reused = 12478 14.58.483.708 I slot print_timing: id 2 | task 14142 | graph reallocs = 0 / 0 (same size) / (changed size) 14.58.483.730 I slot release: id 2 | task 14142 | stop processing: n_tokens = 653, truncated = 0 14.58.483.821 I slot print_timing: id 3 | task 14143 | prompt eval time = 5598.12 ms / 696 tokens ( 8.04 ms per token, 124.33 tokens per second) 14.58.483.827 I slot print_timing: id 3 | task 14143 | eval time = 41.87 ms / 2 tokens ( 41.87 ms per token, 23.88 tokens per second) 14.58.483.828 I slot print_timing: id 3 | task 14143 | total time = 5639.99 ms / 698 tokens 14.58.483.828 I slot print_timing: id 3 | task 14143 | graphs reused = 12478 14.58.483.828 I slot print_timing: id 3 | task 14143 | graph reallocs = 0 / 0 (same size) / (changed size) 14.58.483.848 I slot release: id 3 | task 14143 | stop processing: n_tokens = 697, truncated = 0 14.58.495.177 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.858 (> 0.100 thold), f_keep = 0.893 14.58.495.219 I slot launch_slot_: id 0 | task 14150 | processing task, is_child = 0 14.58.495.283 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 204.063 MiB) 14.58.540.741 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 199.194 MiB) 14.58.572.922 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.889 (> 0.100 thold), f_keep = 0.871 14.58.573.039 I slot launch_slot_: id 1 | task 14151 | processing task, is_child = 0 14.58.573.163 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.862 14.58.573.212 I slot launch_slot_: id 2 | task 14152 | processing task, is_child = 0 14.58.573.269 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.805 14.58.573.319 I slot launch_slot_: id 3 | task 14153 | processing task, is_child = 0 14.59.579.040 I slot print_timing: id 0 | task 14150 | prompt eval time = 963.86 ms / 93 tokens ( 10.36 ms per token, 96.49 tokens per second) 14.59.579.044 I slot print_timing: id 0 | task 14150 | eval time = 41.85 ms / 2 tokens ( 41.85 ms per token, 23.90 tokens per second) 14.59.579.044 I slot print_timing: id 0 | task 14150 | total time = 1005.71 ms / 95 tokens 14.59.579.045 I slot print_timing: id 0 | task 14150 | graphs reused = 12478 14.59.579.045 I slot print_timing: id 0 | task 14150 | graph reallocs = 0 / 0 (same size) / (changed size) 14.59.579.080 I slot release: id 0 | task 14150 | stop processing: n_tokens = 655, truncated = 0 14.59.579.164 I slot print_timing: id 1 | task 14151 | prompt eval time = 962.83 ms / 70 tokens ( 13.75 ms per token, 72.70 tokens per second) 14.59.579.167 I slot print_timing: id 1 | task 14151 | eval time = 41.87 ms / 2 tokens ( 41.87 ms per token, 23.88 tokens per second) 14.59.579.167 I slot print_timing: id 1 | task 14151 | total time = 1004.70 ms / 72 tokens 14.59.579.168 I slot print_timing: id 1 | task 14151 | graphs reused = 12478 14.59.579.168 I slot print_timing: id 1 | task 14151 | graph reallocs = 0 / 0 (same size) / (changed size) 14.59.579.264 I slot release: id 1 | task 14151 | stop processing: n_tokens = 632, truncated = 0 14.59.579.348 I slot print_timing: id 2 | task 14152 | prompt eval time = 961.81 ms / 75 tokens ( 12.82 ms per token, 77.98 tokens per second) 14.59.579.350 I slot print_timing: id 2 | task 14152 | eval time = 41.96 ms / 2 tokens ( 41.96 ms per token, 23.83 tokens per second) 14.59.579.351 I slot print_timing: id 2 | task 14152 | total time = 1003.77 ms / 77 tokens 14.59.579.351 I slot print_timing: id 2 | task 14152 | graphs reused = 12478 14.59.579.351 I slot print_timing: id 2 | task 14152 | graph reallocs = 0 / 0 (same size) / (changed size) 14.59.579.366 I slot release: id 2 | task 14152 | stop processing: n_tokens = 639, truncated = 0 14.59.579.459 I slot print_timing: id 3 | task 14153 | prompt eval time = 960.76 ms / 83 tokens ( 11.58 ms per token, 86.39 tokens per second) 14.59.579.460 I slot print_timing: id 3 | task 14153 | eval time = 41.95 ms / 2 tokens ( 41.95 ms per token, 23.84 tokens per second) 14.59.579.460 I slot print_timing: id 3 | task 14153 | total time = 1002.70 ms / 85 tokens 14.59.579.460 I slot print_timing: id 3 | task 14153 | graphs reused = 12478 14.59.579.461 I slot print_timing: id 3 | task 14153 | graph reallocs = 0 / 0 (same size) / (changed size) 14.59.579.474 I slot release: id 3 | task 14153 | stop processing: n_tokens = 645, truncated = 0 14.59.590.813 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.856 14.59.590.896 I slot launch_slot_: id 0 | task 14157 | processing task, is_child = 0 14.59.590.957 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 232.382 MiB) 14.59.613.091 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 138.843 MiB) 14.59.636.129 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 141.140 MiB) 14.59.667.537 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 349908326260 14.59.667.702 I slot launch_slot_: id 1 | task 14158 | processing task, is_child = 0 14.59.667.827 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 639, t_last = 349908326361 14.59.667.924 I slot launch_slot_: id 2 | task 14159 | processing task, is_child = 0 14.59.667.980 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 645, t_last = 349908326469 14.59.668.085 I slot launch_slot_: id 3 | task 14160 | processing task, is_child = 0 15.01.882.145 I slot print_timing: id 0 | task 14157 | prompt eval time = 1850.27 ms / 84 tokens ( 22.03 ms per token, 45.40 tokens per second) 15.01.882.148 I slot print_timing: id 0 | task 14157 | eval time = 363.78 ms / 2 tokens ( 363.78 ms per token, 2.75 tokens per second) 15.01.882.148 I slot print_timing: id 0 | task 14157 | total time = 2214.05 ms / 86 tokens 15.01.882.149 I slot print_timing: id 0 | task 14157 | graphs reused = 12478 15.01.882.149 I slot print_timing: id 0 | task 14157 | graph reallocs = 0 / 0 (same size) / (changed size) 15.01.882.193 I slot release: id 0 | task 14157 | stop processing: n_tokens = 646, truncated = 0 15.03.940.221 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 349910629188 15.03.940.353 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 142.193 MiB) 15.04.074.142 I slot launch_slot_: id 0 | task 14165 | processing task, is_child = 0 15.04.074.601 I slot print_timing: id 1 | task 14158 | prompt processing, n_tokens = 706, progress = 0.85, t = 4.27 s / 165.30 tokens per second 15.04.078.354 I slot print_timing: id 2 | task 14159 | prompt processing, n_tokens = 706, progress = 0.83, t = 4.27 s / 165.31 tokens per second 15.04.081.228 I slot print_timing: id 3 | task 14160 | prompt processing, n_tokens = 706, progress = 0.82, t = 4.27 s / 165.31 tokens per second 15.05.304.903 I slot print_timing: id 1 | task 14158 | prompt processing, n_tokens = 823, progress = 1.00, t = 5.59 s / 147.30 tokens per second 15.05.310.459 I slot print_timing: id 2 | task 14159 | prompt processing, n_tokens = 845, progress = 1.00, t = 5.59 s / 151.24 tokens per second 15.05.314.454 I slot print_timing: id 3 | task 14160 | prompt processing, n_tokens = 852, progress = 1.00, t = 5.59 s / 152.50 tokens per second 15.06.252.370 I slot print_timing: id 1 | task 14158 | prompt eval time = 6205.58 ms / 827 tokens ( 7.50 ms per token, 133.27 tokens per second) 15.06.252.373 I slot print_timing: id 1 | task 14158 | eval time = 377.55 ms / 2 tokens ( 377.55 ms per token, 2.65 tokens per second) 15.06.252.374 I slot print_timing: id 1 | task 14158 | total time = 6583.12 ms / 829 tokens 15.06.252.374 I slot print_timing: id 1 | task 14158 | graphs reused = 12478 15.06.252.375 I slot print_timing: id 1 | task 14158 | graph reallocs = 0 / 0 (same size) / (changed size) 15.06.252.492 I slot release: id 1 | task 14158 | stop processing: n_tokens = 828, truncated = 0 15.06.252.586 I slot print_timing: id 2 | task 14159 | prompt eval time = 6205.70 ms / 849 tokens ( 7.31 ms per token, 136.81 tokens per second) 15.06.252.592 I slot print_timing: id 2 | task 14159 | eval time = 377.55 ms / 2 tokens ( 377.55 ms per token, 2.65 tokens per second) 15.06.252.592 I slot print_timing: id 2 | task 14159 | total time = 6583.26 ms / 851 tokens 15.06.252.592 I slot print_timing: id 2 | task 14159 | graphs reused = 12478 15.06.252.593 I slot print_timing: id 2 | task 14159 | graph reallocs = 0 / 0 (same size) / (changed size) 15.06.252.636 I slot release: id 2 | task 14159 | stop processing: n_tokens = 850, truncated = 0 15.06.252.735 I slot print_timing: id 3 | task 14160 | prompt eval time = 6205.82 ms / 856 tokens ( 7.25 ms per token, 137.94 tokens per second) 15.06.252.738 I slot print_timing: id 3 | task 14160 | eval time = 377.50 ms / 2 tokens ( 377.50 ms per token, 2.65 tokens per second) 15.06.252.739 I slot print_timing: id 3 | task 14160 | total time = 6583.32 ms / 858 tokens 15.06.252.739 I slot print_timing: id 3 | task 14160 | graphs reused = 12478 15.06.252.739 I slot print_timing: id 3 | task 14160 | graph reallocs = 0 / 0 (same size) / (changed size) 15.06.252.786 I slot release: id 3 | task 14160 | stop processing: n_tokens = 857, truncated = 0 15.06.895.915 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 349914999488 15.06.895.992 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 138.938 MiB) 15.06.896.004 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 175.969 MiB) 15.07.417.185 I slot launch_slot_: id 1 | task 14171 | processing task, is_child = 0 15.07.417.277 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.108 MiB) 15.07.460.700 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 171.704 MiB) 15.07.481.277 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 850, t_last = 349914999632 15.07.481.467 I slot launch_slot_: id 2 | task 14172 | processing task, is_child = 0 15.07.481.533 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 857, t_last = 349914999782 15.07.481.653 I slot launch_slot_: id 3 | task 14173 | processing task, is_child = 0 15.09.922.901 I slot print_timing: id 0 | task 14165 | prompt eval time = 4738.20 ms / 912 tokens ( 5.20 ms per token, 192.48 tokens per second) 15.09.922.904 I slot print_timing: id 0 | task 14165 | eval time = 1110.48 ms / 2 tokens ( 1110.48 ms per token, 0.90 tokens per second) 15.09.922.905 I slot print_timing: id 0 | task 14165 | total time = 5848.68 ms / 914 tokens 15.09.922.905 I slot print_timing: id 0 | task 14165 | graphs reused = 12478 15.09.922.905 I slot print_timing: id 0 | task 14165 | graph reallocs = 0 / 0 (same size) / (changed size) 15.09.922.977 I slot release: id 0 | task 14165 | stop processing: n_tokens = 913, truncated = 0 15.11.814.795 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 913, t_last = 349918669974 15.11.814.890 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.446 MiB) 15.12.205.102 I slot launch_slot_: id 0 | task 14177 | processing task, is_child = 0 15.12.205.273 I slot print_timing: id 1 | task 14171 | prompt processing, n_tokens = 454, progress = 0.47, t = 4.33 s / 104.93 tokens per second 15.12.207.178 I slot print_timing: id 2 | task 14172 | prompt processing, n_tokens = 463, progress = 0.47, t = 4.33 s / 107.01 tokens per second 15.12.208.190 I slot print_timing: id 3 | task 14173 | prompt processing, n_tokens = 1419, progress = 0.73, t = 4.33 s / 327.98 tokens per second 15.14.755.983 I slot print_timing: id 1 | task 14171 | prompt processing, n_tokens = 832, progress = 0.86, t = 7.20 s / 115.48 tokens per second 15.14.758.121 I slot print_timing: id 2 | task 14172 | prompt processing, n_tokens = 832, progress = 0.85, t = 7.20 s / 115.48 tokens per second 15.14.760.608 I slot print_timing: id 3 | task 14173 | prompt processing, n_tokens = 1634, progress = 0.84, t = 7.20 s / 226.80 tokens per second 15.16.311.753 I slot print_timing: id 0 | task 14177 | prompt processing, n_tokens = 598, progress = 0.31, t = 4.11 s / 145.62 tokens per second 15.16.311.779 I slot print_timing: id 1 | task 14171 | prompt processing, n_tokens = 966, progress = 1.00, t = 8.82 s / 109.48 tokens per second 15.16.761.095 I slot print_timing: id 2 | task 14172 | prompt processing, n_tokens = 975, progress = 1.00, t = 8.82 s / 110.50 tokens per second 15.16.765.615 I slot print_timing: id 3 | task 14173 | prompt processing, n_tokens = 1931, progress = 1.00, t = 8.82 s / 218.85 tokens per second 15.18.405.921 I slot print_timing: id 0 | task 14177 | prompt processing, n_tokens = 1431, progress = 0.73, t = 6.20 s / 230.79 tokens per second 15.18.980.446 I slot print_timing: id 1 | task 14171 | prompt eval time = 10917.57 ms / 970 tokens ( 11.26 ms per token, 88.85 tokens per second) 15.18.980.451 I slot print_timing: id 1 | task 14171 | eval time = 574.82 ms / 2 tokens ( 574.82 ms per token, 1.74 tokens per second) 15.18.980.451 I slot print_timing: id 1 | task 14171 | total time = 11492.39 ms / 972 tokens 15.18.980.452 I slot print_timing: id 1 | task 14171 | graphs reused = 12478 15.18.980.452 I slot print_timing: id 1 | task 14171 | graph reallocs = 0 / 0 (same size) / (changed size) 15.18.980.527 I slot release: id 1 | task 14171 | stop processing: n_tokens = 971, truncated = 0 15.18.980.679 I slot print_timing: id 2 | task 14172 | prompt eval time = 10917.61 ms / 979 tokens ( 11.15 ms per token, 89.67 tokens per second) 15.18.980.681 I slot print_timing: id 2 | task 14172 | eval time = 574.91 ms / 2 tokens ( 574.91 ms per token, 1.74 tokens per second) 15.18.980.681 I slot print_timing: id 2 | task 14172 | total time = 11492.52 ms / 981 tokens 15.18.980.682 I slot print_timing: id 2 | task 14172 | graphs reused = 12478 15.18.980.686 I slot print_timing: id 2 | task 14172 | graph reallocs = 0 / 0 (same size) / (changed size) 15.18.980.713 I slot release: id 2 | task 14172 | stop processing: n_tokens = 980, truncated = 0 15.18.980.864 I slot print_timing: id 3 | task 14173 | prompt eval time = 10917.65 ms / 1935 tokens ( 5.64 ms per token, 177.24 tokens per second) 15.18.980.871 I slot print_timing: id 3 | task 14173 | eval time = 574.95 ms / 2 tokens ( 574.95 ms per token, 1.74 tokens per second) 15.18.980.871 I slot print_timing: id 3 | task 14173 | total time = 11492.60 ms / 1937 tokens 15.18.980.871 I slot print_timing: id 3 | task 14173 | graphs reused = 12478 15.18.980.872 I slot print_timing: id 3 | task 14173 | graph reallocs = 0 / 0 (same size) / (changed size) 15.18.982.216 I slot release: id 3 | task 14173 | stop processing: n_tokens = 1936, truncated = 0 15.18.982.231 I slot print_timing: id 0 | task 14177 | prompt processing, n_tokens = 1634, progress = 0.84, t = 6.78 s / 241.17 tokens per second 15.18.993.329 I slot print_timing: id 0 | task 14177 | prompt processing, n_tokens = 1943, progress = 1.00, t = 6.79 s / 286.23 tokens per second 15.19.701.172 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.857 15.19.701.256 I slot launch_slot_: id 3 | task 14184 | processing task, is_child = 0 15.19.701.340 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.829 MiB) 15.19.749.143 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 149.632 MiB) 15.19.795.073 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 971, t_last = 349927727523 15.19.795.247 I slot launch_slot_: id 1 | task 14185 | processing task, is_child = 0 15.19.795.320 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 980, t_last = 349927727708 15.19.795.433 I slot launch_slot_: id 2 | task 14186 | processing task, is_child = 0 15.21.678.247 I slot print_timing: id 0 | task 14177 | prompt eval time = 7496.04 ms / 1947 tokens ( 3.85 ms per token, 259.74 tokens per second) 15.21.678.253 I slot print_timing: id 0 | task 14177 | eval time = 1977.08 ms / 2 tokens ( 1977.08 ms per token, 0.51 tokens per second) 15.21.678.254 I slot print_timing: id 0 | task 14177 | total time = 9473.11 ms / 1949 tokens 15.21.678.254 I slot print_timing: id 0 | task 14177 | graphs reused = 12478 15.21.678.255 I slot print_timing: id 0 | task 14177 | graph reallocs = 0 / 0 (same size) / (changed size) 15.21.678.349 I slot release: id 0 | task 14177 | stop processing: n_tokens = 1948, truncated = 0 15.22.591.169 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.836 (> 0.100 thold), f_keep = 0.852 15.22.591.276 I slot launch_slot_: id 0 | task 14189 | processing task, is_child = 0 15.26.231.752 I slot print_timing: id 3 | task 14184 | prompt eval time = 2795.47 ms / 253 tokens ( 11.05 ms per token, 90.50 tokens per second) 15.26.231.759 I slot print_timing: id 3 | task 14184 | eval time = 3640.59 ms / 2 tokens ( 3640.59 ms per token, 0.27 tokens per second) 15.26.231.759 I slot print_timing: id 3 | task 14184 | total time = 6436.05 ms / 255 tokens 15.26.231.760 I slot print_timing: id 3 | task 14184 | graphs reused = 12478 15.26.231.760 I slot print_timing: id 3 | task 14184 | graph reallocs = 0 / 0 (same size) / (changed size) 15.26.231.876 I slot release: id 3 | task 14184 | stop processing: n_tokens = 1914, truncated = 0 15.26.231.894 I slot print_timing: id 0 | task 14189 | prompt processing, n_tokens = 321, progress = 1.00, t = 3.64 s / 88.18 tokens per second 15.26.234.051 I slot print_timing: id 1 | task 14185 | prompt processing, n_tokens = 1375, progress = 0.73, t = 6.44 s / 213.64 tokens per second 15.26.236.581 I slot print_timing: id 2 | task 14186 | prompt processing, n_tokens = 1443, progress = 0.74, t = 6.44 s / 224.21 tokens per second 15.27.369.667 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.867 15.27.369.778 I slot launch_slot_: id 3 | task 14192 | processing task, is_child = 0 15.27.369.786 I slot print_timing: id 1 | task 14185 | prompt processing, n_tokens = 1634, progress = 0.86, t = 7.57 s / 215.74 tokens per second 15.27.371.613 I slot print_timing: id 2 | task 14186 | prompt processing, n_tokens = 1634, progress = 0.83, t = 7.57 s / 215.74 tokens per second 15.29.241.972 I slot print_timing: id 0 | task 14189 | prompt eval time = 4778.37 ms / 325 tokens ( 14.70 ms per token, 68.01 tokens per second) 15.29.241.974 I slot print_timing: id 0 | task 14189 | eval time = 1872.31 ms / 2 tokens ( 1872.31 ms per token, 0.53 tokens per second) 15.29.241.975 I slot print_timing: id 0 | task 14189 | total time = 6650.68 ms / 327 tokens 15.29.241.975 I slot print_timing: id 0 | task 14189 | graphs reused = 12478 15.29.241.976 I slot print_timing: id 0 | task 14189 | graph reallocs = 0 / 0 (same size) / (changed size) 15.29.242.091 I slot release: id 0 | task 14189 | stop processing: n_tokens = 1986, truncated = 0 15.29.242.105 I slot print_timing: id 1 | task 14185 | prompt processing, n_tokens = 1887, progress = 1.00, t = 9.45 s / 199.76 tokens per second 15.29.244.359 I slot print_timing: id 2 | task 14186 | prompt processing, n_tokens = 1955, progress = 1.00, t = 9.45 s / 206.96 tokens per second 15.29.346.208 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.832 (> 0.100 thold), f_keep = 0.836 15.29.346.340 I slot launch_slot_: id 0 | task 14195 | processing task, is_child = 0 15.30.085.690 I slot print_timing: id 1 | task 14185 | prompt eval time = 9550.51 ms / 1891 tokens ( 5.05 ms per token, 198.00 tokens per second) 15.30.085.694 I slot print_timing: id 1 | task 14185 | eval time = 739.74 ms / 2 tokens ( 739.74 ms per token, 1.35 tokens per second) 15.30.085.696 I slot print_timing: id 1 | task 14185 | total time = 10290.24 ms / 1893 tokens 15.30.085.696 I slot print_timing: id 1 | task 14185 | graphs reused = 12478 15.30.085.697 I slot print_timing: id 1 | task 14185 | graph reallocs = 0 / 0 (same size) / (changed size) 15.30.087.024 I slot release: id 1 | task 14185 | stop processing: n_tokens = 1892, truncated = 0 15.30.087.325 I slot print_timing: id 2 | task 14186 | prompt eval time = 9550.49 ms / 1959 tokens ( 4.88 ms per token, 205.12 tokens per second) 15.30.087.329 I slot print_timing: id 2 | task 14186 | eval time = 741.25 ms / 2 tokens ( 741.25 ms per token, 1.35 tokens per second) 15.30.087.330 I slot print_timing: id 2 | task 14186 | total time = 10291.74 ms / 1961 tokens 15.30.087.331 I slot print_timing: id 2 | task 14186 | graphs reused = 12478 15.30.087.331 I slot print_timing: id 2 | task 14186 | graph reallocs = 0 / 0 (same size) / (changed size) 15.30.087.418 I slot release: id 2 | task 14186 | stop processing: n_tokens = 1960, truncated = 0 15.30.087.698 I slot print_timing: id 3 | task 14192 | prompt eval time = 1969.32 ms / 257 tokens ( 7.66 ms per token, 130.50 tokens per second) 15.30.087.703 I slot print_timing: id 3 | task 14192 | eval time = 741.50 ms / 2 tokens ( 741.50 ms per token, 1.35 tokens per second) 15.30.087.703 I slot print_timing: id 3 | task 14192 | total time = 2710.82 ms / 259 tokens 15.30.087.733 I slot print_timing: id 3 | task 14192 | graphs reused = 12478 15.30.087.736 I slot print_timing: id 3 | task 14192 | graph reallocs = 0 / 0 (same size) / (changed size) 15.30.087.813 I slot release: id 3 | task 14192 | stop processing: n_tokens = 1917, truncated = 0 15.30.137.536 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.877 15.30.137.596 I slot launch_slot_: id 1 | task 14198 | processing task, is_child = 0 15.30.137.731 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 155.185 MiB) 15.30.356.652 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 185.720 MiB) 15.30.356.682 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 155.759 MiB) 15.30.529.092 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.847 15.30.529.207 I slot launch_slot_: id 2 | task 14199 | processing task, is_child = 0 15.30.529.321 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.801 (> 0.100 thold), f_keep = 0.865 15.30.529.366 I slot launch_slot_: id 3 | task 14200 | processing task, is_child = 0 15.32.274.992 I slot print_timing: id 0 | task 14195 | prompt eval time = 791.18 ms / 336 tokens ( 2.35 ms per token, 424.68 tokens per second) 15.32.274.995 I slot print_timing: id 0 | task 14195 | eval time = 2137.46 ms / 2 tokens ( 2137.46 ms per token, 0.47 tokens per second) 15.32.274.995 I slot print_timing: id 0 | task 14195 | total time = 2928.64 ms / 338 tokens 15.32.274.996 I slot print_timing: id 0 | task 14195 | graphs reused = 12478 15.32.274.996 I slot print_timing: id 0 | task 14195 | graph reallocs = 0 / 0 (same size) / (changed size) 15.32.275.128 I slot release: id 0 | task 14195 | stop processing: n_tokens = 1997, truncated = 0 15.32.380.859 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.831 15.32.380.971 I slot launch_slot_: id 0 | task 14203 | processing task, is_child = 0 15.32.958.030 I slot print_timing: id 1 | task 14198 | prompt eval time = 1851.28 ms / 201 tokens ( 9.21 ms per token, 108.57 tokens per second) 15.32.958.035 I slot print_timing: id 1 | task 14198 | eval time = 577.37 ms / 2 tokens ( 577.37 ms per token, 1.73 tokens per second) 15.32.958.035 I slot print_timing: id 1 | task 14198 | total time = 2428.65 ms / 203 tokens 15.32.958.036 I slot print_timing: id 1 | task 14198 | graphs reused = 12478 15.32.958.036 I slot print_timing: id 1 | task 14198 | graph reallocs = 0 / 0 (same size) / (changed size) 15.32.958.163 I slot release: id 1 | task 14198 | stop processing: n_tokens = 1862, truncated = 0 15.32.958.279 I slot print_timing: id 2 | task 14199 | prompt eval time = 1846.26 ms / 169 tokens ( 10.92 ms per token, 91.54 tokens per second) 15.32.958.281 I slot print_timing: id 2 | task 14199 | eval time = 577.52 ms / 2 tokens ( 577.52 ms per token, 1.73 tokens per second) 15.32.958.281 I slot print_timing: id 2 | task 14199 | total time = 2423.78 ms / 171 tokens 15.32.958.282 I slot print_timing: id 2 | task 14199 | graphs reused = 12478 15.32.958.282 I slot print_timing: id 2 | task 14199 | graph reallocs = 0 / 0 (same size) / (changed size) 15.32.958.348 I slot release: id 2 | task 14199 | stop processing: n_tokens = 1830, truncated = 0 15.32.958.450 I slot print_timing: id 3 | task 14200 | prompt eval time = 1832.45 ms / 413 tokens ( 4.44 ms per token, 225.38 tokens per second) 15.32.958.457 I slot print_timing: id 3 | task 14200 | eval time = 577.60 ms / 2 tokens ( 577.60 ms per token, 1.73 tokens per second) 15.32.958.458 I slot print_timing: id 3 | task 14200 | total time = 2410.05 ms / 415 tokens 15.32.958.458 I slot print_timing: id 3 | task 14200 | graphs reused = 12478 15.32.958.459 I slot print_timing: id 3 | task 14200 | graph reallocs = 0 / 0 (same size) / (changed size) 15.32.960.153 I slot release: id 3 | task 14200 | stop processing: n_tokens = 2073, truncated = 0 15.33.004.396 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.891 15.33.004.465 I slot launch_slot_: id 1 | task 14206 | processing task, is_child = 0 15.33.004.595 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 145.256 MiB) 15.33.170.812 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.590 MiB) 15.33.170.839 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 147.650 MiB) 15.33.371.141 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.849 (> 0.100 thold), f_keep = 0.907 15.33.371.252 I slot launch_slot_: id 2 | task 14207 | processing task, is_child = 0 15.33.371.369 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.864 (> 0.100 thold), f_keep = 0.801 15.33.371.419 I slot launch_slot_: id 3 | task 14208 | processing task, is_child = 0 15.35.033.728 I slot print_timing: id 0 | task 14203 | prompt eval time = 623.41 ms / 206 tokens ( 3.03 ms per token, 330.44 tokens per second) 15.35.033.731 I slot print_timing: id 0 | task 14203 | eval time = 2029.33 ms / 2 tokens ( 2029.33 ms per token, 0.49 tokens per second) 15.35.033.731 I slot print_timing: id 0 | task 14203 | total time = 2652.74 ms / 208 tokens 15.35.033.731 I slot print_timing: id 0 | task 14203 | graphs reused = 12478 15.35.033.732 I slot print_timing: id 0 | task 14203 | graph reallocs = 0 / 0 (same size) / (changed size) 15.35.033.859 I slot release: id 0 | task 14203 | stop processing: n_tokens = 1866, truncated = 0 15.35.133.701 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.864 (> 0.100 thold), f_keep = 0.889 15.35.133.762 I slot launch_slot_: id 0 | task 14211 | processing task, is_child = 0 15.35.788.214 I slot print_timing: id 1 | task 14206 | prompt eval time = 1761.98 ms / 169 tokens ( 10.43 ms per token, 95.92 tokens per second) 15.35.788.217 I slot print_timing: id 1 | task 14206 | eval time = 654.80 ms / 2 tokens ( 654.80 ms per token, 1.53 tokens per second) 15.35.788.217 I slot print_timing: id 1 | task 14206 | total time = 2416.78 ms / 171 tokens 15.35.788.218 I slot print_timing: id 1 | task 14206 | graphs reused = 12478 15.35.788.218 I slot print_timing: id 1 | task 14206 | graph reallocs = 0 / 0 (same size) / (changed size) 15.35.788.316 I slot release: id 1 | task 14206 | stop processing: n_tokens = 1829, truncated = 0 15.35.788.474 I slot print_timing: id 2 | task 14207 | prompt eval time = 1760.72 ms / 295 tokens ( 5.97 ms per token, 167.54 tokens per second) 15.35.788.478 I slot print_timing: id 2 | task 14207 | eval time = 654.94 ms / 2 tokens ( 654.94 ms per token, 1.53 tokens per second) 15.35.788.478 I slot print_timing: id 2 | task 14207 | total time = 2415.66 ms / 297 tokens 15.35.788.482 I slot print_timing: id 2 | task 14207 | graphs reused = 12478 15.35.788.483 I slot print_timing: id 2 | task 14207 | graph reallocs = 0 / 0 (same size) / (changed size) 15.35.788.565 I slot release: id 2 | task 14207 | stop processing: n_tokens = 1956, truncated = 0 15.35.788.718 I slot print_timing: id 3 | task 14208 | prompt eval time = 1759.39 ms / 261 tokens ( 6.74 ms per token, 148.35 tokens per second) 15.35.788.720 I slot print_timing: id 3 | task 14208 | eval time = 655.02 ms / 2 tokens ( 655.02 ms per token, 1.53 tokens per second) 15.35.788.722 I slot print_timing: id 3 | task 14208 | total time = 2414.41 ms / 263 tokens 15.35.788.722 I slot print_timing: id 3 | task 14208 | graphs reused = 12478 15.35.788.723 I slot print_timing: id 3 | task 14208 | graph reallocs = 0 / 0 (same size) / (changed size) 15.35.789.214 I slot release: id 3 | task 14208 | stop processing: n_tokens = 1922, truncated = 0 15.35.832.453 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.849 15.35.832.543 I slot launch_slot_: id 2 | task 14214 | processing task, is_child = 0 15.35.832.684 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 174.889 MiB) 15.35.832.702 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 135.643 MiB) 15.36.014.829 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 135.739 MiB) 15.36.014.854 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.609 MiB) 15.36.166.192 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.843 (> 0.100 thold), f_keep = 0.864 15.36.166.294 I slot launch_slot_: id 3 | task 14215 | processing task, is_child = 0 15.36.166.407 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.907 15.36.166.451 I slot launch_slot_: id 1 | task 14216 | processing task, is_child = 0 15.38.066.130 I slot print_timing: id 0 | task 14211 | prompt eval time = 698.68 ms / 262 tokens ( 2.67 ms per token, 374.99 tokens per second) 15.38.066.133 I slot print_timing: id 0 | task 14211 | eval time = 2233.68 ms / 2 tokens ( 2233.68 ms per token, 0.45 tokens per second) 15.38.066.133 I slot print_timing: id 0 | task 14211 | total time = 2932.36 ms / 264 tokens 15.38.066.133 I slot print_timing: id 0 | task 14211 | graphs reused = 12478 15.38.066.134 I slot print_timing: id 0 | task 14211 | graph reallocs = 0 / 0 (same size) / (changed size) 15.38.067.511 I slot release: id 0 | task 14211 | stop processing: n_tokens = 1922, truncated = 0 15.38.167.558 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.819 (> 0.100 thold), f_keep = 0.863 15.38.167.637 I slot launch_slot_: id 0 | task 14219 | processing task, is_child = 0 15.38.943.075 I slot print_timing: id 1 | task 14216 | prompt eval time = 2000.82 ms / 358 tokens ( 5.59 ms per token, 178.93 tokens per second) 15.38.943.077 I slot print_timing: id 1 | task 14216 | eval time = 775.79 ms / 2 tokens ( 775.79 ms per token, 1.29 tokens per second) 15.38.943.078 I slot print_timing: id 1 | task 14216 | total time = 2776.61 ms / 360 tokens 15.38.943.078 I slot print_timing: id 1 | task 14216 | graphs reused = 12478 15.38.943.078 I slot print_timing: id 1 | task 14216 | graph reallocs = 0 / 0 (same size) / (changed size) 15.38.943.208 I slot release: id 1 | task 14216 | stop processing: n_tokens = 2018, truncated = 0 15.38.943.319 I slot print_timing: id 2 | task 14214 | prompt eval time = 1999.76 ms / 168 tokens ( 11.90 ms per token, 84.01 tokens per second) 15.38.943.324 I slot print_timing: id 2 | task 14214 | eval time = 775.86 ms / 2 tokens ( 775.86 ms per token, 1.29 tokens per second) 15.38.943.324 I slot print_timing: id 2 | task 14214 | total time = 2775.62 ms / 170 tokens 15.38.943.325 I slot print_timing: id 2 | task 14214 | graphs reused = 12478 15.38.943.325 I slot print_timing: id 2 | task 14214 | graph reallocs = 0 / 0 (same size) / (changed size) 15.38.943.398 I slot release: id 2 | task 14214 | stop processing: n_tokens = 1829, truncated = 0 15.38.943.505 I slot print_timing: id 3 | task 14215 | prompt eval time = 1998.63 ms / 308 tokens ( 6.49 ms per token, 154.11 tokens per second) 15.38.943.507 I slot print_timing: id 3 | task 14215 | eval time = 775.95 ms / 2 tokens ( 775.95 ms per token, 1.29 tokens per second) 15.38.943.507 I slot print_timing: id 3 | task 14215 | total time = 2774.58 ms / 310 tokens 15.38.943.508 I slot print_timing: id 3 | task 14215 | graphs reused = 12478 15.38.943.508 I slot print_timing: id 3 | task 14215 | graph reallocs = 0 / 0 (same size) / (changed size) 15.38.944.404 I slot release: id 3 | task 14215 | stop processing: n_tokens = 1969, truncated = 0 15.38.989.322 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.908 15.38.989.385 I slot launch_slot_: id 2 | task 14222 | processing task, is_child = 0 15.38.989.514 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 135.260 MiB) 15.38.989.530 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.868 MiB) 15.39.177.111 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 172.345 MiB) 15.39.232.023 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.822 15.39.232.146 I slot launch_slot_: id 1 | task 14223 | processing task, is_child = 0 15.39.232.267 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.843 15.39.232.316 I slot launch_slot_: id 3 | task 14224 | processing task, is_child = 0 15.40.892.250 I slot print_timing: id 0 | task 14219 | prompt eval time = 821.67 ms / 366 tokens ( 2.25 ms per token, 445.43 tokens per second) 15.40.892.252 I slot print_timing: id 0 | task 14219 | eval time = 1902.93 ms / 2 tokens ( 1902.93 ms per token, 0.53 tokens per second) 15.40.892.253 I slot print_timing: id 0 | task 14219 | total time = 2724.60 ms / 368 tokens 15.40.892.253 I slot print_timing: id 0 | task 14219 | graphs reused = 12478 15.40.892.254 I slot print_timing: id 0 | task 14219 | graph reallocs = 0 / 0 (same size) / (changed size) 15.40.894.290 I slot release: id 0 | task 14219 | stop processing: n_tokens = 2026, truncated = 0 15.40.988.855 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.819 15.40.988.954 I slot launch_slot_: id 0 | task 14227 | processing task, is_child = 0 15.41.406.794 I slot print_timing: id 1 | task 14223 | prompt eval time = 1756.15 ms / 194 tokens ( 9.05 ms per token, 110.47 tokens per second) 15.41.406.796 I slot print_timing: id 1 | task 14223 | eval time = 418.32 ms / 2 tokens ( 418.32 ms per token, 2.39 tokens per second) 15.41.406.802 I slot print_timing: id 1 | task 14223 | total time = 2174.46 ms / 196 tokens 15.41.406.802 I slot print_timing: id 1 | task 14223 | graphs reused = 12478 15.41.406.803 I slot print_timing: id 1 | task 14223 | graph reallocs = 0 / 0 (same size) / (changed size) 15.41.406.897 I slot release: id 1 | task 14223 | stop processing: n_tokens = 1854, truncated = 0 15.41.407.058 I slot print_timing: id 2 | task 14222 | prompt eval time = 1755.04 ms / 217 tokens ( 8.09 ms per token, 123.64 tokens per second) 15.41.407.061 I slot print_timing: id 2 | task 14222 | eval time = 418.43 ms / 2 tokens ( 418.43 ms per token, 2.39 tokens per second) 15.41.407.061 I slot print_timing: id 2 | task 14222 | total time = 2173.46 ms / 219 tokens 15.41.407.061 I slot print_timing: id 2 | task 14222 | graphs reused = 12478 15.41.407.062 I slot print_timing: id 2 | task 14222 | graph reallocs = 0 / 0 (same size) / (changed size) 15.41.407.152 I slot release: id 2 | task 14222 | stop processing: n_tokens = 1878, truncated = 0 15.41.407.322 I slot print_timing: id 3 | task 14224 | prompt eval time = 1754.04 ms / 234 tokens ( 7.50 ms per token, 133.41 tokens per second) 15.41.407.328 I slot print_timing: id 3 | task 14224 | eval time = 418.47 ms / 2 tokens ( 418.47 ms per token, 2.39 tokens per second) 15.41.407.328 I slot print_timing: id 3 | task 14224 | total time = 2172.51 ms / 236 tokens 15.41.407.328 I slot print_timing: id 3 | task 14224 | graphs reused = 12478 15.41.407.329 I slot print_timing: id 3 | task 14224 | graph reallocs = 0 / 0 (same size) / (changed size) 15.41.407.406 I slot release: id 3 | task 14224 | stop processing: n_tokens = 1894, truncated = 0 15.41.451.375 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.884 15.41.451.463 I slot launch_slot_: id 2 | task 14230 | processing task, is_child = 0 15.41.451.623 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 205.930 MiB) 15.41.546.149 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.554 MiB) 15.41.546.196 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 171.744 MiB) 15.41.670.783 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1854, t_last = 349950153892 15.41.671.014 I slot launch_slot_: id 1 | task 14231 | processing task, is_child = 0 15.41.671.119 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.876 15.41.671.166 I slot launch_slot_: id 3 | task 14232 | processing task, is_child = 0 15.43.290.605 I slot print_timing: id 0 | task 14227 | prompt eval time = 462.40 ms / 108 tokens ( 4.28 ms per token, 233.56 tokens per second) 15.43.290.608 I slot print_timing: id 0 | task 14227 | eval time = 1839.23 ms / 2 tokens ( 1839.23 ms per token, 0.54 tokens per second) 15.43.290.608 I slot print_timing: id 0 | task 14227 | total time = 2301.63 ms / 110 tokens 15.43.290.609 I slot print_timing: id 0 | task 14227 | graphs reused = 12478 15.43.290.609 I slot print_timing: id 0 | task 14227 | graph reallocs = 0 / 0 (same size) / (changed size) 15.43.290.705 I slot release: id 0 | task 14227 | stop processing: n_tokens = 1768, truncated = 0 15.43.870.336 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1768, t_last = 349952037701 15.43.870.468 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 156.196 MiB) 15.43.963.763 I slot launch_slot_: id 0 | task 14235 | processing task, is_child = 0 15.45.324.837 I slot print_timing: id 2 | task 14230 | prompt eval time = 2198.71 ms / 191 tokens ( 11.51 ms per token, 86.87 tokens per second) 15.45.324.839 I slot print_timing: id 2 | task 14230 | eval time = 1454.73 ms / 2 tokens ( 1454.73 ms per token, 0.69 tokens per second) 15.45.324.840 I slot print_timing: id 2 | task 14230 | total time = 3653.44 ms / 193 tokens 15.45.324.840 I slot print_timing: id 2 | task 14230 | graphs reused = 12478 15.45.324.844 I slot print_timing: id 2 | task 14230 | graph reallocs = 0 / 0 (same size) / (changed size) 15.45.324.944 I slot release: id 2 | task 14230 | stop processing: n_tokens = 1852, truncated = 0 15.45.325.231 I slot print_timing: id 3 | task 14232 | prompt eval time = 2197.74 ms / 152 tokens ( 14.46 ms per token, 69.16 tokens per second) 15.45.325.234 I slot print_timing: id 3 | task 14232 | eval time = 1454.90 ms / 2 tokens ( 1454.90 ms per token, 0.69 tokens per second) 15.45.325.235 I slot print_timing: id 3 | task 14232 | total time = 3652.64 ms / 154 tokens 15.45.325.235 I slot print_timing: id 3 | task 14232 | graphs reused = 12478 15.45.325.235 I slot print_timing: id 3 | task 14232 | graph reallocs = 0 / 0 (same size) / (changed size) 15.45.325.306 I slot release: id 3 | task 14232 | stop processing: n_tokens = 1812, truncated = 0 15.45.335.062 I slot print_timing: id 1 | task 14231 | prompt processing, n_tokens = 798, progress = 0.61, t = 3.65 s / 218.42 tokens per second 15.46.080.365 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1852, t_last = 349954071940 15.46.080.516 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 157.249 MiB) 15.46.098.013 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 210.964 MiB) 15.46.528.186 I slot launch_slot_: id 2 | task 14238 | processing task, is_child = 0 15.46.528.329 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.428 MiB) 15.46.565.737 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1812, t_last = 349954072301 15.46.565.930 I slot launch_slot_: id 3 | task 14239 | processing task, is_child = 0 15.46.565.953 I slot print_timing: id 1 | task 14231 | prompt processing, n_tokens = 1135, progress = 0.86, t = 4.41 s / 257.42 tokens per second 15.48.963.319 I slot print_timing: id 0 | task 14235 | prompt processing, n_tokens = 989, progress = 0.66, t = 5.00 s / 197.82 tokens per second 15.49.272.751 I slot print_timing: id 1 | task 14231 | prompt processing, n_tokens = 1310, progress = 1.00, t = 7.29 s / 179.65 tokens per second 15.50.671.698 I slot print_timing: id 0 | task 14235 | prompt processing, n_tokens = 1135, progress = 0.75, t = 6.71 s / 169.21 tokens per second 15.50.676.538 I slot print_timing: id 2 | task 14238 | prompt processing, n_tokens = 377, progress = 0.42, t = 4.10 s / 91.85 tokens per second 15.50.676.552 I slot print_timing: id 3 | task 14239 | prompt processing, n_tokens = 515, progress = 0.37, t = 4.10 s / 125.48 tokens per second 15.52.241.294 I slot print_timing: id 1 | task 14231 | prompt eval time = 9000.51 ms / 1314 tokens ( 6.85 ms per token, 145.99 tokens per second) 15.52.241.299 I slot print_timing: id 1 | task 14231 | eval time = 1569.59 ms / 2 tokens ( 1569.59 ms per token, 0.64 tokens per second) 15.52.241.300 I slot print_timing: id 1 | task 14231 | total time = 10570.11 ms / 1316 tokens 15.52.241.300 I slot print_timing: id 1 | task 14231 | graphs reused = 12478 15.52.241.319 I slot print_timing: id 1 | task 14231 | graph reallocs = 0 / 0 (same size) / (changed size) 15.52.242.484 I slot release: id 1 | task 14231 | stop processing: n_tokens = 1315, truncated = 0 15.52.242.513 I slot print_timing: id 0 | task 14235 | prompt processing, n_tokens = 1501, progress = 1.00, t = 8.28 s / 181.34 tokens per second 15.52.247.897 I slot print_timing: id 2 | task 14238 | prompt processing, n_tokens = 387, progress = 0.43, t = 5.67 s / 68.21 tokens per second 15.52.250.395 I slot print_timing: id 3 | task 14239 | prompt processing, n_tokens = 866, progress = 0.63, t = 5.67 s / 152.63 tokens per second 15.53.691.233 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1315, t_last = 349960989481 15.53.691.331 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 176.258 MiB) 15.53.712.459 I slot launch_slot_: id 1 | task 14244 | processing task, is_child = 0 15.53.712.646 I slot print_timing: id 2 | task 14238 | prompt processing, n_tokens = 766, progress = 0.85, t = 7.12 s / 107.53 tokens per second 15.53.713.830 I slot print_timing: id 3 | task 14239 | prompt processing, n_tokens = 1135, progress = 0.82, t = 7.12 s / 159.33 tokens per second 15.55.254.692 I slot print_timing: id 0 | task 14235 | prompt eval time = 9727.45 ms / 1505 tokens ( 6.46 ms per token, 154.72 tokens per second) 15.55.254.695 I slot print_timing: id 0 | task 14235 | eval time = 1563.46 ms / 2 tokens ( 1563.46 ms per token, 0.64 tokens per second) 15.55.254.696 I slot print_timing: id 0 | task 14235 | total time = 11290.91 ms / 1507 tokens 15.55.254.697 I slot print_timing: id 0 | task 14235 | graphs reused = 12478 15.55.254.697 I slot print_timing: id 0 | task 14235 | graph reallocs = 0 / 0 (same size) / (changed size) 15.55.254.791 I slot release: id 0 | task 14235 | stop processing: n_tokens = 1506, truncated = 0 15.55.256.760 I slot print_timing: id 2 | task 14238 | prompt processing, n_tokens = 899, progress = 1.00, t = 8.69 s / 103.48 tokens per second 15.55.259.590 I slot print_timing: id 3 | task 14239 | prompt processing, n_tokens = 1378, progress = 1.00, t = 8.69 s / 158.62 tokens per second 15.55.739.471 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1506, t_last = 349964001788 15.55.739.591 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 245.874 MiB) 15.55.772.356 I slot launch_slot_: id 0 | task 14247 | processing task, is_child = 0 15.57.052.718 I slot print_timing: id 2 | task 14238 | prompt eval time = 9172.11 ms / 903 tokens ( 10.16 ms per token, 98.45 tokens per second) 15.57.052.724 I slot print_timing: id 2 | task 14238 | eval time = 1313.46 ms / 2 tokens ( 1313.46 ms per token, 0.76 tokens per second) 15.57.052.724 I slot print_timing: id 2 | task 14238 | total time = 10485.57 ms / 905 tokens 15.57.052.725 I slot print_timing: id 2 | task 14238 | graphs reused = 12478 15.57.052.725 I slot print_timing: id 2 | task 14238 | graph reallocs = 0 / 0 (same size) / (changed size) 15.57.052.791 I slot release: id 2 | task 14238 | stop processing: n_tokens = 904, truncated = 0 15.57.052.976 I slot print_timing: id 3 | task 14239 | prompt eval time = 9172.11 ms / 1382 tokens ( 6.64 ms per token, 150.67 tokens per second) 15.57.052.982 I slot print_timing: id 3 | task 14239 | eval time = 1313.51 ms / 2 tokens ( 1313.51 ms per token, 0.76 tokens per second) 15.57.052.982 I slot print_timing: id 3 | task 14239 | total time = 10485.62 ms / 1384 tokens 15.57.052.983 I slot print_timing: id 3 | task 14239 | graphs reused = 12478 15.57.052.983 I slot print_timing: id 3 | task 14239 | graph reallocs = 0 / 0 (same size) / (changed size) 15.57.053.072 I slot release: id 3 | task 14239 | stop processing: n_tokens = 1383, truncated = 0 15.57.053.771 I slot print_timing: id 1 | task 14244 | prompt processing, n_tokens = 766, progress = 0.86, t = 3.34 s / 229.33 tokens per second 15.57.627.516 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.876 15.57.627.605 I slot launch_slot_: id 2 | task 14250 | processing task, is_child = 0 15.57.627.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.893 MiB) 15.57.665.667 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1383, t_last = 349965800069 15.57.665.878 I slot launch_slot_: id 3 | task 14251 | processing task, is_child = 0 15.57.666.709 I slot print_timing: id 1 | task 14244 | prompt processing, n_tokens = 887, progress = 1.00, t = 3.92 s / 226.56 tokens per second 15.59.370.631 I slot print_timing: id 0 | task 14247 | prompt processing, n_tokens = 766, progress = 0.87, t = 3.60 s / 212.89 tokens per second 16.00.233.774 I slot print_timing: id 1 | task 14244 | prompt eval time = 5658.15 ms / 891 tokens ( 6.35 ms per token, 157.47 tokens per second) 16.00.233.780 I slot print_timing: id 1 | task 14244 | eval time = 863.15 ms / 2 tokens ( 863.15 ms per token, 1.16 tokens per second) 16.00.233.780 I slot print_timing: id 1 | task 14244 | total time = 6521.30 ms / 893 tokens 16.00.233.781 I slot print_timing: id 1 | task 14244 | graphs reused = 12478 16.00.233.781 I slot print_timing: id 1 | task 14244 | graph reallocs = 0 / 0 (same size) / (changed size) 16.00.233.829 I slot release: id 1 | task 14244 | stop processing: n_tokens = 892, truncated = 0 16.00.233.953 I slot print_timing: id 0 | task 14247 | prompt processing, n_tokens = 877, progress = 1.00, t = 4.46 s / 196.58 tokens per second 16.01.040.889 I slot print_timing: id 2 | task 14250 | prompt eval time = 2554.81 ms / 72 tokens ( 35.48 ms per token, 28.18 tokens per second) 16.01.040.892 I slot print_timing: id 2 | task 14250 | eval time = 806.94 ms / 2 tokens ( 806.94 ms per token, 1.24 tokens per second) 16.01.040.892 I slot print_timing: id 2 | task 14250 | total time = 3361.75 ms / 74 tokens 16.01.040.893 I slot print_timing: id 2 | task 14250 | graphs reused = 12478 16.01.040.893 I slot print_timing: id 2 | task 14250 | graph reallocs = 0 / 0 (same size) / (changed size) 16.01.040.942 I slot release: id 2 | task 14250 | stop processing: n_tokens = 865, truncated = 0 16.01.040.951 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.887 16.01.041.043 I slot launch_slot_: id 1 | task 14255 | processing task, is_child = 0 16.01.041.122 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.087 MiB) 16.01.075.463 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.914 16.01.075.557 I slot launch_slot_: id 2 | task 14256 | processing task, is_child = 0 16.01.078.727 I slot print_timing: id 3 | task 14251 | prompt processing, n_tokens = 766, progress = 0.86, t = 3.36 s / 227.96 tokens per second 16.01.918.382 I slot print_timing: id 0 | task 14247 | prompt eval time = 5268.39 ms / 881 tokens ( 5.98 ms per token, 167.22 tokens per second) 16.01.918.388 I slot print_timing: id 0 | task 14247 | eval time = 877.62 ms / 2 tokens ( 877.62 ms per token, 1.14 tokens per second) 16.01.918.388 I slot print_timing: id 0 | task 14247 | total time = 6146.01 ms / 883 tokens 16.01.918.389 I slot print_timing: id 0 | task 14247 | graphs reused = 12478 16.01.918.395 I slot print_timing: id 0 | task 14247 | graph reallocs = 0 / 0 (same size) / (changed size) 16.01.918.442 I slot release: id 0 | task 14247 | stop processing: n_tokens = 882, truncated = 0 16.01.922.614 I slot print_timing: id 3 | task 14251 | prompt processing, n_tokens = 882, progress = 1.00, t = 4.24 s / 208.12 tokens per second 16.02.010.938 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 349970665437 16.02.011.020 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 246.093 MiB) 16.02.033.377 I slot launch_slot_: id 0 | task 14259 | processing task, is_child = 0 16.02.479.130 I slot print_timing: id 1 | task 14255 | prompt eval time = 935.08 ms / 83 tokens ( 11.27 ms per token, 88.76 tokens per second) 16.02.479.135 I slot print_timing: id 1 | task 14255 | eval time = 468.48 ms / 2 tokens ( 468.48 ms per token, 2.13 tokens per second) 16.02.479.136 I slot print_timing: id 1 | task 14255 | total time = 1403.56 ms / 85 tokens 16.02.479.136 I slot print_timing: id 1 | task 14255 | graphs reused = 12478 16.02.479.137 I slot print_timing: id 1 | task 14255 | graph reallocs = 0 / 0 (same size) / (changed size) 16.02.479.188 I slot release: id 1 | task 14255 | stop processing: n_tokens = 875, truncated = 0 16.02.479.292 I slot print_timing: id 2 | task 14256 | prompt eval time = 933.17 ms / 89 tokens ( 10.49 ms per token, 95.37 tokens per second) 16.02.479.294 I slot print_timing: id 2 | task 14256 | eval time = 468.54 ms / 2 tokens ( 468.54 ms per token, 2.13 tokens per second) 16.02.479.294 I slot print_timing: id 2 | task 14256 | total time = 1401.72 ms / 91 tokens 16.02.479.295 I slot print_timing: id 2 | task 14256 | graphs reused = 12478 16.02.479.295 I slot print_timing: id 2 | task 14256 | graph reallocs = 0 / 0 (same size) / (changed size) 16.02.479.322 I slot release: id 2 | task 14256 | stop processing: n_tokens = 881, truncated = 0 16.02.479.490 I slot print_timing: id 3 | task 14251 | prompt eval time = 4330.55 ms / 886 tokens ( 4.89 ms per token, 204.59 tokens per second) 16.02.479.495 I slot print_timing: id 3 | task 14251 | eval time = 468.56 ms / 2 tokens ( 468.56 ms per token, 2.13 tokens per second) 16.02.479.495 I slot print_timing: id 3 | task 14251 | total time = 4799.11 ms / 888 tokens 16.02.479.496 I slot print_timing: id 3 | task 14251 | graphs reused = 12478 16.02.479.496 I slot print_timing: id 3 | task 14251 | graph reallocs = 0 / 0 (same size) / (changed size) 16.02.479.523 I slot release: id 3 | task 14251 | stop processing: n_tokens = 887, truncated = 0 16.02.760.226 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 875, t_last = 349971226183 16.02.760.307 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.784 MiB) 16.03.493.972 I slot launch_slot_: id 1 | task 14263 | processing task, is_child = 0 16.03.494.077 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 245.970 MiB) 16.03.556.071 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 349971226317 16.03.556.242 I slot launch_slot_: id 2 | task 14264 | processing task, is_child = 0 16.03.556.311 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 349971226518 16.03.556.421 I slot launch_slot_: id 3 | task 14265 | processing task, is_child = 0 16.08.966.755 I slot print_timing: id 0 | task 14259 | prompt eval time = 4216.49 ms / 716 tokens ( 5.89 ms per token, 169.81 tokens per second) 16.08.966.758 I slot print_timing: id 0 | task 14259 | eval time = 2716.86 ms / 2 tokens ( 2716.86 ms per token, 0.37 tokens per second) 16.08.966.758 I slot print_timing: id 0 | task 14259 | total time = 6933.35 ms / 718 tokens 16.08.966.759 I slot print_timing: id 0 | task 14259 | graphs reused = 12478 16.08.966.759 I slot print_timing: id 0 | task 14259 | graph reallocs = 0 / 0 (same size) / (changed size) 16.08.966.812 I slot release: id 0 | task 14259 | stop processing: n_tokens = 717, truncated = 0 16.08.966.826 I slot print_timing: id 1 | task 14263 | prompt processing, n_tokens = 973, progress = 0.65, t = 5.40 s / 180.08 tokens per second 16.08.970.716 I slot print_timing: id 2 | task 14264 | prompt processing, n_tokens = 945, progress = 0.65, t = 5.40 s / 174.90 tokens per second 16.08.972.366 I slot print_timing: id 3 | task 14265 | prompt processing, n_tokens = 987, progress = 0.66, t = 5.40 s / 182.68 tokens per second 16.10.651.283 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 349977713807 16.10.651.377 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.196 MiB) 16.10.808.493 I slot launch_slot_: id 0 | task 14270 | processing task, is_child = 0 16.10.808.709 I slot print_timing: id 1 | task 14263 | prompt processing, n_tokens = 1265, progress = 0.85, t = 7.09 s / 178.47 tokens per second 16.10.811.187 I slot print_timing: id 2 | task 14264 | prompt processing, n_tokens = 1265, progress = 0.87, t = 7.09 s / 178.48 tokens per second 16.10.813.634 I slot print_timing: id 3 | task 14265 | prompt processing, n_tokens = 1265, progress = 0.84, t = 7.09 s / 178.48 tokens per second 16.13.161.430 I slot print_timing: id 1 | task 14263 | prompt processing, n_tokens = 1485, progress = 1.00, t = 9.36 s / 158.66 tokens per second 16.13.163.720 I slot print_timing: id 2 | task 14264 | prompt processing, n_tokens = 1457, progress = 1.00, t = 9.36 s / 155.67 tokens per second 16.13.165.201 I slot print_timing: id 3 | task 14265 | prompt processing, n_tokens = 1499, progress = 1.00, t = 9.36 s / 160.16 tokens per second 16.14.602.164 I slot print_timing: id 1 | task 14263 | prompt eval time = 10140.40 ms / 1489 tokens ( 6.81 ms per token, 146.84 tokens per second) 16.14.602.166 I slot print_timing: id 1 | task 14263 | eval time = 898.42 ms / 2 tokens ( 898.42 ms per token, 1.11 tokens per second) 16.14.602.166 I slot print_timing: id 1 | task 14263 | total time = 11038.82 ms / 1491 tokens 16.14.602.167 I slot print_timing: id 1 | task 14263 | graphs reused = 12478 16.14.602.167 I slot print_timing: id 1 | task 14263 | graph reallocs = 0 / 0 (same size) / (changed size) 16.14.604.408 I slot release: id 1 | task 14263 | stop processing: n_tokens = 1490, truncated = 0 16.14.604.691 I slot print_timing: id 2 | task 14264 | prompt eval time = 10140.38 ms / 1461 tokens ( 6.94 ms per token, 144.08 tokens per second) 16.14.604.693 I slot print_timing: id 2 | task 14264 | eval time = 900.85 ms / 2 tokens ( 900.85 ms per token, 1.11 tokens per second) 16.14.604.694 I slot print_timing: id 2 | task 14264 | total time = 11041.23 ms / 1463 tokens 16.14.604.694 I slot print_timing: id 2 | task 14264 | graphs reused = 12478 16.14.604.695 I slot print_timing: id 2 | task 14264 | graph reallocs = 0 / 0 (same size) / (changed size) 16.14.604.748 I slot release: id 2 | task 14264 | stop processing: n_tokens = 1462, truncated = 0 16.14.605.037 I slot print_timing: id 3 | task 14265 | prompt eval time = 10140.52 ms / 1503 tokens ( 6.75 ms per token, 148.22 tokens per second) 16.14.605.042 I slot print_timing: id 3 | task 14265 | eval time = 900.94 ms / 2 tokens ( 900.94 ms per token, 1.11 tokens per second) 16.14.605.043 I slot print_timing: id 3 | task 14265 | total time = 11041.47 ms / 1505 tokens 16.14.605.043 I slot print_timing: id 3 | task 14265 | graphs reused = 12478 16.14.605.043 I slot print_timing: id 3 | task 14265 | graph reallocs = 0 / 0 (same size) / (changed size) 16.14.605.137 I slot release: id 3 | task 14265 | stop processing: n_tokens = 1504, truncated = 0 16.14.605.157 I slot print_timing: id 0 | task 14270 | prompt processing, n_tokens = 989, progress = 0.66, t = 3.79 s / 260.71 tokens per second 16.14.620.219 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1490, t_last = 349983351405 16.14.620.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 169.461 MiB) 16.15.223.871 I slot launch_slot_: id 1 | task 14275 | processing task, is_child = 0 16.15.223.976 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 172.907 MiB) 16.15.288.746 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 175.492 MiB) 16.15.344.789 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1462, t_last = 349983351744 16.15.344.976 I slot launch_slot_: id 2 | task 14276 | processing task, is_child = 0 16.15.345.066 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.812 (> 0.100 thold), f_keep = 0.858 16.15.345.111 I slot launch_slot_: id 3 | task 14277 | processing task, is_child = 0 16.15.345.118 I slot print_timing: id 0 | task 14270 | prompt processing, n_tokens = 1265, progress = 0.84, t = 3.81 s / 331.87 tokens per second 16.16.539.790 I slot print_timing: id 0 | task 14270 | prompt processing, n_tokens = 1501, progress = 1.00, t = 5.73 s / 261.90 tokens per second 16.17.959.602 I slot print_timing: id 0 | task 14270 | prompt eval time = 6759.80 ms / 1505 tokens ( 4.49 ms per token, 222.64 tokens per second) 16.17.959.608 I slot print_timing: id 0 | task 14270 | eval time = 391.29 ms / 2 tokens ( 391.29 ms per token, 2.56 tokens per second) 16.17.959.608 I slot print_timing: id 0 | task 14270 | total time = 7151.09 ms / 1507 tokens 16.17.959.609 I slot print_timing: id 0 | task 14270 | graphs reused = 12478 16.17.959.609 I slot print_timing: id 0 | task 14270 | graph reallocs = 0 / 0 (same size) / (changed size) 16.17.959.706 I slot release: id 0 | task 14270 | stop processing: n_tokens = 1506, truncated = 0 16.17.959.803 I slot print_timing: id 3 | task 14277 | prompt eval time = 2221.80 ms / 298 tokens ( 7.46 ms per token, 134.13 tokens per second) 16.17.959.806 I slot print_timing: id 3 | task 14277 | eval time = 391.33 ms / 2 tokens ( 391.33 ms per token, 2.56 tokens per second) 16.17.959.806 I slot print_timing: id 3 | task 14277 | total time = 2613.14 ms / 300 tokens 16.17.959.806 I slot print_timing: id 3 | task 14277 | graphs reused = 12478 16.17.959.807 I slot print_timing: id 3 | task 14277 | graph reallocs = 0 / 0 (same size) / (changed size) 16.17.959.868 I slot release: id 3 | task 14277 | stop processing: n_tokens = 1589, truncated = 0 16.19.361.161 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1506, t_last = 349986706703 16.19.361.267 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 203.497 MiB) 16.19.518.453 I slot launch_slot_: id 0 | task 14282 | processing task, is_child = 0 16.19.518.623 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 204.755 MiB) 16.19.614.085 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1589, t_last = 349986706864 16.19.614.284 I slot launch_slot_: id 3 | task 14283 | processing task, is_child = 0 16.19.614.484 I slot print_timing: id 1 | task 14275 | prompt processing, n_tokens = 648, progress = 0.87, t = 4.01 s / 161.40 tokens per second 16.19.615.798 I slot print_timing: id 2 | task 14276 | prompt processing, n_tokens = 648, progress = 0.83, t = 4.01 s / 161.41 tokens per second 16.20.831.882 I slot print_timing: id 1 | task 14275 | prompt processing, n_tokens = 745, progress = 0.99, t = 5.45 s / 136.76 tokens per second 16.20.833.209 I slot print_timing: id 2 | task 14276 | prompt processing, n_tokens = 774, progress = 0.99, t = 5.45 s / 142.08 tokens per second 16.22.456.725 I slot print_timing: id 1 | task 14275 | prompt eval time = 6291.85 ms / 749 tokens ( 8.40 ms per token, 119.04 tokens per second) 16.22.456.730 I slot print_timing: id 1 | task 14275 | eval time = 818.56 ms / 2 tokens ( 818.56 ms per token, 1.22 tokens per second) 16.22.456.730 I slot print_timing: id 1 | task 14275 | total time = 7110.41 ms / 751 tokens 16.22.456.731 I slot print_timing: id 1 | task 14275 | graphs reused = 12478 16.22.456.731 I slot print_timing: id 1 | task 14275 | graph reallocs = 0 / 0 (same size) / (changed size) 16.22.457.706 I slot release: id 1 | task 14275 | stop processing: n_tokens = 750, truncated = 0 16.22.457.832 I slot print_timing: id 2 | task 14276 | prompt eval time = 6291.82 ms / 778 tokens ( 8.09 ms per token, 123.65 tokens per second) 16.22.457.834 I slot print_timing: id 2 | task 14276 | eval time = 819.52 ms / 2 tokens ( 819.52 ms per token, 1.22 tokens per second) 16.22.457.834 I slot print_timing: id 2 | task 14276 | total time = 7111.34 ms / 780 tokens 16.22.457.835 I slot print_timing: id 2 | task 14276 | graphs reused = 12478 16.22.457.835 I slot print_timing: id 2 | task 14276 | graph reallocs = 0 / 0 (same size) / (changed size) 16.22.457.864 I slot release: id 2 | task 14276 | stop processing: n_tokens = 779, truncated = 0 16.22.842.283 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 750, t_last = 349991204702 16.22.842.364 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 139.526 MiB) 16.22.842.394 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 140.388 MiB) 16.23.540.709 I slot launch_slot_: id 1 | task 14288 | processing task, is_child = 0 16.23.540.788 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.600 MiB) 16.23.564.457 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 779, t_last = 349991204859 16.23.564.607 I slot launch_slot_: id 2 | task 14289 | processing task, is_child = 0 16.23.564.616 I slot print_timing: id 0 | task 14282 | prompt processing, n_tokens = 739, progress = 0.99, t = 3.23 s / 228.94 tokens per second 16.23.571.328 I slot print_timing: id 3 | task 14283 | prompt processing, n_tokens = 628, progress = 0.82, t = 3.22 s / 195.16 tokens per second 16.24.520.029 I slot print_timing: id 3 | task 14283 | prompt processing, n_tokens = 759, progress = 0.99, t = 4.89 s / 155.07 tokens per second 16.25.243.774 I slot print_timing: id 0 | task 14282 | prompt eval time = 4904.66 ms / 743 tokens ( 6.60 ms per token, 151.49 tokens per second) 16.25.243.778 I slot print_timing: id 0 | task 14282 | eval time = 724.81 ms / 2 tokens ( 724.81 ms per token, 1.38 tokens per second) 16.25.243.779 I slot print_timing: id 0 | task 14282 | total time = 5629.48 ms / 745 tokens 16.25.243.779 I slot print_timing: id 0 | task 14282 | graphs reused = 12478 16.25.243.786 I slot print_timing: id 0 | task 14282 | graph reallocs = 0 / 0 (same size) / (changed size) 16.25.243.838 I slot release: id 0 | task 14282 | stop processing: n_tokens = 744, truncated = 0 16.26.202.504 I slot print_timing: id 3 | task 14283 | prompt eval time = 5619.66 ms / 763 tokens ( 7.37 ms per token, 135.77 tokens per second) 16.26.202.506 I slot print_timing: id 3 | task 14283 | eval time = 958.49 ms / 2 tokens ( 958.49 ms per token, 1.04 tokens per second) 16.26.202.507 I slot print_timing: id 3 | task 14283 | total time = 6578.15 ms / 765 tokens 16.26.202.507 I slot print_timing: id 3 | task 14283 | graphs reused = 12478 16.26.202.507 I slot print_timing: id 3 | task 14283 | graph reallocs = 0 / 0 (same size) / (changed size) 16.26.202.548 I slot release: id 3 | task 14283 | stop processing: n_tokens = 764, truncated = 0 16.26.202.555 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 744, t_last = 349993990833 16.26.202.628 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 174.273 MiB) 16.26.245.298 I slot launch_slot_: id 0 | task 14293 | processing task, is_child = 0 16.26.245.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 175.080 MiB) 16.26.285.087 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 764, t_last = 349994949543 16.26.285.234 I slot launch_slot_: id 3 | task 14294 | processing task, is_child = 0 16.28.033.693 I slot print_timing: id 1 | task 14288 | prompt processing, n_tokens = 675, progress = 0.99, t = 3.92 s / 172.26 tokens per second 16.28.035.811 I slot print_timing: id 2 | task 14289 | prompt processing, n_tokens = 628, progress = 0.80, t = 3.92 s / 160.27 tokens per second 16.28.788.257 I slot print_timing: id 2 | task 14289 | prompt processing, n_tokens = 779, progress = 0.99, t = 5.22 s / 149.34 tokens per second 16.30.295.343 I slot print_timing: id 1 | task 14288 | prompt eval time = 5216.68 ms / 679 tokens ( 7.68 ms per token, 130.16 tokens per second) 16.30.295.349 I slot print_timing: id 1 | task 14288 | eval time = 1507.53 ms / 2 tokens ( 1507.53 ms per token, 0.66 tokens per second) 16.30.295.349 I slot print_timing: id 1 | task 14288 | total time = 6724.21 ms / 681 tokens 16.30.295.350 I slot print_timing: id 1 | task 14288 | graphs reused = 12478 16.30.295.350 I slot print_timing: id 1 | task 14288 | graph reallocs = 0 / 0 (same size) / (changed size) 16.30.295.436 I slot release: id 1 | task 14288 | stop processing: n_tokens = 680, truncated = 0 16.30.295.562 I slot print_timing: id 0 | task 14293 | prompt processing, n_tokens = 544, progress = 0.83, t = 4.01 s / 135.66 tokens per second 16.30.304.599 I slot print_timing: id 3 | task 14294 | prompt processing, n_tokens = 495, progress = 0.82, t = 4.01 s / 123.50 tokens per second 16.31.075.256 I slot print_timing: id 2 | task 14289 | prompt eval time = 6724.32 ms / 783 tokens ( 8.59 ms per token, 116.44 tokens per second) 16.31.075.258 I slot print_timing: id 2 | task 14289 | eval time = 779.69 ms / 2 tokens ( 779.69 ms per token, 1.28 tokens per second) 16.31.075.258 I slot print_timing: id 2 | task 14289 | total time = 7504.02 ms / 785 tokens 16.31.075.259 I slot print_timing: id 2 | task 14289 | graphs reused = 12478 16.31.075.259 I slot print_timing: id 2 | task 14289 | graph reallocs = 0 / 0 (same size) / (changed size) 16.31.075.305 I slot release: id 2 | task 14289 | stop processing: n_tokens = 784, truncated = 0 16.31.075.313 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 680, t_last = 349999042432 16.31.092.535 I slot launch_slot_: id 1 | task 14299 | processing task, is_child = 0 16.31.092.608 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 178.253 MiB) 16.31.133.001 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 784, t_last = 349999822300 16.31.133.140 I slot launch_slot_: id 2 | task 14300 | processing task, is_child = 0 16.31.133.148 I slot print_timing: id 0 | task 14293 | prompt processing, n_tokens = 648, progress = 0.99, t = 4.79 s / 135.28 tokens per second 16.31.148.143 I slot print_timing: id 3 | task 14294 | prompt processing, n_tokens = 599, progress = 0.99, t = 4.79 s / 125.10 tokens per second 16.31.995.523 I slot print_timing: id 0 | task 14293 | prompt eval time = 5452.22 ms / 652 tokens ( 8.36 ms per token, 119.58 tokens per second) 16.31.995.526 I slot print_timing: id 0 | task 14293 | eval time = 258.06 ms / 2 tokens ( 258.06 ms per token, 3.88 tokens per second) 16.31.995.526 I slot print_timing: id 0 | task 14293 | total time = 5710.28 ms / 654 tokens 16.31.995.527 I slot print_timing: id 0 | task 14293 | graphs reused = 12478 16.31.995.527 I slot print_timing: id 0 | task 14293 | graph reallocs = 0 / 0 (same size) / (changed size) 16.31.995.585 I slot release: id 0 | task 14293 | stop processing: n_tokens = 653, truncated = 0 16.31.995.675 I slot print_timing: id 3 | task 14294 | prompt eval time = 5450.44 ms / 603 tokens ( 9.04 ms per token, 110.63 tokens per second) 16.31.995.678 I slot print_timing: id 3 | task 14294 | eval time = 258.07 ms / 2 tokens ( 258.07 ms per token, 3.87 tokens per second) 16.31.995.678 I slot print_timing: id 3 | task 14294 | total time = 5708.51 ms / 605 tokens 16.31.995.678 I slot print_timing: id 3 | task 14294 | graphs reused = 12478 16.31.995.679 I slot print_timing: id 3 | task 14294 | graph reallocs = 0 / 0 (same size) / (changed size) 16.31.995.732 I slot release: id 3 | task 14294 | stop processing: n_tokens = 604, truncated = 0 16.34.160.576 I slot print_timing: id 1 | task 14299 | prompt eval time = 2980.59 ms / 625 tokens ( 4.77 ms per token, 209.69 tokens per second) 16.34.160.581 I slot print_timing: id 1 | task 14299 | eval time = 32.06 ms / 2 tokens ( 32.06 ms per token, 31.19 tokens per second) 16.34.160.581 I slot print_timing: id 1 | task 14299 | total time = 3012.65 ms / 627 tokens 16.34.160.582 I slot print_timing: id 1 | task 14299 | graphs reused = 12478 16.34.160.582 I slot print_timing: id 1 | task 14299 | graph reallocs = 0 / 0 (same size) / (changed size) 16.34.160.617 I slot release: id 1 | task 14299 | stop processing: n_tokens = 626, truncated = 0 16.34.160.702 I slot print_timing: id 2 | task 14300 | prompt eval time = 2980.60 ms / 591 tokens ( 5.04 ms per token, 198.28 tokens per second) 16.34.160.707 I slot print_timing: id 2 | task 14300 | eval time = 32.06 ms / 2 tokens ( 32.06 ms per token, 31.19 tokens per second) 16.34.160.707 I slot print_timing: id 2 | task 14300 | total time = 3012.66 ms / 593 tokens 16.34.160.708 I slot print_timing: id 2 | task 14300 | graphs reused = 12478 16.34.160.708 I slot print_timing: id 2 | task 14300 | graph reallocs = 0 / 0 (same size) / (changed size) 16.34.160.726 I slot release: id 2 | task 14300 | stop processing: n_tokens = 592, truncated = 0 16.38.110.474 I srv operator(): operator(): cleaning up before exit...